Initial import of upstream sources

BUG=30471686

Change-Id: I1270bfb2ee8f7f43683104e92f131dd42222ffd9

166 files changed, 58059 insertions, 0 deletions

diff --git a/Init.s b/Init.s
new file mode 100644
index 0000000..962996b
--- /dev/null
+++ b/Init.s
@@ -0,0 +1,259 @@
+;==================================================================
+; Copyright ARM Ltd 2005. All rights reserved.
+;
+; Cortex-A8 Dhrystone example - Startup Code
+;==================================================================
+
+        PRESERVE8
+        AREA   CORTEXA8, CODE, READONLY
+
+        ENTRY
+
+; Standard definitions of mode bits and interrupt (I & F) flags in PSRs
+
+Mode_USR        EQU     0x10
+Mode_FIQ        EQU     0x11
+Mode_IRQ        EQU     0x12
+Mode_SVC        EQU     0x13
+Mode_ABT        EQU     0x17
+Mode_UNDEF      EQU     0x1B
+Mode_SYS        EQU     0x1F
+
+I_Bit           EQU     0x80 ; when I bit is set, IRQ is disabled
+F_Bit           EQU     0x40 ; when F bit is set, FIQ is disabled
+
+;==================================================================
+; Disable Cortex-A8 MMU if enabled
+;==================================================================
+
+        EXPORT Start
+
+Start
+
+        MRC     p15, 0, r0, c1, c0, 0       ; Read CP15 Control Register into r0
+        TST     r0, #0x1                    ; Is the MMU enabled?
+        BICNE   r0, r0, #0x1                ; Clear bit 0
+        MCRNE   p15, 0, r0, c1, c0, 0       ; Write value back
+
+;==================================================================
+; Initialise Supervisor Mode Stack
+; Note stack must be 8 byte aligned.
+;==================================================================
+
+        IMPORT  ||Image$$STACK$$ZI$$Limit|| ; Linker symbol from scatter file
+        LDR     SP, =||Image$$STACK$$ZI$$Limit||
+
+;==================================================================
+; TLB maintenance, Invalidate Data and Instruction TLB's
+;==================================================================
+
+        MOV    r0,#0
+        MCR    p15, 0, r0, c8, c7, 0 ; Cortex-A8 I-TLB and D-TLB invalidation
+
+;==================================================================
+; Cache Invalidation code for Cortex-A8
+;==================================================================
+
+        ; Invalidate L1 Instruction Cache
+
+        MRC p15, 1, r0, c0, c0, 1   ; Read CLIDR
+        TST r0, #0x3                ; Harvard Cache?
+        MOV r0, #0
+        MCRNE p15, 0, r0, c7, c5, 0 ; Invalidate Instruction Cache
+
+        ; Invalidate Data/Unified Caches
+
+        MRC p15, 1, r0, c0, c0, 1   ; Read CLIDR
+        ANDS r3, r0, #&7000000
+        MOV r3, r3, LSR #23         ; Total cache levels << 1
+        BEQ Finished
+
+        MOV r10, #0                 ; R10 holds current cache level << 1
+Loop1   ADD r2, r10, r10, LSR #1    ; R2 holds cache "Set" position
+        MOV r1, r0, LSR r2          ; Bottom 3 bits are the Cache-type for this level
+        AND r1, R1, #7              ; Get those 3 bits alone
+        CMP r1, #2
+        BLT Skip                    ; No cache or only instruction cache at this level
+
+        MCR p15, 2, r10, c0, c0, 0  ; Write the Cache Size selection register
+        MOV r1, #0
+        MCR p15, 0, r1, c7, c5, 4   ; PrefetchFlush to sync the change to the CacheSizeID reg
+        MRC p15, 1, r1, c0, c0, 0   ; Reads current Cache Size ID register
+        AND r2, r1, #&7             ; Extract the line length field
+        ADD r2, r2, #4              ; Add 4 for the line length offset (log2 16 bytes)
+        LDR r4, =0x3FF
+        ANDS r4, r4, r1, LSR #3     ; R4 is the max number on the way size (right aligned)
+        CLZ r5, r4                  ; R5 is the bit position of the way size increment
+        LDR r7, =0x00007FFF
+        ANDS r7, r7, r1, LSR #13    ; R7 is the max number of the index size (right aligned)
+
+Loop2   MOV r9, r4                  ; R9 working copy of the max way size (right aligned)
+
+Loop3   ORR r11, r10, r9, LSL r5    ; Factor in the Way number and cache number into R11
+        ORR r11, r11, r7, LSL r2    ; Factor in the Set number
+        MCR p15, 0, r11, c7, c14, 2 ; Clean and Invalidate by set/way
+        SUBS r9, r9, #1             ; Decrement the Way number
+        BGE Loop3
+        SUBS r7, r7, #1             ; Decrement the Set number
+        BGE Loop2
+Skip    ADD r10, r10, #2            ; increment the cache number
+        CMP r3, r10
+        BGT Loop1
+
+Finished
+
+
+;===================================================================
+; Cortex-A8 MMU Configuration
+; Set translation table base
+;===================================================================
+
+
+        IMPORT ||Image$$TTB$$ZI$$Base||  ; from scatter file.;
+
+        ; Cortex-A8 supports two translation tables
+        ; Configure translation table base (TTB) control register cp15,c2
+        ; to a value of all zeros, indicates we are using TTB register 0.
+
+        MOV     r0,#0x0
+        MCR     p15, 0, r0, c2, c0, 2
+
+        ; write the address of our page table base to TTB register 0.;
+        ; We are setting to outer-noncachable [4:3] is zero
+
+        LDR     r0,=||Image$$TTB$$ZI$$Base||
+        MCR     p15, 0, r0, c2, c0, 0
+
+
+;===================================================================
+; Cortex-A8 PAGE TABLE generation, using standard Arch v6 tables
+;
+; AP[11:10]   - Access Permissions = b11, Read/Write Access
+; Domain[8:5] - Domain = b1111, Domain 15
+; Type[1:0]   - Descriptor Type = b10, 1Mb descriptors
+;
+; TEX  C  B
+; 000  0  0  Strongly Ordered
+; 001  1  1  Outer and inner write back, write allocate Normal
+;===================================================================
+
+        LDR     r1,=0xfff                   ; loop counter
+        LDR     r2,=2_00000000000000000000110111100010
+
+        ; r0 contains the address of the translation table base
+        ; r1 is loop counter
+        ; r2 is level1 descriptor (bits 19:0)
+
+        ; use loop counter to create 4096 individual table entries
+        ; this writes from address 0x7FFC down to 0x4000 in word steps (4bytes).
+
+init_ttb_1
+
+        ORR     r3, r2, r1, LSL#20          ; r3 now contains full level1 descriptor to write
+        STR     r3, [r0, r1, LSL#2]         ; str table entry at TTB base + loopcount*4
+        SUBS    r1, r1, #1                  ; decrement loop counter
+        BPL     init_ttb_1
+
+        ; In this example we will change the cacheable attribute in the first descriptor.
+        ; Virtual memory from 0 to 1MB will be cacheable (write back mode).
+        ; TEX[14:12]=001 and CB[3:2]= 11, Outer and inner write back, write allocate.
+
+        ORR     r3,r3,#2_0000000001100      ; Set CB bits
+        ORR     r3,r3,#2_1000000000000      ; Set TEX bits
+        STR     r3,[r0]
+
+	ADD r2, r3, #0x100000               ; alter r3 to have correct base address for second descriptor (flat mapping)
+	STR r2, [r0, #4]                    ; store the new descriptor at r0 + 4 (overwrite second section descriptor)
+
+	ADD r2, r3, #0x200000               ; alter r3 to have correct base address for 3 descriptor (flat mapping)
+	STR r2, [r0, #8]                    ; store the new descriptor at r0 + 4 (overwrite second section descriptor)
+
+	ADD r2, r3, #0x300000               ; alter r3 to have correct base address for 4 descriptor (flat mapping)
+	STR r2, [r0, #0xc]                    ; store the new descriptor at r0 + 4 (overwrite second section descriptor)
+
+	ADD r2, r3, #0x400000               ; alter r3 to have correct base address for 5 descriptor (flat mapping)
+	STR r2, [r0, #0x10]                    ; store the new descriptor at r0 + 4 (overwrite second section descriptor)
+
+	ADD r2, r3, #0x500000               ; alter r3 to have correct base address for 6 descriptor (flat mapping)
+	STR r2, [r0, #0x14]                    ; store the new descriptor at r0 + 4 (overwrite second section descriptor)
+
+	ADD r2, r3, #0x600000               ; alter r3 to have correct base address for 7 descriptor (flat mapping)
+	STR r2, [r0, #0x18]                    ; store the new descriptor at r0 + 4 (overwrite second section descriptor)
+
+	ADD r2, r3, #0x700000               ; alter r3 to have correct base address for 8 descriptor (flat mapping)
+	STR r2, [r0, #0x1c]                    ; store the new descriptor at r0 + 4 (overwrite second section descriptor)
+
+	ADD r2, r3, #0x800000               ; alter r3 to have correct base address for 9 descriptor (flat mapping)
+	STR r2, [r0, #0x20]                    ; store the new descriptor at r0 + 4 (overwrite second section descriptor)
+
+	ADD r2, r3, #0x900000               ; alter r3 to have correct base address for 10 descriptor (flat mapping)
+	STR r2, [r0, #0x24]                    ; store the new descriptor at r0 + 4 (overwrite second section descriptor)
+
+	ADD r2, r3, #0xa00000               ; alter r3 to have correct base address for 11 descriptor (flat mapping)
+	STR r2, [r0, #0x28]                    ; store the new descriptor at r0 + 4 (overwrite second section descriptor)
+
+	ADD r2, r3, #0xb00000               ; alter r3 to have correct base address for 12 descriptor (flat mapping)
+	STR r2, [r0, #0x2c]                    ; store the new descriptor at r0 + 4 (overwrite second section descriptor)
+
+	ADD r2, r3, #0xc00000               ; alter r3 to have correct base address for 13 descriptor (flat mapping)
+	STR r2, [r0, #0x30]                    ; store the new descriptor at r0 + 4 (overwrite second section descriptor)
+
+;===================================================================
+; Setup domain control register - Enable all domains to client mode
+;===================================================================
+
+        MRC     p15, 0, r0, c3, c0, 0     ; Read Domain Access Control Register
+        LDR     r0, =0x55555555           ; Initialize every domain entry to b01 (client)
+        MCR     p15, 0, r0, c3, c0, 0     ; Write Domain Access Control Register
+
+;===================================================================
+; Setup L2 Cache - L2 Cache Auxiliary Control
+;===================================================================
+
+        MOV     r0, #0
+        ;MCR     p15, 1, r0, c9, c0, 2      ; Write L2 Auxilary Control Register
+
+;==================================================================
+; Enable access to NEON/VFP by enabling access to Coprocessors 10 and 11.
+; Enables Full Access i.e. in both priv and non priv modes
+;==================================================================
+
+        MRC     p15, 0, r0, c1, c0, 2      ; read CP access register
+        ORR     r0, r0, #(0x3  <<20)       ; enable access CP 10
+        ORR     r0, r0, #(0x3  <<22)       ; enable access CP 11
+        MCR     p15, 0, r0, c1, c0, 2      ; write CP access register back
+
+;==================================================================
+; Switch on the VFP and Neon Hardware
+;=================================================================
+
+        MOV     r0, #0                      ; Set up a register
+        ORR     r0, r0, #(0x1 << 30)
+        FMXR    FPEXC, r0                   ; Write FPEXC register, EN bit set.
+
+;===================================================================
+; Enable MMU and Branch to __main
+;===================================================================
+
+        IMPORT  __main                      ; before MMU enabled import label to __main
+        LDR     r12,=__main                 ; save this in register for possible long jump
+
+
+        MRC     p15, 0, r0, c1, c0, 0       ; read CP15 register 1 into r0
+        ORR     r0, r0, #0x1                ; enable MMU before scatter loading
+        MCR     p15, 0, r0, c1, c0, 0       ; write CP15 register 1
+
+
+; Now the MMU is enabled, virtual to physical address translations will occur.
+; This will affect the next instruction fetches.
+;
+; The two instructions currently in the ARM pipeline will have been fetched
+; before the MMU was enabled. This property is useful because the next two
+; instructions are safe even if new instruction fetches fail. If this routine
+; was mapped out of the new virtual memory map, the branch to __main would
+; still succeed.
+
+        BX      r12                 ; branch to __main  C library entry point
+
+        END                         ; mark the end of this file
+
diff --git a/InitCache.s b/InitCache.s
new file mode 100644
index 0000000..250652a
--- /dev/null
+++ b/InitCache.s
@@ -0,0 +1,52 @@
+; Copyright ARM Ltd 2005. All rights reserved.
+
+;==================================================================
+; This code provides basic global enable for a Cortex-A8 cache
+; and program flow prediction
+; This code must be run from a privileged mode
+;==================================================================
+
+        AREA   CORTEXA8CACHE, CODE, READONLY
+        EXPORT core_init
+
+core_init
+
+;==================================================================
+; Global Enable for Cortex-A8 Instruction and Data Caching
+;==================================================================
+
+        MRC     p15, 0, r0, c1, c0, 0       ; read CP15 register 1 into r0
+        ORR     r0, r0, #(0x1  <<12)        ; enable I Cache
+	;BIC   r0, r0, #(0x1  <<12)         ; Clear bit 0
+        ORR     r0, r0, #(0x1  <<2)         ; enable D Cache
+	;BIC   r0, r0, #(0x1  << 2)         ; Clear bit 0
+	ORR     r0, r0, #0x1                ; enable MMU
+        MCR     p15, 0, r0, c1, c0, 0       ; write CP15 register 1
+
+;==================================================================
+; Enable Cortex-A8 Level2 Unified Cache
+;==================================================================
+
+        MRC p15, 0, r0, c1, c0, 1           ; Read Auxiliary Control Register
+        ORR r0, r0, #2                      ; L2EN bit, enable L2 cache
+	;BIC   r0, r0, #(0x1  << 1)         ; L2EN bit, disable L2 cache
+	;ORR     r0, r0, #(0x1  << 4)        ;Enables speculative accesses on AXI
+	ORR     r0, r0, #(0x1  << 4)        ;Enables speculative accesses on AXI
+	ORR     r0, r0, #(0x1  << 5)        ;Enables caching NEON data within the L1 data cache
+        MCR p15, 0, r0, c1, c0, 1           ; Write Auxiliary Control Register
+
+;==================================================================
+; Cortex-A8 program flow prediction
+;==================================================================
+
+        MRC     p15, 0, r0, c1, c0, 0       ; read CP15 register 1 into r0
+        ORR     r0, r0, #(0x1  <<11)        ; Enable all forms of branch prediction
+	;BIC   	r0, r0, #(0x1  << 11)	    ; Disable all forms of branch prediction
+        MCR     p15, 0, r0, c1, c0, 0       ; write CP15 register 1
+
+;==================================================================
+
+        BX    lr
+
+        END                                 ; mark the end of this file
+
diff --git a/LICENSE b/LICENSE
new file mode 100644
index 0000000..e5b6e99
--- /dev/null
+++ b/LICENSE
@@ -0,0 +1,10 @@
+
+License:
+--------
+All files are covered by the MIT license, except for:
+retarget.c
+Init.s
+InitCache.s
+scatter.scat
+which are covered by ARM's EULA regarding "EXAMPLE CODE", as described
+in license.html.
diff --git a/Makefile b/Makefile
new file mode 100644
index 0000000..6f57790
--- /dev/null
+++ b/Makefile
@@ -0,0 +1,166 @@
+# Copyright (c) 2009, 2010, 2011 STMicroelectronics
+# Written by Christophe Lyon
+
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+# THE SOFTWARE.
+
+CPU=cortex-a9
+# ARM RVCT
+CC.rvct := armcc
+CFLAGS.rvct = -g --cpu=$(CPU) --fp16_format=ieee -Ono_special_regs_postregalloc -I.
+LD.rvct := armlink
+LDFLAGS.rvct := --cpu=$(CPU) --entry 0x2000
+
+# GCC/ARM cross compiler
+CC.gccarm := arm-none-eabi-gcc
+CFLAGS.gccarm := -g -Wall -mcpu=$(CPU) -mfloat-abi=softfp -mfpu=neon -Wno-unused-variable -Wno-unused-function -ffast-math
+#LD.gccarm := $(LD.rvct)
+#LDFLAGS.gccarm := $(LDFLAGS.rvct)
+LD.gccarm := $(CC.gccarm)
+LDFLAGS.gccarm := $(CFLAGS.gccarm) -Tmop500-pm.ld
+
+# List of validated intrinsics
+REFNAMES = vld1 vadd vld1_lane vld1_dup vdup vget_high vget_low		\
+	   vqdmlal_lane vqdmlsl_lane vext vshrn_n vset_lane vget_lane	\
+	   vqsub vqdmulh_lane vqdmull vqdmlal vqdmlsl vceq vcge vcle	\
+	   vcgt vclt vbsl vshl vldX vdup_lane vrshrn_n vqdmull_lane	\
+	   vst1_lane vqshl vqshl_n vqrshrn_n vsub vqadd vabs vqabs	\
+	   vcombine vmax vmin vneg vqneg vmlal vmlal_lane vmlsl		\
+	   vmlsl_lane vmovl vmovn vmull vmull_lane vrev vrshl vshl_n	\
+	   vshr_n vsra_n vtrn vuzp vzip vreinterpret vqdmulh vqrdmulh	\
+	   vqrdmulh_lane vqrshl vaba vabal vabd vabdl vand vorr vorn	\
+	   veor vbic vcreate vldX_lane vldX_dup vmla vmls vmul		\
+	   vmul_lane vmul_n vmull_n vqdmulh_n vqdmull_n vqrdmulh_n	\
+	   vmla_lane vmls_lane vmla_n vmls_n vmlal_n vmlsl_n vqdmlal_n	\
+	   vqdmlsl_n vsri_n vsli_n vtst vaddhn vraddhn vaddl vaddw	\
+	   vhadd vrhadd vhsub vsubl vsubw vsubhn vrsubhn vmvn vqmovn	\
+	   vqmovun vrshr_n vrsra_n vshll_n vpaddl vpadd vpadal		\
+	   vqshlu_n vclz vcls vcnt vqshrn_n vpmax vpmin vqshrun_n	\
+	   vqrshrun_n vstX_lane vtbX vrecpe vrsqrte vcage vcagt vcale	\
+	   vcalt vrecps vrsqrts vcvt
+REFLIST = $(addprefix ref_, $(REFNAMES))
+
+REFNAMES_INT = integer dsp dspfns
+REFLIST_INT = $(addprefix ref_, $(REFNAMES_INT))
+
+all: ref-rvct.qemu
+
+check: check-rvct check-gccarm check-gccarm-rvct
+
+# Building reference files with RVCT
+REFOBJS.rvct = $(addsuffix .rvct.o, $(REFLIST) $(REFLIST_INT))
+REFRVCT=stm-arm-neon.refrvct
+ref-rvct: $(REFRVCT)
+ref-rvct.qemu: $(REFRVCT).qemu
+
+check-rvct: $(REFRVCT)
+	diff $(REFRVCT) ref-rvct-all.txt
+
+$(REFRVCT): compute_ref.axf
+	rvdebug -stdiolog=stdio.log -jou=journal.log -log=log.log -nologo -cmd -init @coretile.core.cpu0@RTSM -inc armscript.inc -exec $^
+
+$(REFRVCT).qemu: compute_ref.axf
+	qemu-system-arm -cpu $(CPU) -semihosting -nographic -kernel $^
+# Avoid rebuilding compute_ref.axf if already present, for users who
+# don't have rvct
+.PRECIOUS .INTERMEDIATE: compute_ref.rvct.o retarget.rvct.o	\
+	InitCache.o Init.o $(REFOBJS.rvct)
+
+compute_ref.axf: scatter.scat compute_ref.rvct.o retarget.rvct.o	\
+	InitCache.o Init.o $(REFOBJS.rvct)
+	$(LD.rvct) $(LDFLAGS.rvct) --scatter $^ -o $@
+
+compute_ref.rvct.o retarget.rvct.o: %.rvct.o: %.c
+	$(CC.rvct) $(CFLAGS.rvct) -c $^ -o $@ -DREFFILE=\"$(REFRVCT)\" -DGCCTESTS_FILE=\"expected_input4gcc.txt\"
+
+ref_%.rvct.o: ref_%.c stm-arm-neon-ref.h
+	$(CC.rvct) $(CFLAGS.rvct) -c $< -o $@
+
+InitCache.o Init.o: %.o: %.s
+	$(CC.rvct) $(CFLAGS.rvct) -c $^ -o $@
+
+
+# Building reference files with GCC/ARM. Link with GCC/ld.
+REFOBJS.gccarm = $(addsuffix .gccarm.o, $(REFLIST))
+REFGCCARM=stm-arm-neon.gccarm
+ref-gccarm: $(REFGCCARM)
+
+check-gccarm: $(REFGCCARM)
+	diff  $(REFGCCARM) ref-rvct-neon-nofp16.txt
+
+$(REFGCCARM): compute_ref.gccarm
+	rvdebug -stdiolog=stdio.log -jou=journal.log -log=log.log -nologo -cmd -init @coretile.core.cpu0@RTSM -inc armscript.inc -exec $^
+
+compute_ref.gccarm: compute_ref.gccarm.o $(REFOBJS.gccarm)
+	$(LD.gccarm) $(LDFLAGS.gccarm) $^ -o $@
+
+compute_ref.gccarm.o: %.gccarm.o: %.c
+	$(CC.gccarm) $(CFLAGS.gccarm) -c $^ -o $@ -DREFFILE=\"$(REFGCCARM)\"
+
+# Building reference files with GCC/ARM. Link with armlink.
+REFGCCARM_RVCT=stm-arm-neon.gccarm-rvct
+ref-gccarm-rvct: $(REFGCCARM_RVCT)
+
+check-gccarm-rvct: $(REFGCCARM_RVCT)
+	diff $(REFGCCARM_RVCT) ref-rvct-neon-nofp16.txt
+
+$(REFGCCARM_RVCT): compute_ref.gccarm-rvct
+	rvdebug -stdiolog=stdio.log -jou=journal.log -log=log.log -nologo -cmd -init @coretile.core.cpu0@RTSM -inc armscript.inc -exec $^
+
+compute_ref.gccarm-rvct: scatter.scat compute_ref.gccarm-rvct.o	\
+	retarget.rvct.o InitCache.o Init.o $(REFOBJS.gccarm)
+	$(LD.rvct) $(LDFLAGS.rvct) --no_strict_wchar_size --scatter $^ -o $@
+
+compute_ref.gccarm-rvct.o: %.gccarm-rvct.o: %.c
+	$(CC.gccarm) $(CFLAGS.gccarm) -c $^ -o $@ -DREFFILE=\"$(REFGCCARM_RVCT)\"
+
+ref_%.gccarm.o: ref_%.c stm-arm-neon-ref.h
+	$(CC.gccarm) $(CFLAGS.gccarm) -c $< -o $@
+
+# Use '*' rather than '%' in these rules:
+# - using '%' does not make them add to the implicit rules above (they
+#   are different rules, only the 1st one matches)
+# - they are needed only when the target already exists, so the
+#   wildcard matches when needed.
+# - if the target does not already exist, the implicit rules apply.
+ref_vadd.*.o ref_vsub.*.o ref_vand.*.o ref_vbic.*.o ref_veor.*.o ref_vorn.*.o ref_vorr.*.o: ref_v_binary_op.c
+ref_vqadd.*.o ref_vqsub.*.o: ref_v_binary_sat_op.c
+ref_vabs.*.o ref_vneg.*.o  ref_vmvn.*.o: ref_v_unary_op.c
+ref_vqabs.*.o ref_vqneg.*.o: ref_v_unary_sat_op.c
+ref_vceq.*.o ref_vcge.*.o ref_vcle.*.o ref_vcgt.*.o ref_vclt.*.o: ref_v_comp_op.c
+ref_vhadd.*.o ref_vrhadd.*.o ref_vhsub.*.o ref_vmin.*.o: ref_vmax.c
+ref_vmls.*.o: ref_vmla.c
+ref_vmls_lane.*.o: ref_vmla_lane.c
+ref_vmls_n.*.o: ref_vmla_n.c
+ref_vmlsl.*.o: ref_vmlal.c
+ref_vmlsl_lane.*.o: ref_vmlal_lane.c
+ref_vmlsl_n.*.o: ref_vmlal_n.c
+ref_vqdmlsl.*.o: ref_vqdmlal.c
+ref_vqdmlsl_lane.*.o: ref_vqdmlal_lane.c
+ref_vqdmlsl_n.*.o: ref_vqdmlal_n.c
+ref_vtrn.*.o ref_vzip.*.o: ref_vuzp.c
+ref_vsli_n.*.o ref_vsri_n.*.o: ref_vsXi_n.c
+ref_vsli_n.*.o: ref_vsli_n.c
+ref_vsri_n.*.o: ref_vsri_n.c
+ref_vraddhn.*.o ref_vsubhn.*.o ref_vrsubhn.*.o: ref_vaddhn.c
+ref_vsubl.*.o: ref_vaddl.c
+ref_vsubw.*.o: ref_vaddw.c
+ref_vcage.*.o ref_vcale.*.o ref_vcagt.*.o ref_vcalt.*.o: ref_v_comp_f_op.c
+
+clean:
+	rm -f *.o *.log stm-arm-neon.refrvct expected_input4gcc.txt
diff --git a/Makefile.gcc b/Makefile.gcc
new file mode 100644
index 0000000..660dcdc
--- /dev/null
+++ b/Makefile.gcc
@@ -0,0 +1,124 @@
+# Copyright (c) 2014 STMicroelectronics
+# Written by Christophe Lyon
+
+# Permission is hereby granted, free of charge, to any person obtaining a copy
+# of this software and associated documentation files (the "Software"), to deal
+# in the Software without restriction, including without limitation the rights
+# to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+# copies of the Software, and to permit persons to whom the Software is
+# furnished to do so, subject to the following conditions:
+
+# The above copyright notice and this permission notice shall be included in
+# all copies or substantial portions of the Software.
+
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+# IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+# FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+# AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+# LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+# OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+# THE SOFTWARE.
+
+# This Makefile is aimed at helping GCC validation, for ARM and
+# AArch64 targets.
+# For example:
+# $ make -f Makefile.gcc clean
+# $ make -f Makefile.gcc CC.gccarm=/path/to/gcc check
+# Note that this will use qemu-system-arm as execution engine which
+# may not be what you want.
+# Alternatively:
+# $ make -f Makefile.gcc clean
+# $ make -f Makefile.gcc CC.gccarm=/path/to/gcc compute_ref.gccarm
+# $ /path/to/qemu -L /path/to/sysroot/lib compute_ref.gccarm
+# $ diff stm-arm-neon.gccarm ref-rvct-neon.txt
+
+CPU=cortex-a9
+
+# GCC/ARM cross compiler
+CC.gccarm := arm-none-eabi-gcc
+CFLAGS.gccarm := -g -Wall -mcpu=$(CPU) -mfloat-abi=hard -mfpu=neon -Wno-unused-variable -Wno-unused-function -ffast-math
+LD.gccarm := $(CC.gccarm)
+LDFLAGS.gccarm := $(CFLAGS.gccarm)
+
+# List of validated intrinsics
+REFNAMES = vld1 vadd vld1_lane vld1_dup vdup vget_high vget_low		\
+	   vqdmlal_lane vqdmlsl_lane vext vshrn_n vset_lane vget_lane	\
+	   vqsub vqdmulh_lane vqdmull vqdmlal vqdmlsl vceq vcge vcle	\
+	   vcgt vclt vbsl vshl vldX vdup_lane vrshrn_n vqdmull_lane	\
+	   vst1_lane vqshl vqshl_n vqrshrn_n vsub vqadd vabs vqabs	\
+	   vcombine vmax vmin vneg vqneg vmlal vmlal_lane vmlsl		\
+	   vmlsl_lane vmovl vmovn vmull vmull_lane vrev vrshl vshl_n	\
+	   vshr_n vsra_n vtrn vuzp vzip vreinterpret vqdmulh vqrdmulh	\
+	   vqrdmulh_lane vqrshl vaba vabal vabd vabdl vand vorr vorn	\
+	   veor vbic vcreate vldX_lane vldX_dup vmla vmls vmul		\
+	   vmul_lane vmul_n vmull_n vqdmulh_n vqdmull_n vqrdmulh_n	\
+	   vmla_lane vmls_lane vmla_n vmls_n vmlal_n vmlsl_n vqdmlal_n	\
+	   vqdmlsl_n vsri_n vsli_n vtst vaddhn vraddhn vaddl vaddw	\
+	   vhadd vrhadd vhsub vsubl vsubw vsubhn vrsubhn vmvn vqmovn	\
+	   vqmovun vrshr_n vrsra_n vshll_n vpaddl vpadd vpadal		\
+	   vqshlu_n vclz vcls vcnt vqshrn_n vpmax vpmin vqshrun_n	\
+	   vqrshrun_n vstX_lane vtbX vrecpe vrsqrte vcage vcagt vcale	\
+	   vcalt vrecps vrsqrts vcvt
+REFLIST = $(addprefix ref_, $(REFNAMES))
+
+REFNAMES_INT = integer dsp dspfns
+REFLIST_INT = $(addprefix ref_, $(REFNAMES_INT))
+
+all: ref-gccarm
+
+check: check-gccarm
+
+# Building reference files with GCC/ARM. Link with GCC/ld.
+REFOBJS.gccarm = $(addsuffix .gccarm.o, $(REFLIST))
+REFGCCARM=stm-arm-neon.gccarm
+ref-gccarm: $(REFGCCARM)
+
+check-gccarm: $(REFGCCARM)
+	diff  $(REFGCCARM) ref-rvct-neon.txt
+
+SIM=qemu-system-arm
+SIMFLAGS=-cpu $(CPU) -semihosting -nographic -kernel 
+$(REFGCCARM): compute_ref.gccarm
+	$(SIM) $(SIMFLAGS) $^
+
+compute_ref.gccarm: compute_ref.gccarm.o $(REFOBJS.gccarm)
+	$(LD.gccarm) $(LDFLAGS.gccarm) $^ -o $@
+
+compute_ref.gccarm.o: %.gccarm.o: %.c
+	$(CC.gccarm) $(CFLAGS.gccarm) -c $^ -o $@ -DREFFILE=\"$(REFGCCARM)\" -DGCCTESTS_FILE=\"expected_input4gcc.txt\"
+
+ref_%.gccarm.o: ref_%.c stm-arm-neon-ref.h
+	$(CC.gccarm) $(CFLAGS.gccarm) -c $< -o $@
+
+# Use '*' rather than '%' in these rules:
+# - using '%' does not make them add to the implicit rules above (they
+#   are different rules, only the 1st one matches)
+# - they are needed only when the target already exists, so the
+#   wildcard matches when needed.
+# - if the target does not already exist, the implicit rules apply.
+ref_vadd.*.o ref_vsub.*.o ref_vand.*.o ref_vbic.*.o ref_veor.*.o ref_vorn.*.o ref_vorr.*.o: ref_v_binary_op.c
+ref_vqadd.*.o ref_vqsub.*.o: ref_v_binary_sat_op.c
+ref_vabs.*.o ref_vneg.*.o  ref_vmvn.*.o: ref_v_unary_op.c
+ref_vqabs.*.o ref_vqneg.*.o: ref_v_unary_sat_op.c
+ref_vceq.*.o ref_vcge.*.o ref_vcle.*.o ref_vcgt.*.o ref_vclt.*.o: ref_v_comp_op.c
+ref_vhadd.*.o ref_vrhadd.*.o ref_vhsub.*.o ref_vmin.*.o: ref_vmax.c
+ref_vmls.*.o: ref_vmla.c
+ref_vmls_lane.*.o: ref_vmla_lane.c
+ref_vmls_n.*.o: ref_vmla_n.c
+ref_vmlsl.*.o: ref_vmlal.c
+ref_vmlsl_lane.*.o: ref_vmlal_lane.c
+ref_vmlsl_n.*.o: ref_vmlal_n.c
+ref_vqdmlsl.*.o: ref_vqdmlal.c
+ref_vqdmlsl_lane.*.o: ref_vqdmlal_lane.c
+ref_vqdmlsl_n.*.o: ref_vqdmlal_n.c
+ref_vtrn.*.o ref_vzip.*.o: ref_vuzp.c
+ref_vsli_n.*.o ref_vsri_n.*.o: ref_vsXi_n.c
+ref_vsli_n.*.o: ref_vsli_n.c
+ref_vsri_n.*.o: ref_vsri_n.c
+ref_vraddhn.*.o ref_vsubhn.*.o ref_vrsubhn.*.o: ref_vaddhn.c
+ref_vsubl.*.o: ref_vaddl.c
+ref_vsubw.*.o: ref_vaddw.c
+ref_vcage.*.o ref_vcale.*.o ref_vcagt.*.o ref_vcalt.*.o: ref_v_comp_f_op.c
+
+clean:
+	rm -f *.o *.log
diff --git a/README b/README
new file mode 100644
index 0000000..327184a
--- /dev/null
+++ b/README
@@ -0,0 +1,60 @@
+ARM Neon reference tests
+========================
+This package contains extensive tests for the ARM/Neon instructions.
+
+It works by building a program which uses all of them, and then
+executing it on an actual target or a simulator.
+
+It can be used to validate the simulator against an actual HW target,
+or to validate C compilers in presence of Neon intrinsics calls.
+
+The supplied Makefile enables to build with both ARM RVCT compiler and
+GNU GCC (for the ARM target), and supports execution with ARM RVDEBUG
+on an ARM simulator and with QEMU.
+
+For convenience, the ARM ELF binary file (as compiled with RVCT) is
+supplied (compute_ref.axf), as well as expected output (ref-rvct.txt).
+
+A second file containing expected output is also supplied:
+ref-rvct-neon.txt, which contains only the results of the Neon
+instrinsics tests. It is aimed at being used to check GCC's results,
+since this compiler does not support the integer & dsp builtins whose
+results are also present in ref-rvct.txt.
+
+Typical usage when used to debug QEmu:
+$ make all # to build the test program with ARM rvct and execute with QEmu
+$ make check # to compare the results with the expected output
+
+
+Known issues:
+-------------
+Some tests currently fail to build with GCC/ARM:
+- missing include files: dspfns.h, armdsp.h
+
+As GCC/ARM provides no support for the
+Neon_Cumulative_Saturation/fpsrc register, auxiliary accessor
+functions have been implemented in stm-arm-neon-ref.h.
+
+Engineering:
+------------
+In order to cover all the Neon instructions extensively, these tests
+make intensive use of the C-preprocessor, to save maintenance efforts.
+
+Most tests (the more regular ones) share a common basic structure. In
+general, variable names are suffixed by their type name, so as to
+differentiate variables with the same purpose but of differente types.
+Hence vector1_int8x8, vector1_int16x4 etc...
+
+For instance in ref_vmul.c the layout of the code is as follows:
+
+- declare input and output vectors (named 'vector1', 'vector2' and
+  'vector_res') of each possible type (s/u, 8/16/32/64 bits).
+
+- clean the result buffers.
+
+- initialize input vectors 'vector1' and 'vector2'.
+
+- call each variant of the intrinsic and store the result in a buffer
+  named 'buffer', whose contents is printed after execution.
+
+One can then compare the actual result with the expected one.
diff --git a/armscript.inc b/armscript.inc
new file mode 100644
index 0000000..ad53a5c
--- /dev/null
+++ b/armscript.inc
@@ -0,0 +1,14 @@
+ERROR=ABORT // Abort if error occurs when processing the script
+WAIT=ON // Wait for each command to finish
+
+GO
+
+STATS
+
+  //STDIOLOG OFF // Close the log file
+
+  //UNLOAD 1 // Unload the image
+  //DELFILE 1 // Remove the symbol definitions
+    //DISCONNECT  // Disconnect from the target
+  //WAIT=OFF
+QUIT Y
diff --git a/compute_ref.axf b/compute_ref.axf
new file mode 100644
index 0000000..e7035b9
--- /dev/null
+++ b/compute_ref.axf
diff --git a/compute_ref.c b/compute_ref.c
new file mode 100644
index 0000000..5839d36
--- /dev/null
+++ b/compute_ref.c
@@ -0,0 +1,370 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2012, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define _AEABI_PORTABILITY_LEVEL 1
+#undef _AEABI_PORTABLE
+#if defined(__cplusplus)
+#include <cstdio>
+#include <cstdlib>
+#else
+#include <stdio.h>
+#include <stdlib.h>
+#endif
+
+FILE* log_file = NULL;
+FILE* ref_file = NULL;
+FILE* gcc_tests_file = NULL;
+
+#define LOGFILE "stm-arm-neon-ref.log"
+
+void cleanup (void)
+{
+  if (log_file) fclose (log_file);
+  if (ref_file) fclose (ref_file);
+  if (gcc_tests_file) fclose (gcc_tests_file);
+  exit (1);
+}
+
+extern void exec_vld1(void);
+extern void exec_vadd(void);
+extern void exec_vld1_lane(void);
+extern void exec_vld1_dup(void);
+extern void exec_vdup(void);
+extern void exec_vget_high(void);
+extern void exec_vget_low(void);
+extern void exec_vqdmlal_lane(void);
+extern void exec_vqdmlsl_lane(void);
+extern void exec_vqdmlal_n(void);
+extern void exec_vqdmlsl_n(void);
+extern void exec_vext(void);
+extern void exec_vshr_n(void);
+extern void exec_vshrn_n(void);
+extern void exec_vrshrn_n(void);
+extern void exec_vqrshrn_n(void);
+extern void exec_vset_lane(void);
+extern void exec_vget_lane(void);
+extern void exec_vqsub(void);
+extern void exec_vqdmulh(void);
+extern void exec_vqdmulh_lane(void);
+extern void exec_vqdmulh_n(void);
+extern void exec_vqdmull(void);
+extern void exec_vqdmlal(void);
+extern void exec_vqdmlsl(void);
+extern void exec_vceq(void);
+extern void exec_vcge(void);
+extern void exec_vcle(void);
+extern void exec_vcgt(void);
+extern void exec_vclt(void);
+extern void exec_vbsl(void);
+extern void exec_vshl(void);
+extern void exec_vqshl(void);
+extern void exec_vqshl_n(void);
+extern void exec_vrshl(void);
+extern void exec_vshl_n(void);
+extern void exec_vldX(void);
+extern void exec_vdup_lane(void);
+extern void exec_vqdmull_lane(void);
+extern void exec_vqdmull_n(void);
+extern void exec_vst1_lane(void);
+extern void exec_vsub(void);
+extern void exec_vqadd(void);
+extern void exec_vabs(void);
+extern void exec_vqabs(void);
+extern void exec_vcombine(void);
+extern void exec_vmax(void);
+extern void exec_vmin(void);
+extern void exec_vneg(void);
+extern void exec_vqneg(void);
+extern void exec_vmlal(void);
+extern void exec_vmlal_lane(void);
+extern void exec_vmlal_n(void);
+extern void exec_vmlsl(void);
+extern void exec_vmlsl_lane(void);
+extern void exec_vmlsl_n(void);
+extern void exec_vmovl(void);
+extern void exec_vmovn(void);
+extern void exec_vmull(void);
+extern void exec_vmull_lane(void);
+extern void exec_vrev(void);
+extern void exec_vsra_n(void);
+extern void exec_vtrn(void);
+extern void exec_vuzp(void);
+extern void exec_vzip(void);
+extern void exec_vreinterpret(void);
+extern void exec_vqrdmulh(void);
+extern void exec_vqrdmulh_lane(void);
+extern void exec_vqrdmulh_n(void);
+extern void exec_vqrshl(void);
+extern void exec_vaba(void);
+extern void exec_vabal(void);
+extern void exec_vabd(void);
+extern void exec_vabdl(void);
+extern void exec_vand(void);
+extern void exec_vorr(void);
+extern void exec_vorn(void);
+extern void exec_veor(void);
+extern void exec_vbic(void);
+extern void exec_vcreate(void);
+extern void exec_vldX_lane(void);
+extern void exec_vldX_dup(void);
+extern void exec_vmla(void);
+extern void exec_vmls(void);
+extern void exec_vmul(void);
+extern void exec_vmul_lane(void);
+extern void exec_vmul_n(void);
+extern void exec_vmull_n(void);
+extern void exec_vmla_lane(void);
+extern void exec_vmls_lane(void);
+extern void exec_vmla_n(void);
+extern void exec_vmls_n(void);
+extern void exec_vsli_n(void);
+extern void exec_vsri_n(void);
+extern void exec_vtst(void);
+extern void exec_vaddhn(void);
+extern void exec_vraddhn(void);
+extern void exec_vaddl(void);
+extern void exec_vaddw(void);
+extern void exec_vhadd(void);
+extern void exec_vrhadd(void);
+extern void exec_vhsub(void);
+extern void exec_vsubl(void);
+extern void exec_vsubw(void);
+extern void exec_vsubhn(void);
+extern void exec_vrsubhn(void);
+extern void exec_vmvn(void);
+extern void exec_vqmovn(void);
+extern void exec_vqmovun(void);
+extern void exec_vrshr_n(void);
+extern void exec_vrsra_n(void);
+extern void exec_vshll_n(void);
+extern void exec_vpaddl(void);
+extern void exec_vpadd(void);
+extern void exec_vpadal(void);
+extern void exec_vqshlu_n(void);
+extern void exec_vclz(void);
+extern void exec_vcls(void);
+extern void exec_vcnt(void);
+extern void exec_vqshrn_n(void);
+extern void exec_vpmax(void);
+extern void exec_vpmin(void);
+extern void exec_vqshrun_n(void);
+extern void exec_vqrshrun_n(void);
+extern void exec_vstX_lane(void);
+extern void exec_vtbX(void);
+extern void exec_vrecpe(void);
+extern void exec_vrsqrte(void);
+
+extern void exec_vcage(void);
+extern void exec_vcagt(void);
+extern void exec_vcale(void);
+extern void exec_vcalt(void);
+extern void exec_vcvt(void);
+extern void exec_vrecps(void);
+extern void exec_vrsqrts(void);
+
+#if defined(__ARMCC_VERSION) || !defined(__arm__)
+extern void exec_integer(void); /* Integer (non-NEON) intrinsics */
+extern void exec_dsp(void); /* DSP (non-NEON) intrinsics */
+extern void exec_dspfns(void); /* DSP FNS (non-NEON/ITU) intrinsics */
+#endif
+
+#include "compute_ref_data.c"
+
+int main (void)
+{
+#if defined(_MSC_VER)
+    /* When compiled with MSVC, force output of FP numbers with only 2
+     * digits for the exponent, for easier comparison of the results
+     * with GCC.  */
+    _set_output_format(_TWO_DIGIT_EXPONENT);
+#endif
+
+  log_file = fopen (LOGFILE, "w");
+  if (log_file == NULL) {
+    fprintf (stderr, "Error opening log file " LOGFILE "\n");
+    cleanup ();
+  }
+
+  ref_file = fopen (REFFILE, "w");
+  if (ref_file == NULL) {
+    fprintf (log_file, "Error opening ref file %s\n", REFFILE);
+    cleanup ();
+  }
+
+  gcc_tests_file = fopen (GCCTESTS_FILE, "w");
+  if (gcc_tests_file == NULL) {
+    fprintf (log_file, "Error opening GCC ref file %s\n", GCCTESTS_FILE);
+    cleanup ();
+  }
+
+  fprintf (log_file, "Computing refs....\n");
+
+  exec_vld1 ();
+  exec_vadd ();
+  exec_vld1_lane ();
+  exec_vld1_dup ();
+  exec_vdup ();
+  exec_vget_high ();
+  exec_vget_low ();
+  exec_vqdmlal_lane ();
+  exec_vqdmlsl_lane ();
+  exec_vqdmlal_n ();
+  exec_vqdmlsl_n ();
+  exec_vext ();
+  exec_vshr_n ();
+  exec_vshrn_n ();
+  exec_vrshrn_n ();
+  exec_vqrshrn_n ();
+  exec_vset_lane ();
+  exec_vget_lane ();
+  exec_vqsub ();
+  exec_vqdmulh ();
+  exec_vqdmulh_lane ();
+  exec_vqdmulh_n ();
+  exec_vqdmull ();
+  exec_vqdmlal ();
+  exec_vqdmlsl ();
+  exec_vceq ();
+  exec_vcge ();
+  exec_vcle ();
+  exec_vcgt ();
+  exec_vclt ();
+  exec_vbsl ();
+  exec_vshl ();
+  exec_vshl_n ();
+  exec_vqshl ();
+  exec_vqshl_n ();
+  exec_vrshl ();
+  exec_vldX ();
+  exec_vdup_lane ();
+  exec_vqdmull_lane ();
+  exec_vqdmull_n ();
+  exec_vst1_lane ();
+  exec_vsub ();
+  exec_vqadd ();
+  exec_vabs ();
+  exec_vqabs ();
+  exec_vcombine ();
+  exec_vmax ();
+  exec_vmin ();
+  exec_vneg ();
+  exec_vqneg ();
+  exec_vmlal ();
+  exec_vmlsl ();
+  exec_vmlal_lane ();
+  exec_vmlsl_lane ();
+  exec_vmlal_n ();
+  exec_vmlsl_n ();
+  exec_vmovl ();
+  exec_vmovn ();
+  exec_vmull ();
+  exec_vmull_lane ();
+  exec_vrev ();
+  exec_vsra_n ();
+  exec_vtrn ();
+  exec_vuzp ();
+  exec_vzip ();
+  exec_vreinterpret ();
+  exec_vqrdmulh ();
+  exec_vqrdmulh_lane ();
+  exec_vqrdmulh_n ();
+  exec_vqrshl ();
+  exec_vaba ();
+  exec_vabal ();
+  exec_vabd ();
+  exec_vabdl ();
+  exec_vand ();
+  exec_vorr ();
+  exec_vorn ();
+  exec_veor ();
+  exec_vbic ();
+  exec_vcreate ();
+  exec_vldX_lane ();
+  exec_vldX_dup ();
+  exec_vmla ();
+  exec_vmls ();
+  exec_vmul ();
+  exec_vmul_lane ();
+  exec_vmul_n ();
+  exec_vmull_n ();
+  exec_vmla_lane ();
+  exec_vmls_lane ();
+  exec_vmla_n ();
+  exec_vmls_n ();
+  exec_vsli_n ();
+  exec_vsri_n ();
+  exec_vtst ();
+  exec_vaddhn ();
+  exec_vraddhn ();
+  exec_vaddl ();
+  exec_vaddw ();
+  exec_vhadd ();
+  exec_vrhadd ();
+  exec_vhsub ();
+  exec_vsubl ();
+  exec_vsubw ();
+  exec_vsubhn ();
+  exec_vrsubhn ();
+  exec_vmvn ();
+  exec_vqmovn ();
+  exec_vqmovun ();
+  exec_vrshr_n ();
+  exec_vrsra_n ();
+  exec_vshll_n ();
+  exec_vpaddl ();
+  exec_vpadd ();
+  exec_vpadal ();
+  exec_vqshlu_n ();
+  exec_vclz ();
+  exec_vcls ();
+  exec_vcnt ();
+  exec_vqshrn_n ();
+  exec_vpmax ();
+  exec_vpmin ();
+  exec_vqshrun_n ();
+  exec_vqrshrun_n ();
+  exec_vstX_lane ();
+  exec_vtbX ();
+  exec_vrecpe ();
+  exec_vrsqrte ();
+
+  exec_vcage ();
+  exec_vcale ();
+  exec_vcagt ();
+  exec_vcalt ();
+  exec_vcvt ();
+  exec_vrecps ();
+  exec_vrsqrts ();
+
+#if defined(__ARMCC_VERSION) || (!defined(__arm__) && !defined(__aarch64__))
+  exec_integer ();
+  exec_dsp ();
+  exec_dspfns ();
+#endif
+
+  fprintf (log_file, "Finished\n");
+
+  return 0;
+}
diff --git a/compute_ref.gccarm b/compute_ref.gccarm
new file mode 100755
index 0000000..664ef29
--- /dev/null
+++ b/compute_ref.gccarm
diff --git a/compute_ref.gccarm-rvct b/compute_ref.gccarm-rvct
new file mode 100644
index 0000000..0e319a3
--- /dev/null
+++ b/compute_ref.gccarm-rvct
diff --git a/compute_ref_data.c b/compute_ref_data.c
new file mode 100644
index 0000000..8dbf727
--- /dev/null
+++ b/compute_ref_data.c
@@ -0,0 +1,566 @@
+/*
+
+Copyright (c) 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+#include "stm-arm-neon-ref.h"
+
+/* Initialization helpers; 4 slices are needed for vld2, vld3 and
+   vld4.  */
+#define MY_INIT_TAB(T,W,N) xNAME(INIT_TAB,N)(T##W##_t)
+#define MY_INIT_TAB2(T,W,N) xNAME(INIT_TAB2,N)(T##W##_t)
+#define MY_INIT_TAB3(T,W,N) xNAME(INIT_TAB3,N)(T##W##_t)
+#define MY_INIT_TAB4(T,W,N) xNAME(INIT_TAB4,N)(T##W##_t)
+
+/* Initialized input buffers.  */
+#define VECT_VAR_DECL_INIT(V, T, W, N)			\
+  VECT_VAR_DECL(V,T,W,N) [] = { MY_INIT_TAB(T,W,N) };
+
+/* Specialized initializer with 4 entries, as used by vldX_dup and
+   vdup tests, which iterate 4 times on input buffers.  */
+#define VECT_VAR_DECL_INIT4(V, T, W, N)			\
+  VECT_VAR_DECL(V,T,W,N) [] = { MY_INIT_TAB(T,W,4) };
+
+/* Initializers for arrays of vectors.  */
+#define VECT_ARRAY_INIT2(V, T, W, N)		\
+  T##W##_t VECT_ARRAY_VAR(V,T,W,N,2)[] =	\
+  { MY_INIT_TAB(T,W,N)				\
+    MY_INIT_TAB2(T,W,N) };
+
+#define VECT_ARRAY_INIT3(V, T, W, N)					\
+  T##W##_t VECT_ARRAY_VAR(V,T,W,N,3)[] =				\
+  { MY_INIT_TAB(T,W,N)							\
+    MY_INIT_TAB2(T,W,N)							\
+    MY_INIT_TAB3(T,W,N) };
+
+#define VECT_ARRAY_INIT4(V, T, W, N)					\
+  T##W##_t VECT_ARRAY_VAR(V,T,W,N,4)[] =				\
+  { MY_INIT_TAB(T,W,N)							\
+    MY_INIT_TAB2(T,W,N)							\
+    MY_INIT_TAB3(T,W,N)							\
+    MY_INIT_TAB4(T,W,N) };
+
+/* Sample initialization vectors.  */
+#define INIT_TAB_1(T)				\
+  (T)-16,
+#define INIT_TAB2_1(T)				\
+  (T)-15,
+#define INIT_TAB3_1(T)				\
+  (T)-14,
+#define INIT_TAB4_1(T)				\
+  (T)-13,
+
+#define INIT_TAB_2(T)				\
+  (T)-16, (T)-15,
+#define INIT_TAB2_2(T)				\
+  (T)-14, (T)-13,
+#define INIT_TAB3_2(T)				\
+  (T)-12, (T)-11,
+#define INIT_TAB4_2(T)				\
+  (T)-10, (T)-9,
+
+/* Initializer for vld3_lane tests.  */
+#define INIT_TAB_3(T)				\
+  (T)-16, (T)-15, (T)-14,
+
+#define INIT_TAB_4(T)				\
+  (T)-16, (T)-15, (T)-14, (T)-13,
+#define INIT_TAB2_4(T)				\
+  (T)-12, (T)-11, (T)-10, (T)-9,
+#define INIT_TAB3_4(T)				\
+  (T)-8, (T)-7, (T)-6, (T)-5,
+#define INIT_TAB4_4(T)				\
+  (T)-4, (T)-3, (T)-2, (T)-1,
+
+#define INIT_TAB_8(T)							\
+  (T)-16, (T)-15, (T)-14, (T)-13, (T)-12, (T)-11, (T)-10, (T)-9,
+#define INIT_TAB2_8(T)							\
+  (T)-8, (T)-7, (T)-6, (T)-5, (T)-4, (T)-3, (T)-2, (T)-1,
+#define INIT_TAB3_8(T)							\
+  (T)0, (T)1, (T)2, (T)3, (T)4, (T)5, (T)6, (T)7,
+#define INIT_TAB4_8(T)							\
+  (T)8, (T)9, (T)10, (T)11, (T)12, (T)13, (T)14, (T)15,
+
+#define INIT_TAB_16(T)							\
+  (T)-16, (T)-15, (T)-14, (T)-13, (T)-12, (T)-11, (T)-10, (T)-9,	\
+  (T)-8, (T)-7, (T)-6, (T)-5, (T)-4, (T)-3, (T)-2, (T)-1,
+#define INIT_TAB2_16(T)							\
+  (T)0, (T)1, (T)2, (T)3, (T)4, (T)5, (T)6, (T)7,			\
+  (T)8, (T)9, (T)10, (T)11, (T)12, (T)13, (T)14, (T)15,
+#define INIT_TAB3_16(T)							\
+  (T)16, (T)17, (T)18, (T)19, (T)20, (T)21, (T)22, (T)23,		\
+   (T)24, (T)25, (T)26, (T)27, (T)28, (T)29, (T)30, (T)31,
+#define INIT_TAB4_16(T)							\
+  (T)32, (T)33, (T)34, (T)35, (T)36, (T)37, (T)38, (T)39,		\
+  (T)40, (T)41, (T)42, (T)43, (T)44, (T)45, (T)46, (T)47,
+
+/* Input buffers, one of each size.  */
+/* Insert some padding to try to exhibit out of bounds accesses.  */
+VECT_VAR_DECL_INIT(buffer, int, 8, 8);
+PAD(buffer_pad, int, 8, 8);
+VECT_VAR_DECL_INIT(buffer, int, 16, 4);
+PAD(buffer_pad, int, 16, 4);
+VECT_VAR_DECL_INIT(buffer, int, 32, 2);
+PAD(buffer_pad, int, 32, 2);
+VECT_VAR_DECL_INIT(buffer, int, 64, 1);
+PAD(buffer_pad, int, 64, 1);
+VECT_VAR_DECL_INIT(buffer, uint, 8, 8);
+PAD(buffer_pad, uint, 8, 8);
+VECT_VAR_DECL_INIT(buffer, poly, 8, 8);
+PAD(buffer_pad, poly, 8, 8);
+VECT_VAR_DECL_INIT(buffer, poly, 16, 4);
+PAD(buffer_pad, poly, 16, 4);
+VECT_VAR_DECL_INIT(buffer, uint, 16, 4);
+PAD(buffer_pad, uint, 16, 4);
+VECT_VAR_DECL_INIT(buffer, uint, 32, 2);
+PAD(buffer_pad, uint, 32, 2);
+VECT_VAR_DECL_INIT(buffer, uint, 64, 1);
+PAD(buffer_pad, uint, 64, 1);
+VECT_VAR_DECL_INIT(buffer, float, 32, 2);
+PAD(buffer_pad, float, 32, 2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+/* We need a different initialization for ARMCC, because the compiler
+   performs the conversion to half-precision internal
+   representation.  */
+#ifdef __ARMCC_VERSION
+__fp16 buffer_float16x4[4] = {-16, -15, -14, -13};
+#else
+VECT_VAR_DECL(buffer, float, 16, 4) [] = {0xcc00 /* -16 */, 0xcb80 /* -15 */,
+					  0xcb00 /* -14 */, 0xca80 /* -13 */};
+#endif
+PAD(buffer_pad, float, 16, 4);
+#endif
+VECT_VAR_DECL_INIT(buffer, int, 8, 16);
+PAD(buffer_pad, int, 8, 16);
+VECT_VAR_DECL_INIT(buffer, int, 16, 8);
+PAD(buffer_pad, int, 16, 8);
+VECT_VAR_DECL_INIT(buffer, int, 32, 4);
+PAD(buffer_pad, int, 32, 4);
+VECT_VAR_DECL_INIT(buffer, int, 64, 2);
+PAD(buffer_pad, int, 64, 2);
+VECT_VAR_DECL_INIT(buffer, uint, 8, 16);
+PAD(buffer_pad, uint, 8, 16);
+VECT_VAR_DECL_INIT(buffer, uint, 16, 8);
+PAD(buffer_pad, uint, 16, 8);
+VECT_VAR_DECL_INIT(buffer, uint, 32, 4);
+PAD(buffer_pad, uint, 32, 4);
+VECT_VAR_DECL_INIT(buffer, uint, 64, 2);
+PAD(buffer_pad, uint, 64, 2);
+VECT_VAR_DECL_INIT(buffer, poly, 8, 16);
+PAD(buffer_pad, poly, 8, 16);
+VECT_VAR_DECL_INIT(buffer, poly, 16, 8);
+PAD(buffer_pad, poly, 16, 8);
+VECT_VAR_DECL_INIT(buffer, float, 32, 4);
+PAD(buffer_pad, float, 32, 4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#ifdef __ARMCC_VERSION
+__fp16 buffer_float16x8[8] = {-16, -15, -14, -13, -12, -11, -10, -9};
+#else
+VECT_VAR_DECL(buffer, float, 16, 8) [] = {0xcc00 /* -16 */, 0xcb80 /* -15 */,
+					  0xcb00 /* -14 */, 0xca80 /* -13 */,
+					  0xca00 /* -12 */, 0xc980 /* -11 */,
+					  0xc900 /* -10 */, 0xc880 /* -9 */};
+#endif
+PAD(buffer_pad, float, 16, 8);
+#endif
+
+/* The tests for vld1_dup and vdup expect at least 4 entries in the
+   input buffer, so force 1- and 2-elements initializers to have 4
+   entries.  */
+VECT_VAR_DECL_INIT(buffer_dup, int, 8, 8);
+VECT_VAR_DECL(buffer_dup_pad, int, 8, 8);
+VECT_VAR_DECL_INIT(buffer_dup, int, 16, 4);
+VECT_VAR_DECL(buffer_dup_pad, int, 16, 4);
+VECT_VAR_DECL_INIT4(buffer_dup, int, 32, 2);
+VECT_VAR_DECL(buffer_dup_pad, int, 32, 2);
+VECT_VAR_DECL_INIT4(buffer_dup, int, 64, 1);
+VECT_VAR_DECL(buffer_dup_pad, int, 64, 1);
+VECT_VAR_DECL_INIT(buffer_dup, uint, 8, 8);
+VECT_VAR_DECL(buffer_dup_pad, uint, 8, 8);
+VECT_VAR_DECL_INIT(buffer_dup, uint, 16, 4);
+VECT_VAR_DECL(buffer_dup_pad, uint, 16, 4);
+VECT_VAR_DECL_INIT4(buffer_dup, uint, 32, 2);
+VECT_VAR_DECL(buffer_dup_pad, uint, 32, 2);
+VECT_VAR_DECL_INIT4(buffer_dup, uint, 64, 1);
+VECT_VAR_DECL(buffer_dup_pad, uint, 64, 1);
+VECT_VAR_DECL_INIT(buffer_dup, poly, 8, 8);
+VECT_VAR_DECL(buffer_dup_pad, poly, 8, 8);
+VECT_VAR_DECL_INIT(buffer_dup, poly, 16, 4);
+VECT_VAR_DECL(buffer_dup_pad, poly, 16, 4);
+VECT_VAR_DECL_INIT4(buffer_dup, float, 32, 2);
+VECT_VAR_DECL(buffer_dup_pad, float, 32, 2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#ifdef __ARMCC_VERSION
+__fp16 buffer_dup_float16x4[4] = {-16, -15, -14, -13};
+#else
+VECT_VAR_DECL(buffer_dup, float, 16, 4)[] = {0xcc00 /* -16 */, 0xcb80 /* -15 */,
+					     0xcb00 /* -14 */, 0xca80 /* -13 */};
+#endif
+PAD(buffer_dup_pad, float, 16, 4);
+#endif
+VECT_VAR_DECL_INIT(buffer_dup, int, 8, 16);
+VECT_VAR_DECL(buffer_dup_pad, int, 8, 16);
+VECT_VAR_DECL_INIT(buffer_dup, int, 16, 8);
+VECT_VAR_DECL(buffer_dup_pad, int, 16, 8);
+VECT_VAR_DECL_INIT(buffer_dup, int, 32, 4);
+VECT_VAR_DECL(buffer_dup_pad, int, 32, 4);
+VECT_VAR_DECL_INIT4(buffer_dup, int, 64, 2);
+VECT_VAR_DECL(buffer_dup_pad, int, 64, 2);
+VECT_VAR_DECL_INIT(buffer_dup, uint, 8, 16);
+VECT_VAR_DECL(buffer_dup_pad, uint, 8, 16);
+VECT_VAR_DECL_INIT(buffer_dup, uint, 16, 8);
+VECT_VAR_DECL(buffer_dup_pad, uint, 16, 8);
+VECT_VAR_DECL_INIT(buffer_dup, uint, 32, 4);
+VECT_VAR_DECL(buffer_dup_pad, uint, 32, 4);
+VECT_VAR_DECL_INIT4(buffer_dup, uint, 64, 2);
+VECT_VAR_DECL(buffer_dup_pad, uint, 64, 2);
+VECT_VAR_DECL_INIT(buffer_dup, poly, 8, 16);
+VECT_VAR_DECL(buffer_dup_pad, poly, 8, 16);
+VECT_VAR_DECL_INIT(buffer_dup, poly, 16, 8);
+VECT_VAR_DECL(buffer_dup_pad, poly, 16, 8);
+VECT_VAR_DECL_INIT(buffer_dup, float, 32, 4);
+VECT_VAR_DECL(buffer_dup_pad, float, 32, 4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#ifdef __ARMCC_VERSION
+__fp16 buffer_dup_float16x8[8] = {-16, -15, -14, -13, -12, -11, -10, -9};
+#else
+VECT_VAR_DECL(buffer_dup, float, 16, 8)[] = {0xcc00 /* -16 */, 0xcb80 /* -15 */,
+					     0xcb00 /* -14 */, 0xca80 /* -13 */,
+					     0xca00 /* -12 */, 0xc980 /* -11 */,
+					     0xc900 /* -10 */, 0xc880 /* -9 */};
+#endif
+PAD(buffer_dup_pad, float, 16, 8);
+#endif
+
+/* Input buffers for vld2, 1 of each size */
+VECT_ARRAY_INIT2(buffer_vld2, int, 8, 8);
+PAD(buffer_vld2_pad, int, 8, 8);
+VECT_ARRAY_INIT2(buffer_vld2, int, 16, 4);
+PAD(buffer_vld2_pad, int, 16, 4);
+VECT_ARRAY_INIT2(buffer_vld2, int, 32, 2);
+PAD(buffer_vld2_pad, int, 32, 2);
+VECT_ARRAY_INIT2(buffer_vld2, int, 64, 1);
+PAD(buffer_vld2_pad, int, 64, 1);
+VECT_ARRAY_INIT2(buffer_vld2, uint, 8, 8);
+PAD(buffer_vld2_pad, uint, 8, 8);
+VECT_ARRAY_INIT2(buffer_vld2, uint, 16, 4);
+PAD(buffer_vld2_pad, uint, 16, 4);
+VECT_ARRAY_INIT2(buffer_vld2, uint, 32, 2);
+PAD(buffer_vld2_pad, uint, 32, 2);
+VECT_ARRAY_INIT2(buffer_vld2, uint, 64, 1);
+PAD(buffer_vld2_pad, uint, 64, 1);
+VECT_ARRAY_INIT2(buffer_vld2, poly, 8, 8);
+PAD(buffer_vld2_pad, poly, 8, 8);
+VECT_ARRAY_INIT2(buffer_vld2, poly, 16, 4);
+PAD(buffer_vld2_pad, poly, 16, 4);
+VECT_ARRAY_INIT2(buffer_vld2, float, 32, 2);
+PAD(buffer_vld2_pad, float, 32, 2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#ifdef __ARMCC_VERSION
+__fp16 buffer_vld2_float16x4x2[4*2] = {-16, -15, -14, -13, -12, -11, -10, -9};
+#else
+float16_t buffer_vld2_float16x4x2[4*2] = {0xcc00 /* -16 */, 0xcb80 /* -15 */,
+					  0xcb00 /* -14 */, 0xca80 /* -13 */,
+					  0xca00 /* -12 */, 0xc980 /* -11 */,
+					  0xc900 /* -10 */, 0xc880 /* -9 */};
+#endif
+PAD(buffer_vld2_pad, float, 16, 4);
+#endif
+VECT_ARRAY_INIT2(buffer_vld2, int, 8, 16);
+PAD(buffer_vld2_pad, int, 8, 16);
+VECT_ARRAY_INIT2(buffer_vld2, int, 16, 8);
+PAD(buffer_vld2_pad, int, 16, 8);
+VECT_ARRAY_INIT2(buffer_vld2, int, 32, 4);
+PAD(buffer_vld2_pad, int, 32, 4);
+VECT_ARRAY_INIT2(buffer_vld2, int, 64, 2);
+PAD(buffer_vld2_pad, int, 64, 2);
+VECT_ARRAY_INIT2(buffer_vld2, uint, 8, 16);
+PAD(buffer_vld2_pad, uint, 8, 16);
+VECT_ARRAY_INIT2(buffer_vld2, uint, 16, 8);
+PAD(buffer_vld2_pad, uint, 16, 8);
+VECT_ARRAY_INIT2(buffer_vld2, uint, 32, 4);
+PAD(buffer_vld2_pad, uint, 32, 4);
+VECT_ARRAY_INIT2(buffer_vld2, uint, 64, 2);
+PAD(buffer_vld2_pad, uint, 64, 2);
+VECT_ARRAY_INIT2(buffer_vld2, poly, 8, 16);
+PAD(buffer_vld2_pad, poly, 8, 16);
+VECT_ARRAY_INIT2(buffer_vld2, poly, 16, 8);
+PAD(buffer_vld2_pad, poly, 16, 8);
+VECT_ARRAY_INIT2(buffer_vld2, float, 32, 4);
+PAD(buffer_vld2_pad, float, 32, 4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#ifdef __ARMCC_VERSION
+__fp16 buffer_vld2_float16x8x2[8*2] = {-16, -15, -14, -13, -12, -11, -10, -9,
+				       -8, -7, -6, -5, -4, -3, -2, -1};
+#else
+float16_t buffer_vld2_float16x8x2[8*2] = {0xcc00 /* -16 */, 0xcb80 /* -15 */,
+					  0xcb00 /* -14 */, 0xca80 /* -13 */,
+					  0xca00 /* -12 */, 0xc980 /* -11 */,
+					  0xc900 /* -10 */, 0xc880 /* -9 */,
+					  0xc800 /* -8 */, 0xc700 /* -7 */,
+					  0xc600 /* -6 */, 0xc500 /* -5 */,
+					  0xc400 /* -4 */, 0xc200 /* -3 */,
+					  0xc000 /* -2 */, 0xbc00 /* -1 */};
+#endif
+PAD(buffer_vld2_pad, float, 16, 8);
+#endif
+
+/* Input buffers for vld3, 1 of each size */
+VECT_ARRAY_INIT3(buffer_vld3, int, 8, 8);
+PAD(buffer_vld3_pad, int, 8, 8);
+VECT_ARRAY_INIT3(buffer_vld3, int, 16, 4);
+PAD(buffer_vld3_pad, int, 16, 4);
+VECT_ARRAY_INIT3(buffer_vld3, int, 32, 2);
+PAD(buffer_vld3_pad, int, 32, 2);
+VECT_ARRAY_INIT3(buffer_vld3, int, 64, 1);
+PAD(buffer_vld3_pad, int, 64, 1);
+VECT_ARRAY_INIT3(buffer_vld3, uint, 8, 8);
+PAD(buffer_vld3_pad, uint, 8, 8);
+VECT_ARRAY_INIT3(buffer_vld3, uint, 16, 4);
+PAD(buffer_vld3_pad, uint, 16, 4);
+VECT_ARRAY_INIT3(buffer_vld3, uint, 32, 2);
+PAD(buffer_vld3_pad, uint, 32, 2);
+VECT_ARRAY_INIT3(buffer_vld3, uint, 64, 1);
+PAD(buffer_vld3_pad, uint, 64, 1);
+VECT_ARRAY_INIT3(buffer_vld3, poly, 8, 8);
+PAD(buffer_vld3_pad, poly, 8, 8);
+VECT_ARRAY_INIT3(buffer_vld3, poly, 16, 4);
+PAD(buffer_vld3_pad, poly, 16, 4);
+VECT_ARRAY_INIT3(buffer_vld3, float, 32, 2);
+PAD(buffer_vld3_pad, float, 32, 2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#ifdef __ARMCC_VERSION
+__fp16 buffer_vld3_float16x4x3[4*3] = {-16, -15, -14, -13, -12, -11, -10, -9,
+				       -8, -7, -6, -5};
+#else
+float16_t buffer_vld3_float16x4x3[4*3] = {0xcc00 /* -16 */, 0xcb80 /* -15 */,
+					  0xcb00 /* -14 */, 0xca80 /* -13 */,
+					  0xca00 /* -12 */, 0xc980 /* -11 */,
+					  0xc900 /* -10 */, 0xc880 /* -9 */,
+					  0xc800 /* -8 */, 0xc700 /* -7 */,
+					  0xc600 /* -6 */, 0xc500 /* -5 */};
+#endif
+PAD(buffer_vld3_pad, float, 16, 4);
+#endif
+VECT_ARRAY_INIT3(buffer_vld3, int, 8, 16);
+PAD(buffer_vld3_pad, int, 8, 16);
+VECT_ARRAY_INIT3(buffer_vld3, int, 16, 8);
+PAD(buffer_vld3_pad, int, 16, 8);
+VECT_ARRAY_INIT3(buffer_vld3, int, 32, 4);
+PAD(buffer_vld3_pad, int, 32, 4);
+VECT_ARRAY_INIT3(buffer_vld3, int, 64, 2);
+PAD(buffer_vld3_pad, int, 64, 2);
+VECT_ARRAY_INIT3(buffer_vld3, uint, 8, 16);
+PAD(buffer_vld3_pad, uint, 8, 16);
+VECT_ARRAY_INIT3(buffer_vld3, uint, 16, 8);
+PAD(buffer_vld3_pad, uint, 16, 8);
+VECT_ARRAY_INIT3(buffer_vld3, uint, 32, 4);
+PAD(buffer_vld3_pad, uint, 32, 4);
+VECT_ARRAY_INIT3(buffer_vld3, uint, 64, 2);
+PAD(buffer_vld3_pad, uint, 64, 2);
+VECT_ARRAY_INIT3(buffer_vld3, poly, 8, 16);
+PAD(buffer_vld3_pad, poly, 8, 16);
+VECT_ARRAY_INIT3(buffer_vld3, poly, 16, 8);
+PAD(buffer_vld3_pad, poly, 16, 8);
+VECT_ARRAY_INIT3(buffer_vld3, float, 32, 4);
+PAD(buffer_vld3_pad, float, 32, 4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#ifdef __ARMCC_VERSION
+__fp16 buffer_vld3_float16x8x3[8*3] = {-16, -15, -14, -13, -12, -11, -10, -9,
+				       -8, -7, -6, -5, -4, -3, -2, -1,
+				       0, 1, 2, 3, 4, 5, 6, 7};
+#else
+float16_t buffer_vld3_float16x8x3[8*3] = {0xcc00 /* -16 */, 0xcb80 /* -15 */,
+					  0xcb00 /* -14 */, 0xca80 /* -13 */,
+					  0xca00 /* -12 */, 0xc980 /* -11 */,
+					  0xc900 /* -10 */, 0xc880 /* -9 */,
+					  0xc800 /* -8 */, 0xc700 /* -7 */,
+					  0xc600 /* -6 */, 0xc500 /* -6 */,
+					  0xc400 /* -4 */, 0xc200 /* -3 */,
+					  0xc000 /* -2 */, 0xbc00 /* -1 */,
+					  0, 0x3c00 /* 1 */,
+					  0x4000 /* 2 */, 0x4200 /* 3 */,
+					  0x4400 /* 4 */, 0x4500 /* 5 */,
+					  0x4600 /* 6 */, 0x4700 /* 7 */};
+#endif
+PAD(buffer_vld3_pad, float, 16, 8);
+#endif
+
+/* Input buffers for vld4, 1 of each size */
+VECT_ARRAY_INIT4(buffer_vld4, int, 8, 8);
+PAD(buffer_vld4_pad, int, 8, 8);
+VECT_ARRAY_INIT4(buffer_vld4, int, 16, 4);
+PAD(buffer_vld4_pad, int, 16, 4);
+VECT_ARRAY_INIT4(buffer_vld4, int, 32, 2);
+PAD(buffer_vld4_pad, int, 32, 2);
+VECT_ARRAY_INIT4(buffer_vld4, int, 64, 1);
+PAD(buffer_vld4_pad, int, 64, 1);
+VECT_ARRAY_INIT4(buffer_vld4, uint, 8, 8);
+PAD(buffer_vld4_pad, uint, 8, 8);
+VECT_ARRAY_INIT4(buffer_vld4, uint, 16, 4);
+PAD(buffer_vld4_pad, uint, 16, 4);
+VECT_ARRAY_INIT4(buffer_vld4, uint, 32, 2);
+PAD(buffer_vld4_pad, uint, 32, 2);
+VECT_ARRAY_INIT4(buffer_vld4, uint, 64, 1);
+PAD(buffer_vld4_pad, uint, 64, 1);
+VECT_ARRAY_INIT4(buffer_vld4, poly, 8, 8);
+PAD(buffer_vld4_pad, poly, 8, 8);
+VECT_ARRAY_INIT4(buffer_vld4, poly, 16, 4);
+PAD(buffer_vld4_pad, poly, 16, 4);
+VECT_ARRAY_INIT4(buffer_vld4, float, 32, 2);
+PAD(buffer_vld4_pad, float, 32, 2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#ifdef __ARMCC_VERSION
+__fp16 buffer_vld4_float16x4x4[4*4] = {-16, -15, -14, -13, -12, -11, -10, -9,
+				       -8, -7, -6, -5, -4, -3, -2, -1};
+#else
+float16_t buffer_vld4_float16x4x4[4*4] = {0xcc00 /* -16 */, 0xcb80 /* -15 */,
+					  0xcb00 /* -14 */, 0xca80 /* -13 */,
+					  0xca00 /* -12 */, 0xc980 /* -11 */,
+					  0xc900 /* -10 */, 0xc880 /* -9 */,
+					  0xc800 /* -8 */, 0xc700 /* -7 */,
+					  0xc600 /* -6 */, 0xc500 /* -5 */,
+					  0xc400 /* -4 */, 0xc200 /* -3 */,
+					  0xc000 /* -2 */, 0xbc00 /* -1 */};
+#endif
+PAD(buffer_vld4_pad, float, 16, 4);
+#endif
+VECT_ARRAY_INIT4(buffer_vld4, int, 8, 16);
+PAD(buffer_vld4_pad, int, 8, 16);
+VECT_ARRAY_INIT4(buffer_vld4, int, 16, 8);
+PAD(buffer_vld4_pad, int, 16, 8);
+VECT_ARRAY_INIT4(buffer_vld4, int, 32, 4);
+PAD(buffer_vld4_pad, int, 32, 4);
+VECT_ARRAY_INIT4(buffer_vld4, int, 64, 2);
+PAD(buffer_vld4_pad, int, 64, 2);
+VECT_ARRAY_INIT4(buffer_vld4, uint, 8, 16);
+PAD(buffer_vld4_pad, uint, 8, 16);
+VECT_ARRAY_INIT4(buffer_vld4, uint, 16, 8);
+PAD(buffer_vld4_pad, uint, 16, 8);
+VECT_ARRAY_INIT4(buffer_vld4, uint, 32, 4);
+PAD(buffer_vld4_pad, uint, 32, 4);
+VECT_ARRAY_INIT4(buffer_vld4, uint, 64, 2);
+PAD(buffer_vld4_pad, uint, 64, 2);
+VECT_ARRAY_INIT4(buffer_vld4, poly, 8, 16);
+PAD(buffer_vld4_pad, poly, 8, 16);
+VECT_ARRAY_INIT4(buffer_vld4, poly, 16, 8);
+PAD(buffer_vld4_pad, poly, 16, 8);
+VECT_ARRAY_INIT4(buffer_vld4, float, 32, 4);
+PAD(buffer_vld4_pad, float, 32, 4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#ifdef __ARMCC_VERSION
+__fp16 buffer_vld4_float16x8x4[8*4] = {-16, -15, -14, -13, -12, -11, -10, -9,
+				       -8, -7, -6, -5, -4, -3, -2, -1,
+				       0, 1, 2, 3, 4, 5, 6, 7,
+				       8, 9, 10, 11, 12, 13, 14, 15};
+#else
+float16_t buffer_vld4_float16x8x4[8*4] = {0xcc00 /* -16 */, 0xcb80 /* -15 */,
+					  0xcb00 /* -14 */, 0xca80 /* -13 */,
+					  0xca00 /* -12 */, 0xc980 /* -11 */,
+					  0xc900 /* -10 */, 0xc880 /* -9 */,
+					  0xc800 /* -8 */, 0xc700 /* -7 */,
+					  0xc600 /* -6 */, 0xc500 /* -6 */,
+					  0xc400 /* -4 */, 0xc200 /* -3 */,
+					  0xc000 /* -2 */, 0xbc00 /* -1 */,
+					  0, 0x3c00 /* 1 */,
+					  0x4000 /* 2 */, 0x4200 /* 3 */,
+					  0x4400 /* 4 */, 0x4500 /* 5 */,
+					  0x4600 /* 6 */, 0x4700 /* 7 */,
+					  0x4800 /* 8 */, 0x4880 /* 9 */,
+					  0x4900 /* 10 */, 0x4980 /* 11 */,
+					  0x4a00 /* 12 */, 0x4a80 /* 13 */,
+					  0x4b00 /* 14 */, 0x04b80 /* 15 */};
+#endif
+PAD(buffer_vld4_pad, float, 16, 8);
+#endif
+
+/* Input buffers for vld2_lane */
+VECT_VAR_DECL_INIT(buffer_vld2_lane, int, 8, 2);
+VECT_VAR_DECL_INIT(buffer_vld2_lane, int, 16, 2);
+VECT_VAR_DECL_INIT(buffer_vld2_lane, int, 32, 2);
+VECT_VAR_DECL_INIT(buffer_vld2_lane, int, 64, 2);
+VECT_VAR_DECL_INIT(buffer_vld2_lane, uint, 8, 2);
+VECT_VAR_DECL_INIT(buffer_vld2_lane, uint, 16, 2);
+VECT_VAR_DECL_INIT(buffer_vld2_lane, uint, 32, 2);
+VECT_VAR_DECL_INIT(buffer_vld2_lane, uint, 64, 2);
+VECT_VAR_DECL_INIT(buffer_vld2_lane, poly, 8, 2);
+VECT_VAR_DECL_INIT(buffer_vld2_lane, poly, 16, 2);
+VECT_VAR_DECL_INIT(buffer_vld2_lane, float, 32, 2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#ifdef __ARMCC_VERSION
+__fp16 buffer_vld2_lane_float16x2[2] = {-16, -15};
+#else
+VECT_VAR_DECL(buffer_vld2_lane, float, 16, 2) [] = {0xcc00 /* -16 */,
+						    0xcb80 /* -15 */};
+#endif
+#endif
+
+/* Input buffers for vld3_lane */
+VECT_VAR_DECL_INIT(buffer_vld3_lane, int, 8, 3);
+VECT_VAR_DECL_INIT(buffer_vld3_lane, int, 16, 3);
+VECT_VAR_DECL_INIT(buffer_vld3_lane, int, 32, 3);
+VECT_VAR_DECL_INIT(buffer_vld3_lane, int, 64, 3);
+VECT_VAR_DECL_INIT(buffer_vld3_lane, uint, 8, 3);
+VECT_VAR_DECL_INIT(buffer_vld3_lane, uint, 16, 3);
+VECT_VAR_DECL_INIT(buffer_vld3_lane, uint, 32, 3);
+VECT_VAR_DECL_INIT(buffer_vld3_lane, uint, 64, 3);
+VECT_VAR_DECL_INIT(buffer_vld3_lane, poly, 8, 3);
+VECT_VAR_DECL_INIT(buffer_vld3_lane, poly, 16, 3);
+VECT_VAR_DECL_INIT(buffer_vld3_lane, float, 32, 3);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#ifdef __ARMCC_VERSION
+__fp16 buffer_vld3_lane_float16x3[3] = {-16, -15, -14};
+#else
+VECT_VAR_DECL(buffer_vld3_lane, float, 16, 3) [] = {0xcc00 /* -16 */,
+						    0xcb80 /* -15 */,
+						    0xcb00 /* -14 */};
+#endif
+#endif
+
+/* Input buffers for vld4_lane */
+VECT_VAR_DECL_INIT(buffer_vld4_lane, int, 8, 4);
+VECT_VAR_DECL_INIT(buffer_vld4_lane, int, 16, 4);
+VECT_VAR_DECL_INIT(buffer_vld4_lane, int, 32, 4);
+VECT_VAR_DECL_INIT(buffer_vld4_lane, int, 64, 4);
+VECT_VAR_DECL_INIT(buffer_vld4_lane, uint, 8, 4);
+VECT_VAR_DECL_INIT(buffer_vld4_lane, uint, 16, 4);
+VECT_VAR_DECL_INIT(buffer_vld4_lane, uint, 32, 4);
+VECT_VAR_DECL_INIT(buffer_vld4_lane, uint, 64, 4);
+VECT_VAR_DECL_INIT(buffer_vld4_lane, poly, 8, 4);
+VECT_VAR_DECL_INIT(buffer_vld4_lane, poly, 16, 4);
+VECT_VAR_DECL_INIT(buffer_vld4_lane, float, 32, 4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#ifdef __ARMCC_VERSION
+__fp16 buffer_vld4_lane_float16x4[4] = {-16, -15, -14, -13};
+#else
+VECT_VAR_DECL(buffer_vld4_lane, float, 16, 4) [] = {0xcc00 /* -16 */,
+						    0xcb80 /* -15 */,
+						    0xcb00 /* -14 */,
+						    0xca80 /* -13 */};
+#endif
+#endif
diff --git a/expected_input4gcc-nofp16.txt b/expected_input4gcc-nofp16.txt
new file mode 100644
index 0000000..fc2d581
--- /dev/null
+++ b/expected_input4gcc-nofp16.txt
@@ -0,0 +1,7087 @@
+
+VLD1/VLD1Q output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1600000, 0xc1500000 };
+
+VADD/VADDQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffec, 0xffed, 0xffee, 0xffef };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff3, 0xfffffff4 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x54 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xe, 0xf, 0x10, 0x11 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x18, 0x19 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xe6, 0xe7, 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffdc, 0xffdd, 0xffde, 0xffdf, 0xffe0, 0xffe1, 0xffe2, 0xffe3 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffd2, 0xffffffd3, 0xffffffd4, 0xffffffd5 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x8, 0x9 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xfc, 0xfd, 0xfe, 0xff, 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7, 0xfff8, 0xfff9, 0xfffa };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x27, 0x28, 0x29, 0x2a };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff3, 0xfffffffffffffff4 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x40d9999a, 0x40d9999a };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x41100000, 0x41100000, 0x41100000, 0x41100000 };
+
+VLD1_LANE/VLD1_LANEQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xf0, 0xaa };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xaaaaaaaa, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xf0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xaaaaaaaa, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xf0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xaaaaaaaa, 0xc1800000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xf0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xfffffff0, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xaaaaaaaaaaaaaaaa, 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xf0, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xfffffff0, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xaaaaaaaaaaaaaaaa };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xf0, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xc1800000, 0xaaaaaaaa };
+
+VLD1_DUP/VLD1_DUPQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1800000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff0, 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff0, 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1800000, 0xc1800000, 0xc1800000 };
+
+VLD1_DUP/VLD1_DUPQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1700000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff1, 0xfffffff1, 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff1, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff1, 0xfffffff1, 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff1, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1700000, 0xc1700000, 0xc1700000, 0xc1700000 };
+
+VLD1_DUP/VLD1_DUPQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xc1600000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff2, 0xfffffff2, 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff2, 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff2, 0xfffffff2, 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff2, 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1600000, 0xc1600000, 0xc1600000, 0xc1600000 };
+
+VDUP/VDUPQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1800000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff0, 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff0, 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1800000, 0xc1800000, 0xc1800000 };
+
+VDUP/VDUPQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1700000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff1, 0xfffffff1, 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff1, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff1, 0xfffffff1, 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff1, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1700000, 0xc1700000, 0xc1700000, 0xc1700000 };
+
+VDUP/VDUPQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xc1600000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff2, 0xfffffff2, 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff2, 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff2, 0xfffffff2, 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff2, 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1600000, 0xc1600000, 0xc1600000, 0xc1600000 };
+
+VMOV/VMOVQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1800000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff0, 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff0, 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1800000, 0xc1800000, 0xc1800000 };
+
+VMOV/VMOVQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1700000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff1, 0xfffffff1, 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff1, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff1, 0xfffffff1, 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff1, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1700000, 0xc1700000, 0xc1700000, 0xc1700000 };
+
+VMOV/VMOVQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xc1600000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff2, 0xfffffff2, 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff2, 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff2, 0xfffffff2, 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff2, 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1600000, 0xc1600000, 0xc1600000, 0xc1600000 };
+
+VGET_HIGH output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VGET_LOW output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQDMLAL_LANE output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7c1e, 0x7c1f, 0x7c20, 0x7c21 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7c1e, 0x7c1f };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQDMLAL_LANE (mul with input=0) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQDMLAL_LANE (check mul cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffef, 0x7ffffff0, 0x7ffffff1, 0x7ffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7fffffffffffffef, 0x7ffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQDMLSL_LANE output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffff83c2, 0xffff83c3, 0xffff83c4, 0xffff83c5 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffff83c2, 0xffffffffffff83c3 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQDMLSL_LANE (mul with input=0) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQDMLSL_LANE (check mul cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x8000000000000000, 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQDMLAL_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x1684, 0x1685, 0x1686, 0x1687 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x21ce, 0x21cf };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQDMLAL_N (check mul cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffef, 0x7ffffff0, 0x7ffffff1, 0x7ffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7fffffffffffffef, 0x7ffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQDMLSL_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffe95c, 0xffffe95d, 0xffffe95e, 0xffffe95f };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffde12, 0xffffffffffffde13 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQDMLSL_N (check mul cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x8000000000000000, 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VEXT/VEXTQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf7, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff3, 0x22, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff1, 0x33 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf6, 0xf7, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff2, 0xfff3, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff1, 0x77 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf6, 0xf7, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff2, 0xfff3, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1700000, 0x42066666 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xfe, 0xff, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff7, 0x22, 0x22, 0x22, 0x22, 0x22, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff3, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff1, 0x44 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xfc, 0xfd, 0xfe, 0xff, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff6, 0xfff7, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff3, 0x77, 0x77, 0x77 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff1, 0x88 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xfc, 0xfd, 0xfe, 0xff, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff6, 0xfff7, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1500000, 0x4204cccd, 0x4204cccd, 0x4204cccd };
+
+VSHR_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffc, 0xfffffffc };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x3c, 0x3c, 0x3c, 0x3c, 0x3d, 0x3d, 0x3d, 0x3d };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x1ffe, 0x1ffe, 0x1ffe, 0x1ffe };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x7ffffff, 0x7ffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x7fffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf8, 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb, 0xfc, 0xfc, 0xfd, 0xfd, 0xfe, 0xfe, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffffc, 0xfffffffc, 0xfffffffc, 0xfffffffc };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x3c, 0x3c, 0x3c, 0x3c, 0x3d, 0x3d, 0x3d, 0x3d, 0x3e, 0x3e, 0x3e, 0x3e, 0x3f, 0x3f, 0x3f, 0x3f };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1ffe, 0x1ffe, 0x1ffe, 0x1ffe, 0x1ffe, 0x1ffe, 0x1ffe, 0x1ffe };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x7ffffff, 0x7ffffff, 0x7ffffff, 0x7ffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VSHRN_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff8, 0xfff8, 0xfff9, 0xfff9 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffc, 0xfffffffc };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xfc, 0xfc, 0xfc, 0xfc, 0xfd, 0xfd, 0xfd, 0xfd };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfffe, 0xfffe, 0xfffe, 0xfffe };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffffe, 0xfffffffe };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSHRN_N (with input = 0) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSHRN_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb, 0xfc };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff8, 0xfff9, 0xfff9, 0xfffa };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffc, 0xfffffffc };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xfc, 0xfc, 0xfd, 0xfd, 0xfd, 0xfd, 0xfe, 0xfe };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfffe, 0xfffe, 0xfffe, 0xfffe };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffffe, 0xfffffffe };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSHRN_N (with large shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQRSHRN_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb, 0xfc };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff8, 0xfff9, 0xfff9, 0xfffa };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffc, 0xfffffffc };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQRSHRN_N (check saturation: shift by 3) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQRSHRN_N (check saturation: shift by max) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VSET_LANE/VSET_LANEQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0x11 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0x22 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0x33 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x44 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0x55, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0x66, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0x77 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x88 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0x55, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0x66, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0x4204cccd };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0x99 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xaa, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xbb };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xcc };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xdd, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xee, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xff, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0x11 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xdd, 0xff };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xee, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1600000, 0x41333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQSUB/VQSUBQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xdf, 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffce, 0xffcf, 0xffd0, 0xffd1 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xffffffbd, 0xffffffbe };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffffac };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, 0xa0, 0xa1, 0xa2 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xff8a, 0xff8b, 0xff8c, 0xff8d };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffff79, 0xffffff7a };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffff68 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xdf, 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffce, 0xffcf, 0xffd0, 0xffd1, 0xffd2, 0xffd3, 0xffd4, 0xffd5 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffbd, 0xffffffbe, 0xffffffbf, 0xffffffc0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffac, 0xffffffffffffffad };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, 0xa8, 0xa9, 0xaa };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xff8a, 0xff8b, 0xff8c, 0xff8d, 0xff8e, 0xff8f, 0xff90, 0xff91 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffff79, 0xffffff7a, 0xffffff7b, 0xffffff7c };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffff68, 0xffffffffffffff69 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffffac };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffff68 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffac, 0xffffffffffffffad };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffff68, 0xffffffffffffff69 };
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7fffffffffffffff, 0x7fffffffffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+
+VQDMULH output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+
+VQDMULH output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+
+VQDMULH_LANE output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+
+VQDMULH_LANE (check mul cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+
+VQDMULH_N output:
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x19, 0x19, 0x19, 0x19 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x4, 0x4 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xa, 0xa, 0xa, 0xa };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+
+VQDMULH_N (check mul cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+
+VQDMULL output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x200, 0x1c2, 0x188, 0x152 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x200, 0x1c2 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+
+VQDMULL (check mul cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7fffffffffffffff, 0x7fffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQDMLAL output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7c1e, 0x7c1f, 0x7c20, 0x7c21 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7c1e, 0x7c1f };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQDMLAL (check mul cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffef, 0x7ffffff0, 0x7ffffff1, 0x7ffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7fffffffffffffef, 0x7ffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQDMLSL output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffff83c2, 0xffff83c3, 0xffff83c4, 0xffff83c5 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffff83c2, 0xffffffffffff83c3 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQDMLSL (check mul cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x8000000000000000, 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VCEQ/VCEQQ output:
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xff, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0xff, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xff, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0xff, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0xff, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0xff, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VCGE/VCGEQ output:
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+
+VCLE/VCLEQ output:
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+
+VCGT/VCGTQ output:
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+
+VCLT/VCLTQ output:
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+
+VBSL/VBSLQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf6, 0xf6, 0xf6, 0xf6 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff0, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffffd };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf3, 0xf3, 0xf3, 0xf3, 0xf7, 0xf7, 0xf7, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff0, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffff1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf3, 0xf3, 0xf3, 0xf3, 0xf7, 0xf7, 0xf7, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff0, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800004, 0xc1700004 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf6, 0xf6, 0xf6, 0xf6, 0xf2, 0xf2, 0xf2, 0xf2, 0xf6, 0xf6, 0xf6, 0xf6 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff0, 0xfff2, 0xfff2, 0xfff4, 0xfff4, 0xfff6, 0xfff6 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff0, 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffffd, 0xfffffffffffffffd };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf3, 0xf3, 0xf3, 0xf3, 0xf7, 0xf7, 0xf7, 0xf7, 0xf3, 0xf3, 0xf3, 0xf3, 0xf7, 0xf7, 0xf7, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff0, 0xfff2, 0xfff2, 0xfff4, 0xfff4, 0xfff6, 0xfff6 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff0, 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf3, 0xf3, 0xf3, 0xf3, 0xf7, 0xf7, 0xf7, 0xf7, 0xf3, 0xf3, 0xf3, 0xf3, 0xf7, 0xf7, 0xf7, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff0, 0xfff2, 0xfff2, 0xfff4, 0xfff4, 0xfff6, 0xfff6 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800001, 0xc1700001, 0xc1600001, 0xc1500001 };
+
+VSHL/VSHLQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xe0, 0xe2, 0xe4, 0xe6, 0xe8, 0xea, 0xec, 0xee };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xff80, 0xff88, 0xff90, 0xff98 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffff000, 0xfffff100 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffff80 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xe0, 0xe2, 0xe4, 0xe6, 0xe8, 0xea, 0xec, 0xee };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xff80, 0xff88, 0xff90, 0xff98 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffff000, 0xfffff100 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffff80 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x20, 0x40, 0x60, 0x80, 0xa0, 0xc0, 0xe0, 0x0, 0x20, 0x40, 0x60, 0x80, 0xa0, 0xc0, 0xe0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x1000, 0x2000, 0x3000, 0x4000, 0x5000, 0x6000, 0x7000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x40000000, 0x80000000, 0xc0000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x20, 0x40, 0x60, 0x80, 0xa0, 0xc0, 0xe0, 0x0, 0x20, 0x40, 0x60, 0x80, 0xa0, 0xc0, 0xe0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x1000, 0x2000, 0x3000, 0x4000, 0x5000, 0x6000, 0x7000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x40000000, 0x80000000, 0xc0000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VSHL/VSHLQ (large shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VSHL/VSHLQ (negative shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff8, 0xfff8, 0xfff9, 0xfff9 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffc, 0xfffffffc };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x78, 0x78, 0x79, 0x79, 0x7a, 0x7a, 0x7b, 0x7b };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x7ff8, 0x7ff8, 0x7ff9, 0x7ff9 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x3ffffffc, 0x3ffffffc };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xfc, 0xfc, 0xfc, 0xfc, 0xfd, 0xfd, 0xfd, 0xfd, 0xfe, 0xfe, 0xfe, 0xfe, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffffe, 0xfffffffe, 0xfffffffe, 0xfffffffe };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x3c, 0x3c, 0x3c, 0x3c, 0x3d, 0x3d, 0x3d, 0x3d, 0x3e, 0x3e, 0x3e, 0x3e, 0x3f, 0x3f, 0x3f, 0x3f };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x7ff, 0x7ff, 0x7ff, 0x7ff, 0x7ff, 0x7ff, 0x7ff, 0x7ff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1ffffffe, 0x1ffffffe, 0x1ffffffe, 0x1ffffffe };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x7ffffffffffffff, 0x7ffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VSHL_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xe0, 0xe2, 0xe4, 0xe6, 0xe8, 0xea, 0xec, 0xee };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffe0, 0xffe2, 0xffe4, 0xffe6 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xffffff80, 0xffffff88 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffffc0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xc0, 0xc4, 0xc8, 0xcc, 0xd0, 0xd4, 0xd8, 0xdc };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xff00, 0xff10, 0xff20, 0xff30 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffff80, 0xffffff88 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffe0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x20, 0x40, 0x60, 0x80, 0xa0, 0xc0, 0xe0, 0x0, 0x20, 0x40, 0x60, 0x80, 0xa0, 0xc0, 0xe0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffe0, 0xffe2, 0xffe4, 0xffe6, 0xffe8, 0xffea, 0xffec, 0xffee };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffc0, 0xffffffc4, 0xffffffc8, 0xffffffcc };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffc0, 0xffffffffffffffc4 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xc0, 0xc4, 0xc8, 0xcc, 0xd0, 0xd4, 0xd8, 0xdc, 0xe0, 0xe4, 0xe8, 0xec, 0xf0, 0xf4, 0xf8, 0xfc };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xff80, 0xff88, 0xff90, 0xff98, 0xffa0, 0xffa8, 0xffb0, 0xffb8 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffc0, 0xffffffc4, 0xffffffc8, 0xffffffcc };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffe0, 0xffffffffffffffe2 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQSHL/VQSHLQ (with input = 0) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQSHL/VQSHLQ (input 0 and negative shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQSHL/VQSHLQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xe0, 0xe2, 0xe4, 0xe6, 0xe8, 0xea, 0xec, 0xee };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xff80, 0xff88, 0xff90, 0xff98 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffff000, 0xfffff100 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffffe };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x1ffffffffffffffe };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x8000000000000000, 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQSHL/VQSHLQ (negative shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfffc, 0xfffc, 0xfffc, 0xfffc };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffe, 0xfffffffe };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x78, 0x78, 0x79, 0x79, 0x7a, 0x7a, 0x7b, 0x7b };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3ffc, 0x3ffc, 0x3ffc, 0x3ffc };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x1ffffffe, 0x1ffffffe };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1f, 0x1f, 0x1f, 0x1f, 0x1f, 0x1f, 0x1f, 0x1f };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x7ffff, 0x7ffff, 0x7ffff, 0x7ffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffff, 0xfffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQSHL/VQSHLQ (large shift amount, negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x8000000000000000, 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQSHL/VQSHLQ (check cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3fff, 0x3fff, 0x3fff, 0x3fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x3fffffff, 0x3fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3fffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x7fffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3fff, 0x3fff, 0x3fff, 0x3fff, 0x3fff, 0x3fff, 0x3fff, 0x3fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x3fffffff, 0x3fffffff, 0x3fffffff, 0x3fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3fffffffffffffff, 0x3fffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x7fffffffffffffff, 0x7fffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQSHL/VQSHLQ (large shift amount, positive input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x7fffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7fffffffffffffff, 0x7fffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQSHL/VQSHLQ (check saturation on 64 bits) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7fffffffffffffff, 0x7fffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQSHL_N/VQSHLQ_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xc0, 0xc4, 0xc8, 0xcc, 0xd0, 0xd4, 0xd8, 0xdc };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffe0, 0xffe2, 0xffe4, 0xffe6 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xffffffe0, 0xffffffe2 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffffc0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xc0, 0xc4, 0xc8, 0xcc, 0xd0, 0xd4, 0xd8, 0xdc, 0xe0, 0xe4, 0xe8, 0xec, 0xf0, 0xf4, 0xf8, 0xfc };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffe0, 0xffe2, 0xffe4, 0xffe6, 0xffe8, 0xffea, 0xffec, 0xffee };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffe0, 0xffffffe2, 0xffffffe4, 0xffffffe6 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffc0, 0xffffffffffffffc4 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQSHL_N/VQSHLQ_N (check saturation with large positive input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x7fffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7fffffffffffffff, 0x7fffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSHL/VRSHLQ (with input = 0) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSHL/VRSHLQ (input 0 and negative shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSHL/VRSHLQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xe0, 0xe2, 0xe4, 0xe6, 0xe8, 0xea, 0xec, 0xee };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xff80, 0xff88, 0xff90, 0xff98 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffff000, 0xfffff100 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffffe };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xe0, 0xe2, 0xe4, 0xe6, 0xe8, 0xea, 0xec, 0xee };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xff80, 0xff88, 0xff90, 0xff98 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffff000, 0xfffff100 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x1ffffffffffffffe };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x1000, 0x2000, 0x3000, 0x4000, 0x5000, 0x6000, 0x7000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x1000, 0x2000, 0x3000, 0x4000, 0x5000, 0x6000, 0x7000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSHL/VRSHLQ (negative shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb, 0xfc };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfffc, 0xfffc, 0xfffd, 0xfffd };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffe, 0xfffffffe };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x78, 0x79, 0x79, 0x7a, 0x7a, 0x7b, 0x7b, 0x7c };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3ffc, 0x3ffc, 0x3ffd, 0x3ffd };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x1ffffffe, 0x1ffffffe };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x80000, 0x80000, 0x80000, 0x80000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x100000000000, 0x100000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSHL/VRSHLQ (checking round_const overflow: shift by -1) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x4000, 0x4000, 0x4000, 0x4000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x40000000, 0x40000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x4000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x4000, 0x4000, 0x4000, 0x4000, 0x4000, 0x4000, 0x4000, 0x4000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x40000000, 0x40000000, 0x40000000, 0x40000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x4000000000000000, 0x4000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x8000000000000000, 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSHL/VRSHLQ (checking round_const overflow: shift by -3) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x1000, 0x1000, 0x1000, 0x1000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x10000000, 0x10000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x1000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x2000, 0x2000, 0x2000, 0x2000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x20000000, 0x20000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x2000000000000000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x1000, 0x1000, 0x1000, 0x1000, 0x1000, 0x1000, 0x1000, 0x1000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x10000000, 0x10000000, 0x10000000, 0x10000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x1000000000000000, 0x1000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x20000000, 0x20000000, 0x20000000, 0x20000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x2000000000000000, 0x2000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSHL/VRSHLQ (checking negative shift amount as large as input vector width) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSHL/VRSHLQ (large shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSHL/VRSHLQ (large negative shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VLD2/VLD2Q chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1600000, 0xc1500000 };
+
+VLD2/VLD2Q chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb, 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff4, 0xfffffff5, 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb, 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff4, 0xfffffff5, 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb, 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1400000, 0xc1300000, 0xc1200000, 0xc1100000 };
+
+VLD3/VLD3Q chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1600000, 0xc1500000 };
+
+VLD3/VLD3Q chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb, 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff4, 0xfffffff5, 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb, 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff4, 0xfffffff5, 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb, 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1400000, 0xc1300000, 0xc1200000, 0xc1100000 };
+
+VLD3/VLD3Q chunk 2 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff4, 0xfffffff5 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff4, 0xfffffff5 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1400000, 0xc1300000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff8, 0xfffffff9, 0xfffffffa, 0xfffffffb };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff8, 0xfffffff9, 0xfffffffa, 0xfffffffb };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1000000, 0xc0e00000, 0xc0c00000, 0xc0a00000 };
+
+VLD4/VLD4Q chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1600000, 0xc1500000 };
+
+VLD4/VLD4Q chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb, 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff4, 0xfffffff5, 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb, 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff4, 0xfffffff5, 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb, 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1400000, 0xc1300000, 0xc1200000, 0xc1100000 };
+
+VLD4/VLD4Q chunk 2 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff4, 0xfffffff5 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff4, 0xfffffff5 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1400000, 0xc1300000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff8, 0xfffffff9, 0xfffffffa, 0xfffffffb };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff8, 0xfffffff9, 0xfffffffa, 0xfffffffb };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1000000, 0xc0e00000, 0xc0c00000, 0xc0a00000 };
+
+VLD4/VLD4Q chunk 3 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff3 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff3 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1200000, 0xc1100000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffffc, 0xfffffffd, 0xfffffffe, 0xffffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffffc, 0xfffffffd, 0xfffffffe, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc0800000, 0xc0400000, 0xc0000000, 0xbf800000 };
+
+VDUP_LANE/VDUP_LANEQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf7, 0xf7, 0xf7, 0xf7, 0xf7, 0xf7, 0xf7, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff3, 0xfff3, 0xfff3, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf7, 0xf7, 0xf7, 0xf7, 0xf7, 0xf7, 0xf7, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff3, 0xfff3, 0xfff3, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1700000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff3, 0xfff3, 0xfff3, 0xfff3, 0xfff3, 0xfff3, 0xfff3, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff1, 0xfffffff1, 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff0, 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1700000, 0xc1700000, 0xc1700000, 0xc1700000 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+
+VQDMULL_LANE output:
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x4000, 0x4000 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7fffffffffffffff, 0x7fffffffffffffff };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+
+VQDMULL_N output:
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x44000, 0x44000, 0x44000, 0x44000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xaa000, 0xaa000 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7fffffffffffffff, 0x7fffffffffffffff };
+
+VST1_LANE/VST1_LANEQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf7, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff3, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff1, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf6, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff2, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf6, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff2, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1700000, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xff, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff5, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff1, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff1, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xfa, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff4, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff3, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xfa, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff4, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1700000, 0x33333333, 0x33333333, 0x33333333 };
+
+VSUB/VSUBQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xee, 0xef, 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xffffffed, 0xffffffee };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffff8c };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xdc, 0xdd, 0xde, 0xdf, 0xe0, 0xe1, 0xe2, 0xe3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffd2, 0xffd3, 0xffd4, 0xffd5 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffc8, 0xffffffc9 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffee };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xe, 0xf, 0x10, 0x11 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffd8, 0xffffffffffffffd9 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xe4, 0xe5, 0xe6, 0xe7, 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffed, 0xffee, 0xffef, 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffb9, 0xffffffba, 0xffffffbb, 0xffffffbc };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffed, 0xffffffffffffffee };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc00ccccd, 0xc00ccccd };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc00ccccc, 0xc00ccccc, 0xc00ccccc, 0xc00ccccc };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQADD/VQADDQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x12, 0x13, 0x14, 0x15 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x23, 0x24 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x34 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf, 0x10 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x23, 0x24, 0x25, 0x26 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x34, 0x35 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x34 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x34, 0x35 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7fffffffffffffff, 0x7fffffffffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+
+VABS/VABSQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x10, 0xf, 0xe, 0xd };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x10, 0xf };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9, 0x8, 0x7, 0x6, 0x5, 0x4, 0x3, 0x2, 0x1 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x10, 0xf, 0xe, 0xd };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x40133333, 0x40133333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x4059999a, 0x4059999a, 0x4059999a, 0x4059999a };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+
+VQABS/VQABSQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x10, 0xf, 0xe, 0xd };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x10, 0xf };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9, 0x8, 0x7, 0x6, 0x5, 0x4, 0x3, 0x2, 0x1 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x10, 0xf, 0xe, 0xd };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+
+VQABS/VQABSQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VCOMBINE output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0x22, 0x22, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0x44 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0x66, 0x66, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0x77, 0x77 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0x88 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0x66, 0x66, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0x40533333, 0x40533333 };
+
+VMAX/VMAXQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf3, 0xf3, 0xf3, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf3, 0xf3, 0xf3, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff1, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1780000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf4, 0xf4, 0xf4, 0xf4, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff3, 0xfff3, 0xfff3, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff1, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf9, 0xf9, 0xf9, 0xf9, 0xf9, 0xf9, 0xf9, 0xf9, 0xf9, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff1, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1680000, 0xc1680000, 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x7fc00000, 0x7fc00000, 0x7fc00000, 0x7fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x7fc00000, 0x7fc00000, 0x7fc00000, 0x7fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x7f800000, 0x7f800000, 0x7f800000, 0x7f800000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+
+VMIN/VMINQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf3, 0xf3, 0xf3, 0xf3 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf3, 0xf3, 0xf3, 0xf3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1780000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf4, 0xf4, 0xf4, 0xf4, 0xf4, 0xf4, 0xf4, 0xf4, 0xf4, 0xf4, 0xf4 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff3, 0xfff3, 0xfff3, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xf9, 0xf9, 0xf9, 0xf9, 0xf9, 0xf9 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1680000, 0xc1680000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x7fc00000, 0x7fc00000, 0x7fc00000, 0x7fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x7fc00000, 0x7fc00000, 0x7fc00000, 0x7fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xff800000, 0xff800000, 0xff800000, 0xff800000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+
+VNEG/VNEGQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x10, 0xf, 0xe, 0xd };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x10, 0xf };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9, 0x8, 0x7, 0x6, 0x5, 0x4, 0x3, 0x2, 0x1 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x10, 0xf, 0xe, 0xd };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc0133333, 0xc0133333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc059999a, 0xc059999a, 0xc059999a, 0xc059999a };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+
+VQNEG/VQNEGQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x10, 0xf, 0xe, 0xd };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x10, 0xf };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9, 0x8, 0x7, 0x6, 0x5, 0x4, 0x3, 0x2, 0x1 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x10, 0xf, 0xe, 0xd };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+
+VQNEG/VQNEGQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VMLAL output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xe907, 0xe908, 0xe909, 0xe90a, 0xe90b, 0xe90c, 0xe90d, 0xe90e };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3e07, 0x3e08 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a, 0x3e0b, 0x3e0c, 0x3e0d, 0x3e0e };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3e07, 0x3e08 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VMLSL output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x16d9, 0x16da, 0x16db, 0x16dc, 0x16dd, 0x16de, 0x16df, 0x16e0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffc1d9, 0xffffc1da, 0xffffc1db, 0xffffc1dc };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffc1d9, 0xffffffffffffc1da };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xc1d9, 0xc1da, 0xc1db, 0xc1dc, 0xc1dd, 0xc1de, 0xc1df, 0xc1e0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffc1d9, 0xffffc1da, 0xffffc1db, 0xffffc1dc };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffc1d9, 0xffffffffffffc1da };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VMLAL_LANE output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3e07, 0x3e08 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3e07, 0x3e08 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VMLSL_LANE output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffc1d9, 0xffffc1da, 0xffffc1db, 0xffffc1dc };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffc1d9, 0xffffffffffffc1da };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffc1d9, 0xffffc1da, 0xffffc1db, 0xffffc1dc };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffc1d9, 0xffffffffffffc1da };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VMLAL_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x595, 0x596, 0x597, 0x598 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xb3a, 0xb3b };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x10df, 0x10e0, 0x10e1, 0x10e2 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x10df, 0x10e0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VMLSL_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffa4b, 0xfffffa4c, 0xfffffa4d, 0xfffffa4e };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffff4a6, 0xfffffffffffff4a7 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffef01, 0xffffef02, 0xffffef03, 0xffffef04 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffef01, 0xffffffffffffef02 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VMOVL output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VMOVN output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VMULL output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x100, 0xe1, 0xc4, 0xa9, 0x90, 0x79, 0x64, 0x51 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x100, 0xe1, 0xc4, 0xa9 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x100, 0xe1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xe100, 0xe2e1, 0xe4c4, 0xe6a9, 0xe890, 0xea79, 0xec64, 0xee51 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffe00100, 0xffe200e1, 0xffe400c4, 0xffe600a9 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffe000000100, 0xffffffe2000000e1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x5500, 0x5501, 0x5504, 0x5505, 0x5510, 0x5511, 0x5514, 0x5515 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VMULL_LANE output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x4000, 0x4000, 0x4000, 0x4000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x2000, 0x2000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x4000, 0x4000, 0x4000, 0x4000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x2000, 0x2000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VREV16 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf1, 0xf0, 0xf3, 0xf2, 0xf5, 0xf4, 0xf7, 0xf6 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf1, 0xf0, 0xf3, 0xf2, 0xf5, 0xf4, 0xf7, 0xf6 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf1, 0xf0, 0xf3, 0xf2, 0xf5, 0xf4, 0xf7, 0xf6 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf1, 0xf0, 0xf3, 0xf2, 0xf5, 0xf4, 0xf7, 0xf6, 0xf9, 0xf8, 0xfb, 0xfa, 0xfd, 0xfc, 0xff, 0xfe };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf1, 0xf0, 0xf3, 0xf2, 0xf5, 0xf4, 0xf7, 0xf6, 0xf9, 0xf8, 0xfb, 0xfa, 0xfd, 0xfc, 0xff, 0xfe };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf1, 0xf0, 0xf3, 0xf2, 0xf5, 0xf4, 0xf7, 0xf6, 0xf9, 0xf8, 0xfb, 0xfa, 0xfd, 0xfc, 0xff, 0xfe };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VREV32 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf3, 0xf2, 0xf1, 0xf0, 0xf7, 0xf6, 0xf5, 0xf4 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff1, 0xfff0, 0xfff3, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf3, 0xf2, 0xf1, 0xf0, 0xf7, 0xf6, 0xf5, 0xf4 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff1, 0xfff0, 0xfff3, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf3, 0xf2, 0xf1, 0xf0, 0xf7, 0xf6, 0xf5, 0xf4 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff1, 0xfff0, 0xfff3, 0xfff2 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf3, 0xf2, 0xf1, 0xf0, 0xf7, 0xf6, 0xf5, 0xf4, 0xfb, 0xfa, 0xf9, 0xf8, 0xff, 0xfe, 0xfd, 0xfc };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff1, 0xfff0, 0xfff3, 0xfff2, 0xfff5, 0xfff4, 0xfff7, 0xfff6 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf3, 0xf2, 0xf1, 0xf0, 0xf7, 0xf6, 0xf5, 0xf4, 0xfb, 0xfa, 0xf9, 0xf8, 0xff, 0xfe, 0xfd, 0xfc };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff1, 0xfff0, 0xfff3, 0xfff2, 0xfff5, 0xfff4, 0xfff7, 0xfff6 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf3, 0xf2, 0xf1, 0xf0, 0xf7, 0xf6, 0xf5, 0xf4, 0xfb, 0xfa, 0xf9, 0xf8, 0xff, 0xfe, 0xfd, 0xfc };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff1, 0xfff0, 0xfff3, 0xfff2, 0xfff5, 0xfff4, 0xfff7, 0xfff6 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VREV64 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf7, 0xf6, 0xf5, 0xf4, 0xf3, 0xf2, 0xf1, 0xf0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff3, 0xfff2, 0xfff1, 0xfff0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff1, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf7, 0xf6, 0xf5, 0xf4, 0xf3, 0xf2, 0xf1, 0xf0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff3, 0xfff2, 0xfff1, 0xfff0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff1, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf7, 0xf6, 0xf5, 0xf4, 0xf3, 0xf2, 0xf1, 0xf0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff3, 0xfff2, 0xfff1, 0xfff0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1700000, 0xc1800000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf7, 0xf6, 0xf5, 0xf4, 0xf3, 0xf2, 0xf1, 0xf0, 0xff, 0xfe, 0xfd, 0xfc, 0xfb, 0xfa, 0xf9, 0xf8 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff3, 0xfff2, 0xfff1, 0xfff0, 0xfff7, 0xfff6, 0xfff5, 0xfff4 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff1, 0xfffffff0, 0xfffffff3, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf7, 0xf6, 0xf5, 0xf4, 0xf3, 0xf2, 0xf1, 0xf0, 0xff, 0xfe, 0xfd, 0xfc, 0xfb, 0xfa, 0xf9, 0xf8 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff3, 0xfff2, 0xfff1, 0xfff0, 0xfff7, 0xfff6, 0xfff5, 0xfff4 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff1, 0xfffffff0, 0xfffffff3, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf7, 0xf6, 0xf5, 0xf4, 0xf3, 0xf2, 0xf1, 0xf0, 0xff, 0xfe, 0xfd, 0xfc, 0xfb, 0xfa, 0xf9, 0xf8 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff3, 0xfff2, 0xfff1, 0xfff0, 0xfff7, 0xfff6, 0xfff5, 0xfff4 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1700000, 0xc1800000, 0xc1500000, 0xc1600000 };
+
+VSRA_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffc, 0xfffffffd };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff3, 0xfffffff4 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffffc, 0xfffffffd, 0xfffffffe, 0xffffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf, 0x10, 0x11, 0x12, 0x13, 0x14 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfffc, 0xfffd, 0xfffe, 0xffff, 0x0, 0x1, 0x2, 0x3 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff3, 0xfffffff4, 0xfffffff5, 0xfffffff6 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VTRN/VTRNQ chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0x11, 0x11, 0xf2, 0xf3, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0x55, 0x55, 0xf2, 0xf3, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0x55, 0x55, 0xf2, 0xf3, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0x11, 0x11, 0xf2, 0xf3, 0x11, 0x11, 0xf4, 0xf5, 0x11, 0x11, 0xf6, 0xf7, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0x22, 0x22, 0xfff2, 0xfff3, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0x55, 0x55, 0xf2, 0xf3, 0x55, 0x55, 0xf4, 0xf5, 0x55, 0x55, 0xf6, 0xf7, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0x66, 0x66, 0xfff2, 0xfff3, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0x77, 0x77 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf1, 0x55, 0x55, 0xf2, 0xf3, 0x55, 0x55, 0xf4, 0xf5, 0x55, 0x55, 0xf6, 0xf7, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0x66, 0x66, 0xfff2, 0xfff3, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0x42073333, 0x42073333 };
+
+VTRN/VTRNQ chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf4, 0xf5, 0x11, 0x11, 0xf6, 0xf7, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff2, 0xfff3, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf4, 0xf5, 0x55, 0x55, 0xf6, 0xf7, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff2, 0xfff3, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x77, 0x77 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf4, 0xf5, 0x55, 0x55, 0xf6, 0xf7, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff2, 0xfff3, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x42066666, 0x42066666 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf8, 0xf9, 0x11, 0x11, 0xfa, 0xfb, 0x11, 0x11, 0xfc, 0xfd, 0x11, 0x11, 0xfe, 0xff, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff4, 0xfff5, 0x22, 0x22, 0xfff6, 0xfff7, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff2, 0xfffffff3, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf8, 0xf9, 0x55, 0x55, 0xfa, 0xfb, 0x55, 0x55, 0xfc, 0xfd, 0x55, 0x55, 0xfe, 0xff, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff4, 0xfff5, 0x66, 0x66, 0xfff6, 0xfff7, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff2, 0xfffffff3, 0x77, 0x77 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf8, 0xf9, 0x55, 0x55, 0xfa, 0xfb, 0x55, 0x55, 0xfc, 0xfd, 0x55, 0x55, 0xfe, 0xff, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff4, 0xfff5, 0x66, 0x66, 0xfff6, 0xfff7, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1600000, 0xc1500000, 0x42073333, 0x42073333 };
+
+VUZP/VUZPQ chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1600000, 0xc1500000 };
+
+VUZP/VUZPQ chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x22, 0x22, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x66, 0x66, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x77, 0x77 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x66, 0x66, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x42066666, 0x42066666 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x22, 0x22, 0x22, 0x22, 0x22, 0x22, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x77, 0x77, 0x77, 0x77 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x42073333, 0x42073333, 0x42073333, 0x42073333 };
+
+VZIP/VZIPQ chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf4, 0x11, 0x11, 0xf1, 0xf5, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff2, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf4, 0x55, 0x55, 0xf1, 0xf5, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff2, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf4, 0x55, 0x55, 0xf1, 0xf5, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff2, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf8, 0x11, 0x11, 0xf1, 0xf9, 0x11, 0x11, 0xf2, 0xfa, 0x11, 0x11, 0xf3, 0xfb, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff4, 0x22, 0x22, 0xfff1, 0xfff5, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff2, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf8, 0x55, 0x55, 0xf1, 0xf9, 0x55, 0x55, 0xf2, 0xfa, 0x55, 0x55, 0xf3, 0xfb, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff4, 0x66, 0x66, 0xfff1, 0xfff5, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff2, 0x77, 0x77 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf8, 0x55, 0x55, 0xf1, 0xf9, 0x55, 0x55, 0xf2, 0xfa, 0x55, 0x55, 0xf3, 0xfb, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff4, 0x66, 0x66, 0xfff1, 0xfff5, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1600000, 0x42073333, 0x42073333 };
+
+VZIP/VZIPQ chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf2, 0xf6, 0x11, 0x11, 0xf3, 0xf7, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff1, 0xfff3, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf2, 0xf6, 0x55, 0x55, 0xf3, 0xf7, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff1, 0xfff3, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x77, 0x77 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf2, 0xf6, 0x55, 0x55, 0xf3, 0xf7, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff1, 0xfff3, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x42066666, 0x42066666 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf4, 0xfc, 0x11, 0x11, 0xf5, 0xfd, 0x11, 0x11, 0xf6, 0xfe, 0x11, 0x11, 0xf7, 0xff, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff2, 0xfff6, 0x22, 0x22, 0xfff3, 0xfff7, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff1, 0xfffffff3, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf4, 0xfc, 0x55, 0x55, 0xf5, 0xfd, 0x55, 0x55, 0xf6, 0xfe, 0x55, 0x55, 0xf7, 0xff, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff2, 0xfff6, 0x66, 0x66, 0xfff3, 0xfff7, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff1, 0xfffffff3, 0x77, 0x77 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf4, 0xfc, 0x55, 0x55, 0xf5, 0xfd, 0x55, 0x55, 0xf6, 0xfe, 0x55, 0x55, 0xf7, 0xff, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff2, 0xfff6, 0x66, 0x66, 0xfff3, 0xfff7, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1700000, 0xc1500000, 0x42073333, 0x42073333 };
+
+VREINTERPRET/VREINTERPRETQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff };
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff };
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xffff, 0xfff1, 0xffff };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xffff, 0xfff1, 0xffff };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xf3f2f1f0, 0xf7f6f5f4 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfff1fff0, 0xfff3fff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xffffffff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xf3f2f1f0, 0xf7f6f5f4 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfff1fff0, 0xfff3fff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xffffffff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xf3f2f1f0, 0xf7f6f5f4 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfff1fff0, 0xfff3fff2 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xf7f6f5f4f3f2f1f0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfff3fff2fff1fff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffff1fffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xf7f6f5f4f3f2f1f0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfff3fff2fff1fff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffff1fffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xf7f6f5f4f3f2f1f0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfff3fff2fff1fff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xffff, 0xfff1, 0xffff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xffff, 0xfff1, 0xffff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xf3f2f1f0, 0xf7f6f5f4 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfff1fff0, 0xfff3fff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xf3f2f1f0, 0xf7f6f5f4 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfff1fff0, 0xfff3fff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xf3f2f1f0, 0xf7f6f5f4 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfff1fff0, 0xfff3fff2 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xf7f6f5f4f3f2f1f0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfff3fff2fff1fff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffff1fffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xf7f6f5f4f3f2f1f0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfff3fff2fff1fff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffff1fffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xf7f6f5f4f3f2f1f0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfff3fff2fff1fff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xffff, 0xfff1, 0xffff };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xffff, 0xfff1, 0xffff };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff, 0xf4, 0xff, 0xf5, 0xff, 0xf6, 0xff, 0xf7, 0xff };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff, 0xf2, 0xff, 0xff, 0xff, 0xf3, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff, 0xf4, 0xff, 0xf5, 0xff, 0xf6, 0xff, 0xf7, 0xff };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff, 0xf2, 0xff, 0xff, 0xff, 0xf3, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff, 0xf4, 0xff, 0xf5, 0xff, 0xf6, 0xff, 0xf7, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6, 0xf9f8, 0xfbfa, 0xfdfc, 0xfffe };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xffff, 0xfff1, 0xffff, 0xfff2, 0xffff, 0xfff3, 0xffff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xffff, 0xffff, 0xffff, 0xfff1, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6, 0xf9f8, 0xfbfa, 0xfdfc, 0xfffe };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xffff, 0xfff1, 0xffff, 0xfff2, 0xffff, 0xfff3, 0xffff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xffff, 0xffff, 0xffff, 0xfff1, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6, 0xf9f8, 0xfbfa, 0xfdfc, 0xfffe };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xf3f2f1f0, 0xf7f6f5f4, 0xfbfaf9f8, 0xfffefdfc };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfff1fff0, 0xfff3fff2, 0xfff5fff4, 0xfff7fff6 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xffffffff, 0xfffffff1, 0xffffffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xf3f2f1f0, 0xf7f6f5f4, 0xfbfaf9f8, 0xfffefdfc };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfff1fff0, 0xfff3fff2, 0xfff5fff4, 0xfff7fff6 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xffffffff, 0xfffffff1, 0xffffffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xf3f2f1f0, 0xf7f6f5f4, 0xfbfaf9f8, 0xfffefdfc };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfff1fff0, 0xfff3fff2, 0xfff5fff4, 0xfff7fff6 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xf7f6f5f4f3f2f1f0, 0xfffefdfcfbfaf9f8 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfff3fff2fff1fff0, 0xfff7fff6fff5fff4 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffff1fffffff0, 0xfffffff3fffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xf7f6f5f4f3f2f1f0, 0xfffefdfcfbfaf9f8 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfff3fff2fff1fff0, 0xfff7fff6fff5fff4 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffff1fffffff0, 0xfffffff3fffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xf7f6f5f4f3f2f1f0, 0xfffefdfcfbfaf9f8 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfff3fff2fff1fff0, 0xfff7fff6fff5fff4 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6, 0xf9f8, 0xfbfa, 0xfdfc, 0xfffe };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xffff, 0xfff1, 0xffff, 0xfff2, 0xffff, 0xfff3, 0xffff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xffff, 0xffff, 0xffff, 0xfff1, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6, 0xf9f8, 0xfbfa, 0xfdfc, 0xfffe };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xffff, 0xfff1, 0xffff, 0xfff2, 0xffff, 0xfff3, 0xffff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xffff, 0xffff, 0xffff, 0xfff1, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6, 0xf9f8, 0xfbfa, 0xfdfc, 0xfffe };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xf3f2f1f0, 0xf7f6f5f4, 0xfbfaf9f8, 0xfffefdfc };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfff1fff0, 0xfff3fff2, 0xfff5fff4, 0xfff7fff6 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xffffffff, 0xfffffff1, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xf3f2f1f0, 0xf7f6f5f4, 0xfbfaf9f8, 0xfffefdfc };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfff1fff0, 0xfff3fff2, 0xfff5fff4, 0xfff7fff6 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xffffffff, 0xfffffff1, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xf3f2f1f0, 0xf7f6f5f4, 0xfbfaf9f8, 0xfffefdfc };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfff1fff0, 0xfff3fff2, 0xfff5fff4, 0xfff7fff6 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xf7f6f5f4f3f2f1f0, 0xfffefdfcfbfaf9f8 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfff3fff2fff1fff0, 0xfff7fff6fff5fff4 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffff1fffffff0, 0xfffffff3fffffff2 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xf7f6f5f4f3f2f1f0, 0xfffefdfcfbfaf9f8 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfff3fff2fff1fff0, 0xfff7fff6fff5fff4 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffff1fffffff0, 0xfffffff3fffffff2 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xf7f6f5f4f3f2f1f0, 0xfffefdfcfbfaf9f8 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfff3fff2fff1fff0, 0xfff7fff6fff5fff4 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff, 0xf4, 0xff, 0xf5, 0xff, 0xf6, 0xff, 0xf7, 0xff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff, 0xf2, 0xff, 0xff, 0xff, 0xf3, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff, 0xf4, 0xff, 0xf5, 0xff, 0xf6, 0xff, 0xf7, 0xff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff, 0xf2, 0xff, 0xff, 0xff, 0xf3, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff, 0xf4, 0xff, 0xf5, 0xff, 0xf6, 0xff, 0xf7, 0xff };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xf3f2f1f0, 0xf7f6f5f4 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xfff1fff0, 0xfff3fff2 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xfffffff0, 0xffffffff };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xf3f2f1f0, 0xf7f6f5f4 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xfff1fff0, 0xfff3fff2 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xfffffff0, 0xffffffff };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xf3f2f1f0, 0xf7f6f5f4 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xfff1fff0, 0xfff3fff2 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xf3f2f1f0, 0xf7f6f5f4, 0xfbfaf9f8, 0xfffefdfc };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xfff1fff0, 0xfff3fff2, 0xfff5fff4, 0xfff7fff6 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xfffffff0, 0xffffffff, 0xfffffff1, 0xffffffff };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xf3f2f1f0, 0xf7f6f5f4, 0xfbfaf9f8, 0xfffefdfc };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xfff1fff0, 0xfff3fff2, 0xfff5fff4, 0xfff7fff6 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xfffffff0, 0xffffffff, 0xfffffff1, 0xffffffff };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xf3f2f1f0, 0xf7f6f5f4, 0xfbfaf9f8, 0xfffefdfc };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xfff1fff0, 0xfff3fff2, 0xfff5fff4, 0xfff7fff6 };
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x80, 0xc1, 0x0, 0x0, 0x70, 0xc1 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0xc180, 0x0, 0xc170 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xc1700000c1800000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x80, 0xc1, 0x0, 0x0, 0x70, 0xc1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0xc180, 0x0, 0xc170 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xc1700000c1800000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x0, 0x0, 0x80, 0xc1, 0x0, 0x0, 0x70, 0xc1 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x0, 0xc180, 0x0, 0xc170 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x80, 0xc1, 0x0, 0x0, 0x70, 0xc1, 0x0, 0x0, 0x60, 0xc1, 0x0, 0x0, 0x50, 0xc1 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0xc180, 0x0, 0xc170, 0x0, 0xc160, 0x0, 0xc150 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xc1700000c1800000, 0xc1500000c1600000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x80, 0xc1, 0x0, 0x0, 0x70, 0xc1, 0x0, 0x0, 0x60, 0xc1, 0x0, 0x0, 0x50, 0xc1 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0xc180, 0x0, 0xc170, 0x0, 0xc160, 0x0, 0xc150 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xc1700000c1800000, 0xc1500000c1600000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x0, 0x0, 0x80, 0xc1, 0x0, 0x0, 0x70, 0xc1, 0x0, 0x0, 0x60, 0xc1, 0x0, 0x0, 0x50, 0xc1 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x0, 0xc180, 0x0, 0xc170, 0x0, 0xc160, 0x0, 0xc150 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+
+VQRDMULH output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff5, 0xfff6, 0xfff7, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+
+VQRDMULH (check mul cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+
+VQRDMULH (check rounding cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+
+VQRDMULH_LANE output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+
+VQRDMULH_LANE (check mul cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+
+VQRDMULH_LANE (check rounding cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+
+VQRDMULH_N output:
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfffc, 0xfffc, 0xfffc, 0xfffd };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffe, 0xfffffffe };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x6, 0x6, 0x6, 0x5, 0x5, 0x4, 0x4, 0x4 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffffe, 0xfffffffe, 0xfffffffe, 0xfffffffe };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+
+VQRDMULH_N (check mul cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+
+VQRDMULH_N (check rounding cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQRSHL/VQRSHLQ (with input = 0) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQRSHL/VQRSHLQ (input 0 and negative shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQRSHL/VQRSHLQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xe0, 0xe2, 0xe4, 0xe6, 0xe8, 0xea, 0xec, 0xee };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xff80, 0xff88, 0xff90, 0xff98 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffff000, 0xfffff100 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffff80 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x8000000000000000, 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQRSHL/VQRSHLQ (negative shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xfc, 0xfc, 0xfd, 0xfd, 0xfd, 0xfd, 0xfe, 0xfe };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfffc, 0xfffc, 0xfffd, 0xfffd };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffe, 0xfffffffe };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x3c, 0x3c, 0x3d, 0x3d, 0x3d, 0x3d, 0x3e, 0x3e };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3ffc, 0x3ffc, 0x3ffd, 0x3ffd };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x1ffffffe, 0x1ffffffe };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x80000, 0x80000, 0x80000, 0x80000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x100000000000, 0x100000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: shift by -1) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x4000, 0x4000, 0x4000, 0x4000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x40000000, 0x40000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x4000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x4000, 0x4000, 0x4000, 0x4000, 0x4000, 0x4000, 0x4000, 0x4000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x40000000, 0x40000000, 0x40000000, 0x40000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x4000000000000000, 0x4000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x8000000000000000, 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: shift by -3) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x1000, 0x1000, 0x1000, 0x1000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x10000000, 0x10000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x1000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x2000, 0x2000, 0x2000, 0x2000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x20000000, 0x20000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x2000000000000000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x1000, 0x1000, 0x1000, 0x1000, 0x1000, 0x1000, 0x1000, 0x1000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x10000000, 0x10000000, 0x10000000, 0x10000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x1000000000000000, 0x1000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x20000000, 0x20000000, 0x20000000, 0x20000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x2000000000000000, 0x2000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x7fffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7fffffffffffffff, 0x7fffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large shift amount with negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x8000000000000000, 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large negative shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large shift amount with 0 input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VABA/VABAQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x16, 0x17, 0x18, 0x19 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x20, 0x21 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5a };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x907, 0x908, 0x909, 0x90a };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffe7, 0xffffffe8 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x5e, 0x5f, 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xb9c, 0xb9d, 0xb9e, 0xb9f, 0xba0, 0xba1, 0xba2, 0xba3 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x26e0, 0x26e1, 0x26e2, 0x26e3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff9, 0xfffa, 0xfffb, 0xfffc, 0xfffd, 0xfffe, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VABAL output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff6, 0xfff7, 0xfff8, 0xfff9, 0xfffa, 0xfffb, 0xfffc, 0xfffd };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x16, 0x17, 0x18, 0x19 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x20, 0x21 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5a };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x907, 0x908, 0x909, 0x90a };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffe7, 0xffffffe8 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VABAL test intermediate overflow output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xef, 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffef, 0xfff0, 0xfff1, 0xfff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffef, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xee, 0xef, 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffe2, 0xffe3, 0xffe4, 0xffe5 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffe7, 0xffffffe8 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VABD/VABDQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x11, 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3, 0x2, 0x1, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x18, 0x17 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xef, 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffe3, 0xffe4, 0xffe5, 0xffe6 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffe8, 0xffffffe9 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x41c26666, 0x41ba6666 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x1a, 0x19, 0x18, 0x17, 0x16, 0x15, 0x14, 0x13, 0x12, 0x11, 0x10, 0xf, 0xe, 0xd, 0xc, 0xb };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x4, 0x3, 0x2, 0x1, 0x0, 0x1, 0x2, 0x3 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x30, 0x2f, 0x2e, 0x2d };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xe6, 0xe7, 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffe4, 0xffe5, 0xffe6, 0xffe7, 0xffe8, 0xffe9, 0xffea, 0xffeb };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffd0, 0xffffffd1, 0xffffffd2, 0xffffffd3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x42407ae1, 0x423c7ae1, 0x42387ae1, 0x42347ae1 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+
+VABDL output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x11, 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x3, 0x2, 0x1, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x18, 0x17 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xef, 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffe3, 0xffe4, 0xffe5, 0xffe6 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffe8, 0xffffffe9 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VAND/VANDQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x2, 0x2, 0x0, 0x0, 0x2, 0x2 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x60 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x10, 0x10, 0x10, 0x10, 0x14, 0x14, 0x14, 0x14 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x10, 0x10, 0x12, 0x12 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf0, 0xf2, 0xf2, 0xf4, 0xf4, 0xf6, 0xf6, 0xf0, 0xf0, 0xf2, 0xf2, 0xf4, 0xf4, 0xf6, 0xf6 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffe0, 0xffe0, 0xffe0, 0xffe0, 0xffe4, 0xffe4, 0xffe4, 0xffe4 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffe0, 0xffffffe0, 0xffffffe2, 0xffffffe2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x10, 0x10 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x4, 0x4, 0x4, 0x4, 0x8, 0x8, 0x8, 0x8, 0xc, 0xc, 0xc, 0xc };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x0, 0x1, 0x2, 0x3 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x30, 0x31, 0x32, 0x33 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VORR/VORRQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf2, 0xf3, 0xf2, 0xf3, 0xf6, 0xf7, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff3, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff4 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf4, 0xf5, 0xf6, 0xf7, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfffe, 0xffff, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff8, 0xfffffff9 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf6, 0xf7, 0xf6, 0xf7, 0xf6, 0xf7, 0xf6, 0xf7, 0xfe, 0xff, 0xfe, 0xff, 0xfe, 0xff, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfffc, 0xfffd, 0xfffe, 0xffff, 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff2, 0xfffffff3, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff8, 0xfffffffffffffff9 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xfc, 0xfd, 0xfe, 0xff, 0xfc, 0xfd, 0xfe, 0xff, 0xfc, 0xfd, 0xfe, 0xff, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff3, 0xfff3, 0xfff3, 0xfff3, 0xfff7, 0xfff7, 0xfff7, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff7, 0xfffffff7, 0xfffffff7, 0xfffffff7 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff3, 0xfffffffffffffff3 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VORN/VORNQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xfd, 0xfd, 0xff, 0xff, 0xfd, 0xfd, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff3, 0xfff3, 0xfff3, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffc, 0xfffffffd };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffffb };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xfb, 0xfb, 0xfb, 0xfb, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff1, 0xfff1, 0xfff3, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff7, 0xfffffff7 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffffd };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf9, 0xf9, 0xfb, 0xfb, 0xfd, 0xfd, 0xff, 0xff, 0xf9, 0xf9, 0xfb, 0xfb, 0xfd, 0xfd, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff3, 0xfff3, 0xfff3, 0xfff3, 0xfff7, 0xfff7, 0xfff7, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffffd, 0xfffffffd, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff7, 0xfffffffffffffff7 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf3, 0xf3, 0xf3, 0xf3, 0xf7, 0xf7, 0xf7, 0xf7, 0xfb, 0xfb, 0xfb, 0xfb, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfffc, 0xfffd, 0xfffe, 0xffff, 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff8, 0xfffffff9, 0xfffffffa, 0xfffffffb };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffffc, 0xfffffffffffffffd };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VEOR/VEORQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf2, 0xf3, 0xf0, 0xf1, 0xf6, 0xf7, 0xf4, 0xf5 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff3, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffff94 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xe4, 0xe5, 0xe6, 0xe7, 0xe0, 0xe1, 0xe2, 0xe3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffee, 0xffef, 0xffec, 0xffed };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffd8, 0xffffffd9 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x6, 0x7, 0x4, 0x5, 0x2, 0x3, 0x0, 0x1, 0xe, 0xf, 0xc, 0xd, 0xa, 0xb, 0x8, 0x9 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x1c, 0x1d, 0x1e, 0x1f, 0x18, 0x19, 0x1a, 0x1b };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x12, 0x13, 0x10, 0x11 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffe8, 0xffffffffffffffe9 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xfc, 0xfd, 0xfe, 0xff, 0xf8, 0xf9, 0xfa, 0xfb, 0xf4, 0xf5, 0xf6, 0xf7, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff3, 0xfff2, 0xfff1, 0xfff0, 0xfff7, 0xfff6, 0xfff5, 0xfff4 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffc7, 0xffffffc6, 0xffffffc5, 0xffffffc4 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff3, 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VBIC/VBICQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf0, 0xf1, 0xf4, 0xf5, 0xf4, 0xf5 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x1, 0x2, 0x3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffff90 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xe0, 0xe1, 0xe2, 0xe3, 0xe0, 0xe1, 0xe2, 0xe3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffe0, 0xffe1, 0xffe0, 0xffe1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffd0, 0xffffffd1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x1, 0x0, 0x1, 0x0, 0x1, 0x0, 0x1, 0x8, 0x9, 0x8, 0x9, 0x8, 0x9, 0x8, 0x9 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x10, 0x11, 0x12, 0x13, 0x10, 0x11, 0x12, 0x13 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x10, 0x11, 0x10, 0x11 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffe0, 0xffffffffffffffe1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff4, 0xfff4, 0xfff4, 0xfff4 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffc0, 0xffffffc0, 0xffffffc0, 0xffffffc0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VCREATE output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xde, 0xbc, 0x9a, 0x78, 0x56, 0x34, 0x12 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xdef0, 0x9abc, 0x5678, 0x1234 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x9abcdef0, 0x12345678 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x123456789abcdef0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xde, 0xbc, 0x9a, 0x78, 0x56, 0x34, 0x12 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xdef0, 0x9abc, 0x5678, 0x1234 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x9abcdef0, 0x12345678 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x123456789abcdef0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xde, 0xbc, 0x9a, 0x78, 0x56, 0x34, 0x12 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xdef0, 0x9abc, 0x5678, 0x1234 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x9abcdef0, 0x12345678 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VLD2_LANE/VLD2Q_LANE chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+
+VLD2_LANE/VLD2Q_LANE chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xf0, 0xf1 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0, 0xfff1, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xfff0, 0xfff1, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xfff0, 0xfff1, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0xaaaaaaaa, 0xaaaaaaaa };
+
+VLD3_LANE/VLD3Q_LANE chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+
+VLD3_LANE/VLD3Q_LANE chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xf0, 0xf1, 0xf2, 0xaa };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xaaaaaaaa, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xf0, 0xf1, 0xf2, 0xaa };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xc1800000, 0xc1700000 };
+
+VLD3_LANE/VLD3Q_LANE chunk 2 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xf0, 0xf1, 0xf2 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff2, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xaaaa, 0xfff0, 0xfff1, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff1, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xaaaa, 0xfff0, 0xfff1, 0xfff2 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xfff0, 0xfff1, 0xfff2, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff2, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff1, 0xfff2, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff1, 0xfff2, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1600000, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+
+VLD4_LANE/VLD4Q_LANE chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+
+VLD4_LANE/VLD4Q_LANE chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+
+VLD4_LANE/VLD4Q_LANE chunk 2 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1600000, 0xc1500000 };
+
+VLD4_LANE/VLD4Q_LANE chunk 3 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+
+VLD2_DUP/VLD2Q_DUP chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf0, 0xf1, 0xf0, 0xf1, 0xf0, 0xf1 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf0, 0xf1, 0xf0, 0xf1, 0xf0, 0xf1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf0, 0xf1, 0xf0, 0xf1, 0xf0, 0xf1 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VLD2_DUP/VLD2Q_DUP chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf0, 0xf1, 0xf0, 0xf1, 0xf0, 0xf1 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf0, 0xf1, 0xf0, 0xf1, 0xf0, 0xf1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf0, 0xf1, 0xf0, 0xf1, 0xf0, 0xf1 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VLD3_DUP/VLD3Q_DUP chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf0, 0xf1, 0xf2, 0xf0, 0xf1 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf0, 0xf1, 0xf2, 0xf0, 0xf1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf0, 0xf1, 0xf2, 0xf0, 0xf1 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VLD3_DUP/VLD3Q_DUP chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf2, 0xf0, 0xf1, 0xf2, 0xf0, 0xf1, 0xf2, 0xf0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff1, 0xfff2, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf2, 0xf0, 0xf1, 0xf2, 0xf0, 0xf1, 0xf2, 0xf0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff1, 0xfff2, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf2, 0xf0, 0xf1, 0xf2, 0xf0, 0xf1, 0xf2, 0xf0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff1, 0xfff2, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xc1800000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VLD3_DUP/VLD3Q_DUP chunk 2 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf1, 0xf2, 0xf0, 0xf1, 0xf2, 0xf0, 0xf1, 0xf2 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff2, 0xfff0, 0xfff1, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff1, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf1, 0xf2, 0xf0, 0xf1, 0xf2, 0xf0, 0xf1, 0xf2 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff2, 0xfff0, 0xfff1, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff1, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf1, 0xf2, 0xf0, 0xf1, 0xf2, 0xf0, 0xf1, 0xf2 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff2, 0xfff0, 0xfff1, 0xfff2 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1700000, 0xc1600000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VLD4_DUP/VLD4Q_DUP chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VLD4_DUP/VLD4Q_DUP chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VLD4_DUP/VLD4Q_DUP chunk 2 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VLD4_DUP/VLD4Q_DUP chunk 3 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff3 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff3 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VMLA output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xdf, 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x1f8c, 0x1f8d, 0x1f8e, 0x1f8f };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x2bf7, 0x2bf8 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x43ac, 0x43ad };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x43a14e76, 0x43a1ce76 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf, 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x4830, 0x4831, 0x4832, 0x4833, 0x4834, 0x4835, 0x4836, 0x4837 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x470f, 0x4710, 0x4711, 0x4712 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xac, 0xad, 0xae, 0xaf, 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, 0xb8, 0xb9, 0xba, 0xbb };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a, 0x3e0b, 0x3e0c, 0x3e0d, 0x3e0e };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x3620, 0x3621, 0x3622, 0x3623 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x45f0ae15, 0x45f0b615, 0x45f0be15, 0x45f0c615 };
+
+VMLS output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xe054, 0xe055, 0xe056, 0xe057 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xffffd3e9, 0xffffd3ea };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xc1d9, 0xc1da, 0xc1db, 0xc1dc };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffbc34, 0xffffbc35 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc3b14e76, 0xc3b0ce76 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, 0xe0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xb7b0, 0xb7b1, 0xb7b2, 0xb7b3, 0xb7b4, 0xb7b5, 0xb7b6, 0xb7b7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffb8d1, 0xffffb8d2, 0xffffb8d3, 0xffffb8d4 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, 0x40, 0x41, 0x42, 0x43 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xc1d9, 0xc1da, 0xc1db, 0xc1dc, 0xc1dd, 0xc1de, 0xc1df, 0xc1e0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffc9c0, 0xffffc9c1, 0xffffc9c2, 0xffffc9c3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc5f1ae15, 0xc5f1a615, 0xc5f19e15, 0xc5f19615 };
+
+VMUL output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0x1, 0x12, 0x23, 0x34, 0x45, 0x56, 0x67 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfde0, 0xfe02, 0xfe24, 0xfe46 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffcd0, 0xfffffd03 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xc0, 0x4, 0x48, 0x8c, 0xd0, 0x14, 0x58, 0x9c };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfab0, 0xfb05, 0xfb5a, 0xfbaf };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffff9a0, 0xfffffa06 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xc0, 0x84, 0x48, 0xc, 0xd0, 0x94, 0x58, 0x1c };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc4053333, 0xc3f9c000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x90, 0x7, 0x7e, 0xf5, 0x6c, 0xe3, 0x5a, 0xd1, 0x48, 0xbf, 0x36, 0xad, 0x24, 0x9b, 0x12, 0x89 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xf780, 0xf808, 0xf890, 0xf918, 0xf9a0, 0xfa28, 0xfab0, 0xfb38 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffff670, 0xfffff709, 0xfffff7a2, 0xfffff83b };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x60, 0xa, 0xb4, 0x5e, 0x8, 0xb2, 0x5c, 0x6, 0xb0, 0x5a, 0x4, 0xae, 0x58, 0x2, 0xac, 0x56 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xf450, 0xf50b, 0xf5c6, 0xf681, 0xf73c, 0xf7f7, 0xf8b2, 0xf96d };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffff340, 0xfffff40c, 0xfffff4d8, 0xfffff5a4 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x60, 0xca, 0x34, 0x9e, 0xc8, 0x62, 0x9c, 0x36, 0x30, 0x9a, 0x64, 0xce, 0x98, 0x32, 0xcc, 0x66 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc4c73333, 0xc4bac000, 0xc4ae4ccd, 0xc4a1d999 };
+
+VMUL_LANE output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffc0, 0xffc4, 0xffc8, 0xffcc };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffde0, 0xfffffe02 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xbbc0, 0xc004, 0xc448, 0xc88c };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffface0, 0xffffb212 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc3b66666, 0xc3ab0000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffc0, 0xffc4, 0xffc8, 0xffcc, 0xffd0, 0xffd4, 0xffd8, 0xffdc };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffde0, 0xfffffe02, 0xfffffe24, 0xfffffe46 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xbbc0, 0xc004, 0xc448, 0xc88c, 0xccd0, 0xd114, 0xd558, 0xd99c };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffface0, 0xffffb212, 0xffffb744, 0xffffbc76 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc3b66666, 0xc3ab0000, 0xc39f9999, 0xc3943333 };
+
+VMUL_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfef0, 0xff01, 0xff12, 0xff23 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffde0, 0xfffffe02 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfcd0, 0xfd03, 0xfd36, 0xfd69 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffbc0, 0xfffffc04 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc3b26666, 0xc3a74000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfab0, 0xfb05, 0xfb5a, 0xfbaf, 0xfc04, 0xfc59, 0xfcae, 0xfd03 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffff9a0, 0xfffffa06, 0xfffffa6c, 0xfffffad2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xf890, 0xf907, 0xf97e, 0xf9f5, 0xfa6c, 0xfae3, 0xfb5a, 0xfbd1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffff780, 0xfffff808, 0xfffff890, 0xfffff918 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc4b1cccd, 0xc4a6b000, 0xc49b9333, 0xc4907667 };
+
+VMULL_N output:
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x11000, 0x11000, 0x11000, 0x11000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x22000, 0x22000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33000, 0x33000, 0x33000, 0x33000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x44000, 0x44000 };
+
+VMLA_LANE output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x3e07, 0x3e08 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x3e07, 0x3e08 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x4418c687, 0x44190687 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a, 0x3e0b, 0x3e0c, 0x3e0d, 0x3e0e };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a, 0x3e0b, 0x3e0c, 0x3e0d, 0x3e0e };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x441a3168, 0x441a7168, 0x441ab168, 0x441af168 };
+
+VMLS_LANE output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xc1d9, 0xc1da, 0xc1db, 0xc1dc };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xffffc1d9, 0xffffc1da };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xc1d9, 0xc1da, 0xc1db, 0xc1dc };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffc1d9, 0xffffc1da };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc420c687, 0xc4208687 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xc1d9, 0xc1da, 0xc1db, 0xc1dc, 0xc1dd, 0xc1de, 0xc1df, 0xc1e0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffc1d9, 0xffffc1da, 0xffffc1db, 0xffffc1dc };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xc1d9, 0xc1da, 0xc1db, 0xc1dc, 0xc1dd, 0xc1de, 0xc1df, 0xc1e0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffc1d9, 0xffffc1da, 0xffffc1db, 0xffffc1dc };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc4223168, 0xc421f168, 0xc421b168, 0xc4217168 };
+
+VMLA_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x595, 0x596, 0x597, 0x598 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xb3a, 0xb3b };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x10df, 0x10e0, 0x10e1, 0x10e2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x1684, 0x1685 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x4497deb8, 0x4497feb8 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x1c29, 0x1c2a, 0x1c2b, 0x1c2c, 0x1c2d, 0x1c2e, 0x1c2f, 0x1c30 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x21ce, 0x21cf, 0x21d0, 0x21d1 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x2773, 0x2774, 0x2775, 0x2776, 0x2777, 0x2778, 0x2779, 0x277a };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x2d18, 0x2d19, 0x2d1a, 0x2d1b };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x4568087b, 0x4568187b, 0x4568287b, 0x4568387b };
+
+VMLS_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfa4b, 0xfa4c, 0xfa4d, 0xfa4e };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffff4a6, 0xfffff4a7 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xef01, 0xef02, 0xef03, 0xef04 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffe95c, 0xffffe95d };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc49bdeb8, 0xc49bbeb8 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xe3b7, 0xe3b8, 0xe3b9, 0xe3ba, 0xe3bb, 0xe3bc, 0xe3bd, 0xe3be };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffde12, 0xffffde13, 0xffffde14, 0xffffde15 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xd86d, 0xd86e, 0xd86f, 0xd870, 0xd871, 0xd872, 0xd873, 0xd874 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffd2c8, 0xffffd2c9, 0xffffd2ca, 0xffffd2cb };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc56a087b, 0xc569f87b, 0xc569e87b, 0xc569d87b };
+
+VSLI_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffe0, 0xffe1, 0xffe2, 0xffe3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x6, 0x7 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x64fffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x50, 0x51, 0x52, 0x53, 0x50, 0x51, 0x52, 0x53 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x7bf0, 0x7bf1, 0x7bf2, 0x7bf3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x3ffffff0, 0x3ffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x10 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x50, 0x51, 0x52, 0x53, 0x50, 0x51, 0x52, 0x53 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x7bf0, 0x7bf1, 0x7bf2, 0x7bf3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xff60, 0xff61, 0xff62, 0xff63, 0xff64, 0xff65, 0xff66, 0xff67 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfe2ffff0, 0xfe2ffff1, 0xfe2ffff2, 0xfe2ffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x18fff0, 0x18fff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3ff0, 0x3ff1, 0x3ff2, 0x3ff3, 0x3ff4, 0x3ff5, 0x3ff6, 0x3ff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1bfffff0, 0x1bfffff1, 0x1bfffff2, 0x1bfffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x7ffffffffffff0, 0x7ffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3ff0, 0x3ff1, 0x3ff2, 0x3ff3, 0x3ff4, 0x3ff5, 0x3ff6, 0x3ff7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VSLI_Nmax shift amount output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7ff0, 0x7ff1, 0x7ff2, 0x7ff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x7ffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x7ff0, 0x7ff1, 0x7ff2, 0x7ff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x7ffffff0, 0x7ffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x7ffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x7ff0, 0x7ff1, 0x7ff2, 0x7ff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7ff0, 0x7ff1, 0x7ff2, 0x7ff3, 0x7ff4, 0x7ff5, 0x7ff6, 0x7ff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7ffffff0, 0x7ffffff1, 0x7ffffff2, 0x7ffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7ffffffffffffff0, 0x7ffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VSRI_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x80000001, 0x80000001 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffff00000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xc5, 0xc5, 0xc5, 0xc5, 0xc5, 0xc5, 0xc5, 0xc5 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffc0, 0xffc0, 0xffc0, 0xffc0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xe000000000000000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xc5, 0xc5, 0xc5, 0xc5, 0xc5, 0xc5, 0xc5, 0xc5 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xffc0, 0xffc0, 0xffc0, 0xffc0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf7, 0xf7, 0xf7, 0xf7, 0xf7, 0xf7, 0xf7, 0xf7, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0xfffd };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffff000000000000, 0xffff000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffe00, 0xfffffe00, 0xfffffe00, 0xfffffe00 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffff800, 0xfffffffffffff800 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VSRI_N max shift amount output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VTST/VTSTQ (signed input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0xffff, 0x0, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0xffff, 0x0, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0xffffffff, 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VTST/VTSTQ (unsigned input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0xffff, 0x0, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0xffff, 0x0, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0xffffffff, 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VADDHN output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x32, 0x32, 0x32, 0x32, 0x32, 0x32, 0x32, 0x32 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x32, 0x32, 0x32, 0x32 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x18, 0x18 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x37, 0x37, 0x37, 0x37 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x3, 0x3 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRADDHN output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x19, 0x19 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x4, 0x4, 0x4, 0x4, 0x4, 0x4, 0x4, 0x4 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x38, 0x38, 0x38, 0x38 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x4, 0x4 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VADDL output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffe3, 0xffe4, 0xffe5, 0xffe6, 0xffe7, 0xffe8, 0xffe9, 0xffea };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffe2, 0xffffffe3, 0xffffffe4, 0xffffffe5 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffe0, 0xffffffffffffffe1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1e3, 0x1e4, 0x1e5, 0x1e6, 0x1e7, 0x1e8, 0x1e9, 0x1ea };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1ffe1, 0x1ffe2, 0x1ffe3, 0x1ffe4 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x1ffffffe0, 0x1ffffffe1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VADDW output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffe3, 0xffe4, 0xffe5, 0xffe6, 0xffe7, 0xffe8, 0xffe9, 0xffea };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffe2, 0xffffffe3, 0xffffffe4, 0xffffffe5 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffe0, 0xffffffffffffffe1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, 0xe8, 0xe9, 0xea };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffe1, 0xffe2, 0xffe3, 0xffe4 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffe0, 0xffffffe1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VHADD/VHADDQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf1, 0xf2, 0xf2, 0xf3, 0xf3, 0xf4, 0xf4, 0xf5 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff1, 0xfff1, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf1, 0xf2, 0xf2, 0xf3, 0xf3, 0xf4, 0xf4, 0xf5 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff1, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf2, 0xf2, 0xf3, 0xf3, 0xf4, 0xf4, 0xf5, 0xf5, 0xf6, 0xf6, 0xf7, 0xf7, 0xf8, 0xf8, 0xf9, 0xf9 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff1, 0xfff2, 0xfff2, 0xfff3, 0xfff3, 0xfff4, 0xfff4, 0xfff5 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff1, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf4, 0xf5, 0xf5, 0xf6, 0xf6, 0xf7, 0xf7, 0xf8, 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb, 0xfc };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff1, 0xfff1, 0xfff2, 0xfff2, 0xfff3, 0xfff3, 0xfff4, 0xfff4 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff1, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRHADD/VRHADDQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf2, 0xf2, 0xf3, 0xf3, 0xf4, 0xf4, 0xf5, 0xf5 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff1, 0xfff2, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf2, 0xf2, 0xf3, 0xf3, 0xf4, 0xf4, 0xf5, 0xf5 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff1, 0xfff1, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf2, 0xf3, 0xf3, 0xf4, 0xf4, 0xf5, 0xf5, 0xf6, 0xf6, 0xf7, 0xf7, 0xf8, 0xf8, 0xf9, 0xf9, 0xfa };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff2, 0xfff2, 0xfff3, 0xfff3, 0xfff4, 0xfff4, 0xfff5, 0xfff5 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff1, 0xfffffff1, 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf5, 0xf5, 0xf6, 0xf6, 0xf7, 0xf7, 0xf8, 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb, 0xfc, 0xfc };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff1, 0xfff2, 0xfff2, 0xfff3, 0xfff3, 0xfff4, 0xfff4, 0xfff5 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff1, 0xfffffff1, 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VHSUB/VHSUBQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xfe, 0xff, 0xff, 0x0, 0x0, 0x1, 0x1, 0x2 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffff, 0xffff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xfe, 0xff, 0xff, 0x0, 0x0, 0x1, 0x1, 0x2 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0x0, 0x0, 0x1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xfe, 0xfe, 0xff, 0xff, 0x0, 0x0, 0x1, 0x1, 0x2, 0x2, 0x3, 0x3, 0x4, 0x4, 0x5, 0x5 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfffe, 0xffff, 0xffff, 0x0, 0x0, 0x1, 0x1, 0x2 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffff, 0x0, 0x0, 0x1 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xfb, 0xfc, 0xfc, 0xfd, 0xfd, 0xfe, 0xfe, 0xff, 0xff, 0x0, 0x0, 0x1, 0x1, 0x2, 0x2, 0x3 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0x0, 0x0, 0x1, 0x1, 0x2, 0x2 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0x0, 0x0, 0x1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VSUBL output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfffd, 0xfffe, 0xffff, 0x0, 0x1, 0x2, 0x3, 0x4 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffffe, 0xffffffff, 0x0, 0x1 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfffd, 0xfffe, 0xffff, 0x0, 0x1, 0x2, 0x3, 0x4 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0x0, 0x1, 0x2 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VSUBW output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfffd, 0xfffe, 0xffff, 0x0, 0x1, 0x2, 0x3, 0x4 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffffe, 0xffffffff, 0x0, 0x1 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfefd, 0xfefe, 0xfeff, 0xff00, 0xff01, 0xff02, 0xff03, 0xff04 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffeffff, 0xffff0000, 0xffff0001, 0xffff0002 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffff00000000, 0xffffffff00000001 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VSUBHN output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x31, 0x31, 0x31, 0x31, 0x31, 0x31, 0x31, 0x31 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x31, 0x31, 0x31, 0x31 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x17, 0x17 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x36, 0x36, 0x36, 0x36 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x2, 0x2 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSUBHN output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x31, 0x31, 0x31, 0x31, 0x31, 0x31, 0x31, 0x31 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x31, 0x31, 0x31, 0x31 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x17, 0x17 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x36, 0x36, 0x36, 0x36 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x2, 0x2 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VMVN/VMVNQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9, 0x8 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xf, 0xe, 0xd, 0xc };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xf, 0xe };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9, 0x8 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xf, 0xe, 0xd, 0xc };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xf, 0xe };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9, 0x8 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9, 0x8, 0x7, 0x6, 0x5, 0x4, 0x3, 0x2, 0x1, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9, 0x8 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xf, 0xe, 0xd, 0xc };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9, 0x8, 0x7, 0x6, 0x5, 0x4, 0x3, 0x2, 0x1, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9, 0x8 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xf, 0xe, 0xd, 0xc };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9, 0x8, 0x7, 0x6, 0x5, 0x4, 0x3, 0x2, 0x1, 0x0 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+
+VQMOVN output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x12, 0x12, 0x12, 0x12, 0x12, 0x12, 0x12, 0x12 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x1278, 0x1278, 0x1278, 0x1278 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x12345678, 0x12345678 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x82, 0x82, 0x82, 0x82, 0x82, 0x82, 0x82, 0x82 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x8765, 0x8765, 0x8765, 0x8765 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x87654321, 0x87654321 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+
+VQMOVN output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+
+VQMOVUN output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x34, 0x34, 0x34, 0x34, 0x34, 0x34, 0x34, 0x34 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x5678, 0x5678, 0x5678, 0x5678 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x12345678, 0x12345678 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+
+VQMOVUN (negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSHR_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb, 0xfc };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffc, 0xfffffffc };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x3c, 0x3c, 0x3d, 0x3d, 0x3d, 0x3d, 0x3e, 0x3e };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x1ffe, 0x1ffe, 0x1ffe, 0x1ffe };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x8000000, 0x8000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x80000000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb, 0xfc, 0xfc, 0xfd, 0xfd, 0xfe, 0xfe, 0xff, 0xff, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffffc, 0xfffffffc, 0xfffffffd, 0xfffffffd };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x3c, 0x3c, 0x3d, 0x3d, 0x3d, 0x3d, 0x3e, 0x3e, 0x3e, 0x3e, 0x3f, 0x3f, 0x3f, 0x3f, 0x40, 0x40 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1ffe, 0x1ffe, 0x1ffe, 0x1ffe, 0x1fff, 0x1fff, 0x1fff, 0x1fff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x8000000, 0x8000000, 0x8000000, 0x8000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSHR_N (overflow test: max shift amount, positive input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSHR_N (overflow test: shift by 1, with negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x4000, 0x4000, 0x4000, 0x4000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x40000000, 0x40000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x4000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x4000, 0x4000, 0x4000, 0x4000, 0x4000, 0x4000, 0x4000, 0x4000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x40000000, 0x40000000, 0x40000000, 0x40000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x4000000000000000, 0x4000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x8000000000000000, 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSHR_N (overflow test: shift by 3, positive input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x1000, 0x1000, 0x1000, 0x1000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x10000000, 0x10000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x1000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x2000, 0x2000, 0x2000, 0x2000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x20000000, 0x20000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x2000000000000000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x1000, 0x1000, 0x1000, 0x1000, 0x1000, 0x1000, 0x1000, 0x1000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x10000000, 0x10000000, 0x10000000, 0x10000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x1000000000000000, 0x1000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x20000000, 0x20000000, 0x20000000, 0x20000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x2000000000000000, 0x2000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSHR_N (overflow test: shift by 1, with negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xc000, 0xc000, 0xc000, 0xc000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xc0000000, 0xc0000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xc000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xc000, 0xc000, 0xc000, 0xc000, 0xc000, 0xc000, 0xc000, 0xc000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xc0000000, 0xc0000000, 0xc0000000, 0xc0000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xc000000000000000, 0xc000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x8000000000000000, 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSHR_N (overflow test: shift by 3, with negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xf000, 0xf000, 0xf000, 0xf000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xf0000000, 0xf0000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xf000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x2000, 0x2000, 0x2000, 0x2000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x20000000, 0x20000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x2000000000000000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xf000, 0xf000, 0xf000, 0xf000, 0xf000, 0xf000, 0xf000, 0xf000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xf0000000, 0xf0000000, 0xf0000000, 0xf0000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xf000000000000000, 0xf000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x20000000, 0x20000000, 0x20000000, 0x20000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x2000000000000000, 0x2000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSRA_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffd, 0xfffffffe };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfffd, 0xfffe, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff4, 0xfffffff5 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffffd, 0xfffffffe, 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf, 0x10, 0x11, 0x12, 0x13, 0x14 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfffd, 0xfffe, 0xffff, 0x0, 0x1, 0x2, 0x3, 0x4 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff4, 0xfffffff5, 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSRA_N (checking overflow: shift by 1, positive input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x4000, 0x4000, 0x4000, 0x4000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x40000000, 0x40000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x4000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x4000, 0x4000, 0x4000, 0x4000, 0x4000, 0x4000, 0x4000, 0x4000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x40000000, 0x40000000, 0x40000000, 0x40000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x4000000000000000, 0x4000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x8000000000000000, 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSRA_N (checking overflow: shift by 3, positive input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x1000, 0x1000, 0x1000, 0x1000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x10000000, 0x10000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x1000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x2000, 0x2000, 0x2000, 0x2000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x20000000, 0x20000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x2000000000000000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x1000, 0x1000, 0x1000, 0x1000, 0x1000, 0x1000, 0x1000, 0x1000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x10000000, 0x10000000, 0x10000000, 0x10000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x1000000000000000, 0x1000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x20000000, 0x20000000, 0x20000000, 0x20000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x2000000000000000, 0x2000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSRA_N (checking overflow: shift by max, positive input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSRA_N (checking overflow: shift by 1, negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xc000, 0xc000, 0xc000, 0xc000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xc0000000, 0xc0000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xc000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xc000, 0xc000, 0xc000, 0xc000, 0xc000, 0xc000, 0xc000, 0xc000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xc0000000, 0xc0000000, 0xc0000000, 0xc0000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xc000000000000000, 0xc000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSRA_N (checking overflow: shift by max, negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xf000, 0xf000, 0xf000, 0xf000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xf0000000, 0xf0000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xf000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xf000, 0xf000, 0xf000, 0xf000, 0xf000, 0xf000, 0xf000, 0xf000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xf0000000, 0xf0000000, 0xf0000000, 0xf0000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xf000000000000000, 0xf000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VRSRA_N (checking overflow: shift by max, negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VSHLL_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffe0, 0xffe2, 0xffe4, 0xffe6, 0xffe8, 0xffea, 0xffec, 0xffee };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffe0, 0xffffffe2, 0xffffffe4, 0xffffffe6 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffff80, 0xffffffffffffff88 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3c0, 0x3c4, 0x3c8, 0x3cc, 0x3d0, 0x3d4, 0x3d8, 0x3dc };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfff00, 0xfff10, 0xfff20, 0xfff30 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x7ffffff80, 0x7ffffff88 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VPADDL/VPADDLQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffe1, 0xffe5, 0xffe9, 0xffed };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xffffffe1, 0xffffffe5 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffffe1 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x1e1, 0x1e5, 0x1e9, 0x1ed };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x1ffe1, 0x1ffe5 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x1ffffffe1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffe1, 0xffe5, 0xffe9, 0xffed, 0xfff1, 0xfff5, 0xfff9, 0xfffd };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffe1, 0xffffffe5, 0xffffffe9, 0xffffffed };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffe1, 0xffffffffffffffe5 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1e1, 0x1e5, 0x1e9, 0x1ed, 0x1f1, 0x1f5, 0x1f9, 0x1fd };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1ffe1, 0x1ffe5, 0x1ffe9, 0x1ffed };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x1ffffffe1, 0x1ffffffe5 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VPADD output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xe1, 0xe5, 0xe9, 0xed, 0xe1, 0xe5, 0xe9, 0xed };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffe1, 0xffe5, 0xffe1, 0xffe5 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xffffffe1, 0xffffffe1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xe1, 0xe5, 0xe9, 0xed, 0xe1, 0xe5, 0xe9, 0xed };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffe1, 0xffe5, 0xffe1, 0xffe5 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffe1, 0xffffffe1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1f80000, 0xc1f80000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VPADAL/VPADALQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffd1, 0xffd6, 0xffdb, 0xffe0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xffffffd1, 0xffffffd6 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffffd1 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x1d1, 0x1d6, 0x1db, 0x1e0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x1ffd1, 0x1ffd6 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x1ffffffd1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffd1, 0xffd6, 0xffdb, 0xffe0, 0xffe5, 0xffea, 0xffef, 0xfff4 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffd1, 0xffffffd6, 0xffffffdb, 0xffffffe0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffd1, 0xffffffffffffffd6 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1d1, 0x1d6, 0x1db, 0x1e0, 0x1e5, 0x1ea, 0x1ef, 0x1f4 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1ffd1, 0x1ffd6, 0x1ffdb, 0x1ffe0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x1ffffffd1, 0x1ffffffd6 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQSHLU_N/VQSHLUQ_N (negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQSHLU_N/VQSHLUQ_N (check cumulative saturation: shift by 1) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfffe, 0xfffe, 0xfffe, 0xfffe };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffffe, 0xfffffffe };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffffe };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfffe, 0xfffe, 0xfffe, 0xfffe, 0xfffe, 0xfffe, 0xfffe, 0xfffe };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffffe, 0xfffffffe, 0xfffffffe, 0xfffffffe };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffffe, 0xfffffffffffffffe };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQSHLU_N/VQSHLUQ_N (check cumulative saturation: shift by 2) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQSHLU_N/VQSHLUQ_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x8, 0x8, 0x8, 0x8 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x18, 0x18 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x40 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x180, 0x180, 0x180, 0x180, 0x180, 0x180, 0x180, 0x180 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x380, 0x380, 0x380, 0x380 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x800, 0x800 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VCLZ/VCLZQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3, 0x3, 0x3, 0x3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x5, 0x5 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x3, 0x3, 0x3, 0x3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xd, 0xd, 0xd, 0xd, 0xd, 0xd, 0xd, 0xd };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1f, 0x1f, 0x1f, 0x1f };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VCLZ/VCLZQ (input=0) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x20, 0x20 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VCLS/VCLSQ (positive input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x2, 0x2, 0x2, 0x2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x19, 0x19 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x14, 0x14, 0x14, 0x14 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VCLS/VCLSQ (negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VCNT/VCNTQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x4, 0x4, 0x4, 0x4, 0x4, 0x4, 0x4, 0x4 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x4, 0x4, 0x4, 0x4, 0x4, 0x4, 0x4, 0x4 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQSHRN_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff8, 0xfff8, 0xfff9, 0xfff9 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffc, 0xfffffffc };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQSHRN_N (check saturation: shift by 3) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQSHRN_N (check saturation: shift by max) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VPMAX output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf1, 0xf3, 0xf5, 0xf7, 0xf1, 0xf3, 0xf5, 0xf7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff1, 0xfff3, 0xfff1, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf1, 0xf3, 0xf5, 0xf7, 0xf1, 0xf3, 0xf5, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff1, 0xfff3, 0xfff1, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1700000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VPMIN output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf2, 0xf4, 0xf6, 0xf0, 0xf2, 0xf4, 0xf6 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff2, 0xfff0, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf2, 0xf4, 0xf6, 0xf0, 0xf2, 0xf4, 0xf6 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff2, 0xfff0, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1800000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQSHRUN_N (negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQSHRUN_N (check cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQSHRUN_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x48, 0x48, 0x48, 0x48, 0x48, 0x48, 0x48, 0x48 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xdeadbe, 0xdeadbe };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQRSHRUN_N (negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQRSHRUN_N (check cumulative saturation: shift by 1) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQRSHRUN_N (check cumulative saturation: shift by max, positive input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQRSHRUN_N (check cumulative saturation: shift by max, negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQRSHRUN_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x49, 0x49, 0x49, 0x49, 0x49, 0x49, 0x49, 0x49 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xdeadbf, 0xdeadbf };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VST2_LANE/VST2Q_LANE chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0x0, 0x0 };
+
+VST2_LANE/VST2Q_LANE chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+
+VST3_LANE/VST3Q_LANE chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1600000, 0x0 };
+
+VST3_LANE/VST3Q_LANE chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+
+VST3_LANE/VST3Q_LANE chunk 2 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+
+VST4_LANE/VST4Q_LANE chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1600000, 0xc1500000 };
+
+VST4_LANE/VST4Q_LANE chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+
+VST4_LANE/VST4Q_LANE chunk 2 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+
+VST4_LANE/VST4Q_LANE chunk 3 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+
+VTBL1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0xf2, 0xf2, 0xf2, 0x0, 0x0, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0xf3, 0xf3, 0xf3, 0x0, 0x0, 0xf3, 0xf3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x0, 0xf3, 0xf3, 0xf3, 0x0, 0x0, 0xf3, 0xf3 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VTBL2 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf6, 0xf3, 0xf3, 0xf3, 0x0, 0x0, 0xf3, 0xf3 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf6, 0xf5, 0xf5, 0xf5, 0x0, 0x0, 0xf5, 0xf5 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf6, 0xf5, 0xf5, 0xf5, 0x0, 0x0, 0xf5, 0xf5 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VTBL3 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf4, 0xf4, 0xf4, 0xff, 0x0, 0xf4, 0xf4 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf8, 0xf7, 0xf7, 0xf7, 0xff, 0x0, 0xf7, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf8, 0xf7, 0xf7, 0xf7, 0xff, 0x0, 0xf7, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VTBL4 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xfa, 0xf5, 0xf5, 0xf5, 0x3, 0x0, 0xf5, 0xf5 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xfa, 0xf9, 0xf9, 0xf9, 0x3, 0x0, 0xf9, 0xf9 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xfa, 0xf9, 0xf9, 0xf9, 0x3, 0x0, 0xf9, 0xf9 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VTBX1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0xf2, 0xf2, 0xf2, 0x33, 0x33, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xcc, 0xf3, 0xf3, 0xf3, 0xcc, 0xcc, 0xf3, 0xf3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xcc, 0xf3, 0xf3, 0xf3, 0xcc, 0xcc, 0xf3, 0xf3 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VTBX2 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf6, 0xf3, 0xf3, 0xf3, 0x33, 0x33, 0xf3, 0xf3 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf6, 0xf5, 0xf5, 0xf5, 0xcc, 0xcc, 0xf5, 0xf5 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf6, 0xf5, 0xf5, 0xf5, 0xcc, 0xcc, 0xf5, 0xf5 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VTBX3 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf4, 0xf4, 0xf4, 0xff, 0x33, 0xf4, 0xf4 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf8, 0xf7, 0xf7, 0xf7, 0xff, 0xcc, 0xf7, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf8, 0xf7, 0xf7, 0xf7, 0xff, 0xcc, 0xf7, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+
+VTBX4 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xfa, 0xf5, 0xf5, 0xf5, 0x3, 0x33, 0xf5, 0xf5 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xfa, 0xf9, 0xf9, 0xf9, 0x3, 0xcc, 0xf9, 0xf9 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xfa, 0xf9, 0xf9, 0xf9, 0x3, 0xcc, 0xf9, 0xf9 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x3f068000, 0x3f068000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x3c030000, 0x3c030000, 0x3c030000, 0x3c030000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xee800000, 0xee800000, 0xee800000, 0xee800000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xbdcc8000, 0xbdcc8000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xbc030000, 0xbc030000, 0xbc030000, 0xbc030000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x7fc00000, 0x7fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x7f800000, 0x7f800000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xff800000, 0xff800000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x80000000, 0x80000000 };
+
+VRSQRTE/VRSQRTEQ output:
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x9c800000, 0x9c800000, 0x9c800000, 0x9c800000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x3e498000, 0x3e498000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x3e700000, 0x3e700000, 0x3e700000, 0x3e700000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xae800000, 0xae800000, 0xae800000, 0xae800000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xb4800000, 0xb4800000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xed000000, 0xed000000, 0xed000000, 0xed000000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x7fc00000, 0x7fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x7f800000, 0x7f800000, 0x7f800000, 0x7f800000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x7fc00000, 0x7fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xff800000, 0xff800000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x7fc00000, 0x7fc00000, 0x7fc00000, 0x7fc00000 };
+
+VCAGE/VCAGEQ output:
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0x0 };
+
+VCAGE/VCAGEQ output:
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+
+VCALE/VCALEQ output:
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0xffffffff, 0xffffffff };
+
+VCALE/VCALEQ output:
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+
+VCAGT/VCAGTQ output:
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0x0, 0x0 };
+
+VCAGT/VCAGTQ output:
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+
+VCALT/VCALTQ output:
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0xffffffff };
+
+VCALT/VCALTQ output:
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+
+VCVT/VCVTQ output:
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x4f800000, 0x4f800000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x4f800000, 0x4f800000, 0x4f800000, 0x4f800000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff1, 0x5 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x5 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0xf, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0xf, 0x0 };
+
+VCVT_N/VCVTQ_N output:
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc0800000, 0xc0700000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x4c000000, 0x4c000000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xb2800000, 0xb2700000, 0xb2600000, 0xb2500000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x49800000, 0x49800000, 0x49800000, 0x49800000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xff0b3333, 0x54cccd };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x15 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x1e3d7, 0xfffe1c29 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x1e, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xa, 0xa };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xa, 0xa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7d, 0x7d, 0x7d, 0x7d };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x7d, 0x7d, 0x7d, 0x7d };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xa66666, 0xa66666 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xa66666, 0xa66666 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfbccc, 0xfbccc, 0xfbccc, 0xfbccc };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfbccc, 0xfbccc, 0xfbccc, 0xfbccc };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+
+VRECPS/VRECPSQ output:
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc2e19eb7, 0xc2e19eb7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1db851f, 0xc1db851f, 0xc1db851f, 0xc1db851f };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x7fc00000, 0x7fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x7fc00000, 0x7fc00000, 0x7fc00000, 0x7fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xff800000, 0xff800000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x40000000, 0x40000000, 0x40000000, 0x40000000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x40000000, 0x40000000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x40000000, 0x40000000, 0x40000000, 0x40000000 };
+
+VRSQRTS/VRSQRTSQ output:
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc2796b84, 0xc2796b84 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc0e4a3d8, 0xc0e4a3d8, 0xc0e4a3d8, 0xc0e4a3d8 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x7fc00000, 0x7fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x7fc00000, 0x7fc00000, 0x7fc00000, 0x7fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xff800000, 0xff800000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x3fc00000, 0x3fc00000, 0x3fc00000, 0x3fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x3fc00000, 0x3fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x3fc00000, 0x3fc00000, 0x3fc00000, 0x3fc00000 };
diff --git a/expected_input4gcc.txt b/expected_input4gcc.txt
new file mode 100644
index 0000000..df294b9
--- /dev/null
+++ b/expected_input4gcc.txt
@@ -0,0 +1,7627 @@
+
+VLD1/VLD1Q output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xcc00, 0xcb80, 0xcb00, 0xca80 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xcc00, 0xcb80, 0xcb00, 0xca80, 0xca00, 0xc980, 0xc900, 0xc880 };
+
+VADD/VADDQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffec, 0xffed, 0xffee, 0xffef };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff3, 0xfffffff4 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x54 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xe, 0xf, 0x10, 0x11 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x18, 0x19 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xe6, 0xe7, 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffdc, 0xffdd, 0xffde, 0xffdf, 0xffe0, 0xffe1, 0xffe2, 0xffe3 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffd2, 0xffffffd3, 0xffffffd4, 0xffffffd5 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x8, 0x9 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xfc, 0xfd, 0xfe, 0xff, 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7, 0xfff8, 0xfff9, 0xfffa };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x27, 0x28, 0x29, 0x2a };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff3, 0xfffffffffffffff4 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x40d9999a, 0x40d9999a };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x41100000, 0x41100000, 0x41100000, 0x41100000 };
+
+VLD1_LANE/VLD1_LANEQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xf0, 0xaa };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xaaaaaaaa, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xf0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xaaaaaaaa, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xf0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xaaaaaaaa, 0xc1800000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xaaaa, 0xaaaa, 0xcc00, 0xaaaa };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xf0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xfffffff0, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xaaaaaaaaaaaaaaaa, 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xf0, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xfffffff0, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xaaaaaaaaaaaaaaaa };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xf0, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xc1800000, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xcc00, 0xaaaa, 0xaaaa };
+
+VLD1_DUP/VLD1_DUPQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1800000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xcc00, 0xcc00, 0xcc00, 0xcc00 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff0, 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff0, 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1800000, 0xc1800000, 0xc1800000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xcc00, 0xcc00, 0xcc00, 0xcc00, 0xcc00, 0xcc00, 0xcc00, 0xcc00 };
+
+VLD1_DUP/VLD1_DUPQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1700000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xcb80, 0xcb80, 0xcb80, 0xcb80 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff1, 0xfffffff1, 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff1, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff1, 0xfffffff1, 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff1, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1700000, 0xc1700000, 0xc1700000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xcb80, 0xcb80, 0xcb80, 0xcb80, 0xcb80, 0xcb80, 0xcb80, 0xcb80 };
+
+VLD1_DUP/VLD1_DUPQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xc1600000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xcb00, 0xcb00, 0xcb00, 0xcb00 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff2, 0xfffffff2, 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff2, 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff2, 0xfffffff2, 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff2, 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1600000, 0xc1600000, 0xc1600000, 0xc1600000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xcb00, 0xcb00, 0xcb00, 0xcb00, 0xcb00, 0xcb00, 0xcb00, 0xcb00 };
+
+VDUP/VDUPQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1800000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff0, 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff0, 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1800000, 0xc1800000, 0xc1800000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VDUP/VDUPQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1700000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff1, 0xfffffff1, 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff1, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff1, 0xfffffff1, 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff1, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1700000, 0xc1700000, 0xc1700000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VDUP/VDUPQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xc1600000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff2, 0xfffffff2, 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff2, 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff2, 0xfffffff2, 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff2, 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1600000, 0xc1600000, 0xc1600000, 0xc1600000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VMOV/VMOVQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1800000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff0, 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff0, 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1800000, 0xc1800000, 0xc1800000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VMOV/VMOVQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1700000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff1, 0xfffffff1, 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff1, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff1, 0xfffffff1, 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff1, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1700000, 0xc1700000, 0xc1700000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VMOV/VMOVQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xc1600000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff2, 0xfffffff2, 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff2, 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff2, 0xfffffff2, 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff2, 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1600000, 0xc1600000, 0xc1600000, 0xc1600000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VGET_HIGH output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xca00, 0xc980, 0xc900, 0xc880 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VGET_LOW output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xcc00, 0xcb80, 0xcb00, 0xca80 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQDMLAL_LANE output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7c1e, 0x7c1f, 0x7c20, 0x7c21 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7c1e, 0x7c1f };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQDMLAL_LANE (mul with input=0) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQDMLAL_LANE (check mul cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffef, 0x7ffffff0, 0x7ffffff1, 0x7ffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7fffffffffffffef, 0x7ffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQDMLSL_LANE output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffff83c2, 0xffff83c3, 0xffff83c4, 0xffff83c5 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffff83c2, 0xffffffffffff83c3 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQDMLSL_LANE (mul with input=0) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQDMLSL_LANE (check mul cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x8000000000000000, 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQDMLAL_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x1684, 0x1685, 0x1686, 0x1687 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x21ce, 0x21cf };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQDMLAL_N (check mul cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffef, 0x7ffffff0, 0x7ffffff1, 0x7ffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7fffffffffffffef, 0x7ffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQDMLSL_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffe95c, 0xffffe95d, 0xffffe95e, 0xffffe95f };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffde12, 0xffffffffffffde13 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQDMLSL_N (check mul cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x8000000000000000, 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VEXT/VEXTQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf7, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff3, 0x22, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff1, 0x33 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf6, 0xf7, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff2, 0xfff3, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff1, 0x77 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf6, 0xf7, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff2, 0xfff3, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1700000, 0x42066666 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xfe, 0xff, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff7, 0x22, 0x22, 0x22, 0x22, 0x22, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff3, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff1, 0x44 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xfc, 0xfd, 0xfe, 0xff, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff6, 0xfff7, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff3, 0x77, 0x77, 0x77 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff1, 0x88 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xfc, 0xfd, 0xfe, 0xff, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff6, 0xfff7, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1500000, 0x4204cccd, 0x4204cccd, 0x4204cccd };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VSHR_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffc, 0xfffffffc };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x3c, 0x3c, 0x3c, 0x3c, 0x3d, 0x3d, 0x3d, 0x3d };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x1ffe, 0x1ffe, 0x1ffe, 0x1ffe };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x7ffffff, 0x7ffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x7fffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf8, 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb, 0xfc, 0xfc, 0xfd, 0xfd, 0xfe, 0xfe, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffffc, 0xfffffffc, 0xfffffffc, 0xfffffffc };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x3c, 0x3c, 0x3c, 0x3c, 0x3d, 0x3d, 0x3d, 0x3d, 0x3e, 0x3e, 0x3e, 0x3e, 0x3f, 0x3f, 0x3f, 0x3f };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1ffe, 0x1ffe, 0x1ffe, 0x1ffe, 0x1ffe, 0x1ffe, 0x1ffe, 0x1ffe };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x7ffffff, 0x7ffffff, 0x7ffffff, 0x7ffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VSHRN_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff8, 0xfff8, 0xfff9, 0xfff9 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffc, 0xfffffffc };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xfc, 0xfc, 0xfc, 0xfc, 0xfd, 0xfd, 0xfd, 0xfd };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfffe, 0xfffe, 0xfffe, 0xfffe };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffffe, 0xfffffffe };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSHRN_N (with input = 0) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSHRN_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb, 0xfc };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff8, 0xfff9, 0xfff9, 0xfffa };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffc, 0xfffffffc };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xfc, 0xfc, 0xfd, 0xfd, 0xfd, 0xfd, 0xfe, 0xfe };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfffe, 0xfffe, 0xfffe, 0xfffe };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffffe, 0xfffffffe };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSHRN_N (with large shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQRSHRN_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb, 0xfc };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff8, 0xfff9, 0xfff9, 0xfffa };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffc, 0xfffffffc };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQRSHRN_N (check saturation: shift by 3) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQRSHRN_N (check saturation: shift by max) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VSET_LANE/VSET_LANEQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0x11 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0x22 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0x33 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x44 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0x55, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0x66, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0x77 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x88 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0x55, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0x66, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0x4204cccd };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0x99 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xaa, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xbb };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xcc };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xdd, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xee, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xff, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0x11 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xdd, 0xff };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xee, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1600000, 0x41333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQSUB/VQSUBQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xdf, 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffce, 0xffcf, 0xffd0, 0xffd1 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xffffffbd, 0xffffffbe };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffffac };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, 0xa0, 0xa1, 0xa2 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xff8a, 0xff8b, 0xff8c, 0xff8d };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffff79, 0xffffff7a };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffff68 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xdf, 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffce, 0xffcf, 0xffd0, 0xffd1, 0xffd2, 0xffd3, 0xffd4, 0xffd5 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffbd, 0xffffffbe, 0xffffffbf, 0xffffffc0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffac, 0xffffffffffffffad };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x9b, 0x9c, 0x9d, 0x9e, 0x9f, 0xa0, 0xa1, 0xa2, 0xa3, 0xa4, 0xa5, 0xa6, 0xa7, 0xa8, 0xa9, 0xaa };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xff8a, 0xff8b, 0xff8c, 0xff8d, 0xff8e, 0xff8f, 0xff90, 0xff91 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffff79, 0xffffff7a, 0xffffff7b, 0xffffff7c };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffff68, 0xffffffffffffff69 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffffac };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffff68 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffac, 0xffffffffffffffad };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffff68, 0xffffffffffffff69 };
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7fffffffffffffff, 0x7fffffffffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+
+VQDMULH output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+
+VQDMULH output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+
+VQDMULH_LANE output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+
+VQDMULH_LANE (check mul cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+
+VQDMULH_N output:
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x19, 0x19, 0x19, 0x19 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x4, 0x4 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xa, 0xa, 0xa, 0xa };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+
+VQDMULH_N (check mul cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+
+VQDMULL output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x200, 0x1c2, 0x188, 0x152 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x200, 0x1c2 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+
+VQDMULL (check mul cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7fffffffffffffff, 0x7fffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQDMLAL output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7c1e, 0x7c1f, 0x7c20, 0x7c21 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7c1e, 0x7c1f };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQDMLAL (check mul cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffef, 0x7ffffff0, 0x7ffffff1, 0x7ffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7fffffffffffffef, 0x7ffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQDMLSL output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffff83c2, 0xffff83c3, 0xffff83c4, 0xffff83c5 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffff83c2, 0xffffffffffff83c3 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQDMLSL (check mul cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x8000000000000000, 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VCEQ/VCEQQ output:
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xff, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0xff, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xff, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0xff, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0xff, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0xff, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VCGE/VCGEQ output:
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+
+VCLE/VCLEQ output:
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+
+VCGT/VCGTQ output:
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+
+VCLT/VCLTQ output:
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+
+VBSL/VBSLQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf6, 0xf6, 0xf6, 0xf6 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff0, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffffd };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf3, 0xf3, 0xf3, 0xf3, 0xf7, 0xf7, 0xf7, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff0, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffff1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf3, 0xf3, 0xf3, 0xf3, 0xf7, 0xf7, 0xf7, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff0, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800004, 0xc1700004 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf6, 0xf6, 0xf6, 0xf6, 0xf2, 0xf2, 0xf2, 0xf2, 0xf6, 0xf6, 0xf6, 0xf6 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff0, 0xfff2, 0xfff2, 0xfff4, 0xfff4, 0xfff6, 0xfff6 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff0, 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffffd, 0xfffffffffffffffd };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf3, 0xf3, 0xf3, 0xf3, 0xf7, 0xf7, 0xf7, 0xf7, 0xf3, 0xf3, 0xf3, 0xf3, 0xf7, 0xf7, 0xf7, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff0, 0xfff2, 0xfff2, 0xfff4, 0xfff4, 0xfff6, 0xfff6 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff0, 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf3, 0xf3, 0xf3, 0xf3, 0xf7, 0xf7, 0xf7, 0xf7, 0xf3, 0xf3, 0xf3, 0xf3, 0xf7, 0xf7, 0xf7, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff0, 0xfff2, 0xfff2, 0xfff4, 0xfff4, 0xfff6, 0xfff6 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800001, 0xc1700001, 0xc1600001, 0xc1500001 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VSHL/VSHLQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xe0, 0xe2, 0xe4, 0xe6, 0xe8, 0xea, 0xec, 0xee };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xff80, 0xff88, 0xff90, 0xff98 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffff000, 0xfffff100 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffff80 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xe0, 0xe2, 0xe4, 0xe6, 0xe8, 0xea, 0xec, 0xee };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xff80, 0xff88, 0xff90, 0xff98 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffff000, 0xfffff100 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffff80 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x20, 0x40, 0x60, 0x80, 0xa0, 0xc0, 0xe0, 0x0, 0x20, 0x40, 0x60, 0x80, 0xa0, 0xc0, 0xe0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x1000, 0x2000, 0x3000, 0x4000, 0x5000, 0x6000, 0x7000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x40000000, 0x80000000, 0xc0000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x20, 0x40, 0x60, 0x80, 0xa0, 0xc0, 0xe0, 0x0, 0x20, 0x40, 0x60, 0x80, 0xa0, 0xc0, 0xe0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x1000, 0x2000, 0x3000, 0x4000, 0x5000, 0x6000, 0x7000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x40000000, 0x80000000, 0xc0000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VSHL/VSHLQ (large shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VSHL/VSHLQ (negative shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff8, 0xfff8, 0xfff9, 0xfff9 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffc, 0xfffffffc };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x78, 0x78, 0x79, 0x79, 0x7a, 0x7a, 0x7b, 0x7b };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x7ff8, 0x7ff8, 0x7ff9, 0x7ff9 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x3ffffffc, 0x3ffffffc };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xfc, 0xfc, 0xfc, 0xfc, 0xfd, 0xfd, 0xfd, 0xfd, 0xfe, 0xfe, 0xfe, 0xfe, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffffe, 0xfffffffe, 0xfffffffe, 0xfffffffe };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x3c, 0x3c, 0x3c, 0x3c, 0x3d, 0x3d, 0x3d, 0x3d, 0x3e, 0x3e, 0x3e, 0x3e, 0x3f, 0x3f, 0x3f, 0x3f };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x7ff, 0x7ff, 0x7ff, 0x7ff, 0x7ff, 0x7ff, 0x7ff, 0x7ff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1ffffffe, 0x1ffffffe, 0x1ffffffe, 0x1ffffffe };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x7ffffffffffffff, 0x7ffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VSHL_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xe0, 0xe2, 0xe4, 0xe6, 0xe8, 0xea, 0xec, 0xee };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffe0, 0xffe2, 0xffe4, 0xffe6 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xffffff80, 0xffffff88 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffffc0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xc0, 0xc4, 0xc8, 0xcc, 0xd0, 0xd4, 0xd8, 0xdc };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xff00, 0xff10, 0xff20, 0xff30 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffff80, 0xffffff88 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffe0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x20, 0x40, 0x60, 0x80, 0xa0, 0xc0, 0xe0, 0x0, 0x20, 0x40, 0x60, 0x80, 0xa0, 0xc0, 0xe0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffe0, 0xffe2, 0xffe4, 0xffe6, 0xffe8, 0xffea, 0xffec, 0xffee };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffc0, 0xffffffc4, 0xffffffc8, 0xffffffcc };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffc0, 0xffffffffffffffc4 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xc0, 0xc4, 0xc8, 0xcc, 0xd0, 0xd4, 0xd8, 0xdc, 0xe0, 0xe4, 0xe8, 0xec, 0xf0, 0xf4, 0xf8, 0xfc };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xff80, 0xff88, 0xff90, 0xff98, 0xffa0, 0xffa8, 0xffb0, 0xffb8 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffc0, 0xffffffc4, 0xffffffc8, 0xffffffcc };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffe0, 0xffffffffffffffe2 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQSHL/VQSHLQ (with input = 0) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQSHL/VQSHLQ (input 0 and negative shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQSHL/VQSHLQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xe0, 0xe2, 0xe4, 0xe6, 0xe8, 0xea, 0xec, 0xee };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xff80, 0xff88, 0xff90, 0xff98 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffff000, 0xfffff100 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffffe };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x1ffffffffffffffe };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x8000000000000000, 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQSHL/VQSHLQ (negative shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfffc, 0xfffc, 0xfffc, 0xfffc };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffe, 0xfffffffe };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x78, 0x78, 0x79, 0x79, 0x7a, 0x7a, 0x7b, 0x7b };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3ffc, 0x3ffc, 0x3ffc, 0x3ffc };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x1ffffffe, 0x1ffffffe };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1f, 0x1f, 0x1f, 0x1f, 0x1f, 0x1f, 0x1f, 0x1f };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x7ffff, 0x7ffff, 0x7ffff, 0x7ffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffff, 0xfffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQSHL/VQSHLQ (large shift amount, negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x8000000000000000, 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQSHL/VQSHLQ (check cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3fff, 0x3fff, 0x3fff, 0x3fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x3fffffff, 0x3fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3fffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x7fffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f, 0x3f };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3fff, 0x3fff, 0x3fff, 0x3fff, 0x3fff, 0x3fff, 0x3fff, 0x3fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x3fffffff, 0x3fffffff, 0x3fffffff, 0x3fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3fffffffffffffff, 0x3fffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x7fffffffffffffff, 0x7fffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQSHL/VQSHLQ (large shift amount, positive input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x7fffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7fffffffffffffff, 0x7fffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQSHL/VQSHLQ (check saturation on 64 bits) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7fffffffffffffff, 0x7fffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQSHL_N/VQSHLQ_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xc0, 0xc4, 0xc8, 0xcc, 0xd0, 0xd4, 0xd8, 0xdc };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffe0, 0xffe2, 0xffe4, 0xffe6 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xffffffe0, 0xffffffe2 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffffc0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xc0, 0xc4, 0xc8, 0xcc, 0xd0, 0xd4, 0xd8, 0xdc, 0xe0, 0xe4, 0xe8, 0xec, 0xf0, 0xf4, 0xf8, 0xfc };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffe0, 0xffe2, 0xffe4, 0xffe6, 0xffe8, 0xffea, 0xffec, 0xffee };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffe0, 0xffffffe2, 0xffffffe4, 0xffffffe6 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffc0, 0xffffffffffffffc4 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQSHL_N/VQSHLQ_N (check saturation with large positive input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x7fffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7fffffffffffffff, 0x7fffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSHL/VRSHLQ (with input = 0) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSHL/VRSHLQ (input 0 and negative shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSHL/VRSHLQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xe0, 0xe2, 0xe4, 0xe6, 0xe8, 0xea, 0xec, 0xee };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xff80, 0xff88, 0xff90, 0xff98 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffff000, 0xfffff100 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffffe };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xe0, 0xe2, 0xe4, 0xe6, 0xe8, 0xea, 0xec, 0xee };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xff80, 0xff88, 0xff90, 0xff98 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffff000, 0xfffff100 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x1ffffffffffffffe };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x1000, 0x2000, 0x3000, 0x4000, 0x5000, 0x6000, 0x7000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x1000, 0x2000, 0x3000, 0x4000, 0x5000, 0x6000, 0x7000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSHL/VRSHLQ (negative shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb, 0xfc };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfffc, 0xfffc, 0xfffd, 0xfffd };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffe, 0xfffffffe };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x78, 0x79, 0x79, 0x7a, 0x7a, 0x7b, 0x7b, 0x7c };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3ffc, 0x3ffc, 0x3ffd, 0x3ffd };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x1ffffffe, 0x1ffffffe };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x80000, 0x80000, 0x80000, 0x80000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x100000000000, 0x100000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSHL/VRSHLQ (checking round_const overflow: shift by -1) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x4000, 0x4000, 0x4000, 0x4000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x40000000, 0x40000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x4000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x4000, 0x4000, 0x4000, 0x4000, 0x4000, 0x4000, 0x4000, 0x4000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x40000000, 0x40000000, 0x40000000, 0x40000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x4000000000000000, 0x4000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x8000000000000000, 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSHL/VRSHLQ (checking round_const overflow: shift by -3) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x1000, 0x1000, 0x1000, 0x1000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x10000000, 0x10000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x1000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x2000, 0x2000, 0x2000, 0x2000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x20000000, 0x20000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x2000000000000000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x1000, 0x1000, 0x1000, 0x1000, 0x1000, 0x1000, 0x1000, 0x1000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x10000000, 0x10000000, 0x10000000, 0x10000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x1000000000000000, 0x1000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x20000000, 0x20000000, 0x20000000, 0x20000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x2000000000000000, 0x2000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSHL/VRSHLQ (checking negative shift amount as large as input vector width) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSHL/VRSHLQ (large shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSHL/VRSHLQ (large negative shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VLD2/VLD2Q chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xcc00, 0xcb80, 0xcb00, 0xca80 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xcc00, 0xcb80, 0xcb00, 0xca80, 0xca00, 0xc980, 0xc900, 0xc880 };
+
+VLD2/VLD2Q chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xca00, 0xc980, 0xc900, 0xc880 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb, 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff4, 0xfffffff5, 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb, 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff4, 0xfffffff5, 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb, 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1400000, 0xc1300000, 0xc1200000, 0xc1100000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xc800, 0xc700, 0xc600, 0xc500, 0xc400, 0xc200, 0xc000, 0xbc00 };
+
+VLD3/VLD3Q chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xcc00, 0xcb80, 0xcb00, 0xca80 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xcc00, 0xcb80, 0xcb00, 0xca80, 0xca00, 0xc980, 0xc900, 0xc880 };
+
+VLD3/VLD3Q chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xca00, 0xc980, 0xc900, 0xc880 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb, 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff4, 0xfffffff5, 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb, 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff4, 0xfffffff5, 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb, 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1400000, 0xc1300000, 0xc1200000, 0xc1100000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xc800, 0xc700, 0xc600, 0xc500, 0xc400, 0xc200, 0xc000, 0xbc00 };
+
+VLD3/VLD3Q chunk 2 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff4, 0xfffffff5 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff4, 0xfffffff5 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1400000, 0xc1300000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xc800, 0xc700, 0xc600, 0xc500 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff8, 0xfffffff9, 0xfffffffa, 0xfffffffb };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff8, 0xfffffff9, 0xfffffffa, 0xfffffffb };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1000000, 0xc0e00000, 0xc0c00000, 0xc0a00000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x3c00, 0x4000, 0x4200, 0x4400, 0x4500, 0x4600, 0x4700 };
+
+VLD4/VLD4Q chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xcc00, 0xcb80, 0xcb00, 0xca80 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xcc00, 0xcb80, 0xcb00, 0xca80, 0xca00, 0xc980, 0xc900, 0xc880 };
+
+VLD4/VLD4Q chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xca00, 0xc980, 0xc900, 0xc880 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb, 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff4, 0xfffffff5, 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb, 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff4, 0xfffffff5, 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb, 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1400000, 0xc1300000, 0xc1200000, 0xc1100000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xc800, 0xc700, 0xc600, 0xc500, 0xc400, 0xc200, 0xc000, 0xbc00 };
+
+VLD4/VLD4Q chunk 2 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff4, 0xfffffff5 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff4, 0xfffffff5 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff8, 0xfff9, 0xfffa, 0xfffb };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1400000, 0xc1300000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xc800, 0xc700, 0xc600, 0xc500 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff8, 0xfffffff9, 0xfffffffa, 0xfffffffb };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff8, 0xfffffff9, 0xfffffffa, 0xfffffffb };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1000000, 0xc0e00000, 0xc0c00000, 0xc0a00000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x3c00, 0x4000, 0x4200, 0x4400, 0x4500, 0x4600, 0x4700 };
+
+VLD4/VLD4Q chunk 3 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff3 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff3 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1200000, 0xc1100000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xc400, 0xc200, 0xc000, 0xbc00 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffffc, 0xfffffffd, 0xfffffffe, 0xffffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffffc, 0xfffffffd, 0xfffffffe, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 0x28, 0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc0800000, 0xc0400000, 0xc0000000, 0xbf800000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x4800, 0x4880, 0x4900, 0x4980, 0x4a00, 0x4a80, 0x4b00, 0x4b80 };
+
+VDUP_LANE/VDUP_LANEQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1, 0xf1 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf7, 0xf7, 0xf7, 0xf7, 0xf7, 0xf7, 0xf7, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff3, 0xfff3, 0xfff3, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf7, 0xf7, 0xf7, 0xf7, 0xf7, 0xf7, 0xf7, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff3, 0xfff3, 0xfff3, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1700000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff3, 0xfff3, 0xfff3, 0xfff3, 0xfff3, 0xfff3, 0xfff3, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff1, 0xfffffff1, 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff0, 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5, 0xf5 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1700000, 0xc1700000, 0xc1700000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+
+VQDMULL_LANE output:
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x4000, 0x4000 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7fffffffffffffff, 0x7fffffffffffffff };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+
+VQDMULL_N output:
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x44000, 0x44000, 0x44000, 0x44000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xaa000, 0xaa000 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7fffffffffffffff, 0x7fffffffffffffff };
+
+VST1_LANE/VST1_LANEQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf7, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff3, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff1, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf6, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff2, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf6, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff2, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1700000, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xcb00, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xff, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff5, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff1, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff1, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xfa, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff4, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff3, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xfa, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff4, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1700000, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xc980, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VSUB/VSUBQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xee, 0xef, 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xffffffed, 0xffffffee };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffff8c };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xdc, 0xdd, 0xde, 0xdf, 0xe0, 0xe1, 0xe2, 0xe3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffd2, 0xffd3, 0xffd4, 0xffd5 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffc8, 0xffffffc9 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffee };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xe, 0xf, 0x10, 0x11 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffd8, 0xffffffffffffffd9 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xe4, 0xe5, 0xe6, 0xe7, 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffed, 0xffee, 0xffef, 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffb9, 0xffffffba, 0xffffffbb, 0xffffffbc };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffed, 0xffffffffffffffee };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc00ccccd, 0xc00ccccd };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc00ccccc, 0xc00ccccc, 0xc00ccccc, 0xc00ccccc };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQADD/VQADDQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x12, 0x13, 0x14, 0x15 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x23, 0x24 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x34 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf, 0x10 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x23, 0x24, 0x25, 0x26 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x34, 0x35 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x34 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x34, 0x35 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7fffffffffffffff, 0x7fffffffffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+
+VABS/VABSQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x10, 0xf, 0xe, 0xd };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x10, 0xf };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9, 0x8, 0x7, 0x6, 0x5, 0x4, 0x3, 0x2, 0x1 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x10, 0xf, 0xe, 0xd };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x40133333, 0x40133333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x4059999a, 0x4059999a, 0x4059999a, 0x4059999a };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+
+VQABS/VQABSQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x10, 0xf, 0xe, 0xd };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x10, 0xf };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9, 0x8, 0x7, 0x6, 0x5, 0x4, 0x3, 0x2, 0x1 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x10, 0xf, 0xe, 0xd };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+
+VQABS/VQABSQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VCOMBINE output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0x22, 0x22, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0x44 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0x66, 0x66, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0x77, 0x77 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0x88 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0x66, 0x66, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0x40533333, 0x40533333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xcc00, 0xcb80, 0xcb00, 0xca80, 0x4b80, 0x4b80, 0x4b80, 0x4b80 };
+
+VMAX/VMAXQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf3, 0xf3, 0xf3, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf3, 0xf3, 0xf3, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff1, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1780000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf4, 0xf4, 0xf4, 0xf4, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff3, 0xfff3, 0xfff3, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff1, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf9, 0xf9, 0xf9, 0xf9, 0xf9, 0xf9, 0xf9, 0xf9, 0xf9, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff2, 0xfff2, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff1, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1680000, 0xc1680000, 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x7fc00000, 0x7fc00000, 0x7fc00000, 0x7fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x7fc00000, 0x7fc00000, 0x7fc00000, 0x7fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x7f800000, 0x7f800000, 0x7f800000, 0x7f800000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+
+VMIN/VMINQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf3, 0xf3, 0xf3, 0xf3 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf3, 0xf3, 0xf3, 0xf3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff1, 0xfff1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1780000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf4, 0xf4, 0xf4, 0xf4, 0xf4, 0xf4, 0xf4, 0xf4, 0xf4, 0xf4, 0xf4 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff3, 0xfff3, 0xfff3, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xf9, 0xf9, 0xf9, 0xf9, 0xf9, 0xf9 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1680000, 0xc1680000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x7fc00000, 0x7fc00000, 0x7fc00000, 0x7fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x7fc00000, 0x7fc00000, 0x7fc00000, 0x7fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x3f800000, 0x3f800000, 0x3f800000, 0x3f800000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xff800000, 0xff800000, 0xff800000, 0xff800000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+
+VNEG/VNEGQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x10, 0xf, 0xe, 0xd };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x10, 0xf };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9, 0x8, 0x7, 0x6, 0x5, 0x4, 0x3, 0x2, 0x1 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x10, 0xf, 0xe, 0xd };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc0133333, 0xc0133333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc059999a, 0xc059999a, 0xc059999a, 0xc059999a };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+
+VQNEG/VQNEGQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x10, 0xf, 0xe, 0xd };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x10, 0xf };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9, 0x8, 0x7, 0x6, 0x5, 0x4, 0x3, 0x2, 0x1 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x10, 0xf, 0xe, 0xd };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+
+VQNEG/VQNEGQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VMLAL output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xe907, 0xe908, 0xe909, 0xe90a, 0xe90b, 0xe90c, 0xe90d, 0xe90e };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3e07, 0x3e08 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a, 0x3e0b, 0x3e0c, 0x3e0d, 0x3e0e };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3e07, 0x3e08 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VMLSL output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x16d9, 0x16da, 0x16db, 0x16dc, 0x16dd, 0x16de, 0x16df, 0x16e0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffc1d9, 0xffffc1da, 0xffffc1db, 0xffffc1dc };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffc1d9, 0xffffffffffffc1da };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xc1d9, 0xc1da, 0xc1db, 0xc1dc, 0xc1dd, 0xc1de, 0xc1df, 0xc1e0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffc1d9, 0xffffc1da, 0xffffc1db, 0xffffc1dc };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffc1d9, 0xffffffffffffc1da };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VMLAL_LANE output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3e07, 0x3e08 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3e07, 0x3e08 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VMLSL_LANE output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffc1d9, 0xffffc1da, 0xffffc1db, 0xffffc1dc };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffc1d9, 0xffffffffffffc1da };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffc1d9, 0xffffc1da, 0xffffc1db, 0xffffc1dc };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffc1d9, 0xffffffffffffc1da };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VMLAL_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x595, 0x596, 0x597, 0x598 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xb3a, 0xb3b };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x10df, 0x10e0, 0x10e1, 0x10e2 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x10df, 0x10e0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VMLSL_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffa4b, 0xfffffa4c, 0xfffffa4d, 0xfffffa4e };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffff4a6, 0xfffffffffffff4a7 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffef01, 0xffffef02, 0xffffef03, 0xffffef04 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffef01, 0xffffffffffffef02 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VMOVL output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VMOVN output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VMULL output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x100, 0xe1, 0xc4, 0xa9, 0x90, 0x79, 0x64, 0x51 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x100, 0xe1, 0xc4, 0xa9 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x100, 0xe1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xe100, 0xe2e1, 0xe4c4, 0xe6a9, 0xe890, 0xea79, 0xec64, 0xee51 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffe00100, 0xffe200e1, 0xffe400c4, 0xffe600a9 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffe000000100, 0xffffffe2000000e1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x5500, 0x5501, 0x5504, 0x5505, 0x5510, 0x5511, 0x5514, 0x5515 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VMULL_LANE output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x4000, 0x4000, 0x4000, 0x4000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x2000, 0x2000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x4000, 0x4000, 0x4000, 0x4000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x2000, 0x2000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VREV16 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf1, 0xf0, 0xf3, 0xf2, 0xf5, 0xf4, 0xf7, 0xf6 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf1, 0xf0, 0xf3, 0xf2, 0xf5, 0xf4, 0xf7, 0xf6 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf1, 0xf0, 0xf3, 0xf2, 0xf5, 0xf4, 0xf7, 0xf6 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf1, 0xf0, 0xf3, 0xf2, 0xf5, 0xf4, 0xf7, 0xf6, 0xf9, 0xf8, 0xfb, 0xfa, 0xfd, 0xfc, 0xff, 0xfe };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf1, 0xf0, 0xf3, 0xf2, 0xf5, 0xf4, 0xf7, 0xf6, 0xf9, 0xf8, 0xfb, 0xfa, 0xfd, 0xfc, 0xff, 0xfe };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf1, 0xf0, 0xf3, 0xf2, 0xf5, 0xf4, 0xf7, 0xf6, 0xf9, 0xf8, 0xfb, 0xfa, 0xfd, 0xfc, 0xff, 0xfe };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VREV32 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf3, 0xf2, 0xf1, 0xf0, 0xf7, 0xf6, 0xf5, 0xf4 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff1, 0xfff0, 0xfff3, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf3, 0xf2, 0xf1, 0xf0, 0xf7, 0xf6, 0xf5, 0xf4 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff1, 0xfff0, 0xfff3, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf3, 0xf2, 0xf1, 0xf0, 0xf7, 0xf6, 0xf5, 0xf4 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff1, 0xfff0, 0xfff3, 0xfff2 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf3, 0xf2, 0xf1, 0xf0, 0xf7, 0xf6, 0xf5, 0xf4, 0xfb, 0xfa, 0xf9, 0xf8, 0xff, 0xfe, 0xfd, 0xfc };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff1, 0xfff0, 0xfff3, 0xfff2, 0xfff5, 0xfff4, 0xfff7, 0xfff6 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf3, 0xf2, 0xf1, 0xf0, 0xf7, 0xf6, 0xf5, 0xf4, 0xfb, 0xfa, 0xf9, 0xf8, 0xff, 0xfe, 0xfd, 0xfc };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff1, 0xfff0, 0xfff3, 0xfff2, 0xfff5, 0xfff4, 0xfff7, 0xfff6 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf3, 0xf2, 0xf1, 0xf0, 0xf7, 0xf6, 0xf5, 0xf4, 0xfb, 0xfa, 0xf9, 0xf8, 0xff, 0xfe, 0xfd, 0xfc };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff1, 0xfff0, 0xfff3, 0xfff2, 0xfff5, 0xfff4, 0xfff7, 0xfff6 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VREV64 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf7, 0xf6, 0xf5, 0xf4, 0xf3, 0xf2, 0xf1, 0xf0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff3, 0xfff2, 0xfff1, 0xfff0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff1, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf7, 0xf6, 0xf5, 0xf4, 0xf3, 0xf2, 0xf1, 0xf0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff3, 0xfff2, 0xfff1, 0xfff0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff1, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf7, 0xf6, 0xf5, 0xf4, 0xf3, 0xf2, 0xf1, 0xf0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff3, 0xfff2, 0xfff1, 0xfff0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1700000, 0xc1800000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf7, 0xf6, 0xf5, 0xf4, 0xf3, 0xf2, 0xf1, 0xf0, 0xff, 0xfe, 0xfd, 0xfc, 0xfb, 0xfa, 0xf9, 0xf8 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff3, 0xfff2, 0xfff1, 0xfff0, 0xfff7, 0xfff6, 0xfff5, 0xfff4 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff1, 0xfffffff0, 0xfffffff3, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf7, 0xf6, 0xf5, 0xf4, 0xf3, 0xf2, 0xf1, 0xf0, 0xff, 0xfe, 0xfd, 0xfc, 0xfb, 0xfa, 0xf9, 0xf8 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff3, 0xfff2, 0xfff1, 0xfff0, 0xfff7, 0xfff6, 0xfff5, 0xfff4 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff1, 0xfffffff0, 0xfffffff3, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf7, 0xf6, 0xf5, 0xf4, 0xf3, 0xf2, 0xf1, 0xf0, 0xff, 0xfe, 0xfd, 0xfc, 0xfb, 0xfa, 0xf9, 0xf8 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff3, 0xfff2, 0xfff1, 0xfff0, 0xfff7, 0xfff6, 0xfff5, 0xfff4 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1700000, 0xc1800000, 0xc1500000, 0xc1600000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VSRA_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffc, 0xfffffffd };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff3, 0xfffffff4 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffffc, 0xfffffffd, 0xfffffffe, 0xffffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf, 0x10, 0x11, 0x12, 0x13, 0x14 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfffc, 0xfffd, 0xfffe, 0xffff, 0x0, 0x1, 0x2, 0x3 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff3, 0xfffffff4, 0xfffffff5, 0xfffffff6 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VTRN/VTRNQ chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0x11, 0x11, 0xf2, 0xf3, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0x55, 0x55, 0xf2, 0xf3, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0x55, 0x55, 0xf2, 0xf3, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0x11, 0x11, 0xf2, 0xf3, 0x11, 0x11, 0xf4, 0xf5, 0x11, 0x11, 0xf6, 0xf7, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0x22, 0x22, 0xfff2, 0xfff3, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0x55, 0x55, 0xf2, 0xf3, 0x55, 0x55, 0xf4, 0xf5, 0x55, 0x55, 0xf6, 0xf7, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0x66, 0x66, 0xfff2, 0xfff3, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0x77, 0x77 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf1, 0x55, 0x55, 0xf2, 0xf3, 0x55, 0x55, 0xf4, 0xf5, 0x55, 0x55, 0xf6, 0xf7, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0x66, 0x66, 0xfff2, 0xfff3, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0x42073333, 0x42073333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VTRN/VTRNQ chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf4, 0xf5, 0x11, 0x11, 0xf6, 0xf7, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff2, 0xfff3, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf4, 0xf5, 0x55, 0x55, 0xf6, 0xf7, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff2, 0xfff3, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x77, 0x77 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf4, 0xf5, 0x55, 0x55, 0xf6, 0xf7, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff2, 0xfff3, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x42066666, 0x42066666 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf8, 0xf9, 0x11, 0x11, 0xfa, 0xfb, 0x11, 0x11, 0xfc, 0xfd, 0x11, 0x11, 0xfe, 0xff, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff4, 0xfff5, 0x22, 0x22, 0xfff6, 0xfff7, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff2, 0xfffffff3, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf8, 0xf9, 0x55, 0x55, 0xfa, 0xfb, 0x55, 0x55, 0xfc, 0xfd, 0x55, 0x55, 0xfe, 0xff, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff4, 0xfff5, 0x66, 0x66, 0xfff6, 0xfff7, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff2, 0xfffffff3, 0x77, 0x77 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf8, 0xf9, 0x55, 0x55, 0xfa, 0xfb, 0x55, 0x55, 0xfc, 0xfd, 0x55, 0x55, 0xfe, 0xff, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff4, 0xfff5, 0x66, 0x66, 0xfff6, 0xfff7, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1600000, 0xc1500000, 0x42073333, 0x42073333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VUZP/VUZPQ chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VUZP/VUZPQ chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x22, 0x22, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x66, 0x66, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x77, 0x77 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x66, 0x66, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x42066666, 0x42066666 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x22, 0x22, 0x22, 0x22, 0x22, 0x22, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x77, 0x77, 0x77, 0x77 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x42073333, 0x42073333, 0x42073333, 0x42073333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VZIP/VZIPQ chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf4, 0x11, 0x11, 0xf1, 0xf5, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff2, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf4, 0x55, 0x55, 0xf1, 0xf5, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff2, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf4, 0x55, 0x55, 0xf1, 0xf5, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff2, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf8, 0x11, 0x11, 0xf1, 0xf9, 0x11, 0x11, 0xf2, 0xfa, 0x11, 0x11, 0xf3, 0xfb, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff4, 0x22, 0x22, 0xfff1, 0xfff5, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff2, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf8, 0x55, 0x55, 0xf1, 0xf9, 0x55, 0x55, 0xf2, 0xfa, 0x55, 0x55, 0xf3, 0xfb, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff4, 0x66, 0x66, 0xfff1, 0xfff5, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff2, 0x77, 0x77 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf8, 0x55, 0x55, 0xf1, 0xf9, 0x55, 0x55, 0xf2, 0xfa, 0x55, 0x55, 0xf3, 0xfb, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff4, 0x66, 0x66, 0xfff1, 0xfff5, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1600000, 0x42073333, 0x42073333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VZIP/VZIPQ chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf2, 0xf6, 0x11, 0x11, 0xf3, 0xf7, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff1, 0xfff3, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf2, 0xf6, 0x55, 0x55, 0xf3, 0xf7, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff1, 0xfff3, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x77, 0x77 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf2, 0xf6, 0x55, 0x55, 0xf3, 0xf7, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff1, 0xfff3, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x42066666, 0x42066666 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf4, 0xfc, 0x11, 0x11, 0xf5, 0xfd, 0x11, 0x11, 0xf6, 0xfe, 0x11, 0x11, 0xf7, 0xff, 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff2, 0xfff6, 0x22, 0x22, 0xfff3, 0xfff7, 0x22, 0x22 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff1, 0xfffffff3, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf4, 0xfc, 0x55, 0x55, 0xf5, 0xfd, 0x55, 0x55, 0xf6, 0xfe, 0x55, 0x55, 0xf7, 0xff, 0x55, 0x55 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff2, 0xfff6, 0x66, 0x66, 0xfff3, 0xfff7, 0x66, 0x66 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff1, 0xfffffff3, 0x77, 0x77 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf4, 0xfc, 0x55, 0x55, 0xf5, 0xfd, 0x55, 0x55, 0xf6, 0xfe, 0x55, 0x55, 0xf7, 0xff, 0x55, 0x55 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff2, 0xfff6, 0x66, 0x66, 0xfff3, 0xfff7, 0x66, 0x66 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1700000, 0xc1500000, 0x42073333, 0x42073333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VREINTERPRET/VREINTERPRETQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff };
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff };
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xffff, 0xfff1, 0xffff };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xffff, 0xfff1, 0xffff };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xf3f2f1f0, 0xf7f6f5f4 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfff1fff0, 0xfff3fff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xffffffff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xf3f2f1f0, 0xf7f6f5f4 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfff1fff0, 0xfff3fff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xffffffff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xf3f2f1f0, 0xf7f6f5f4 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfff1fff0, 0xfff3fff2 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xf7f6f5f4f3f2f1f0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfff3fff2fff1fff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffff1fffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xf7f6f5f4f3f2f1f0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfff3fff2fff1fff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffff1fffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xf7f6f5f4f3f2f1f0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfff3fff2fff1fff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xffff, 0xfff1, 0xffff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xffff, 0xfff1, 0xffff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xf3f2f1f0, 0xf7f6f5f4 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfff1fff0, 0xfff3fff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xf3f2f1f0, 0xf7f6f5f4 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfff1fff0, 0xfff3fff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xf3f2f1f0, 0xf7f6f5f4 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfff1fff0, 0xfff3fff2 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xf7f6f5f4f3f2f1f0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfff3fff2fff1fff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffff1fffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xf7f6f5f4f3f2f1f0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfff3fff2fff1fff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffff1fffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xf7f6f5f4f3f2f1f0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfff3fff2fff1fff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xffff, 0xfff1, 0xffff };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xffff, 0xfff1, 0xffff };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff, 0xf4, 0xff, 0xf5, 0xff, 0xf6, 0xff, 0xf7, 0xff };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff, 0xf2, 0xff, 0xff, 0xff, 0xf3, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff, 0xf4, 0xff, 0xf5, 0xff, 0xf6, 0xff, 0xf7, 0xff };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff, 0xf2, 0xff, 0xff, 0xff, 0xf3, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff, 0xf4, 0xff, 0xf5, 0xff, 0xf6, 0xff, 0xf7, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6, 0xf9f8, 0xfbfa, 0xfdfc, 0xfffe };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xffff, 0xfff1, 0xffff, 0xfff2, 0xffff, 0xfff3, 0xffff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xffff, 0xffff, 0xffff, 0xfff1, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6, 0xf9f8, 0xfbfa, 0xfdfc, 0xfffe };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xffff, 0xfff1, 0xffff, 0xfff2, 0xffff, 0xfff3, 0xffff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xffff, 0xffff, 0xffff, 0xfff1, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6, 0xf9f8, 0xfbfa, 0xfdfc, 0xfffe };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xf3f2f1f0, 0xf7f6f5f4, 0xfbfaf9f8, 0xfffefdfc };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfff1fff0, 0xfff3fff2, 0xfff5fff4, 0xfff7fff6 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xffffffff, 0xfffffff1, 0xffffffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xf3f2f1f0, 0xf7f6f5f4, 0xfbfaf9f8, 0xfffefdfc };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfff1fff0, 0xfff3fff2, 0xfff5fff4, 0xfff7fff6 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xffffffff, 0xfffffff1, 0xffffffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xf3f2f1f0, 0xf7f6f5f4, 0xfbfaf9f8, 0xfffefdfc };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfff1fff0, 0xfff3fff2, 0xfff5fff4, 0xfff7fff6 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xf7f6f5f4f3f2f1f0, 0xfffefdfcfbfaf9f8 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfff3fff2fff1fff0, 0xfff7fff6fff5fff4 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffff1fffffff0, 0xfffffff3fffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xf7f6f5f4f3f2f1f0, 0xfffefdfcfbfaf9f8 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfff3fff2fff1fff0, 0xfff7fff6fff5fff4 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffff1fffffff0, 0xfffffff3fffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xf7f6f5f4f3f2f1f0, 0xfffefdfcfbfaf9f8 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfff3fff2fff1fff0, 0xfff7fff6fff5fff4 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6, 0xf9f8, 0xfbfa, 0xfdfc, 0xfffe };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xffff, 0xfff1, 0xffff, 0xfff2, 0xffff, 0xfff3, 0xffff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xffff, 0xffff, 0xffff, 0xfff1, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6, 0xf9f8, 0xfbfa, 0xfdfc, 0xfffe };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xffff, 0xfff1, 0xffff, 0xfff2, 0xffff, 0xfff3, 0xffff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xffff, 0xffff, 0xffff, 0xfff1, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6, 0xf9f8, 0xfbfa, 0xfdfc, 0xfffe };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xf3f2f1f0, 0xf7f6f5f4, 0xfbfaf9f8, 0xfffefdfc };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfff1fff0, 0xfff3fff2, 0xfff5fff4, 0xfff7fff6 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xffffffff, 0xfffffff1, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xf3f2f1f0, 0xf7f6f5f4, 0xfbfaf9f8, 0xfffefdfc };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfff1fff0, 0xfff3fff2, 0xfff5fff4, 0xfff7fff6 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xffffffff, 0xfffffff1, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xf3f2f1f0, 0xf7f6f5f4, 0xfbfaf9f8, 0xfffefdfc };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfff1fff0, 0xfff3fff2, 0xfff5fff4, 0xfff7fff6 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xf7f6f5f4f3f2f1f0, 0xfffefdfcfbfaf9f8 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfff3fff2fff1fff0, 0xfff7fff6fff5fff4 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffff1fffffff0, 0xfffffff3fffffff2 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xf7f6f5f4f3f2f1f0, 0xfffefdfcfbfaf9f8 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfff3fff2fff1fff0, 0xfff7fff6fff5fff4 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffff1fffffff0, 0xfffffff3fffffff2 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xf7f6f5f4f3f2f1f0, 0xfffefdfcfbfaf9f8 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfff3fff2fff1fff0, 0xfff7fff6fff5fff4 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff, 0xf4, 0xff, 0xf5, 0xff, 0xf6, 0xff, 0xf7, 0xff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff, 0xf2, 0xff, 0xff, 0xff, 0xf3, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff, 0xf4, 0xff, 0xf5, 0xff, 0xf6, 0xff, 0xf7, 0xff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff, 0xf2, 0xff, 0xff, 0xff, 0xf3, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xf1, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xff, 0xf1, 0xff, 0xf2, 0xff, 0xf3, 0xff, 0xf4, 0xff, 0xf5, 0xff, 0xf6, 0xff, 0xf7, 0xff };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xf3f2f1f0, 0xf7f6f5f4 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xfff1fff0, 0xfff3fff2 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xfffffff0, 0xffffffff };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xf3f2f1f0, 0xf7f6f5f4 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xfff1fff0, 0xfff3fff2 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xfffffff0, 0xffffffff };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xf3f2f1f0, 0xf7f6f5f4 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xfff1fff0, 0xfff3fff2 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xf3f2f1f0, 0xf7f6f5f4, 0xfbfaf9f8, 0xfffefdfc };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xfff1fff0, 0xfff3fff2, 0xfff5fff4, 0xfff7fff6 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xfffffff0, 0xffffffff, 0xfffffff1, 0xffffffff };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xf3f2f1f0, 0xf7f6f5f4, 0xfbfaf9f8, 0xfffefdfc };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xfff1fff0, 0xfff3fff2, 0xfff5fff4, 0xfff7fff6 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xfffffff0, 0xffffffff, 0xfffffff1, 0xffffffff };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xf3f2f1f0, 0xf7f6f5f4, 0xfbfaf9f8, 0xfffefdfc };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xfff1fff0, 0xfff3fff2, 0xfff5fff4, 0xfff7fff6 };
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x80, 0xc1, 0x0, 0x0, 0x70, 0xc1 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0xc180, 0x0, 0xc170 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xc1700000c1800000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x80, 0xc1, 0x0, 0x0, 0x70, 0xc1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0xc180, 0x0, 0xc170 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xc1700000c1800000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x0, 0x0, 0x80, 0xc1, 0x0, 0x0, 0x70, 0xc1 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x0, 0xc180, 0x0, 0xc170 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x80, 0xc1, 0x0, 0x0, 0x70, 0xc1, 0x0, 0x0, 0x60, 0xc1, 0x0, 0x0, 0x50, 0xc1 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0xc180, 0x0, 0xc170, 0x0, 0xc160, 0x0, 0xc150 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xc1700000c1800000, 0xc1500000c1600000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x80, 0xc1, 0x0, 0x0, 0x70, 0xc1, 0x0, 0x0, 0x60, 0xc1, 0x0, 0x0, 0x50, 0xc1 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0xc180, 0x0, 0xc170, 0x0, 0xc160, 0x0, 0xc150 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xc1700000c1800000, 0xc1500000c1600000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x0, 0x0, 0x80, 0xc1, 0x0, 0x0, 0x70, 0xc1, 0x0, 0x0, 0x60, 0xc1, 0x0, 0x0, 0x50, 0xc1 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x0, 0xc180, 0x0, 0xc170, 0x0, 0xc160, 0x0, 0xc150 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xfff0, 0xffff, 0xfff1, 0xffff };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xfff0, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xfff0, 0xffff, 0xfff1, 0xffff };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xfff0, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0xc180, 0x0, 0xc170 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6, 0xf9f8, 0xfbfa, 0xfdfc, 0xfffe };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xfff0, 0xffff, 0xfff1, 0xffff, 0xfff2, 0xffff, 0xfff3, 0xffff };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xfff0, 0xffff, 0xffff, 0xffff, 0xfff1, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6, 0xf9f8, 0xfbfa, 0xfdfc, 0xfffe };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xfff0, 0xffff, 0xfff1, 0xffff, 0xfff2, 0xffff, 0xfff3, 0xffff };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xfff0, 0xffff, 0xffff, 0xffff, 0xfff1, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xf1f0, 0xf3f2, 0xf5f4, 0xf7f6, 0xf9f8, 0xfbfa, 0xfdfc, 0xfffe };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0xc180, 0x0, 0xc170, 0x0, 0xc160, 0x0, 0xc150 };
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0xcc, 0x80, 0xcb, 0x0, 0xcb, 0x80, 0xca };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xcc00, 0xcb80, 0xcb00, 0xca80 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xcb80cc00, 0xca80cb00 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xca80cb00cb80cc00 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0xcc, 0x80, 0xcb, 0x0, 0xcb, 0x80, 0xca };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xcc00, 0xcb80, 0xcb00, 0xca80 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xcb80cc00, 0xca80cb00 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xca80cb00cb80cc00 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x0, 0xcc, 0x80, 0xcb, 0x0, 0xcb, 0x80, 0xca };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xcc00, 0xcb80, 0xcb00, 0xca80 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xcb80cc00, 0xca80cb00 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0xcc, 0x80, 0xcb, 0x0, 0xcb, 0x80, 0xca, 0x0, 0xca, 0x80, 0xc9, 0x0, 0xc9, 0x80, 0xc8 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xcc00, 0xcb80, 0xcb00, 0xca80, 0xca00, 0xc980, 0xc900, 0xc880 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xcb80cc00, 0xca80cb00, 0xc980ca00, 0xc880c900 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xca80cb00cb80cc00, 0xc880c900c980ca00 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0xcc, 0x80, 0xcb, 0x0, 0xcb, 0x80, 0xca, 0x0, 0xca, 0x80, 0xc9, 0x0, 0xc9, 0x80, 0xc8 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xcc00, 0xcb80, 0xcb00, 0xca80, 0xca00, 0xc980, 0xc900, 0xc880 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xcb80cc00, 0xca80cb00, 0xc980ca00, 0xc880c900 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xca80cb00cb80cc00, 0xc880c900c980ca00 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x0, 0xcc, 0x80, 0xcb, 0x0, 0xcb, 0x80, 0xca, 0x0, 0xca, 0x80, 0xc9, 0x0, 0xc9, 0x80, 0xc8 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xcc00, 0xcb80, 0xcb00, 0xca80, 0xca00, 0xc980, 0xc900, 0xc880 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xcb80cc00, 0xca80cb00, 0xc980ca00, 0xc880c900 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+
+VQRDMULH output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff5, 0xfff6, 0xfff7, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+
+VQRDMULH (check mul cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+
+VQRDMULH (check rounding cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+
+VQRDMULH_LANE output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+
+VQRDMULH_LANE (check mul cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+
+VQRDMULH_LANE (check rounding cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+
+VQRDMULH_N output:
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfffc, 0xfffc, 0xfffc, 0xfffd };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffe, 0xfffffffe };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x6, 0x6, 0x6, 0x5, 0x5, 0x4, 0x4, 0x4 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffffe, 0xfffffffe, 0xfffffffe, 0xfffffffe };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+
+VQRDMULH_N (check mul cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+
+VQRDMULH_N (check rounding cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQRSHL/VQRSHLQ (with input = 0) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQRSHL/VQRSHLQ (input 0 and negative shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQRSHL/VQRSHLQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xe0, 0xe2, 0xe4, 0xe6, 0xe8, 0xea, 0xec, 0xee };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xff80, 0xff88, 0xff90, 0xff98 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffff000, 0xfffff100 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffff80 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x8000000000000000, 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQRSHL/VQRSHLQ (negative shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xfc, 0xfc, 0xfd, 0xfd, 0xfd, 0xfd, 0xfe, 0xfe };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfffc, 0xfffc, 0xfffd, 0xfffd };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffe, 0xfffffffe };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x3c, 0x3c, 0x3d, 0x3d, 0x3d, 0x3d, 0x3e, 0x3e };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3ffc, 0x3ffc, 0x3ffd, 0x3ffd };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x1ffffffe, 0x1ffffffe };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x80000, 0x80000, 0x80000, 0x80000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x100000000000, 0x100000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: shift by -1) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x4000, 0x4000, 0x4000, 0x4000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x40000000, 0x40000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x4000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x4000, 0x4000, 0x4000, 0x4000, 0x4000, 0x4000, 0x4000, 0x4000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x40000000, 0x40000000, 0x40000000, 0x40000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x4000000000000000, 0x4000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x8000000000000000, 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: shift by -3) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x1000, 0x1000, 0x1000, 0x1000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x10000000, 0x10000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x1000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x2000, 0x2000, 0x2000, 0x2000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x20000000, 0x20000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x2000000000000000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x1000, 0x1000, 0x1000, 0x1000, 0x1000, 0x1000, 0x1000, 0x1000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x10000000, 0x10000000, 0x10000000, 0x10000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x1000000000000000, 0x1000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x20000000, 0x20000000, 0x20000000, 0x20000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x2000000000000000, 0x2000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x7fffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7fffffffffffffff, 0x7fffffffffffffff };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large shift amount with negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x8000000000000000, 0x8000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large negative shift amount) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large shift amount with 0 input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VABA/VABAQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x16, 0x17, 0x18, 0x19 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x20, 0x21 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5a };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x907, 0x908, 0x909, 0x90a };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffe7, 0xffffffe8 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x5e, 0x5f, 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x6a, 0x6b, 0x6c, 0x6d };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xb9c, 0xb9d, 0xb9e, 0xb9f, 0xba0, 0xba1, 0xba2, 0xba3 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x26e0, 0x26e1, 0x26e2, 0x26e3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff9, 0xfffa, 0xfffb, 0xfffc, 0xfffd, 0xfffe, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VABAL output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff6, 0xfff7, 0xfff8, 0xfff9, 0xfffa, 0xfffb, 0xfffc, 0xfffd };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x16, 0x17, 0x18, 0x19 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x20, 0x21 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x5a };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x907, 0x908, 0x909, 0x90a };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffe7, 0xffffffe8 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VABAL test intermediate overflow output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xef, 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffef, 0xfff0, 0xfff1, 0xfff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffef, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xee, 0xef, 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffe2, 0xffe3, 0xffe4, 0xffe5 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffe7, 0xffffffe8 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VABD/VABDQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x11, 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3, 0x2, 0x1, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x18, 0x17 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xef, 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffe3, 0xffe4, 0xffe5, 0xffe6 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffe8, 0xffffffe9 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x41c26666, 0x41ba6666 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x1a, 0x19, 0x18, 0x17, 0x16, 0x15, 0x14, 0x13, 0x12, 0x11, 0x10, 0xf, 0xe, 0xd, 0xc, 0xb };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x4, 0x3, 0x2, 0x1, 0x0, 0x1, 0x2, 0x3 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x30, 0x2f, 0x2e, 0x2d };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xe6, 0xe7, 0xe8, 0xe9, 0xea, 0xeb, 0xec, 0xed, 0xee, 0xef, 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffe4, 0xffe5, 0xffe6, 0xffe7, 0xffe8, 0xffe9, 0xffea, 0xffeb };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffd0, 0xffffffd1, 0xffffffd2, 0xffffffd3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x42407ae1, 0x423c7ae1, 0x42387ae1, 0x42347ae1 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+
+VABDL output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x11, 0x10, 0xf, 0xe, 0xd, 0xc, 0xb, 0xa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x3, 0x2, 0x1, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x18, 0x17 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xef, 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffe3, 0xffe4, 0xffe5, 0xffe6 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffe8, 0xffffffe9 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VAND/VANDQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x2, 0x2, 0x0, 0x0, 0x2, 0x2 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x60 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x10, 0x10, 0x10, 0x10, 0x14, 0x14, 0x14, 0x14 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x10, 0x10, 0x12, 0x12 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf0, 0xf2, 0xf2, 0xf4, 0xf4, 0xf6, 0xf6, 0xf0, 0xf0, 0xf2, 0xf2, 0xf4, 0xf4, 0xf6, 0xf6 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffe0, 0xffe0, 0xffe0, 0xffe0, 0xffe4, 0xffe4, 0xffe4, 0xffe4 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffe0, 0xffffffe0, 0xffffffe2, 0xffffffe2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x10, 0x10 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x4, 0x4, 0x4, 0x4, 0x8, 0x8, 0x8, 0x8, 0xc, 0xc, 0xc, 0xc };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x1, 0x2, 0x3, 0x0, 0x1, 0x2, 0x3 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x30, 0x31, 0x32, 0x33 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VORR/VORRQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf2, 0xf3, 0xf2, 0xf3, 0xf6, 0xf7, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff3, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff4 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf4, 0xf5, 0xf6, 0xf7, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfffe, 0xffff, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff8, 0xfffffff9 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf6, 0xf7, 0xf6, 0xf7, 0xf6, 0xf7, 0xf6, 0xf7, 0xfe, 0xff, 0xfe, 0xff, 0xfe, 0xff, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfffc, 0xfffd, 0xfffe, 0xffff, 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff2, 0xfffffff3, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff8, 0xfffffffffffffff9 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xfc, 0xfd, 0xfe, 0xff, 0xfc, 0xfd, 0xfe, 0xff, 0xfc, 0xfd, 0xfe, 0xff, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff3, 0xfff3, 0xfff3, 0xfff3, 0xfff7, 0xfff7, 0xfff7, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff7, 0xfffffff7, 0xfffffff7, 0xfffffff7 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff3, 0xfffffffffffffff3 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VORN/VORNQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xfd, 0xfd, 0xff, 0xff, 0xfd, 0xfd, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff3, 0xfff3, 0xfff3, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffc, 0xfffffffd };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffffb };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xfb, 0xfb, 0xfb, 0xfb, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff1, 0xfff1, 0xfff3, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff7, 0xfffffff7 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffffd };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf9, 0xf9, 0xfb, 0xfb, 0xfd, 0xfd, 0xff, 0xff, 0xf9, 0xf9, 0xfb, 0xfb, 0xfd, 0xfd, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff3, 0xfff3, 0xfff3, 0xfff3, 0xfff7, 0xfff7, 0xfff7, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffffd, 0xfffffffd, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff7, 0xfffffffffffffff7 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf3, 0xf3, 0xf3, 0xf3, 0xf7, 0xf7, 0xf7, 0xf7, 0xfb, 0xfb, 0xfb, 0xfb, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfffc, 0xfffd, 0xfffe, 0xffff, 0xfffc, 0xfffd, 0xfffe, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff8, 0xfffffff9, 0xfffffffa, 0xfffffffb };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffffc, 0xfffffffffffffffd };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VEOR/VEORQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf2, 0xf3, 0xf0, 0xf1, 0xf6, 0xf7, 0xf4, 0xf5 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xc, 0xd, 0xe, 0xf };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff3, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffff94 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xe4, 0xe5, 0xe6, 0xe7, 0xe0, 0xe1, 0xe2, 0xe3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffee, 0xffef, 0xffec, 0xffed };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffd8, 0xffffffd9 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x6, 0x7, 0x4, 0x5, 0x2, 0x3, 0x0, 0x1, 0xe, 0xf, 0xc, 0xd, 0xa, 0xb, 0x8, 0x9 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x1c, 0x1d, 0x1e, 0x1f, 0x18, 0x19, 0x1a, 0x1b };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x12, 0x13, 0x10, 0x11 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffe8, 0xffffffffffffffe9 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xfc, 0xfd, 0xfe, 0xff, 0xf8, 0xf9, 0xfa, 0xfb, 0xf4, 0xf5, 0xf6, 0xf7, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff3, 0xfff2, 0xfff1, 0xfff0, 0xfff7, 0xfff6, 0xfff5, 0xfff4 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffc7, 0xffffffc6, 0xffffffc5, 0xffffffc4 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff3, 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VBIC/VBICQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf0, 0xf1, 0xf4, 0xf5, 0xf4, 0xf5 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x1, 0x2, 0x3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffff90 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xe0, 0xe1, 0xe2, 0xe3, 0xe0, 0xe1, 0xe2, 0xe3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffe0, 0xffe1, 0xffe0, 0xffe1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffd0, 0xffffffd1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x1, 0x0, 0x1, 0x0, 0x1, 0x0, 0x1, 0x8, 0x9, 0x8, 0x9, 0x8, 0x9, 0x8, 0x9 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x10, 0x11, 0x12, 0x13, 0x10, 0x11, 0x12, 0x13 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x10, 0x11, 0x10, 0x11 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffe0, 0xffffffffffffffe1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff4, 0xfff4, 0xfff4, 0xfff4 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffc0, 0xffffffc0, 0xffffffc0, 0xffffffc0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VCREATE output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xde, 0xbc, 0x9a, 0x78, 0x56, 0x34, 0x12 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xdef0, 0x9abc, 0x5678, 0x1234 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x9abcdef0, 0x12345678 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x123456789abcdef0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xde, 0xbc, 0x9a, 0x78, 0x56, 0x34, 0x12 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xdef0, 0x9abc, 0x5678, 0x1234 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x9abcdef0, 0x12345678 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x123456789abcdef0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xde, 0xbc, 0x9a, 0x78, 0x56, 0x34, 0x12 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xdef0, 0x9abc, 0x5678, 0x1234 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x9abcdef0, 0x12345678 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xdef0, 0x9abc, 0x5678, 0x1234 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VLD2_LANE/VLD2Q_LANE chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xcc00, 0xcb80, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xcc00, 0xcb80, 0xaaaa, 0xaaaa };
+
+VLD2_LANE/VLD2Q_LANE chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xf0, 0xf1 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0, 0xfff1, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xfff0, 0xfff1, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xfff0, 0xfff1, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+
+VLD3_LANE/VLD3Q_LANE chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xcc00, 0xcb80, 0xcb00, 0xaaaa };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xcc00, 0xcb80 };
+
+VLD3_LANE/VLD3Q_LANE chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xf0, 0xf1, 0xf2, 0xaa };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xaaaaaaaa, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xf0, 0xf1, 0xf2, 0xaa };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xcb00, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+
+VLD3_LANE/VLD3Q_LANE chunk 2 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xf0, 0xf1, 0xf2 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff2, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xaaaa, 0xfff0, 0xfff1, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff1, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xaaaa, 0xfff0, 0xfff1, 0xfff2 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xfff0, 0xfff1, 0xfff2, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff2, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff1, 0xfff2, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff1, 0xfff2, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1600000, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+
+VLD4_LANE/VLD4Q_LANE chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xcc00, 0xcb80, 0xcb00, 0xca80 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+
+VLD4_LANE/VLD4Q_LANE chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xcc00, 0xcb80, 0xcb00, 0xca80, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+
+VLD4_LANE/VLD4Q_LANE chunk 2 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+
+VLD4_LANE/VLD4Q_LANE chunk 3 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa, 0xaa };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa, 0xaaaaaaaa };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa, 0xaaaa };
+
+VLD2_DUP/VLD2Q_DUP chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf0, 0xf1, 0xf0, 0xf1, 0xf0, 0xf1 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf0, 0xf1, 0xf0, 0xf1, 0xf0, 0xf1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf0, 0xf1, 0xf0, 0xf1, 0xf0, 0xf1 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xcc00, 0xcb80, 0xcc00, 0xcb80 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VLD2_DUP/VLD2Q_DUP chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf0, 0xf1, 0xf0, 0xf1, 0xf0, 0xf1 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf0, 0xf1, 0xf0, 0xf1, 0xf0, 0xf1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf0, 0xf1, 0xf0, 0xf1, 0xf0, 0xf1 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xcc00, 0xcb80, 0xcc00, 0xcb80 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VLD3_DUP/VLD3Q_DUP chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf0, 0xf1, 0xf2, 0xf0, 0xf1 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf0, 0xf1, 0xf2, 0xf0, 0xf1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf0, 0xf1, 0xf2, 0xf0, 0xf1 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xcc00, 0xcb80, 0xcb00, 0xcc00 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VLD3_DUP/VLD3Q_DUP chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf2, 0xf0, 0xf1, 0xf2, 0xf0, 0xf1, 0xf2, 0xf0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff1, 0xfff2, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf2, 0xf0, 0xf1, 0xf2, 0xf0, 0xf1, 0xf2, 0xf0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff1, 0xfff2, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf2, 0xf0, 0xf1, 0xf2, 0xf0, 0xf1, 0xf2, 0xf0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff1, 0xfff2, 0xfff0, 0xfff1 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xc1800000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xcb80, 0xcb00, 0xcc00, 0xcb80 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VLD3_DUP/VLD3Q_DUP chunk 2 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf1, 0xf2, 0xf0, 0xf1, 0xf2, 0xf0, 0xf1, 0xf2 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff2, 0xfff0, 0xfff1, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff1, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf1, 0xf2, 0xf0, 0xf1, 0xf2, 0xf0, 0xf1, 0xf2 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff2, 0xfff0, 0xfff1, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff1, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf1, 0xf2, 0xf0, 0xf1, 0xf2, 0xf0, 0xf1, 0xf2 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff2, 0xfff0, 0xfff1, 0xfff2 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1700000, 0xc1600000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xcb00, 0xcc00, 0xcb80, 0xcb00 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VLD4_DUP/VLD4Q_DUP chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xcc00, 0xcb80, 0xcb00, 0xca80 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VLD4_DUP/VLD4Q_DUP chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xcc00, 0xcb80, 0xcb00, 0xca80 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VLD4_DUP/VLD4Q_DUP chunk 2 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff2 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xcc00, 0xcb80, 0xcb00, 0xca80 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VLD4_DUP/VLD4Q_DUP chunk 3 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff3 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff3 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf0, 0xf1, 0xf2, 0xf3 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xcc00, 0xcb80, 0xcb00, 0xca80 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VMLA output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xdf, 0xe0, 0xe1, 0xe2, 0xe3, 0xe4, 0xe5, 0xe6 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x1f8c, 0x1f8d, 0x1f8e, 0x1f8f };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x2bf7, 0x2bf8 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x43ac, 0x43ad };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x43a14e76, 0x43a1ce76 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf, 0x10, 0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18, 0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x4830, 0x4831, 0x4832, 0x4833, 0x4834, 0x4835, 0x4836, 0x4837 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x470f, 0x4710, 0x4711, 0x4712 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xac, 0xad, 0xae, 0xaf, 0xb0, 0xb1, 0xb2, 0xb3, 0xb4, 0xb5, 0xb6, 0xb7, 0xb8, 0xb9, 0xba, 0xbb };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a, 0x3e0b, 0x3e0c, 0x3e0d, 0x3e0e };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x3620, 0x3621, 0x3622, 0x3623 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x45f0ae15, 0x45f0b615, 0x45f0be15, 0x45f0c615 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VMLS output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xe054, 0xe055, 0xe056, 0xe057 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xffffd3e9, 0xffffd3ea };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xc0, 0xc1, 0xc2, 0xc3, 0xc4, 0xc5, 0xc6, 0xc7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xc1d9, 0xc1da, 0xc1db, 0xc1dc };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffbc34, 0xffffbc35 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc3b14e76, 0xc3b0ce76 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf, 0xe0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xb7b0, 0xb7b1, 0xb7b2, 0xb7b3, 0xb7b4, 0xb7b5, 0xb7b6, 0xb7b7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffb8d1, 0xffffb8d2, 0xffffb8d3, 0xffffb8d4 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x34, 0x35, 0x36, 0x37, 0x38, 0x39, 0x3a, 0x3b, 0x3c, 0x3d, 0x3e, 0x3f, 0x40, 0x41, 0x42, 0x43 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xc1d9, 0xc1da, 0xc1db, 0xc1dc, 0xc1dd, 0xc1de, 0xc1df, 0xc1e0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffc9c0, 0xffffc9c1, 0xffffc9c2, 0xffffc9c3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc5f1ae15, 0xc5f1a615, 0xc5f19e15, 0xc5f19615 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VMUL output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0x1, 0x12, 0x23, 0x34, 0x45, 0x56, 0x67 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfde0, 0xfe02, 0xfe24, 0xfe46 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffcd0, 0xfffffd03 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xc0, 0x4, 0x48, 0x8c, 0xd0, 0x14, 0x58, 0x9c };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfab0, 0xfb05, 0xfb5a, 0xfbaf };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffff9a0, 0xfffffa06 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xc0, 0x84, 0x48, 0xc, 0xd0, 0x94, 0x58, 0x1c };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc4053333, 0xc3f9c000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x90, 0x7, 0x7e, 0xf5, 0x6c, 0xe3, 0x5a, 0xd1, 0x48, 0xbf, 0x36, 0xad, 0x24, 0x9b, 0x12, 0x89 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xf780, 0xf808, 0xf890, 0xf918, 0xf9a0, 0xfa28, 0xfab0, 0xfb38 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffff670, 0xfffff709, 0xfffff7a2, 0xfffff83b };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x60, 0xa, 0xb4, 0x5e, 0x8, 0xb2, 0x5c, 0x6, 0xb0, 0x5a, 0x4, 0xae, 0x58, 0x2, 0xac, 0x56 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xf450, 0xf50b, 0xf5c6, 0xf681, 0xf73c, 0xf7f7, 0xf8b2, 0xf96d };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffff340, 0xfffff40c, 0xfffff4d8, 0xfffff5a4 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x60, 0xca, 0x34, 0x9e, 0xc8, 0x62, 0x9c, 0x36, 0x30, 0x9a, 0x64, 0xce, 0x98, 0x32, 0xcc, 0x66 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc4c73333, 0xc4bac000, 0xc4ae4ccd, 0xc4a1d999 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VMUL_LANE output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffc0, 0xffc4, 0xffc8, 0xffcc };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffde0, 0xfffffe02 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xbbc0, 0xc004, 0xc448, 0xc88c };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffface0, 0xffffb212 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc3b66666, 0xc3ab0000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffc0, 0xffc4, 0xffc8, 0xffcc, 0xffd0, 0xffd4, 0xffd8, 0xffdc };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffde0, 0xfffffe02, 0xfffffe24, 0xfffffe46 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xbbc0, 0xc004, 0xc448, 0xc88c, 0xccd0, 0xd114, 0xd558, 0xd99c };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffface0, 0xffffb212, 0xffffb744, 0xffffbc76 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc3b66666, 0xc3ab0000, 0xc39f9999, 0xc3943333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VMUL_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfef0, 0xff01, 0xff12, 0xff23 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffde0, 0xfffffe02 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfcd0, 0xfd03, 0xfd36, 0xfd69 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffbc0, 0xfffffc04 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc3b26666, 0xc3a74000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfab0, 0xfb05, 0xfb5a, 0xfbaf, 0xfc04, 0xfc59, 0xfcae, 0xfd03 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffff9a0, 0xfffffa06, 0xfffffa6c, 0xfffffad2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xf890, 0xf907, 0xf97e, 0xf9f5, 0xfa6c, 0xfae3, 0xfb5a, 0xfbd1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffff780, 0xfffff808, 0xfffff890, 0xfffff918 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc4b1cccd, 0xc4a6b000, 0xc49b9333, 0xc4907667 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VMULL_N output:
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x11000, 0x11000, 0x11000, 0x11000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x22000, 0x22000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33000, 0x33000, 0x33000, 0x33000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x44000, 0x44000 };
+
+VMLA_LANE output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x3e07, 0x3e08 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x3e07, 0x3e08 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x4418c687, 0x44190687 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a, 0x3e0b, 0x3e0c, 0x3e0d, 0x3e0e };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a, 0x3e0b, 0x3e0c, 0x3e0d, 0x3e0e };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x3e07, 0x3e08, 0x3e09, 0x3e0a };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x441a3168, 0x441a7168, 0x441ab168, 0x441af168 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VMLS_LANE output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xc1d9, 0xc1da, 0xc1db, 0xc1dc };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xffffc1d9, 0xffffc1da };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xc1d9, 0xc1da, 0xc1db, 0xc1dc };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffc1d9, 0xffffc1da };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc420c687, 0xc4208687 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xc1d9, 0xc1da, 0xc1db, 0xc1dc, 0xc1dd, 0xc1de, 0xc1df, 0xc1e0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffc1d9, 0xffffc1da, 0xffffc1db, 0xffffc1dc };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xc1d9, 0xc1da, 0xc1db, 0xc1dc, 0xc1dd, 0xc1de, 0xc1df, 0xc1e0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffc1d9, 0xffffc1da, 0xffffc1db, 0xffffc1dc };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc4223168, 0xc421f168, 0xc421b168, 0xc4217168 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VMLA_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x595, 0x596, 0x597, 0x598 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xb3a, 0xb3b };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x10df, 0x10e0, 0x10e1, 0x10e2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x1684, 0x1685 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x4497deb8, 0x4497feb8 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x1c29, 0x1c2a, 0x1c2b, 0x1c2c, 0x1c2d, 0x1c2e, 0x1c2f, 0x1c30 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x21ce, 0x21cf, 0x21d0, 0x21d1 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x2773, 0x2774, 0x2775, 0x2776, 0x2777, 0x2778, 0x2779, 0x277a };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x2d18, 0x2d19, 0x2d1a, 0x2d1b };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x4568087b, 0x4568187b, 0x4568287b, 0x4568387b };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VMLS_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfa4b, 0xfa4c, 0xfa4d, 0xfa4e };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffff4a6, 0xfffff4a7 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xef01, 0xef02, 0xef03, 0xef04 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffe95c, 0xffffe95d };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc49bdeb8, 0xc49bbeb8 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xe3b7, 0xe3b8, 0xe3b9, 0xe3ba, 0xe3bb, 0xe3bc, 0xe3bd, 0xe3be };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffde12, 0xffffde13, 0xffffde14, 0xffffde15 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xd86d, 0xd86e, 0xd86f, 0xd870, 0xd871, 0xd872, 0xd873, 0xd874 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffd2c8, 0xffffd2c9, 0xffffd2ca, 0xffffd2cb };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc56a087b, 0xc569f87b, 0xc569e87b, 0xc569d87b };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VSLI_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x20, 0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffe0, 0xffe1, 0xffe2, 0xffe3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x6, 0x7 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x64fffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x50, 0x51, 0x52, 0x53, 0x50, 0x51, 0x52, 0x53 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x7bf0, 0x7bf1, 0x7bf2, 0x7bf3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x3ffffff0, 0x3ffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x10 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x50, 0x51, 0x52, 0x53, 0x50, 0x51, 0x52, 0x53 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x7bf0, 0x7bf1, 0x7bf2, 0x7bf3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xd0, 0xd1, 0xd2, 0xd3, 0xd4, 0xd5, 0xd6, 0xd7, 0xd8, 0xd9, 0xda, 0xdb, 0xdc, 0xdd, 0xde, 0xdf };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xff60, 0xff61, 0xff62, 0xff63, 0xff64, 0xff65, 0xff66, 0xff67 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfe2ffff0, 0xfe2ffff1, 0xfe2ffff2, 0xfe2ffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x18fff0, 0x18fff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3ff0, 0x3ff1, 0x3ff2, 0x3ff3, 0x3ff4, 0x3ff5, 0x3ff6, 0x3ff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1bfffff0, 0x1bfffff1, 0x1bfffff2, 0x1bfffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x7ffffffffffff0, 0x7ffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x60, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3ff0, 0x3ff1, 0x3ff2, 0x3ff3, 0x3ff4, 0x3ff5, 0x3ff6, 0x3ff7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VSLI_Nmax shift amount output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7ff0, 0x7ff1, 0x7ff2, 0x7ff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x7ffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x7ff0, 0x7ff1, 0x7ff2, 0x7ff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x7ffffff0, 0x7ffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x7ffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x7ff0, 0x7ff1, 0x7ff2, 0x7ff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x7ff0, 0x7ff1, 0x7ff2, 0x7ff3, 0x7ff4, 0x7ff5, 0x7ff6, 0x7ff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7ffffff0, 0x7ffffff1, 0x7ffffff2, 0x7ffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x7ffffffffffffff0, 0x7ffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x7a, 0x7b, 0x7c, 0x7d, 0x7e, 0x7f };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VSRI_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x80000001, 0x80000001 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffff00000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xc5, 0xc5, 0xc5, 0xc5, 0xc5, 0xc5, 0xc5, 0xc5 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffc0, 0xffc0, 0xffc0, 0xffc0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xe000000000000000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xc5, 0xc5, 0xc5, 0xc5, 0xc5, 0xc5, 0xc5, 0xc5 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xffc0, 0xffc0, 0xffc0, 0xffc0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf7, 0xf7, 0xf7, 0xf7, 0xf7, 0xf7, 0xf7, 0xf7, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0xfffd, 0xfffd };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffff000000000000, 0xffff000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffe00, 0xfffffe00, 0xfffffe00, 0xfffffe00 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffff800, 0xfffffffffffff800 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1, 0xe1 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0, 0xfff0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VSRI_N max shift amount output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0xf4, 0xf5, 0xf6, 0xf7, 0xf8, 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VTST/VTSTQ (signed input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0xffff, 0x0, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0xffff, 0x0, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0xffffffff, 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VTST/VTSTQ (unsigned input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0xffff, 0x0, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0xffff, 0x0, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0xffffffff, 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VADDHN output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x32, 0x32, 0x32, 0x32, 0x32, 0x32, 0x32, 0x32 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x32, 0x32, 0x32, 0x32 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x18, 0x18 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x37, 0x37, 0x37, 0x37 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x3, 0x3 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRADDHN output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x19, 0x19 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x4, 0x4, 0x4, 0x4, 0x4, 0x4, 0x4, 0x4 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x38, 0x38, 0x38, 0x38 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x4, 0x4 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VADDL output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffe3, 0xffe4, 0xffe5, 0xffe6, 0xffe7, 0xffe8, 0xffe9, 0xffea };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffe2, 0xffffffe3, 0xffffffe4, 0xffffffe5 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffe0, 0xffffffffffffffe1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1e3, 0x1e4, 0x1e5, 0x1e6, 0x1e7, 0x1e8, 0x1e9, 0x1ea };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1ffe1, 0x1ffe2, 0x1ffe3, 0x1ffe4 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x1ffffffe0, 0x1ffffffe1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VADDW output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffe3, 0xffe4, 0xffe5, 0xffe6, 0xffe7, 0xffe8, 0xffe9, 0xffea };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffe2, 0xffffffe3, 0xffffffe4, 0xffffffe5 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffe0, 0xffffffffffffffe1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xe3, 0xe4, 0xe5, 0xe6, 0xe7, 0xe8, 0xe9, 0xea };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffe1, 0xffe2, 0xffe3, 0xffe4 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffe0, 0xffffffe1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VHADD/VHADDQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf1, 0xf2, 0xf2, 0xf3, 0xf3, 0xf4, 0xf4, 0xf5 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff1, 0xfff1, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf1, 0xf2, 0xf2, 0xf3, 0xf3, 0xf4, 0xf4, 0xf5 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff1, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf2, 0xf2, 0xf3, 0xf3, 0xf4, 0xf4, 0xf5, 0xf5, 0xf6, 0xf6, 0xf7, 0xf7, 0xf8, 0xf8, 0xf9, 0xf9 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff1, 0xfff2, 0xfff2, 0xfff3, 0xfff3, 0xfff4, 0xfff4, 0xfff5 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff1, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf4, 0xf5, 0xf5, 0xf6, 0xf6, 0xf7, 0xf7, 0xf8, 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb, 0xfc };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff1, 0xfff1, 0xfff2, 0xfff2, 0xfff3, 0xfff3, 0xfff4, 0xfff4 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff1, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRHADD/VRHADDQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf2, 0xf2, 0xf3, 0xf3, 0xf4, 0xf4, 0xf5, 0xf5 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff1, 0xfff2, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf2, 0xf2, 0xf3, 0xf3, 0xf4, 0xf4, 0xf5, 0xf5 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff1, 0xfff1, 0xfff2, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf2, 0xf3, 0xf3, 0xf4, 0xf4, 0xf5, 0xf5, 0xf6, 0xf6, 0xf7, 0xf7, 0xf8, 0xf8, 0xf9, 0xf9, 0xfa };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff2, 0xfff2, 0xfff3, 0xfff3, 0xfff4, 0xfff4, 0xfff5, 0xfff5 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff1, 0xfffffff1, 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf5, 0xf5, 0xf6, 0xf6, 0xf7, 0xf7, 0xf8, 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb, 0xfc, 0xfc };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff1, 0xfff2, 0xfff2, 0xfff3, 0xfff3, 0xfff4, 0xfff4, 0xfff5 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff1, 0xfffffff1, 0xfffffff2, 0xfffffff2 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VHSUB/VHSUBQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xfe, 0xff, 0xff, 0x0, 0x0, 0x1, 0x1, 0x2 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffff, 0xffff, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xfe, 0xff, 0xff, 0x0, 0x0, 0x1, 0x1, 0x2 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0x0, 0x0, 0x1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xfe, 0xfe, 0xff, 0xff, 0x0, 0x0, 0x1, 0x1, 0x2, 0x2, 0x3, 0x3, 0x4, 0x4, 0x5, 0x5 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfffe, 0xffff, 0xffff, 0x0, 0x0, 0x1, 0x1, 0x2 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffff, 0x0, 0x0, 0x1 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xfb, 0xfc, 0xfc, 0xfd, 0xfd, 0xfe, 0xfe, 0xff, 0xff, 0x0, 0x0, 0x1, 0x1, 0x2, 0x2, 0x3 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0x0, 0x0, 0x1, 0x1, 0x2, 0x2 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0x0, 0x0, 0x1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VSUBL output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfffd, 0xfffe, 0xffff, 0x0, 0x1, 0x2, 0x3, 0x4 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffffe, 0xffffffff, 0x0, 0x1 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfffd, 0xfffe, 0xffff, 0x0, 0x1, 0x2, 0x3, 0x4 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0x0, 0x1, 0x2 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VSUBW output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfffd, 0xfffe, 0xffff, 0x0, 0x1, 0x2, 0x3, 0x4 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffffe, 0xffffffff, 0x0, 0x1 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfefd, 0xfefe, 0xfeff, 0xff00, 0xff01, 0xff02, 0xff03, 0xff04 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffeffff, 0xffff0000, 0xffff0001, 0xffff0002 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffff00000000, 0xffffffff00000001 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VSUBHN output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x31, 0x31, 0x31, 0x31, 0x31, 0x31, 0x31, 0x31 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x31, 0x31, 0x31, 0x31 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x17, 0x17 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x36, 0x36, 0x36, 0x36 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x2, 0x2 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSUBHN output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x31, 0x31, 0x31, 0x31, 0x31, 0x31, 0x31, 0x31 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x31, 0x31, 0x31, 0x31 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x17, 0x17 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x36, 0x36, 0x36, 0x36 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x2, 0x2 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VMVN/VMVNQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9, 0x8 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xf, 0xe, 0xd, 0xc };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xf, 0xe };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9, 0x8 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xf, 0xe, 0xd, 0xc };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xf, 0xe };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9, 0x8 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9, 0x8, 0x7, 0x6, 0x5, 0x4, 0x3, 0x2, 0x1, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9, 0x8 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xf, 0xe, 0xd, 0xc };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9, 0x8, 0x7, 0x6, 0x5, 0x4, 0x3, 0x2, 0x1, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9, 0x8 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xf, 0xe, 0xd, 0xc };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0xf, 0xe, 0xd, 0xc, 0xb, 0xa, 0x9, 0x8, 0x7, 0x6, 0x5, 0x4, 0x3, 0x2, 0x1, 0x0 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+
+VQMOVN output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x12, 0x12, 0x12, 0x12, 0x12, 0x12, 0x12, 0x12 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x1278, 0x1278, 0x1278, 0x1278 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x12345678, 0x12345678 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x82, 0x82, 0x82, 0x82, 0x82, 0x82, 0x82, 0x82 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x8765, 0x8765, 0x8765, 0x8765 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x87654321, 0x87654321 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+
+VQMOVN output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 0;
+
+VQMOVUN output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x34, 0x34, 0x34, 0x34, 0x34, 0x34, 0x34, 0x34 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x5678, 0x5678, 0x5678, 0x5678 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x12345678, 0x12345678 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,uint,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,2) = 1;
+
+VQMOVUN (negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSHR_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb, 0xfc };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffc, 0xfffffffc };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x3c, 0x3c, 0x3d, 0x3d, 0x3d, 0x3d, 0x3e, 0x3e };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x1ffe, 0x1ffe, 0x1ffe, 0x1ffe };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x8000000, 0x8000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x80000000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb, 0xfc, 0xfc, 0xfd, 0xfd, 0xfe, 0xfe, 0xff, 0xff, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffffc, 0xfffffffc, 0xfffffffd, 0xfffffffd };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x3c, 0x3c, 0x3d, 0x3d, 0x3d, 0x3d, 0x3e, 0x3e, 0x3e, 0x3e, 0x3f, 0x3f, 0x3f, 0x3f, 0x40, 0x40 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1ffe, 0x1ffe, 0x1ffe, 0x1ffe, 0x1fff, 0x1fff, 0x1fff, 0x1fff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x8000000, 0x8000000, 0x8000000, 0x8000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSHR_N (overflow test: max shift amount, positive input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSHR_N (overflow test: shift by 1, with negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x4000, 0x4000, 0x4000, 0x4000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x40000000, 0x40000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x4000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x4000, 0x4000, 0x4000, 0x4000, 0x4000, 0x4000, 0x4000, 0x4000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x40000000, 0x40000000, 0x40000000, 0x40000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x4000000000000000, 0x4000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x8000000000000000, 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSHR_N (overflow test: shift by 3, positive input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x1000, 0x1000, 0x1000, 0x1000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x10000000, 0x10000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x1000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x2000, 0x2000, 0x2000, 0x2000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x20000000, 0x20000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x2000000000000000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x1000, 0x1000, 0x1000, 0x1000, 0x1000, 0x1000, 0x1000, 0x1000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x10000000, 0x10000000, 0x10000000, 0x10000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x1000000000000000, 0x1000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x20000000, 0x20000000, 0x20000000, 0x20000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x2000000000000000, 0x2000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSHR_N (overflow test: shift by 1, with negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xc000, 0xc000, 0xc000, 0xc000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xc0000000, 0xc0000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xc000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xc000, 0xc000, 0xc000, 0xc000, 0xc000, 0xc000, 0xc000, 0xc000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xc0000000, 0xc0000000, 0xc0000000, 0xc0000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xc000000000000000, 0xc000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x8000000000000000, 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSHR_N (overflow test: shift by 3, with negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xf000, 0xf000, 0xf000, 0xf000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xf0000000, 0xf0000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xf000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x2000, 0x2000, 0x2000, 0x2000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x20000000, 0x20000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x2000000000000000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xf000, 0xf000, 0xf000, 0xf000, 0xf000, 0xf000, 0xf000, 0xf000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xf0000000, 0xf0000000, 0xf0000000, 0xf0000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xf000000000000000, 0xf000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x20000000, 0x20000000, 0x20000000, 0x20000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x2000000000000000, 0x2000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSRA_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffd, 0xfffffffe };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfffd, 0xfffe, 0xffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff4, 0xfffffff5 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffff0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf9, 0xfa, 0xfb, 0xfc, 0xfd, 0xfe, 0xff, 0x0, 0x1, 0x2, 0x3, 0x4, 0x5, 0x6, 0x7, 0x8 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0xfff4, 0xfff5, 0xfff6, 0xfff7 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffffd, 0xfffffffe, 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x5, 0x6, 0x7, 0x8, 0x9, 0xa, 0xb, 0xc, 0xd, 0xe, 0xf, 0x10, 0x11, 0x12, 0x13, 0x14 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfffd, 0xfffe, 0xffff, 0x0, 0x1, 0x2, 0x3, 0x4 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff4, 0xfffffff5, 0xfffffff6, 0xfffffff7 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffff0, 0xfffffffffffffff1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSRA_N (checking overflow: shift by 1, positive input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x4000, 0x4000, 0x4000, 0x4000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x40000000, 0x40000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x4000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x4000, 0x4000, 0x4000, 0x4000, 0x4000, 0x4000, 0x4000, 0x4000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x40000000, 0x40000000, 0x40000000, 0x40000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x4000000000000000, 0x4000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x8000000000000000, 0x8000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSRA_N (checking overflow: shift by 3, positive input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x1000, 0x1000, 0x1000, 0x1000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x10000000, 0x10000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x1000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x2000, 0x2000, 0x2000, 0x2000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x20000000, 0x20000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x2000000000000000 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x1000, 0x1000, 0x1000, 0x1000, 0x1000, 0x1000, 0x1000, 0x1000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x10000000, 0x10000000, 0x10000000, 0x10000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x1000000000000000, 0x1000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000, 0x2000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x20000000, 0x20000000, 0x20000000, 0x20000000 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x2000000000000000, 0x2000000000000000 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSRA_N (checking overflow: shift by max, positive input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSRA_N (checking overflow: shift by 1, negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xc000, 0xc000, 0xc000, 0xc000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xc0000000, 0xc0000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xc000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0, 0xc0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xc000, 0xc000, 0xc000, 0xc000, 0xc000, 0xc000, 0xc000, 0xc000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xc0000000, 0xc0000000, 0xc0000000, 0xc0000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xc000000000000000, 0xc000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSRA_N (checking overflow: shift by max, negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xf000, 0xf000, 0xf000, 0xf000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xf0000000, 0xf0000000 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xf000000000000000 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0, 0xf0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xf000, 0xf000, 0xf000, 0xf000, 0xf000, 0xf000, 0xf000, 0xf000 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xf0000000, 0xf0000000, 0xf0000000, 0xf0000000 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xf000000000000000, 0xf000000000000000 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VRSRA_N (checking overflow: shift by max, negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VSHLL_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffe0, 0xffe2, 0xffe4, 0xffe6, 0xffe8, 0xffea, 0xffec, 0xffee };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffe0, 0xffffffe2, 0xffffffe4, 0xffffffe6 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffff80, 0xffffffffffffff88 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3c0, 0x3c4, 0x3c8, 0x3cc, 0x3d0, 0x3d4, 0x3d8, 0x3dc };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfff00, 0xfff10, 0xfff20, 0xfff30 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x7ffffff80, 0x7ffffff88 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VPADDL/VPADDLQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffe1, 0xffe5, 0xffe9, 0xffed };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xffffffe1, 0xffffffe5 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffffe1 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x1e1, 0x1e5, 0x1e9, 0x1ed };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x1ffe1, 0x1ffe5 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x1ffffffe1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffe1, 0xffe5, 0xffe9, 0xffed, 0xfff1, 0xfff5, 0xfff9, 0xfffd };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffe1, 0xffffffe5, 0xffffffe9, 0xffffffed };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffe1, 0xffffffffffffffe5 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1e1, 0x1e5, 0x1e9, 0x1ed, 0x1f1, 0x1f5, 0x1f9, 0x1fd };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1ffe1, 0x1ffe5, 0x1ffe9, 0x1ffed };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x1ffffffe1, 0x1ffffffe5 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VPADD output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xe1, 0xe5, 0xe9, 0xed, 0xe1, 0xe5, 0xe9, 0xed };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffe1, 0xffe5, 0xffe1, 0xffe5 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xffffffe1, 0xffffffe1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xe1, 0xe5, 0xe9, 0xed, 0xe1, 0xe5, 0xe9, 0xed };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffe1, 0xffe5, 0xffe1, 0xffe5 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffe1, 0xffffffe1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1f80000, 0xc1f80000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VPADAL/VPADALQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xffd1, 0xffd6, 0xffdb, 0xffe0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xffffffd1, 0xffffffd6 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0xffffffffffffffd1 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x1d1, 0x1d6, 0x1db, 0x1e0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x1ffd1, 0x1ffd6 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x1ffffffd1 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xffd1, 0xffd6, 0xffdb, 0xffe0, 0xffe5, 0xffea, 0xffef, 0xfff4 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xffffffd1, 0xffffffd6, 0xffffffdb, 0xffffffe0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0xffffffffffffffd1, 0xffffffffffffffd6 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x1d1, 0x1d6, 0x1db, 0x1e0, 0x1e5, 0x1ea, 0x1ef, 0x1f4 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1ffd1, 0x1ffd6, 0x1ffdb, 0x1ffe0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x1ffffffd1, 0x1ffffffd6 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQSHLU_N/VQSHLUQ_N (negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x0 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQSHLU_N/VQSHLUQ_N (check cumulative saturation: shift by 1) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfffe, 0xfffe, 0xfffe, 0xfffe };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffffe, 0xfffffffe };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xfffffffffffffffe };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe, 0xfe };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfffe, 0xfffe, 0xfffe, 0xfffe, 0xfffe, 0xfffe, 0xfffe, 0xfffe };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffffe, 0xfffffffe, 0xfffffffe, 0xfffffffe };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xfffffffffffffffe, 0xfffffffffffffffe };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 1;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 1;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQSHLU_N/VQSHLUQ_N (check cumulative saturation: shift by 2) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0xffffffffffffffff, 0xffffffffffffffff };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,8,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,2) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,1) = 0;
+int VECT_VAR(expected_cumulative_sat,int,8,16) = 0;
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQSHLU_N/VQSHLUQ_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x8, 0x8, 0x8, 0x8 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x18, 0x18 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x40 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0, 0xa0 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x180, 0x180, 0x180, 0x180, 0x180, 0x180, 0x180, 0x180 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x380, 0x380, 0x380, 0x380 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x800, 0x800 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VCLZ/VCLZQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3, 0x3, 0x3, 0x3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x11, 0x11 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x5, 0x5 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x3, 0x3, 0x3, 0x3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3, 0x3 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xd, 0xd, 0xd, 0xd, 0xd, 0xd, 0xd, 0xd };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x1f, 0x1f, 0x1f, 0x1f };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VCLZ/VCLZQ (input=0) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x20, 0x20 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10, 0x10 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x20, 0x20, 0x20, 0x20 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VCLS/VCLSQ (positive input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x2, 0x2, 0x2, 0x2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x19, 0x19 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x14, 0x14, 0x14, 0x14 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VCLS/VCLSQ (negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7, 0x7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x1, 0x1, 0x1, 0x1 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x1, 0x1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2, 0x2 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VCNT/VCNTQ output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8, 0x8 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x4, 0x4, 0x4, 0x4, 0x4, 0x4, 0x4, 0x4 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x4, 0x4, 0x4, 0x4, 0x4, 0x4, 0x4, 0x4 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6, 0x6 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQSHRN_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf8, 0xf9, 0xf9, 0xfa, 0xfa, 0xfb, 0xfb };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff8, 0xfff8, 0xfff9, 0xfff9 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffffc, 0xfffffffc };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 1;
+
+VQSHRN_N (check saturation: shift by 3) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,uint,64,2) = 0;
+
+VQSHRN_N (check saturation: shift by max) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f, 0x7f };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x7fff, 0x7fff, 0x7fff, 0x7fff };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VPMAX output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf1, 0xf3, 0xf5, 0xf7, 0xf1, 0xf3, 0xf5, 0xf7 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff1, 0xfff3, 0xfff1, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf1, 0xf3, 0xf5, 0xf7, 0xf1, 0xf3, 0xf5, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff1, 0xfff3, 0xfff1, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff1, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1700000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VPMIN output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf2, 0xf4, 0xf6, 0xf0, 0xf2, 0xf4, 0xf6 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff2, 0xfff0, 0xfff2 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf2, 0xf4, 0xf6, 0xf0, 0xf2, 0xf4, 0xf6 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff2, 0xfff0, 0xfff2 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1800000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQSHRUN_N (negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQSHRUN_N (check cumulative saturation) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQSHRUN_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x48, 0x48, 0x48, 0x48, 0x48, 0x48, 0x48, 0x48 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xdeadbe, 0xdeadbe };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQRSHRUN_N (negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQRSHRUN_N (check cumulative saturation: shift by 1) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xffff, 0xffff, 0xffff, 0xffff };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 0;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQRSHRUN_N (check cumulative saturation: shift by max, positive input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x8000, 0x8000, 0x8000, 0x8000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 1;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 1;
+
+VQRSHRUN_N (check cumulative saturation: shift by max, negative input) output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+int VECT_VAR(expected_cumulative_sat,int,16,8) = 0;
+int VECT_VAR(expected_cumulative_sat,int,32,4) = 1;
+int VECT_VAR(expected_cumulative_sat,int,64,2) = 0;
+
+VQRSHRUN_N output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x49, 0x49, 0x49, 0x49, 0x49, 0x49, 0x49, 0x49 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xdeadbf, 0xdeadbf };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VST2_LANE/VST2Q_LANE chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xcc00, 0xcb80, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xcc00, 0xcb80, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VST2_LANE/VST2Q_LANE chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VST3_LANE/VST3Q_LANE chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xcc00, 0xcb80, 0xcb00, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1600000, 0x0 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xcc00, 0xcb80, 0xcb00, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VST3_LANE/VST3Q_LANE chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0x0 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VST3_LANE/VST3Q_LANE chunk 2 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VST4_LANE/VST4Q_LANE chunk 0 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff0, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf0, 0xf1, 0xf2, 0xf3, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0xcc00, 0xcb80, 0xcb00, 0xca80 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfffffff0, 0xfffffff1, 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0xfff0, 0xfff1, 0xfff2, 0xfff3, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0xcc00, 0xcb80, 0xcb00, 0xca80, 0x0, 0x0, 0x0, 0x0 };
+
+VST4_LANE/VST4Q_LANE chunk 1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xfffffff2, 0xfffffff3 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VST4_LANE/VST4Q_LANE chunk 2 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VST4_LANE/VST4Q_LANE chunk 3 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VTBL1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x0, 0xf2, 0xf2, 0xf2, 0x0, 0x0, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0x0, 0xf3, 0xf3, 0xf3, 0x0, 0x0, 0xf3, 0xf3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0x0, 0xf3, 0xf3, 0xf3, 0x0, 0x0, 0xf3, 0xf3 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VTBL2 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf6, 0xf3, 0xf3, 0xf3, 0x0, 0x0, 0xf3, 0xf3 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf6, 0xf5, 0xf5, 0xf5, 0x0, 0x0, 0xf5, 0xf5 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf6, 0xf5, 0xf5, 0xf5, 0x0, 0x0, 0xf5, 0xf5 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VTBL3 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf4, 0xf4, 0xf4, 0xff, 0x0, 0xf4, 0xf4 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf8, 0xf7, 0xf7, 0xf7, 0xff, 0x0, 0xf7, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf8, 0xf7, 0xf7, 0xf7, 0xff, 0x0, 0xf7, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VTBL4 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xfa, 0xf5, 0xf5, 0xf5, 0x3, 0x0, 0xf5, 0xf5 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xfa, 0xf9, 0xf9, 0xf9, 0x3, 0x0, 0xf9, 0xf9 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xfa, 0xf9, 0xf9, 0xf9, 0x3, 0x0, 0xf9, 0xf9 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VTBX1 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0x33, 0xf2, 0xf2, 0xf2, 0x33, 0x33, 0xf2, 0xf2 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xcc, 0xf3, 0xf3, 0xf3, 0xcc, 0xcc, 0xf3, 0xf3 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xcc, 0xf3, 0xf3, 0xf3, 0xcc, 0xcc, 0xf3, 0xf3 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VTBX2 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf6, 0xf3, 0xf3, 0xf3, 0x33, 0x33, 0xf3, 0xf3 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf6, 0xf5, 0xf5, 0xf5, 0xcc, 0xcc, 0xf5, 0xf5 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf6, 0xf5, 0xf5, 0xf5, 0xcc, 0xcc, 0xf5, 0xf5 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VTBX3 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xf8, 0xf4, 0xf4, 0xf4, 0xff, 0x33, 0xf4, 0xf4 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xf8, 0xf7, 0xf7, 0xf7, 0xff, 0xcc, 0xf7, 0xf7 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xf8, 0xf7, 0xf7, 0xf7, 0xff, 0xcc, 0xf7, 0xf7 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+
+VTBX4 output:
+VECT_VAR_DECL(expected,int,8,8) [] = { 0xfa, 0xf5, 0xf5, 0xf5, 0x3, 0x33, 0xf5, 0xf5 };
+VECT_VAR_DECL(expected,int,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,8) [] = { 0xfa, 0xf9, 0xf9, 0xf9, 0x3, 0xcc, 0xf9, 0xf9 };
+VECT_VAR_DECL(expected,uint,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,1) [] = { 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,8) [] = { 0xfa, 0xf9, 0xf9, 0xf9, 0x3, 0xcc, 0xf9, 0xf9 };
+VECT_VAR_DECL(expected,poly,16,4) [] = { 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,int,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,int,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,int,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,uint,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,uint,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,uint,64,2) [] = { 0x3333333333333333, 0x3333333333333333 };
+VECT_VAR_DECL(expected,poly,8,16) [] = { 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33, 0x33 };
+VECT_VAR_DECL(expected,poly,16,8) [] = { 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333, 0x3333 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x33333333, 0x33333333, 0x33333333, 0x33333333 };
+VECT_VAR_DECL(expected,hfloat,16,8) [] = { 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xbf000000, 0xbf000000, 0xbf000000, 0xbf000000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x3f068000, 0x3f068000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x3c030000, 0x3c030000, 0x3c030000, 0x3c030000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xee800000, 0xee800000, 0xee800000, 0xee800000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xbdcc8000, 0xbdcc8000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xbc030000, 0xbc030000, 0xbc030000, 0xbc030000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x7fc00000, 0x7fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x7f800000, 0x7f800000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xff800000, 0xff800000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x80000000, 0x80000000, 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x80000000, 0x80000000 };
+
+VRSQRTE/VRSQRTEQ output:
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x9c800000, 0x9c800000, 0x9c800000, 0x9c800000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x3e498000, 0x3e498000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x3e700000, 0x3e700000, 0x3e700000, 0x3e700000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x80000000, 0x80000000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xae800000, 0xae800000, 0xae800000, 0xae800000 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xb4800000, 0xb4800000 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xed000000, 0xed000000, 0xed000000, 0xed000000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x7fc00000, 0x7fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x7f800000, 0x7f800000, 0x7f800000, 0x7f800000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x7fc00000, 0x7fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xff800000, 0xff800000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x7fc00000, 0x7fc00000, 0x7fc00000, 0x7fc00000 };
+
+VCAGE/VCAGEQ output:
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0x0 };
+
+VCAGE/VCAGEQ output:
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+
+VCALE/VCALEQ output:
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0xffffffff, 0xffffffff };
+
+VCALE/VCALEQ output:
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+
+VCAGT/VCAGTQ output:
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0x0, 0x0 };
+
+VCAGT/VCAGTQ output:
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xffffffff, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xffffffff, 0xffffffff, 0xffffffff, 0xffffffff };
+
+VCALT/VCALTQ output:
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0xffffffff };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0xffffffff };
+
+VCALT/VCALTQ output:
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x0 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x0, 0x0 };
+
+VCVT/VCVTQ output:
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc1800000, 0xc1700000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x4f800000, 0x4f800000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x41720000, 0xc1720000, 0x0, 0x80000000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1800000, 0xc1700000, 0xc1600000, 0xc1500000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x4f800000, 0x4f800000, 0x4f800000, 0x4f800000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xfffffff1, 0x5 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x5 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x0, 0x8000, 0x4b8f, 0xcb8f };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0xf, 0xfffffff1 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0xf, 0x0 };
+
+VCVT_N/VCVTQ_N output:
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc0800000, 0xc0700000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x4c000000, 0x4c000000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xb2800000, 0xb2700000, 0xb2600000, 0xb2500000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x49800000, 0x49800000, 0x49800000, 0x49800000 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xff0b3333, 0x54cccd };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0x0, 0x15 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x0, 0x0, 0x1e3d7, 0xfffe1c29 };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x0, 0x0, 0x1e, 0x0 };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xa, 0xa };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xa, 0xa };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7d, 0x7d, 0x7d, 0x7d };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0x7d, 0x7d, 0x7d, 0x7d };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0xa66666, 0xa66666 };
+VECT_VAR_DECL(expected,uint,32,2) [] = { 0xa66666, 0xa66666 };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0xfbccc, 0xfbccc, 0xfbccc, 0xfbccc };
+VECT_VAR_DECL(expected,uint,32,4) [] = { 0xfbccc, 0xfbccc, 0xfbccc, 0xfbccc };
+VECT_VAR_DECL(expected,int,32,2) [] = { 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,int,32,4) [] = { 0x7fffffff, 0x7fffffff, 0x7fffffff, 0x7fffffff };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x38640000, 0x7f800000, 0x7fc00000, 0xff800000 };
+VECT_VAR_DECL(expected,hfloat,16,4) [] = { 0x7e00, 0x7c00, 0xfc00, 0x8000 };
+
+VRECPS/VRECPSQ output:
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc2e19eb7, 0xc2e19eb7 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc1db851f, 0xc1db851f, 0xc1db851f, 0xc1db851f };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x7fc00000, 0x7fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x7fc00000, 0x7fc00000, 0x7fc00000, 0x7fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xff800000, 0xff800000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x40000000, 0x40000000, 0x40000000, 0x40000000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x40000000, 0x40000000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x40000000, 0x40000000, 0x40000000, 0x40000000 };
+
+VRSQRTS/VRSQRTSQ output:
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xc2796b84, 0xc2796b84 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0xc0e4a3d8, 0xc0e4a3d8, 0xc0e4a3d8, 0xc0e4a3d8 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x7fc00000, 0x7fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x7fc00000, 0x7fc00000, 0x7fc00000, 0x7fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0xff800000, 0xff800000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x3fc00000, 0x3fc00000, 0x3fc00000, 0x3fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,2) [] = { 0x3fc00000, 0x3fc00000 };
+VECT_VAR_DECL(expected,hfloat,32,4) [] = { 0x3fc00000, 0x3fc00000, 0x3fc00000, 0x3fc00000 };
diff --git a/license.html b/license.html
new file mode 100644
index 0000000..ad41df4
--- /dev/null
+++ b/license.html
@@ -0,0 +1,456 @@
+<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">

+

+<html>

+<head>

+<meta http-equiv="content-type" content="text/html; charset=ISO-8859-1">

+<title>RVDS 3.1 EULA - LEC-ELA-00069</title>

+</head>

+<body>

+<div align="center"><b>

+END USER LICENCE AGREEMENT FOR THE ARM REALVIEW DEVELOPMENT SUITE

+</b><br></div><br>

+THIS END USER LICENCE AGREEMENT ("<b>LICENCE</b>") IS A LEGAL AGREEMENT

+BETWEEN YOU (EITHER A SINGLE INDIVIDUAL, OR SINGLE LEGAL ENTITY) AND ARM

+LIMITED ("<b>ARM</b>") FOR THE USE OF THE SOFTWARE ACCOMPANYING THIS

+LICENCE. ARM IS ONLY WILLING TO LICENSE THE SOFTWARE TO YOU ON CONDITION

+THAT YOU ACCEPT ALL OF THE TERMS IN THIS LICENCE. BY CLICKING "<b>I

+AGREE</b>" OR BY INSTALLING OR OTHERWISE USING OR COPYING THE SOFTWARE

+YOU INDICATE THAT YOU AGREE TO BE BOUND BY ALL THE TERMS OF THIS

+LICENCE. IF YOU DO NOT AGREE TO THE TERMS OF THIS LICENCE, ARM IS

+UNWILLING TO LICENSE THE SOFTWARE TO YOU AND YOU MAY NOT INSTALL, USE OR

+COPY THE SOFTWARE, BUT YOU SHOULD PROMPTLY RETURN THE SOFTWARE TO YOUR

+SUPPLIER AND ASK FOR A REFUND OF ANY LICENCE FEE PAID.

+<br><br>

+"<b>Software</b>" means any software, firmware and data accompanying

+this Licence, any printed, electronic or online documentation supplied

+with it, and any updates, patches and modifications ARM may agree to

+make available to you under the terms of this Licence, in all cases

+relating to the RealView Development Suite package of software

+development tools. The package includes; (i) RealView Compilation Tools,

+including compiler, assembler, linker, libraries and example code; (ii)

+RealView Debugger; (iii) instruction set level models of ARM

+microprocessors; (iv) ARM plug-ins for the Eclipse Integrated

+Development Environment (IDE); and (v) if you have obtained the

+CodeWarrior version of the Suite, then your package also includes the

+Metrowerks CodeWarrior IDE. For convenience, your package also includes

+a version of the Eclipse IDE, and other Separate Files (defined below in

+Clause 7), but these are licensed under their own terms and not as part

+of the Software.

+<br><br>

+"<b>Seat</b>" means a written or electronic authorisation from ARM

+to run any Software component as a single task or process on one (1)

+processing unit (such as a processor core, hardware partition, blade,

+virtual machine or emulator) only, by itself or concurrently with other

+Seats, for the time period specified in that authorization.

+<br><br>

+"<b>Licence Key</b>" means an electronic licence key issued to you by

+ARM to enable the use of the Software.<br>

+<br><br>

+<b>1. LICENCE GRANTS.</b><br>

+(i) SOFTWARE: ARM hereby grants to you, subject to the terms and

+conditions of this Licence, a non-exclusive, non-transferable licence,

+only for the Seats, to use the Software, solely for the purposes of your

+internal development, testing and debugging of software applications

+(referred to in this Licence as "Software Applications"). You shall not

+modify or redistribute any of the Software except as may be permitted by

+clauses 1(ii)-1(iv) below.

+<br><br>

+(ii) LIBRARIES: In respect of any Language Libraries and Helper

+Libraries (together "Target Libraries") identified in the Schedule, ARM

+hereby grants you, provided you comply with the terms of clause 1(iv),

+additional non-exclusive, non-transferable licences to; (a) incorporate

+and link the Language Libraries into or with Software Applications,

+provided that Software Applications contain substantial additional

+functionality; (b) incorporate and link the Helper Libraries into, or

+use them in, Software Applications; and (c) reproduce and distribute the

+Target Libraries, only in object code form, and only as part of Software

+Applications.

+<br><br>

+(iii) EXAMPLE CODE: In respect of any Example Code identified in the

+Schedule, ARM hereby grants you, provided you comply with the terms of

+clause 1(iv), additional non-exclusive, non-transferable licences to;

+(a) use copy and modify the Example Code, only for internal testing,

+evaluation, and development and testing of Software Applications; (b)

+incorporate, compile and link the Example Code and any modifications

+into Software Applications (except for Dhrystone which may only be used

+for internal testing and evaluation); (c) reproduce and distribute the

+Example Code identified in the Schedule as "Limited Use", and any

+modifications, only in object code form (except for Dhrystone which

+shall not be reproduced except as necessary to exercise the above

+internal use licence, nor redistributed); and (d) reproduce and

+distribute the Example Code identified in the Schedule as "Extended

+Use", and any modifications, in source or object code form and only as

+part of Software Applications.

+<br><br>

+(iv) FURTHER CONDITIONS ON REDISTRIBUTION: If you are authorised and

+choose to redistribute the whole or any part of the Example Code or

+Target Libraries, you agree to; (a) ensure that they are licensed for

+use only as part of Software Applications and only on microprocessors

+manufactured or simulated under licence from ARM; (b) not use ARM's

+name, logo or trademarks to market Software Applications; (c) include

+valid copyright notices on Software Applications, and preserve any

+copyright notices which are included with, or in, the Example Code and

+Target Libraries; (d) comply with all the other terms of this Licence;

+and (e) not permit further redistribution of the Example Code or Target

+Libraries by your customers except where your distributors redistribute

+them to your end-user customers only as part of Software Applications

+and your distributors otherwise comply with the terms of this Licence.

+<br><br>

+<b>2. RESTRICTIONS ON USE OF THE SOFTWARE.</b><br>

+SEATS, INSTALLATION AND LICENCE KEYS: Your use of the Software is

+limited to the specific number of Seats issued to you by ARM. For each

+Seat, ARM will make a Licence Key available to you to enable use of the

+Software, or certain components or optional functionality in the

+Software, as applicable. You shall only install and use the Software and

+Licence Keys on computers, or virtual machines running on computers,

+which are owned by you (or which are in your exclusive possession under

+an equipment finance arrangement) and which are either; (i) located at

+your premises; or (ii) portable computers which shall remain in the

+possession and control of your employees when outside such premises.

+Each Seat and Licence Key shall be limited or locked to a single item of

+your personal computer hardware (also known as host ID) on which the

+Seat or Licence Key is initially installed, except where ARM may

+separately agree to authorise the transfer (also known as re-hosting) of

+such Seat or Licence Key to another host ID.

+<br><br>

+COPYING: You shall not use or copy the Software or Licence Keys except

+as expressly authorised in this Licence. You may make one additional

+copy of the delivered Software media or image for backup or archival

+purposes.

+<br><br>

+UPDATES AND UPGRADES: Upgrades and updates replace the earlier releases

+of Software that you are upgrading or updating, and are not additional

+copies. When you upgrade or update the Software, the Licence Key for

+such new release replaces your existing Licence Key. Therefore, if you

+are receiving the Software as an update or upgrade, you obtain no rights

+to, and shall not, install or use this update or upgrade unless you have

+first ceased all use of, and deleted, your Licence Key for the version

+of the Software that you are updating or upgrading.

+<br><br>

+PERMITTED USERS: The Software and Licence Keys shall be used only by

+your employees,or by your bona fide sub-contractors for whose acts and

+omissions you hereby agree to be responsible to ARM to the same extent

+as those of your employees, and provided always that such

+sub-contractors; (i) work only onsite at your premises; (ii) are aware

+of the terms of this Licence; (iii) are contractually obligated to use

+the same only for your benefit, and (iv) agree to assign all their work

+product and any rights they create therein in the supply of such work to

+you. Only the single individual, company or other legal entity to whom

+ARM is supplying this Licence may use the Software and Licence Keys. You

+shall not allow third parties (including but not limited to any

+subsidiary, parent or affiliated companies, or offsite contractors you

+may have) to use the Software or Licence Keys unless ARM specifically

+agrees otherwise with you on a case by case basis.

+<br><br>

+REMOTE USE: The Software and Licence Keys shall only be used onsite at

+your premises, except when used offsite by an employee (but not a

+sub-contractor) of yours, on a portable computer, in accordance with the

+"SEATS, INSTALLATION AND LICENCE KEYS" paragraph above, as part of his

+or her normal work activities, and only for your benefit.

+<br><br>

+MULTIPLE VERSIONS: The media on which the Software resides may contain

+more than one version of the Software, each of which is compatible with

+a different operating system (such as Microsoft Windows XP Professional

+and Red Hat Linux). Each version may only be installed and used by you

+to the extent that you have valid Seats and Licence Keys from ARM.

+<br><br>

+ACADEMIC OR EDUCATIONAL USE RESTRICTION: If you or your employer or

+institution paid academic or educational pricing for the Software, or

+the Software is identified as an academic or educational version

+(collectively "Academic Software"), then notwithstanding anything else

+in this Licence, YOU AGREE TO USE THE ACADEMIC SOFTWARE ONLY FOR

+ACADEMIC, NON-COMMERCIAL PURPOSES, AND ARM DOES NOT GRANT YOU ANY RIGHTS

+TO DISTRIBUTE OR SUB-LICENCE SOFTWARE APPLICATIONS UNDER THIS LICENCE.

+<br><br>

+REVERSE ENGINEERING: Except to the extent that such activity is

+permitted by applicable law you shall not reverse engineer, decompile or

+disassemble any of the Software. If the Software was provided to you in

+Europe you shall not reverse engineer, decompile or disassemble any of

+the Software for the purposes of error correction.

+<br><br>

+BENCHMARKING: This licence does not prevent you from using the Software

+for internal benchmarking purposes. However, you shall treat any and all

+benchmarking data relating to the Software, and any other results of

+your use or testing of the Software which are indicative of its

+performance, efficacy, reliability or quality, as confidential

+information and you shall not disclose such information to any third

+party without the express written permission of ARM. ARM may agree to

+waive the restrictions in this paragraph if requested in writing.

+<br><br>

+RESTRICTIONS ON TRANSFER OF LICENSED RIGHTS: The rights granted to you

+under this agreement may not be assigned, sublicensed or otherwise

+transferred by you to any third party without the prior written consent

+of ARM. You shall not rent or lease the Software, or share it with

+contractors or third parties.

+<br><br>

+COPYRIGHT AND RESERVATION OF RIGHTS: The Software is owned by ARM or its

+licensors and is protected by copyright and other intellectual property

+laws and international treaties. The Software is licensed not sold. You

+acquire no rights to the Software other than as expressly provided by

+this Licence. You shall not remove from the Software any copyright

+notice or other notice and shall ensure that any such notice is

+reproduced in any copies of the whole or any part of the Software made

+by you.

+<br><br>

+<b>3. SUPPORT.</b><br>

+If you purchased the Software directly from ARM, and you are not

+receiving it as Academic Software (defined in clause 2), you are

+entitled to reasonable support for the Software, for the period of one

+(1) year, commencing from the day of purchase. The support will be

+provided by telephone, email or other written format designated by ARM,

+prioritised at ARM's discretion, and may not be used as a substitute for

+training or as additional resource for your programming projects. If you

+obtained the Software from an ARM authorised reseller or other third

+party, or no charge was made by ARM for the Software, update or upgrade,

+or it is Academic Software, then, except as provided as a remedy to any

+claim under the limited warranties provided in clause 5, you are not

+entitled to any support for the Software from ARM under this Licence.

+The vendor of the Software may or may not offer support to you for the

+Software. Please refer to the Technical Support area of

+http://www.arm.com for contact details for ARM's support service and (if

+applicable) other authorised support channels.

+<br><br>

+<b>4. CONFIDENTIALITY.</b><br>

+You acknowledge that the Software, Licence Keys, and any benchmarking

+data and related information mentioned in Clause 2 contain trade secrets

+and confidential material, and you agree to maintain them in confidence

+and apply security measures no less stringent than the measures which

+you apply to protect your own like information, but not less than a

+reasonable degree of care, to prevent their unauthorised disclosure and

+use. Subject to any restrictions imposed by applicable law, the period

+of confidentiality shall be indefinite. You agree that you shall not use

+any such information other than in normal use of the Software under the

+licences granted in this Licence.

+<br><br>

+<b>5. LIMITED WARRANTIES.</b><br>

+For the period of ninety (90) days from the date of receipt by you of

+the Software, ARM warrants to you that (i) the media on which the

+Software is provided shall be free from defects in materials and

+workmanship under normal use; and (ii) the Software will perform

+substantially in accordance with its accompanying documentation (if

+any). ARM's total liability and your exclusive remedy for breach of

+these limited warranties shall be limited to ARM, at ARM's option; (a)

+refunding the price paid by you for the Software; or (b) replacing the

+defective Software; or (c) using reasonable efforts to correct material,

+documented, reproducible defects in the Software and delivering such

+corrected Software to you. Any replacement Software will be warranted

+for the remainder of the original warranty period or thirty (30) days,

+whichever is the longer.

+<br><br>

+EXCEPT AS MAY BE PROVIDED ABOVE, YOU AGREE THAT THE SOFTWARE IS LICENSED

+"AS IS", AND THAT ARM EXPRESSLY DISCLAIMS ALL REPRESENTATIONS,

+WARRANTIES, CONDITIONS OR OTHER TERMS, EXPRESS OR IMPLIED, INCLUDING

+WITHOUT LIMITATION THE IMPLIED WARRANTIES OF NON-INFRINGEMENT,

+SATISFACTORY QUALITY, AND FITNESS FOR A PARTICULAR PURPOSE.

+<br><br>

+YOU EXPRESSLY ASSUME ALL LIABILITIES AND RISKS, FOR USE OR OPERATION OF

+SOFTWARE APPLICATIONS, INCLUDING WITHOUT LIMITATION, APPLICATIONS

+DESIGNED OR INTENDED FOR MISSION CRITICAL APPLICATIONS, SUCH AS

+PACEMAKERS, WEAPONARY, AIRCRAFT NAVIGATION, FACTORY CONTROL SYSTEMS,

+ETC. SHOULD THE SOFTWARE PROVE DEFECTIVE, YOU ASSUME THE ENTIRE COST OF

+ALL NECESSARY SERVICING, REPAIR OR CORRECTION.

+<br><br>

+<b>6. LIMITATION OF LIABILITY.</b><br>

+TO THE MAXIMUM EXTENT PERMITTED BY APPLICABLE LAW, IN NO EVENT SHALL ARM

+BE LIABLE FOR ANY INDIRECT, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES

+(INCLUDING LOSS OF PROFITS) ARISING OUT OF THE USE OR INABILITY TO USE

+THE SOFTWARE WHETHER BASED ON A CLAIM UNDER CONTRACT, TORT OR OTHER

+LEGAL THEORY, EVEN IF ARM WAS ADVISED OF THE POSSIBILITY OF SUCH

+DAMAGES.

+<br><br>

+ARM does not seek to limit or exclude liability for death or personal

+injury arising from ARM's negligence and because some jurisdictions do

+not permit the exclusion or limitation of liability for consequential or

+incidental damages the above limitation relating to liability for

+consequential damages may not apply to you.

+<br><br>

+NOTWITHSTANDING ANYTHING TO THE CONTRARY CONTAINED IN THIS LICENCE, THE

+MAXIMUM LIABILITY OF ARM TO YOU IN AGGREGATE FOR ALL CLAIMS MADE AGAINST

+ARM IN CONTRACT TORT OR OTHERWISE UNDER OR IN CONNECTION WITH THE

+SUBJECT MATTER OF THIS LICENCE SHALL NOT EXCEED THE TOTAL OF SUMS PAID

+BY YOU TO ARM (IF ANY) FOR THIS LICENCE.

+<br><br>

+<b>7. THIRD PARTY RIGHTS.</b><br>

+The Software is supplied with, and uses, third party software or

+materials which are governed by their own separate licence agreements

+(together "Separate Files"). This Licence does not apply to such

+Separate Files and they are not included in the term "Software" under

+this Licence. You agree to comply with all terms and conditions imposed

+on you in respect of such Separate Files including those identified in

+the Schedule ("Third Party Terms").  Any provisions in this Licence

+which differ from Third Party Terms are offered by ARM alone and shall

+not supersede or modify any Third Party Terms. In addition to Third

+Party Terms, the disclaimer of warranty and limitation of liability

+provisions in this Licence shall apply to all Software and Separate

+Files.

+<br><br>

+ARM HEREBY DISCLAIMS ANY AND ALL WARRANTIES EXPRESS OR IMPLIED FROM ANY

+THIRD PARTIES REGARDING ANY SEPARATE FILES, ANY THIRD PARTY MATERIALS

+INCLUDED IN THE SOFTWARE, ANY THIRD PARTY MATERIALS FROM WHICH THE

+SOFTWARE IS DERIVED (COLLECTIVELY "OTHER CODE"), AND THE USE OF ANY OR

+ALL THE OTHER CODE IN CONNECTION WITH THE SOFTWARE, INCLUDING (WITHOUT

+LIMITATION) ANY WARRANTIES OF SATISFACTORY QUALITY OR FITNESS FOR A

+PARTICULAR PURPOSE.

+<br><br>

+NO THIRD PARTY LICENSORS OF OTHER CODE SHALL HAVE ANY LIABILITY FOR ANY

+DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL

+DAMAGES (INCLUDING WITHOUT LIMITATION LOST PROFITS), HOWEVER CAUSED AND

+WHETHER MADE UNDER CONTRACT, TORT OR OTHER LEGAL THEORY, ARISING IN ANY

+WAY OUT OF THE USE OR DISTRIBUTION OF THE OTHER CODE OR THE EXERCISE OF

+ANY RIGHTS GRANTED UNDER EITHER OR BOTH THIS LICENCE AND THE LEGAL TERMS

+APPLICABLE TO ANY SEPARATE FILES, EVEN IF ADVISED OF THE POSSIBILITY OF

+SUCH DAMAGES.

+<br><br>

+Distribution of code from the Rogue Wave C++ Language Libraries is

+permitted only if: (a) you are granted the right to redistribute those

+Libraries under Clauses 1 and 2 of this Licence; and (b) they do not

+constitute a major portion of the value of the Software Applications. No

+right is granted to use those libraries on any computers as are marketed

+or commonly considered to be mainframe computers in the computer

+industry. Notwithstanding any provisions in this Licence to the

+contrary, you shall not: (a) distribute in any manner any of the header

+files, object modules, template-based classes, or independent static

+libraries of those libraries or documentation relating thereto; (b)

+distribute any portion of the same in a software utility product or

+otherwise in competition with Rogue Wave Software Inc's distribution

+thereof; nor (c) rent or lease the Software. "Rogue Wave" is a

+registered trademark of Rogue Wave Software, Inc.

+<br><br>

+<b>8. U.S. GOVERNMENT END USERS.</b><br>

+US Government Restrictions: Use, duplication, reproduction, release,

+modification, disclosure or transfer of this commercial product and

+accompanying documentation is restricted in accordance with the terms of

+this Licence.

+<br><br>

+<b>9. TERM AND TERMINATION.</b><br>

+This Licence shall remain in force until terminated by you, by ARM or by

+expiry (in the case of a time limited licence). Without prejudice to any

+of its other rights if you are in breach of any of the terms and

+conditions of this Licence then ARM may terminate this Licence

+immediately upon giving written notice to you. You may terminate this

+Licence at any time. Upon termination of this Licence by you or by ARM

+you shall stop using the Software and destroy all copies of the Software

+in your possession together with all documentation and related

+materials. The provisions of clauses 4, 6, 7, 8, 9 and 10 shall survive

+termination of this Licence.

+<br><br>

+<b>10. GENERAL.</b><br>

+This Licence is governed by English Law. Except where ARM agrees

+otherwise in a written contract signed by you and ARM, this is the only

+agreement between you and ARM relating to the Software and it may only

+be modified by written agreement between you and ARM. Except as

+expressly agreed in writing, this Licence may not be modified by

+purchase orders, advertising or other representation by any person. If

+any clause or sentence in this Licence is held by a court of law to be

+illegal or unenforceable the remaining provisions of this Licence shall

+not be affected thereby. The failure by ARM to enforce any of the

+provisions of this Licence, unless waived in writing, shall not

+constitute a waiver of ARM's rights to enforce such provision or any

+other provision of this Licence in the future.

+<br><br>

+At ARM's request, you agree to check your computers for installations of

+the Software, copies of Licence Keys, contents of any licence server log

+files, individual or concurrent usage of Seats, and any other

+information requested by ARM relating to Software installation, usage

+and Licence Key management, and to provide this information to ARM. ARM

+will not make such a request more frequently than once per year, except

+as necessary where ARM believes, in good faith, that an additional check

+is needed (for example after re-hosting a Licence Key). You agree that

+auditors nominated by ARM may also perform such checking and reporting

+on behalf of ARM by prior appointment during your normal business hours

+on seven (7) days' notice. ARM shall bear the auditors' costs for that

+audit unless it reveals unlicensed usage in which case you shall

+promptly reimburse ARM for all reasonable costs and expenses, including

+professional fees, relating to such audit. Any information which is

+disclosed to ARM or such auditors during checking or audit shall be

+treated as your confidential information and shall only be used by ARM

+for licence management, compliance and enforcement purposes.

+<br><br>

+The Software provided under this Licence is subject to U.S. export

+control laws, including the U.S. Export Administration Act and its

+associated regulations, and may be subject to export or import

+regulations in other countries. You agree to comply fully with all laws

+and regulations of the United States and other countries ("Export Laws")

+to assure that the Software, is not (1) exported, directly or

+indirectly, in violation of Export Laws, either to any countries that

+are subject to U.S.A. export restrictions or to any end user who has

+been prohibited from participating in the U.S.A. export transactions by

+any federal agency of the U.S.A. government; or (2) intended to be used

+for any purpose prohibited by Export Laws, including, without

+limitation, nuclear, chemical, or biological weapons proliferation.

+<br><br> <div align="center"><b>

+THE SCHEDULE

+</b><br></div><b>

+TARGET LIBRARIES (OBJECT CODE):

+</b><br>

+<i>Language Libraries:</i> C Libraries; C++ runtime support library;

+Rogue Wave C++ Libraries <br>

+<i>Helper Libraries:</i> ARM Compiler Helper Libraries found in your

+installation at:

+<br><tt>"&lt;install_dir&gt;/RVCT/Data/3.1/&lt;buildno&gt;/lib/armlib/h_*.*"</tt><br>

+<br><b>

+EXAMPLE CODE - LIMITED USE:

+</b><br>

+Dhrystone; MMUgen; FFT example code

+<br><br><b>

+EXAMPLE CODE - EXTENDED USE:

+</b><br>

+Example Flash Download Algorithms found in your installation at:

+<br><tt>"&lt;install_dir&gt;/RVD/Flash/3.1/&lt;buildno&gt;/&lt;OS&gt;/&lt;platform&gt;/*.*"</tt><br>

+Any and all other example code identified as such and included with the

+Software

+<br><br><b>

+SEPARATE FILES:

+</b><br>

+A. GNU standard C and C++ language libraries (only installed on Linux

+host computers):

+<br>

+This package includes GNU libgcc_s and libstdc++ libraries in binary

+form, licensed to you under the GNU General Public License, version 2.

+<br><br>

+B. zthread library (only installed on Windows host computers):

+<br>

+This package includes zthread shared library in source and binary form,

+licensed to you under the GNU Lesser General Public License, version

+2.1.

+<br><br>

+C. Portions of the ARM installer:

+<br>

+Portions of the installer use the JAXB XML binding library and Java 2

+Platform Standard Edition Runtime (JRE) binary runtime files. The

+applicable Third Party Terms are set out in the

+THIRDPARTYLICENSEREADME.txt files, which ARM received with such

+binaries, and (in the case of any portions of the MESA graphics library

+used in the JRE) in the "SGI Free Software License B" in file

+SGIFREEB.txt.

+<br><br>

+D. The Eclipse IDE:

+<br>

+The Eclipse IDE is distributed subject to the terms of the Eclipse

+Software User Agreement (SUA) version March 17, 2005, except that the

+term "Content" used in the SUA shall mean only those Eclipse IDE

+materials contained in this package, and it is ARM, not the Eclipse

+Foundation, who makes the agreement with you and supplies you with that

+Content. That Content is also subject to the legal terms and notices

+referred to in the SUA, including but not limited to the Eclipse Public

+License version 1.0, the Common Public License version 1.0, the Apache

+Software License version 1.1, the Apache Software License version 2.0,

+the IBM Public License version 1.0, the Metro Link Public License 1.00,

+and the Mozilla Public License version 1.1. For further information on

+the Eclipse Foundation's approach to licensing, please see their

+guidance notes at 

+<a href="http://www.eclipse.org/legal/guidetolegaldoc.php">

+http://www.eclipse.org/legal/guidetolegaldoc.php</a>,

+or more generally the Eclipse legal resources website at

+<a href="http://www.eclipse.org/legal">http://www.eclipse.org/legal</a>.

+<br><br>

+E. Portions of the ARM plug-ins for the Eclipse IDE:

+<br>

+Certain modules used in these plug-ins are licensed to you under the

+Eclipse Public License, version 1.0.

+<br><br>

+ARM contract references: LEC-ELA-00069-V14.0 RVDS 3.1 FCS AB/AB

+<br>/end

+<br>

+</body>

+</html>

diff --git a/ref-rvct-all.txt b/ref-rvct-all.txt
new file mode 100644
index 0000000..cb7ab02
--- /dev/null
+++ b/ref-rvct-all.txt
@@ -0,0 +1,8833 @@
+
+VLD1/VLD1Q output:
+VLD1/VLD1Q:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD1/VLD1Q:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD1/VLD1Q:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD1/VLD1Q:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD1/VLD1Q:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VLD1/VLD1Q:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD1/VLD1Q:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD1/VLD1Q:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD1/VLD1Q:8:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VLD1/VLD1Q:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD1/VLD1Q:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD1/VLD1Q:11:result_float16x4 [] = { cc00, cb80, cb00, ca80,  }
+VLD1/VLD1Q:12:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD1/VLD1Q:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD1/VLD1Q:14:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD1/VLD1Q:15:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VLD1/VLD1Q:16:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD1/VLD1Q:17:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VLD1/VLD1Q:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD1/VLD1Q:19:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VLD1/VLD1Q:20:result_poly8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD1/VLD1Q:21:result_poly16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VLD1/VLD1Q:22:result_float32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+VLD1/VLD1Q:23:result_float16x8 [] = { cc00, cb80, cb00, ca80, ca00, c980, c900, c880,  }
+
+VADD/VADDQ output:
+VADD/VADDQ:0:result_int8x8 [] = { fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9,  }
+VADD/VADDQ:1:result_int16x4 [] = { ffffffec, ffffffed, ffffffee, ffffffef,  }
+VADD/VADDQ:2:result_int32x2 [] = { fffffff3, fffffff4,  }
+VADD/VADDQ:3:result_int64x1 [] = { 54,  }
+VADD/VADDQ:4:result_uint8x8 [] = { 4, 5, 6, 7, 8, 9, a, b,  }
+VADD/VADDQ:5:result_uint16x4 [] = { e, f, 10, 11,  }
+VADD/VADDQ:6:result_uint32x2 [] = { 18, 19,  }
+VADD/VADDQ:7:result_uint64x1 [] = { fffffffffffffff2,  }
+VADD/VADDQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADD/VADDQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VADD/VADDQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VADD/VADDQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VADD/VADDQ:12:result_int8x16 [] = { ffffffe6, ffffffe7, ffffffe8, ffffffe9, ffffffea, ffffffeb, ffffffec, ffffffed, ffffffee, ffffffef, fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5,  }
+VADD/VADDQ:13:result_int16x8 [] = { ffffffdc, ffffffdd, ffffffde, ffffffdf, ffffffe0, ffffffe1, ffffffe2, ffffffe3,  }
+VADD/VADDQ:14:result_int32x4 [] = { ffffffd2, ffffffd3, ffffffd4, ffffffd5,  }
+VADD/VADDQ:15:result_int64x2 [] = { 8, 9,  }
+VADD/VADDQ:16:result_uint8x16 [] = { fc, fd, fe, ff, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b,  }
+VADD/VADDQ:17:result_uint16x8 [] = { fff3, fff4, fff5, fff6, fff7, fff8, fff9, fffa,  }
+VADD/VADDQ:18:result_uint32x4 [] = { 27, 28, 29, 2a,  }
+VADD/VADDQ:19:result_uint64x2 [] = { fffffffffffffff3, fffffffffffffff4,  }
+VADD/VADDQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADD/VADDQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VADD/VADDQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VADD/VADDQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+float32:
+VADD/VADDQ:24:result_float32x2 [] = { 40d9999a, 40d9999a,  }
+VADD/VADDQ:25:result_float32x4 [] = { 41100000, 41100000, 41100000, 41100000,  }
+
+VLD1_LANE/VLD1_LANEQ output:
+VLD1_LANE/VLD1_LANEQ:0:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, fffffff0, ffffffaa,  }
+VLD1_LANE/VLD1_LANEQ:1:result_int16x4 [] = { ffffaaaa, ffffaaaa, ffffaaaa, fffffff0,  }
+VLD1_LANE/VLD1_LANEQ:2:result_int32x2 [] = { aaaaaaaa, fffffff0,  }
+VLD1_LANE/VLD1_LANEQ:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD1_LANE/VLD1_LANEQ:4:result_uint8x8 [] = { aa, aa, aa, aa, aa, aa, aa, f0,  }
+VLD1_LANE/VLD1_LANEQ:5:result_uint16x4 [] = { aaaa, aaaa, aaaa, fff0,  }
+VLD1_LANE/VLD1_LANEQ:6:result_uint32x2 [] = { aaaaaaaa, fffffff0,  }
+VLD1_LANE/VLD1_LANEQ:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD1_LANE/VLD1_LANEQ:8:result_poly8x8 [] = { aa, aa, aa, aa, aa, aa, aa, f0,  }
+VLD1_LANE/VLD1_LANEQ:9:result_poly16x4 [] = { aaaa, aaaa, aaaa, fff0,  }
+VLD1_LANE/VLD1_LANEQ:10:result_float32x2 [] = { aaaaaaaa, c1800000,  }
+VLD1_LANE/VLD1_LANEQ:11:result_float16x4 [] = { aaaa, aaaa, cc00, aaaa,  }
+VLD1_LANE/VLD1_LANEQ:12:result_int8x16 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, fffffff0,  }
+VLD1_LANE/VLD1_LANEQ:13:result_int16x8 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, fffffff0, ffffaaaa, ffffaaaa,  }
+VLD1_LANE/VLD1_LANEQ:14:result_int32x4 [] = { aaaaaaaa, aaaaaaaa, fffffff0, aaaaaaaa,  }
+VLD1_LANE/VLD1_LANEQ:15:result_int64x2 [] = { aaaaaaaaaaaaaaaa, fffffffffffffff0,  }
+VLD1_LANE/VLD1_LANEQ:16:result_uint8x16 [] = { aa, aa, aa, aa, aa, aa, aa, aa, aa, aa, aa, aa, f0, aa, aa, aa,  }
+VLD1_LANE/VLD1_LANEQ:17:result_uint16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, fff0, aaaa,  }
+VLD1_LANE/VLD1_LANEQ:18:result_uint32x4 [] = { aaaaaaaa, aaaaaaaa, fffffff0, aaaaaaaa,  }
+VLD1_LANE/VLD1_LANEQ:19:result_uint64x2 [] = { fffffffffffffff0, aaaaaaaaaaaaaaaa,  }
+VLD1_LANE/VLD1_LANEQ:20:result_poly8x16 [] = { aa, aa, aa, aa, aa, aa, aa, aa, aa, aa, aa, aa, f0, aa, aa, aa,  }
+VLD1_LANE/VLD1_LANEQ:21:result_poly16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, fff0, aaaa,  }
+VLD1_LANE/VLD1_LANEQ:22:result_float32x4 [] = { aaaaaaaa, aaaaaaaa, c1800000, aaaaaaaa,  }
+VLD1_LANE/VLD1_LANEQ:23:result_float16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, cc00, aaaa, aaaa,  }
+
+VLD1_DUP/VLD1_DUPQ output:
+VLD1_DUP/VLD1_DUPQ:0:result_int8x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VLD1_DUP/VLD1_DUPQ:1:result_int16x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VLD1_DUP/VLD1_DUPQ:2:result_int32x2 [] = { fffffff0, fffffff0,  }
+VLD1_DUP/VLD1_DUPQ:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD1_DUP/VLD1_DUPQ:4:result_uint8x8 [] = { f0, f0, f0, f0, f0, f0, f0, f0,  }
+VLD1_DUP/VLD1_DUPQ:5:result_uint16x4 [] = { fff0, fff0, fff0, fff0,  }
+VLD1_DUP/VLD1_DUPQ:6:result_uint32x2 [] = { fffffff0, fffffff0,  }
+VLD1_DUP/VLD1_DUPQ:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD1_DUP/VLD1_DUPQ:8:result_poly8x8 [] = { f0, f0, f0, f0, f0, f0, f0, f0,  }
+VLD1_DUP/VLD1_DUPQ:9:result_poly16x4 [] = { fff0, fff0, fff0, fff0,  }
+VLD1_DUP/VLD1_DUPQ:10:result_float32x2 [] = { c1800000, c1800000,  }
+VLD1_DUP/VLD1_DUPQ:11:result_float16x4 [] = { cc00, cc00, cc00, cc00,  }
+VLD1_DUP/VLD1_DUPQ:12:result_int8x16 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VLD1_DUP/VLD1_DUPQ:13:result_int16x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VLD1_DUP/VLD1_DUPQ:14:result_int32x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VLD1_DUP/VLD1_DUPQ:15:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VLD1_DUP/VLD1_DUPQ:16:result_uint8x16 [] = { f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0,  }
+VLD1_DUP/VLD1_DUPQ:17:result_uint16x8 [] = { fff0, fff0, fff0, fff0, fff0, fff0, fff0, fff0,  }
+VLD1_DUP/VLD1_DUPQ:18:result_uint32x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VLD1_DUP/VLD1_DUPQ:19:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VLD1_DUP/VLD1_DUPQ:20:result_poly8x16 [] = { f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0,  }
+VLD1_DUP/VLD1_DUPQ:21:result_poly16x8 [] = { fff0, fff0, fff0, fff0, fff0, fff0, fff0, fff0,  }
+VLD1_DUP/VLD1_DUPQ:22:result_float32x4 [] = { c1800000, c1800000, c1800000, c1800000,  }
+VLD1_DUP/VLD1_DUPQ:23:result_float16x8 [] = { cc00, cc00, cc00, cc00, cc00, cc00, cc00, cc00,  }
+
+VLD1_DUP/VLD1_DUPQ output:
+VLD1_DUP/VLD1_DUPQ:0:result_int8x8 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VLD1_DUP/VLD1_DUPQ:1:result_int16x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VLD1_DUP/VLD1_DUPQ:2:result_int32x2 [] = { fffffff1, fffffff1,  }
+VLD1_DUP/VLD1_DUPQ:3:result_int64x1 [] = { fffffffffffffff1,  }
+VLD1_DUP/VLD1_DUPQ:4:result_uint8x8 [] = { f1, f1, f1, f1, f1, f1, f1, f1,  }
+VLD1_DUP/VLD1_DUPQ:5:result_uint16x4 [] = { fff1, fff1, fff1, fff1,  }
+VLD1_DUP/VLD1_DUPQ:6:result_uint32x2 [] = { fffffff1, fffffff1,  }
+VLD1_DUP/VLD1_DUPQ:7:result_uint64x1 [] = { fffffffffffffff1,  }
+VLD1_DUP/VLD1_DUPQ:8:result_poly8x8 [] = { f1, f1, f1, f1, f1, f1, f1, f1,  }
+VLD1_DUP/VLD1_DUPQ:9:result_poly16x4 [] = { fff1, fff1, fff1, fff1,  }
+VLD1_DUP/VLD1_DUPQ:10:result_float32x2 [] = { c1700000, c1700000,  }
+VLD1_DUP/VLD1_DUPQ:11:result_float16x4 [] = { cb80, cb80, cb80, cb80,  }
+VLD1_DUP/VLD1_DUPQ:12:result_int8x16 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VLD1_DUP/VLD1_DUPQ:13:result_int16x8 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VLD1_DUP/VLD1_DUPQ:14:result_int32x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VLD1_DUP/VLD1_DUPQ:15:result_int64x2 [] = { fffffffffffffff1, fffffffffffffff1,  }
+VLD1_DUP/VLD1_DUPQ:16:result_uint8x16 [] = { f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1,  }
+VLD1_DUP/VLD1_DUPQ:17:result_uint16x8 [] = { fff1, fff1, fff1, fff1, fff1, fff1, fff1, fff1,  }
+VLD1_DUP/VLD1_DUPQ:18:result_uint32x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VLD1_DUP/VLD1_DUPQ:19:result_uint64x2 [] = { fffffffffffffff1, fffffffffffffff1,  }
+VLD1_DUP/VLD1_DUPQ:20:result_poly8x16 [] = { f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1,  }
+VLD1_DUP/VLD1_DUPQ:21:result_poly16x8 [] = { fff1, fff1, fff1, fff1, fff1, fff1, fff1, fff1,  }
+VLD1_DUP/VLD1_DUPQ:22:result_float32x4 [] = { c1700000, c1700000, c1700000, c1700000,  }
+VLD1_DUP/VLD1_DUPQ:23:result_float16x8 [] = { cb80, cb80, cb80, cb80, cb80, cb80, cb80, cb80,  }
+
+VLD1_DUP/VLD1_DUPQ output:
+VLD1_DUP/VLD1_DUPQ:0:result_int8x8 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VLD1_DUP/VLD1_DUPQ:1:result_int16x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VLD1_DUP/VLD1_DUPQ:2:result_int32x2 [] = { fffffff2, fffffff2,  }
+VLD1_DUP/VLD1_DUPQ:3:result_int64x1 [] = { fffffffffffffff2,  }
+VLD1_DUP/VLD1_DUPQ:4:result_uint8x8 [] = { f2, f2, f2, f2, f2, f2, f2, f2,  }
+VLD1_DUP/VLD1_DUPQ:5:result_uint16x4 [] = { fff2, fff2, fff2, fff2,  }
+VLD1_DUP/VLD1_DUPQ:6:result_uint32x2 [] = { fffffff2, fffffff2,  }
+VLD1_DUP/VLD1_DUPQ:7:result_uint64x1 [] = { fffffffffffffff2,  }
+VLD1_DUP/VLD1_DUPQ:8:result_poly8x8 [] = { f2, f2, f2, f2, f2, f2, f2, f2,  }
+VLD1_DUP/VLD1_DUPQ:9:result_poly16x4 [] = { fff2, fff2, fff2, fff2,  }
+VLD1_DUP/VLD1_DUPQ:10:result_float32x2 [] = { c1600000, c1600000,  }
+VLD1_DUP/VLD1_DUPQ:11:result_float16x4 [] = { cb00, cb00, cb00, cb00,  }
+VLD1_DUP/VLD1_DUPQ:12:result_int8x16 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VLD1_DUP/VLD1_DUPQ:13:result_int16x8 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VLD1_DUP/VLD1_DUPQ:14:result_int32x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VLD1_DUP/VLD1_DUPQ:15:result_int64x2 [] = { fffffffffffffff2, fffffffffffffff2,  }
+VLD1_DUP/VLD1_DUPQ:16:result_uint8x16 [] = { f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2,  }
+VLD1_DUP/VLD1_DUPQ:17:result_uint16x8 [] = { fff2, fff2, fff2, fff2, fff2, fff2, fff2, fff2,  }
+VLD1_DUP/VLD1_DUPQ:18:result_uint32x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VLD1_DUP/VLD1_DUPQ:19:result_uint64x2 [] = { fffffffffffffff2, fffffffffffffff2,  }
+VLD1_DUP/VLD1_DUPQ:20:result_poly8x16 [] = { f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2,  }
+VLD1_DUP/VLD1_DUPQ:21:result_poly16x8 [] = { fff2, fff2, fff2, fff2, fff2, fff2, fff2, fff2,  }
+VLD1_DUP/VLD1_DUPQ:22:result_float32x4 [] = { c1600000, c1600000, c1600000, c1600000,  }
+VLD1_DUP/VLD1_DUPQ:23:result_float16x8 [] = { cb00, cb00, cb00, cb00, cb00, cb00, cb00, cb00,  }
+
+VDUP/VDUPQ output:
+VDUP/VDUPQ:0:result_int8x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VDUP/VDUPQ:1:result_int16x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VDUP/VDUPQ:2:result_int32x2 [] = { fffffff0, fffffff0,  }
+VDUP/VDUPQ:3:result_int64x1 [] = { fffffffffffffff0,  }
+VDUP/VDUPQ:4:result_uint8x8 [] = { f0, f0, f0, f0, f0, f0, f0, f0,  }
+VDUP/VDUPQ:5:result_uint16x4 [] = { fff0, fff0, fff0, fff0,  }
+VDUP/VDUPQ:6:result_uint32x2 [] = { fffffff0, fffffff0,  }
+VDUP/VDUPQ:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VDUP/VDUPQ:8:result_poly8x8 [] = { f0, f0, f0, f0, f0, f0, f0, f0,  }
+VDUP/VDUPQ:9:result_poly16x4 [] = { fff0, fff0, fff0, fff0,  }
+VDUP/VDUPQ:10:result_float32x2 [] = { c1800000, c1800000,  }
+VDUP/VDUPQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VDUP/VDUPQ:12:result_int8x16 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VDUP/VDUPQ:13:result_int16x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VDUP/VDUPQ:14:result_int32x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VDUP/VDUPQ:15:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VDUP/VDUPQ:16:result_uint8x16 [] = { f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0,  }
+VDUP/VDUPQ:17:result_uint16x8 [] = { fff0, fff0, fff0, fff0, fff0, fff0, fff0, fff0,  }
+VDUP/VDUPQ:18:result_uint32x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VDUP/VDUPQ:19:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VDUP/VDUPQ:20:result_poly8x16 [] = { f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0,  }
+VDUP/VDUPQ:21:result_poly16x8 [] = { fff0, fff0, fff0, fff0, fff0, fff0, fff0, fff0,  }
+VDUP/VDUPQ:22:result_float32x4 [] = { c1800000, c1800000, c1800000, c1800000,  }
+VDUP/VDUPQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VDUP/VDUPQ output:
+VDUP/VDUPQ:0:result_int8x8 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VDUP/VDUPQ:1:result_int16x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VDUP/VDUPQ:2:result_int32x2 [] = { fffffff1, fffffff1,  }
+VDUP/VDUPQ:3:result_int64x1 [] = { fffffffffffffff1,  }
+VDUP/VDUPQ:4:result_uint8x8 [] = { f1, f1, f1, f1, f1, f1, f1, f1,  }
+VDUP/VDUPQ:5:result_uint16x4 [] = { fff1, fff1, fff1, fff1,  }
+VDUP/VDUPQ:6:result_uint32x2 [] = { fffffff1, fffffff1,  }
+VDUP/VDUPQ:7:result_uint64x1 [] = { fffffffffffffff1,  }
+VDUP/VDUPQ:8:result_poly8x8 [] = { f1, f1, f1, f1, f1, f1, f1, f1,  }
+VDUP/VDUPQ:9:result_poly16x4 [] = { fff1, fff1, fff1, fff1,  }
+VDUP/VDUPQ:10:result_float32x2 [] = { c1700000, c1700000,  }
+VDUP/VDUPQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VDUP/VDUPQ:12:result_int8x16 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VDUP/VDUPQ:13:result_int16x8 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VDUP/VDUPQ:14:result_int32x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VDUP/VDUPQ:15:result_int64x2 [] = { fffffffffffffff1, fffffffffffffff1,  }
+VDUP/VDUPQ:16:result_uint8x16 [] = { f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1,  }
+VDUP/VDUPQ:17:result_uint16x8 [] = { fff1, fff1, fff1, fff1, fff1, fff1, fff1, fff1,  }
+VDUP/VDUPQ:18:result_uint32x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VDUP/VDUPQ:19:result_uint64x2 [] = { fffffffffffffff1, fffffffffffffff1,  }
+VDUP/VDUPQ:20:result_poly8x16 [] = { f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1,  }
+VDUP/VDUPQ:21:result_poly16x8 [] = { fff1, fff1, fff1, fff1, fff1, fff1, fff1, fff1,  }
+VDUP/VDUPQ:22:result_float32x4 [] = { c1700000, c1700000, c1700000, c1700000,  }
+VDUP/VDUPQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VDUP/VDUPQ output:
+VDUP/VDUPQ:0:result_int8x8 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VDUP/VDUPQ:1:result_int16x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VDUP/VDUPQ:2:result_int32x2 [] = { fffffff2, fffffff2,  }
+VDUP/VDUPQ:3:result_int64x1 [] = { fffffffffffffff2,  }
+VDUP/VDUPQ:4:result_uint8x8 [] = { f2, f2, f2, f2, f2, f2, f2, f2,  }
+VDUP/VDUPQ:5:result_uint16x4 [] = { fff2, fff2, fff2, fff2,  }
+VDUP/VDUPQ:6:result_uint32x2 [] = { fffffff2, fffffff2,  }
+VDUP/VDUPQ:7:result_uint64x1 [] = { fffffffffffffff2,  }
+VDUP/VDUPQ:8:result_poly8x8 [] = { f2, f2, f2, f2, f2, f2, f2, f2,  }
+VDUP/VDUPQ:9:result_poly16x4 [] = { fff2, fff2, fff2, fff2,  }
+VDUP/VDUPQ:10:result_float32x2 [] = { c1600000, c1600000,  }
+VDUP/VDUPQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VDUP/VDUPQ:12:result_int8x16 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VDUP/VDUPQ:13:result_int16x8 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VDUP/VDUPQ:14:result_int32x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VDUP/VDUPQ:15:result_int64x2 [] = { fffffffffffffff2, fffffffffffffff2,  }
+VDUP/VDUPQ:16:result_uint8x16 [] = { f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2,  }
+VDUP/VDUPQ:17:result_uint16x8 [] = { fff2, fff2, fff2, fff2, fff2, fff2, fff2, fff2,  }
+VDUP/VDUPQ:18:result_uint32x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VDUP/VDUPQ:19:result_uint64x2 [] = { fffffffffffffff2, fffffffffffffff2,  }
+VDUP/VDUPQ:20:result_poly8x16 [] = { f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2,  }
+VDUP/VDUPQ:21:result_poly16x8 [] = { fff2, fff2, fff2, fff2, fff2, fff2, fff2, fff2,  }
+VDUP/VDUPQ:22:result_float32x4 [] = { c1600000, c1600000, c1600000, c1600000,  }
+VDUP/VDUPQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMOV/VMOVQ output:
+VMOV/VMOVQ:0:result_int8x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VMOV/VMOVQ:1:result_int16x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VMOV/VMOVQ:2:result_int32x2 [] = { fffffff0, fffffff0,  }
+VMOV/VMOVQ:3:result_int64x1 [] = { fffffffffffffff0,  }
+VMOV/VMOVQ:4:result_uint8x8 [] = { f0, f0, f0, f0, f0, f0, f0, f0,  }
+VMOV/VMOVQ:5:result_uint16x4 [] = { fff0, fff0, fff0, fff0,  }
+VMOV/VMOVQ:6:result_uint32x2 [] = { fffffff0, fffffff0,  }
+VMOV/VMOVQ:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VMOV/VMOVQ:8:result_poly8x8 [] = { f0, f0, f0, f0, f0, f0, f0, f0,  }
+VMOV/VMOVQ:9:result_poly16x4 [] = { fff0, fff0, fff0, fff0,  }
+VMOV/VMOVQ:10:result_float32x2 [] = { c1800000, c1800000,  }
+VMOV/VMOVQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMOV/VMOVQ:12:result_int8x16 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VMOV/VMOVQ:13:result_int16x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VMOV/VMOVQ:14:result_int32x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VMOV/VMOVQ:15:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VMOV/VMOVQ:16:result_uint8x16 [] = { f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0,  }
+VMOV/VMOVQ:17:result_uint16x8 [] = { fff0, fff0, fff0, fff0, fff0, fff0, fff0, fff0,  }
+VMOV/VMOVQ:18:result_uint32x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VMOV/VMOVQ:19:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VMOV/VMOVQ:20:result_poly8x16 [] = { f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0,  }
+VMOV/VMOVQ:21:result_poly16x8 [] = { fff0, fff0, fff0, fff0, fff0, fff0, fff0, fff0,  }
+VMOV/VMOVQ:22:result_float32x4 [] = { c1800000, c1800000, c1800000, c1800000,  }
+VMOV/VMOVQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMOV/VMOVQ output:
+VMOV/VMOVQ:0:result_int8x8 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VMOV/VMOVQ:1:result_int16x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VMOV/VMOVQ:2:result_int32x2 [] = { fffffff1, fffffff1,  }
+VMOV/VMOVQ:3:result_int64x1 [] = { fffffffffffffff1,  }
+VMOV/VMOVQ:4:result_uint8x8 [] = { f1, f1, f1, f1, f1, f1, f1, f1,  }
+VMOV/VMOVQ:5:result_uint16x4 [] = { fff1, fff1, fff1, fff1,  }
+VMOV/VMOVQ:6:result_uint32x2 [] = { fffffff1, fffffff1,  }
+VMOV/VMOVQ:7:result_uint64x1 [] = { fffffffffffffff1,  }
+VMOV/VMOVQ:8:result_poly8x8 [] = { f1, f1, f1, f1, f1, f1, f1, f1,  }
+VMOV/VMOVQ:9:result_poly16x4 [] = { fff1, fff1, fff1, fff1,  }
+VMOV/VMOVQ:10:result_float32x2 [] = { c1700000, c1700000,  }
+VMOV/VMOVQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMOV/VMOVQ:12:result_int8x16 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VMOV/VMOVQ:13:result_int16x8 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VMOV/VMOVQ:14:result_int32x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VMOV/VMOVQ:15:result_int64x2 [] = { fffffffffffffff1, fffffffffffffff1,  }
+VMOV/VMOVQ:16:result_uint8x16 [] = { f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1,  }
+VMOV/VMOVQ:17:result_uint16x8 [] = { fff1, fff1, fff1, fff1, fff1, fff1, fff1, fff1,  }
+VMOV/VMOVQ:18:result_uint32x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VMOV/VMOVQ:19:result_uint64x2 [] = { fffffffffffffff1, fffffffffffffff1,  }
+VMOV/VMOVQ:20:result_poly8x16 [] = { f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1,  }
+VMOV/VMOVQ:21:result_poly16x8 [] = { fff1, fff1, fff1, fff1, fff1, fff1, fff1, fff1,  }
+VMOV/VMOVQ:22:result_float32x4 [] = { c1700000, c1700000, c1700000, c1700000,  }
+VMOV/VMOVQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMOV/VMOVQ output:
+VMOV/VMOVQ:0:result_int8x8 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VMOV/VMOVQ:1:result_int16x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VMOV/VMOVQ:2:result_int32x2 [] = { fffffff2, fffffff2,  }
+VMOV/VMOVQ:3:result_int64x1 [] = { fffffffffffffff2,  }
+VMOV/VMOVQ:4:result_uint8x8 [] = { f2, f2, f2, f2, f2, f2, f2, f2,  }
+VMOV/VMOVQ:5:result_uint16x4 [] = { fff2, fff2, fff2, fff2,  }
+VMOV/VMOVQ:6:result_uint32x2 [] = { fffffff2, fffffff2,  }
+VMOV/VMOVQ:7:result_uint64x1 [] = { fffffffffffffff2,  }
+VMOV/VMOVQ:8:result_poly8x8 [] = { f2, f2, f2, f2, f2, f2, f2, f2,  }
+VMOV/VMOVQ:9:result_poly16x4 [] = { fff2, fff2, fff2, fff2,  }
+VMOV/VMOVQ:10:result_float32x2 [] = { c1600000, c1600000,  }
+VMOV/VMOVQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMOV/VMOVQ:12:result_int8x16 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VMOV/VMOVQ:13:result_int16x8 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VMOV/VMOVQ:14:result_int32x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VMOV/VMOVQ:15:result_int64x2 [] = { fffffffffffffff2, fffffffffffffff2,  }
+VMOV/VMOVQ:16:result_uint8x16 [] = { f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2,  }
+VMOV/VMOVQ:17:result_uint16x8 [] = { fff2, fff2, fff2, fff2, fff2, fff2, fff2, fff2,  }
+VMOV/VMOVQ:18:result_uint32x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VMOV/VMOVQ:19:result_uint64x2 [] = { fffffffffffffff2, fffffffffffffff2,  }
+VMOV/VMOVQ:20:result_poly8x16 [] = { f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2,  }
+VMOV/VMOVQ:21:result_poly16x8 [] = { fff2, fff2, fff2, fff2, fff2, fff2, fff2, fff2,  }
+VMOV/VMOVQ:22:result_float32x4 [] = { c1600000, c1600000, c1600000, c1600000,  }
+VMOV/VMOVQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VGET_HIGH output:
+VGET_HIGH:0:result_int8x8 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VGET_HIGH:1:result_int16x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VGET_HIGH:2:result_int32x2 [] = { fffffff2, fffffff3,  }
+VGET_HIGH:3:result_int64x1 [] = { fffffffffffffff1,  }
+VGET_HIGH:4:result_uint8x8 [] = { f8, f9, fa, fb, fc, fd, fe, ff,  }
+VGET_HIGH:5:result_uint16x4 [] = { fff4, fff5, fff6, fff7,  }
+VGET_HIGH:6:result_uint32x2 [] = { fffffff2, fffffff3,  }
+VGET_HIGH:7:result_uint64x1 [] = { fffffffffffffff1,  }
+VGET_HIGH:8:result_poly8x8 [] = { f8, f9, fa, fb, fc, fd, fe, ff,  }
+VGET_HIGH:9:result_poly16x4 [] = { fff4, fff5, fff6, fff7,  }
+VGET_HIGH:10:result_float32x2 [] = { c1600000, c1500000,  }
+VGET_HIGH:11:result_float16x4 [] = { ca00, c980, c900, c880,  }
+VGET_HIGH:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VGET_HIGH:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VGET_HIGH:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VGET_HIGH:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VGET_HIGH:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VGET_HIGH:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VGET_HIGH:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VGET_HIGH:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VGET_HIGH:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VGET_HIGH:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VGET_HIGH:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VGET_HIGH:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VGET_LOW output:
+VGET_LOW:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VGET_LOW:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VGET_LOW:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VGET_LOW:3:result_int64x1 [] = { fffffffffffffff0,  }
+VGET_LOW:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VGET_LOW:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VGET_LOW:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VGET_LOW:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VGET_LOW:8:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VGET_LOW:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VGET_LOW:10:result_float32x2 [] = { c1800000, c1700000,  }
+VGET_LOW:11:result_float16x4 [] = { cc00, cb80, cb00, ca80,  }
+VGET_LOW:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VGET_LOW:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VGET_LOW:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VGET_LOW:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VGET_LOW:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VGET_LOW:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VGET_LOW:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VGET_LOW:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VGET_LOW:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VGET_LOW:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VGET_LOW:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VGET_LOW:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLAL_LANE cumulative saturation output:
+VQDMLAL_LANE:0:vqdmlal_lane_s16 Neon cumulative saturation 0
+VQDMLAL_LANE:1:vqdmlal_lane_s32 Neon cumulative saturation 0
+
+VQDMLAL_LANE output:
+VQDMLAL_LANE:2:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:3:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:4:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:5:result_int64x1 [] = { 3333333333333333,  }
+VQDMLAL_LANE:6:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:7:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:8:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:9:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLAL_LANE:10:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:11:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:12:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:13:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLAL_LANE:14:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:15:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:16:result_int32x4 [] = { 7c1e, 7c1f, 7c20, 7c21,  }
+VQDMLAL_LANE:17:result_int64x2 [] = { 7c1e, 7c1f,  }
+VQDMLAL_LANE:18:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:19:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:20:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_LANE:21:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLAL_LANE:22:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:23:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:24:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_LANE:25:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLAL_LANE (mul with input=0) cumulative saturation output:
+VQDMLAL_LANE:26:vqdmlal_lane_s16 Neon cumulative saturation 0
+VQDMLAL_LANE:27:vqdmlal_lane_s32 Neon cumulative saturation 0
+
+VQDMLAL_LANE (mul with input=0) output:
+VQDMLAL_LANE:28:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:29:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:30:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:31:result_int64x1 [] = { 3333333333333333,  }
+VQDMLAL_LANE:32:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:33:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:34:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:35:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLAL_LANE:36:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:37:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:38:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:39:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLAL_LANE:40:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:41:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:42:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VQDMLAL_LANE:43:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VQDMLAL_LANE:44:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:45:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:46:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_LANE:47:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLAL_LANE:48:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:49:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:50:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_LANE:51:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLAL_LANE (check mul cumulative saturation) cumulative saturation output:
+VQDMLAL_LANE:52:vqdmlal_lane_s16 Neon cumulative saturation 1
+VQDMLAL_LANE:53:vqdmlal_lane_s32 Neon cumulative saturation 1
+
+VQDMLAL_LANE (check mul cumulative saturation) output:
+VQDMLAL_LANE:54:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:55:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:56:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:57:result_int64x1 [] = { 3333333333333333,  }
+VQDMLAL_LANE:58:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:59:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:60:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:61:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLAL_LANE:62:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:63:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:64:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:65:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLAL_LANE:66:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:67:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:68:result_int32x4 [] = { 7fffffef, 7ffffff0, 7ffffff1, 7ffffff2,  }
+VQDMLAL_LANE:69:result_int64x2 [] = { 7fffffffffffffef, 7ffffffffffffff0,  }
+VQDMLAL_LANE:70:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:71:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:72:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_LANE:73:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLAL_LANE:74:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:75:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:76:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_LANE:77:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLSL_LANE cumulative saturation output:
+VQDMLSL_LANE:0:vqdmlsl_lane_s16 Neon cumulative saturation 0
+VQDMLSL_LANE:1:vqdmlsl_lane_s32 Neon cumulative saturation 0
+
+VQDMLSL_LANE output:
+VQDMLSL_LANE:2:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:3:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:4:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:5:result_int64x1 [] = { 3333333333333333,  }
+VQDMLSL_LANE:6:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:7:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:8:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:9:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLSL_LANE:10:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:11:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:12:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:13:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLSL_LANE:14:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:15:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:16:result_int32x4 [] = { ffff83c2, ffff83c3, ffff83c4, ffff83c5,  }
+VQDMLSL_LANE:17:result_int64x2 [] = { ffffffffffff83c2, ffffffffffff83c3,  }
+VQDMLSL_LANE:18:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:19:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:20:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_LANE:21:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLSL_LANE:22:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:23:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:24:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_LANE:25:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLSL_LANE (mul with input=0) cumulative saturation output:
+VQDMLSL_LANE:26:vqdmlsl_lane_s16 Neon cumulative saturation 0
+VQDMLSL_LANE:27:vqdmlsl_lane_s32 Neon cumulative saturation 0
+
+VQDMLSL_LANE (mul with input=0) output:
+VQDMLSL_LANE:28:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:29:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:30:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:31:result_int64x1 [] = { 3333333333333333,  }
+VQDMLSL_LANE:32:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:33:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:34:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:35:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLSL_LANE:36:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:37:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:38:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:39:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLSL_LANE:40:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:41:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:42:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VQDMLSL_LANE:43:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VQDMLSL_LANE:44:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:45:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:46:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_LANE:47:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLSL_LANE:48:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:49:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:50:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_LANE:51:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLSL_LANE (check mul cumulative saturation) cumulative saturation output:
+VQDMLSL_LANE:52:vqdmlsl_lane_s16 Neon cumulative saturation 1
+VQDMLSL_LANE:53:vqdmlsl_lane_s32 Neon cumulative saturation 1
+
+VQDMLSL_LANE (check mul cumulative saturation) output:
+VQDMLSL_LANE:54:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:55:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:56:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:57:result_int64x1 [] = { 3333333333333333,  }
+VQDMLSL_LANE:58:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:59:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:60:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:61:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLSL_LANE:62:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:63:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:64:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:65:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLSL_LANE:66:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:67:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:68:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VQDMLSL_LANE:69:result_int64x2 [] = { 8000000000000000, 8000000000000000,  }
+VQDMLSL_LANE:70:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:71:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:72:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_LANE:73:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLSL_LANE:74:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:75:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:76:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_LANE:77:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLAL_N cumulative saturation output:
+VQDMLAL_N:0:vqdmlal_n_s16 Neon cumulative saturation 0
+VQDMLAL_N:1:vqdmlal_n_s32 Neon cumulative saturation 0
+
+VQDMLAL_N output:
+VQDMLAL_N:2:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:3:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:4:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_N:5:result_int64x1 [] = { 3333333333333333,  }
+VQDMLAL_N:6:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:7:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:8:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_N:9:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLAL_N:10:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:11:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:12:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_N:13:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLAL_N:14:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:15:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:16:result_int32x4 [] = { 1684, 1685, 1686, 1687,  }
+VQDMLAL_N:17:result_int64x2 [] = { 21ce, 21cf,  }
+VQDMLAL_N:18:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:19:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:20:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_N:21:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLAL_N:22:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:23:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:24:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_N:25:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLAL_N (check mul cumulative saturation) cumulative saturation output:
+VQDMLAL_N:26:vqdmlal_n_s16 Neon cumulative saturation 1
+VQDMLAL_N:27:vqdmlal_n_s32 Neon cumulative saturation 1
+
+VQDMLAL_N (check mul cumulative saturation) output:
+VQDMLAL_N:28:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:29:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:30:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_N:31:result_int64x1 [] = { 3333333333333333,  }
+VQDMLAL_N:32:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:33:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:34:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_N:35:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLAL_N:36:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:37:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:38:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_N:39:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLAL_N:40:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:41:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:42:result_int32x4 [] = { 7fffffef, 7ffffff0, 7ffffff1, 7ffffff2,  }
+VQDMLAL_N:43:result_int64x2 [] = { 7fffffffffffffef, 7ffffffffffffff0,  }
+VQDMLAL_N:44:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:45:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:46:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_N:47:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLAL_N:48:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:49:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:50:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_N:51:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLSL_N cumulative saturation output:
+VQDMLSL_N:0:vqdmlsl_n_s16 Neon cumulative saturation 0
+VQDMLSL_N:1:vqdmlsl_n_s32 Neon cumulative saturation 0
+
+VQDMLSL_N output:
+VQDMLSL_N:2:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:3:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:4:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_N:5:result_int64x1 [] = { 3333333333333333,  }
+VQDMLSL_N:6:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:7:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:8:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_N:9:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLSL_N:10:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:11:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:12:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_N:13:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLSL_N:14:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:15:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:16:result_int32x4 [] = { ffffe95c, ffffe95d, ffffe95e, ffffe95f,  }
+VQDMLSL_N:17:result_int64x2 [] = { ffffffffffffde12, ffffffffffffde13,  }
+VQDMLSL_N:18:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:19:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:20:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_N:21:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLSL_N:22:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:23:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:24:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_N:25:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLSL_N (check mul cumulative saturation) cumulative saturation output:
+VQDMLSL_N:26:vqdmlsl_n_s16 Neon cumulative saturation 1
+VQDMLSL_N:27:vqdmlsl_n_s32 Neon cumulative saturation 1
+
+VQDMLSL_N (check mul cumulative saturation) output:
+VQDMLSL_N:28:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:29:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:30:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_N:31:result_int64x1 [] = { 3333333333333333,  }
+VQDMLSL_N:32:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:33:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:34:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_N:35:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLSL_N:36:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:37:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:38:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_N:39:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLSL_N:40:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:41:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:42:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VQDMLSL_N:43:result_int64x2 [] = { 8000000000000000, 8000000000000000,  }
+VQDMLSL_N:44:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:45:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:46:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_N:47:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLSL_N:48:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:49:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:50:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_N:51:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VEXT/VEXTQ output:
+VEXT/VEXTQ:0:result_int8x8 [] = { fffffff7, 11, 11, 11, 11, 11, 11, 11,  }
+VEXT/VEXTQ:1:result_int16x4 [] = { fffffff3, 22, 22, 22,  }
+VEXT/VEXTQ:2:result_int32x2 [] = { fffffff1, 33,  }
+VEXT/VEXTQ:3:result_int64x1 [] = { fffffffffffffff0,  }
+VEXT/VEXTQ:4:result_uint8x8 [] = { f6, f7, 55, 55, 55, 55, 55, 55,  }
+VEXT/VEXTQ:5:result_uint16x4 [] = { fff2, fff3, 66, 66,  }
+VEXT/VEXTQ:6:result_uint32x2 [] = { fffffff1, 77,  }
+VEXT/VEXTQ:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VEXT/VEXTQ:8:result_poly8x8 [] = { f6, f7, 55, 55, 55, 55, 55, 55,  }
+VEXT/VEXTQ:9:result_poly16x4 [] = { fff2, fff3, 66, 66,  }
+VEXT/VEXTQ:10:result_float32x2 [] = { c1700000, 42066666,  }
+VEXT/VEXTQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VEXT/VEXTQ:12:result_int8x16 [] = { fffffffe, ffffffff, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11,  }
+VEXT/VEXTQ:13:result_int16x8 [] = { fffffff7, 22, 22, 22, 22, 22, 22, 22,  }
+VEXT/VEXTQ:14:result_int32x4 [] = { fffffff3, 33, 33, 33,  }
+VEXT/VEXTQ:15:result_int64x2 [] = { fffffffffffffff1, 44,  }
+VEXT/VEXTQ:16:result_uint8x16 [] = { fc, fd, fe, ff, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55,  }
+VEXT/VEXTQ:17:result_uint16x8 [] = { fff6, fff7, 66, 66, 66, 66, 66, 66,  }
+VEXT/VEXTQ:18:result_uint32x4 [] = { fffffff3, 77, 77, 77,  }
+VEXT/VEXTQ:19:result_uint64x2 [] = { fffffffffffffff1, 88,  }
+VEXT/VEXTQ:20:result_poly8x16 [] = { fc, fd, fe, ff, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55,  }
+VEXT/VEXTQ:21:result_poly16x8 [] = { fff6, fff7, 66, 66, 66, 66, 66, 66,  }
+VEXT/VEXTQ:22:result_float32x4 [] = { c1500000, 4204cccd, 4204cccd, 4204cccd,  }
+VEXT/VEXTQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSHR_N output:
+VSHR_N:0:result_int8x8 [] = { fffffff8, fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb,  }
+VSHR_N:1:result_int16x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VSHR_N:2:result_int32x2 [] = { fffffffc, fffffffc,  }
+VSHR_N:3:result_int64x1 [] = { ffffffffffffffff,  }
+VSHR_N:4:result_uint8x8 [] = { 3c, 3c, 3c, 3c, 3d, 3d, 3d, 3d,  }
+VSHR_N:5:result_uint16x4 [] = { 1ffe, 1ffe, 1ffe, 1ffe,  }
+VSHR_N:6:result_uint32x2 [] = { 7ffffff, 7ffffff,  }
+VSHR_N:7:result_uint64x1 [] = { 7fffffff,  }
+VSHR_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHR_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHR_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSHR_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSHR_N:12:result_int8x16 [] = { fffffff8, fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb, fffffffc, fffffffc, fffffffd, fffffffd, fffffffe, fffffffe, ffffffff, ffffffff,  }
+VSHR_N:13:result_int16x8 [] = { ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VSHR_N:14:result_int32x4 [] = { fffffffc, fffffffc, fffffffc, fffffffc,  }
+VSHR_N:15:result_int64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VSHR_N:16:result_uint8x16 [] = { 3c, 3c, 3c, 3c, 3d, 3d, 3d, 3d, 3e, 3e, 3e, 3e, 3f, 3f, 3f, 3f,  }
+VSHR_N:17:result_uint16x8 [] = { 1ffe, 1ffe, 1ffe, 1ffe, 1ffe, 1ffe, 1ffe, 1ffe,  }
+VSHR_N:18:result_uint32x4 [] = { 7ffffff, 7ffffff, 7ffffff, 7ffffff,  }
+VSHR_N:19:result_uint64x2 [] = { 7fffffff, 7fffffff,  }
+VSHR_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHR_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHR_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSHR_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSHRN_N output:
+VSHRN_N:0:result_int8x8 [] = { fffffff8, fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb,  }
+VSHRN_N:1:result_int16x4 [] = { fffffff8, fffffff8, fffffff9, fffffff9,  }
+VSHRN_N:2:result_int32x2 [] = { fffffffc, fffffffc,  }
+VSHRN_N:3:result_int64x1 [] = { 3333333333333333,  }
+VSHRN_N:4:result_uint8x8 [] = { fc, fc, fc, fc, fd, fd, fd, fd,  }
+VSHRN_N:5:result_uint16x4 [] = { fffe, fffe, fffe, fffe,  }
+VSHRN_N:6:result_uint32x2 [] = { fffffffe, fffffffe,  }
+VSHRN_N:7:result_uint64x1 [] = { 3333333333333333,  }
+VSHRN_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHRN_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHRN_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSHRN_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSHRN_N:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHRN_N:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHRN_N:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSHRN_N:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VSHRN_N:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHRN_N:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHRN_N:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSHRN_N:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VSHRN_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHRN_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHRN_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSHRN_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHRN_N (with input = 0) output:
+VRSHRN_N:0:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHRN_N:1:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHRN_N:2:result_int32x2 [] = { 0, 0,  }
+VRSHRN_N:3:result_int64x1 [] = { 3333333333333333,  }
+VRSHRN_N:4:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHRN_N:5:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VRSHRN_N:6:result_uint32x2 [] = { 0, 0,  }
+VRSHRN_N:7:result_uint64x1 [] = { 3333333333333333,  }
+VRSHRN_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHRN_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHRN_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHRN_N:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHRN_N:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRSHRN_N:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHRN_N:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRSHRN_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHRN_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHRN_N output:
+VRSHRN_N:24:result_int8x8 [] = { fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb, fffffffc,  }
+VRSHRN_N:25:result_int16x4 [] = { fffffff8, fffffff9, fffffff9, fffffffa,  }
+VRSHRN_N:26:result_int32x2 [] = { fffffffc, fffffffc,  }
+VRSHRN_N:27:result_int64x1 [] = { 3333333333333333,  }
+VRSHRN_N:28:result_uint8x8 [] = { fc, fc, fd, fd, fd, fd, fe, fe,  }
+VRSHRN_N:29:result_uint16x4 [] = { fffe, fffe, fffe, fffe,  }
+VRSHRN_N:30:result_uint32x2 [] = { fffffffe, fffffffe,  }
+VRSHRN_N:31:result_uint64x1 [] = { 3333333333333333,  }
+VRSHRN_N:32:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:33:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHRN_N:34:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHRN_N:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHRN_N:36:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:37:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:38:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHRN_N:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRSHRN_N:40:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:41:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:42:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHRN_N:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRSHRN_N:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:45:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHRN_N:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHRN_N (with large shift amount) output:
+VRSHRN_N:48:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHRN_N:49:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHRN_N:50:result_int32x2 [] = { 0, 0,  }
+VRSHRN_N:51:result_int64x1 [] = { 3333333333333333,  }
+VRSHRN_N:52:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHRN_N:53:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VRSHRN_N:54:result_uint32x2 [] = { 0, 0,  }
+VRSHRN_N:55:result_uint64x1 [] = { 3333333333333333,  }
+VRSHRN_N:56:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:57:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHRN_N:58:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHRN_N:59:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHRN_N:60:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:61:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:62:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHRN_N:63:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRSHRN_N:64:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:65:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:66:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHRN_N:67:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRSHRN_N:68:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:69:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:70:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHRN_N:71:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHRN_N cumulative saturation output:
+VQRSHRN_N:0:vqrshrn_n_s16 Neon cumulative saturation 0
+VQRSHRN_N:1:vqrshrn_n_s32 Neon cumulative saturation 0
+VQRSHRN_N:2:vqrshrn_n_s64 Neon cumulative saturation 0
+VQRSHRN_N:3:vqrshrn_n_u16 Neon cumulative saturation 1
+VQRSHRN_N:4:vqrshrn_n_u32 Neon cumulative saturation 1
+VQRSHRN_N:5:vqrshrn_n_u64 Neon cumulative saturation 1
+
+VQRSHRN_N output:
+VQRSHRN_N:6:result_int8x8 [] = { fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb, fffffffc,  }
+VQRSHRN_N:7:result_int16x4 [] = { fffffff8, fffffff9, fffffff9, fffffffa,  }
+VQRSHRN_N:8:result_int32x2 [] = { fffffffc, fffffffc,  }
+VQRSHRN_N:9:result_int64x1 [] = { 3333333333333333,  }
+VQRSHRN_N:10:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHRN_N:11:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQRSHRN_N:12:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQRSHRN_N:13:result_uint64x1 [] = { 3333333333333333,  }
+VQRSHRN_N:14:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:15:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:16:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHRN_N:17:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRN_N:18:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:19:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:20:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRN_N:21:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRN_N:22:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:23:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:24:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRN_N:25:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRN_N:26:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:27:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:28:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRN_N:29:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHRN_N (check saturation: shift by 3) cumulative saturation output:
+VQRSHRN_N:30:vqrshrn_n_s16 Neon cumulative saturation 1
+VQRSHRN_N:31:vqrshrn_n_s32 Neon cumulative saturation 1
+VQRSHRN_N:32:vqrshrn_n_s64 Neon cumulative saturation 1
+VQRSHRN_N:33:vqrshrn_n_u16 Neon cumulative saturation 1
+VQRSHRN_N:34:vqrshrn_n_u32 Neon cumulative saturation 1
+VQRSHRN_N:35:vqrshrn_n_u64 Neon cumulative saturation 1
+
+VQRSHRN_N (check saturation: shift by 3) output:
+VQRSHRN_N:36:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQRSHRN_N:37:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRSHRN_N:38:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRSHRN_N:39:result_int64x1 [] = { 3333333333333333,  }
+VQRSHRN_N:40:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHRN_N:41:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQRSHRN_N:42:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQRSHRN_N:43:result_uint64x1 [] = { 3333333333333333,  }
+VQRSHRN_N:44:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:45:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:46:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHRN_N:47:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRN_N:48:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:49:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:50:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRN_N:51:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRN_N:52:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:53:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:54:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRN_N:55:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRN_N:56:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:57:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:58:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRN_N:59:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHRN_N (check saturation: shift by max) cumulative saturation output:
+VQRSHRN_N:60:vqrshrn_n_s16 Neon cumulative saturation 1
+VQRSHRN_N:61:vqrshrn_n_s32 Neon cumulative saturation 1
+VQRSHRN_N:62:vqrshrn_n_s64 Neon cumulative saturation 1
+VQRSHRN_N:63:vqrshrn_n_u16 Neon cumulative saturation 1
+VQRSHRN_N:64:vqrshrn_n_u32 Neon cumulative saturation 1
+VQRSHRN_N:65:vqrshrn_n_u64 Neon cumulative saturation 1
+
+VQRSHRN_N (check saturation: shift by max) output:
+VQRSHRN_N:66:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQRSHRN_N:67:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRSHRN_N:68:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRSHRN_N:69:result_int64x1 [] = { 3333333333333333,  }
+VQRSHRN_N:70:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHRN_N:71:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQRSHRN_N:72:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQRSHRN_N:73:result_uint64x1 [] = { 3333333333333333,  }
+VQRSHRN_N:74:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:75:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:76:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHRN_N:77:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRN_N:78:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:79:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:80:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRN_N:81:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRN_N:82:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:83:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:84:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRN_N:85:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRN_N:86:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:87:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:88:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRN_N:89:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSET_LANE/VSET_LANEQ output:
+VSET_LANE/VSET_LANEQ:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, 11,  }
+VSET_LANE/VSET_LANEQ:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, 22,  }
+VSET_LANE/VSET_LANEQ:2:result_int32x2 [] = { fffffff0, 33,  }
+VSET_LANE/VSET_LANEQ:3:result_int64x1 [] = { 44,  }
+VSET_LANE/VSET_LANEQ:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, 55, f7,  }
+VSET_LANE/VSET_LANEQ:5:result_uint16x4 [] = { fff0, fff1, 66, fff3,  }
+VSET_LANE/VSET_LANEQ:6:result_uint32x2 [] = { fffffff0, 77,  }
+VSET_LANE/VSET_LANEQ:7:result_uint64x1 [] = { 88,  }
+VSET_LANE/VSET_LANEQ:8:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, 55, f7,  }
+VSET_LANE/VSET_LANEQ:9:result_poly16x4 [] = { fff0, fff1, 66, fff3,  }
+VSET_LANE/VSET_LANEQ:10:result_float32x2 [] = { c1800000, 4204cccd,  }
+VSET_LANE/VSET_LANEQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSET_LANE/VSET_LANEQ:12:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffff99,  }
+VSET_LANE/VSET_LANEQ:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, aa, fffffff6, fffffff7,  }
+VSET_LANE/VSET_LANEQ:14:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, bb,  }
+VSET_LANE/VSET_LANEQ:15:result_int64x2 [] = { fffffffffffffff0, cc,  }
+VSET_LANE/VSET_LANEQ:16:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, dd, ff,  }
+VSET_LANE/VSET_LANEQ:17:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, ee, fff7,  }
+VSET_LANE/VSET_LANEQ:18:result_uint32x4 [] = { fffffff0, fffffff1, ff, fffffff3,  }
+VSET_LANE/VSET_LANEQ:19:result_uint64x2 [] = { fffffffffffffff0, 11,  }
+VSET_LANE/VSET_LANEQ:20:result_poly8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, dd, ff,  }
+VSET_LANE/VSET_LANEQ:21:result_poly16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, ee, fff7,  }
+VSET_LANE/VSET_LANEQ:22:result_float32x4 [] = { c1800000, c1700000, c1600000, 41333333,  }
+VSET_LANE/VSET_LANEQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VGET_LANE/VGETQ_LANE output:
+vget_lane_s8: fffffff7
+vget_lane_s16: fffffff3
+vget_lane_s32: fffffff1
+vget_lane_s64: fffffffffffffff0
+vget_lane_u8: f6
+vget_lane_u16: fff2
+vget_lane_u32: fffffff1
+vget_lane_u64: fffffffffffffff0
+vget_lane_p8: f6
+vget_lane_p16: fff2
+vget_lane_f32: c1700000
+vgetq_lane_s8: ffffffff
+vgetq_lane_s16: fffffff5
+vgetq_lane_s32: fffffff3
+vgetq_lane_s64: fffffffffffffff1
+vgetq_lane_u8: fe
+vgetq_lane_u16: fff6
+vgetq_lane_u32: fffffff2
+vgetq_lane_u64: fffffffffffffff1
+vgetq_lane_p8: fe
+vgetq_lane_p16: fff6
+vgetq_lane_f32: c1500000
+
+
+VQSUB/VQSUBQ cumulative saturation output:
+VQSUB/VQSUBQ:0:vqsub_s8 Neon cumulative saturation 0
+VQSUB/VQSUBQ:1:vqsub_s16 Neon cumulative saturation 0
+VQSUB/VQSUBQ:2:vqsub_s32 Neon cumulative saturation 0
+VQSUB/VQSUBQ:3:vqsub_s64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:4:vqsub_u8 Neon cumulative saturation 0
+VQSUB/VQSUBQ:5:vqsub_u16 Neon cumulative saturation 0
+VQSUB/VQSUBQ:6:vqsub_u32 Neon cumulative saturation 0
+VQSUB/VQSUBQ:7:vqsub_u64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:8:vqsubq_s8 Neon cumulative saturation 0
+VQSUB/VQSUBQ:9:vqsubq_s16 Neon cumulative saturation 0
+VQSUB/VQSUBQ:10:vqsubq_s32 Neon cumulative saturation 0
+VQSUB/VQSUBQ:11:vqsubq_s64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:12:vqsubq_u8 Neon cumulative saturation 0
+VQSUB/VQSUBQ:13:vqsubq_u16 Neon cumulative saturation 0
+VQSUB/VQSUBQ:14:vqsubq_u32 Neon cumulative saturation 0
+VQSUB/VQSUBQ:15:vqsubq_u64 Neon cumulative saturation 0
+
+VQSUB/VQSUBQ output:
+VQSUB/VQSUBQ:16:result_int8x8 [] = { ffffffdf, ffffffe0, ffffffe1, ffffffe2, ffffffe3, ffffffe4, ffffffe5, ffffffe6,  }
+VQSUB/VQSUBQ:17:result_int16x4 [] = { ffffffce, ffffffcf, ffffffd0, ffffffd1,  }
+VQSUB/VQSUBQ:18:result_int32x2 [] = { ffffffbd, ffffffbe,  }
+VQSUB/VQSUBQ:19:result_int64x1 [] = { ffffffffffffffac,  }
+VQSUB/VQSUBQ:20:result_uint8x8 [] = { 9b, 9c, 9d, 9e, 9f, a0, a1, a2,  }
+VQSUB/VQSUBQ:21:result_uint16x4 [] = { ff8a, ff8b, ff8c, ff8d,  }
+VQSUB/VQSUBQ:22:result_uint32x2 [] = { ffffff79, ffffff7a,  }
+VQSUB/VQSUBQ:23:result_uint64x1 [] = { ffffffffffffff68,  }
+VQSUB/VQSUBQ:24:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSUB/VQSUBQ:25:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSUB/VQSUBQ:26:result_float32x2 [] = { 33333333, 33333333,  }
+VQSUB/VQSUBQ:27:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSUB/VQSUBQ:28:result_int8x16 [] = { ffffffdf, ffffffe0, ffffffe1, ffffffe2, ffffffe3, ffffffe4, ffffffe5, ffffffe6, ffffffe7, ffffffe8, ffffffe9, ffffffea, ffffffeb, ffffffec, ffffffed, ffffffee,  }
+VQSUB/VQSUBQ:29:result_int16x8 [] = { ffffffce, ffffffcf, ffffffd0, ffffffd1, ffffffd2, ffffffd3, ffffffd4, ffffffd5,  }
+VQSUB/VQSUBQ:30:result_int32x4 [] = { ffffffbd, ffffffbe, ffffffbf, ffffffc0,  }
+VQSUB/VQSUBQ:31:result_int64x2 [] = { ffffffffffffffac, ffffffffffffffad,  }
+VQSUB/VQSUBQ:32:result_uint8x16 [] = { 9b, 9c, 9d, 9e, 9f, a0, a1, a2, a3, a4, a5, a6, a7, a8, a9, aa,  }
+VQSUB/VQSUBQ:33:result_uint16x8 [] = { ff8a, ff8b, ff8c, ff8d, ff8e, ff8f, ff90, ff91,  }
+VQSUB/VQSUBQ:34:result_uint32x4 [] = { ffffff79, ffffff7a, ffffff7b, ffffff7c,  }
+VQSUB/VQSUBQ:35:result_uint64x2 [] = { ffffffffffffff68, ffffffffffffff69,  }
+VQSUB/VQSUBQ:36:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSUB/VQSUBQ:37:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSUB/VQSUBQ:38:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSUB/VQSUBQ:39:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSUB/VQSUBQ 64 bits saturation cumulative saturation output:
+VQSUB/VQSUBQ:40:vqsub_s64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:41:vqsub_u64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:42:vqsubq_s64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:43:vqsubq_u64 Neon cumulative saturation 0
+
+64 bits saturation:
+VQSUB/VQSUBQ:44:result_int64x1 [] = { fffffffffffffff0,  }
+VQSUB/VQSUBQ:45:result_uint64x1 [] = { fffffffffffffff0,  }
+VQSUB/VQSUBQ:46:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VQSUB/VQSUBQ:47:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+
+VQSUB/VQSUBQ 64 bits saturation cumulative saturation output:
+VQSUB/VQSUBQ:48:vqsub_s64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:49:vqsub_u64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:50:vqsubq_s64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:51:vqsubq_u64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:52:result_int64x1 [] = { ffffffffffffffac,  }
+VQSUB/VQSUBQ:53:result_uint64x1 [] = { ffffffffffffff68,  }
+VQSUB/VQSUBQ:54:result_int64x2 [] = { ffffffffffffffac, ffffffffffffffad,  }
+VQSUB/VQSUBQ:55:result_uint64x2 [] = { ffffffffffffff68, ffffffffffffff69,  }
+
+VQSUB/VQSUBQ 64 bits saturation cumulative saturation output:
+VQSUB/VQSUBQ:56:vqsub_s64 Neon cumulative saturation 1
+VQSUB/VQSUBQ:57:vqsub_u64 Neon cumulative saturation 1
+VQSUB/VQSUBQ:58:vqsubq_s64 Neon cumulative saturation 1
+VQSUB/VQSUBQ:59:vqsubq_u64 Neon cumulative saturation 1
+VQSUB/VQSUBQ:60:result_int64x1 [] = { 8000000000000000,  }
+VQSUB/VQSUBQ:61:result_uint64x1 [] = { 0,  }
+VQSUB/VQSUBQ:62:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+VQSUB/VQSUBQ:63:result_uint64x2 [] = { 0, 0,  }
+
+less than 64 bits saturation:
+VQSUB/VQSUBQ:64:vqsub_s8 Neon cumulative saturation 1
+VQSUB/VQSUBQ:65:vqsub_s16 Neon cumulative saturation 1
+VQSUB/VQSUBQ:66:vqsub_s32 Neon cumulative saturation 1
+VQSUB/VQSUBQ:67:vqsubq_s8 Neon cumulative saturation 1
+VQSUB/VQSUBQ:68:vqsubq_s16 Neon cumulative saturation 1
+VQSUB/VQSUBQ:69:vqsubq_s32 Neon cumulative saturation 1
+VQSUB/VQSUBQ:70:result_int8x8 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQSUB/VQSUBQ:71:result_int16x4 [] = { ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQSUB/VQSUBQ:72:result_int32x2 [] = { 80000000, 80000000,  }
+VQSUB/VQSUBQ:73:result_int8x16 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQSUB/VQSUBQ:74:result_int16x8 [] = { ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQSUB/VQSUBQ:75:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+
+VQSUB/VQSUBQ less than 64 bits saturation cumulative saturation output:
+VQSUB/VQSUBQ:76:vqsub_u8 Neon cumulative saturation 1
+VQSUB/VQSUBQ:77:vqsub_u16 Neon cumulative saturation 1
+VQSUB/VQSUBQ:78:vqsub_u32 Neon cumulative saturation 1
+VQSUB/VQSUBQ:79:vqsubq_u8 Neon cumulative saturation 1
+VQSUB/VQSUBQ:80:vqsubq_u16 Neon cumulative saturation 1
+VQSUB/VQSUBQ:81:vqsubq_u32 Neon cumulative saturation 1
+VQSUB/VQSUBQ:82:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSUB/VQSUBQ:83:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQSUB/VQSUBQ:84:result_uint32x2 [] = { 0, 0,  }
+VQSUB/VQSUBQ:85:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSUB/VQSUBQ:86:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSUB/VQSUBQ:87:result_uint32x4 [] = { 0, 0, 0, 0,  }
+
+VQDMULH cumulative saturation output:
+VQDMULH:0:vqdmulh_s16 Neon cumulative saturation 0
+VQDMULH:1:vqdmulh_s32 Neon cumulative saturation 0
+VQDMULH:2:vqdmulhq_s16 Neon cumulative saturation 0
+VQDMULH:3:vqdmulhq_s32 Neon cumulative saturation 0
+
+VQDMULH output:
+VQDMULH:4:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:5:result_int16x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQDMULH:6:result_int32x2 [] = { ffffffff, ffffffff,  }
+VQDMULH:7:result_int64x1 [] = { 3333333333333333,  }
+VQDMULH:8:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:9:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH:10:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMULH:11:result_uint64x1 [] = { 3333333333333333,  }
+VQDMULH:12:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:13:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH:14:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMULH:15:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMULH:16:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:17:result_int16x8 [] = { ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQDMULH:18:result_int32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQDMULH:19:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH:20:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:21:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH:22:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH:23:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH:24:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:25:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH:26:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH:27:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMULH cumulative saturation output:
+VQDMULH:28:vqdmulh_s16 Neon cumulative saturation 1
+VQDMULH:29:vqdmulh_s32 Neon cumulative saturation 1
+VQDMULH:30:vqdmulhq_s16 Neon cumulative saturation 1
+VQDMULH:31:vqdmulhq_s32 Neon cumulative saturation 1
+
+VQDMULH output:
+VQDMULH:32:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:33:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQDMULH:34:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQDMULH:35:result_int64x1 [] = { 3333333333333333,  }
+VQDMULH:36:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:37:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH:38:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMULH:39:result_uint64x1 [] = { 3333333333333333,  }
+VQDMULH:40:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:41:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH:42:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMULH:43:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMULH:44:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:45:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQDMULH:46:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQDMULH:47:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH:48:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:49:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH:50:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH:51:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH:52:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:53:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH:54:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH:55:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMULH_LANE cumulative saturation output:
+VQDMULH_LANE:0:vqdmulh_lane_s16 Neon cumulative saturation 0
+VQDMULH_LANE:1:vqdmulh_lane_s32 Neon cumulative saturation 0
+VQDMULH_LANE:2:vqdmulhq_lane_s16 Neon cumulative saturation 0
+VQDMULH_LANE:3:vqdmulhq_lane_s32 Neon cumulative saturation 0
+
+VQDMULH_LANE output:
+VQDMULH_LANE:4:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:5:result_int16x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQDMULH_LANE:6:result_int32x2 [] = { ffffffff, ffffffff,  }
+VQDMULH_LANE:7:result_int64x1 [] = { 3333333333333333,  }
+VQDMULH_LANE:8:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:9:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH_LANE:10:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMULH_LANE:11:result_uint64x1 [] = { 3333333333333333,  }
+VQDMULH_LANE:12:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:13:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH_LANE:14:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMULH_LANE:15:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMULH_LANE:16:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:17:result_int16x8 [] = { ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQDMULH_LANE:18:result_int32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQDMULH_LANE:19:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH_LANE:20:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:21:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH_LANE:22:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH_LANE:23:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH_LANE:24:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:25:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH_LANE:26:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH_LANE:27:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMULH_LANE (check mul cumulative saturation) cumulative saturation output:
+VQDMULH_LANE:28:vqdmulh_lane_s16 Neon cumulative saturation 1
+VQDMULH_LANE:29:vqdmulh_lane_s32 Neon cumulative saturation 1
+VQDMULH_LANE:30:vqdmulhq_lane_s16 Neon cumulative saturation 1
+VQDMULH_LANE:31:vqdmulhq_lane_s32 Neon cumulative saturation 1
+
+VQDMULH_LANE (check mul cumulative saturation) output:
+VQDMULH_LANE:32:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:33:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQDMULH_LANE:34:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQDMULH_LANE:35:result_int64x1 [] = { 3333333333333333,  }
+VQDMULH_LANE:36:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:37:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH_LANE:38:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMULH_LANE:39:result_uint64x1 [] = { 3333333333333333,  }
+VQDMULH_LANE:40:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:41:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH_LANE:42:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMULH_LANE:43:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMULH_LANE:44:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:45:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQDMULH_LANE:46:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQDMULH_LANE:47:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH_LANE:48:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:49:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH_LANE:50:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH_LANE:51:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH_LANE:52:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:53:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH_LANE:54:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH_LANE:55:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMULH_N cumulative saturation output:
+VQDMULH_N:0:vqdmulh_n_s16 Neon cumulative saturation 0
+VQDMULH_N:1:vqdmulh_n_s32 Neon cumulative saturation 0
+VQDMULH_N:2:vqdmulhq_n_s16 Neon cumulative saturation 0
+VQDMULH_N:3:vqdmulhq_n_s32 Neon cumulative saturation 0
+
+VQDMULH_N output:
+VQDMULH_N:4:result_int16x4 [] = { 19, 19, 19, 19,  }
+VQDMULH_N:5:result_int32x2 [] = { 4, 4,  }
+VQDMULH_N:6:result_int16x8 [] = { 10, 10, 10, 10, 10, 10, 10, 10,  }
+VQDMULH_N:7:result_int32x4 [] = { a, a, a, a,  }
+
+VQDMULH_N (check mul cumulative saturation) cumulative saturation output:
+VQDMULH_N:8:vqdmulh_n_s16 Neon cumulative saturation 1
+VQDMULH_N:9:vqdmulh_n_s32 Neon cumulative saturation 1
+VQDMULH_N:10:vqdmulhq_n_s16 Neon cumulative saturation 1
+VQDMULH_N:11:vqdmulhq_n_s32 Neon cumulative saturation 1
+
+VQDMULH_N (check mul cumulative saturation) output:
+VQDMULH_N:12:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_N:13:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQDMULH_N:14:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQDMULH_N:15:result_int64x1 [] = { 3333333333333333,  }
+VQDMULH_N:16:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_N:17:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH_N:18:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMULH_N:19:result_uint64x1 [] = { 3333333333333333,  }
+VQDMULH_N:20:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_N:21:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH_N:22:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMULH_N:23:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMULH_N:24:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_N:25:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQDMULH_N:26:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQDMULH_N:27:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH_N:28:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_N:29:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH_N:30:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH_N:31:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH_N:32:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_N:33:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH_N:34:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH_N:35:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMULL cumulative saturation output:
+VQDMULL:0:vqdmull_s16 Neon cumulative saturation 0
+VQDMULL:1:vqdmull_s32 Neon cumulative saturation 0
+
+VQDMULL output:
+VQDMULL:2:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:3:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULL:4:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMULL:5:result_int64x1 [] = { 3333333333333333,  }
+VQDMULL:6:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:7:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULL:8:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMULL:9:result_uint64x1 [] = { 3333333333333333,  }
+VQDMULL:10:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:11:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULL:12:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMULL:13:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMULL:14:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:15:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULL:16:result_int32x4 [] = { 200, 1c2, 188, 152,  }
+VQDMULL:17:result_int64x2 [] = { 200, 1c2,  }
+VQDMULL:18:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:19:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULL:20:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULL:21:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULL:22:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:23:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULL:24:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULL:25:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMULL (check mul cumulative saturation) cumulative saturation output:
+VQDMULL:26:vqdmull_s16 Neon cumulative saturation 1
+VQDMULL:27:vqdmull_s32 Neon cumulative saturation 1
+
+VQDMULL (check mul cumulative saturation) output:
+VQDMULL:28:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:29:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULL:30:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMULL:31:result_int64x1 [] = { 3333333333333333,  }
+VQDMULL:32:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:33:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULL:34:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMULL:35:result_uint64x1 [] = { 3333333333333333,  }
+VQDMULL:36:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:37:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULL:38:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMULL:39:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMULL:40:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:41:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULL:42:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQDMULL:43:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+VQDMULL:44:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:45:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULL:46:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULL:47:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULL:48:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:49:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULL:50:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULL:51:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLAL cumulative saturation output:
+VQDMLAL:0:vqdmlal_s16 Neon cumulative saturation 0
+VQDMLAL:1:vqdmlal_s32 Neon cumulative saturation 0
+
+VQDMLAL output:
+VQDMLAL:2:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:3:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL:4:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLAL:5:result_int64x1 [] = { 3333333333333333,  }
+VQDMLAL:6:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:7:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL:8:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLAL:9:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLAL:10:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:11:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL:12:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLAL:13:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLAL:14:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:15:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL:16:result_int32x4 [] = { 7c1e, 7c1f, 7c20, 7c21,  }
+VQDMLAL:17:result_int64x2 [] = { 7c1e, 7c1f,  }
+VQDMLAL:18:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:19:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL:20:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL:21:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLAL:22:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:23:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL:24:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL:25:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLAL (check mul cumulative saturation) cumulative saturation output:
+VQDMLAL:26:vqdmlal_s16 Neon cumulative saturation 1
+VQDMLAL:27:vqdmlal_s32 Neon cumulative saturation 1
+
+VQDMLAL (check mul cumulative saturation) output:
+VQDMLAL:28:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:29:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL:30:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLAL:31:result_int64x1 [] = { 3333333333333333,  }
+VQDMLAL:32:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:33:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL:34:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLAL:35:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLAL:36:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:37:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL:38:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLAL:39:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLAL:40:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:41:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL:42:result_int32x4 [] = { 7fffffef, 7ffffff0, 7ffffff1, 7ffffff2,  }
+VQDMLAL:43:result_int64x2 [] = { 7fffffffffffffef, 7ffffffffffffff0,  }
+VQDMLAL:44:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:45:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL:46:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL:47:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLAL:48:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:49:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL:50:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL:51:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLSL cumulative saturation output:
+VQDMLSL:0:vqdmlsl_s16 Neon cumulative saturation 0
+VQDMLSL:1:vqdmlsl_s32 Neon cumulative saturation 0
+
+VQDMLSL output:
+VQDMLSL:2:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:3:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL:4:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLSL:5:result_int64x1 [] = { 3333333333333333,  }
+VQDMLSL:6:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:7:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL:8:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLSL:9:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLSL:10:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:11:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL:12:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLSL:13:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLSL:14:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:15:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL:16:result_int32x4 [] = { ffff83c2, ffff83c3, ffff83c4, ffff83c5,  }
+VQDMLSL:17:result_int64x2 [] = { ffffffffffff83c2, ffffffffffff83c3,  }
+VQDMLSL:18:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:19:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL:20:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL:21:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLSL:22:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:23:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL:24:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL:25:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLSL (check mul cumulative saturation) cumulative saturation output:
+VQDMLSL:26:vqdmlsl_s16 Neon cumulative saturation 1
+VQDMLSL:27:vqdmlsl_s32 Neon cumulative saturation 1
+
+VQDMLSL (check mul cumulative saturation) output:
+VQDMLSL:28:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:29:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL:30:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLSL:31:result_int64x1 [] = { 3333333333333333,  }
+VQDMLSL:32:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:33:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL:34:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLSL:35:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLSL:36:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:37:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL:38:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLSL:39:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLSL:40:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:41:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL:42:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VQDMLSL:43:result_int64x2 [] = { 8000000000000000, 8000000000000000,  }
+VQDMLSL:44:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:45:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL:46:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL:47:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLSL:48:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:49:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL:50:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL:51:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VCEQ/VCEQQ output:
+VCEQ/VCEQQ:0:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, ff, 0,  }
+VCEQ/VCEQQ:1:result_uint16x4 [] = { 0, 0, ffff, 0,  }
+VCEQ/VCEQQ:2:result_uint32x2 [] = { ffffffff, 0,  }
+VCEQ/VCEQQ:3:result_uint8x8 [] = { 0, 0, 0, ff, 0, 0, 0, 0,  }
+VCEQ/VCEQQ:4:result_uint16x4 [] = { 0, 0, ffff, 0,  }
+VCEQ/VCEQQ:5:result_uint32x2 [] = { 0, ffffffff,  }
+VCEQ/VCEQQ:6:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ff, 0, 0, 0,  }
+VCEQ/VCEQQ:7:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, ffff, 0,  }
+VCEQ/VCEQQ:8:result_uint32x4 [] = { 0, 0, ffffffff, 0,  }
+VCEQ/VCEQQ:9:result_uint8x16 [] = { 0, 0, 0, 0, ff, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VCEQ/VCEQQ:10:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, ffff, 0,  }
+VCEQ/VCEQQ:11:result_uint32x4 [] = { 0, 0, ffffffff, 0,  }
+VCEQ/VCEQQ:12:result_uint32x2 [] = { 0, ffffffff,  }
+VCEQ/VCEQQ:13:result_uint32x4 [] = { 0, 0, ffffffff, 0,  }
+VCEQ/VCEQQ:14:result_uint32x2 [] = { ffffffff, 0,  }
+VCEQ/VCEQQ:15:result_uint32x2 [] = { 0, ffffffff,  }
+VCEQ/VCEQQ:16:result_uint32x2 [] = { ffffffff, 0,  }
+VCEQ/VCEQQ FP special (NaN):17:result_uint32x2 [] = { 0, 0,  }
+VCEQ/VCEQQ FP special (-NaN):18:result_uint32x2 [] = { 0, 0,  }
+VCEQ/VCEQQ FP special (NaN):19:result_uint32x2 [] = { 0, 0,  }
+VCEQ/VCEQQ FP special (inf):20:result_uint32x2 [] = { 0, 0,  }
+VCEQ/VCEQQ FP special (-inf):21:result_uint32x2 [] = { 0, 0,  }
+VCEQ/VCEQQ FP special (inf):22:result_uint32x2 [] = { 0, 0,  }
+VCEQ/VCEQQ FP special (-0.0):23:result_uint32x2 [] = { ffffffff, ffffffff,  }
+
+VCEQ/VCEQQ p8 output:
+VCEQ/VCEQQ:0:result_uint8x8 [] = { 0, 0, 0, ff, 0, 0, 0, 0,  }
+VCEQ/VCEQQ:1:result_uint8x16 [] = { 0, 0, 0, 0, ff, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VCGE/VCGEQ output:
+VCGE/VCGEQ:0:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, ff, ff,  }
+VCGE/VCGEQ:1:result_uint16x4 [] = { 0, 0, ffff, ffff,  }
+VCGE/VCGEQ:2:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCGE/VCGEQ:3:result_uint8x8 [] = { 0, 0, 0, ff, ff, ff, ff, ff,  }
+VCGE/VCGEQ:4:result_uint16x4 [] = { 0, 0, ffff, ffff,  }
+VCGE/VCGEQ:5:result_uint32x2 [] = { 0, ffffffff,  }
+VCGE/VCGEQ:6:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ff, ff, ff, ff,  }
+VCGE/VCGEQ:7:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, ffff, ffff,  }
+VCGE/VCGEQ:8:result_uint32x4 [] = { 0, 0, ffffffff, ffffffff,  }
+VCGE/VCGEQ:9:result_uint8x16 [] = { 0, 0, 0, 0, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VCGE/VCGEQ:10:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, ffff, ffff,  }
+VCGE/VCGEQ:11:result_uint32x4 [] = { 0, 0, ffffffff, ffffffff,  }
+VCGE/VCGEQ:12:result_uint32x2 [] = { 0, ffffffff,  }
+VCGE/VCGEQ:13:result_uint32x4 [] = { 0, 0, ffffffff, ffffffff,  }
+VCGE/VCGEQ:14:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCGE/VCGEQ:15:result_uint32x2 [] = { 0, ffffffff,  }
+VCGE/VCGEQ:16:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCGE/VCGEQ FP special (NaN):17:result_uint32x2 [] = { 0, 0,  }
+VCGE/VCGEQ FP special (-NaN):18:result_uint32x2 [] = { 0, 0,  }
+VCGE/VCGEQ FP special (NaN):19:result_uint32x2 [] = { 0, 0,  }
+VCGE/VCGEQ FP special (inf):20:result_uint32x2 [] = { 0, 0,  }
+VCGE/VCGEQ FP special (-inf):21:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCGE/VCGEQ FP special (inf):22:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCGE/VCGEQ FP special (-0.0):23:result_uint32x2 [] = { ffffffff, ffffffff,  }
+
+VCLE/VCLEQ output:
+VCLE/VCLEQ:0:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, 0,  }
+VCLE/VCLEQ:1:result_uint16x4 [] = { ffff, ffff, ffff, 0,  }
+VCLE/VCLEQ:2:result_uint32x2 [] = { ffffffff, 0,  }
+VCLE/VCLEQ:3:result_uint8x8 [] = { ff, ff, ff, ff, 0, 0, 0, 0,  }
+VCLE/VCLEQ:4:result_uint16x4 [] = { ffff, ffff, ffff, 0,  }
+VCLE/VCLEQ:5:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCLE/VCLEQ:6:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, 0, 0, 0,  }
+VCLE/VCLEQ:7:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, 0,  }
+VCLE/VCLEQ:8:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, 0,  }
+VCLE/VCLEQ:9:result_uint8x16 [] = { ff, ff, ff, ff, ff, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VCLE/VCLEQ:10:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, 0,  }
+VCLE/VCLEQ:11:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, 0,  }
+VCLE/VCLEQ:12:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCLE/VCLEQ:13:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, 0,  }
+VCLE/VCLEQ:14:result_uint32x2 [] = { ffffffff, 0,  }
+VCLE/VCLEQ:15:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCLE/VCLEQ:16:result_uint32x2 [] = { ffffffff, 0,  }
+VCLE/VCLEQ FP special (NaN):17:result_uint32x2 [] = { 0, 0,  }
+VCLE/VCLEQ FP special (-NaN):18:result_uint32x2 [] = { 0, 0,  }
+VCLE/VCLEQ FP special (NaN):19:result_uint32x2 [] = { 0, 0,  }
+VCLE/VCLEQ FP special (inf):20:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCLE/VCLEQ FP special (-inf):21:result_uint32x2 [] = { 0, 0,  }
+VCLE/VCLEQ FP special (inf):22:result_uint32x2 [] = { 0, 0,  }
+VCLE/VCLEQ FP special (-0.0):23:result_uint32x2 [] = { ffffffff, ffffffff,  }
+
+VCGT/VCGTQ output:
+VCGT/VCGTQ:0:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, ff,  }
+VCGT/VCGTQ:1:result_uint16x4 [] = { 0, 0, 0, ffff,  }
+VCGT/VCGTQ:2:result_uint32x2 [] = { 0, ffffffff,  }
+VCGT/VCGTQ:3:result_uint8x8 [] = { 0, 0, 0, 0, ff, ff, ff, ff,  }
+VCGT/VCGTQ:4:result_uint16x4 [] = { 0, 0, 0, ffff,  }
+VCGT/VCGTQ:5:result_uint32x2 [] = { 0, 0,  }
+VCGT/VCGTQ:6:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ff, ff, ff,  }
+VCGT/VCGTQ:7:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, ffff,  }
+VCGT/VCGTQ:8:result_uint32x4 [] = { 0, 0, 0, ffffffff,  }
+VCGT/VCGTQ:9:result_uint8x16 [] = { 0, 0, 0, 0, 0, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VCGT/VCGTQ:10:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, ffff,  }
+VCGT/VCGTQ:11:result_uint32x4 [] = { 0, 0, 0, ffffffff,  }
+VCGT/VCGTQ:12:result_uint32x2 [] = { 0, 0,  }
+VCGT/VCGTQ:13:result_uint32x4 [] = { 0, 0, 0, ffffffff,  }
+VCGT/VCGTQ:14:result_uint32x2 [] = { 0, ffffffff,  }
+VCGT/VCGTQ:15:result_uint32x2 [] = { 0, 0,  }
+VCGT/VCGTQ:16:result_uint32x2 [] = { 0, ffffffff,  }
+VCGT/VCGTQ FP special (NaN):17:result_uint32x2 [] = { 0, 0,  }
+VCGT/VCGTQ FP special (-NaN):18:result_uint32x2 [] = { 0, 0,  }
+VCGT/VCGTQ FP special (NaN):19:result_uint32x2 [] = { 0, 0,  }
+VCGT/VCGTQ FP special (inf):20:result_uint32x2 [] = { 0, 0,  }
+VCGT/VCGTQ FP special (-inf):21:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCGT/VCGTQ FP special (inf):22:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCGT/VCGTQ FP special (-0.0):23:result_uint32x2 [] = { 0, 0,  }
+
+VCLT/VCLTQ output:
+VCLT/VCLTQ:0:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, 0, 0,  }
+VCLT/VCLTQ:1:result_uint16x4 [] = { ffff, ffff, 0, 0,  }
+VCLT/VCLTQ:2:result_uint32x2 [] = { 0, 0,  }
+VCLT/VCLTQ:3:result_uint8x8 [] = { ff, ff, ff, 0, 0, 0, 0, 0,  }
+VCLT/VCLTQ:4:result_uint16x4 [] = { ffff, ffff, 0, 0,  }
+VCLT/VCLTQ:5:result_uint32x2 [] = { ffffffff, 0,  }
+VCLT/VCLTQ:6:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, 0, 0, 0, 0,  }
+VCLT/VCLTQ:7:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, 0, 0,  }
+VCLT/VCLTQ:8:result_uint32x4 [] = { ffffffff, ffffffff, 0, 0,  }
+VCLT/VCLTQ:9:result_uint8x16 [] = { ff, ff, ff, ff, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VCLT/VCLTQ:10:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, 0, 0,  }
+VCLT/VCLTQ:11:result_uint32x4 [] = { ffffffff, ffffffff, 0, 0,  }
+VCLT/VCLTQ:12:result_uint32x2 [] = { ffffffff, 0,  }
+VCLT/VCLTQ:13:result_uint32x4 [] = { ffffffff, ffffffff, 0, 0,  }
+VCLT/VCLTQ:14:result_uint32x2 [] = { 0, 0,  }
+VCLT/VCLTQ:15:result_uint32x2 [] = { ffffffff, 0,  }
+VCLT/VCLTQ:16:result_uint32x2 [] = { 0, 0,  }
+VCLT/VCLTQ FP special (NaN):17:result_uint32x2 [] = { 0, 0,  }
+VCLT/VCLTQ FP special (-NaN):18:result_uint32x2 [] = { 0, 0,  }
+VCLT/VCLTQ FP special (NaN):19:result_uint32x2 [] = { 0, 0,  }
+VCLT/VCLTQ FP special (inf):20:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCLT/VCLTQ FP special (-inf):21:result_uint32x2 [] = { 0, 0,  }
+VCLT/VCLTQ FP special (inf):22:result_uint32x2 [] = { 0, 0,  }
+VCLT/VCLTQ FP special (-0.0):23:result_uint32x2 [] = { 0, 0,  }
+
+VBSL/VBSLQ output:
+VBSL/VBSLQ:0:result_int8x8 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff6, fffffff6, fffffff6, fffffff6,  }
+VBSL/VBSLQ:1:result_int16x4 [] = { fffffff0, fffffff0, fffffff2, fffffff2,  }
+VBSL/VBSLQ:2:result_int32x2 [] = { fffffff0, fffffff0,  }
+VBSL/VBSLQ:3:result_int64x1 [] = { fffffffffffffffd,  }
+VBSL/VBSLQ:4:result_uint8x8 [] = { f3, f3, f3, f3, f7, f7, f7, f7,  }
+VBSL/VBSLQ:5:result_uint16x4 [] = { fff0, fff0, fff2, fff2,  }
+VBSL/VBSLQ:6:result_uint32x2 [] = { fffffff0, fffffff0,  }
+VBSL/VBSLQ:7:result_uint64x1 [] = { fffffff1,  }
+VBSL/VBSLQ:8:result_poly8x8 [] = { f3, f3, f3, f3, f7, f7, f7, f7,  }
+VBSL/VBSLQ:9:result_poly16x4 [] = { fff0, fff0, fff2, fff2,  }
+VBSL/VBSLQ:10:result_float32x2 [] = { c1800004, c1700004,  }
+VBSL/VBSLQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VBSL/VBSLQ:12:result_int8x16 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff6, fffffff6, fffffff6, fffffff6, fffffff2, fffffff2, fffffff2, fffffff2, fffffff6, fffffff6, fffffff6, fffffff6,  }
+VBSL/VBSLQ:13:result_int16x8 [] = { fffffff0, fffffff0, fffffff2, fffffff2, fffffff4, fffffff4, fffffff6, fffffff6,  }
+VBSL/VBSLQ:14:result_int32x4 [] = { fffffff0, fffffff0, fffffff2, fffffff2,  }
+VBSL/VBSLQ:15:result_int64x2 [] = { fffffffffffffffd, fffffffffffffffd,  }
+VBSL/VBSLQ:16:result_uint8x16 [] = { f3, f3, f3, f3, f7, f7, f7, f7, f3, f3, f3, f3, f7, f7, f7, f7,  }
+VBSL/VBSLQ:17:result_uint16x8 [] = { fff0, fff0, fff2, fff2, fff4, fff4, fff6, fff6,  }
+VBSL/VBSLQ:18:result_uint32x4 [] = { fffffff0, fffffff0, fffffff2, fffffff2,  }
+VBSL/VBSLQ:19:result_uint64x2 [] = { fffffff1, fffffff1,  }
+VBSL/VBSLQ:20:result_poly8x16 [] = { f3, f3, f3, f3, f7, f7, f7, f7, f3, f3, f3, f3, f7, f7, f7, f7,  }
+VBSL/VBSLQ:21:result_poly16x8 [] = { fff0, fff0, fff2, fff2, fff4, fff4, fff6, fff6,  }
+VBSL/VBSLQ:22:result_float32x4 [] = { c1800001, c1700001, c1600001, c1500001,  }
+VBSL/VBSLQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSHL/VSHLQ output:
+VSHL/VSHLQ:0:result_int8x8 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6, ffffffe8, ffffffea, ffffffec, ffffffee,  }
+VSHL/VSHLQ:1:result_int16x4 [] = { ffffff80, ffffff88, ffffff90, ffffff98,  }
+VSHL/VSHLQ:2:result_int32x2 [] = { fffff000, fffff100,  }
+VSHL/VSHLQ:3:result_int64x1 [] = { ffffffffffffff80,  }
+VSHL/VSHLQ:4:result_uint8x8 [] = { e0, e2, e4, e6, e8, ea, ec, ee,  }
+VSHL/VSHLQ:5:result_uint16x4 [] = { ff80, ff88, ff90, ff98,  }
+VSHL/VSHLQ:6:result_uint32x2 [] = { fffff000, fffff100,  }
+VSHL/VSHLQ:7:result_uint64x1 [] = { ffffffffffffff80,  }
+VSHL/VSHLQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHL/VSHLQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHL/VSHLQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSHL/VSHLQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSHL/VSHLQ:12:result_int8x16 [] = { 0, 20, 40, 60, ffffff80, ffffffa0, ffffffc0, ffffffe0, 0, 20, 40, 60, ffffff80, ffffffa0, ffffffc0, ffffffe0,  }
+VSHL/VSHLQ:13:result_int16x8 [] = { 0, 1000, 2000, 3000, 4000, 5000, 6000, 7000,  }
+VSHL/VSHLQ:14:result_int32x4 [] = { 0, 40000000, 80000000, c0000000,  }
+VSHL/VSHLQ:15:result_int64x2 [] = { 0, 8000000000000000,  }
+VSHL/VSHLQ:16:result_uint8x16 [] = { 0, 20, 40, 60, 80, a0, c0, e0, 0, 20, 40, 60, 80, a0, c0, e0,  }
+VSHL/VSHLQ:17:result_uint16x8 [] = { 0, 1000, 2000, 3000, 4000, 5000, 6000, 7000,  }
+VSHL/VSHLQ:18:result_uint32x4 [] = { 0, 40000000, 80000000, c0000000,  }
+VSHL/VSHLQ:19:result_uint64x2 [] = { 0, 8000000000000000,  }
+VSHL/VSHLQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHL/VSHLQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHL/VSHLQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSHL/VSHLQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSHL/VSHLQ (large shift amount) output:
+VSHL/VSHLQ:24:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VSHL/VSHLQ:25:result_int16x4 [] = { 0, 0, 0, 0,  }
+VSHL/VSHLQ:26:result_int32x2 [] = { 0, 0,  }
+VSHL/VSHLQ:27:result_int64x1 [] = { 0,  }
+VSHL/VSHLQ:28:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VSHL/VSHLQ:29:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VSHL/VSHLQ:30:result_uint32x2 [] = { 0, 0,  }
+VSHL/VSHLQ:31:result_uint64x1 [] = { 0,  }
+VSHL/VSHLQ:32:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHL/VSHLQ:33:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHL/VSHLQ:34:result_float32x2 [] = { 33333333, 33333333,  }
+VSHL/VSHLQ:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSHL/VSHLQ:36:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VSHL/VSHLQ:37:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VSHL/VSHLQ:38:result_int32x4 [] = { 0, 0, 0, 0,  }
+VSHL/VSHLQ:39:result_int64x2 [] = { 0, 0,  }
+VSHL/VSHLQ:40:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VSHL/VSHLQ:41:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VSHL/VSHLQ:42:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VSHL/VSHLQ:43:result_uint64x2 [] = { 0, 0,  }
+VSHL/VSHLQ:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHL/VSHLQ:45:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHL/VSHLQ:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSHL/VSHLQ:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSHL/VSHLQ (negative shift amount) output:
+VSHL/VSHLQ:48:result_int8x8 [] = { fffffff8, fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb,  }
+VSHL/VSHLQ:49:result_int16x4 [] = { fffffff8, fffffff8, fffffff9, fffffff9,  }
+VSHL/VSHLQ:50:result_int32x2 [] = { fffffffc, fffffffc,  }
+VSHL/VSHLQ:51:result_int64x1 [] = { ffffffffffffffff,  }
+VSHL/VSHLQ:52:result_uint8x8 [] = { 78, 78, 79, 79, 7a, 7a, 7b, 7b,  }
+VSHL/VSHLQ:53:result_uint16x4 [] = { 7ff8, 7ff8, 7ff9, 7ff9,  }
+VSHL/VSHLQ:54:result_uint32x2 [] = { 3ffffffc, 3ffffffc,  }
+VSHL/VSHLQ:55:result_uint64x1 [] = { fffffffffffffff,  }
+VSHL/VSHLQ:56:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHL/VSHLQ:57:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHL/VSHLQ:58:result_float32x2 [] = { 33333333, 33333333,  }
+VSHL/VSHLQ:59:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSHL/VSHLQ:60:result_int8x16 [] = { fffffffc, fffffffc, fffffffc, fffffffc, fffffffd, fffffffd, fffffffd, fffffffd, fffffffe, fffffffe, fffffffe, fffffffe, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VSHL/VSHLQ:61:result_int16x8 [] = { ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VSHL/VSHLQ:62:result_int32x4 [] = { fffffffe, fffffffe, fffffffe, fffffffe,  }
+VSHL/VSHLQ:63:result_int64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VSHL/VSHLQ:64:result_uint8x16 [] = { 3c, 3c, 3c, 3c, 3d, 3d, 3d, 3d, 3e, 3e, 3e, 3e, 3f, 3f, 3f, 3f,  }
+VSHL/VSHLQ:65:result_uint16x8 [] = { 7ff, 7ff, 7ff, 7ff, 7ff, 7ff, 7ff, 7ff,  }
+VSHL/VSHLQ:66:result_uint32x4 [] = { 1ffffffe, 1ffffffe, 1ffffffe, 1ffffffe,  }
+VSHL/VSHLQ:67:result_uint64x2 [] = { 7ffffffffffffff, 7ffffffffffffff,  }
+VSHL/VSHLQ:68:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHL/VSHLQ:69:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHL/VSHLQ:70:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSHL/VSHLQ:71:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSHL_N output:
+VSHL_N:0:result_int8x8 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6, ffffffe8, ffffffea, ffffffec, ffffffee,  }
+VSHL_N:1:result_int16x4 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6,  }
+VSHL_N:2:result_int32x2 [] = { ffffff80, ffffff88,  }
+VSHL_N:3:result_int64x1 [] = { ffffffffffffffc0,  }
+VSHL_N:4:result_uint8x8 [] = { c0, c4, c8, cc, d0, d4, d8, dc,  }
+VSHL_N:5:result_uint16x4 [] = { ff00, ff10, ff20, ff30,  }
+VSHL_N:6:result_uint32x2 [] = { ffffff80, ffffff88,  }
+VSHL_N:7:result_uint64x1 [] = { ffffffffffffffe0,  }
+VSHL_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHL_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHL_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSHL_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSHL_N:12:result_int8x16 [] = { 0, 20, 40, 60, ffffff80, ffffffa0, ffffffc0, ffffffe0, 0, 20, 40, 60, ffffff80, ffffffa0, ffffffc0, ffffffe0,  }
+VSHL_N:13:result_int16x8 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6, ffffffe8, ffffffea, ffffffec, ffffffee,  }
+VSHL_N:14:result_int32x4 [] = { ffffffc0, ffffffc4, ffffffc8, ffffffcc,  }
+VSHL_N:15:result_int64x2 [] = { ffffffffffffffc0, ffffffffffffffc4,  }
+VSHL_N:16:result_uint8x16 [] = { c0, c4, c8, cc, d0, d4, d8, dc, e0, e4, e8, ec, f0, f4, f8, fc,  }
+VSHL_N:17:result_uint16x8 [] = { ff80, ff88, ff90, ff98, ffa0, ffa8, ffb0, ffb8,  }
+VSHL_N:18:result_uint32x4 [] = { ffffffc0, ffffffc4, ffffffc8, ffffffcc,  }
+VSHL_N:19:result_uint64x2 [] = { ffffffffffffffe0, ffffffffffffffe2,  }
+VSHL_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHL_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHL_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSHL_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHL/VQSHLQ (with input = 0) cumulative saturation output:
+VQSHL/VQSHLQ:0:vqshl_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:1:vqshl_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:2:vqshl_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:3:vqshl_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:4:vqshl_u8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:5:vqshl_u16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:6:vqshl_u32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:7:vqshl_u64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:8:vqshlq_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:9:vqshlq_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:10:vqshlq_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:11:vqshlq_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:12:vqshlq_u8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:13:vqshlq_u16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:14:vqshlq_u32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:15:vqshlq_u64 Neon cumulative saturation 0
+
+VQSHL/VQSHLQ (with input = 0) output:
+VQSHL/VQSHLQ:16:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:17:result_int16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:18:result_int32x2 [] = { 0, 0,  }
+VQSHL/VQSHLQ:19:result_int64x1 [] = { 0,  }
+VQSHL/VQSHLQ:20:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:21:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:22:result_uint32x2 [] = { 0, 0,  }
+VQSHL/VQSHLQ:23:result_uint64x1 [] = { 0,  }
+VQSHL/VQSHLQ:24:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:25:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:26:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL/VQSHLQ:27:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:28:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:29:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:30:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:31:result_int64x2 [] = { 0, 0,  }
+VQSHL/VQSHLQ:32:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:33:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:34:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:35:result_uint64x2 [] = { 0, 0,  }
+VQSHL/VQSHLQ:36:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:37:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:38:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHL/VQSHLQ:39:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHL/VQSHLQ (input 0 and negative shift amount) cumulative saturation output:
+VQSHL/VQSHLQ:40:vqshl_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:41:vqshl_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:42:vqshl_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:43:vqshl_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:44:vqshl_u8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:45:vqshl_u16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:46:vqshl_u32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:47:vqshl_u64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:48:vqshlq_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:49:vqshlq_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:50:vqshlq_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:51:vqshlq_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:52:vqshlq_u8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:53:vqshlq_u16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:54:vqshlq_u32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:55:vqshlq_u64 Neon cumulative saturation 0
+
+VQSHL/VQSHLQ (input 0 and negative shift amount) output:
+VQSHL/VQSHLQ:56:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:57:result_int16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:58:result_int32x2 [] = { 0, 0,  }
+VQSHL/VQSHLQ:59:result_int64x1 [] = { 0,  }
+VQSHL/VQSHLQ:60:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:61:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:62:result_uint32x2 [] = { 0, 0,  }
+VQSHL/VQSHLQ:63:result_uint64x1 [] = { 0,  }
+VQSHL/VQSHLQ:64:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:65:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:66:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL/VQSHLQ:67:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:68:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:69:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:70:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:71:result_int64x2 [] = { 0, 0,  }
+VQSHL/VQSHLQ:72:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:73:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:74:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:75:result_uint64x2 [] = { 0, 0,  }
+VQSHL/VQSHLQ:76:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:77:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:78:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHL/VQSHLQ:79:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHL/VQSHLQ cumulative saturation output:
+VQSHL/VQSHLQ:80:vqshl_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:81:vqshl_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:82:vqshl_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:83:vqshl_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:84:vqshl_u8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:85:vqshl_u16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:86:vqshl_u32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:87:vqshl_u64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:88:vqshlq_s8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:89:vqshlq_s16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:90:vqshlq_s32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:91:vqshlq_s64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:92:vqshlq_u8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:93:vqshlq_u16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:94:vqshlq_u32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:95:vqshlq_u64 Neon cumulative saturation 1
+
+VQSHL/VQSHLQ output:
+VQSHL/VQSHLQ:96:result_int8x8 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6, ffffffe8, ffffffea, ffffffec, ffffffee,  }
+VQSHL/VQSHLQ:97:result_int16x4 [] = { ffffff80, ffffff88, ffffff90, ffffff98,  }
+VQSHL/VQSHLQ:98:result_int32x2 [] = { fffff000, fffff100,  }
+VQSHL/VQSHLQ:99:result_int64x1 [] = { fffffffffffffffe,  }
+VQSHL/VQSHLQ:100:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL/VQSHLQ:101:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHL/VQSHLQ:102:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:103:result_uint64x1 [] = { 1ffffffffffffffe,  }
+VQSHL/VQSHLQ:104:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:105:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:106:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL/VQSHLQ:107:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:108:result_int8x16 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQSHL/VQSHLQ:109:result_int16x8 [] = { ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQSHL/VQSHLQ:110:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VQSHL/VQSHLQ:111:result_int64x2 [] = { 8000000000000000, 8000000000000000,  }
+VQSHL/VQSHLQ:112:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL/VQSHLQ:113:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQSHL/VQSHLQ:114:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:115:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQSHL/VQSHLQ:116:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:117:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:118:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHL/VQSHLQ:119:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHL/VQSHLQ (negative shift amount) cumulative saturation output:
+VQSHL/VQSHLQ:120:vqshl_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:121:vqshl_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:122:vqshl_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:123:vqshl_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:124:vqshl_u8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:125:vqshl_u16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:126:vqshl_u32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:127:vqshl_u64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:128:vqshlq_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:129:vqshlq_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:130:vqshlq_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:131:vqshlq_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:132:vqshlq_u8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:133:vqshlq_u16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:134:vqshlq_u32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:135:vqshlq_u64 Neon cumulative saturation 0
+
+VQSHL/VQSHLQ (negative shift amount) output:
+VQSHL/VQSHLQ:136:result_int8x8 [] = { fffffff8, fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb,  }
+VQSHL/VQSHLQ:137:result_int16x4 [] = { fffffffc, fffffffc, fffffffc, fffffffc,  }
+VQSHL/VQSHLQ:138:result_int32x2 [] = { fffffffe, fffffffe,  }
+VQSHL/VQSHLQ:139:result_int64x1 [] = { ffffffffffffffff,  }
+VQSHL/VQSHLQ:140:result_uint8x8 [] = { 78, 78, 79, 79, 7a, 7a, 7b, 7b,  }
+VQSHL/VQSHLQ:141:result_uint16x4 [] = { 3ffc, 3ffc, 3ffc, 3ffc,  }
+VQSHL/VQSHLQ:142:result_uint32x2 [] = { 1ffffffe, 1ffffffe,  }
+VQSHL/VQSHLQ:143:result_uint64x1 [] = { fffffffffffffff,  }
+VQSHL/VQSHLQ:144:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:145:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:146:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL/VQSHLQ:147:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:148:result_int8x16 [] = { ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:149:result_int16x8 [] = { ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:150:result_int32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:151:result_int64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQSHL/VQSHLQ:152:result_uint8x16 [] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  }
+VQSHL/VQSHLQ:153:result_uint16x8 [] = { 1f, 1f, 1f, 1f, 1f, 1f, 1f, 1f,  }
+VQSHL/VQSHLQ:154:result_uint32x4 [] = { 7ffff, 7ffff, 7ffff, 7ffff,  }
+VQSHL/VQSHLQ:155:result_uint64x2 [] = { fffffffffff, fffffffffff,  }
+VQSHL/VQSHLQ:156:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:157:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:158:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHL/VQSHLQ:159:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHL/VQSHLQ (large shift amount, negative input) cumulative saturation output:
+VQSHL/VQSHLQ:160:vqshl_s8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:161:vqshl_s16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:162:vqshl_s32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:163:vqshl_s64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:164:vqshl_u8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:165:vqshl_u16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:166:vqshl_u32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:167:vqshl_u64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:168:vqshlq_s8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:169:vqshlq_s16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:170:vqshlq_s32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:171:vqshlq_s64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:172:vqshlq_u8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:173:vqshlq_u16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:174:vqshlq_u32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:175:vqshlq_u64 Neon cumulative saturation 1
+
+VQSHL/VQSHLQ (large shift amount, negative input) output:
+VQSHL/VQSHLQ:176:result_int8x8 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQSHL/VQSHLQ:177:result_int16x4 [] = { ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQSHL/VQSHLQ:178:result_int32x2 [] = { 80000000, 80000000,  }
+VQSHL/VQSHLQ:179:result_int64x1 [] = { 8000000000000000,  }
+VQSHL/VQSHLQ:180:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL/VQSHLQ:181:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHL/VQSHLQ:182:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:183:result_uint64x1 [] = { ffffffffffffffff,  }
+VQSHL/VQSHLQ:184:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:185:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:186:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL/VQSHLQ:187:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:188:result_int8x16 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQSHL/VQSHLQ:189:result_int16x8 [] = { ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQSHL/VQSHLQ:190:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VQSHL/VQSHLQ:191:result_int64x2 [] = { 8000000000000000, 8000000000000000,  }
+VQSHL/VQSHLQ:192:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL/VQSHLQ:193:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQSHL/VQSHLQ:194:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:195:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQSHL/VQSHLQ:196:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:197:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:198:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHL/VQSHLQ:199:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHL/VQSHLQ (check cumulative saturation) cumulative saturation output:
+VQSHL/VQSHLQ:200:vqshl_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:201:vqshl_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:202:vqshl_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:203:vqshl_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:204:vqshl_u8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:205:vqshl_u16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:206:vqshl_u32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:207:vqshl_u64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:208:vqshlq_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:209:vqshlq_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:210:vqshlq_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:211:vqshlq_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:212:vqshlq_u8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:213:vqshlq_u16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:214:vqshlq_u32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:215:vqshlq_u64 Neon cumulative saturation 0
+
+VQSHL/VQSHLQ (check cumulative saturation) output:
+VQSHL/VQSHLQ:216:result_int8x8 [] = { 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f,  }
+VQSHL/VQSHLQ:217:result_int16x4 [] = { 3fff, 3fff, 3fff, 3fff,  }
+VQSHL/VQSHLQ:218:result_int32x2 [] = { 3fffffff, 3fffffff,  }
+VQSHL/VQSHLQ:219:result_int64x1 [] = { 3fffffffffffffff,  }
+VQSHL/VQSHLQ:220:result_uint8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHL/VQSHLQ:221:result_uint16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQSHL/VQSHLQ:222:result_uint32x2 [] = { 7fffffff, 7fffffff,  }
+VQSHL/VQSHLQ:223:result_uint64x1 [] = { 7fffffffffffffff,  }
+VQSHL/VQSHLQ:224:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:225:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:226:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL/VQSHLQ:227:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:228:result_int8x16 [] = { 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f,  }
+VQSHL/VQSHLQ:229:result_int16x8 [] = { 3fff, 3fff, 3fff, 3fff, 3fff, 3fff, 3fff, 3fff,  }
+VQSHL/VQSHLQ:230:result_int32x4 [] = { 3fffffff, 3fffffff, 3fffffff, 3fffffff,  }
+VQSHL/VQSHLQ:231:result_int64x2 [] = { 3fffffffffffffff, 3fffffffffffffff,  }
+VQSHL/VQSHLQ:232:result_uint8x16 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHL/VQSHLQ:233:result_uint16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQSHL/VQSHLQ:234:result_uint32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQSHL/VQSHLQ:235:result_uint64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+VQSHL/VQSHLQ:236:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:237:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:238:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHL/VQSHLQ:239:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHL/VQSHLQ (large shift amount, positive input) cumulative saturation output:
+VQSHL/VQSHLQ:240:vqshl_s8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:241:vqshl_s16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:242:vqshl_s32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:243:vqshl_s64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:244:vqshl_u8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:245:vqshl_u16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:246:vqshl_u32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:247:vqshl_u64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:248:vqshlq_s8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:249:vqshlq_s16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:250:vqshlq_s32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:251:vqshlq_s64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:252:vqshlq_u8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:253:vqshlq_u16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:254:vqshlq_u32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:255:vqshlq_u64 Neon cumulative saturation 1
+
+VQSHL/VQSHLQ (large shift amount, positive input) output:
+VQSHL/VQSHLQ:256:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHL/VQSHLQ:257:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQSHL/VQSHLQ:258:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQSHL/VQSHLQ:259:result_int64x1 [] = { 7fffffffffffffff,  }
+VQSHL/VQSHLQ:260:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL/VQSHLQ:261:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHL/VQSHLQ:262:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:263:result_uint64x1 [] = { ffffffffffffffff,  }
+VQSHL/VQSHLQ:264:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:265:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:266:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL/VQSHLQ:267:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:268:result_int8x16 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHL/VQSHLQ:269:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQSHL/VQSHLQ:270:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQSHL/VQSHLQ:271:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+VQSHL/VQSHLQ:272:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL/VQSHLQ:273:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQSHL/VQSHLQ:274:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:275:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQSHL/VQSHLQ:276:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:277:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:278:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHL/VQSHLQ:279:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHL/VQSHLQ (check saturation on 64 bits) cumulative saturation output:
+VQSHL/VQSHLQ:280:vqshl_s8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:281:vqshl_s16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:282:vqshl_s32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:283:vqshl_s64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:284:vqshl_u8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:285:vqshl_u16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:286:vqshl_u32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:287:vqshl_u64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:288:vqshlq_s8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:289:vqshlq_s16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:290:vqshlq_s32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:291:vqshlq_s64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:292:vqshlq_u8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:293:vqshlq_u16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:294:vqshlq_u32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:295:vqshlq_u64 Neon cumulative saturation 1
+
+VQSHL/VQSHLQ (check saturation on 64 bits) output:
+VQSHL/VQSHLQ:296:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHL/VQSHLQ:297:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQSHL/VQSHLQ:298:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQSHL/VQSHLQ:299:result_int64x1 [] = { 8000000000000000,  }
+VQSHL/VQSHLQ:300:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL/VQSHLQ:301:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHL/VQSHLQ:302:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:303:result_uint64x1 [] = { ffffffffffffffff,  }
+VQSHL/VQSHLQ:304:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:305:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:306:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL/VQSHLQ:307:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:308:result_int8x16 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHL/VQSHLQ:309:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQSHL/VQSHLQ:310:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQSHL/VQSHLQ:311:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+VQSHL/VQSHLQ:312:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL/VQSHLQ:313:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQSHL/VQSHLQ:314:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:315:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQSHL/VQSHLQ:316:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:317:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:318:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHL/VQSHLQ:319:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHL_N/VQSHLQ_N cumulative saturation output:
+VQSHL_N/VQSHLQ_N:0:vqshl_n_s8 Neon cumulative saturation 0
+VQSHL_N/VQSHLQ_N:1:vqshl_n_s16 Neon cumulative saturation 0
+VQSHL_N/VQSHLQ_N:2:vqshl_n_s32 Neon cumulative saturation 0
+VQSHL_N/VQSHLQ_N:3:vqshl_n_s64 Neon cumulative saturation 0
+VQSHL_N/VQSHLQ_N:4:vqshl_n_u8 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:5:vqshl_n_u16 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:6:vqshl_n_u32 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:7:vqshl_n_u64 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:8:vqshlq_n_s8 Neon cumulative saturation 0
+VQSHL_N/VQSHLQ_N:9:vqshlq_n_s16 Neon cumulative saturation 0
+VQSHL_N/VQSHLQ_N:10:vqshlq_n_s32 Neon cumulative saturation 0
+VQSHL_N/VQSHLQ_N:11:vqshlq_n_s64 Neon cumulative saturation 0
+VQSHL_N/VQSHLQ_N:12:vqshlq_n_u8 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:13:vqshlq_n_u16 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:14:vqshlq_n_u32 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:15:vqshlq_n_u64 Neon cumulative saturation 1
+
+VQSHL_N/VQSHLQ_N output:
+VQSHL_N/VQSHLQ_N:16:result_int8x8 [] = { ffffffc0, ffffffc4, ffffffc8, ffffffcc, ffffffd0, ffffffd4, ffffffd8, ffffffdc,  }
+VQSHL_N/VQSHLQ_N:17:result_int16x4 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6,  }
+VQSHL_N/VQSHLQ_N:18:result_int32x2 [] = { ffffffe0, ffffffe2,  }
+VQSHL_N/VQSHLQ_N:19:result_int64x1 [] = { ffffffffffffffc0,  }
+VQSHL_N/VQSHLQ_N:20:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL_N/VQSHLQ_N:21:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHL_N/VQSHLQ_N:22:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHL_N/VQSHLQ_N:23:result_uint64x1 [] = { ffffffffffffffff,  }
+VQSHL_N/VQSHLQ_N:24:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL_N/VQSHLQ_N:25:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL_N/VQSHLQ_N:26:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL_N/VQSHLQ_N:27:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHL_N/VQSHLQ_N:28:result_int8x16 [] = { ffffffc0, ffffffc4, ffffffc8, ffffffcc, ffffffd0, ffffffd4, ffffffd8, ffffffdc, ffffffe0, ffffffe4, ffffffe8, ffffffec, fffffff0, fffffff4, fffffff8, fffffffc,  }
+VQSHL_N/VQSHLQ_N:29:result_int16x8 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6, ffffffe8, ffffffea, ffffffec, ffffffee,  }
+VQSHL_N/VQSHLQ_N:30:result_int32x4 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6,  }
+VQSHL_N/VQSHLQ_N:31:result_int64x2 [] = { ffffffffffffffc0, ffffffffffffffc4,  }
+VQSHL_N/VQSHLQ_N:32:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL_N/VQSHLQ_N:33:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQSHL_N/VQSHLQ_N:34:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL_N/VQSHLQ_N:35:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQSHL_N/VQSHLQ_N:36:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL_N/VQSHLQ_N:37:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL_N/VQSHLQ_N:38:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHL_N/VQSHLQ_N:39:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHL_N/VQSHLQ_N (check saturation with large positive input) cumulative saturation output:
+VQSHL_N/VQSHLQ_N:40:vqshl_n_s8 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:41:vqshl_n_s16 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:42:vqshl_n_s32 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:43:vqshl_n_s64 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:44:vqshl_n_u8 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:45:vqshl_n_u16 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:46:vqshl_n_u32 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:47:vqshl_n_u64 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:48:vqshlq_n_s8 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:49:vqshlq_n_s16 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:50:vqshlq_n_s32 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:51:vqshlq_n_s64 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:52:vqshlq_n_u8 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:53:vqshlq_n_u16 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:54:vqshlq_n_u32 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:55:vqshlq_n_u64 Neon cumulative saturation 1
+
+VQSHL_N/VQSHLQ_N (check saturation with large positive input) output:
+VQSHL_N/VQSHLQ_N:56:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHL_N/VQSHLQ_N:57:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQSHL_N/VQSHLQ_N:58:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQSHL_N/VQSHLQ_N:59:result_int64x1 [] = { 7fffffffffffffff,  }
+VQSHL_N/VQSHLQ_N:60:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL_N/VQSHLQ_N:61:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHL_N/VQSHLQ_N:62:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHL_N/VQSHLQ_N:63:result_uint64x1 [] = { ffffffffffffffff,  }
+VQSHL_N/VQSHLQ_N:64:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL_N/VQSHLQ_N:65:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL_N/VQSHLQ_N:66:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL_N/VQSHLQ_N:67:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHL_N/VQSHLQ_N:68:result_int8x16 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHL_N/VQSHLQ_N:69:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQSHL_N/VQSHLQ_N:70:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQSHL_N/VQSHLQ_N:71:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+VQSHL_N/VQSHLQ_N:72:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL_N/VQSHLQ_N:73:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQSHL_N/VQSHLQ_N:74:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL_N/VQSHLQ_N:75:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQSHL_N/VQSHLQ_N:76:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL_N/VQSHLQ_N:77:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL_N/VQSHLQ_N:78:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHL_N/VQSHLQ_N:79:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHL/VRSHLQ (with input = 0) output:
+VRSHL/VRSHLQ:0:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:1:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:2:result_int32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:3:result_int64x1 [] = { 0,  }
+VRSHL/VRSHLQ:4:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:5:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:6:result_uint32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:7:result_uint64x1 [] = { 0,  }
+VRSHL/VRSHLQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:12:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:13:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:14:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:15:result_int64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:16:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:17:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:18:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:19:result_uint64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHL/VRSHLQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHL/VRSHLQ (input 0 and negative shift amount) output:
+VRSHL/VRSHLQ:24:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:25:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:26:result_int32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:27:result_int64x1 [] = { 0,  }
+VRSHL/VRSHLQ:28:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:29:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:30:result_uint32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:31:result_uint64x1 [] = { 0,  }
+VRSHL/VRSHLQ:32:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:33:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:34:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:36:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:37:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:38:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:39:result_int64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:40:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:41:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:42:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:43:result_uint64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:45:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHL/VRSHLQ:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHL/VRSHLQ output:
+VRSHL/VRSHLQ:48:result_int8x8 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6, ffffffe8, ffffffea, ffffffec, ffffffee,  }
+VRSHL/VRSHLQ:49:result_int16x4 [] = { ffffff80, ffffff88, ffffff90, ffffff98,  }
+VRSHL/VRSHLQ:50:result_int32x2 [] = { fffff000, fffff100,  }
+VRSHL/VRSHLQ:51:result_int64x1 [] = { fffffffffffffffe,  }
+VRSHL/VRSHLQ:52:result_uint8x8 [] = { e0, e2, e4, e6, e8, ea, ec, ee,  }
+VRSHL/VRSHLQ:53:result_uint16x4 [] = { ff80, ff88, ff90, ff98,  }
+VRSHL/VRSHLQ:54:result_uint32x2 [] = { fffff000, fffff100,  }
+VRSHL/VRSHLQ:55:result_uint64x1 [] = { 1ffffffffffffffe,  }
+VRSHL/VRSHLQ:56:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:57:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:58:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:59:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:60:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:61:result_int16x8 [] = { 0, 1000, 2000, 3000, 4000, 5000, 6000, 7000,  }
+VRSHL/VRSHLQ:62:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:63:result_int64x2 [] = { 0, 8000000000000000,  }
+VRSHL/VRSHLQ:64:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:65:result_uint16x8 [] = { 0, 1000, 2000, 3000, 4000, 5000, 6000, 7000,  }
+VRSHL/VRSHLQ:66:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:67:result_uint64x2 [] = { 0, 8000000000000000,  }
+VRSHL/VRSHLQ:68:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:69:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:70:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHL/VRSHLQ:71:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHL/VRSHLQ (negative shift amount) output:
+VRSHL/VRSHLQ:72:result_int8x8 [] = { fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb, fffffffc,  }
+VRSHL/VRSHLQ:73:result_int16x4 [] = { fffffffc, fffffffc, fffffffd, fffffffd,  }
+VRSHL/VRSHLQ:74:result_int32x2 [] = { fffffffe, fffffffe,  }
+VRSHL/VRSHLQ:75:result_int64x1 [] = { ffffffffffffffff,  }
+VRSHL/VRSHLQ:76:result_uint8x8 [] = { 78, 79, 79, 7a, 7a, 7b, 7b, 7c,  }
+VRSHL/VRSHLQ:77:result_uint16x4 [] = { 3ffc, 3ffc, 3ffd, 3ffd,  }
+VRSHL/VRSHLQ:78:result_uint32x2 [] = { 1ffffffe, 1ffffffe,  }
+VRSHL/VRSHLQ:79:result_uint64x1 [] = { fffffffffffffff,  }
+VRSHL/VRSHLQ:80:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:81:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:82:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:83:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:84:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:85:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:86:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:87:result_int64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:88:result_uint8x16 [] = { 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,  }
+VRSHL/VRSHLQ:89:result_uint16x8 [] = { 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSHL/VRSHLQ:90:result_uint32x4 [] = { 80000, 80000, 80000, 80000,  }
+VRSHL/VRSHLQ:91:result_uint64x2 [] = { 100000000000, 100000000000,  }
+VRSHL/VRSHLQ:92:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:93:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:94:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHL/VRSHLQ:95:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHL/VRSHLQ (checking round_const overflow: shift by -1) output:
+VRSHL/VRSHLQ:96:result_int8x8 [] = { 40, 40, 40, 40, 40, 40, 40, 40,  }
+VRSHL/VRSHLQ:97:result_int16x4 [] = { 4000, 4000, 4000, 4000,  }
+VRSHL/VRSHLQ:98:result_int32x2 [] = { 40000000, 40000000,  }
+VRSHL/VRSHLQ:99:result_int64x1 [] = { 4000000000000000,  }
+VRSHL/VRSHLQ:100:result_uint8x8 [] = { 80, 80, 80, 80, 80, 80, 80, 80,  }
+VRSHL/VRSHLQ:101:result_uint16x4 [] = { 8000, 8000, 8000, 8000,  }
+VRSHL/VRSHLQ:102:result_uint32x2 [] = { 80000000, 80000000,  }
+VRSHL/VRSHLQ:103:result_uint64x1 [] = { 8000000000000000,  }
+VRSHL/VRSHLQ:104:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:105:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:106:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:107:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:108:result_int8x16 [] = { 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40,  }
+VRSHL/VRSHLQ:109:result_int16x8 [] = { 4000, 4000, 4000, 4000, 4000, 4000, 4000, 4000,  }
+VRSHL/VRSHLQ:110:result_int32x4 [] = { 40000000, 40000000, 40000000, 40000000,  }
+VRSHL/VRSHLQ:111:result_int64x2 [] = { 4000000000000000, 4000000000000000,  }
+VRSHL/VRSHLQ:112:result_uint8x16 [] = { 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80,  }
+VRSHL/VRSHLQ:113:result_uint16x8 [] = { 8000, 8000, 8000, 8000, 8000, 8000, 8000, 8000,  }
+VRSHL/VRSHLQ:114:result_uint32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VRSHL/VRSHLQ:115:result_uint64x2 [] = { 8000000000000000, 8000000000000000,  }
+VRSHL/VRSHLQ:116:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:117:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:118:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHL/VRSHLQ:119:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHL/VRSHLQ (checking round_const overflow: shift by -3) output:
+VRSHL/VRSHLQ:120:result_int8x8 [] = { 10, 10, 10, 10, 10, 10, 10, 10,  }
+VRSHL/VRSHLQ:121:result_int16x4 [] = { 1000, 1000, 1000, 1000,  }
+VRSHL/VRSHLQ:122:result_int32x2 [] = { 10000000, 10000000,  }
+VRSHL/VRSHLQ:123:result_int64x1 [] = { 1000000000000000,  }
+VRSHL/VRSHLQ:124:result_uint8x8 [] = { 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSHL/VRSHLQ:125:result_uint16x4 [] = { 2000, 2000, 2000, 2000,  }
+VRSHL/VRSHLQ:126:result_uint32x2 [] = { 20000000, 20000000,  }
+VRSHL/VRSHLQ:127:result_uint64x1 [] = { 2000000000000000,  }
+VRSHL/VRSHLQ:128:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:129:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:130:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:131:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:132:result_int8x16 [] = { 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10,  }
+VRSHL/VRSHLQ:133:result_int16x8 [] = { 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000,  }
+VRSHL/VRSHLQ:134:result_int32x4 [] = { 10000000, 10000000, 10000000, 10000000,  }
+VRSHL/VRSHLQ:135:result_int64x2 [] = { 1000000000000000, 1000000000000000,  }
+VRSHL/VRSHLQ:136:result_uint8x16 [] = { 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSHL/VRSHLQ:137:result_uint16x8 [] = { 2000, 2000, 2000, 2000, 2000, 2000, 2000, 2000,  }
+VRSHL/VRSHLQ:138:result_uint32x4 [] = { 20000000, 20000000, 20000000, 20000000,  }
+VRSHL/VRSHLQ:139:result_uint64x2 [] = { 2000000000000000, 2000000000000000,  }
+VRSHL/VRSHLQ:140:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:141:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:142:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHL/VRSHLQ:143:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHL/VRSHLQ (checking negative shift amount as large as input vector width) output:
+VRSHL/VRSHLQ:144:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:145:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:146:result_int32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:147:result_int64x1 [] = { 0,  }
+VRSHL/VRSHLQ:148:result_uint8x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSHL/VRSHLQ:149:result_uint16x4 [] = { 1, 1, 1, 1,  }
+VRSHL/VRSHLQ:150:result_uint32x2 [] = { 1, 1,  }
+VRSHL/VRSHLQ:151:result_uint64x1 [] = { 1,  }
+VRSHL/VRSHLQ:152:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:153:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:154:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:155:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:156:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:157:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:158:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:159:result_int64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:160:result_uint8x16 [] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSHL/VRSHLQ:161:result_uint16x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSHL/VRSHLQ:162:result_uint32x4 [] = { 1, 1, 1, 1,  }
+VRSHL/VRSHLQ:163:result_uint64x2 [] = { 1, 1,  }
+VRSHL/VRSHLQ:164:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:165:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:166:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHL/VRSHLQ:167:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHL/VRSHLQ (large shift amount) output:
+VRSHL/VRSHLQ:168:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:169:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:170:result_int32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:171:result_int64x1 [] = { 0,  }
+VRSHL/VRSHLQ:172:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:173:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:174:result_uint32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:175:result_uint64x1 [] = { 0,  }
+VRSHL/VRSHLQ:176:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:177:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:178:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:179:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:180:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:181:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:182:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:183:result_int64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:184:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:185:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:186:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:187:result_uint64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:188:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:189:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:190:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHL/VRSHLQ:191:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHL/VRSHLQ (large negative shift amount) output:
+VRSHL/VRSHLQ:192:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:193:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:194:result_int32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:195:result_int64x1 [] = { 0,  }
+VRSHL/VRSHLQ:196:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:197:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:198:result_uint32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:199:result_uint64x1 [] = { 0,  }
+VRSHL/VRSHLQ:200:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:201:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:202:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:203:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:204:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:205:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:206:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:207:result_int64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:208:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:209:result_uint16x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSHL/VRSHLQ:210:result_uint32x4 [] = { 1, 1, 1, 1,  }
+VRSHL/VRSHLQ:211:result_uint64x2 [] = { 1, 1,  }
+VRSHL/VRSHLQ:212:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:213:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:214:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHL/VRSHLQ:215:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VLD2/VLD2Q chunk 0 output:
+VLD2/VLD2Q:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD2/VLD2Q:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD2/VLD2Q:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD2/VLD2Q:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD2/VLD2Q:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VLD2/VLD2Q:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD2/VLD2Q:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD2/VLD2Q:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD2/VLD2Q:8:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VLD2/VLD2Q:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD2/VLD2Q:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD2/VLD2Q:11:result_float16x4 [] = { cc00, cb80, cb00, ca80,  }
+VLD2/VLD2Q:12:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD2/VLD2Q:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD2/VLD2Q:14:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD2/VLD2Q:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2/VLD2Q:16:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD2/VLD2Q:17:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VLD2/VLD2Q:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD2/VLD2Q:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2/VLD2Q:20:result_poly8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD2/VLD2Q:21:result_poly16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VLD2/VLD2Q:22:result_float32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+VLD2/VLD2Q:23:result_float16x8 [] = { cc00, cb80, cb00, ca80, ca00, c980, c900, c880,  }
+
+VLD2/VLD2Q chunk 1 output:
+VLD2/VLD2Q:24:result_int8x8 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD2/VLD2Q:25:result_int16x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD2/VLD2Q:26:result_int32x2 [] = { fffffff2, fffffff3,  }
+VLD2/VLD2Q:27:result_int64x1 [] = { fffffffffffffff1,  }
+VLD2/VLD2Q:28:result_uint8x8 [] = { f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD2/VLD2Q:29:result_uint16x4 [] = { fff4, fff5, fff6, fff7,  }
+VLD2/VLD2Q:30:result_uint32x2 [] = { fffffff2, fffffff3,  }
+VLD2/VLD2Q:31:result_uint64x1 [] = { fffffffffffffff1,  }
+VLD2/VLD2Q:32:result_poly8x8 [] = { f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD2/VLD2Q:33:result_poly16x4 [] = { fff4, fff5, fff6, fff7,  }
+VLD2/VLD2Q:34:result_float32x2 [] = { c1600000, c1500000,  }
+VLD2/VLD2Q:35:result_float16x4 [] = { ca00, c980, c900, c880,  }
+VLD2/VLD2Q:36:result_int8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD2/VLD2Q:37:result_int16x8 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD2/VLD2Q:38:result_int32x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD2/VLD2Q:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2/VLD2Q:40:result_uint8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD2/VLD2Q:41:result_uint16x8 [] = { fff8, fff9, fffa, fffb, fffc, fffd, fffe, ffff,  }
+VLD2/VLD2Q:42:result_uint32x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD2/VLD2Q:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2/VLD2Q:44:result_poly8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD2/VLD2Q:45:result_poly16x8 [] = { fff8, fff9, fffa, fffb, fffc, fffd, fffe, ffff,  }
+VLD2/VLD2Q:46:result_float32x4 [] = { c1400000, c1300000, c1200000, c1100000,  }
+VLD2/VLD2Q:47:result_float16x8 [] = { c800, c700, c600, c500, c400, c200, c000, bc00,  }
+
+VLD3/VLD3Q chunk 0 output:
+VLD3/VLD3Q:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD3/VLD3Q:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD3/VLD3Q:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD3/VLD3Q:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD3/VLD3Q:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VLD3/VLD3Q:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD3/VLD3Q:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD3/VLD3Q:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD3/VLD3Q:8:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VLD3/VLD3Q:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD3/VLD3Q:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD3/VLD3Q:11:result_float16x4 [] = { cc00, cb80, cb00, ca80,  }
+VLD3/VLD3Q:12:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD3/VLD3Q:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD3/VLD3Q:14:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD3/VLD3Q:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3/VLD3Q:16:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD3/VLD3Q:17:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VLD3/VLD3Q:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD3/VLD3Q:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3/VLD3Q:20:result_poly8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD3/VLD3Q:21:result_poly16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VLD3/VLD3Q:22:result_float32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+VLD3/VLD3Q:23:result_float16x8 [] = { cc00, cb80, cb00, ca80, ca00, c980, c900, c880,  }
+
+VLD3/VLD3Q chunk 1 output:
+VLD3/VLD3Q:24:result_int8x8 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD3/VLD3Q:25:result_int16x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD3/VLD3Q:26:result_int32x2 [] = { fffffff2, fffffff3,  }
+VLD3/VLD3Q:27:result_int64x1 [] = { fffffffffffffff1,  }
+VLD3/VLD3Q:28:result_uint8x8 [] = { f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD3/VLD3Q:29:result_uint16x4 [] = { fff4, fff5, fff6, fff7,  }
+VLD3/VLD3Q:30:result_uint32x2 [] = { fffffff2, fffffff3,  }
+VLD3/VLD3Q:31:result_uint64x1 [] = { fffffffffffffff1,  }
+VLD3/VLD3Q:32:result_poly8x8 [] = { f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD3/VLD3Q:33:result_poly16x4 [] = { fff4, fff5, fff6, fff7,  }
+VLD3/VLD3Q:34:result_float32x2 [] = { c1600000, c1500000,  }
+VLD3/VLD3Q:35:result_float16x4 [] = { ca00, c980, c900, c880,  }
+VLD3/VLD3Q:36:result_int8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD3/VLD3Q:37:result_int16x8 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD3/VLD3Q:38:result_int32x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD3/VLD3Q:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3/VLD3Q:40:result_uint8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD3/VLD3Q:41:result_uint16x8 [] = { fff8, fff9, fffa, fffb, fffc, fffd, fffe, ffff,  }
+VLD3/VLD3Q:42:result_uint32x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD3/VLD3Q:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3/VLD3Q:44:result_poly8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD3/VLD3Q:45:result_poly16x8 [] = { fff8, fff9, fffa, fffb, fffc, fffd, fffe, ffff,  }
+VLD3/VLD3Q:46:result_float32x4 [] = { c1400000, c1300000, c1200000, c1100000,  }
+VLD3/VLD3Q:47:result_float16x8 [] = { c800, c700, c600, c500, c400, c200, c000, bc00,  }
+
+VLD3/VLD3Q chunk 2 output:
+VLD3/VLD3Q:48:result_int8x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD3/VLD3Q:49:result_int16x4 [] = { fffffff8, fffffff9, fffffffa, fffffffb,  }
+VLD3/VLD3Q:50:result_int32x2 [] = { fffffff4, fffffff5,  }
+VLD3/VLD3Q:51:result_int64x1 [] = { fffffffffffffff2,  }
+VLD3/VLD3Q:52:result_uint8x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD3/VLD3Q:53:result_uint16x4 [] = { fff8, fff9, fffa, fffb,  }
+VLD3/VLD3Q:54:result_uint32x2 [] = { fffffff4, fffffff5,  }
+VLD3/VLD3Q:55:result_uint64x1 [] = { fffffffffffffff2,  }
+VLD3/VLD3Q:56:result_poly8x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD3/VLD3Q:57:result_poly16x4 [] = { fff8, fff9, fffa, fffb,  }
+VLD3/VLD3Q:58:result_float32x2 [] = { c1400000, c1300000,  }
+VLD3/VLD3Q:59:result_float16x4 [] = { c800, c700, c600, c500,  }
+VLD3/VLD3Q:60:result_int8x16 [] = { 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 1a, 1b, 1c, 1d, 1e, 1f,  }
+VLD3/VLD3Q:61:result_int16x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD3/VLD3Q:62:result_int32x4 [] = { fffffff8, fffffff9, fffffffa, fffffffb,  }
+VLD3/VLD3Q:63:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3/VLD3Q:64:result_uint8x16 [] = { 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 1a, 1b, 1c, 1d, 1e, 1f,  }
+VLD3/VLD3Q:65:result_uint16x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD3/VLD3Q:66:result_uint32x4 [] = { fffffff8, fffffff9, fffffffa, fffffffb,  }
+VLD3/VLD3Q:67:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3/VLD3Q:68:result_poly8x16 [] = { 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 1a, 1b, 1c, 1d, 1e, 1f,  }
+VLD3/VLD3Q:69:result_poly16x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD3/VLD3Q:70:result_float32x4 [] = { c1000000, c0e00000, c0c00000, c0a00000,  }
+VLD3/VLD3Q:71:result_float16x8 [] = { 0, 3c00, 4000, 4200, 4400, 4500, 4600, 4700,  }
+
+VLD4/VLD4Q chunk 0 output:
+VLD4/VLD4Q:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD4/VLD4Q:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4/VLD4Q:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD4/VLD4Q:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD4/VLD4Q:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VLD4/VLD4Q:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4/VLD4Q:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD4/VLD4Q:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD4/VLD4Q:8:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VLD4/VLD4Q:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4/VLD4Q:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD4/VLD4Q:11:result_float16x4 [] = { cc00, cb80, cb00, ca80,  }
+VLD4/VLD4Q:12:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD4/VLD4Q:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD4/VLD4Q:14:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4/VLD4Q:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4/VLD4Q:16:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD4/VLD4Q:17:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VLD4/VLD4Q:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4/VLD4Q:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4/VLD4Q:20:result_poly8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD4/VLD4Q:21:result_poly16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VLD4/VLD4Q:22:result_float32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+VLD4/VLD4Q:23:result_float16x8 [] = { cc00, cb80, cb00, ca80, ca00, c980, c900, c880,  }
+
+VLD4/VLD4Q chunk 1 output:
+VLD4/VLD4Q:24:result_int8x8 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD4/VLD4Q:25:result_int16x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD4/VLD4Q:26:result_int32x2 [] = { fffffff2, fffffff3,  }
+VLD4/VLD4Q:27:result_int64x1 [] = { fffffffffffffff1,  }
+VLD4/VLD4Q:28:result_uint8x8 [] = { f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD4/VLD4Q:29:result_uint16x4 [] = { fff4, fff5, fff6, fff7,  }
+VLD4/VLD4Q:30:result_uint32x2 [] = { fffffff2, fffffff3,  }
+VLD4/VLD4Q:31:result_uint64x1 [] = { fffffffffffffff1,  }
+VLD4/VLD4Q:32:result_poly8x8 [] = { f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD4/VLD4Q:33:result_poly16x4 [] = { fff4, fff5, fff6, fff7,  }
+VLD4/VLD4Q:34:result_float32x2 [] = { c1600000, c1500000,  }
+VLD4/VLD4Q:35:result_float16x4 [] = { ca00, c980, c900, c880,  }
+VLD4/VLD4Q:36:result_int8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:37:result_int16x8 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD4/VLD4Q:38:result_int32x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD4/VLD4Q:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4/VLD4Q:40:result_uint8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:41:result_uint16x8 [] = { fff8, fff9, fffa, fffb, fffc, fffd, fffe, ffff,  }
+VLD4/VLD4Q:42:result_uint32x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD4/VLD4Q:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4/VLD4Q:44:result_poly8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:45:result_poly16x8 [] = { fff8, fff9, fffa, fffb, fffc, fffd, fffe, ffff,  }
+VLD4/VLD4Q:46:result_float32x4 [] = { c1400000, c1300000, c1200000, c1100000,  }
+VLD4/VLD4Q:47:result_float16x8 [] = { c800, c700, c600, c500, c400, c200, c000, bc00,  }
+
+VLD4/VLD4Q chunk 2 output:
+VLD4/VLD4Q:48:result_int8x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD4/VLD4Q:49:result_int16x4 [] = { fffffff8, fffffff9, fffffffa, fffffffb,  }
+VLD4/VLD4Q:50:result_int32x2 [] = { fffffff4, fffffff5,  }
+VLD4/VLD4Q:51:result_int64x1 [] = { fffffffffffffff2,  }
+VLD4/VLD4Q:52:result_uint8x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD4/VLD4Q:53:result_uint16x4 [] = { fff8, fff9, fffa, fffb,  }
+VLD4/VLD4Q:54:result_uint32x2 [] = { fffffff4, fffffff5,  }
+VLD4/VLD4Q:55:result_uint64x1 [] = { fffffffffffffff2,  }
+VLD4/VLD4Q:56:result_poly8x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD4/VLD4Q:57:result_poly16x4 [] = { fff8, fff9, fffa, fffb,  }
+VLD4/VLD4Q:58:result_float32x2 [] = { c1400000, c1300000,  }
+VLD4/VLD4Q:59:result_float16x4 [] = { c800, c700, c600, c500,  }
+VLD4/VLD4Q:60:result_int8x16 [] = { 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 1a, 1b, 1c, 1d, 1e, 1f,  }
+VLD4/VLD4Q:61:result_int16x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD4/VLD4Q:62:result_int32x4 [] = { fffffff8, fffffff9, fffffffa, fffffffb,  }
+VLD4/VLD4Q:63:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4/VLD4Q:64:result_uint8x16 [] = { 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 1a, 1b, 1c, 1d, 1e, 1f,  }
+VLD4/VLD4Q:65:result_uint16x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD4/VLD4Q:66:result_uint32x4 [] = { fffffff8, fffffff9, fffffffa, fffffffb,  }
+VLD4/VLD4Q:67:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4/VLD4Q:68:result_poly8x16 [] = { 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 1a, 1b, 1c, 1d, 1e, 1f,  }
+VLD4/VLD4Q:69:result_poly16x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD4/VLD4Q:70:result_float32x4 [] = { c1000000, c0e00000, c0c00000, c0a00000,  }
+VLD4/VLD4Q:71:result_float16x8 [] = { 0, 3c00, 4000, 4200, 4400, 4500, 4600, 4700,  }
+
+VLD4/VLD4Q chunk 3 output:
+VLD4/VLD4Q:72:result_int8x8 [] = { 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:73:result_int16x4 [] = { fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD4/VLD4Q:74:result_int32x2 [] = { fffffff6, fffffff7,  }
+VLD4/VLD4Q:75:result_int64x1 [] = { fffffffffffffff3,  }
+VLD4/VLD4Q:76:result_uint8x8 [] = { 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:77:result_uint16x4 [] = { fffc, fffd, fffe, ffff,  }
+VLD4/VLD4Q:78:result_uint32x2 [] = { fffffff6, fffffff7,  }
+VLD4/VLD4Q:79:result_uint64x1 [] = { fffffffffffffff3,  }
+VLD4/VLD4Q:80:result_poly8x8 [] = { 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:81:result_poly16x4 [] = { fffc, fffd, fffe, ffff,  }
+VLD4/VLD4Q:82:result_float32x2 [] = { c1200000, c1100000,  }
+VLD4/VLD4Q:83:result_float16x4 [] = { c400, c200, c000, bc00,  }
+VLD4/VLD4Q:84:result_int8x16 [] = { 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 2a, 2b, 2c, 2d, 2e, 2f,  }
+VLD4/VLD4Q:85:result_int16x8 [] = { 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:86:result_int32x4 [] = { fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD4/VLD4Q:87:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4/VLD4Q:88:result_uint8x16 [] = { 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 2a, 2b, 2c, 2d, 2e, 2f,  }
+VLD4/VLD4Q:89:result_uint16x8 [] = { 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:90:result_uint32x4 [] = { fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD4/VLD4Q:91:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4/VLD4Q:92:result_poly8x16 [] = { 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 2a, 2b, 2c, 2d, 2e, 2f,  }
+VLD4/VLD4Q:93:result_poly16x8 [] = { 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:94:result_float32x4 [] = { c0800000, c0400000, c0000000, bf800000,  }
+VLD4/VLD4Q:95:result_float16x8 [] = { 4800, 4880, 4900, 4980, 4a00, 4a80, 4b00, 4b80,  }
+
+VDUP_LANE/VDUP_LANEQ output:
+VDUP_LANE/VDUP_LANEQ:0:result_int8x8 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VDUP_LANE/VDUP_LANEQ:1:result_int16x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VDUP_LANE/VDUP_LANEQ:2:result_int32x2 [] = { fffffff1, fffffff1,  }
+VDUP_LANE/VDUP_LANEQ:3:result_int64x1 [] = { fffffffffffffff0,  }
+VDUP_LANE/VDUP_LANEQ:4:result_uint8x8 [] = { f7, f7, f7, f7, f7, f7, f7, f7,  }
+VDUP_LANE/VDUP_LANEQ:5:result_uint16x4 [] = { fff3, fff3, fff3, fff3,  }
+VDUP_LANE/VDUP_LANEQ:6:result_uint32x2 [] = { fffffff1, fffffff1,  }
+VDUP_LANE/VDUP_LANEQ:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VDUP_LANE/VDUP_LANEQ:8:result_poly8x8 [] = { f7, f7, f7, f7, f7, f7, f7, f7,  }
+VDUP_LANE/VDUP_LANEQ:9:result_poly16x4 [] = { fff3, fff3, fff3, fff3,  }
+VDUP_LANE/VDUP_LANEQ:10:result_float32x2 [] = { c1700000, c1700000,  }
+VDUP_LANE/VDUP_LANEQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VDUP_LANE/VDUP_LANEQ:12:result_int8x16 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VDUP_LANE/VDUP_LANEQ:13:result_int16x8 [] = { fffffff3, fffffff3, fffffff3, fffffff3, fffffff3, fffffff3, fffffff3, fffffff3,  }
+VDUP_LANE/VDUP_LANEQ:14:result_int32x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VDUP_LANE/VDUP_LANEQ:15:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VDUP_LANE/VDUP_LANEQ:16:result_uint8x16 [] = { f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5,  }
+VDUP_LANE/VDUP_LANEQ:17:result_uint16x8 [] = { fff1, fff1, fff1, fff1, fff1, fff1, fff1, fff1,  }
+VDUP_LANE/VDUP_LANEQ:18:result_uint32x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VDUP_LANE/VDUP_LANEQ:19:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VDUP_LANE/VDUP_LANEQ:20:result_poly8x16 [] = { f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5,  }
+VDUP_LANE/VDUP_LANEQ:21:result_poly16x8 [] = { fff1, fff1, fff1, fff1, fff1, fff1, fff1, fff1,  }
+VDUP_LANE/VDUP_LANEQ:22:result_float32x4 [] = { c1700000, c1700000, c1700000, c1700000,  }
+VDUP_LANE/VDUP_LANEQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMULL_LANE cumulative saturation output:
+VQDMULL_LANE:0:vqdmull_lane_s16 Neon cumulative saturation 0
+VQDMULL_LANE:1:vqdmull_lane_s32 Neon cumulative saturation 0
+
+VQDMULL_LANE output:
+VQDMULL_LANE:2:result_int32x4 [] = { 8000, 8000, 8000, 8000,  }
+VQDMULL_LANE:3:result_int64x2 [] = { 4000, 4000,  }
+
+VQDMULL_LANE (check mul cumulative saturation) cumulative saturation output:
+VQDMULL_LANE:4:vqdmull_lane_s16 Neon cumulative saturation 1
+VQDMULL_LANE:5:vqdmull_lane_s32 Neon cumulative saturation 1
+
+VQDMULL_LANE (check mul cumulative saturation) output:
+VQDMULL_LANE:6:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQDMULL_LANE:7:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+
+VQDMULL_N cumulative saturation output:
+VQDMULL_N:0:vqdmull_n_s16 Neon cumulative saturation 0
+VQDMULL_N:1:vqdmull_n_s32 Neon cumulative saturation 0
+
+VQDMULL_N output:
+VQDMULL_N:2:result_int32x4 [] = { 44000, 44000, 44000, 44000,  }
+VQDMULL_N:3:result_int64x2 [] = { aa000, aa000,  }
+
+VQDMULL_N (check mul cumulative saturation) cumulative saturation output:
+VQDMULL_N:4:vqdmull_n_s16 Neon cumulative saturation 1
+VQDMULL_N:5:vqdmull_n_s32 Neon cumulative saturation 1
+
+VQDMULL_N (check mul cumulative saturation) output:
+VQDMULL_N:6:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQDMULL_N:7:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+
+VST1_LANE/VST1_LANEQ output:
+VST1_LANE/VST1_LANEQ:0:result_int8x8 [] = { fffffff7, 33, 33, 33, 33, 33, 33, 33,  }
+VST1_LANE/VST1_LANEQ:1:result_int16x4 [] = { fffffff3, 3333, 3333, 3333,  }
+VST1_LANE/VST1_LANEQ:2:result_int32x2 [] = { fffffff1, 33333333,  }
+VST1_LANE/VST1_LANEQ:3:result_int64x1 [] = { fffffffffffffff0,  }
+VST1_LANE/VST1_LANEQ:4:result_uint8x8 [] = { f6, 33, 33, 33, 33, 33, 33, 33,  }
+VST1_LANE/VST1_LANEQ:5:result_uint16x4 [] = { fff2, 3333, 3333, 3333,  }
+VST1_LANE/VST1_LANEQ:6:result_uint32x2 [] = { fffffff0, 33333333,  }
+VST1_LANE/VST1_LANEQ:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VST1_LANE/VST1_LANEQ:8:result_poly8x8 [] = { f6, 33, 33, 33, 33, 33, 33, 33,  }
+VST1_LANE/VST1_LANEQ:9:result_poly16x4 [] = { fff2, 3333, 3333, 3333,  }
+VST1_LANE/VST1_LANEQ:10:result_float32x2 [] = { c1700000, 33333333,  }
+VST1_LANE/VST1_LANEQ:11:result_float16x4 [] = { cb00, 0, 0, 0,  }
+VST1_LANE/VST1_LANEQ:12:result_int8x16 [] = { ffffffff, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST1_LANE/VST1_LANEQ:13:result_int16x8 [] = { fffffff5, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VST1_LANE/VST1_LANEQ:14:result_int32x4 [] = { fffffff1, 33333333, 33333333, 33333333,  }
+VST1_LANE/VST1_LANEQ:15:result_int64x2 [] = { fffffffffffffff1, 3333333333333333,  }
+VST1_LANE/VST1_LANEQ:16:result_uint8x16 [] = { fa, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST1_LANE/VST1_LANEQ:17:result_uint16x8 [] = { fff4, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VST1_LANE/VST1_LANEQ:18:result_uint32x4 [] = { fffffff3, 33333333, 33333333, 33333333,  }
+VST1_LANE/VST1_LANEQ:19:result_uint64x2 [] = { fffffffffffffff0, 3333333333333333,  }
+VST1_LANE/VST1_LANEQ:20:result_poly8x16 [] = { fa, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST1_LANE/VST1_LANEQ:21:result_poly16x8 [] = { fff4, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VST1_LANE/VST1_LANEQ:22:result_float32x4 [] = { c1700000, 33333333, 33333333, 33333333,  }
+VST1_LANE/VST1_LANEQ:23:result_float16x8 [] = { c980, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSUB/VSUBQ output:
+VSUB/VSUBQ:0:result_int8x8 [] = { ffffffee, ffffffef, fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5,  }
+VSUB/VSUBQ:1:result_int16x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VSUB/VSUBQ:2:result_int32x2 [] = { ffffffed, ffffffee,  }
+VSUB/VSUBQ:3:result_int64x1 [] = { ffffffffffffff8c,  }
+VSUB/VSUBQ:4:result_uint8x8 [] = { dc, dd, de, df, e0, e1, e2, e3,  }
+VSUB/VSUBQ:5:result_uint16x4 [] = { ffd2, ffd3, ffd4, ffd5,  }
+VSUB/VSUBQ:6:result_uint32x2 [] = { ffffffc8, ffffffc9,  }
+VSUB/VSUBQ:7:result_uint64x1 [] = { ffffffffffffffee,  }
+VSUB/VSUBQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUB/VSUBQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSUB/VSUBQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSUB/VSUBQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSUB/VSUBQ:12:result_int8x16 [] = { fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9,  }
+VSUB/VSUBQ:13:result_int16x8 [] = { 4, 5, 6, 7, 8, 9, a, b,  }
+VSUB/VSUBQ:14:result_int32x4 [] = { e, f, 10, 11,  }
+VSUB/VSUBQ:15:result_int64x2 [] = { ffffffffffffffd8, ffffffffffffffd9,  }
+VSUB/VSUBQ:16:result_uint8x16 [] = { e4, e5, e6, e7, e8, e9, ea, eb, ec, ed, ee, ef, f0, f1, f2, f3,  }
+VSUB/VSUBQ:17:result_uint16x8 [] = { ffed, ffee, ffef, fff0, fff1, fff2, fff3, fff4,  }
+VSUB/VSUBQ:18:result_uint32x4 [] = { ffffffb9, ffffffba, ffffffbb, ffffffbc,  }
+VSUB/VSUBQ:19:result_uint64x2 [] = { ffffffffffffffed, ffffffffffffffee,  }
+VSUB/VSUBQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUB/VSUBQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSUB/VSUBQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSUB/VSUBQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+float32:
+VSUB/VSUBQ:24:result_float32x2 [] = { c00ccccd, c00ccccd,  }
+VSUB/VSUBQ:25:result_float32x4 [] = { c00ccccc, c00ccccc, c00ccccc, c00ccccc,  }
+
+VQADD/VQADDQ cumulative saturation output:
+VQADD/VQADDQ:0:vqadd_s8 Neon cumulative saturation 0
+VQADD/VQADDQ:1:vqadd_s16 Neon cumulative saturation 0
+VQADD/VQADDQ:2:vqadd_s32 Neon cumulative saturation 0
+VQADD/VQADDQ:3:vqadd_s64 Neon cumulative saturation 0
+VQADD/VQADDQ:4:vqadd_u8 Neon cumulative saturation 1
+VQADD/VQADDQ:5:vqadd_u16 Neon cumulative saturation 1
+VQADD/VQADDQ:6:vqadd_u32 Neon cumulative saturation 1
+VQADD/VQADDQ:7:vqadd_u64 Neon cumulative saturation 1
+VQADD/VQADDQ:8:vqaddq_s8 Neon cumulative saturation 0
+VQADD/VQADDQ:9:vqaddq_s16 Neon cumulative saturation 0
+VQADD/VQADDQ:10:vqaddq_s32 Neon cumulative saturation 0
+VQADD/VQADDQ:11:vqaddq_s64 Neon cumulative saturation 0
+VQADD/VQADDQ:12:vqaddq_u8 Neon cumulative saturation 1
+VQADD/VQADDQ:13:vqaddq_u16 Neon cumulative saturation 1
+VQADD/VQADDQ:14:vqaddq_u32 Neon cumulative saturation 1
+VQADD/VQADDQ:15:vqaddq_u64 Neon cumulative saturation 1
+
+VQADD/VQADDQ output:
+VQADD/VQADDQ:16:result_int8x8 [] = { 1, 2, 3, 4, 5, 6, 7, 8,  }
+VQADD/VQADDQ:17:result_int16x4 [] = { 12, 13, 14, 15,  }
+VQADD/VQADDQ:18:result_int32x2 [] = { 23, 24,  }
+VQADD/VQADDQ:19:result_int64x1 [] = { 34,  }
+VQADD/VQADDQ:20:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQADD/VQADDQ:21:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQADD/VQADDQ:22:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQADD/VQADDQ:23:result_uint64x1 [] = { ffffffffffffffff,  }
+VQADD/VQADDQ:24:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQADD/VQADDQ:25:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQADD/VQADDQ:26:result_float32x2 [] = { 33333333, 33333333,  }
+VQADD/VQADDQ:27:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQADD/VQADDQ:28:result_int8x16 [] = { 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f, 10,  }
+VQADD/VQADDQ:29:result_int16x8 [] = { 12, 13, 14, 15, 16, 17, 18, 19,  }
+VQADD/VQADDQ:30:result_int32x4 [] = { 23, 24, 25, 26,  }
+VQADD/VQADDQ:31:result_int64x2 [] = { 34, 35,  }
+VQADD/VQADDQ:32:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQADD/VQADDQ:33:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQADD/VQADDQ:34:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQADD/VQADDQ:35:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQADD/VQADDQ:36:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQADD/VQADDQ:37:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQADD/VQADDQ:38:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQADD/VQADDQ:39:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQADD/VQADDQ 64 bits saturation cumulative saturation output:
+VQADD/VQADDQ:40:vqadd_s64 Neon cumulative saturation 0
+VQADD/VQADDQ:41:vqadd_u64 Neon cumulative saturation 0
+VQADD/VQADDQ:42:vqaddq_s64 Neon cumulative saturation 0
+VQADD/VQADDQ:43:vqaddq_u64 Neon cumulative saturation 0
+
+64 bits saturation:
+VQADD/VQADDQ:44:result_int64x1 [] = { fffffffffffffff0,  }
+VQADD/VQADDQ:45:result_uint64x1 [] = { fffffffffffffff0,  }
+VQADD/VQADDQ:46:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VQADD/VQADDQ:47:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+
+VQADD/VQADDQ 64 bits saturation cumulative saturation output:
+VQADD/VQADDQ:48:vqadd_s64 Neon cumulative saturation 0
+VQADD/VQADDQ:49:vqadd_u64 Neon cumulative saturation 1
+VQADD/VQADDQ:50:vqaddq_s64 Neon cumulative saturation 0
+VQADD/VQADDQ:51:vqaddq_u64 Neon cumulative saturation 1
+VQADD/VQADDQ:52:result_int64x1 [] = { 34,  }
+VQADD/VQADDQ:53:result_uint64x1 [] = { ffffffffffffffff,  }
+VQADD/VQADDQ:54:result_int64x2 [] = { 34, 35,  }
+VQADD/VQADDQ:55:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+
+VQADD/VQADDQ 64 bits saturation cumulative saturation output:
+VQADD/VQADDQ:56:vqadd_s64 Neon cumulative saturation 1
+VQADD/VQADDQ:57:vqadd_u64 Neon cumulative saturation 1
+VQADD/VQADDQ:58:vqaddq_s64 Neon cumulative saturation 1
+VQADD/VQADDQ:59:vqaddq_u64 Neon cumulative saturation 1
+VQADD/VQADDQ:60:result_int64x1 [] = { 8000000000000000,  }
+VQADD/VQADDQ:61:result_uint64x1 [] = { ffffffffffffffff,  }
+VQADD/VQADDQ:62:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+VQADD/VQADDQ:63:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+
+less than 64 bits saturation:
+VQADD/VQADDQ:64:vqadd_s8 Neon cumulative saturation 1
+VQADD/VQADDQ:65:vqadd_s16 Neon cumulative saturation 1
+VQADD/VQADDQ:66:vqadd_s32 Neon cumulative saturation 1
+VQADD/VQADDQ:67:vqaddq_s8 Neon cumulative saturation 1
+VQADD/VQADDQ:68:vqaddq_s16 Neon cumulative saturation 1
+VQADD/VQADDQ:69:vqaddq_s32 Neon cumulative saturation 1
+VQADD/VQADDQ:70:result_int8x8 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQADD/VQADDQ:71:result_int16x4 [] = { ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQADD/VQADDQ:72:result_int32x2 [] = { 80000000, 80000000,  }
+VQADD/VQADDQ:73:result_int8x16 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQADD/VQADDQ:74:result_int16x8 [] = { ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQADD/VQADDQ:75:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+
+VQADD/VQADDQ less than 64 bits saturation cumulative saturation output:
+VQADD/VQADDQ:76:vqadd_u8 Neon cumulative saturation 1
+VQADD/VQADDQ:77:vqadd_u16 Neon cumulative saturation 1
+VQADD/VQADDQ:78:vqadd_u32 Neon cumulative saturation 1
+VQADD/VQADDQ:79:vqaddq_u8 Neon cumulative saturation 1
+VQADD/VQADDQ:80:vqaddq_u16 Neon cumulative saturation 1
+VQADD/VQADDQ:81:vqaddq_u32 Neon cumulative saturation 1
+VQADD/VQADDQ:82:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQADD/VQADDQ:83:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQADD/VQADDQ:84:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQADD/VQADDQ:85:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQADD/VQADDQ:86:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQADD/VQADDQ:87:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+
+VABS/VABSQ output:
+VABS/VABSQ:0:result_int8x8 [] = { 10, f, e, d, c, b, a, 9,  }
+VABS/VABSQ:1:result_int16x4 [] = { 10, f, e, d,  }
+VABS/VABSQ:2:result_int32x2 [] = { 10, f,  }
+VABS/VABSQ:3:result_int64x1 [] = { 3333333333333333,  }
+VABS/VABSQ:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABS/VABSQ:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABS/VABSQ:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VABS/VABSQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VABS/VABSQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABS/VABSQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABS/VABSQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VABS/VABSQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VABS/VABSQ:12:result_int8x16 [] = { 10, f, e, d, c, b, a, 9, 8, 7, 6, 5, 4, 3, 2, 1,  }
+VABS/VABSQ:13:result_int16x8 [] = { 10, f, e, d, c, b, a, 9,  }
+VABS/VABSQ:14:result_int32x4 [] = { 10, f, e, d,  }
+VABS/VABSQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VABS/VABSQ:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABS/VABSQ:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VABS/VABSQ:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VABS/VABSQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VABS/VABSQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABS/VABSQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VABS/VABSQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VABS/VABSQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+float32:
+VABS/VABSQ:24:result_float32x2 [] = { 40133333, 40133333,  }
+VABS/VABSQ:25:result_float32x4 [] = { 4059999a, 4059999a, 4059999a, 4059999a,  }
+
+VQABS/VQABSQ cumulative saturation output:
+VQABS/VQABSQ:0:vqabs_s8 Neon cumulative saturation 0
+VQABS/VQABSQ:1:vqabs_s16 Neon cumulative saturation 0
+VQABS/VQABSQ:2:vqabs_s32 Neon cumulative saturation 0
+VQABS/VQABSQ:3:vqabsq_s8 Neon cumulative saturation 0
+VQABS/VQABSQ:4:vqabsq_s16 Neon cumulative saturation 0
+VQABS/VQABSQ:5:vqabsq_s32 Neon cumulative saturation 0
+
+VQABS/VQABSQ output:
+VQABS/VQABSQ:6:result_int8x8 [] = { 10, f, e, d, c, b, a, 9,  }
+VQABS/VQABSQ:7:result_int16x4 [] = { 10, f, e, d,  }
+VQABS/VQABSQ:8:result_int32x2 [] = { 10, f,  }
+VQABS/VQABSQ:9:result_int64x1 [] = { 3333333333333333,  }
+VQABS/VQABSQ:10:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQABS/VQABSQ:11:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQABS/VQABSQ:12:result_uint32x2 [] = { 33333333, 33333333,  }
+VQABS/VQABSQ:13:result_uint64x1 [] = { 3333333333333333,  }
+VQABS/VQABSQ:14:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQABS/VQABSQ:15:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQABS/VQABSQ:16:result_float32x2 [] = { 33333333, 33333333,  }
+VQABS/VQABSQ:17:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQABS/VQABSQ:18:result_int8x16 [] = { 10, f, e, d, c, b, a, 9, 8, 7, 6, 5, 4, 3, 2, 1,  }
+VQABS/VQABSQ:19:result_int16x8 [] = { 10, f, e, d, c, b, a, 9,  }
+VQABS/VQABSQ:20:result_int32x4 [] = { 10, f, e, d,  }
+VQABS/VQABSQ:21:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQABS/VQABSQ:22:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQABS/VQABSQ:23:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQABS/VQABSQ:24:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQABS/VQABSQ:25:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQABS/VQABSQ:26:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQABS/VQABSQ:27:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQABS/VQABSQ:28:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQABS/VQABSQ:29:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQABS/VQABSQ cumulative saturation output:
+VQABS/VQABSQ:0:vqabs_s8 Neon cumulative saturation 1
+VQABS/VQABSQ:1:vqabs_s16 Neon cumulative saturation 1
+VQABS/VQABSQ:2:vqabs_s32 Neon cumulative saturation 1
+VQABS/VQABSQ:3:vqabsq_s8 Neon cumulative saturation 1
+VQABS/VQABSQ:4:vqabsq_s16 Neon cumulative saturation 1
+VQABS/VQABSQ:5:vqabsq_s32 Neon cumulative saturation 1
+
+VQABS/VQABSQ output:
+VQABS/VQABSQ:6:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQABS/VQABSQ:7:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQABS/VQABSQ:8:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQABS/VQABSQ:9:result_int64x1 [] = { 3333333333333333,  }
+VQABS/VQABSQ:10:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQABS/VQABSQ:11:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQABS/VQABSQ:12:result_uint32x2 [] = { 33333333, 33333333,  }
+VQABS/VQABSQ:13:result_uint64x1 [] = { 3333333333333333,  }
+VQABS/VQABSQ:14:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQABS/VQABSQ:15:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQABS/VQABSQ:16:result_float32x2 [] = { 33333333, 33333333,  }
+VQABS/VQABSQ:17:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQABS/VQABSQ:18:result_int8x16 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQABS/VQABSQ:19:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQABS/VQABSQ:20:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQABS/VQABSQ:21:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQABS/VQABSQ:22:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQABS/VQABSQ:23:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQABS/VQABSQ:24:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQABS/VQABSQ:25:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQABS/VQABSQ:26:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQABS/VQABSQ:27:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQABS/VQABSQ:28:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQABS/VQABSQ:29:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VCOMBINE output:
+VCOMBINE:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCOMBINE:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCOMBINE:2:result_int32x2 [] = { 33333333, 33333333,  }
+VCOMBINE:3:result_int64x1 [] = { 3333333333333333,  }
+VCOMBINE:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCOMBINE:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCOMBINE:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VCOMBINE:7:result_uint64x1 [] = { 3333333333333333,  }
+VCOMBINE:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCOMBINE:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCOMBINE:10:result_float32x2 [] = { 33333333, 33333333,  }
+VCOMBINE:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VCOMBINE:12:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, 11, 11, 11, 11, 11, 11, 11, 11,  }
+VCOMBINE:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, 22, 22, 22, 22,  }
+VCOMBINE:14:result_int32x4 [] = { fffffff0, fffffff1, 33, 33,  }
+VCOMBINE:15:result_int64x2 [] = { fffffffffffffff0, 44,  }
+VCOMBINE:16:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, 55, 55, 55, 55, 55, 55, 55, 55,  }
+VCOMBINE:17:result_uint16x8 [] = { fff0, fff1, fff2, fff3, 66, 66, 66, 66,  }
+VCOMBINE:18:result_uint32x4 [] = { fffffff0, fffffff1, 77, 77,  }
+VCOMBINE:19:result_uint64x2 [] = { fffffffffffffff0, 88,  }
+VCOMBINE:20:result_poly8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, 55, 55, 55, 55, 55, 55, 55, 55,  }
+VCOMBINE:21:result_poly16x8 [] = { fff0, fff1, fff2, fff3, 66, 66, 66, 66,  }
+VCOMBINE:22:result_float32x4 [] = { c1800000, c1700000, 40533333, 40533333,  }
+VCOMBINE:23:result_float16x8 [] = { cc00, cb80, cb00, ca80, 4b80, 4b80, 4b80, 4b80,  }
+
+VMAX/VMAXQ output:
+VMAX/VMAXQ:0:result_int8x8 [] = { fffffff3, fffffff3, fffffff3, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VMAX/VMAXQ:1:result_int16x4 [] = { fffffff2, fffffff2, fffffff2, fffffff3,  }
+VMAX/VMAXQ:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VMAX/VMAXQ:3:result_int64x1 [] = { 3333333333333333,  }
+VMAX/VMAXQ:4:result_uint8x8 [] = { f3, f3, f3, f3, f4, f5, f6, f7,  }
+VMAX/VMAXQ:5:result_uint16x4 [] = { fff1, fff1, fff2, fff3,  }
+VMAX/VMAXQ:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VMAX/VMAXQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VMAX/VMAXQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMAX/VMAXQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMAX/VMAXQ:10:result_float32x2 [] = { c1780000, c1700000,  }
+VMAX/VMAXQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMAX/VMAXQ:12:result_int8x16 [] = { fffffff4, fffffff4, fffffff4, fffffff4, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VMAX/VMAXQ:13:result_int16x8 [] = { fffffff3, fffffff3, fffffff3, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VMAX/VMAXQ:14:result_int32x4 [] = { fffffff1, fffffff1, fffffff2, fffffff3,  }
+VMAX/VMAXQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMAX/VMAXQ:16:result_uint8x16 [] = { f9, f9, f9, f9, f9, f9, f9, f9, f9, f9, fa, fb, fc, fd, fe, ff,  }
+VMAX/VMAXQ:17:result_uint16x8 [] = { fff2, fff2, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VMAX/VMAXQ:18:result_uint32x4 [] = { fffffff1, fffffff1, fffffff2, fffffff3,  }
+VMAX/VMAXQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMAX/VMAXQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMAX/VMAXQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMAX/VMAXQ:22:result_float32x4 [] = { c1680000, c1680000, c1600000, c1500000,  }
+VMAX/VMAXQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VMAX/VMAXQ FP special (NaN):24:result_float32x4 [] = { 7fc00000, 7fc00000, 7fc00000, 7fc00000,  }
+VMAX/VMAXQ FP special (-NaN):25:result_float32x4 [] = { 7fc00000, 7fc00000, 7fc00000, 7fc00000,  }
+VMAX/VMAXQ FP special (inf):26:result_float32x4 [] = { 7f800000, 7f800000, 7f800000, 7f800000,  }
+VMAX/VMAXQ FP special (-inf):27:result_float32x4 [] = { 3f800000, 3f800000, 3f800000, 3f800000,  }
+VMAX/VMAXQ FP special (-0.0):28:result_float32x4 [] = { 0, 0, 0, 0,  }
+VMAX/VMAXQ FP special (-0.0):29:result_float32x4 [] = { 0, 0, 0, 0,  }
+
+VMIN/VMINQ output:
+VMIN/VMINQ:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff3, fffffff3, fffffff3, fffffff3,  }
+VMIN/VMINQ:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff2,  }
+VMIN/VMINQ:2:result_int32x2 [] = { fffffff0, fffffff0,  }
+VMIN/VMINQ:3:result_int64x1 [] = { 3333333333333333,  }
+VMIN/VMINQ:4:result_uint8x8 [] = { f0, f1, f2, f3, f3, f3, f3, f3,  }
+VMIN/VMINQ:5:result_uint16x4 [] = { fff0, fff1, fff1, fff1,  }
+VMIN/VMINQ:6:result_uint32x2 [] = { fffffff0, fffffff0,  }
+VMIN/VMINQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VMIN/VMINQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMIN/VMINQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMIN/VMINQ:10:result_float32x2 [] = { c1800000, c1780000,  }
+VMIN/VMINQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMIN/VMINQ:12:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff4, fffffff4, fffffff4, fffffff4, fffffff4, fffffff4, fffffff4, fffffff4, fffffff4, fffffff4, fffffff4,  }
+VMIN/VMINQ:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff3, fffffff3, fffffff3, fffffff3,  }
+VMIN/VMINQ:14:result_int32x4 [] = { fffffff0, fffffff1, fffffff1, fffffff1,  }
+VMIN/VMINQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMIN/VMINQ:16:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, f9, f9, f9, f9, f9, f9,  }
+VMIN/VMINQ:17:result_uint16x8 [] = { fff0, fff1, fff2, fff2, fff2, fff2, fff2, fff2,  }
+VMIN/VMINQ:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff1, fffffff1,  }
+VMIN/VMINQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMIN/VMINQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMIN/VMINQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMIN/VMINQ:22:result_float32x4 [] = { c1800000, c1700000, c1680000, c1680000,  }
+VMIN/VMINQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VMIN/VMINQ FP special (NaN):24:result_float32x4 [] = { 7fc00000, 7fc00000, 7fc00000, 7fc00000,  }
+VMIN/VMINQ FP special (-NaN):25:result_float32x4 [] = { 7fc00000, 7fc00000, 7fc00000, 7fc00000,  }
+VMIN/VMINQ FP special (inf):26:result_float32x4 [] = { 3f800000, 3f800000, 3f800000, 3f800000,  }
+VMIN/VMINQ FP special (-inf):27:result_float32x4 [] = { ff800000, ff800000, ff800000, ff800000,  }
+VMIN/VMINQ FP special (-0.0):28:result_float32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VMIN/VMINQ FP special (-0.0):29:result_float32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+
+VNEG/VNEGQ output:
+VNEG/VNEGQ:0:result_int8x8 [] = { 10, f, e, d, c, b, a, 9,  }
+VNEG/VNEGQ:1:result_int16x4 [] = { 10, f, e, d,  }
+VNEG/VNEGQ:2:result_int32x2 [] = { 10, f,  }
+VNEG/VNEGQ:3:result_int64x1 [] = { 3333333333333333,  }
+VNEG/VNEGQ:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VNEG/VNEGQ:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VNEG/VNEGQ:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VNEG/VNEGQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VNEG/VNEGQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VNEG/VNEGQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VNEG/VNEGQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VNEG/VNEGQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VNEG/VNEGQ:12:result_int8x16 [] = { 10, f, e, d, c, b, a, 9, 8, 7, 6, 5, 4, 3, 2, 1,  }
+VNEG/VNEGQ:13:result_int16x8 [] = { 10, f, e, d, c, b, a, 9,  }
+VNEG/VNEGQ:14:result_int32x4 [] = { 10, f, e, d,  }
+VNEG/VNEGQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VNEG/VNEGQ:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VNEG/VNEGQ:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VNEG/VNEGQ:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VNEG/VNEGQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VNEG/VNEGQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VNEG/VNEGQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VNEG/VNEGQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VNEG/VNEGQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+float32:
+VNEG/VNEGQ:24:result_float32x2 [] = { c0133333, c0133333,  }
+VNEG/VNEGQ:25:result_float32x4 [] = { c059999a, c059999a, c059999a, c059999a,  }
+
+VQNEG/VQNEGQ cumulative saturation output:
+VQNEG/VQNEGQ:0:vqneg_s8 Neon cumulative saturation 0
+VQNEG/VQNEGQ:1:vqneg_s16 Neon cumulative saturation 0
+VQNEG/VQNEGQ:2:vqneg_s32 Neon cumulative saturation 0
+VQNEG/VQNEGQ:3:vqnegq_s8 Neon cumulative saturation 0
+VQNEG/VQNEGQ:4:vqnegq_s16 Neon cumulative saturation 0
+VQNEG/VQNEGQ:5:vqnegq_s32 Neon cumulative saturation 0
+
+VQNEG/VQNEGQ output:
+VQNEG/VQNEGQ:6:result_int8x8 [] = { 10, f, e, d, c, b, a, 9,  }
+VQNEG/VQNEGQ:7:result_int16x4 [] = { 10, f, e, d,  }
+VQNEG/VQNEGQ:8:result_int32x2 [] = { 10, f,  }
+VQNEG/VQNEGQ:9:result_int64x1 [] = { 3333333333333333,  }
+VQNEG/VQNEGQ:10:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQNEG/VQNEGQ:11:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQNEG/VQNEGQ:12:result_uint32x2 [] = { 33333333, 33333333,  }
+VQNEG/VQNEGQ:13:result_uint64x1 [] = { 3333333333333333,  }
+VQNEG/VQNEGQ:14:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQNEG/VQNEGQ:15:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQNEG/VQNEGQ:16:result_float32x2 [] = { 33333333, 33333333,  }
+VQNEG/VQNEGQ:17:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQNEG/VQNEGQ:18:result_int8x16 [] = { 10, f, e, d, c, b, a, 9, 8, 7, 6, 5, 4, 3, 2, 1,  }
+VQNEG/VQNEGQ:19:result_int16x8 [] = { 10, f, e, d, c, b, a, 9,  }
+VQNEG/VQNEGQ:20:result_int32x4 [] = { 10, f, e, d,  }
+VQNEG/VQNEGQ:21:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQNEG/VQNEGQ:22:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQNEG/VQNEGQ:23:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQNEG/VQNEGQ:24:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQNEG/VQNEGQ:25:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQNEG/VQNEGQ:26:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQNEG/VQNEGQ:27:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQNEG/VQNEGQ:28:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQNEG/VQNEGQ:29:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQNEG/VQNEGQ cumulative saturation output:
+VQNEG/VQNEGQ:0:vqneg_s8 Neon cumulative saturation 1
+VQNEG/VQNEGQ:1:vqneg_s16 Neon cumulative saturation 1
+VQNEG/VQNEGQ:2:vqneg_s32 Neon cumulative saturation 1
+VQNEG/VQNEGQ:3:vqnegq_s8 Neon cumulative saturation 1
+VQNEG/VQNEGQ:4:vqnegq_s16 Neon cumulative saturation 1
+VQNEG/VQNEGQ:5:vqnegq_s32 Neon cumulative saturation 1
+
+VQNEG/VQNEGQ output:
+VQNEG/VQNEGQ:6:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQNEG/VQNEGQ:7:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQNEG/VQNEGQ:8:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQNEG/VQNEGQ:9:result_int64x1 [] = { 3333333333333333,  }
+VQNEG/VQNEGQ:10:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQNEG/VQNEGQ:11:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQNEG/VQNEGQ:12:result_uint32x2 [] = { 33333333, 33333333,  }
+VQNEG/VQNEGQ:13:result_uint64x1 [] = { 3333333333333333,  }
+VQNEG/VQNEGQ:14:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQNEG/VQNEGQ:15:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQNEG/VQNEGQ:16:result_float32x2 [] = { 33333333, 33333333,  }
+VQNEG/VQNEGQ:17:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQNEG/VQNEGQ:18:result_int8x16 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQNEG/VQNEGQ:19:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQNEG/VQNEGQ:20:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQNEG/VQNEGQ:21:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQNEG/VQNEGQ:22:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQNEG/VQNEGQ:23:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQNEG/VQNEGQ:24:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQNEG/VQNEGQ:25:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQNEG/VQNEGQ:26:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQNEG/VQNEGQ:27:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQNEG/VQNEGQ:28:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQNEG/VQNEGQ:29:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMLAL output:
+VMLAL:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMLAL:3:result_int64x1 [] = { 3333333333333333,  }
+VMLAL:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMLAL:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLAL:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMLAL:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMLAL:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL:13:result_int16x8 [] = { ffffe907, ffffe908, ffffe909, ffffe90a, ffffe90b, ffffe90c, ffffe90d, ffffe90e,  }
+VMLAL:14:result_int32x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLAL:15:result_int64x2 [] = { 3e07, 3e08,  }
+VMLAL:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL:17:result_uint16x8 [] = { 3e07, 3e08, 3e09, 3e0a, 3e0b, 3e0c, 3e0d, 3e0e,  }
+VMLAL:18:result_uint32x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLAL:19:result_uint64x2 [] = { 3e07, 3e08,  }
+VMLAL:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLAL:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMLAL:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMLSL output:
+VMLSL:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMLSL:3:result_int64x1 [] = { 3333333333333333,  }
+VMLSL:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMLSL:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLSL:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMLSL:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMLSL:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL:13:result_int16x8 [] = { 16d9, 16da, 16db, 16dc, 16dd, 16de, 16df, 16e0,  }
+VMLSL:14:result_int32x4 [] = { ffffc1d9, ffffc1da, ffffc1db, ffffc1dc,  }
+VMLSL:15:result_int64x2 [] = { ffffffffffffc1d9, ffffffffffffc1da,  }
+VMLSL:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL:17:result_uint16x8 [] = { c1d9, c1da, c1db, c1dc, c1dd, c1de, c1df, c1e0,  }
+VMLSL:18:result_uint32x4 [] = { ffffc1d9, ffffc1da, ffffc1db, ffffc1dc,  }
+VMLSL:19:result_uint64x2 [] = { ffffffffffffc1d9, ffffffffffffc1da,  }
+VMLSL:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLSL:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMLSL:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMLAL_LANE output:
+VMLAL_LANE:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_LANE:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL_LANE:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMLAL_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VMLAL_LANE:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_LANE:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL_LANE:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMLAL_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLAL_LANE:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_LANE:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL_LANE:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMLAL_LANE:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMLAL_LANE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_LANE:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLAL_LANE:14:result_int32x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLAL_LANE:15:result_int64x2 [] = { 3e07, 3e08,  }
+VMLAL_LANE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_LANE:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLAL_LANE:18:result_uint32x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLAL_LANE:19:result_uint64x2 [] = { 3e07, 3e08,  }
+VMLAL_LANE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_LANE:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLAL_LANE:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMLAL_LANE:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMLSL_LANE output:
+VMLSL_LANE:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_LANE:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL_LANE:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMLSL_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VMLSL_LANE:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_LANE:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL_LANE:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMLSL_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLSL_LANE:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_LANE:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL_LANE:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMLSL_LANE:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMLSL_LANE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_LANE:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLSL_LANE:14:result_int32x4 [] = { ffffc1d9, ffffc1da, ffffc1db, ffffc1dc,  }
+VMLSL_LANE:15:result_int64x2 [] = { ffffffffffffc1d9, ffffffffffffc1da,  }
+VMLSL_LANE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_LANE:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLSL_LANE:18:result_uint32x4 [] = { ffffc1d9, ffffc1da, ffffc1db, ffffc1dc,  }
+VMLSL_LANE:19:result_uint64x2 [] = { ffffffffffffc1d9, ffffffffffffc1da,  }
+VMLSL_LANE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_LANE:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLSL_LANE:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMLSL_LANE:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMLAL_N output:
+VMLAL_N:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_N:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL_N:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMLAL_N:3:result_int64x1 [] = { 3333333333333333,  }
+VMLAL_N:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_N:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL_N:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMLAL_N:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLAL_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMLAL_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMLAL_N:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_N:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLAL_N:14:result_int32x4 [] = { 595, 596, 597, 598,  }
+VMLAL_N:15:result_int64x2 [] = { b3a, b3b,  }
+VMLAL_N:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_N:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLAL_N:18:result_uint32x4 [] = { 10df, 10e0, 10e1, 10e2,  }
+VMLAL_N:19:result_uint64x2 [] = { 10df, 10e0,  }
+VMLAL_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLAL_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMLAL_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMLSL_N output:
+VMLSL_N:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_N:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL_N:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMLSL_N:3:result_int64x1 [] = { 3333333333333333,  }
+VMLSL_N:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_N:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL_N:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMLSL_N:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLSL_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMLSL_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMLSL_N:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_N:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLSL_N:14:result_int32x4 [] = { fffffa4b, fffffa4c, fffffa4d, fffffa4e,  }
+VMLSL_N:15:result_int64x2 [] = { fffffffffffff4a6, fffffffffffff4a7,  }
+VMLSL_N:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_N:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLSL_N:18:result_uint32x4 [] = { ffffef01, ffffef02, ffffef03, ffffef04,  }
+VMLSL_N:19:result_uint64x2 [] = { ffffffffffffef01, ffffffffffffef02,  }
+VMLSL_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLSL_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMLSL_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMOVL output:
+VMOVL:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVL:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMOVL:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMOVL:3:result_int64x1 [] = { 3333333333333333,  }
+VMOVL:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVL:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMOVL:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMOVL:7:result_uint64x1 [] = { 3333333333333333,  }
+VMOVL:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMOVL:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMOVL:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMOVL:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVL:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VMOVL:14:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VMOVL:15:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VMOVL:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVL:17:result_uint16x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VMOVL:18:result_uint32x4 [] = { fff0, fff1, fff2, fff3,  }
+VMOVL:19:result_uint64x2 [] = { fffffff0, fffffff1,  }
+VMOVL:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVL:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMOVL:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMOVL:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMOVN output:
+VMOVN:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VMOVN:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VMOVN:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VMOVN:3:result_int64x1 [] = { 3333333333333333,  }
+VMOVN:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VMOVN:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VMOVN:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VMOVN:7:result_uint64x1 [] = { 3333333333333333,  }
+VMOVN:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVN:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMOVN:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMOVN:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMOVN:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVN:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMOVN:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMOVN:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMOVN:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVN:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMOVN:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMOVN:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMOVN:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVN:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMOVN:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMOVN:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMULL output:
+VMULL:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMULL:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMULL:3:result_int64x1 [] = { 3333333333333333,  }
+VMULL:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMULL:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMULL:7:result_uint64x1 [] = { 3333333333333333,  }
+VMULL:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMULL:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMULL:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMULL:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL:13:result_int16x8 [] = { 100, e1, c4, a9, 90, 79, 64, 51,  }
+VMULL:14:result_int32x4 [] = { 100, e1, c4, a9,  }
+VMULL:15:result_int64x2 [] = { 100, e1,  }
+VMULL:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL:17:result_uint16x8 [] = { e100, e2e1, e4c4, e6a9, e890, ea79, ec64, ee51,  }
+VMULL:18:result_uint32x4 [] = { ffe00100, ffe200e1, ffe400c4, ffe600a9,  }
+VMULL:19:result_uint64x2 [] = { ffffffe000000100, ffffffe2000000e1,  }
+VMULL:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL:21:result_poly16x8 [] = { 5500, 5501, 5504, 5505, 5510, 5511, 5514, 5515,  }
+VMULL:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMULL:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMULL_LANE output:
+VMULL_LANE:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL_LANE:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMULL_LANE:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMULL_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VMULL_LANE:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL_LANE:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMULL_LANE:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMULL_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VMULL_LANE:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL_LANE:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMULL_LANE:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMULL_LANE:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMULL_LANE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL_LANE:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMULL_LANE:14:result_int32x4 [] = { 4000, 4000, 4000, 4000,  }
+VMULL_LANE:15:result_int64x2 [] = { 2000, 2000,  }
+VMULL_LANE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL_LANE:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMULL_LANE:18:result_uint32x4 [] = { 4000, 4000, 4000, 4000,  }
+VMULL_LANE:19:result_uint64x2 [] = { 2000, 2000,  }
+VMULL_LANE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL_LANE:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMULL_LANE:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMULL_LANE:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VREV16 output:
+VREV16:0:result_int8x8 [] = { fffffff1, fffffff0, fffffff3, fffffff2, fffffff5, fffffff4, fffffff7, fffffff6,  }
+VREV16:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VREV16:2:result_int32x2 [] = { 33333333, 33333333,  }
+VREV16:3:result_int64x1 [] = { 3333333333333333,  }
+VREV16:4:result_uint8x8 [] = { f1, f0, f3, f2, f5, f4, f7, f6,  }
+VREV16:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VREV16:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VREV16:7:result_uint64x1 [] = { 3333333333333333,  }
+VREV16:8:result_poly8x8 [] = { f1, f0, f3, f2, f5, f4, f7, f6,  }
+VREV16:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VREV16:10:result_float32x2 [] = { 33333333, 33333333,  }
+VREV16:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VREV16:12:result_int8x16 [] = { fffffff1, fffffff0, fffffff3, fffffff2, fffffff5, fffffff4, fffffff7, fffffff6, fffffff9, fffffff8, fffffffb, fffffffa, fffffffd, fffffffc, ffffffff, fffffffe,  }
+VREV16:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VREV16:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VREV16:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VREV16:16:result_uint8x16 [] = { f1, f0, f3, f2, f5, f4, f7, f6, f9, f8, fb, fa, fd, fc, ff, fe,  }
+VREV16:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VREV16:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VREV16:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VREV16:20:result_poly8x16 [] = { f1, f0, f3, f2, f5, f4, f7, f6, f9, f8, fb, fa, fd, fc, ff, fe,  }
+VREV16:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VREV16:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VREV16:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VREV32 output:
+VREV32:24:result_int8x8 [] = { fffffff3, fffffff2, fffffff1, fffffff0, fffffff7, fffffff6, fffffff5, fffffff4,  }
+VREV32:25:result_int16x4 [] = { fffffff1, fffffff0, fffffff3, fffffff2,  }
+VREV32:26:result_int32x2 [] = { 33333333, 33333333,  }
+VREV32:27:result_int64x1 [] = { 3333333333333333,  }
+VREV32:28:result_uint8x8 [] = { f3, f2, f1, f0, f7, f6, f5, f4,  }
+VREV32:29:result_uint16x4 [] = { fff1, fff0, fff3, fff2,  }
+VREV32:30:result_uint32x2 [] = { 33333333, 33333333,  }
+VREV32:31:result_uint64x1 [] = { 3333333333333333,  }
+VREV32:32:result_poly8x8 [] = { f3, f2, f1, f0, f7, f6, f5, f4,  }
+VREV32:33:result_poly16x4 [] = { fff1, fff0, fff3, fff2,  }
+VREV32:34:result_float32x2 [] = { 33333333, 33333333,  }
+VREV32:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VREV32:36:result_int8x16 [] = { fffffff3, fffffff2, fffffff1, fffffff0, fffffff7, fffffff6, fffffff5, fffffff4, fffffffb, fffffffa, fffffff9, fffffff8, ffffffff, fffffffe, fffffffd, fffffffc,  }
+VREV32:37:result_int16x8 [] = { fffffff1, fffffff0, fffffff3, fffffff2, fffffff5, fffffff4, fffffff7, fffffff6,  }
+VREV32:38:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VREV32:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VREV32:40:result_uint8x16 [] = { f3, f2, f1, f0, f7, f6, f5, f4, fb, fa, f9, f8, ff, fe, fd, fc,  }
+VREV32:41:result_uint16x8 [] = { fff1, fff0, fff3, fff2, fff5, fff4, fff7, fff6,  }
+VREV32:42:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VREV32:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VREV32:44:result_poly8x16 [] = { f3, f2, f1, f0, f7, f6, f5, f4, fb, fa, f9, f8, ff, fe, fd, fc,  }
+VREV32:45:result_poly16x8 [] = { fff1, fff0, fff3, fff2, fff5, fff4, fff7, fff6,  }
+VREV32:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VREV32:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VREV64 output:
+VREV64:48:result_int8x8 [] = { fffffff7, fffffff6, fffffff5, fffffff4, fffffff3, fffffff2, fffffff1, fffffff0,  }
+VREV64:49:result_int16x4 [] = { fffffff3, fffffff2, fffffff1, fffffff0,  }
+VREV64:50:result_int32x2 [] = { fffffff1, fffffff0,  }
+VREV64:51:result_int64x1 [] = { 3333333333333333,  }
+VREV64:52:result_uint8x8 [] = { f7, f6, f5, f4, f3, f2, f1, f0,  }
+VREV64:53:result_uint16x4 [] = { fff3, fff2, fff1, fff0,  }
+VREV64:54:result_uint32x2 [] = { fffffff1, fffffff0,  }
+VREV64:55:result_uint64x1 [] = { 3333333333333333,  }
+VREV64:56:result_poly8x8 [] = { f7, f6, f5, f4, f3, f2, f1, f0,  }
+VREV64:57:result_poly16x4 [] = { fff3, fff2, fff1, fff0,  }
+VREV64:58:result_float32x2 [] = { c1700000, c1800000,  }
+VREV64:59:result_float16x4 [] = { 0, 0, 0, 0,  }
+VREV64:60:result_int8x16 [] = { fffffff7, fffffff6, fffffff5, fffffff4, fffffff3, fffffff2, fffffff1, fffffff0, ffffffff, fffffffe, fffffffd, fffffffc, fffffffb, fffffffa, fffffff9, fffffff8,  }
+VREV64:61:result_int16x8 [] = { fffffff3, fffffff2, fffffff1, fffffff0, fffffff7, fffffff6, fffffff5, fffffff4,  }
+VREV64:62:result_int32x4 [] = { fffffff1, fffffff0, fffffff3, fffffff2,  }
+VREV64:63:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VREV64:64:result_uint8x16 [] = { f7, f6, f5, f4, f3, f2, f1, f0, ff, fe, fd, fc, fb, fa, f9, f8,  }
+VREV64:65:result_uint16x8 [] = { fff3, fff2, fff1, fff0, fff7, fff6, fff5, fff4,  }
+VREV64:66:result_uint32x4 [] = { fffffff1, fffffff0, fffffff3, fffffff2,  }
+VREV64:67:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VREV64:68:result_poly8x16 [] = { f7, f6, f5, f4, f3, f2, f1, f0, ff, fe, fd, fc, fb, fa, f9, f8,  }
+VREV64:69:result_poly16x8 [] = { fff3, fff2, fff1, fff0, fff7, fff6, fff5, fff4,  }
+VREV64:70:result_float32x4 [] = { c1700000, c1800000, c1500000, c1600000,  }
+VREV64:71:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSRA_N output:
+VSRA_N:0:result_int8x8 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VSRA_N:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VSRA_N:2:result_int32x2 [] = { fffffffc, fffffffd,  }
+VSRA_N:3:result_int64x1 [] = { fffffffffffffff0,  }
+VSRA_N:4:result_uint8x8 [] = { 5, 6, 7, 8, 9, a, b, c,  }
+VSRA_N:5:result_uint16x4 [] = { fffc, fffd, fffe, ffff,  }
+VSRA_N:6:result_uint32x2 [] = { fffffff3, fffffff4,  }
+VSRA_N:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VSRA_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSRA_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSRA_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSRA_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSRA_N:12:result_int8x16 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff, 0, 1, 2, 3, 4, 5, 6, 7,  }
+VSRA_N:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VSRA_N:14:result_int32x4 [] = { fffffffc, fffffffd, fffffffe, ffffffff,  }
+VSRA_N:15:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VSRA_N:16:result_uint8x16 [] = { 5, 6, 7, 8, 9, a, b, c, d, e, f, 10, 11, 12, 13, 14,  }
+VSRA_N:17:result_uint16x8 [] = { fffc, fffd, fffe, ffff, 0, 1, 2, 3,  }
+VSRA_N:18:result_uint32x4 [] = { fffffff3, fffffff4, fffffff5, fffffff6,  }
+VSRA_N:19:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VSRA_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSRA_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSRA_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSRA_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VTRN/VTRNQ chunk 0 output:
+VTRN/VTRNQ:0:result_int8x8 [] = { fffffff0, fffffff1, 11, 11, fffffff2, fffffff3, 11, 11,  }
+VTRN/VTRNQ:1:result_int16x4 [] = { fffffff0, fffffff1, 22, 22,  }
+VTRN/VTRNQ:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VTRN/VTRNQ:3:result_int64x1 [] = { 3333333333333333,  }
+VTRN/VTRNQ:4:result_uint8x8 [] = { f0, f1, 55, 55, f2, f3, 55, 55,  }
+VTRN/VTRNQ:5:result_uint16x4 [] = { fff0, fff1, 66, 66,  }
+VTRN/VTRNQ:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VTRN/VTRNQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VTRN/VTRNQ:8:result_poly8x8 [] = { f0, f1, 55, 55, f2, f3, 55, 55,  }
+VTRN/VTRNQ:9:result_poly16x4 [] = { fff0, fff1, 66, 66,  }
+VTRN/VTRNQ:10:result_float32x2 [] = { c1800000, c1700000,  }
+VTRN/VTRNQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VTRN/VTRNQ:12:result_int8x16 [] = { fffffff0, fffffff1, 11, 11, fffffff2, fffffff3, 11, 11, fffffff4, fffffff5, 11, 11, fffffff6, fffffff7, 11, 11,  }
+VTRN/VTRNQ:13:result_int16x8 [] = { fffffff0, fffffff1, 22, 22, fffffff2, fffffff3, 22, 22,  }
+VTRN/VTRNQ:14:result_int32x4 [] = { fffffff0, fffffff1, 33, 33,  }
+VTRN/VTRNQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTRN/VTRNQ:16:result_uint8x16 [] = { f0, f1, 55, 55, f2, f3, 55, 55, f4, f5, 55, 55, f6, f7, 55, 55,  }
+VTRN/VTRNQ:17:result_uint16x8 [] = { fff0, fff1, 66, 66, fff2, fff3, 66, 66,  }
+VTRN/VTRNQ:18:result_uint32x4 [] = { fffffff0, fffffff1, 77, 77,  }
+VTRN/VTRNQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTRN/VTRNQ:20:result_poly8x16 [] = { f0, f1, 55, 55, f2, f3, 55, 55, f4, f5, 55, 55, f6, f7, 55, 55,  }
+VTRN/VTRNQ:21:result_poly16x8 [] = { fff0, fff1, 66, 66, fff2, fff3, 66, 66,  }
+VTRN/VTRNQ:22:result_float32x4 [] = { c1800000, c1700000, 42073333, 42073333,  }
+VTRN/VTRNQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VTRN/VTRNQ chunk 1 output:
+VTRN/VTRNQ:24:result_int8x8 [] = { fffffff4, fffffff5, 11, 11, fffffff6, fffffff7, 11, 11,  }
+VTRN/VTRNQ:25:result_int16x4 [] = { fffffff2, fffffff3, 22, 22,  }
+VTRN/VTRNQ:26:result_int32x2 [] = { 33, 33,  }
+VTRN/VTRNQ:27:result_int64x1 [] = { 3333333333333333,  }
+VTRN/VTRNQ:28:result_uint8x8 [] = { f4, f5, 55, 55, f6, f7, 55, 55,  }
+VTRN/VTRNQ:29:result_uint16x4 [] = { fff2, fff3, 66, 66,  }
+VTRN/VTRNQ:30:result_uint32x2 [] = { 77, 77,  }
+VTRN/VTRNQ:31:result_uint64x1 [] = { 3333333333333333,  }
+VTRN/VTRNQ:32:result_poly8x8 [] = { f4, f5, 55, 55, f6, f7, 55, 55,  }
+VTRN/VTRNQ:33:result_poly16x4 [] = { fff2, fff3, 66, 66,  }
+VTRN/VTRNQ:34:result_float32x2 [] = { 42066666, 42066666,  }
+VTRN/VTRNQ:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VTRN/VTRNQ:36:result_int8x16 [] = { fffffff8, fffffff9, 11, 11, fffffffa, fffffffb, 11, 11, fffffffc, fffffffd, 11, 11, fffffffe, ffffffff, 11, 11,  }
+VTRN/VTRNQ:37:result_int16x8 [] = { fffffff4, fffffff5, 22, 22, fffffff6, fffffff7, 22, 22,  }
+VTRN/VTRNQ:38:result_int32x4 [] = { fffffff2, fffffff3, 33, 33,  }
+VTRN/VTRNQ:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTRN/VTRNQ:40:result_uint8x16 [] = { f8, f9, 55, 55, fa, fb, 55, 55, fc, fd, 55, 55, fe, ff, 55, 55,  }
+VTRN/VTRNQ:41:result_uint16x8 [] = { fff4, fff5, 66, 66, fff6, fff7, 66, 66,  }
+VTRN/VTRNQ:42:result_uint32x4 [] = { fffffff2, fffffff3, 77, 77,  }
+VTRN/VTRNQ:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTRN/VTRNQ:44:result_poly8x16 [] = { f8, f9, 55, 55, fa, fb, 55, 55, fc, fd, 55, 55, fe, ff, 55, 55,  }
+VTRN/VTRNQ:45:result_poly16x8 [] = { fff4, fff5, 66, 66, fff6, fff7, 66, 66,  }
+VTRN/VTRNQ:46:result_float32x4 [] = { c1600000, c1500000, 42073333, 42073333,  }
+VTRN/VTRNQ:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VUZP/VUZPQ chunk 0 output:
+VUZP/VUZPQ:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VUZP/VUZPQ:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VUZP/VUZPQ:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VUZP/VUZPQ:3:result_int64x1 [] = { 3333333333333333,  }
+VUZP/VUZPQ:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VUZP/VUZPQ:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VUZP/VUZPQ:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VUZP/VUZPQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VUZP/VUZPQ:8:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VUZP/VUZPQ:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VUZP/VUZPQ:10:result_float32x2 [] = { c1800000, c1700000,  }
+VUZP/VUZPQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VUZP/VUZPQ:12:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VUZP/VUZPQ:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VUZP/VUZPQ:14:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VUZP/VUZPQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VUZP/VUZPQ:16:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VUZP/VUZPQ:17:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VUZP/VUZPQ:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VUZP/VUZPQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VUZP/VUZPQ:20:result_poly8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VUZP/VUZPQ:21:result_poly16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VUZP/VUZPQ:22:result_float32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+VUZP/VUZPQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VUZP/VUZPQ chunk 1 output:
+VUZP/VUZPQ:24:result_int8x8 [] = { 11, 11, 11, 11, 11, 11, 11, 11,  }
+VUZP/VUZPQ:25:result_int16x4 [] = { 22, 22, 22, 22,  }
+VUZP/VUZPQ:26:result_int32x2 [] = { 33, 33,  }
+VUZP/VUZPQ:27:result_int64x1 [] = { 3333333333333333,  }
+VUZP/VUZPQ:28:result_uint8x8 [] = { 55, 55, 55, 55, 55, 55, 55, 55,  }
+VUZP/VUZPQ:29:result_uint16x4 [] = { 66, 66, 66, 66,  }
+VUZP/VUZPQ:30:result_uint32x2 [] = { 77, 77,  }
+VUZP/VUZPQ:31:result_uint64x1 [] = { 3333333333333333,  }
+VUZP/VUZPQ:32:result_poly8x8 [] = { 55, 55, 55, 55, 55, 55, 55, 55,  }
+VUZP/VUZPQ:33:result_poly16x4 [] = { 66, 66, 66, 66,  }
+VUZP/VUZPQ:34:result_float32x2 [] = { 42066666, 42066666,  }
+VUZP/VUZPQ:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VUZP/VUZPQ:36:result_int8x16 [] = { 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11,  }
+VUZP/VUZPQ:37:result_int16x8 [] = { 22, 22, 22, 22, 22, 22, 22, 22,  }
+VUZP/VUZPQ:38:result_int32x4 [] = { 33, 33, 33, 33,  }
+VUZP/VUZPQ:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VUZP/VUZPQ:40:result_uint8x16 [] = { 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55,  }
+VUZP/VUZPQ:41:result_uint16x8 [] = { 66, 66, 66, 66, 66, 66, 66, 66,  }
+VUZP/VUZPQ:42:result_uint32x4 [] = { 77, 77, 77, 77,  }
+VUZP/VUZPQ:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VUZP/VUZPQ:44:result_poly8x16 [] = { 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55,  }
+VUZP/VUZPQ:45:result_poly16x8 [] = { 66, 66, 66, 66, 66, 66, 66, 66,  }
+VUZP/VUZPQ:46:result_float32x4 [] = { 42073333, 42073333, 42073333, 42073333,  }
+VUZP/VUZPQ:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VZIP/VZIPQ chunk 0 output:
+VZIP/VZIPQ:0:result_int8x8 [] = { fffffff0, fffffff4, 11, 11, fffffff1, fffffff5, 11, 11,  }
+VZIP/VZIPQ:1:result_int16x4 [] = { fffffff0, fffffff2, 22, 22,  }
+VZIP/VZIPQ:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VZIP/VZIPQ:3:result_int64x1 [] = { 3333333333333333,  }
+VZIP/VZIPQ:4:result_uint8x8 [] = { f0, f4, 55, 55, f1, f5, 55, 55,  }
+VZIP/VZIPQ:5:result_uint16x4 [] = { fff0, fff2, 66, 66,  }
+VZIP/VZIPQ:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VZIP/VZIPQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VZIP/VZIPQ:8:result_poly8x8 [] = { f0, f4, 55, 55, f1, f5, 55, 55,  }
+VZIP/VZIPQ:9:result_poly16x4 [] = { fff0, fff2, 66, 66,  }
+VZIP/VZIPQ:10:result_float32x2 [] = { c1800000, c1700000,  }
+VZIP/VZIPQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VZIP/VZIPQ:12:result_int8x16 [] = { fffffff0, fffffff8, 11, 11, fffffff1, fffffff9, 11, 11, fffffff2, fffffffa, 11, 11, fffffff3, fffffffb, 11, 11,  }
+VZIP/VZIPQ:13:result_int16x8 [] = { fffffff0, fffffff4, 22, 22, fffffff1, fffffff5, 22, 22,  }
+VZIP/VZIPQ:14:result_int32x4 [] = { fffffff0, fffffff2, 33, 33,  }
+VZIP/VZIPQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VZIP/VZIPQ:16:result_uint8x16 [] = { f0, f8, 55, 55, f1, f9, 55, 55, f2, fa, 55, 55, f3, fb, 55, 55,  }
+VZIP/VZIPQ:17:result_uint16x8 [] = { fff0, fff4, 66, 66, fff1, fff5, 66, 66,  }
+VZIP/VZIPQ:18:result_uint32x4 [] = { fffffff0, fffffff2, 77, 77,  }
+VZIP/VZIPQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VZIP/VZIPQ:20:result_poly8x16 [] = { f0, f8, 55, 55, f1, f9, 55, 55, f2, fa, 55, 55, f3, fb, 55, 55,  }
+VZIP/VZIPQ:21:result_poly16x8 [] = { fff0, fff4, 66, 66, fff1, fff5, 66, 66,  }
+VZIP/VZIPQ:22:result_float32x4 [] = { c1800000, c1600000, 42073333, 42073333,  }
+VZIP/VZIPQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VZIP/VZIPQ chunk 1 output:
+VZIP/VZIPQ:24:result_int8x8 [] = { fffffff2, fffffff6, 11, 11, fffffff3, fffffff7, 11, 11,  }
+VZIP/VZIPQ:25:result_int16x4 [] = { fffffff1, fffffff3, 22, 22,  }
+VZIP/VZIPQ:26:result_int32x2 [] = { 33, 33,  }
+VZIP/VZIPQ:27:result_int64x1 [] = { 3333333333333333,  }
+VZIP/VZIPQ:28:result_uint8x8 [] = { f2, f6, 55, 55, f3, f7, 55, 55,  }
+VZIP/VZIPQ:29:result_uint16x4 [] = { fff1, fff3, 66, 66,  }
+VZIP/VZIPQ:30:result_uint32x2 [] = { 77, 77,  }
+VZIP/VZIPQ:31:result_uint64x1 [] = { 3333333333333333,  }
+VZIP/VZIPQ:32:result_poly8x8 [] = { f2, f6, 55, 55, f3, f7, 55, 55,  }
+VZIP/VZIPQ:33:result_poly16x4 [] = { fff1, fff3, 66, 66,  }
+VZIP/VZIPQ:34:result_float32x2 [] = { 42066666, 42066666,  }
+VZIP/VZIPQ:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VZIP/VZIPQ:36:result_int8x16 [] = { fffffff4, fffffffc, 11, 11, fffffff5, fffffffd, 11, 11, fffffff6, fffffffe, 11, 11, fffffff7, ffffffff, 11, 11,  }
+VZIP/VZIPQ:37:result_int16x8 [] = { fffffff2, fffffff6, 22, 22, fffffff3, fffffff7, 22, 22,  }
+VZIP/VZIPQ:38:result_int32x4 [] = { fffffff1, fffffff3, 33, 33,  }
+VZIP/VZIPQ:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VZIP/VZIPQ:40:result_uint8x16 [] = { f4, fc, 55, 55, f5, fd, 55, 55, f6, fe, 55, 55, f7, ff, 55, 55,  }
+VZIP/VZIPQ:41:result_uint16x8 [] = { fff2, fff6, 66, 66, fff3, fff7, 66, 66,  }
+VZIP/VZIPQ:42:result_uint32x4 [] = { fffffff1, fffffff3, 77, 77,  }
+VZIP/VZIPQ:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VZIP/VZIPQ:44:result_poly8x16 [] = { f4, fc, 55, 55, f5, fd, 55, 55, f6, fe, 55, 55, f7, ff, 55, 55,  }
+VZIP/VZIPQ:45:result_poly16x8 [] = { fff2, fff6, 66, 66, fff3, fff7, 66, 66,  }
+VZIP/VZIPQ:46:result_float32x4 [] = { c1700000, c1500000, 42073333, 42073333,  }
+VZIP/VZIPQ:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VREINTERPRET/VREINTERPRETQ output:
+VREINTERPRET/VREINTERPRETQ:0:result_int8x8 [] = { fffffff0, ffffffff, fffffff1, ffffffff, fffffff2, ffffffff, fffffff3, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:1:result_int8x8 [] = { fffffff0, ffffffff, ffffffff, ffffffff, fffffff1, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:2:result_int8x8 [] = { fffffff0, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:3:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VREINTERPRET/VREINTERPRETQ:4:result_int8x8 [] = { fffffff0, ffffffff, fffffff1, ffffffff, fffffff2, ffffffff, fffffff3, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:5:result_int8x8 [] = { fffffff0, ffffffff, ffffffff, ffffffff, fffffff1, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:6:result_int8x8 [] = { fffffff0, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:7:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VREINTERPRET/VREINTERPRETQ:8:result_int8x8 [] = { fffffff0, ffffffff, fffffff1, ffffffff, fffffff2, ffffffff, fffffff3, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:9:result_int16x4 [] = { fffff1f0, fffff3f2, fffff5f4, fffff7f6,  }
+VREINTERPRET/VREINTERPRETQ:10:result_int16x4 [] = { fffffff0, ffffffff, fffffff1, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:11:result_int16x4 [] = { fffffff0, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:12:result_int16x4 [] = { fffff1f0, fffff3f2, fffff5f4, fffff7f6,  }
+VREINTERPRET/VREINTERPRETQ:13:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VREINTERPRET/VREINTERPRETQ:14:result_int16x4 [] = { fffffff0, ffffffff, fffffff1, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:15:result_int16x4 [] = { fffffff0, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:16:result_int16x4 [] = { fffff1f0, fffff3f2, fffff5f4, fffff7f6,  }
+VREINTERPRET/VREINTERPRETQ:17:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VREINTERPRET/VREINTERPRETQ:18:result_int32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:19:result_int32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:20:result_int32x2 [] = { fffffff0, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:21:result_int32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:22:result_int32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:23:result_int32x2 [] = { fffffff0, fffffff1,  }
+VREINTERPRET/VREINTERPRETQ:24:result_int32x2 [] = { fffffff0, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:25:result_int32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:26:result_int32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:27:result_int64x1 [] = { f7f6f5f4f3f2f1f0,  }
+VREINTERPRET/VREINTERPRETQ:28:result_int64x1 [] = { fff3fff2fff1fff0,  }
+VREINTERPRET/VREINTERPRETQ:29:result_int64x1 [] = { fffffff1fffffff0,  }
+VREINTERPRET/VREINTERPRETQ:30:result_int64x1 [] = { f7f6f5f4f3f2f1f0,  }
+VREINTERPRET/VREINTERPRETQ:31:result_int64x1 [] = { fff3fff2fff1fff0,  }
+VREINTERPRET/VREINTERPRETQ:32:result_int64x1 [] = { fffffff1fffffff0,  }
+VREINTERPRET/VREINTERPRETQ:33:result_int64x1 [] = { fffffffffffffff0,  }
+VREINTERPRET/VREINTERPRETQ:34:result_int64x1 [] = { f7f6f5f4f3f2f1f0,  }
+VREINTERPRET/VREINTERPRETQ:35:result_int64x1 [] = { fff3fff2fff1fff0,  }
+VREINTERPRET/VREINTERPRETQ:36:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VREINTERPRET/VREINTERPRETQ:37:result_uint8x8 [] = { f0, ff, f1, ff, f2, ff, f3, ff,  }
+VREINTERPRET/VREINTERPRETQ:38:result_uint8x8 [] = { f0, ff, ff, ff, f1, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:39:result_uint8x8 [] = { f0, ff, ff, ff, ff, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:40:result_uint8x8 [] = { f0, ff, f1, ff, f2, ff, f3, ff,  }
+VREINTERPRET/VREINTERPRETQ:41:result_uint8x8 [] = { f0, ff, ff, ff, f1, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:42:result_uint8x8 [] = { f0, ff, ff, ff, ff, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:43:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VREINTERPRET/VREINTERPRETQ:44:result_uint8x8 [] = { f0, ff, f1, ff, f2, ff, f3, ff,  }
+VREINTERPRET/VREINTERPRETQ:45:result_uint16x4 [] = { f1f0, f3f2, f5f4, f7f6,  }
+VREINTERPRET/VREINTERPRETQ:46:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VREINTERPRET/VREINTERPRETQ:47:result_uint16x4 [] = { fff0, ffff, fff1, ffff,  }
+VREINTERPRET/VREINTERPRETQ:48:result_uint16x4 [] = { fff0, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:49:result_uint16x4 [] = { f1f0, f3f2, f5f4, f7f6,  }
+VREINTERPRET/VREINTERPRETQ:50:result_uint16x4 [] = { fff0, ffff, fff1, ffff,  }
+VREINTERPRET/VREINTERPRETQ:51:result_uint16x4 [] = { fff0, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:52:result_uint16x4 [] = { f1f0, f3f2, f5f4, f7f6,  }
+VREINTERPRET/VREINTERPRETQ:53:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VREINTERPRET/VREINTERPRETQ:54:result_uint32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:55:result_uint32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:56:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VREINTERPRET/VREINTERPRETQ:57:result_uint32x2 [] = { fffffff0, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:58:result_uint32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:59:result_uint32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:60:result_uint32x2 [] = { fffffff0, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:61:result_uint32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:62:result_uint32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:63:result_uint64x1 [] = { f7f6f5f4f3f2f1f0,  }
+VREINTERPRET/VREINTERPRETQ:64:result_uint64x1 [] = { fff3fff2fff1fff0,  }
+VREINTERPRET/VREINTERPRETQ:65:result_uint64x1 [] = { fffffff1fffffff0,  }
+VREINTERPRET/VREINTERPRETQ:66:result_uint64x1 [] = { fffffffffffffff0,  }
+VREINTERPRET/VREINTERPRETQ:67:result_uint64x1 [] = { f7f6f5f4f3f2f1f0,  }
+VREINTERPRET/VREINTERPRETQ:68:result_uint64x1 [] = { fff3fff2fff1fff0,  }
+VREINTERPRET/VREINTERPRETQ:69:result_uint64x1 [] = { fffffff1fffffff0,  }
+VREINTERPRET/VREINTERPRETQ:70:result_uint64x1 [] = { f7f6f5f4f3f2f1f0,  }
+VREINTERPRET/VREINTERPRETQ:71:result_uint64x1 [] = { fff3fff2fff1fff0,  }
+VREINTERPRET/VREINTERPRETQ:72:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VREINTERPRET/VREINTERPRETQ:73:result_poly8x8 [] = { f0, ff, f1, ff, f2, ff, f3, ff,  }
+VREINTERPRET/VREINTERPRETQ:74:result_poly8x8 [] = { f0, ff, ff, ff, f1, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:75:result_poly8x8 [] = { f0, ff, ff, ff, ff, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:76:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VREINTERPRET/VREINTERPRETQ:77:result_poly8x8 [] = { f0, ff, f1, ff, f2, ff, f3, ff,  }
+VREINTERPRET/VREINTERPRETQ:78:result_poly8x8 [] = { f0, ff, ff, ff, f1, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:79:result_poly8x8 [] = { f0, ff, ff, ff, ff, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:80:result_poly8x8 [] = { f0, ff, f1, ff, f2, ff, f3, ff,  }
+VREINTERPRET/VREINTERPRETQ:81:result_poly16x4 [] = { f1f0, f3f2, f5f4, f7f6,  }
+VREINTERPRET/VREINTERPRETQ:82:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VREINTERPRET/VREINTERPRETQ:83:result_poly16x4 [] = { fff0, ffff, fff1, ffff,  }
+VREINTERPRET/VREINTERPRETQ:84:result_poly16x4 [] = { fff0, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:85:result_poly16x4 [] = { f1f0, f3f2, f5f4, f7f6,  }
+VREINTERPRET/VREINTERPRETQ:86:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VREINTERPRET/VREINTERPRETQ:87:result_poly16x4 [] = { fff0, ffff, fff1, ffff,  }
+VREINTERPRET/VREINTERPRETQ:88:result_poly16x4 [] = { fff0, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:89:result_poly16x4 [] = { f1f0, f3f2, f5f4, f7f6,  }
+VREINTERPRET/VREINTERPRETQ:90:result_int8x16 [] = { fffffff0, ffffffff, fffffff1, ffffffff, fffffff2, ffffffff, fffffff3, ffffffff, fffffff4, ffffffff, fffffff5, ffffffff, fffffff6, ffffffff, fffffff7, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:91:result_int8x16 [] = { fffffff0, ffffffff, ffffffff, ffffffff, fffffff1, ffffffff, ffffffff, ffffffff, fffffff2, ffffffff, ffffffff, ffffffff, fffffff3, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:92:result_int8x16 [] = { fffffff0, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, fffffff1, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:93:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:94:result_int8x16 [] = { fffffff0, ffffffff, fffffff1, ffffffff, fffffff2, ffffffff, fffffff3, ffffffff, fffffff4, ffffffff, fffffff5, ffffffff, fffffff6, ffffffff, fffffff7, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:95:result_int8x16 [] = { fffffff0, ffffffff, ffffffff, ffffffff, fffffff1, ffffffff, ffffffff, ffffffff, fffffff2, ffffffff, ffffffff, ffffffff, fffffff3, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:96:result_int8x16 [] = { fffffff0, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, fffffff1, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:97:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:98:result_int8x16 [] = { fffffff0, ffffffff, fffffff1, ffffffff, fffffff2, ffffffff, fffffff3, ffffffff, fffffff4, ffffffff, fffffff5, ffffffff, fffffff6, ffffffff, fffffff7, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:99:result_int16x8 [] = { fffff1f0, fffff3f2, fffff5f4, fffff7f6, fffff9f8, fffffbfa, fffffdfc, fffffffe,  }
+VREINTERPRET/VREINTERPRETQ:100:result_int16x8 [] = { fffffff0, ffffffff, fffffff1, ffffffff, fffffff2, ffffffff, fffffff3, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:101:result_int16x8 [] = { fffffff0, ffffffff, ffffffff, ffffffff, fffffff1, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:102:result_int16x8 [] = { fffff1f0, fffff3f2, fffff5f4, fffff7f6, fffff9f8, fffffbfa, fffffdfc, fffffffe,  }
+VREINTERPRET/VREINTERPRETQ:103:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VREINTERPRET/VREINTERPRETQ:104:result_int16x8 [] = { fffffff0, ffffffff, fffffff1, ffffffff, fffffff2, ffffffff, fffffff3, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:105:result_int16x8 [] = { fffffff0, ffffffff, ffffffff, ffffffff, fffffff1, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:106:result_int16x8 [] = { fffff1f0, fffff3f2, fffff5f4, fffff7f6, fffff9f8, fffffbfa, fffffdfc, fffffffe,  }
+VREINTERPRET/VREINTERPRETQ:107:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VREINTERPRET/VREINTERPRETQ:108:result_int32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:109:result_int32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:110:result_int32x4 [] = { fffffff0, ffffffff, fffffff1, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:111:result_int32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:112:result_int32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:113:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VREINTERPRET/VREINTERPRETQ:114:result_int32x4 [] = { fffffff0, ffffffff, fffffff1, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:115:result_int32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:116:result_int32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:117:result_int64x2 [] = { f7f6f5f4f3f2f1f0, fffefdfcfbfaf9f8,  }
+VREINTERPRET/VREINTERPRETQ:118:result_int64x2 [] = { fff3fff2fff1fff0, fff7fff6fff5fff4,  }
+VREINTERPRET/VREINTERPRETQ:119:result_int64x2 [] = { fffffff1fffffff0, fffffff3fffffff2,  }
+VREINTERPRET/VREINTERPRETQ:120:result_int64x2 [] = { f7f6f5f4f3f2f1f0, fffefdfcfbfaf9f8,  }
+VREINTERPRET/VREINTERPRETQ:121:result_int64x2 [] = { fff3fff2fff1fff0, fff7fff6fff5fff4,  }
+VREINTERPRET/VREINTERPRETQ:122:result_int64x2 [] = { fffffff1fffffff0, fffffff3fffffff2,  }
+VREINTERPRET/VREINTERPRETQ:123:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VREINTERPRET/VREINTERPRETQ:124:result_int64x2 [] = { f7f6f5f4f3f2f1f0, fffefdfcfbfaf9f8,  }
+VREINTERPRET/VREINTERPRETQ:125:result_int64x2 [] = { fff3fff2fff1fff0, fff7fff6fff5fff4,  }
+VREINTERPRET/VREINTERPRETQ:126:result_uint16x8 [] = { f1f0, f3f2, f5f4, f7f6, f9f8, fbfa, fdfc, fffe,  }
+VREINTERPRET/VREINTERPRETQ:127:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VREINTERPRET/VREINTERPRETQ:128:result_uint16x8 [] = { fff0, ffff, fff1, ffff, fff2, ffff, fff3, ffff,  }
+VREINTERPRET/VREINTERPRETQ:129:result_uint16x8 [] = { fff0, ffff, ffff, ffff, fff1, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:130:result_uint16x8 [] = { f1f0, f3f2, f5f4, f7f6, f9f8, fbfa, fdfc, fffe,  }
+VREINTERPRET/VREINTERPRETQ:131:result_uint16x8 [] = { fff0, ffff, fff1, ffff, fff2, ffff, fff3, ffff,  }
+VREINTERPRET/VREINTERPRETQ:132:result_uint16x8 [] = { fff0, ffff, ffff, ffff, fff1, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:133:result_uint16x8 [] = { f1f0, f3f2, f5f4, f7f6, f9f8, fbfa, fdfc, fffe,  }
+VREINTERPRET/VREINTERPRETQ:134:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VREINTERPRET/VREINTERPRETQ:135:result_uint32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:136:result_uint32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:137:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VREINTERPRET/VREINTERPRETQ:138:result_uint32x4 [] = { fffffff0, ffffffff, fffffff1, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:139:result_uint32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:140:result_uint32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:141:result_uint32x4 [] = { fffffff0, ffffffff, fffffff1, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:142:result_uint32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:143:result_uint32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:144:result_uint64x2 [] = { f7f6f5f4f3f2f1f0, fffefdfcfbfaf9f8,  }
+VREINTERPRET/VREINTERPRETQ:145:result_uint64x2 [] = { fff3fff2fff1fff0, fff7fff6fff5fff4,  }
+VREINTERPRET/VREINTERPRETQ:146:result_uint64x2 [] = { fffffff1fffffff0, fffffff3fffffff2,  }
+VREINTERPRET/VREINTERPRETQ:147:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VREINTERPRET/VREINTERPRETQ:148:result_uint64x2 [] = { f7f6f5f4f3f2f1f0, fffefdfcfbfaf9f8,  }
+VREINTERPRET/VREINTERPRETQ:149:result_uint64x2 [] = { fff3fff2fff1fff0, fff7fff6fff5fff4,  }
+VREINTERPRET/VREINTERPRETQ:150:result_uint64x2 [] = { fffffff1fffffff0, fffffff3fffffff2,  }
+VREINTERPRET/VREINTERPRETQ:151:result_uint64x2 [] = { f7f6f5f4f3f2f1f0, fffefdfcfbfaf9f8,  }
+VREINTERPRET/VREINTERPRETQ:152:result_uint64x2 [] = { fff3fff2fff1fff0, fff7fff6fff5fff4,  }
+VREINTERPRET/VREINTERPRETQ:153:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VREINTERPRET/VREINTERPRETQ:154:result_uint8x16 [] = { f0, ff, f1, ff, f2, ff, f3, ff, f4, ff, f5, ff, f6, ff, f7, ff,  }
+VREINTERPRET/VREINTERPRETQ:155:result_uint8x16 [] = { f0, ff, ff, ff, f1, ff, ff, ff, f2, ff, ff, ff, f3, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:156:result_uint8x16 [] = { f0, ff, ff, ff, ff, ff, ff, ff, f1, ff, ff, ff, ff, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:157:result_uint8x16 [] = { f0, ff, f1, ff, f2, ff, f3, ff, f4, ff, f5, ff, f6, ff, f7, ff,  }
+VREINTERPRET/VREINTERPRETQ:158:result_uint8x16 [] = { f0, ff, ff, ff, f1, ff, ff, ff, f2, ff, ff, ff, f3, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:159:result_uint8x16 [] = { f0, ff, ff, ff, ff, ff, ff, ff, f1, ff, ff, ff, ff, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:160:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VREINTERPRET/VREINTERPRETQ:161:result_uint8x16 [] = { f0, ff, f1, ff, f2, ff, f3, ff, f4, ff, f5, ff, f6, ff, f7, ff,  }
+VREINTERPRET/VREINTERPRETQ:162:result_float32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:163:result_float32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:164:result_float32x2 [] = { fffffff0, fffffff1,  }
+VREINTERPRET/VREINTERPRETQ:165:result_float32x2 [] = { fffffff0, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:166:result_float32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:167:result_float32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:168:result_float32x2 [] = { fffffff0, fffffff1,  }
+VREINTERPRET/VREINTERPRETQ:169:result_float32x2 [] = { fffffff0, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:170:result_float32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:171:result_float32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:172:result_float32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:173:result_float32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:174:result_float32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VREINTERPRET/VREINTERPRETQ:175:result_float32x4 [] = { fffffff0, ffffffff, fffffff1, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:176:result_float32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:177:result_float32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:178:result_float32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VREINTERPRET/VREINTERPRETQ:179:result_float32x4 [] = { fffffff0, ffffffff, fffffff1, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:180:result_float32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:181:result_float32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:182:result_int8x8 [] = { 0, 0, ffffff80, ffffffc1, 0, 0, 70, ffffffc1,  }
+VREINTERPRET/VREINTERPRETQ:183:result_int16x4 [] = { 0, ffffc180, 0, ffffc170,  }
+VREINTERPRET/VREINTERPRETQ:184:result_int32x2 [] = { c1800000, c1700000,  }
+VREINTERPRET/VREINTERPRETQ:185:result_int64x1 [] = { c1700000c1800000,  }
+VREINTERPRET/VREINTERPRETQ:186:result_uint8x8 [] = { 0, 0, 80, c1, 0, 0, 70, c1,  }
+VREINTERPRET/VREINTERPRETQ:187:result_uint16x4 [] = { 0, c180, 0, c170,  }
+VREINTERPRET/VREINTERPRETQ:188:result_uint32x2 [] = { c1800000, c1700000,  }
+VREINTERPRET/VREINTERPRETQ:189:result_uint64x1 [] = { c1700000c1800000,  }
+VREINTERPRET/VREINTERPRETQ:190:result_poly8x8 [] = { 0, 0, 80, c1, 0, 0, 70, c1,  }
+VREINTERPRET/VREINTERPRETQ:191:result_poly16x4 [] = { 0, c180, 0, c170,  }
+VREINTERPRET/VREINTERPRETQ:192:result_int8x16 [] = { 0, 0, ffffff80, ffffffc1, 0, 0, 70, ffffffc1, 0, 0, 60, ffffffc1, 0, 0, 50, ffffffc1,  }
+VREINTERPRET/VREINTERPRETQ:193:result_int16x8 [] = { 0, ffffc180, 0, ffffc170, 0, ffffc160, 0, ffffc150,  }
+VREINTERPRET/VREINTERPRETQ:194:result_int32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+VREINTERPRET/VREINTERPRETQ:195:result_int64x2 [] = { c1700000c1800000, c1500000c1600000,  }
+VREINTERPRET/VREINTERPRETQ:196:result_uint8x16 [] = { 0, 0, 80, c1, 0, 0, 70, c1, 0, 0, 60, c1, 0, 0, 50, c1,  }
+VREINTERPRET/VREINTERPRETQ:197:result_uint16x8 [] = { 0, c180, 0, c170, 0, c160, 0, c150,  }
+VREINTERPRET/VREINTERPRETQ:198:result_uint32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+VREINTERPRET/VREINTERPRETQ:199:result_uint64x2 [] = { c1700000c1800000, c1500000c1600000,  }
+VREINTERPRET/VREINTERPRETQ:200:result_poly8x16 [] = { 0, 0, 80, c1, 0, 0, 70, c1, 0, 0, 60, c1, 0, 0, 50, c1,  }
+VREINTERPRET/VREINTERPRETQ:201:result_poly16x8 [] = { 0, c180, 0, c170, 0, c160, 0, c150,  }
+VREINTERPRET/VREINTERPRETQ:202:result_float16x4 [] = { f1f0, f3f2, f5f4, f7f6,  }
+VREINTERPRET/VREINTERPRETQ:203:result_float16x4 [] = { fff0, fff1, fff2, fff3,  }
+VREINTERPRET/VREINTERPRETQ:204:result_float16x4 [] = { fff0, ffff, fff1, ffff,  }
+VREINTERPRET/VREINTERPRETQ:205:result_float16x4 [] = { fff0, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:206:result_float16x4 [] = { f1f0, f3f2, f5f4, f7f6,  }
+VREINTERPRET/VREINTERPRETQ:207:result_float16x4 [] = { fff0, fff1, fff2, fff3,  }
+VREINTERPRET/VREINTERPRETQ:208:result_float16x4 [] = { fff0, ffff, fff1, ffff,  }
+VREINTERPRET/VREINTERPRETQ:209:result_float16x4 [] = { fff0, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:210:result_float16x4 [] = { f1f0, f3f2, f5f4, f7f6,  }
+VREINTERPRET/VREINTERPRETQ:211:result_float16x4 [] = { fff0, fff1, fff2, fff3,  }
+VREINTERPRET/VREINTERPRETQ:212:result_float16x4 [] = { 0, c180, 0, c170,  }
+VREINTERPRET/VREINTERPRETQ:213:result_float16x8 [] = { f1f0, f3f2, f5f4, f7f6, f9f8, fbfa, fdfc, fffe,  }
+VREINTERPRET/VREINTERPRETQ:214:result_float16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VREINTERPRET/VREINTERPRETQ:215:result_float16x8 [] = { fff0, ffff, fff1, ffff, fff2, ffff, fff3, ffff,  }
+VREINTERPRET/VREINTERPRETQ:216:result_float16x8 [] = { fff0, ffff, ffff, ffff, fff1, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:217:result_float16x8 [] = { f1f0, f3f2, f5f4, f7f6, f9f8, fbfa, fdfc, fffe,  }
+VREINTERPRET/VREINTERPRETQ:218:result_float16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VREINTERPRET/VREINTERPRETQ:219:result_float16x8 [] = { fff0, ffff, fff1, ffff, fff2, ffff, fff3, ffff,  }
+VREINTERPRET/VREINTERPRETQ:220:result_float16x8 [] = { fff0, ffff, ffff, ffff, fff1, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:221:result_float16x8 [] = { f1f0, f3f2, f5f4, f7f6, f9f8, fbfa, fdfc, fffe,  }
+VREINTERPRET/VREINTERPRETQ:222:result_float16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VREINTERPRET/VREINTERPRETQ:223:result_float16x8 [] = { 0, c180, 0, c170, 0, c160, 0, c150,  }
+VREINTERPRET/VREINTERPRETQ:224:result_int8x8 [] = { 0, ffffffcc, ffffff80, ffffffcb, 0, ffffffcb, ffffff80, ffffffca,  }
+VREINTERPRET/VREINTERPRETQ:225:result_int16x4 [] = { ffffcc00, ffffcb80, ffffcb00, ffffca80,  }
+VREINTERPRET/VREINTERPRETQ:226:result_int32x2 [] = { cb80cc00, ca80cb00,  }
+VREINTERPRET/VREINTERPRETQ:227:result_int64x1 [] = { ca80cb00cb80cc00,  }
+VREINTERPRET/VREINTERPRETQ:228:result_uint8x8 [] = { 0, cc, 80, cb, 0, cb, 80, ca,  }
+VREINTERPRET/VREINTERPRETQ:229:result_uint16x4 [] = { cc00, cb80, cb00, ca80,  }
+VREINTERPRET/VREINTERPRETQ:230:result_uint32x2 [] = { cb80cc00, ca80cb00,  }
+VREINTERPRET/VREINTERPRETQ:231:result_uint64x1 [] = { ca80cb00cb80cc00,  }
+VREINTERPRET/VREINTERPRETQ:232:result_poly8x8 [] = { 0, cc, 80, cb, 0, cb, 80, ca,  }
+VREINTERPRET/VREINTERPRETQ:233:result_poly16x4 [] = { cc00, cb80, cb00, ca80,  }
+VREINTERPRET/VREINTERPRETQ:234:result_float32x2 [] = { cb80cc00, ca80cb00,  }
+VREINTERPRET/VREINTERPRETQ:235:result_int8x16 [] = { 0, ffffffcc, ffffff80, ffffffcb, 0, ffffffcb, ffffff80, ffffffca, 0, ffffffca, ffffff80, ffffffc9, 0, ffffffc9, ffffff80, ffffffc8,  }
+VREINTERPRET/VREINTERPRETQ:236:result_int16x8 [] = { ffffcc00, ffffcb80, ffffcb00, ffffca80, ffffca00, ffffc980, ffffc900, ffffc880,  }
+VREINTERPRET/VREINTERPRETQ:237:result_int32x4 [] = { cb80cc00, ca80cb00, c980ca00, c880c900,  }
+VREINTERPRET/VREINTERPRETQ:238:result_int64x2 [] = { ca80cb00cb80cc00, c880c900c980ca00,  }
+VREINTERPRET/VREINTERPRETQ:239:result_uint8x16 [] = { 0, cc, 80, cb, 0, cb, 80, ca, 0, ca, 80, c9, 0, c9, 80, c8,  }
+VREINTERPRET/VREINTERPRETQ:240:result_uint16x8 [] = { cc00, cb80, cb00, ca80, ca00, c980, c900, c880,  }
+VREINTERPRET/VREINTERPRETQ:241:result_uint32x4 [] = { cb80cc00, ca80cb00, c980ca00, c880c900,  }
+VREINTERPRET/VREINTERPRETQ:242:result_uint64x2 [] = { ca80cb00cb80cc00, c880c900c980ca00,  }
+VREINTERPRET/VREINTERPRETQ:243:result_poly8x16 [] = { 0, cc, 80, cb, 0, cb, 80, ca, 0, ca, 80, c9, 0, c9, 80, c8,  }
+VREINTERPRET/VREINTERPRETQ:244:result_poly16x8 [] = { cc00, cb80, cb00, ca80, ca00, c980, c900, c880,  }
+VREINTERPRET/VREINTERPRETQ:245:result_float32x4 [] = { cb80cc00, ca80cb00, c980ca00, c880c900,  }
+
+VQRDMULH cumulative saturation output:
+VQRDMULH:0:vqrdmulh_s16 Neon cumulative saturation 0
+VQRDMULH:1:vqrdmulh_s32 Neon cumulative saturation 0
+VQRDMULH:2:vqrdmulhq_s16 Neon cumulative saturation 0
+VQRDMULH:3:vqrdmulhq_s32 Neon cumulative saturation 0
+
+VQRDMULH output:
+VQRDMULH:4:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:5:result_int16x4 [] = { fffffff5, fffffff6, fffffff7, fffffff7,  }
+VQRDMULH:6:result_int32x2 [] = { 0, 0,  }
+VQRDMULH:7:result_int64x1 [] = { 3333333333333333,  }
+VQRDMULH:8:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:9:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH:10:result_uint32x2 [] = { 33333333, 33333333,  }
+VQRDMULH:11:result_uint64x1 [] = { 3333333333333333,  }
+VQRDMULH:12:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:13:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH:14:result_float32x2 [] = { 33333333, 33333333,  }
+VQRDMULH:15:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH:16:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:17:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRDMULH:18:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH:19:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH:20:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:21:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH:22:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH:23:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH:24:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:25:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH:26:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH:27:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRDMULH (check mul cumulative saturation) cumulative saturation output:
+VQRDMULH:28:vqrdmulh_s16 Neon cumulative saturation 1
+VQRDMULH:29:vqrdmulh_s32 Neon cumulative saturation 1
+VQRDMULH:30:vqrdmulhq_s16 Neon cumulative saturation 1
+VQRDMULH:31:vqrdmulhq_s32 Neon cumulative saturation 1
+
+VQRDMULH (check mul cumulative saturation) output:
+VQRDMULH:32:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:33:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH:34:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRDMULH:35:result_int64x1 [] = { 3333333333333333,  }
+VQRDMULH:36:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:37:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH:38:result_uint32x2 [] = { 33333333, 33333333,  }
+VQRDMULH:39:result_uint64x1 [] = { 3333333333333333,  }
+VQRDMULH:40:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:41:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH:42:result_float32x2 [] = { 33333333, 33333333,  }
+VQRDMULH:43:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH:44:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:45:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH:46:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQRDMULH:47:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH:48:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:49:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH:50:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH:51:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH:52:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:53:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH:54:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH:55:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRDMULH (check rounding cumulative saturation) cumulative saturation output:
+VQRDMULH:56:vqrdmulh_s16 Neon cumulative saturation 0
+VQRDMULH:57:vqrdmulh_s32 Neon cumulative saturation 0
+VQRDMULH:58:vqrdmulhq_s16 Neon cumulative saturation 0
+VQRDMULH:59:vqrdmulhq_s32 Neon cumulative saturation 0
+
+VQRDMULH (check rounding cumulative saturation) output:
+VQRDMULH:60:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:61:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH:62:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRDMULH:63:result_int64x1 [] = { 3333333333333333,  }
+VQRDMULH:64:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:65:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH:66:result_uint32x2 [] = { 33333333, 33333333,  }
+VQRDMULH:67:result_uint64x1 [] = { 3333333333333333,  }
+VQRDMULH:68:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:69:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH:70:result_float32x2 [] = { 33333333, 33333333,  }
+VQRDMULH:71:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH:72:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:73:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH:74:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQRDMULH:75:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH:76:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:77:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH:78:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH:79:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH:80:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:81:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH:82:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH:83:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRDMULH_LANE cumulative saturation output:
+VQRDMULH_LANE:0:vqrdmulh_lane_s16 Neon cumulative saturation 0
+VQRDMULH_LANE:1:vqrdmulh_lane_s32 Neon cumulative saturation 0
+VQRDMULH_LANE:2:vqrdmulhq_lane_s16 Neon cumulative saturation 0
+VQRDMULH_LANE:3:vqrdmulhq_lane_s32 Neon cumulative saturation 0
+
+VQRDMULH_LANE output:
+VQRDMULH_LANE:4:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:5:result_int16x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH_LANE:6:result_int32x2 [] = { 0, 0,  }
+VQRDMULH_LANE:7:result_int64x1 [] = { 3333333333333333,  }
+VQRDMULH_LANE:8:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:9:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:10:result_uint32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_LANE:11:result_uint64x1 [] = { 3333333333333333,  }
+VQRDMULH_LANE:12:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:13:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:14:result_float32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_LANE:15:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH_LANE:16:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:17:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRDMULH_LANE:18:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH_LANE:19:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_LANE:20:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:21:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:22:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_LANE:23:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_LANE:24:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:25:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:26:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_LANE:27:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRDMULH_LANE (check mul cumulative saturation) cumulative saturation output:
+VQRDMULH_LANE:28:vqrdmulh_lane_s16 Neon cumulative saturation 1
+VQRDMULH_LANE:29:vqrdmulh_lane_s32 Neon cumulative saturation 1
+VQRDMULH_LANE:30:vqrdmulhq_lane_s16 Neon cumulative saturation 1
+VQRDMULH_LANE:31:vqrdmulhq_lane_s32 Neon cumulative saturation 1
+
+VQRDMULH_LANE (check mul cumulative saturation) output:
+VQRDMULH_LANE:32:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:33:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH_LANE:34:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRDMULH_LANE:35:result_int64x1 [] = { 3333333333333333,  }
+VQRDMULH_LANE:36:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:37:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:38:result_uint32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_LANE:39:result_uint64x1 [] = { 3333333333333333,  }
+VQRDMULH_LANE:40:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:41:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:42:result_float32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_LANE:43:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH_LANE:44:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:45:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH_LANE:46:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQRDMULH_LANE:47:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_LANE:48:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:49:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:50:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_LANE:51:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_LANE:52:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:53:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:54:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_LANE:55:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRDMULH_LANE (check rounding cumulative saturation) cumulative saturation output:
+VQRDMULH_LANE:56:vqrdmulh_lane_s16 Neon cumulative saturation 0
+VQRDMULH_LANE:57:vqrdmulh_lane_s32 Neon cumulative saturation 0
+VQRDMULH_LANE:58:vqrdmulhq_lane_s16 Neon cumulative saturation 0
+VQRDMULH_LANE:59:vqrdmulhq_lane_s32 Neon cumulative saturation 0
+
+VQRDMULH_LANE (check rounding cumulative saturation) output:
+VQRDMULH_LANE:60:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:61:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH_LANE:62:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRDMULH_LANE:63:result_int64x1 [] = { 3333333333333333,  }
+VQRDMULH_LANE:64:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:65:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:66:result_uint32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_LANE:67:result_uint64x1 [] = { 3333333333333333,  }
+VQRDMULH_LANE:68:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:69:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:70:result_float32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_LANE:71:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH_LANE:72:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:73:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH_LANE:74:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQRDMULH_LANE:75:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_LANE:76:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:77:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:78:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_LANE:79:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_LANE:80:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:81:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:82:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_LANE:83:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRDMULH_N cumulative saturation output:
+VQRDMULH_N:0:vqrdmulh_n_s16 Neon cumulative saturation 0
+VQRDMULH_N:1:vqrdmulh_n_s32 Neon cumulative saturation 0
+VQRDMULH_N:2:vqrdmulhq_n_s16 Neon cumulative saturation 0
+VQRDMULH_N:3:vqrdmulhq_n_s32 Neon cumulative saturation 0
+
+VQRDMULH_N output:
+VQRDMULH_N:4:result_int16x4 [] = { fffffffc, fffffffc, fffffffc, fffffffd,  }
+VQRDMULH_N:5:result_int32x2 [] = { fffffffe, fffffffe,  }
+VQRDMULH_N:6:result_int16x8 [] = { 6, 6, 6, 5, 5, 4, 4, 4,  }
+VQRDMULH_N:7:result_int32x4 [] = { fffffffe, fffffffe, fffffffe, fffffffe,  }
+
+VQRDMULH_N (check mul cumulative saturation) cumulative saturation output:
+VQRDMULH_N:8:vqrdmulh_n_s16 Neon cumulative saturation 1
+VQRDMULH_N:9:vqrdmulh_n_s32 Neon cumulative saturation 1
+VQRDMULH_N:10:vqrdmulhq_n_s16 Neon cumulative saturation 1
+VQRDMULH_N:11:vqrdmulhq_n_s32 Neon cumulative saturation 1
+
+VQRDMULH_N (check mul cumulative saturation) output:
+VQRDMULH_N:12:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:13:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH_N:14:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRDMULH_N:15:result_int64x1 [] = { 3333333333333333,  }
+VQRDMULH_N:16:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:17:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_N:18:result_uint32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_N:19:result_uint64x1 [] = { 3333333333333333,  }
+VQRDMULH_N:20:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:21:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_N:22:result_float32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_N:23:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH_N:24:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:25:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH_N:26:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQRDMULH_N:27:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_N:28:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:29:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_N:30:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_N:31:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_N:32:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:33:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_N:34:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_N:35:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRDMULH_N (check rounding cumulative saturation) cumulative saturation output:
+VQRDMULH_N:36:vqrdmulh_n_s16 Neon cumulative saturation 0
+VQRDMULH_N:37:vqrdmulh_n_s32 Neon cumulative saturation 0
+VQRDMULH_N:38:vqrdmulhq_n_s16 Neon cumulative saturation 0
+VQRDMULH_N:39:vqrdmulhq_n_s32 Neon cumulative saturation 0
+
+VQRDMULH_N (check rounding cumulative saturation) output:
+VQRDMULH_N:40:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:41:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH_N:42:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRDMULH_N:43:result_int64x1 [] = { 3333333333333333,  }
+VQRDMULH_N:44:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:45:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_N:46:result_uint32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_N:47:result_uint64x1 [] = { 3333333333333333,  }
+VQRDMULH_N:48:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:49:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_N:50:result_float32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_N:51:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH_N:52:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:53:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH_N:54:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQRDMULH_N:55:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_N:56:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:57:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_N:58:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_N:59:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_N:60:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:61:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_N:62:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_N:63:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHL/VQRSHLQ (with input = 0) cumulative saturation output:
+VQRSHL/VQRSHLQ:0:vqrshl_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:1:vqrshl_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:2:vqrshl_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:3:vqrshl_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:4:vqrshl_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:5:vqrshl_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:6:vqrshl_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:7:vqrshl_u64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:8:vqrshlq_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:9:vqrshlq_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:10:vqrshlq_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:11:vqrshlq_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:12:vqrshlq_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:13:vqrshlq_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:14:vqrshlq_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:15:vqrshlq_u64 Neon cumulative saturation 0
+
+VQRSHL/VQRSHLQ (with input = 0) output:
+VQRSHL/VQRSHLQ:16:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:17:result_int16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:18:result_int32x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:19:result_int64x1 [] = { 0,  }
+VQRSHL/VQRSHLQ:20:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:21:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:22:result_uint32x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:23:result_uint64x1 [] = { 0,  }
+VQRSHL/VQRSHLQ:24:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:25:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:26:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:27:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:28:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:29:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:30:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:31:result_int64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:32:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:33:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:34:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:35:result_uint64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:36:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:37:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:38:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:39:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHL/VQRSHLQ (input 0 and negative shift amount) cumulative saturation output:
+VQRSHL/VQRSHLQ:40:vqrshl_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:41:vqrshl_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:42:vqrshl_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:43:vqrshl_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:44:vqrshl_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:45:vqrshl_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:46:vqrshl_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:47:vqrshl_u64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:48:vqrshlq_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:49:vqrshlq_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:50:vqrshlq_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:51:vqrshlq_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:52:vqrshlq_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:53:vqrshlq_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:54:vqrshlq_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:55:vqrshlq_u64 Neon cumulative saturation 0
+
+VQRSHL/VQRSHLQ (input 0 and negative shift amount) output:
+VQRSHL/VQRSHLQ:56:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:57:result_int16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:58:result_int32x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:59:result_int64x1 [] = { 0,  }
+VQRSHL/VQRSHLQ:60:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:61:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:62:result_uint32x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:63:result_uint64x1 [] = { 0,  }
+VQRSHL/VQRSHLQ:64:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:65:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:66:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:67:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:68:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:69:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:70:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:71:result_int64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:72:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:73:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:74:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:75:result_uint64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:76:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:77:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:78:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:79:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHL/VQRSHLQ cumulative saturation output:
+VQRSHL/VQRSHLQ:80:vqrshl_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:81:vqrshl_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:82:vqrshl_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:83:vqrshl_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:84:vqrshl_u8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:85:vqrshl_u16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:86:vqrshl_u32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:87:vqrshl_u64 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:88:vqrshlq_s8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:89:vqrshlq_s16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:90:vqrshlq_s32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:91:vqrshlq_s64 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:92:vqrshlq_u8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:93:vqrshlq_u16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:94:vqrshlq_u32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:95:vqrshlq_u64 Neon cumulative saturation 1
+
+VQRSHL/VQRSHLQ output:
+VQRSHL/VQRSHLQ:96:result_int8x8 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6, ffffffe8, ffffffea, ffffffec, ffffffee,  }
+VQRSHL/VQRSHLQ:97:result_int16x4 [] = { ffffff80, ffffff88, ffffff90, ffffff98,  }
+VQRSHL/VQRSHLQ:98:result_int32x2 [] = { fffff000, fffff100,  }
+VQRSHL/VQRSHLQ:99:result_int64x1 [] = { ffffffffffffff80,  }
+VQRSHL/VQRSHLQ:100:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHL/VQRSHLQ:101:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQRSHL/VQRSHLQ:102:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQRSHL/VQRSHLQ:103:result_uint64x1 [] = { ffffffffffffffff,  }
+VQRSHL/VQRSHLQ:104:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:105:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:106:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:107:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:108:result_int8x16 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQRSHL/VQRSHLQ:109:result_int16x8 [] = { ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQRSHL/VQRSHLQ:110:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VQRSHL/VQRSHLQ:111:result_int64x2 [] = { 8000000000000000, 8000000000000000,  }
+VQRSHL/VQRSHLQ:112:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHL/VQRSHLQ:113:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQRSHL/VQRSHLQ:114:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQRSHL/VQRSHLQ:115:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQRSHL/VQRSHLQ:116:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:117:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:118:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:119:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHL/VQRSHLQ (negative shift amount) cumulative saturation output:
+VQRSHL/VQRSHLQ:120:vqrshl_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:121:vqrshl_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:122:vqrshl_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:123:vqrshl_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:124:vqrshl_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:125:vqrshl_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:126:vqrshl_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:127:vqrshl_u64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:128:vqrshlq_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:129:vqrshlq_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:130:vqrshlq_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:131:vqrshlq_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:132:vqrshlq_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:133:vqrshlq_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:134:vqrshlq_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:135:vqrshlq_u64 Neon cumulative saturation 0
+
+VQRSHL/VQRSHLQ (negative shift amount) output:
+VQRSHL/VQRSHLQ:136:result_int8x8 [] = { fffffffc, fffffffc, fffffffd, fffffffd, fffffffd, fffffffd, fffffffe, fffffffe,  }
+VQRSHL/VQRSHLQ:137:result_int16x4 [] = { fffffffc, fffffffc, fffffffd, fffffffd,  }
+VQRSHL/VQRSHLQ:138:result_int32x2 [] = { fffffffe, fffffffe,  }
+VQRSHL/VQRSHLQ:139:result_int64x1 [] = { ffffffffffffffff,  }
+VQRSHL/VQRSHLQ:140:result_uint8x8 [] = { 3c, 3c, 3d, 3d, 3d, 3d, 3e, 3e,  }
+VQRSHL/VQRSHLQ:141:result_uint16x4 [] = { 3ffc, 3ffc, 3ffd, 3ffd,  }
+VQRSHL/VQRSHLQ:142:result_uint32x2 [] = { 1ffffffe, 1ffffffe,  }
+VQRSHL/VQRSHLQ:143:result_uint64x1 [] = { fffffffffffffff,  }
+VQRSHL/VQRSHLQ:144:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:145:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:146:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:147:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:148:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:149:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:150:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:151:result_int64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:152:result_uint8x16 [] = { 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,  }
+VQRSHL/VQRSHLQ:153:result_uint16x8 [] = { 20, 20, 20, 20, 20, 20, 20, 20,  }
+VQRSHL/VQRSHLQ:154:result_uint32x4 [] = { 80000, 80000, 80000, 80000,  }
+VQRSHL/VQRSHLQ:155:result_uint64x2 [] = { 100000000000, 100000000000,  }
+VQRSHL/VQRSHLQ:156:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:157:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:158:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:159:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: shift by -1) cumulative saturation output:
+VQRSHL/VQRSHLQ:160:vqrshl_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:161:vqrshl_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:162:vqrshl_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:163:vqrshl_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:164:vqrshl_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:165:vqrshl_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:166:vqrshl_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:167:vqrshl_u64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:168:vqrshlq_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:169:vqrshlq_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:170:vqrshlq_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:171:vqrshlq_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:172:vqrshlq_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:173:vqrshlq_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:174:vqrshlq_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:175:vqrshlq_u64 Neon cumulative saturation 0
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: shift by -1) output:
+VQRSHL/VQRSHLQ:176:result_int8x8 [] = { 40, 40, 40, 40, 40, 40, 40, 40,  }
+VQRSHL/VQRSHLQ:177:result_int16x4 [] = { 4000, 4000, 4000, 4000,  }
+VQRSHL/VQRSHLQ:178:result_int32x2 [] = { 40000000, 40000000,  }
+VQRSHL/VQRSHLQ:179:result_int64x1 [] = { 4000000000000000,  }
+VQRSHL/VQRSHLQ:180:result_uint8x8 [] = { 80, 80, 80, 80, 80, 80, 80, 80,  }
+VQRSHL/VQRSHLQ:181:result_uint16x4 [] = { 8000, 8000, 8000, 8000,  }
+VQRSHL/VQRSHLQ:182:result_uint32x2 [] = { 80000000, 80000000,  }
+VQRSHL/VQRSHLQ:183:result_uint64x1 [] = { 8000000000000000,  }
+VQRSHL/VQRSHLQ:184:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:185:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:186:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:187:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:188:result_int8x16 [] = { 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40,  }
+VQRSHL/VQRSHLQ:189:result_int16x8 [] = { 4000, 4000, 4000, 4000, 4000, 4000, 4000, 4000,  }
+VQRSHL/VQRSHLQ:190:result_int32x4 [] = { 40000000, 40000000, 40000000, 40000000,  }
+VQRSHL/VQRSHLQ:191:result_int64x2 [] = { 4000000000000000, 4000000000000000,  }
+VQRSHL/VQRSHLQ:192:result_uint8x16 [] = { 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80,  }
+VQRSHL/VQRSHLQ:193:result_uint16x8 [] = { 8000, 8000, 8000, 8000, 8000, 8000, 8000, 8000,  }
+VQRSHL/VQRSHLQ:194:result_uint32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VQRSHL/VQRSHLQ:195:result_uint64x2 [] = { 8000000000000000, 8000000000000000,  }
+VQRSHL/VQRSHLQ:196:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:197:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:198:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:199:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: shift by -3) cumulative saturation output:
+VQRSHL/VQRSHLQ:200:vqrshl_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:201:vqrshl_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:202:vqrshl_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:203:vqrshl_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:204:vqrshl_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:205:vqrshl_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:206:vqrshl_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:207:vqrshl_u64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:208:vqrshlq_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:209:vqrshlq_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:210:vqrshlq_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:211:vqrshlq_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:212:vqrshlq_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:213:vqrshlq_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:214:vqrshlq_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:215:vqrshlq_u64 Neon cumulative saturation 0
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: shift by -3) output:
+VQRSHL/VQRSHLQ:216:result_int8x8 [] = { 10, 10, 10, 10, 10, 10, 10, 10,  }
+VQRSHL/VQRSHLQ:217:result_int16x4 [] = { 1000, 1000, 1000, 1000,  }
+VQRSHL/VQRSHLQ:218:result_int32x2 [] = { 10000000, 10000000,  }
+VQRSHL/VQRSHLQ:219:result_int64x1 [] = { 1000000000000000,  }
+VQRSHL/VQRSHLQ:220:result_uint8x8 [] = { 20, 20, 20, 20, 20, 20, 20, 20,  }
+VQRSHL/VQRSHLQ:221:result_uint16x4 [] = { 2000, 2000, 2000, 2000,  }
+VQRSHL/VQRSHLQ:222:result_uint32x2 [] = { 20000000, 20000000,  }
+VQRSHL/VQRSHLQ:223:result_uint64x1 [] = { 2000000000000000,  }
+VQRSHL/VQRSHLQ:224:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:225:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:226:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:227:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:228:result_int8x16 [] = { 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10,  }
+VQRSHL/VQRSHLQ:229:result_int16x8 [] = { 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000,  }
+VQRSHL/VQRSHLQ:230:result_int32x4 [] = { 10000000, 10000000, 10000000, 10000000,  }
+VQRSHL/VQRSHLQ:231:result_int64x2 [] = { 1000000000000000, 1000000000000000,  }
+VQRSHL/VQRSHLQ:232:result_uint8x16 [] = { 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20,  }
+VQRSHL/VQRSHLQ:233:result_uint16x8 [] = { 2000, 2000, 2000, 2000, 2000, 2000, 2000, 2000,  }
+VQRSHL/VQRSHLQ:234:result_uint32x4 [] = { 20000000, 20000000, 20000000, 20000000,  }
+VQRSHL/VQRSHLQ:235:result_uint64x2 [] = { 2000000000000000, 2000000000000000,  }
+VQRSHL/VQRSHLQ:236:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:237:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:238:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:239:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large shift amount) cumulative saturation output:
+VQRSHL/VQRSHLQ:240:vqrshl_s8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:241:vqrshl_s16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:242:vqrshl_s32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:243:vqrshl_s64 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:244:vqrshl_u8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:245:vqrshl_u16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:246:vqrshl_u32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:247:vqrshl_u64 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:248:vqrshlq_s8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:249:vqrshlq_s16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:250:vqrshlq_s32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:251:vqrshlq_s64 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:252:vqrshlq_u8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:253:vqrshlq_u16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:254:vqrshlq_u32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:255:vqrshlq_u64 Neon cumulative saturation 1
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large shift amount) output:
+VQRSHL/VQRSHLQ:256:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQRSHL/VQRSHLQ:257:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRSHL/VQRSHLQ:258:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRSHL/VQRSHLQ:259:result_int64x1 [] = { 7fffffffffffffff,  }
+VQRSHL/VQRSHLQ:260:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHL/VQRSHLQ:261:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQRSHL/VQRSHLQ:262:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQRSHL/VQRSHLQ:263:result_uint64x1 [] = { ffffffffffffffff,  }
+VQRSHL/VQRSHLQ:264:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:265:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:266:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:267:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:268:result_int8x16 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQRSHL/VQRSHLQ:269:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQRSHL/VQRSHLQ:270:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQRSHL/VQRSHLQ:271:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+VQRSHL/VQRSHLQ:272:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHL/VQRSHLQ:273:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQRSHL/VQRSHLQ:274:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQRSHL/VQRSHLQ:275:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQRSHL/VQRSHLQ:276:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:277:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:278:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:279:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large shift amount with negative input) cumulative saturation output:
+VQRSHL/VQRSHLQ:280:vqrshl_s8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:281:vqrshl_s16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:282:vqrshl_s32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:283:vqrshl_s64 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:284:vqrshl_u8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:285:vqrshl_u16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:286:vqrshl_u32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:287:vqrshl_u64 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:288:vqrshlq_s8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:289:vqrshlq_s16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:290:vqrshlq_s32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:291:vqrshlq_s64 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:292:vqrshlq_u8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:293:vqrshlq_u16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:294:vqrshlq_u32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:295:vqrshlq_u64 Neon cumulative saturation 1
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large shift amount with negative input) output:
+VQRSHL/VQRSHLQ:296:result_int8x8 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQRSHL/VQRSHLQ:297:result_int16x4 [] = { ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQRSHL/VQRSHLQ:298:result_int32x2 [] = { 80000000, 80000000,  }
+VQRSHL/VQRSHLQ:299:result_int64x1 [] = { 8000000000000000,  }
+VQRSHL/VQRSHLQ:300:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHL/VQRSHLQ:301:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQRSHL/VQRSHLQ:302:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQRSHL/VQRSHLQ:303:result_uint64x1 [] = { ffffffffffffffff,  }
+VQRSHL/VQRSHLQ:304:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:305:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:306:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:307:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:308:result_int8x16 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQRSHL/VQRSHLQ:309:result_int16x8 [] = { ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQRSHL/VQRSHLQ:310:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VQRSHL/VQRSHLQ:311:result_int64x2 [] = { 8000000000000000, 8000000000000000,  }
+VQRSHL/VQRSHLQ:312:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHL/VQRSHLQ:313:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQRSHL/VQRSHLQ:314:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQRSHL/VQRSHLQ:315:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQRSHL/VQRSHLQ:316:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:317:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:318:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:319:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large negative shift amount) cumulative saturation output:
+VQRSHL/VQRSHLQ:320:vqrshl_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:321:vqrshl_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:322:vqrshl_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:323:vqrshl_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:324:vqrshl_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:325:vqrshl_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:326:vqrshl_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:327:vqrshl_u64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:328:vqrshlq_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:329:vqrshlq_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:330:vqrshlq_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:331:vqrshlq_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:332:vqrshlq_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:333:vqrshlq_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:334:vqrshlq_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:335:vqrshlq_u64 Neon cumulative saturation 0
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large negative shift amount) output:
+VQRSHL/VQRSHLQ:336:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:337:result_int16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:338:result_int32x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:339:result_int64x1 [] = { 0,  }
+VQRSHL/VQRSHLQ:340:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:341:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:342:result_uint32x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:343:result_uint64x1 [] = { 0,  }
+VQRSHL/VQRSHLQ:344:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:345:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:346:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:347:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:348:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:349:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:350:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:351:result_int64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:352:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:353:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:354:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:355:result_uint64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:356:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:357:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:358:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:359:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large shift amount with 0 input) cumulative saturation output:
+VQRSHL/VQRSHLQ:360:vqrshl_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:361:vqrshl_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:362:vqrshl_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:363:vqrshl_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:364:vqrshl_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:365:vqrshl_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:366:vqrshl_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:367:vqrshl_u64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:368:vqrshlq_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:369:vqrshlq_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:370:vqrshlq_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:371:vqrshlq_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:372:vqrshlq_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:373:vqrshlq_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:374:vqrshlq_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:375:vqrshlq_u64 Neon cumulative saturation 0
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large shift amount with 0 input) output:
+VQRSHL/VQRSHLQ:376:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:377:result_int16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:378:result_int32x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:379:result_int64x1 [] = { 0,  }
+VQRSHL/VQRSHLQ:380:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:381:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:382:result_uint32x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:383:result_uint64x1 [] = { 0,  }
+VQRSHL/VQRSHLQ:384:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:385:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:386:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:387:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:388:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:389:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:390:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:391:result_int64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:392:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:393:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:394:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:395:result_uint64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:396:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:397:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:398:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:399:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VABA/VABAQ output:
+VABA/VABAQ:0:result_int8x8 [] = { fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd,  }
+VABA/VABAQ:1:result_int16x4 [] = { 16, 17, 18, 19,  }
+VABA/VABAQ:2:result_int32x2 [] = { 20, 21,  }
+VABA/VABAQ:3:result_int64x1 [] = { 3333333333333333,  }
+VABA/VABAQ:4:result_uint8x8 [] = { 53, 54, 55, 56, 57, 58, 59, 5a,  }
+VABA/VABAQ:5:result_uint16x4 [] = { 907, 908, 909, 90a,  }
+VABA/VABAQ:6:result_uint32x2 [] = { ffffffe7, ffffffe8,  }
+VABA/VABAQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VABA/VABAQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABA/VABAQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABA/VABAQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VABA/VABAQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VABA/VABAQ:12:result_int8x16 [] = { 5e, 5f, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 6a, 6b, 6c, 6d,  }
+VABA/VABAQ:13:result_int16x8 [] = { b9c, b9d, b9e, b9f, ba0, ba1, ba2, ba3,  }
+VABA/VABAQ:14:result_int32x4 [] = { 26e0, 26e1, 26e2, 26e3,  }
+VABA/VABAQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VABA/VABAQ:16:result_uint8x16 [] = { f8, f9, fa, fb, fc, fd, fe, ff, 0, 1, 2, 3, 4, 5, 6, 7,  }
+VABA/VABAQ:17:result_uint16x8 [] = { fff9, fffa, fffb, fffc, fffd, fffe, ffff, 0,  }
+VABA/VABAQ:18:result_uint32x4 [] = { c, d, e, f,  }
+VABA/VABAQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VABA/VABAQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABA/VABAQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VABA/VABAQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VABA/VABAQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VABAL output:
+VABAL:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABAL:2:result_int32x2 [] = { 33333333, 33333333,  }
+VABAL:3:result_int64x1 [] = { 3333333333333333,  }
+VABAL:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABAL:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VABAL:7:result_uint64x1 [] = { 3333333333333333,  }
+VABAL:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABAL:10:result_float32x2 [] = { 33333333, 33333333,  }
+VABAL:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VABAL:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:13:result_int16x8 [] = { fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd,  }
+VABAL:14:result_int32x4 [] = { 16, 17, 18, 19,  }
+VABAL:15:result_int64x2 [] = { 20, 21,  }
+VABAL:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:17:result_uint16x8 [] = { 53, 54, 55, 56, 57, 58, 59, 5a,  }
+VABAL:18:result_uint32x4 [] = { 907, 908, 909, 90a,  }
+VABAL:19:result_uint64x2 [] = { ffffffe7, ffffffe8,  }
+VABAL:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VABAL:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VABAL:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VABAL test intermediate overflow output:
+VABAL:24:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:25:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABAL:26:result_int32x2 [] = { 33333333, 33333333,  }
+VABAL:27:result_int64x1 [] = { 3333333333333333,  }
+VABAL:28:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:29:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABAL:30:result_uint32x2 [] = { 33333333, 33333333,  }
+VABAL:31:result_uint64x1 [] = { 3333333333333333,  }
+VABAL:32:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:33:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABAL:34:result_float32x2 [] = { 33333333, 33333333,  }
+VABAL:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VABAL:36:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:37:result_int16x8 [] = { ef, f0, f1, f2, f3, f4, f5, f6,  }
+VABAL:38:result_int32x4 [] = { ffef, fff0, fff1, fff2,  }
+VABAL:39:result_int64x2 [] = { ffffffef, fffffff0,  }
+VABAL:40:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:41:result_uint16x8 [] = { ee, ef, f0, f1, f2, f3, f4, f5,  }
+VABAL:42:result_uint32x4 [] = { ffe2, ffe3, ffe4, ffe5,  }
+VABAL:43:result_uint64x2 [] = { ffffffe7, ffffffe8,  }
+VABAL:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:45:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VABAL:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VABAL:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VABD/VABDQ output:
+VABD/VABDQ:0:result_int8x8 [] = { 11, 10, f, e, d, c, b, a,  }
+VABD/VABDQ:1:result_int16x4 [] = { 3, 2, 1, 0,  }
+VABD/VABDQ:2:result_int32x2 [] = { 18, 17,  }
+VABD/VABDQ:3:result_int64x1 [] = { 3333333333333333,  }
+VABD/VABDQ:4:result_uint8x8 [] = { ef, f0, f1, f2, f3, f4, f5, f6,  }
+VABD/VABDQ:5:result_uint16x4 [] = { ffe3, ffe4, ffe5, ffe6,  }
+VABD/VABDQ:6:result_uint32x2 [] = { ffffffe8, ffffffe9,  }
+VABD/VABDQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VABD/VABDQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABD/VABDQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABD/VABDQ:10:result_float32x2 [] = { 41c26666, 41ba6666,  }
+VABD/VABDQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VABD/VABDQ:12:result_int8x16 [] = { 1a, 19, 18, 17, 16, 15, 14, 13, 12, 11, 10, f, e, d, c, b,  }
+VABD/VABDQ:13:result_int16x8 [] = { 4, 3, 2, 1, 0, 1, 2, 3,  }
+VABD/VABDQ:14:result_int32x4 [] = { 30, 2f, 2e, 2d,  }
+VABD/VABDQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VABD/VABDQ:16:result_uint8x16 [] = { e6, e7, e8, e9, ea, eb, ec, ed, ee, ef, f0, f1, f2, f3, f4, f5,  }
+VABD/VABDQ:17:result_uint16x8 [] = { ffe4, ffe5, ffe6, ffe7, ffe8, ffe9, ffea, ffeb,  }
+VABD/VABDQ:18:result_uint32x4 [] = { ffffffd0, ffffffd1, ffffffd2, ffffffd3,  }
+VABD/VABDQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VABD/VABDQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABD/VABDQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VABD/VABDQ:22:result_float32x4 [] = { 42407ae1, 423c7ae1, 42387ae1, 42347ae1,  }
+VABD/VABDQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VABD/VABDQ FP special (-0.0):24:result_float32x4 [] = { 0, 0, 0, 0,  }
+VABD/VABDQ FP special (-0.0):25:result_float32x4 [] = { 0, 0, 0, 0,  }
+
+VABDL output:
+VABDL:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABDL:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABDL:2:result_int32x2 [] = { 33333333, 33333333,  }
+VABDL:3:result_int64x1 [] = { 3333333333333333,  }
+VABDL:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABDL:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABDL:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VABDL:7:result_uint64x1 [] = { 3333333333333333,  }
+VABDL:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABDL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABDL:10:result_float32x2 [] = { 33333333, 33333333,  }
+VABDL:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VABDL:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABDL:13:result_int16x8 [] = { 11, 10, f, e, d, c, b, a,  }
+VABDL:14:result_int32x4 [] = { 3, 2, 1, 0,  }
+VABDL:15:result_int64x2 [] = { 18, 17,  }
+VABDL:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABDL:17:result_uint16x8 [] = { ef, f0, f1, f2, f3, f4, f5, f6,  }
+VABDL:18:result_uint32x4 [] = { ffe3, ffe4, ffe5, ffe6,  }
+VABDL:19:result_uint64x2 [] = { ffffffe8, ffffffe9,  }
+VABDL:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABDL:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VABDL:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VABDL:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VAND/VANDQ output:
+VAND/VANDQ:0:result_int8x8 [] = { 0, 0, 2, 2, 0, 0, 2, 2,  }
+VAND/VANDQ:1:result_int16x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VAND/VANDQ:2:result_int32x2 [] = { 0, 1,  }
+VAND/VANDQ:3:result_int64x1 [] = { 60,  }
+VAND/VANDQ:4:result_uint8x8 [] = { 10, 10, 10, 10, 14, 14, 14, 14,  }
+VAND/VANDQ:5:result_uint16x4 [] = { 10, 10, 12, 12,  }
+VAND/VANDQ:6:result_uint32x2 [] = { 20, 20,  }
+VAND/VANDQ:7:result_uint64x1 [] = { 0,  }
+VAND/VANDQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VAND/VANDQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VAND/VANDQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VAND/VANDQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VAND/VANDQ:12:result_int8x16 [] = { fffffff0, fffffff0, fffffff2, fffffff2, fffffff4, fffffff4, fffffff6, fffffff6, fffffff0, fffffff0, fffffff2, fffffff2, fffffff4, fffffff4, fffffff6, fffffff6,  }
+VAND/VANDQ:13:result_int16x8 [] = { ffffffe0, ffffffe0, ffffffe0, ffffffe0, ffffffe4, ffffffe4, ffffffe4, ffffffe4,  }
+VAND/VANDQ:14:result_int32x4 [] = { ffffffe0, ffffffe0, ffffffe2, ffffffe2,  }
+VAND/VANDQ:15:result_int64x2 [] = { 10, 10,  }
+VAND/VANDQ:16:result_uint8x16 [] = { 0, 0, 0, 0, 4, 4, 4, 4, 8, 8, 8, 8, c, c, c, c,  }
+VAND/VANDQ:17:result_uint16x8 [] = { 0, 1, 2, 3, 0, 1, 2, 3,  }
+VAND/VANDQ:18:result_uint32x4 [] = { 30, 31, 32, 33,  }
+VAND/VANDQ:19:result_uint64x2 [] = { 0, 1,  }
+VAND/VANDQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VAND/VANDQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VAND/VANDQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VAND/VANDQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VORR/VORRQ output:
+VORR/VORRQ:0:result_int8x8 [] = { fffffff2, fffffff3, fffffff2, fffffff3, fffffff6, fffffff7, fffffff6, fffffff7,  }
+VORR/VORRQ:1:result_int16x4 [] = { fffffffc, fffffffd, fffffffe, ffffffff,  }
+VORR/VORRQ:2:result_int32x2 [] = { fffffff3, fffffff3,  }
+VORR/VORRQ:3:result_int64x1 [] = { fffffffffffffff4,  }
+VORR/VORRQ:4:result_uint8x8 [] = { f4, f5, f6, f7, f4, f5, f6, f7,  }
+VORR/VORRQ:5:result_uint16x4 [] = { fffe, ffff, fffe, ffff,  }
+VORR/VORRQ:6:result_uint32x2 [] = { fffffff8, fffffff9,  }
+VORR/VORRQ:7:result_uint64x1 [] = { fffffffffffffff2,  }
+VORR/VORRQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VORR/VORRQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VORR/VORRQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VORR/VORRQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VORR/VORRQ:12:result_int8x16 [] = { fffffff6, fffffff7, fffffff6, fffffff7, fffffff6, fffffff7, fffffff6, fffffff7, fffffffe, ffffffff, fffffffe, ffffffff, fffffffe, ffffffff, fffffffe, ffffffff,  }
+VORR/VORRQ:13:result_int16x8 [] = { fffffffc, fffffffd, fffffffe, ffffffff, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VORR/VORRQ:14:result_int32x4 [] = { fffffff2, fffffff3, fffffff2, fffffff3,  }
+VORR/VORRQ:15:result_int64x2 [] = { fffffffffffffff8, fffffffffffffff9,  }
+VORR/VORRQ:16:result_uint8x16 [] = { fc, fd, fe, ff, fc, fd, fe, ff, fc, fd, fe, ff, fc, fd, fe, ff,  }
+VORR/VORRQ:17:result_uint16x8 [] = { fff3, fff3, fff3, fff3, fff7, fff7, fff7, fff7,  }
+VORR/VORRQ:18:result_uint32x4 [] = { fffffff7, fffffff7, fffffff7, fffffff7,  }
+VORR/VORRQ:19:result_uint64x2 [] = { fffffffffffffff3, fffffffffffffff3,  }
+VORR/VORRQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VORR/VORRQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VORR/VORRQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VORR/VORRQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VORN/VORNQ output:
+VORN/VORNQ:0:result_int8x8 [] = { fffffffd, fffffffd, ffffffff, ffffffff, fffffffd, fffffffd, ffffffff, ffffffff,  }
+VORN/VORNQ:1:result_int16x4 [] = { fffffff3, fffffff3, fffffff3, fffffff3,  }
+VORN/VORNQ:2:result_int32x2 [] = { fffffffc, fffffffd,  }
+VORN/VORNQ:3:result_int64x1 [] = { fffffffffffffffb,  }
+VORN/VORNQ:4:result_uint8x8 [] = { fb, fb, fb, fb, ff, ff, ff, ff,  }
+VORN/VORNQ:5:result_uint16x4 [] = { fff1, fff1, fff3, fff3,  }
+VORN/VORNQ:6:result_uint32x2 [] = { fffffff7, fffffff7,  }
+VORN/VORNQ:7:result_uint64x1 [] = { fffffffffffffffd,  }
+VORN/VORNQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VORN/VORNQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VORN/VORNQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VORN/VORNQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VORN/VORNQ:12:result_int8x16 [] = { fffffff9, fffffff9, fffffffb, fffffffb, fffffffd, fffffffd, ffffffff, ffffffff, fffffff9, fffffff9, fffffffb, fffffffb, fffffffd, fffffffd, ffffffff, ffffffff,  }
+VORN/VORNQ:13:result_int16x8 [] = { fffffff3, fffffff3, fffffff3, fffffff3, fffffff7, fffffff7, fffffff7, fffffff7,  }
+VORN/VORNQ:14:result_int32x4 [] = { fffffffd, fffffffd, ffffffff, ffffffff,  }
+VORN/VORNQ:15:result_int64x2 [] = { fffffffffffffff7, fffffffffffffff7,  }
+VORN/VORNQ:16:result_uint8x16 [] = { f3, f3, f3, f3, f7, f7, f7, f7, fb, fb, fb, fb, ff, ff, ff, ff,  }
+VORN/VORNQ:17:result_uint16x8 [] = { fffc, fffd, fffe, ffff, fffc, fffd, fffe, ffff,  }
+VORN/VORNQ:18:result_uint32x4 [] = { fffffff8, fffffff9, fffffffa, fffffffb,  }
+VORN/VORNQ:19:result_uint64x2 [] = { fffffffffffffffc, fffffffffffffffd,  }
+VORN/VORNQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VORN/VORNQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VORN/VORNQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VORN/VORNQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VEOR/VEORQ output:
+VEOR/VEORQ:0:result_int8x8 [] = { fffffff2, fffffff3, fffffff0, fffffff1, fffffff6, fffffff7, fffffff4, fffffff5,  }
+VEOR/VEORQ:1:result_int16x4 [] = { c, d, e, f,  }
+VEOR/VEORQ:2:result_int32x2 [] = { fffffff3, fffffff2,  }
+VEOR/VEORQ:3:result_int64x1 [] = { ffffffffffffff94,  }
+VEOR/VEORQ:4:result_uint8x8 [] = { e4, e5, e6, e7, e0, e1, e2, e3,  }
+VEOR/VEORQ:5:result_uint16x4 [] = { ffee, ffef, ffec, ffed,  }
+VEOR/VEORQ:6:result_uint32x2 [] = { ffffffd8, ffffffd9,  }
+VEOR/VEORQ:7:result_uint64x1 [] = { fffffffffffffff2,  }
+VEOR/VEORQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VEOR/VEORQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VEOR/VEORQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VEOR/VEORQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VEOR/VEORQ:12:result_int8x16 [] = { 6, 7, 4, 5, 2, 3, 0, 1, e, f, c, d, a, b, 8, 9,  }
+VEOR/VEORQ:13:result_int16x8 [] = { 1c, 1d, 1e, 1f, 18, 19, 1a, 1b,  }
+VEOR/VEORQ:14:result_int32x4 [] = { 12, 13, 10, 11,  }
+VEOR/VEORQ:15:result_int64x2 [] = { ffffffffffffffe8, ffffffffffffffe9,  }
+VEOR/VEORQ:16:result_uint8x16 [] = { fc, fd, fe, ff, f8, f9, fa, fb, f4, f5, f6, f7, f0, f1, f2, f3,  }
+VEOR/VEORQ:17:result_uint16x8 [] = { fff3, fff2, fff1, fff0, fff7, fff6, fff5, fff4,  }
+VEOR/VEORQ:18:result_uint32x4 [] = { ffffffc7, ffffffc6, ffffffc5, ffffffc4,  }
+VEOR/VEORQ:19:result_uint64x2 [] = { fffffffffffffff3, fffffffffffffff2,  }
+VEOR/VEORQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VEOR/VEORQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VEOR/VEORQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VEOR/VEORQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VBIC/VBICQ output:
+VBIC/VBICQ:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff0, fffffff1, fffffff4, fffffff5, fffffff4, fffffff5,  }
+VBIC/VBICQ:1:result_int16x4 [] = { 0, 1, 2, 3,  }
+VBIC/VBICQ:2:result_int32x2 [] = { fffffff0, fffffff0,  }
+VBIC/VBICQ:3:result_int64x1 [] = { ffffffffffffff90,  }
+VBIC/VBICQ:4:result_uint8x8 [] = { e0, e1, e2, e3, e0, e1, e2, e3,  }
+VBIC/VBICQ:5:result_uint16x4 [] = { ffe0, ffe1, ffe0, ffe1,  }
+VBIC/VBICQ:6:result_uint32x2 [] = { ffffffd0, ffffffd1,  }
+VBIC/VBICQ:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VBIC/VBICQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VBIC/VBICQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VBIC/VBICQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VBIC/VBICQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VBIC/VBICQ:12:result_int8x16 [] = { 0, 1, 0, 1, 0, 1, 0, 1, 8, 9, 8, 9, 8, 9, 8, 9,  }
+VBIC/VBICQ:13:result_int16x8 [] = { 10, 11, 12, 13, 10, 11, 12, 13,  }
+VBIC/VBICQ:14:result_int32x4 [] = { 10, 11, 10, 11,  }
+VBIC/VBICQ:15:result_int64x2 [] = { ffffffffffffffe0, ffffffffffffffe1,  }
+VBIC/VBICQ:16:result_uint8x16 [] = { f0, f1, f2, f3, f0, f1, f2, f3, f0, f1, f2, f3, f0, f1, f2, f3,  }
+VBIC/VBICQ:17:result_uint16x8 [] = { fff0, fff0, fff0, fff0, fff4, fff4, fff4, fff4,  }
+VBIC/VBICQ:18:result_uint32x4 [] = { ffffffc0, ffffffc0, ffffffc0, ffffffc0,  }
+VBIC/VBICQ:19:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VBIC/VBICQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VBIC/VBICQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VBIC/VBICQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VBIC/VBICQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VCREATE output:
+VCREATE:0:result_int8x8 [] = { fffffff0, ffffffde, ffffffbc, ffffff9a, 78, 56, 34, 12,  }
+VCREATE:1:result_int16x4 [] = { ffffdef0, ffff9abc, 5678, 1234,  }
+VCREATE:2:result_int32x2 [] = { 9abcdef0, 12345678,  }
+VCREATE:3:result_int64x1 [] = { 123456789abcdef0,  }
+VCREATE:4:result_uint8x8 [] = { f0, de, bc, 9a, 78, 56, 34, 12,  }
+VCREATE:5:result_uint16x4 [] = { def0, 9abc, 5678, 1234,  }
+VCREATE:6:result_uint32x2 [] = { 9abcdef0, 12345678,  }
+VCREATE:7:result_uint64x1 [] = { 123456789abcdef0,  }
+VCREATE:8:result_poly8x8 [] = { f0, de, bc, 9a, 78, 56, 34, 12,  }
+VCREATE:9:result_poly16x4 [] = { def0, 9abc, 5678, 1234,  }
+VCREATE:10:result_float32x2 [] = { 9abcdef0, 12345678,  }
+VCREATE:11:result_float16x4 [] = { def0, 9abc, 5678, 1234,  }
+VCREATE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCREATE:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCREATE:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCREATE:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCREATE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCREATE:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCREATE:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCREATE:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCREATE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCREATE:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCREATE:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCREATE:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VLD2_LANE/VLD2Q_LANE chunk 0 output:
+VLD2_LANE/VLD2Q_LANE:0:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa,  }
+VLD2_LANE/VLD2Q_LANE:1:result_int16x4 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD2_LANE/VLD2Q_LANE:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD2_LANE/VLD2Q_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VLD2_LANE/VLD2Q_LANE:4:result_uint8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD2_LANE/VLD2Q_LANE:5:result_uint16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD2_LANE/VLD2Q_LANE:6:result_uint32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VLD2_LANE/VLD2Q_LANE:8:result_poly8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD2_LANE/VLD2Q_LANE:9:result_poly16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD2_LANE/VLD2Q_LANE:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD2_LANE/VLD2Q_LANE:11:result_float16x4 [] = { cc00, cb80, aaaa, aaaa,  }
+VLD2_LANE/VLD2Q_LANE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_LANE/VLD2Q_LANE:13:result_int16x8 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD2_LANE/VLD2Q_LANE:14:result_int32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2_LANE/VLD2Q_LANE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_LANE/VLD2Q_LANE:17:result_uint16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD2_LANE/VLD2Q_LANE:18:result_uint32x4 [] = { fffffff0, fffffff1, aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2_LANE/VLD2Q_LANE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_LANE/VLD2Q_LANE:21:result_poly16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD2_LANE/VLD2Q_LANE:22:result_float32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:23:result_float16x8 [] = { aaaa, aaaa, aaaa, aaaa, cc00, cb80, aaaa, aaaa,  }
+
+VLD2_LANE/VLD2Q_LANE chunk 1 output:
+VLD2_LANE/VLD2Q_LANE:24:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, fffffff0, fffffff1,  }
+VLD2_LANE/VLD2Q_LANE:25:result_int16x4 [] = { fffffff0, fffffff1, ffffaaaa, ffffaaaa,  }
+VLD2_LANE/VLD2Q_LANE:26:result_int32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:27:result_int64x1 [] = { 3333333333333333,  }
+VLD2_LANE/VLD2Q_LANE:28:result_uint8x8 [] = { f0, f1, aa, aa, aa, aa, aa, aa,  }
+VLD2_LANE/VLD2Q_LANE:29:result_uint16x4 [] = { aaaa, aaaa, fff0, fff1,  }
+VLD2_LANE/VLD2Q_LANE:30:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD2_LANE/VLD2Q_LANE:31:result_uint64x1 [] = { 3333333333333333,  }
+VLD2_LANE/VLD2Q_LANE:32:result_poly8x8 [] = { f0, f1, aa, aa, aa, aa, aa, aa,  }
+VLD2_LANE/VLD2Q_LANE:33:result_poly16x4 [] = { aaaa, aaaa, fff0, fff1,  }
+VLD2_LANE/VLD2Q_LANE:34:result_float32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:35:result_float16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD2_LANE/VLD2Q_LANE:36:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_LANE/VLD2Q_LANE:37:result_int16x8 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, fffffff0, fffffff1, ffffaaaa, ffffaaaa,  }
+VLD2_LANE/VLD2Q_LANE:38:result_int32x4 [] = { fffffff0, fffffff1, aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2_LANE/VLD2Q_LANE:40:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_LANE/VLD2Q_LANE:41:result_uint16x8 [] = { aaaa, aaaa, fff0, fff1, aaaa, aaaa, aaaa, aaaa,  }
+VLD2_LANE/VLD2Q_LANE:42:result_uint32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2_LANE/VLD2Q_LANE:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_LANE/VLD2Q_LANE:45:result_poly16x8 [] = { aaaa, aaaa, fff0, fff1, aaaa, aaaa, aaaa, aaaa,  }
+VLD2_LANE/VLD2Q_LANE:46:result_float32x4 [] = { c1800000, c1700000, aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:47:result_float16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+
+VLD3_LANE/VLD3Q_LANE chunk 0 output:
+VLD3_LANE/VLD3Q_LANE:0:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa,  }
+VLD3_LANE/VLD3Q_LANE:1:result_int16x4 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD3_LANE/VLD3Q_LANE:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD3_LANE/VLD3Q_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:4:result_uint8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD3_LANE/VLD3Q_LANE:5:result_uint16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:6:result_uint32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:8:result_poly8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD3_LANE/VLD3Q_LANE:9:result_poly16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD3_LANE/VLD3Q_LANE:11:result_float16x4 [] = { cc00, cb80, cb00, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:13:result_int16x8 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD3_LANE/VLD3Q_LANE:14:result_int32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:17:result_uint16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:21:result_poly16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:22:result_float32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:23:result_float16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, cc00, cb80,  }
+
+VLD3_LANE/VLD3Q_LANE chunk 1 output:
+VLD3_LANE/VLD3Q_LANE:24:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa,  }
+VLD3_LANE/VLD3Q_LANE:25:result_int16x4 [] = { ffffaaaa, ffffaaaa, fffffff0, fffffff1,  }
+VLD3_LANE/VLD3Q_LANE:26:result_int32x2 [] = { fffffff2, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:27:result_int64x1 [] = { 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:28:result_uint8x8 [] = { aa, aa, aa, aa, f0, f1, f2, aa,  }
+VLD3_LANE/VLD3Q_LANE:29:result_uint16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:30:result_uint32x2 [] = { aaaaaaaa, fffffff0,  }
+VLD3_LANE/VLD3Q_LANE:31:result_uint64x1 [] = { 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:32:result_poly8x8 [] = { aa, aa, aa, aa, f0, f1, f2, aa,  }
+VLD3_LANE/VLD3Q_LANE:33:result_poly16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:34:result_float32x2 [] = { c1600000, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:35:result_float16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:36:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:37:result_int16x8 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD3_LANE/VLD3Q_LANE:38:result_int32x4 [] = { aaaaaaaa, aaaaaaaa, fffffff0, fffffff1,  }
+VLD3_LANE/VLD3Q_LANE:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:40:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:41:result_uint16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, fff0,  }
+VLD3_LANE/VLD3Q_LANE:42:result_uint32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:45:result_poly16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, fff0,  }
+VLD3_LANE/VLD3Q_LANE:46:result_float32x4 [] = { aaaaaaaa, aaaaaaaa, c1800000, c1700000,  }
+VLD3_LANE/VLD3Q_LANE:47:result_float16x8 [] = { cb00, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+
+VLD3_LANE/VLD3Q_LANE chunk 2 output:
+VLD3_LANE/VLD3Q_LANE:48:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, fffffff0, fffffff1, fffffff2,  }
+VLD3_LANE/VLD3Q_LANE:49:result_int16x4 [] = { fffffff2, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD3_LANE/VLD3Q_LANE:50:result_int32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:51:result_int64x1 [] = { 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:52:result_uint8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD3_LANE/VLD3Q_LANE:53:result_uint16x4 [] = { aaaa, fff0, fff1, fff2,  }
+VLD3_LANE/VLD3Q_LANE:54:result_uint32x2 [] = { fffffff1, fffffff2,  }
+VLD3_LANE/VLD3Q_LANE:55:result_uint64x1 [] = { 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:56:result_poly8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD3_LANE/VLD3Q_LANE:57:result_poly16x4 [] = { aaaa, fff0, fff1, fff2,  }
+VLD3_LANE/VLD3Q_LANE:58:result_float32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:59:result_float16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:60:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:61:result_int16x8 [] = { ffffaaaa, ffffaaaa, fffffff0, fffffff1, fffffff2, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD3_LANE/VLD3Q_LANE:62:result_int32x4 [] = { fffffff2, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:63:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:64:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:65:result_uint16x8 [] = { fff1, fff2, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:66:result_uint32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:67:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:68:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:69:result_poly16x8 [] = { fff1, fff2, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:70:result_float32x4 [] = { c1600000, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:71:result_float16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+
+VLD4_LANE/VLD4Q_LANE chunk 0 output:
+VLD4_LANE/VLD4Q_LANE:0:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa,  }
+VLD4_LANE/VLD4Q_LANE:1:result_int16x4 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD4_LANE/VLD4Q_LANE:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD4_LANE/VLD4Q_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:4:result_uint8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD4_LANE/VLD4Q_LANE:5:result_uint16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:6:result_uint32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:8:result_poly8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD4_LANE/VLD4Q_LANE:9:result_poly16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD4_LANE/VLD4Q_LANE:11:result_float16x4 [] = { cc00, cb80, cb00, ca80,  }
+VLD4_LANE/VLD4Q_LANE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:13:result_int16x8 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD4_LANE/VLD4Q_LANE:14:result_int32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:17:result_uint16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_LANE/VLD4Q_LANE:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:21:result_poly16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:22:result_float32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:23:result_float16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+
+VLD4_LANE/VLD4Q_LANE chunk 1 output:
+VLD4_LANE/VLD4Q_LANE:24:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa,  }
+VLD4_LANE/VLD4Q_LANE:25:result_int16x4 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD4_LANE/VLD4Q_LANE:26:result_int32x2 [] = { fffffff2, fffffff3,  }
+VLD4_LANE/VLD4Q_LANE:27:result_int64x1 [] = { 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:28:result_uint8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD4_LANE/VLD4Q_LANE:29:result_uint16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:30:result_uint32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:31:result_uint64x1 [] = { 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:32:result_poly8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD4_LANE/VLD4Q_LANE:33:result_poly16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:34:result_float32x2 [] = { c1600000, c1500000,  }
+VLD4_LANE/VLD4Q_LANE:35:result_float16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:36:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:37:result_int16x8 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD4_LANE/VLD4Q_LANE:38:result_int32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:40:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:41:result_uint16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:42:result_uint32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:45:result_poly16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:46:result_float32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:47:result_float16x8 [] = { cc00, cb80, cb00, ca80, aaaa, aaaa, aaaa, aaaa,  }
+
+VLD4_LANE/VLD4Q_LANE chunk 2 output:
+VLD4_LANE/VLD4Q_LANE:48:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa,  }
+VLD4_LANE/VLD4Q_LANE:49:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_LANE/VLD4Q_LANE:50:result_int32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:51:result_int64x1 [] = { 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:52:result_uint8x8 [] = { f0, f1, f2, f3, aa, aa, aa, aa,  }
+VLD4_LANE/VLD4Q_LANE:53:result_uint16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:54:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD4_LANE/VLD4Q_LANE:55:result_uint64x1 [] = { 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:56:result_poly8x8 [] = { f0, f1, f2, f3, aa, aa, aa, aa,  }
+VLD4_LANE/VLD4Q_LANE:57:result_poly16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:58:result_float32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:59:result_float16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:60:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:61:result_int16x8 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD4_LANE/VLD4Q_LANE:62:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_LANE/VLD4Q_LANE:63:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:64:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:65:result_uint16x8 [] = { aaaa, aaaa, aaaa, aaaa, fff0, fff1, fff2, fff3,  }
+VLD4_LANE/VLD4Q_LANE:66:result_uint32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:67:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:68:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:69:result_poly16x8 [] = { aaaa, aaaa, aaaa, aaaa, fff0, fff1, fff2, fff3,  }
+VLD4_LANE/VLD4Q_LANE:70:result_float32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+VLD4_LANE/VLD4Q_LANE:71:result_float16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+
+VLD4_LANE/VLD4Q_LANE chunk 3 output:
+VLD4_LANE/VLD4Q_LANE:72:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_LANE/VLD4Q_LANE:73:result_int16x4 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD4_LANE/VLD4Q_LANE:74:result_int32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:75:result_int64x1 [] = { 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:76:result_uint8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD4_LANE/VLD4Q_LANE:77:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_LANE/VLD4Q_LANE:78:result_uint32x2 [] = { fffffff2, fffffff3,  }
+VLD4_LANE/VLD4Q_LANE:79:result_uint64x1 [] = { 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:80:result_poly8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD4_LANE/VLD4Q_LANE:81:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_LANE/VLD4Q_LANE:82:result_float32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:83:result_float16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:84:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:85:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD4_LANE/VLD4Q_LANE:86:result_int32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:87:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:88:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:89:result_uint16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:90:result_uint32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:91:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:92:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:93:result_poly16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:94:result_float32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:95:result_float16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+
+VLD2_DUP/VLD2Q_DUP chunk 0 output:
+VLD2_DUP/VLD2Q_DUP:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff0, fffffff1, fffffff0, fffffff1, fffffff0, fffffff1,  }
+VLD2_DUP/VLD2Q_DUP:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff0, fffffff1,  }
+VLD2_DUP/VLD2Q_DUP:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD2_DUP/VLD2Q_DUP:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD2_DUP/VLD2Q_DUP:4:result_uint8x8 [] = { f0, f1, f0, f1, f0, f1, f0, f1,  }
+VLD2_DUP/VLD2Q_DUP:5:result_uint16x4 [] = { fff0, fff1, fff0, fff1,  }
+VLD2_DUP/VLD2Q_DUP:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD2_DUP/VLD2Q_DUP:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD2_DUP/VLD2Q_DUP:8:result_poly8x8 [] = { f0, f1, f0, f1, f0, f1, f0, f1,  }
+VLD2_DUP/VLD2Q_DUP:9:result_poly16x4 [] = { fff0, fff1, fff0, fff1,  }
+VLD2_DUP/VLD2Q_DUP:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD2_DUP/VLD2Q_DUP:11:result_float16x4 [] = { cc00, cb80, cc00, cb80,  }
+VLD2_DUP/VLD2Q_DUP:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_DUP/VLD2Q_DUP:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD2_DUP/VLD2Q_DUP:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD2_DUP/VLD2Q_DUP:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2_DUP/VLD2Q_DUP:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_DUP/VLD2Q_DUP:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD2_DUP/VLD2Q_DUP:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD2_DUP/VLD2Q_DUP:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2_DUP/VLD2Q_DUP:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_DUP/VLD2Q_DUP:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD2_DUP/VLD2Q_DUP:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD2_DUP/VLD2Q_DUP:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VLD2_DUP/VLD2Q_DUP chunk 1 output:
+VLD2_DUP/VLD2Q_DUP:24:result_int8x8 [] = { fffffff0, fffffff1, fffffff0, fffffff1, fffffff0, fffffff1, fffffff0, fffffff1,  }
+VLD2_DUP/VLD2Q_DUP:25:result_int16x4 [] = { fffffff0, fffffff1, fffffff0, fffffff1,  }
+VLD2_DUP/VLD2Q_DUP:26:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD2_DUP/VLD2Q_DUP:27:result_int64x1 [] = { fffffffffffffff1,  }
+VLD2_DUP/VLD2Q_DUP:28:result_uint8x8 [] = { f0, f1, f0, f1, f0, f1, f0, f1,  }
+VLD2_DUP/VLD2Q_DUP:29:result_uint16x4 [] = { fff0, fff1, fff0, fff1,  }
+VLD2_DUP/VLD2Q_DUP:30:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD2_DUP/VLD2Q_DUP:31:result_uint64x1 [] = { fffffffffffffff1,  }
+VLD2_DUP/VLD2Q_DUP:32:result_poly8x8 [] = { f0, f1, f0, f1, f0, f1, f0, f1,  }
+VLD2_DUP/VLD2Q_DUP:33:result_poly16x4 [] = { fff0, fff1, fff0, fff1,  }
+VLD2_DUP/VLD2Q_DUP:34:result_float32x2 [] = { c1800000, c1700000,  }
+VLD2_DUP/VLD2Q_DUP:35:result_float16x4 [] = { cc00, cb80, cc00, cb80,  }
+VLD2_DUP/VLD2Q_DUP:36:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_DUP/VLD2Q_DUP:37:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD2_DUP/VLD2Q_DUP:38:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD2_DUP/VLD2Q_DUP:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2_DUP/VLD2Q_DUP:40:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_DUP/VLD2Q_DUP:41:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD2_DUP/VLD2Q_DUP:42:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD2_DUP/VLD2Q_DUP:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2_DUP/VLD2Q_DUP:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_DUP/VLD2Q_DUP:45:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD2_DUP/VLD2Q_DUP:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD2_DUP/VLD2Q_DUP:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VLD3_DUP/VLD3Q_DUP chunk 0 output:
+VLD3_DUP/VLD3Q_DUP:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff0, fffffff1, fffffff2, fffffff0, fffffff1,  }
+VLD3_DUP/VLD3Q_DUP:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff0,  }
+VLD3_DUP/VLD3Q_DUP:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD3_DUP/VLD3Q_DUP:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD3_DUP/VLD3Q_DUP:4:result_uint8x8 [] = { f0, f1, f2, f0, f1, f2, f0, f1,  }
+VLD3_DUP/VLD3Q_DUP:5:result_uint16x4 [] = { fff0, fff1, fff2, fff0,  }
+VLD3_DUP/VLD3Q_DUP:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD3_DUP/VLD3Q_DUP:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD3_DUP/VLD3Q_DUP:8:result_poly8x8 [] = { f0, f1, f2, f0, f1, f2, f0, f1,  }
+VLD3_DUP/VLD3Q_DUP:9:result_poly16x4 [] = { fff0, fff1, fff2, fff0,  }
+VLD3_DUP/VLD3Q_DUP:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD3_DUP/VLD3Q_DUP:11:result_float16x4 [] = { cc00, cb80, cb00, cc00,  }
+VLD3_DUP/VLD3Q_DUP:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD3_DUP/VLD3Q_DUP:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_DUP/VLD3Q_DUP:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD3_DUP/VLD3Q_DUP:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_DUP/VLD3Q_DUP:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD3_DUP/VLD3Q_DUP:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VLD3_DUP/VLD3Q_DUP chunk 1 output:
+VLD3_DUP/VLD3Q_DUP:24:result_int8x8 [] = { fffffff2, fffffff0, fffffff1, fffffff2, fffffff0, fffffff1, fffffff2, fffffff0,  }
+VLD3_DUP/VLD3Q_DUP:25:result_int16x4 [] = { fffffff1, fffffff2, fffffff0, fffffff1,  }
+VLD3_DUP/VLD3Q_DUP:26:result_int32x2 [] = { fffffff2, fffffff0,  }
+VLD3_DUP/VLD3Q_DUP:27:result_int64x1 [] = { fffffffffffffff1,  }
+VLD3_DUP/VLD3Q_DUP:28:result_uint8x8 [] = { f2, f0, f1, f2, f0, f1, f2, f0,  }
+VLD3_DUP/VLD3Q_DUP:29:result_uint16x4 [] = { fff1, fff2, fff0, fff1,  }
+VLD3_DUP/VLD3Q_DUP:30:result_uint32x2 [] = { fffffff2, fffffff0,  }
+VLD3_DUP/VLD3Q_DUP:31:result_uint64x1 [] = { fffffffffffffff1,  }
+VLD3_DUP/VLD3Q_DUP:32:result_poly8x8 [] = { f2, f0, f1, f2, f0, f1, f2, f0,  }
+VLD3_DUP/VLD3Q_DUP:33:result_poly16x4 [] = { fff1, fff2, fff0, fff1,  }
+VLD3_DUP/VLD3Q_DUP:34:result_float32x2 [] = { c1600000, c1800000,  }
+VLD3_DUP/VLD3Q_DUP:35:result_float16x4 [] = { cb80, cb00, cc00, cb80,  }
+VLD3_DUP/VLD3Q_DUP:36:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:37:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:38:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD3_DUP/VLD3Q_DUP:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_DUP/VLD3Q_DUP:40:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:41:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:42:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD3_DUP/VLD3Q_DUP:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_DUP/VLD3Q_DUP:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:45:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD3_DUP/VLD3Q_DUP:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VLD3_DUP/VLD3Q_DUP chunk 2 output:
+VLD3_DUP/VLD3Q_DUP:48:result_int8x8 [] = { fffffff1, fffffff2, fffffff0, fffffff1, fffffff2, fffffff0, fffffff1, fffffff2,  }
+VLD3_DUP/VLD3Q_DUP:49:result_int16x4 [] = { fffffff2, fffffff0, fffffff1, fffffff2,  }
+VLD3_DUP/VLD3Q_DUP:50:result_int32x2 [] = { fffffff1, fffffff2,  }
+VLD3_DUP/VLD3Q_DUP:51:result_int64x1 [] = { fffffffffffffff2,  }
+VLD3_DUP/VLD3Q_DUP:52:result_uint8x8 [] = { f1, f2, f0, f1, f2, f0, f1, f2,  }
+VLD3_DUP/VLD3Q_DUP:53:result_uint16x4 [] = { fff2, fff0, fff1, fff2,  }
+VLD3_DUP/VLD3Q_DUP:54:result_uint32x2 [] = { fffffff1, fffffff2,  }
+VLD3_DUP/VLD3Q_DUP:55:result_uint64x1 [] = { fffffffffffffff2,  }
+VLD3_DUP/VLD3Q_DUP:56:result_poly8x8 [] = { f1, f2, f0, f1, f2, f0, f1, f2,  }
+VLD3_DUP/VLD3Q_DUP:57:result_poly16x4 [] = { fff2, fff0, fff1, fff2,  }
+VLD3_DUP/VLD3Q_DUP:58:result_float32x2 [] = { c1700000, c1600000,  }
+VLD3_DUP/VLD3Q_DUP:59:result_float16x4 [] = { cb00, cc00, cb80, cb00,  }
+VLD3_DUP/VLD3Q_DUP:60:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:61:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:62:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD3_DUP/VLD3Q_DUP:63:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_DUP/VLD3Q_DUP:64:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:65:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:66:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD3_DUP/VLD3Q_DUP:67:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_DUP/VLD3Q_DUP:68:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:69:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:70:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD3_DUP/VLD3Q_DUP:71:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VLD4_DUP/VLD4Q_DUP chunk 0 output:
+VLD4_DUP/VLD4Q_DUP:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD4_DUP/VLD4Q_DUP:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD4_DUP/VLD4Q_DUP:4:result_uint8x8 [] = { f0, f1, f2, f3, f0, f1, f2, f3,  }
+VLD4_DUP/VLD4Q_DUP:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_DUP/VLD4Q_DUP:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD4_DUP/VLD4Q_DUP:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD4_DUP/VLD4Q_DUP:8:result_poly8x8 [] = { f0, f1, f2, f3, f0, f1, f2, f3,  }
+VLD4_DUP/VLD4Q_DUP:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_DUP/VLD4Q_DUP:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD4_DUP/VLD4Q_DUP:11:result_float16x4 [] = { cc00, cb80, cb00, ca80,  }
+VLD4_DUP/VLD4Q_DUP:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_DUP/VLD4Q_DUP:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_DUP/VLD4Q_DUP:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VLD4_DUP/VLD4Q_DUP chunk 1 output:
+VLD4_DUP/VLD4Q_DUP:24:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:25:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:26:result_int32x2 [] = { fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:27:result_int64x1 [] = { fffffffffffffff1,  }
+VLD4_DUP/VLD4Q_DUP:28:result_uint8x8 [] = { f0, f1, f2, f3, f0, f1, f2, f3,  }
+VLD4_DUP/VLD4Q_DUP:29:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_DUP/VLD4Q_DUP:30:result_uint32x2 [] = { fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:31:result_uint64x1 [] = { fffffffffffffff1,  }
+VLD4_DUP/VLD4Q_DUP:32:result_poly8x8 [] = { f0, f1, f2, f3, f0, f1, f2, f3,  }
+VLD4_DUP/VLD4Q_DUP:33:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_DUP/VLD4Q_DUP:34:result_float32x2 [] = { c1600000, c1500000,  }
+VLD4_DUP/VLD4Q_DUP:35:result_float16x4 [] = { cc00, cb80, cb00, ca80,  }
+VLD4_DUP/VLD4Q_DUP:36:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:37:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:38:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_DUP/VLD4Q_DUP:40:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:41:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:42:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_DUP/VLD4Q_DUP:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:45:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VLD4_DUP/VLD4Q_DUP chunk 2 output:
+VLD4_DUP/VLD4Q_DUP:48:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:49:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:50:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD4_DUP/VLD4Q_DUP:51:result_int64x1 [] = { fffffffffffffff2,  }
+VLD4_DUP/VLD4Q_DUP:52:result_uint8x8 [] = { f0, f1, f2, f3, f0, f1, f2, f3,  }
+VLD4_DUP/VLD4Q_DUP:53:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_DUP/VLD4Q_DUP:54:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD4_DUP/VLD4Q_DUP:55:result_uint64x1 [] = { fffffffffffffff2,  }
+VLD4_DUP/VLD4Q_DUP:56:result_poly8x8 [] = { f0, f1, f2, f3, f0, f1, f2, f3,  }
+VLD4_DUP/VLD4Q_DUP:57:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_DUP/VLD4Q_DUP:58:result_float32x2 [] = { c1800000, c1700000,  }
+VLD4_DUP/VLD4Q_DUP:59:result_float16x4 [] = { cc00, cb80, cb00, ca80,  }
+VLD4_DUP/VLD4Q_DUP:60:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:61:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:62:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:63:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_DUP/VLD4Q_DUP:64:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:65:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:66:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:67:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_DUP/VLD4Q_DUP:68:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:69:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:70:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:71:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VLD4_DUP/VLD4Q_DUP chunk 3 output:
+VLD4_DUP/VLD4Q_DUP:72:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:73:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:74:result_int32x2 [] = { fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:75:result_int64x1 [] = { fffffffffffffff3,  }
+VLD4_DUP/VLD4Q_DUP:76:result_uint8x8 [] = { f0, f1, f2, f3, f0, f1, f2, f3,  }
+VLD4_DUP/VLD4Q_DUP:77:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_DUP/VLD4Q_DUP:78:result_uint32x2 [] = { fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:79:result_uint64x1 [] = { fffffffffffffff3,  }
+VLD4_DUP/VLD4Q_DUP:80:result_poly8x8 [] = { f0, f1, f2, f3, f0, f1, f2, f3,  }
+VLD4_DUP/VLD4Q_DUP:81:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_DUP/VLD4Q_DUP:82:result_float32x2 [] = { c1600000, c1500000,  }
+VLD4_DUP/VLD4Q_DUP:83:result_float16x4 [] = { cc00, cb80, cb00, ca80,  }
+VLD4_DUP/VLD4Q_DUP:84:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:85:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:86:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:87:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_DUP/VLD4Q_DUP:88:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:89:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:90:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:91:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_DUP/VLD4Q_DUP:92:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:93:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:94:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:95:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMLA output:
+VMLA:0:result_int8x8 [] = { ffffffdf, ffffffe0, ffffffe1, ffffffe2, ffffffe3, ffffffe4, ffffffe5, ffffffe6,  }
+VMLA:1:result_int16x4 [] = { 1f8c, 1f8d, 1f8e, 1f8f,  }
+VMLA:2:result_int32x2 [] = { 2bf7, 2bf8,  }
+VMLA:3:result_int64x1 [] = { 3333333333333333,  }
+VMLA:4:result_uint8x8 [] = { 20, 21, 22, 23, 24, 25, 26, 27,  }
+VMLA:5:result_uint16x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLA:6:result_uint32x2 [] = { 43ac, 43ad,  }
+VMLA:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLA:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLA:10:result_float32x2 [] = { 43a14e76, 43a1ce76,  }
+VMLA:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMLA:12:result_int8x16 [] = { f, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 1a, 1b, 1c, 1d, 1e,  }
+VMLA:13:result_int16x8 [] = { 4830, 4831, 4832, 4833, 4834, 4835, 4836, 4837,  }
+VMLA:14:result_int32x4 [] = { 470f, 4710, 4711, 4712,  }
+VMLA:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLA:16:result_uint8x16 [] = { ac, ad, ae, af, b0, b1, b2, b3, b4, b5, b6, b7, b8, b9, ba, bb,  }
+VMLA:17:result_uint16x8 [] = { 3e07, 3e08, 3e09, 3e0a, 3e0b, 3e0c, 3e0d, 3e0e,  }
+VMLA:18:result_uint32x4 [] = { 3620, 3621, 3622, 3623,  }
+VMLA:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLA:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLA:22:result_float32x4 [] = { 45f0ae15, 45f0b615, 45f0be15, 45f0c615,  }
+VMLA:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMLS output:
+VMLS:0:result_int8x8 [] = { 1, 2, 3, 4, 5, 6, 7, 8,  }
+VMLS:1:result_int16x4 [] = { ffffe054, ffffe055, ffffe056, ffffe057,  }
+VMLS:2:result_int32x2 [] = { ffffd3e9, ffffd3ea,  }
+VMLS:3:result_int64x1 [] = { 3333333333333333,  }
+VMLS:4:result_uint8x8 [] = { c0, c1, c2, c3, c4, c5, c6, c7,  }
+VMLS:5:result_uint16x4 [] = { c1d9, c1da, c1db, c1dc,  }
+VMLS:6:result_uint32x2 [] = { ffffbc34, ffffbc35,  }
+VMLS:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLS:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLS:10:result_float32x2 [] = { c3b14e76, c3b0ce76,  }
+VMLS:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMLS:12:result_int8x16 [] = { ffffffd1, ffffffd2, ffffffd3, ffffffd4, ffffffd5, ffffffd6, ffffffd7, ffffffd8, ffffffd9, ffffffda, ffffffdb, ffffffdc, ffffffdd, ffffffde, ffffffdf, ffffffe0,  }
+VMLS:13:result_int16x8 [] = { ffffb7b0, ffffb7b1, ffffb7b2, ffffb7b3, ffffb7b4, ffffb7b5, ffffb7b6, ffffb7b7,  }
+VMLS:14:result_int32x4 [] = { ffffb8d1, ffffb8d2, ffffb8d3, ffffb8d4,  }
+VMLS:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLS:16:result_uint8x16 [] = { 34, 35, 36, 37, 38, 39, 3a, 3b, 3c, 3d, 3e, 3f, 40, 41, 42, 43,  }
+VMLS:17:result_uint16x8 [] = { c1d9, c1da, c1db, c1dc, c1dd, c1de, c1df, c1e0,  }
+VMLS:18:result_uint32x4 [] = { ffffc9c0, ffffc9c1, ffffc9c2, ffffc9c3,  }
+VMLS:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLS:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLS:22:result_float32x4 [] = { c5f1ae15, c5f1a615, c5f19e15, c5f19615,  }
+VMLS:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMUL output:
+VMUL:0:result_int8x8 [] = { fffffff0, 1, 12, 23, 34, 45, 56, 67,  }
+VMUL:1:result_int16x4 [] = { fffffde0, fffffe02, fffffe24, fffffe46,  }
+VMUL:2:result_int32x2 [] = { fffffcd0, fffffd03,  }
+VMUL:3:result_int64x1 [] = { 3333333333333333,  }
+VMUL:4:result_uint8x8 [] = { c0, 4, 48, 8c, d0, 14, 58, 9c,  }
+VMUL:5:result_uint16x4 [] = { fab0, fb05, fb5a, fbaf,  }
+VMUL:6:result_uint32x2 [] = { fffff9a0, fffffa06,  }
+VMUL:7:result_uint64x1 [] = { 3333333333333333,  }
+VMUL:8:result_poly8x8 [] = { c0, 84, 48, c, d0, 94, 58, 1c,  }
+VMUL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMUL:10:result_float32x2 [] = { c4053333, c3f9c000,  }
+VMUL:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMUL:12:result_int8x16 [] = { ffffff90, 7, 7e, fffffff5, 6c, ffffffe3, 5a, ffffffd1, 48, ffffffbf, 36, ffffffad, 24, ffffff9b, 12, ffffff89,  }
+VMUL:13:result_int16x8 [] = { fffff780, fffff808, fffff890, fffff918, fffff9a0, fffffa28, fffffab0, fffffb38,  }
+VMUL:14:result_int32x4 [] = { fffff670, fffff709, fffff7a2, fffff83b,  }
+VMUL:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMUL:16:result_uint8x16 [] = { 60, a, b4, 5e, 8, b2, 5c, 6, b0, 5a, 4, ae, 58, 2, ac, 56,  }
+VMUL:17:result_uint16x8 [] = { f450, f50b, f5c6, f681, f73c, f7f7, f8b2, f96d,  }
+VMUL:18:result_uint32x4 [] = { fffff340, fffff40c, fffff4d8, fffff5a4,  }
+VMUL:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMUL:20:result_poly8x16 [] = { 60, ca, 34, 9e, c8, 62, 9c, 36, 30, 9a, 64, ce, 98, 32, cc, 66,  }
+VMUL:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMUL:22:result_float32x4 [] = { c4c73333, c4bac000, c4ae4ccd, c4a1d999,  }
+VMUL:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMUL_LANE output:
+VMUL_LANE:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_LANE:1:result_int16x4 [] = { ffffffc0, ffffffc4, ffffffc8, ffffffcc,  }
+VMUL_LANE:2:result_int32x2 [] = { fffffde0, fffffe02,  }
+VMUL_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VMUL_LANE:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_LANE:5:result_uint16x4 [] = { bbc0, c004, c448, c88c,  }
+VMUL_LANE:6:result_uint32x2 [] = { fffface0, ffffb212,  }
+VMUL_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VMUL_LANE:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_LANE:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMUL_LANE:10:result_float32x2 [] = { c3b66666, c3ab0000,  }
+VMUL_LANE:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMUL_LANE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_LANE:13:result_int16x8 [] = { ffffffc0, ffffffc4, ffffffc8, ffffffcc, ffffffd0, ffffffd4, ffffffd8, ffffffdc,  }
+VMUL_LANE:14:result_int32x4 [] = { fffffde0, fffffe02, fffffe24, fffffe46,  }
+VMUL_LANE:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMUL_LANE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_LANE:17:result_uint16x8 [] = { bbc0, c004, c448, c88c, ccd0, d114, d558, d99c,  }
+VMUL_LANE:18:result_uint32x4 [] = { fffface0, ffffb212, ffffb744, ffffbc76,  }
+VMUL_LANE:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMUL_LANE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_LANE:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMUL_LANE:22:result_float32x4 [] = { c3b66666, c3ab0000, c39f9999, c3943333,  }
+VMUL_LANE:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMUL_N output:
+VMUL_N:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_N:1:result_int16x4 [] = { fffffef0, ffffff01, ffffff12, ffffff23,  }
+VMUL_N:2:result_int32x2 [] = { fffffde0, fffffe02,  }
+VMUL_N:3:result_int64x1 [] = { 3333333333333333,  }
+VMUL_N:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_N:5:result_uint16x4 [] = { fcd0, fd03, fd36, fd69,  }
+VMUL_N:6:result_uint32x2 [] = { fffffbc0, fffffc04,  }
+VMUL_N:7:result_uint64x1 [] = { 3333333333333333,  }
+VMUL_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMUL_N:10:result_float32x2 [] = { c3b26666, c3a74000,  }
+VMUL_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMUL_N:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_N:13:result_int16x8 [] = { fffffab0, fffffb05, fffffb5a, fffffbaf, fffffc04, fffffc59, fffffcae, fffffd03,  }
+VMUL_N:14:result_int32x4 [] = { fffff9a0, fffffa06, fffffa6c, fffffad2,  }
+VMUL_N:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMUL_N:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_N:17:result_uint16x8 [] = { f890, f907, f97e, f9f5, fa6c, fae3, fb5a, fbd1,  }
+VMUL_N:18:result_uint32x4 [] = { fffff780, fffff808, fffff890, fffff918,  }
+VMUL_N:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMUL_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMUL_N:22:result_float32x4 [] = { c4b1cccd, c4a6b000, c49b9333, c4907667,  }
+VMUL_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMULL_N output:
+VMULL_N:0:result_int32x4 [] = { 11000, 11000, 11000, 11000,  }
+VMULL_N:1:result_int64x2 [] = { 22000, 22000,  }
+VMULL_N:2:result_uint32x4 [] = { 33000, 33000, 33000, 33000,  }
+VMULL_N:3:result_uint64x2 [] = { 44000, 44000,  }
+
+VMLA_LANE output:
+VMLA_LANE:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_LANE:1:result_int16x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLA_LANE:2:result_int32x2 [] = { 3e07, 3e08,  }
+VMLA_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VMLA_LANE:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_LANE:5:result_uint16x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLA_LANE:6:result_uint32x2 [] = { 3e07, 3e08,  }
+VMLA_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLA_LANE:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_LANE:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLA_LANE:10:result_float32x2 [] = { 4418c687, 44190687,  }
+VMLA_LANE:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMLA_LANE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_LANE:13:result_int16x8 [] = { 3e07, 3e08, 3e09, 3e0a, 3e0b, 3e0c, 3e0d, 3e0e,  }
+VMLA_LANE:14:result_int32x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLA_LANE:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLA_LANE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_LANE:17:result_uint16x8 [] = { 3e07, 3e08, 3e09, 3e0a, 3e0b, 3e0c, 3e0d, 3e0e,  }
+VMLA_LANE:18:result_uint32x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLA_LANE:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLA_LANE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_LANE:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLA_LANE:22:result_float32x4 [] = { 441a3168, 441a7168, 441ab168, 441af168,  }
+VMLA_LANE:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMLS_LANE output:
+VMLS_LANE:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_LANE:1:result_int16x4 [] = { ffffc1d9, ffffc1da, ffffc1db, ffffc1dc,  }
+VMLS_LANE:2:result_int32x2 [] = { ffffc1d9, ffffc1da,  }
+VMLS_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VMLS_LANE:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_LANE:5:result_uint16x4 [] = { c1d9, c1da, c1db, c1dc,  }
+VMLS_LANE:6:result_uint32x2 [] = { ffffc1d9, ffffc1da,  }
+VMLS_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLS_LANE:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_LANE:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLS_LANE:10:result_float32x2 [] = { c420c687, c4208687,  }
+VMLS_LANE:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMLS_LANE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_LANE:13:result_int16x8 [] = { ffffc1d9, ffffc1da, ffffc1db, ffffc1dc, ffffc1dd, ffffc1de, ffffc1df, ffffc1e0,  }
+VMLS_LANE:14:result_int32x4 [] = { ffffc1d9, ffffc1da, ffffc1db, ffffc1dc,  }
+VMLS_LANE:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLS_LANE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_LANE:17:result_uint16x8 [] = { c1d9, c1da, c1db, c1dc, c1dd, c1de, c1df, c1e0,  }
+VMLS_LANE:18:result_uint32x4 [] = { ffffc1d9, ffffc1da, ffffc1db, ffffc1dc,  }
+VMLS_LANE:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLS_LANE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_LANE:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLS_LANE:22:result_float32x4 [] = { c4223168, c421f168, c421b168, c4217168,  }
+VMLS_LANE:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMLA_N output:
+VMLA_N:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_N:1:result_int16x4 [] = { 595, 596, 597, 598,  }
+VMLA_N:2:result_int32x2 [] = { b3a, b3b,  }
+VMLA_N:3:result_int64x1 [] = { 3333333333333333,  }
+VMLA_N:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_N:5:result_uint16x4 [] = { 10df, 10e0, 10e1, 10e2,  }
+VMLA_N:6:result_uint32x2 [] = { 1684, 1685,  }
+VMLA_N:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLA_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLA_N:10:result_float32x2 [] = { 4497deb8, 4497feb8,  }
+VMLA_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMLA_N:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_N:13:result_int16x8 [] = { 1c29, 1c2a, 1c2b, 1c2c, 1c2d, 1c2e, 1c2f, 1c30,  }
+VMLA_N:14:result_int32x4 [] = { 21ce, 21cf, 21d0, 21d1,  }
+VMLA_N:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLA_N:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_N:17:result_uint16x8 [] = { 2773, 2774, 2775, 2776, 2777, 2778, 2779, 277a,  }
+VMLA_N:18:result_uint32x4 [] = { 2d18, 2d19, 2d1a, 2d1b,  }
+VMLA_N:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLA_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLA_N:22:result_float32x4 [] = { 4568087b, 4568187b, 4568287b, 4568387b,  }
+VMLA_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMLS_N output:
+VMLS_N:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_N:1:result_int16x4 [] = { fffffa4b, fffffa4c, fffffa4d, fffffa4e,  }
+VMLS_N:2:result_int32x2 [] = { fffff4a6, fffff4a7,  }
+VMLS_N:3:result_int64x1 [] = { 3333333333333333,  }
+VMLS_N:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_N:5:result_uint16x4 [] = { ef01, ef02, ef03, ef04,  }
+VMLS_N:6:result_uint32x2 [] = { ffffe95c, ffffe95d,  }
+VMLS_N:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLS_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLS_N:10:result_float32x2 [] = { c49bdeb8, c49bbeb8,  }
+VMLS_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMLS_N:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_N:13:result_int16x8 [] = { ffffe3b7, ffffe3b8, ffffe3b9, ffffe3ba, ffffe3bb, ffffe3bc, ffffe3bd, ffffe3be,  }
+VMLS_N:14:result_int32x4 [] = { ffffde12, ffffde13, ffffde14, ffffde15,  }
+VMLS_N:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLS_N:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_N:17:result_uint16x8 [] = { d86d, d86e, d86f, d870, d871, d872, d873, d874,  }
+VMLS_N:18:result_uint32x4 [] = { ffffd2c8, ffffd2c9, ffffd2ca, ffffd2cb,  }
+VMLS_N:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLS_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLS_N:22:result_float32x4 [] = { c56a087b, c569f87b, c569e87b, c569d87b,  }
+VMLS_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSLI_N output:
+VSLI_N:0:result_int8x8 [] = { 20, 21, 22, 23, 24, 25, 26, 27,  }
+VSLI_N:1:result_int16x4 [] = { ffffffe0, ffffffe1, ffffffe2, ffffffe3,  }
+VSLI_N:2:result_int32x2 [] = { 6, 7,  }
+VSLI_N:3:result_int64x1 [] = { 64fffffff0,  }
+VSLI_N:4:result_uint8x8 [] = { 50, 51, 52, 53, 50, 51, 52, 53,  }
+VSLI_N:5:result_uint16x4 [] = { 7bf0, 7bf1, 7bf2, 7bf3,  }
+VSLI_N:6:result_uint32x2 [] = { 3ffffff0, 3ffffff1,  }
+VSLI_N:7:result_uint64x1 [] = { 10,  }
+VSLI_N:8:result_poly8x8 [] = { 50, 51, 52, 53, 50, 51, 52, 53,  }
+VSLI_N:9:result_poly16x4 [] = { 7bf0, 7bf1, 7bf2, 7bf3,  }
+VSLI_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSLI_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSLI_N:12:result_int8x16 [] = { ffffffd0, ffffffd1, ffffffd2, ffffffd3, ffffffd4, ffffffd5, ffffffd6, ffffffd7, ffffffd8, ffffffd9, ffffffda, ffffffdb, ffffffdc, ffffffdd, ffffffde, ffffffdf,  }
+VSLI_N:13:result_int16x8 [] = { ffffff60, ffffff61, ffffff62, ffffff63, ffffff64, ffffff65, ffffff66, ffffff67,  }
+VSLI_N:14:result_int32x4 [] = { fe2ffff0, fe2ffff1, fe2ffff2, fe2ffff3,  }
+VSLI_N:15:result_int64x2 [] = { 18fff0, 18fff1,  }
+VSLI_N:16:result_uint8x16 [] = { 60, 61, 62, 63, 64, 65, 66, 67, 60, 61, 62, 63, 64, 65, 66, 67,  }
+VSLI_N:17:result_uint16x8 [] = { 3ff0, 3ff1, 3ff2, 3ff3, 3ff4, 3ff5, 3ff6, 3ff7,  }
+VSLI_N:18:result_uint32x4 [] = { 1bfffff0, 1bfffff1, 1bfffff2, 1bfffff3,  }
+VSLI_N:19:result_uint64x2 [] = { 7ffffffffffff0, 7ffffffffffff1,  }
+VSLI_N:20:result_poly8x16 [] = { 60, 61, 62, 63, 64, 65, 66, 67, 60, 61, 62, 63, 64, 65, 66, 67,  }
+VSLI_N:21:result_poly16x8 [] = { 3ff0, 3ff1, 3ff2, 3ff3, 3ff4, 3ff5, 3ff6, 3ff7,  }
+VSLI_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSLI_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSLI_Nmax shift amount output:
+VSLI_N:0:result_int8x8 [] = { 70, 71, 72, 73, 74, 75, 76, 77,  }
+VSLI_N:1:result_int16x4 [] = { 7ff0, 7ff1, 7ff2, 7ff3,  }
+VSLI_N:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VSLI_N:3:result_int64x1 [] = { 7ffffffffffffff0,  }
+VSLI_N:4:result_uint8x8 [] = { 70, 71, 72, 73, 74, 75, 76, 77,  }
+VSLI_N:5:result_uint16x4 [] = { 7ff0, 7ff1, 7ff2, 7ff3,  }
+VSLI_N:6:result_uint32x2 [] = { 7ffffff0, 7ffffff1,  }
+VSLI_N:7:result_uint64x1 [] = { 7ffffffffffffff0,  }
+VSLI_N:8:result_poly8x8 [] = { 70, 71, 72, 73, 74, 75, 76, 77,  }
+VSLI_N:9:result_poly16x4 [] = { 7ff0, 7ff1, 7ff2, 7ff3,  }
+VSLI_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSLI_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSLI_N:12:result_int8x16 [] = { 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 7a, 7b, 7c, 7d, 7e, 7f,  }
+VSLI_N:13:result_int16x8 [] = { 7ff0, 7ff1, 7ff2, 7ff3, 7ff4, 7ff5, 7ff6, 7ff7,  }
+VSLI_N:14:result_int32x4 [] = { 7ffffff0, 7ffffff1, 7ffffff2, 7ffffff3,  }
+VSLI_N:15:result_int64x2 [] = { 7ffffffffffffff0, 7ffffffffffffff1,  }
+VSLI_N:16:result_uint8x16 [] = { 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 7a, 7b, 7c, 7d, 7e, 7f,  }
+VSLI_N:17:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VSLI_N:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VSLI_N:19:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VSLI_N:20:result_poly8x16 [] = { 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 7a, 7b, 7c, 7d, 7e, 7f,  }
+VSLI_N:21:result_poly16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VSLI_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSLI_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSRI_N output:
+VSRI_N:0:result_int8x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VSRI_N:1:result_int16x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VSRI_N:2:result_int32x2 [] = { 80000001, 80000001,  }
+VSRI_N:3:result_int64x1 [] = { ffffffff00000000,  }
+VSRI_N:4:result_uint8x8 [] = { c5, c5, c5, c5, c5, c5, c5, c5,  }
+VSRI_N:5:result_uint16x4 [] = { ffc0, ffc0, ffc0, ffc0,  }
+VSRI_N:6:result_uint32x2 [] = { fffffff0, fffffff0,  }
+VSRI_N:7:result_uint64x1 [] = { e000000000000000,  }
+VSRI_N:8:result_poly8x8 [] = { c5, c5, c5, c5, c5, c5, c5, c5,  }
+VSRI_N:9:result_poly16x4 [] = { ffc0, ffc0, ffc0, ffc0,  }
+VSRI_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSRI_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSRI_N:12:result_int8x16 [] = { fffffff7, fffffff7, fffffff7, fffffff7, fffffff7, fffffff7, fffffff7, fffffff7, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VSRI_N:13:result_int16x8 [] = { fffffffd, fffffffd, fffffffd, fffffffd, fffffffd, fffffffd, fffffffd, fffffffd,  }
+VSRI_N:14:result_int32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VSRI_N:15:result_int64x2 [] = { ffff000000000000, ffff000000000000,  }
+VSRI_N:16:result_uint8x16 [] = { e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1,  }
+VSRI_N:17:result_uint16x8 [] = { fff0, fff0, fff0, fff0, fff0, fff0, fff0, fff0,  }
+VSRI_N:18:result_uint32x4 [] = { fffffe00, fffffe00, fffffe00, fffffe00,  }
+VSRI_N:19:result_uint64x2 [] = { fffffffffffff800, fffffffffffff800,  }
+VSRI_N:20:result_poly8x16 [] = { e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1,  }
+VSRI_N:21:result_poly16x8 [] = { fff0, fff0, fff0, fff0, fff0, fff0, fff0, fff0,  }
+VSRI_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSRI_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSRI_N max shift amount output:
+VSRI_N:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VSRI_N:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VSRI_N:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VSRI_N:3:result_int64x1 [] = { fffffffffffffff0,  }
+VSRI_N:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VSRI_N:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VSRI_N:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VSRI_N:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VSRI_N:8:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VSRI_N:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VSRI_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSRI_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSRI_N:12:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VSRI_N:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VSRI_N:14:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VSRI_N:15:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VSRI_N:16:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VSRI_N:17:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VSRI_N:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VSRI_N:19:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VSRI_N:20:result_poly8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VSRI_N:21:result_poly16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VSRI_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSRI_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VTST/VTSTQ (signed input) output:
+VTST/VTSTQ:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTST/VTSTQ:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTST/VTSTQ:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTST/VTSTQ:3:result_int64x1 [] = { 3333333333333333,  }
+VTST/VTSTQ:4:result_uint8x8 [] = { 0, ff, ff, ff, ff, ff, ff, ff,  }
+VTST/VTSTQ:5:result_uint16x4 [] = { 0, ffff, 0, ffff,  }
+VTST/VTSTQ:6:result_uint32x2 [] = { 0, ffffffff,  }
+VTST/VTSTQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VTST/VTSTQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTST/VTSTQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTST/VTSTQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTST/VTSTQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VTST/VTSTQ:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTST/VTSTQ:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTST/VTSTQ:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTST/VTSTQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTST/VTSTQ:16:result_uint8x16 [] = { 0, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VTST/VTSTQ:17:result_uint16x8 [] = { 0, ffff, 0, ffff, ffff, ffff, ffff, ffff,  }
+VTST/VTSTQ:18:result_uint32x4 [] = { 0, ffffffff, 0, ffffffff,  }
+VTST/VTSTQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTST/VTSTQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTST/VTSTQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTST/VTSTQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTST/VTSTQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VTST/VTSTQ (unsigned input) output:
+VTST/VTSTQ:24:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTST/VTSTQ:25:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTST/VTSTQ:26:result_int32x2 [] = { 33333333, 33333333,  }
+VTST/VTSTQ:27:result_int64x1 [] = { 3333333333333333,  }
+VTST/VTSTQ:28:result_uint8x8 [] = { 0, ff, ff, ff, ff, ff, ff, ff,  }
+VTST/VTSTQ:29:result_uint16x4 [] = { 0, ffff, 0, ffff,  }
+VTST/VTSTQ:30:result_uint32x2 [] = { 0, ffffffff,  }
+VTST/VTSTQ:31:result_uint64x1 [] = { 3333333333333333,  }
+VTST/VTSTQ:32:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTST/VTSTQ:33:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTST/VTSTQ:34:result_float32x2 [] = { 33333333, 33333333,  }
+VTST/VTSTQ:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VTST/VTSTQ:36:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTST/VTSTQ:37:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTST/VTSTQ:38:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTST/VTSTQ:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTST/VTSTQ:40:result_uint8x16 [] = { 0, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VTST/VTSTQ:41:result_uint16x8 [] = { 0, ffff, 0, ffff, ffff, ffff, ffff, ffff,  }
+VTST/VTSTQ:42:result_uint32x4 [] = { 0, ffffffff, 0, ffffffff,  }
+VTST/VTSTQ:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTST/VTSTQ:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTST/VTSTQ:45:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTST/VTSTQ:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTST/VTSTQ:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VADDHN output:
+VADDHN:0:result_int8x8 [] = { 32, 32, 32, 32, 32, 32, 32, 32,  }
+VADDHN:1:result_int16x4 [] = { 32, 32, 32, 32,  }
+VADDHN:2:result_int32x2 [] = { 18, 18,  }
+VADDHN:3:result_int64x1 [] = { 3333333333333333,  }
+VADDHN:4:result_uint8x8 [] = { 3, 3, 3, 3, 3, 3, 3, 3,  }
+VADDHN:5:result_uint16x4 [] = { 37, 37, 37, 37,  }
+VADDHN:6:result_uint32x2 [] = { 3, 3,  }
+VADDHN:7:result_uint64x1 [] = { 3333333333333333,  }
+VADDHN:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDHN:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VADDHN:10:result_float32x2 [] = { 33333333, 33333333,  }
+VADDHN:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VADDHN:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDHN:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VADDHN:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VADDHN:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VADDHN:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDHN:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VADDHN:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VADDHN:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VADDHN:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDHN:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VADDHN:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VADDHN:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRADDHN output:
+VRADDHN:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRADDHN:1:result_int16x4 [] = { 33, 33, 33, 33,  }
+VRADDHN:2:result_int32x2 [] = { 19, 19,  }
+VRADDHN:3:result_int64x1 [] = { 3333333333333333,  }
+VRADDHN:4:result_uint8x8 [] = { 4, 4, 4, 4, 4, 4, 4, 4,  }
+VRADDHN:5:result_uint16x4 [] = { 38, 38, 38, 38,  }
+VRADDHN:6:result_uint32x2 [] = { 4, 4,  }
+VRADDHN:7:result_uint64x1 [] = { 3333333333333333,  }
+VRADDHN:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRADDHN:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRADDHN:10:result_float32x2 [] = { 33333333, 33333333,  }
+VRADDHN:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRADDHN:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRADDHN:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRADDHN:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRADDHN:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRADDHN:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRADDHN:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRADDHN:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRADDHN:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRADDHN:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRADDHN:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRADDHN:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRADDHN:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VADDL output:
+VADDL:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDL:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VADDL:2:result_int32x2 [] = { 33333333, 33333333,  }
+VADDL:3:result_int64x1 [] = { 3333333333333333,  }
+VADDL:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDL:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VADDL:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VADDL:7:result_uint64x1 [] = { 3333333333333333,  }
+VADDL:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VADDL:10:result_float32x2 [] = { 33333333, 33333333,  }
+VADDL:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VADDL:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDL:13:result_int16x8 [] = { ffffffe3, ffffffe4, ffffffe5, ffffffe6, ffffffe7, ffffffe8, ffffffe9, ffffffea,  }
+VADDL:14:result_int32x4 [] = { ffffffe2, ffffffe3, ffffffe4, ffffffe5,  }
+VADDL:15:result_int64x2 [] = { ffffffffffffffe0, ffffffffffffffe1,  }
+VADDL:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDL:17:result_uint16x8 [] = { 1e3, 1e4, 1e5, 1e6, 1e7, 1e8, 1e9, 1ea,  }
+VADDL:18:result_uint32x4 [] = { 1ffe1, 1ffe2, 1ffe3, 1ffe4,  }
+VADDL:19:result_uint64x2 [] = { 1ffffffe0, 1ffffffe1,  }
+VADDL:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDL:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VADDL:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VADDL:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VADDW output:
+VADDW:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDW:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VADDW:2:result_int32x2 [] = { 33333333, 33333333,  }
+VADDW:3:result_int64x1 [] = { 3333333333333333,  }
+VADDW:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDW:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VADDW:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VADDW:7:result_uint64x1 [] = { 3333333333333333,  }
+VADDW:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDW:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VADDW:10:result_float32x2 [] = { 33333333, 33333333,  }
+VADDW:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VADDW:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDW:13:result_int16x8 [] = { ffffffe3, ffffffe4, ffffffe5, ffffffe6, ffffffe7, ffffffe8, ffffffe9, ffffffea,  }
+VADDW:14:result_int32x4 [] = { ffffffe2, ffffffe3, ffffffe4, ffffffe5,  }
+VADDW:15:result_int64x2 [] = { ffffffffffffffe0, ffffffffffffffe1,  }
+VADDW:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDW:17:result_uint16x8 [] = { e3, e4, e5, e6, e7, e8, e9, ea,  }
+VADDW:18:result_uint32x4 [] = { ffe1, ffe2, ffe3, ffe4,  }
+VADDW:19:result_uint64x2 [] = { ffffffe0, ffffffe1,  }
+VADDW:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDW:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VADDW:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VADDW:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VHADD/VHADDQ output:
+VHADD/VHADDQ:0:result_int8x8 [] = { fffffff1, fffffff2, fffffff2, fffffff3, fffffff3, fffffff4, fffffff4, fffffff5,  }
+VHADD/VHADDQ:1:result_int16x4 [] = { fffffff1, fffffff1, fffffff2, fffffff2,  }
+VHADD/VHADDQ:2:result_int32x2 [] = { fffffff0, fffffff0,  }
+VHADD/VHADDQ:3:result_int64x1 [] = { 3333333333333333,  }
+VHADD/VHADDQ:4:result_uint8x8 [] = { f1, f2, f2, f3, f3, f4, f4, f5,  }
+VHADD/VHADDQ:5:result_uint16x4 [] = { fff0, fff1, fff1, fff2,  }
+VHADD/VHADDQ:6:result_uint32x2 [] = { fffffff0, fffffff0,  }
+VHADD/VHADDQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VHADD/VHADDQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VHADD/VHADDQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VHADD/VHADDQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VHADD/VHADDQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VHADD/VHADDQ:12:result_int8x16 [] = { fffffff2, fffffff2, fffffff3, fffffff3, fffffff4, fffffff4, fffffff5, fffffff5, fffffff6, fffffff6, fffffff7, fffffff7, fffffff8, fffffff8, fffffff9, fffffff9,  }
+VHADD/VHADDQ:13:result_int16x8 [] = { fffffff1, fffffff2, fffffff2, fffffff3, fffffff3, fffffff4, fffffff4, fffffff5,  }
+VHADD/VHADDQ:14:result_int32x4 [] = { fffffff0, fffffff1, fffffff1, fffffff2,  }
+VHADD/VHADDQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VHADD/VHADDQ:16:result_uint8x16 [] = { f4, f5, f5, f6, f6, f7, f7, f8, f8, f9, f9, fa, fa, fb, fb, fc,  }
+VHADD/VHADDQ:17:result_uint16x8 [] = { fff1, fff1, fff2, fff2, fff3, fff3, fff4, fff4,  }
+VHADD/VHADDQ:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff1, fffffff2,  }
+VHADD/VHADDQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VHADD/VHADDQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VHADD/VHADDQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VHADD/VHADDQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VHADD/VHADDQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRHADD/VRHADDQ output:
+VRHADD/VRHADDQ:0:result_int8x8 [] = { fffffff2, fffffff2, fffffff3, fffffff3, fffffff4, fffffff4, fffffff5, fffffff5,  }
+VRHADD/VRHADDQ:1:result_int16x4 [] = { fffffff1, fffffff2, fffffff2, fffffff3,  }
+VRHADD/VRHADDQ:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VRHADD/VRHADDQ:3:result_int64x1 [] = { 3333333333333333,  }
+VRHADD/VRHADDQ:4:result_uint8x8 [] = { f2, f2, f3, f3, f4, f4, f5, f5,  }
+VRHADD/VRHADDQ:5:result_uint16x4 [] = { fff1, fff1, fff2, fff2,  }
+VRHADD/VRHADDQ:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VRHADD/VRHADDQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VRHADD/VRHADDQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRHADD/VRHADDQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRHADD/VRHADDQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VRHADD/VRHADDQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRHADD/VRHADDQ:12:result_int8x16 [] = { fffffff2, fffffff3, fffffff3, fffffff4, fffffff4, fffffff5, fffffff5, fffffff6, fffffff6, fffffff7, fffffff7, fffffff8, fffffff8, fffffff9, fffffff9, fffffffa,  }
+VRHADD/VRHADDQ:13:result_int16x8 [] = { fffffff2, fffffff2, fffffff3, fffffff3, fffffff4, fffffff4, fffffff5, fffffff5,  }
+VRHADD/VRHADDQ:14:result_int32x4 [] = { fffffff1, fffffff1, fffffff2, fffffff2,  }
+VRHADD/VRHADDQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRHADD/VRHADDQ:16:result_uint8x16 [] = { f5, f5, f6, f6, f7, f7, f8, f8, f9, f9, fa, fa, fb, fb, fc, fc,  }
+VRHADD/VRHADDQ:17:result_uint16x8 [] = { fff1, fff2, fff2, fff3, fff3, fff4, fff4, fff5,  }
+VRHADD/VRHADDQ:18:result_uint32x4 [] = { fffffff1, fffffff1, fffffff2, fffffff2,  }
+VRHADD/VRHADDQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRHADD/VRHADDQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRHADD/VRHADDQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRHADD/VRHADDQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRHADD/VRHADDQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VHSUB/VHSUBQ output:
+VHSUB/VHSUBQ:0:result_int8x8 [] = { fffffffe, ffffffff, ffffffff, 0, 0, 1, 1, 2,  }
+VHSUB/VHSUBQ:1:result_int16x4 [] = { ffffffff, ffffffff, 0, 0,  }
+VHSUB/VHSUBQ:2:result_int32x2 [] = { 0, 0,  }
+VHSUB/VHSUBQ:3:result_int64x1 [] = { 3333333333333333,  }
+VHSUB/VHSUBQ:4:result_uint8x8 [] = { fe, ff, ff, 0, 0, 1, 1, 2,  }
+VHSUB/VHSUBQ:5:result_uint16x4 [] = { ffff, 0, 0, 1,  }
+VHSUB/VHSUBQ:6:result_uint32x2 [] = { 0, 0,  }
+VHSUB/VHSUBQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VHSUB/VHSUBQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VHSUB/VHSUBQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VHSUB/VHSUBQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VHSUB/VHSUBQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VHSUB/VHSUBQ:12:result_int8x16 [] = { fffffffe, fffffffe, ffffffff, ffffffff, 0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5,  }
+VHSUB/VHSUBQ:13:result_int16x8 [] = { fffffffe, ffffffff, ffffffff, 0, 0, 1, 1, 2,  }
+VHSUB/VHSUBQ:14:result_int32x4 [] = { ffffffff, 0, 0, 1,  }
+VHSUB/VHSUBQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VHSUB/VHSUBQ:16:result_uint8x16 [] = { fb, fc, fc, fd, fd, fe, fe, ff, ff, 0, 0, 1, 1, 2, 2, 3,  }
+VHSUB/VHSUBQ:17:result_uint16x8 [] = { ffff, ffff, 0, 0, 1, 1, 2, 2,  }
+VHSUB/VHSUBQ:18:result_uint32x4 [] = { ffffffff, 0, 0, 1,  }
+VHSUB/VHSUBQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VHSUB/VHSUBQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VHSUB/VHSUBQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VHSUB/VHSUBQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VHSUB/VHSUBQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSUBL output:
+VSUBL:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBL:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSUBL:2:result_int32x2 [] = { 33333333, 33333333,  }
+VSUBL:3:result_int64x1 [] = { 3333333333333333,  }
+VSUBL:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBL:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSUBL:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VSUBL:7:result_uint64x1 [] = { 3333333333333333,  }
+VSUBL:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSUBL:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSUBL:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSUBL:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBL:13:result_int16x8 [] = { fffffffd, fffffffe, ffffffff, 0, 1, 2, 3, 4,  }
+VSUBL:14:result_int32x4 [] = { fffffffe, ffffffff, 0, 1,  }
+VSUBL:15:result_int64x2 [] = { 0, 1,  }
+VSUBL:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBL:17:result_uint16x8 [] = { fffd, fffe, ffff, 0, 1, 2, 3, 4,  }
+VSUBL:18:result_uint32x4 [] = { ffffffff, 0, 1, 2,  }
+VSUBL:19:result_uint64x2 [] = { 0, 1,  }
+VSUBL:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBL:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSUBL:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSUBL:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSUBW output:
+VSUBW:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBW:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSUBW:2:result_int32x2 [] = { 33333333, 33333333,  }
+VSUBW:3:result_int64x1 [] = { 3333333333333333,  }
+VSUBW:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBW:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSUBW:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VSUBW:7:result_uint64x1 [] = { 3333333333333333,  }
+VSUBW:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBW:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSUBW:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSUBW:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSUBW:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBW:13:result_int16x8 [] = { fffffffd, fffffffe, ffffffff, 0, 1, 2, 3, 4,  }
+VSUBW:14:result_int32x4 [] = { fffffffe, ffffffff, 0, 1,  }
+VSUBW:15:result_int64x2 [] = { 0, 1,  }
+VSUBW:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBW:17:result_uint16x8 [] = { fefd, fefe, feff, ff00, ff01, ff02, ff03, ff04,  }
+VSUBW:18:result_uint32x4 [] = { fffeffff, ffff0000, ffff0001, ffff0002,  }
+VSUBW:19:result_uint64x2 [] = { ffffffff00000000, ffffffff00000001,  }
+VSUBW:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBW:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSUBW:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSUBW:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSUBHN output:
+VSUBHN:0:result_int8x8 [] = { 31, 31, 31, 31, 31, 31, 31, 31,  }
+VSUBHN:1:result_int16x4 [] = { 31, 31, 31, 31,  }
+VSUBHN:2:result_int32x2 [] = { 17, 17,  }
+VSUBHN:3:result_int64x1 [] = { 3333333333333333,  }
+VSUBHN:4:result_uint8x8 [] = { 2, 2, 2, 2, 2, 2, 2, 2,  }
+VSUBHN:5:result_uint16x4 [] = { 36, 36, 36, 36,  }
+VSUBHN:6:result_uint32x2 [] = { 2, 2,  }
+VSUBHN:7:result_uint64x1 [] = { 3333333333333333,  }
+VSUBHN:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBHN:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSUBHN:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSUBHN:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSUBHN:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBHN:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSUBHN:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSUBHN:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VSUBHN:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBHN:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSUBHN:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSUBHN:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VSUBHN:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBHN:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSUBHN:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSUBHN:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSUBHN output:
+VRSUBHN:0:result_int8x8 [] = { 31, 31, 31, 31, 31, 31, 31, 31,  }
+VRSUBHN:1:result_int16x4 [] = { 31, 31, 31, 31,  }
+VRSUBHN:2:result_int32x2 [] = { 17, 17,  }
+VRSUBHN:3:result_int64x1 [] = { 3333333333333333,  }
+VRSUBHN:4:result_uint8x8 [] = { 2, 2, 2, 2, 2, 2, 2, 2,  }
+VRSUBHN:5:result_uint16x4 [] = { 36, 36, 36, 36,  }
+VRSUBHN:6:result_uint32x2 [] = { 2, 2,  }
+VRSUBHN:7:result_uint64x1 [] = { 3333333333333333,  }
+VRSUBHN:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSUBHN:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSUBHN:10:result_float32x2 [] = { 33333333, 33333333,  }
+VRSUBHN:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSUBHN:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSUBHN:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSUBHN:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSUBHN:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRSUBHN:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSUBHN:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSUBHN:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSUBHN:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRSUBHN:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSUBHN:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSUBHN:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSUBHN:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMVN/VMVNQ output:
+VMVN/VMVNQ:0:result_int8x8 [] = { f, e, d, c, b, a, 9, 8,  }
+VMVN/VMVNQ:1:result_int16x4 [] = { f, e, d, c,  }
+VMVN/VMVNQ:2:result_int32x2 [] = { f, e,  }
+VMVN/VMVNQ:3:result_int64x1 [] = { 3333333333333333,  }
+VMVN/VMVNQ:4:result_uint8x8 [] = { f, e, d, c, b, a, 9, 8,  }
+VMVN/VMVNQ:5:result_uint16x4 [] = { f, e, d, c,  }
+VMVN/VMVNQ:6:result_uint32x2 [] = { f, e,  }
+VMVN/VMVNQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VMVN/VMVNQ:8:result_poly8x8 [] = { f, e, d, c, b, a, 9, 8,  }
+VMVN/VMVNQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMVN/VMVNQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMVN/VMVNQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMVN/VMVNQ:12:result_int8x16 [] = { f, e, d, c, b, a, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0,  }
+VMVN/VMVNQ:13:result_int16x8 [] = { f, e, d, c, b, a, 9, 8,  }
+VMVN/VMVNQ:14:result_int32x4 [] = { f, e, d, c,  }
+VMVN/VMVNQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMVN/VMVNQ:16:result_uint8x16 [] = { f, e, d, c, b, a, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0,  }
+VMVN/VMVNQ:17:result_uint16x8 [] = { f, e, d, c, b, a, 9, 8,  }
+VMVN/VMVNQ:18:result_uint32x4 [] = { f, e, d, c,  }
+VMVN/VMVNQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMVN/VMVNQ:20:result_poly8x16 [] = { f, e, d, c, b, a, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0,  }
+VMVN/VMVNQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMVN/VMVNQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMVN/VMVNQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQMOVN cumulative saturation output:
+VQMOVN:0:vqmovn_s16 Neon cumulative saturation 0
+VQMOVN:1:vqmovn_s32 Neon cumulative saturation 0
+VQMOVN:2:vqmovn_s64 Neon cumulative saturation 0
+VQMOVN:3:vqmovn_u16 Neon cumulative saturation 0
+VQMOVN:4:vqmovn_u32 Neon cumulative saturation 0
+VQMOVN:5:vqmovn_u64 Neon cumulative saturation 0
+
+VQMOVN output:
+VQMOVN:6:result_int8x8 [] = { 12, 12, 12, 12, 12, 12, 12, 12,  }
+VQMOVN:7:result_int16x4 [] = { 1278, 1278, 1278, 1278,  }
+VQMOVN:8:result_int32x2 [] = { 12345678, 12345678,  }
+VQMOVN:9:result_int64x1 [] = { 3333333333333333,  }
+VQMOVN:10:result_uint8x8 [] = { 82, 82, 82, 82, 82, 82, 82, 82,  }
+VQMOVN:11:result_uint16x4 [] = { 8765, 8765, 8765, 8765,  }
+VQMOVN:12:result_uint32x2 [] = { 87654321, 87654321,  }
+VQMOVN:13:result_uint64x1 [] = { 3333333333333333,  }
+VQMOVN:14:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVN:15:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQMOVN:16:result_float32x2 [] = { 33333333, 33333333,  }
+VQMOVN:17:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQMOVN:18:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVN:19:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVN:20:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVN:21:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQMOVN:22:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVN:23:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVN:24:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVN:25:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQMOVN:26:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVN:27:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVN:28:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVN:29:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQMOVN cumulative saturation output:
+VQMOVN:30:vqmovn_s16 Neon cumulative saturation 1
+VQMOVN:31:vqmovn_s32 Neon cumulative saturation 1
+VQMOVN:32:vqmovn_s64 Neon cumulative saturation 1
+VQMOVN:33:vqmovn_u16 Neon cumulative saturation 1
+VQMOVN:34:vqmovn_u32 Neon cumulative saturation 1
+VQMOVN:35:vqmovn_u64 Neon cumulative saturation 1
+
+VQMOVN output:
+VQMOVN:36:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQMOVN:37:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQMOVN:38:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQMOVN:39:result_int64x1 [] = { 3333333333333333,  }
+VQMOVN:40:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQMOVN:41:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQMOVN:42:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQMOVN:43:result_uint64x1 [] = { 3333333333333333,  }
+VQMOVN:44:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVN:45:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQMOVN:46:result_float32x2 [] = { 33333333, 33333333,  }
+VQMOVN:47:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQMOVN:48:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVN:49:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVN:50:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVN:51:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQMOVN:52:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVN:53:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVN:54:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVN:55:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQMOVN:56:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVN:57:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVN:58:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVN:59:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQMOVUN cumulative saturation output:
+VQMOVUN:0:vqmovun_s16 Neon cumulative saturation 0
+VQMOVUN:1:vqmovun_s32 Neon cumulative saturation 0
+VQMOVUN:2:vqmovun_s64 Neon cumulative saturation 0
+
+VQMOVUN output:
+VQMOVUN:3:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:4:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQMOVUN:5:result_int32x2 [] = { 33333333, 33333333,  }
+VQMOVUN:6:result_int64x1 [] = { 3333333333333333,  }
+VQMOVUN:7:result_uint8x8 [] = { 34, 34, 34, 34, 34, 34, 34, 34,  }
+VQMOVUN:8:result_uint16x4 [] = { 5678, 5678, 5678, 5678,  }
+VQMOVUN:9:result_uint32x2 [] = { 12345678, 12345678,  }
+VQMOVUN:10:result_uint64x1 [] = { 3333333333333333,  }
+VQMOVUN:11:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:12:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQMOVUN:13:result_float32x2 [] = { 33333333, 33333333,  }
+VQMOVUN:14:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQMOVUN:15:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:16:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVUN:17:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVUN:18:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQMOVUN:19:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:20:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVUN:21:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVUN:22:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQMOVUN:23:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:24:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVUN:25:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVUN:26:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQMOVUN (negative input) cumulative saturation output:
+VQMOVUN:27:vqmovun_s16 Neon cumulative saturation 1
+VQMOVUN:28:vqmovun_s32 Neon cumulative saturation 1
+VQMOVUN:29:vqmovun_s64 Neon cumulative saturation 1
+
+VQMOVUN (negative input) output:
+VQMOVUN:30:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:31:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQMOVUN:32:result_int32x2 [] = { 33333333, 33333333,  }
+VQMOVUN:33:result_int64x1 [] = { 3333333333333333,  }
+VQMOVUN:34:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQMOVUN:35:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQMOVUN:36:result_uint32x2 [] = { 0, 0,  }
+VQMOVUN:37:result_uint64x1 [] = { 3333333333333333,  }
+VQMOVUN:38:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:39:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQMOVUN:40:result_float32x2 [] = { 33333333, 33333333,  }
+VQMOVUN:41:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQMOVUN:42:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:43:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVUN:44:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVUN:45:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQMOVUN:46:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:47:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVUN:48:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVUN:49:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQMOVUN:50:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:51:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVUN:52:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVUN:53:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHR_N output:
+VRSHR_N:0:result_int8x8 [] = { fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb, fffffffc,  }
+VRSHR_N:1:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHR_N:2:result_int32x2 [] = { fffffffc, fffffffc,  }
+VRSHR_N:3:result_int64x1 [] = { 0,  }
+VRSHR_N:4:result_uint8x8 [] = { 3c, 3c, 3d, 3d, 3d, 3d, 3e, 3e,  }
+VRSHR_N:5:result_uint16x4 [] = { 1ffe, 1ffe, 1ffe, 1ffe,  }
+VRSHR_N:6:result_uint32x2 [] = { 8000000, 8000000,  }
+VRSHR_N:7:result_uint64x1 [] = { 80000000,  }
+VRSHR_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHR_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHR_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHR_N:12:result_int8x16 [] = { fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb, fffffffc, fffffffc, fffffffd, fffffffd, fffffffe, fffffffe, ffffffff, ffffffff, 0,  }
+VRSHR_N:13:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHR_N:14:result_int32x4 [] = { fffffffc, fffffffc, fffffffd, fffffffd,  }
+VRSHR_N:15:result_int64x2 [] = { 0, 0,  }
+VRSHR_N:16:result_uint8x16 [] = { 3c, 3c, 3d, 3d, 3d, 3d, 3e, 3e, 3e, 3e, 3f, 3f, 3f, 3f, 40, 40,  }
+VRSHR_N:17:result_uint16x8 [] = { 1ffe, 1ffe, 1ffe, 1ffe, 1fff, 1fff, 1fff, 1fff,  }
+VRSHR_N:18:result_uint32x4 [] = { 8000000, 8000000, 8000000, 8000000,  }
+VRSHR_N:19:result_uint64x2 [] = { 80000000, 80000000,  }
+VRSHR_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHR_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHR_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHR_N (overflow test: max shift amount, positive input) output:
+VRSHR_N:24:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHR_N:25:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHR_N:26:result_int32x2 [] = { 0, 0,  }
+VRSHR_N:27:result_int64x1 [] = { 0,  }
+VRSHR_N:28:result_uint8x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSHR_N:29:result_uint16x4 [] = { 1, 1, 1, 1,  }
+VRSHR_N:30:result_uint32x2 [] = { 1, 1,  }
+VRSHR_N:31:result_uint64x1 [] = { 1,  }
+VRSHR_N:32:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:33:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHR_N:34:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHR_N:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHR_N:36:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHR_N:37:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHR_N:38:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSHR_N:39:result_int64x2 [] = { 0, 0,  }
+VRSHR_N:40:result_uint8x16 [] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSHR_N:41:result_uint16x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSHR_N:42:result_uint32x4 [] = { 1, 1, 1, 1,  }
+VRSHR_N:43:result_uint64x2 [] = { 1, 1,  }
+VRSHR_N:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:45:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHR_N:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHR_N:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHR_N (overflow test: shift by 1, with negative input) output:
+VRSHR_N:48:result_int8x8 [] = { 40, 40, 40, 40, 40, 40, 40, 40,  }
+VRSHR_N:49:result_int16x4 [] = { 4000, 4000, 4000, 4000,  }
+VRSHR_N:50:result_int32x2 [] = { 40000000, 40000000,  }
+VRSHR_N:51:result_int64x1 [] = { 4000000000000000,  }
+VRSHR_N:52:result_uint8x8 [] = { 80, 80, 80, 80, 80, 80, 80, 80,  }
+VRSHR_N:53:result_uint16x4 [] = { 8000, 8000, 8000, 8000,  }
+VRSHR_N:54:result_uint32x2 [] = { 80000000, 80000000,  }
+VRSHR_N:55:result_uint64x1 [] = { 8000000000000000,  }
+VRSHR_N:56:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:57:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHR_N:58:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHR_N:59:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHR_N:60:result_int8x16 [] = { 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40,  }
+VRSHR_N:61:result_int16x8 [] = { 4000, 4000, 4000, 4000, 4000, 4000, 4000, 4000,  }
+VRSHR_N:62:result_int32x4 [] = { 40000000, 40000000, 40000000, 40000000,  }
+VRSHR_N:63:result_int64x2 [] = { 4000000000000000, 4000000000000000,  }
+VRSHR_N:64:result_uint8x16 [] = { 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80,  }
+VRSHR_N:65:result_uint16x8 [] = { 8000, 8000, 8000, 8000, 8000, 8000, 8000, 8000,  }
+VRSHR_N:66:result_uint32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VRSHR_N:67:result_uint64x2 [] = { 8000000000000000, 8000000000000000,  }
+VRSHR_N:68:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:69:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHR_N:70:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHR_N:71:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHR_N (overflow test: shift by 3, positive input) output:
+VRSHR_N:72:result_int8x8 [] = { 10, 10, 10, 10, 10, 10, 10, 10,  }
+VRSHR_N:73:result_int16x4 [] = { 1000, 1000, 1000, 1000,  }
+VRSHR_N:74:result_int32x2 [] = { 10000000, 10000000,  }
+VRSHR_N:75:result_int64x1 [] = { 1000000000000000,  }
+VRSHR_N:76:result_uint8x8 [] = { 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSHR_N:77:result_uint16x4 [] = { 2000, 2000, 2000, 2000,  }
+VRSHR_N:78:result_uint32x2 [] = { 20000000, 20000000,  }
+VRSHR_N:79:result_uint64x1 [] = { 2000000000000000,  }
+VRSHR_N:80:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:81:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHR_N:82:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHR_N:83:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHR_N:84:result_int8x16 [] = { 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10,  }
+VRSHR_N:85:result_int16x8 [] = { 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000,  }
+VRSHR_N:86:result_int32x4 [] = { 10000000, 10000000, 10000000, 10000000,  }
+VRSHR_N:87:result_int64x2 [] = { 1000000000000000, 1000000000000000,  }
+VRSHR_N:88:result_uint8x16 [] = { 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSHR_N:89:result_uint16x8 [] = { 2000, 2000, 2000, 2000, 2000, 2000, 2000, 2000,  }
+VRSHR_N:90:result_uint32x4 [] = { 20000000, 20000000, 20000000, 20000000,  }
+VRSHR_N:91:result_uint64x2 [] = { 2000000000000000, 2000000000000000,  }
+VRSHR_N:92:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:93:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHR_N:94:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHR_N:95:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHR_N (overflow test: shift by 1, with negative input) output:
+VRSHR_N:96:result_int8x8 [] = { ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0,  }
+VRSHR_N:97:result_int16x4 [] = { ffffc000, ffffc000, ffffc000, ffffc000,  }
+VRSHR_N:98:result_int32x2 [] = { c0000000, c0000000,  }
+VRSHR_N:99:result_int64x1 [] = { c000000000000000,  }
+VRSHR_N:100:result_uint8x8 [] = { 80, 80, 80, 80, 80, 80, 80, 80,  }
+VRSHR_N:101:result_uint16x4 [] = { 8000, 8000, 8000, 8000,  }
+VRSHR_N:102:result_uint32x2 [] = { 80000000, 80000000,  }
+VRSHR_N:103:result_uint64x1 [] = { 8000000000000000,  }
+VRSHR_N:104:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:105:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHR_N:106:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHR_N:107:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHR_N:108:result_int8x16 [] = { ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0,  }
+VRSHR_N:109:result_int16x8 [] = { ffffc000, ffffc000, ffffc000, ffffc000, ffffc000, ffffc000, ffffc000, ffffc000,  }
+VRSHR_N:110:result_int32x4 [] = { c0000000, c0000000, c0000000, c0000000,  }
+VRSHR_N:111:result_int64x2 [] = { c000000000000000, c000000000000000,  }
+VRSHR_N:112:result_uint8x16 [] = { 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80,  }
+VRSHR_N:113:result_uint16x8 [] = { 8000, 8000, 8000, 8000, 8000, 8000, 8000, 8000,  }
+VRSHR_N:114:result_uint32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VRSHR_N:115:result_uint64x2 [] = { 8000000000000000, 8000000000000000,  }
+VRSHR_N:116:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:117:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHR_N:118:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHR_N:119:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHR_N (overflow test: shift by 3, with negative input) output:
+VRSHR_N:120:result_int8x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VRSHR_N:121:result_int16x4 [] = { fffff000, fffff000, fffff000, fffff000,  }
+VRSHR_N:122:result_int32x2 [] = { f0000000, f0000000,  }
+VRSHR_N:123:result_int64x1 [] = { f000000000000000,  }
+VRSHR_N:124:result_uint8x8 [] = { 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSHR_N:125:result_uint16x4 [] = { 2000, 2000, 2000, 2000,  }
+VRSHR_N:126:result_uint32x2 [] = { 20000000, 20000000,  }
+VRSHR_N:127:result_uint64x1 [] = { 2000000000000000,  }
+VRSHR_N:128:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:129:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHR_N:130:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHR_N:131:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHR_N:132:result_int8x16 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VRSHR_N:133:result_int16x8 [] = { fffff000, fffff000, fffff000, fffff000, fffff000, fffff000, fffff000, fffff000,  }
+VRSHR_N:134:result_int32x4 [] = { f0000000, f0000000, f0000000, f0000000,  }
+VRSHR_N:135:result_int64x2 [] = { f000000000000000, f000000000000000,  }
+VRSHR_N:136:result_uint8x16 [] = { 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSHR_N:137:result_uint16x8 [] = { 2000, 2000, 2000, 2000, 2000, 2000, 2000, 2000,  }
+VRSHR_N:138:result_uint32x4 [] = { 20000000, 20000000, 20000000, 20000000,  }
+VRSHR_N:139:result_uint64x2 [] = { 2000000000000000, 2000000000000000,  }
+VRSHR_N:140:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:141:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHR_N:142:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHR_N:143:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSRA_N output:
+VRSRA_N:0:result_int8x8 [] = { fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff, 0,  }
+VRSRA_N:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VRSRA_N:2:result_int32x2 [] = { fffffffd, fffffffe,  }
+VRSRA_N:3:result_int64x1 [] = { fffffffffffffff0,  }
+VRSRA_N:4:result_uint8x8 [] = { 5, 6, 7, 8, 9, a, b, c,  }
+VRSRA_N:5:result_uint16x4 [] = { fffd, fffe, ffff, 0,  }
+VRSRA_N:6:result_uint32x2 [] = { fffffff4, fffffff5,  }
+VRSRA_N:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VRSRA_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSRA_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VRSRA_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:12:result_int8x16 [] = { fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff, 0, 1, 2, 3, 4, 5, 6, 7, 8,  }
+VRSRA_N:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VRSRA_N:14:result_int32x4 [] = { fffffffd, fffffffe, ffffffff, 0,  }
+VRSRA_N:15:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VRSRA_N:16:result_uint8x16 [] = { 5, 6, 7, 8, 9, a, b, c, d, e, f, 10, 11, 12, 13, 14,  }
+VRSRA_N:17:result_uint16x8 [] = { fffd, fffe, ffff, 0, 1, 2, 3, 4,  }
+VRSRA_N:18:result_uint32x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VRSRA_N:19:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VRSRA_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSRA_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSRA_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSRA_N (checking overflow: shift by 1, positive input) output:
+VRSRA_N:24:result_int8x8 [] = { 40, 40, 40, 40, 40, 40, 40, 40,  }
+VRSRA_N:25:result_int16x4 [] = { 4000, 4000, 4000, 4000,  }
+VRSRA_N:26:result_int32x2 [] = { 40000000, 40000000,  }
+VRSRA_N:27:result_int64x1 [] = { 4000000000000000,  }
+VRSRA_N:28:result_uint8x8 [] = { 80, 80, 80, 80, 80, 80, 80, 80,  }
+VRSRA_N:29:result_uint16x4 [] = { 8000, 8000, 8000, 8000,  }
+VRSRA_N:30:result_uint32x2 [] = { 80000000, 80000000,  }
+VRSRA_N:31:result_uint64x1 [] = { 8000000000000000,  }
+VRSRA_N:32:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:33:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSRA_N:34:result_float32x2 [] = { 33333333, 33333333,  }
+VRSRA_N:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:36:result_int8x16 [] = { 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40,  }
+VRSRA_N:37:result_int16x8 [] = { 4000, 4000, 4000, 4000, 4000, 4000, 4000, 4000,  }
+VRSRA_N:38:result_int32x4 [] = { 40000000, 40000000, 40000000, 40000000,  }
+VRSRA_N:39:result_int64x2 [] = { 4000000000000000, 4000000000000000,  }
+VRSRA_N:40:result_uint8x16 [] = { 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80,  }
+VRSRA_N:41:result_uint16x8 [] = { 8000, 8000, 8000, 8000, 8000, 8000, 8000, 8000,  }
+VRSRA_N:42:result_uint32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VRSRA_N:43:result_uint64x2 [] = { 8000000000000000, 8000000000000000,  }
+VRSRA_N:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:45:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSRA_N:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSRA_N:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSRA_N (checking overflow: shift by 3, positive input) output:
+VRSRA_N:48:result_int8x8 [] = { 10, 10, 10, 10, 10, 10, 10, 10,  }
+VRSRA_N:49:result_int16x4 [] = { 1000, 1000, 1000, 1000,  }
+VRSRA_N:50:result_int32x2 [] = { 10000000, 10000000,  }
+VRSRA_N:51:result_int64x1 [] = { 1000000000000000,  }
+VRSRA_N:52:result_uint8x8 [] = { 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSRA_N:53:result_uint16x4 [] = { 2000, 2000, 2000, 2000,  }
+VRSRA_N:54:result_uint32x2 [] = { 20000000, 20000000,  }
+VRSRA_N:55:result_uint64x1 [] = { 2000000000000000,  }
+VRSRA_N:56:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:57:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSRA_N:58:result_float32x2 [] = { 33333333, 33333333,  }
+VRSRA_N:59:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:60:result_int8x16 [] = { 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10,  }
+VRSRA_N:61:result_int16x8 [] = { 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000,  }
+VRSRA_N:62:result_int32x4 [] = { 10000000, 10000000, 10000000, 10000000,  }
+VRSRA_N:63:result_int64x2 [] = { 1000000000000000, 1000000000000000,  }
+VRSRA_N:64:result_uint8x16 [] = { 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSRA_N:65:result_uint16x8 [] = { 2000, 2000, 2000, 2000, 2000, 2000, 2000, 2000,  }
+VRSRA_N:66:result_uint32x4 [] = { 20000000, 20000000, 20000000, 20000000,  }
+VRSRA_N:67:result_uint64x2 [] = { 2000000000000000, 2000000000000000,  }
+VRSRA_N:68:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:69:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSRA_N:70:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSRA_N:71:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSRA_N (checking overflow: shift by max, positive input) output:
+VRSRA_N:72:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSRA_N:73:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:74:result_int32x2 [] = { 0, 0,  }
+VRSRA_N:75:result_int64x1 [] = { 0,  }
+VRSRA_N:76:result_uint8x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:77:result_uint16x4 [] = { 1, 1, 1, 1,  }
+VRSRA_N:78:result_uint32x2 [] = { 1, 1,  }
+VRSRA_N:79:result_uint64x1 [] = { 1,  }
+VRSRA_N:80:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:81:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSRA_N:82:result_float32x2 [] = { 33333333, 33333333,  }
+VRSRA_N:83:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:84:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSRA_N:85:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSRA_N:86:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:87:result_int64x2 [] = { 0, 0,  }
+VRSRA_N:88:result_uint8x16 [] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:89:result_uint16x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:90:result_uint32x4 [] = { 1, 1, 1, 1,  }
+VRSRA_N:91:result_uint64x2 [] = { 1, 1,  }
+VRSRA_N:92:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:93:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSRA_N:94:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSRA_N:95:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSRA_N (checking overflow: shift by 1, negative input) output:
+VRSRA_N:96:result_int8x8 [] = { ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0,  }
+VRSRA_N:97:result_int16x4 [] = { ffffc000, ffffc000, ffffc000, ffffc000,  }
+VRSRA_N:98:result_int32x2 [] = { c0000000, c0000000,  }
+VRSRA_N:99:result_int64x1 [] = { c000000000000000,  }
+VRSRA_N:100:result_uint8x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:101:result_uint16x4 [] = { 1, 1, 1, 1,  }
+VRSRA_N:102:result_uint32x2 [] = { 1, 1,  }
+VRSRA_N:103:result_uint64x1 [] = { 1,  }
+VRSRA_N:104:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:105:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSRA_N:106:result_float32x2 [] = { 33333333, 33333333,  }
+VRSRA_N:107:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:108:result_int8x16 [] = { ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0,  }
+VRSRA_N:109:result_int16x8 [] = { ffffc000, ffffc000, ffffc000, ffffc000, ffffc000, ffffc000, ffffc000, ffffc000,  }
+VRSRA_N:110:result_int32x4 [] = { c0000000, c0000000, c0000000, c0000000,  }
+VRSRA_N:111:result_int64x2 [] = { c000000000000000, c000000000000000,  }
+VRSRA_N:112:result_uint8x16 [] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:113:result_uint16x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:114:result_uint32x4 [] = { 1, 1, 1, 1,  }
+VRSRA_N:115:result_uint64x2 [] = { 1, 1,  }
+VRSRA_N:116:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:117:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSRA_N:118:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSRA_N:119:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSRA_N (checking overflow: shift by max, negative input) output:
+VRSRA_N:120:result_int8x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VRSRA_N:121:result_int16x4 [] = { fffff000, fffff000, fffff000, fffff000,  }
+VRSRA_N:122:result_int32x2 [] = { f0000000, f0000000,  }
+VRSRA_N:123:result_int64x1 [] = { f000000000000000,  }
+VRSRA_N:124:result_uint8x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:125:result_uint16x4 [] = { 1, 1, 1, 1,  }
+VRSRA_N:126:result_uint32x2 [] = { 1, 1,  }
+VRSRA_N:127:result_uint64x1 [] = { 1,  }
+VRSRA_N:128:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:129:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSRA_N:130:result_float32x2 [] = { 33333333, 33333333,  }
+VRSRA_N:131:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:132:result_int8x16 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VRSRA_N:133:result_int16x8 [] = { fffff000, fffff000, fffff000, fffff000, fffff000, fffff000, fffff000, fffff000,  }
+VRSRA_N:134:result_int32x4 [] = { f0000000, f0000000, f0000000, f0000000,  }
+VRSRA_N:135:result_int64x2 [] = { f000000000000000, f000000000000000,  }
+VRSRA_N:136:result_uint8x16 [] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:137:result_uint16x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:138:result_uint32x4 [] = { 1, 1, 1, 1,  }
+VRSRA_N:139:result_uint64x2 [] = { 1, 1,  }
+VRSRA_N:140:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:141:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSRA_N:142:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSRA_N:143:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSRA_N (checking overflow: shift by max, negative input) output:
+VRSRA_N:144:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSRA_N:145:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:146:result_int32x2 [] = { 0, 0,  }
+VRSRA_N:147:result_int64x1 [] = { 0,  }
+VRSRA_N:148:result_uint8x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:149:result_uint16x4 [] = { 1, 1, 1, 1,  }
+VRSRA_N:150:result_uint32x2 [] = { 1, 1,  }
+VRSRA_N:151:result_uint64x1 [] = { 1,  }
+VRSRA_N:152:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:153:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSRA_N:154:result_float32x2 [] = { 33333333, 33333333,  }
+VRSRA_N:155:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:156:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSRA_N:157:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSRA_N:158:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:159:result_int64x2 [] = { 0, 0,  }
+VRSRA_N:160:result_uint8x16 [] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:161:result_uint16x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:162:result_uint32x4 [] = { 1, 1, 1, 1,  }
+VRSRA_N:163:result_uint64x2 [] = { 1, 1,  }
+VRSRA_N:164:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:165:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSRA_N:166:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSRA_N:167:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSHLL_N output:
+VSHLL_N:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHLL_N:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHLL_N:2:result_int32x2 [] = { 33333333, 33333333,  }
+VSHLL_N:3:result_int64x1 [] = { 3333333333333333,  }
+VSHLL_N:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHLL_N:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHLL_N:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VSHLL_N:7:result_uint64x1 [] = { 3333333333333333,  }
+VSHLL_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHLL_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHLL_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSHLL_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSHLL_N:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHLL_N:13:result_int16x8 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6, ffffffe8, ffffffea, ffffffec, ffffffee,  }
+VSHLL_N:14:result_int32x4 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6,  }
+VSHLL_N:15:result_int64x2 [] = { ffffffffffffff80, ffffffffffffff88,  }
+VSHLL_N:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHLL_N:17:result_uint16x8 [] = { 3c0, 3c4, 3c8, 3cc, 3d0, 3d4, 3d8, 3dc,  }
+VSHLL_N:18:result_uint32x4 [] = { fff00, fff10, fff20, fff30,  }
+VSHLL_N:19:result_uint64x2 [] = { 7ffffff80, 7ffffff88,  }
+VSHLL_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHLL_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHLL_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSHLL_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VPADDL/VPADDLQ output:
+VPADDL/VPADDLQ:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADDL/VPADDLQ:1:result_int16x4 [] = { ffffffe1, ffffffe5, ffffffe9, ffffffed,  }
+VPADDL/VPADDLQ:2:result_int32x2 [] = { ffffffe1, ffffffe5,  }
+VPADDL/VPADDLQ:3:result_int64x1 [] = { ffffffffffffffe1,  }
+VPADDL/VPADDLQ:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADDL/VPADDLQ:5:result_uint16x4 [] = { 1e1, 1e5, 1e9, 1ed,  }
+VPADDL/VPADDLQ:6:result_uint32x2 [] = { 1ffe1, 1ffe5,  }
+VPADDL/VPADDLQ:7:result_uint64x1 [] = { 1ffffffe1,  }
+VPADDL/VPADDLQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADDL/VPADDLQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VPADDL/VPADDLQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VPADDL/VPADDLQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VPADDL/VPADDLQ:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADDL/VPADDLQ:13:result_int16x8 [] = { ffffffe1, ffffffe5, ffffffe9, ffffffed, fffffff1, fffffff5, fffffff9, fffffffd,  }
+VPADDL/VPADDLQ:14:result_int32x4 [] = { ffffffe1, ffffffe5, ffffffe9, ffffffed,  }
+VPADDL/VPADDLQ:15:result_int64x2 [] = { ffffffffffffffe1, ffffffffffffffe5,  }
+VPADDL/VPADDLQ:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADDL/VPADDLQ:17:result_uint16x8 [] = { 1e1, 1e5, 1e9, 1ed, 1f1, 1f5, 1f9, 1fd,  }
+VPADDL/VPADDLQ:18:result_uint32x4 [] = { 1ffe1, 1ffe5, 1ffe9, 1ffed,  }
+VPADDL/VPADDLQ:19:result_uint64x2 [] = { 1ffffffe1, 1ffffffe5,  }
+VPADDL/VPADDLQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADDL/VPADDLQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPADDL/VPADDLQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPADDL/VPADDLQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VPADD output:
+VPADD:0:result_int8x8 [] = { ffffffe1, ffffffe5, ffffffe9, ffffffed, ffffffe1, ffffffe5, ffffffe9, ffffffed,  }
+VPADD:1:result_int16x4 [] = { ffffffe1, ffffffe5, ffffffe1, ffffffe5,  }
+VPADD:2:result_int32x2 [] = { ffffffe1, ffffffe1,  }
+VPADD:3:result_int64x1 [] = { 3333333333333333,  }
+VPADD:4:result_uint8x8 [] = { e1, e5, e9, ed, e1, e5, e9, ed,  }
+VPADD:5:result_uint16x4 [] = { ffe1, ffe5, ffe1, ffe5,  }
+VPADD:6:result_uint32x2 [] = { ffffffe1, ffffffe1,  }
+VPADD:7:result_uint64x1 [] = { 3333333333333333,  }
+VPADD:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADD:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VPADD:10:result_float32x2 [] = { c1f80000, c1f80000,  }
+VPADD:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VPADD:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADD:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPADD:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPADD:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VPADD:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADD:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPADD:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPADD:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VPADD:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADD:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPADD:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPADD:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VPADAL/VPADALQ output:
+VPADAL/VPADALQ:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADAL/VPADALQ:1:result_int16x4 [] = { ffffffd1, ffffffd6, ffffffdb, ffffffe0,  }
+VPADAL/VPADALQ:2:result_int32x2 [] = { ffffffd1, ffffffd6,  }
+VPADAL/VPADALQ:3:result_int64x1 [] = { ffffffffffffffd1,  }
+VPADAL/VPADALQ:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADAL/VPADALQ:5:result_uint16x4 [] = { 1d1, 1d6, 1db, 1e0,  }
+VPADAL/VPADALQ:6:result_uint32x2 [] = { 1ffd1, 1ffd6,  }
+VPADAL/VPADALQ:7:result_uint64x1 [] = { 1ffffffd1,  }
+VPADAL/VPADALQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADAL/VPADALQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VPADAL/VPADALQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VPADAL/VPADALQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VPADAL/VPADALQ:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADAL/VPADALQ:13:result_int16x8 [] = { ffffffd1, ffffffd6, ffffffdb, ffffffe0, ffffffe5, ffffffea, ffffffef, fffffff4,  }
+VPADAL/VPADALQ:14:result_int32x4 [] = { ffffffd1, ffffffd6, ffffffdb, ffffffe0,  }
+VPADAL/VPADALQ:15:result_int64x2 [] = { ffffffffffffffd1, ffffffffffffffd6,  }
+VPADAL/VPADALQ:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADAL/VPADALQ:17:result_uint16x8 [] = { 1d1, 1d6, 1db, 1e0, 1e5, 1ea, 1ef, 1f4,  }
+VPADAL/VPADALQ:18:result_uint32x4 [] = { 1ffd1, 1ffd6, 1ffdb, 1ffe0,  }
+VPADAL/VPADALQ:19:result_uint64x2 [] = { 1ffffffd1, 1ffffffd6,  }
+VPADAL/VPADALQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADAL/VPADALQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPADAL/VPADALQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPADAL/VPADALQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHLU_N/VQSHLUQ_N (negative input) cumulative saturation output:
+VQSHLU_N/VQSHLUQ_N:0:vqshlu_n_s8 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:1:vqshlu_n_s16 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:2:vqshlu_n_s32 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:3:vqshlu_n_s64 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:4:vqshluq_n_s8 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:5:vqshluq_n_s16 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:6:vqshluq_n_s32 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:7:vqshluq_n_s64 Neon cumulative saturation 1
+
+VQSHLU_N/VQSHLUQ_N (negative input) output:
+VQSHLU_N/VQSHLUQ_N:8:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:9:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:10:result_int32x2 [] = { 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:11:result_int64x1 [] = { 3333333333333333,  }
+VQSHLU_N/VQSHLUQ_N:12:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:13:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:14:result_uint32x2 [] = { 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:15:result_uint64x1 [] = { 0,  }
+VQSHLU_N/VQSHLUQ_N:16:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:17:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:18:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:19:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:20:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:21:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:22:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:23:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHLU_N/VQSHLUQ_N:24:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:25:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:26:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:27:result_uint64x2 [] = { 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:28:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:29:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:30:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:31:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHLU_N/VQSHLUQ_N (check cumulative saturation: shift by 1) cumulative saturation output:
+VQSHLU_N/VQSHLUQ_N:32:vqshlu_n_s8 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:33:vqshlu_n_s16 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:34:vqshlu_n_s32 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:35:vqshlu_n_s64 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:36:vqshluq_n_s8 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:37:vqshluq_n_s16 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:38:vqshluq_n_s32 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:39:vqshluq_n_s64 Neon cumulative saturation 0
+
+VQSHLU_N/VQSHLUQ_N (check cumulative saturation: shift by 1) output:
+VQSHLU_N/VQSHLUQ_N:40:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:41:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:42:result_int32x2 [] = { 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:43:result_int64x1 [] = { 3333333333333333,  }
+VQSHLU_N/VQSHLUQ_N:44:result_uint8x8 [] = { fe, fe, fe, fe, fe, fe, fe, fe,  }
+VQSHLU_N/VQSHLUQ_N:45:result_uint16x4 [] = { fffe, fffe, fffe, fffe,  }
+VQSHLU_N/VQSHLUQ_N:46:result_uint32x2 [] = { fffffffe, fffffffe,  }
+VQSHLU_N/VQSHLUQ_N:47:result_uint64x1 [] = { fffffffffffffffe,  }
+VQSHLU_N/VQSHLUQ_N:48:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:49:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:50:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:51:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:52:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:53:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:54:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:55:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHLU_N/VQSHLUQ_N:56:result_uint8x16 [] = { fe, fe, fe, fe, fe, fe, fe, fe, fe, fe, fe, fe, fe, fe, fe, fe,  }
+VQSHLU_N/VQSHLUQ_N:57:result_uint16x8 [] = { fffe, fffe, fffe, fffe, fffe, fffe, fffe, fffe,  }
+VQSHLU_N/VQSHLUQ_N:58:result_uint32x4 [] = { fffffffe, fffffffe, fffffffe, fffffffe,  }
+VQSHLU_N/VQSHLUQ_N:59:result_uint64x2 [] = { fffffffffffffffe, fffffffffffffffe,  }
+VQSHLU_N/VQSHLUQ_N:60:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:61:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:62:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:63:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHLU_N/VQSHLUQ_N (check cumulative saturation: shift by 2) cumulative saturation output:
+VQSHLU_N/VQSHLUQ_N:64:vqshlu_n_s8 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:65:vqshlu_n_s16 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:66:vqshlu_n_s32 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:67:vqshlu_n_s64 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:68:vqshluq_n_s8 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:69:vqshluq_n_s16 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:70:vqshluq_n_s32 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:71:vqshluq_n_s64 Neon cumulative saturation 1
+
+VQSHLU_N/VQSHLUQ_N (check cumulative saturation: shift by 2) output:
+VQSHLU_N/VQSHLUQ_N:72:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:73:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:74:result_int32x2 [] = { 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:75:result_int64x1 [] = { 3333333333333333,  }
+VQSHLU_N/VQSHLUQ_N:76:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHLU_N/VQSHLUQ_N:77:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHLU_N/VQSHLUQ_N:78:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHLU_N/VQSHLUQ_N:79:result_uint64x1 [] = { ffffffffffffffff,  }
+VQSHLU_N/VQSHLUQ_N:80:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:81:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:82:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:83:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:84:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:85:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:86:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:87:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHLU_N/VQSHLUQ_N:88:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHLU_N/VQSHLUQ_N:89:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQSHLU_N/VQSHLUQ_N:90:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHLU_N/VQSHLUQ_N:91:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQSHLU_N/VQSHLUQ_N:92:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:93:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:94:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:95:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHLU_N/VQSHLUQ_N cumulative saturation output:
+VQSHLU_N/VQSHLUQ_N:96:vqshlu_n_s8 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:97:vqshlu_n_s16 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:98:vqshlu_n_s32 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:99:vqshlu_n_s64 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:100:vqshluq_n_s8 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:101:vqshluq_n_s16 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:102:vqshluq_n_s32 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:103:vqshluq_n_s64 Neon cumulative saturation 0
+
+VQSHLU_N/VQSHLUQ_N output:
+VQSHLU_N/VQSHLUQ_N:104:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:105:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:106:result_int32x2 [] = { 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:107:result_int64x1 [] = { 3333333333333333,  }
+VQSHLU_N/VQSHLUQ_N:108:result_uint8x8 [] = { 2, 2, 2, 2, 2, 2, 2, 2,  }
+VQSHLU_N/VQSHLUQ_N:109:result_uint16x4 [] = { 8, 8, 8, 8,  }
+VQSHLU_N/VQSHLUQ_N:110:result_uint32x2 [] = { 18, 18,  }
+VQSHLU_N/VQSHLUQ_N:111:result_uint64x1 [] = { 40,  }
+VQSHLU_N/VQSHLUQ_N:112:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:113:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:114:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:115:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:116:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:117:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:118:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:119:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHLU_N/VQSHLUQ_N:120:result_uint8x16 [] = { a0, a0, a0, a0, a0, a0, a0, a0, a0, a0, a0, a0, a0, a0, a0, a0,  }
+VQSHLU_N/VQSHLUQ_N:121:result_uint16x8 [] = { 180, 180, 180, 180, 180, 180, 180, 180,  }
+VQSHLU_N/VQSHLUQ_N:122:result_uint32x4 [] = { 380, 380, 380, 380,  }
+VQSHLU_N/VQSHLUQ_N:123:result_uint64x2 [] = { 800, 800,  }
+VQSHLU_N/VQSHLUQ_N:124:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:125:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:126:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:127:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VCLZ/VCLZQ output:
+VCLZ/VCLZQ:0:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VCLZ/VCLZQ:1:result_int16x4 [] = { 3, 3, 3, 3,  }
+VCLZ/VCLZQ:2:result_int32x2 [] = { 11, 11,  }
+VCLZ/VCLZQ:3:result_int64x1 [] = { 3333333333333333,  }
+VCLZ/VCLZQ:4:result_uint8x8 [] = { 2, 2, 2, 2, 2, 2, 2, 2,  }
+VCLZ/VCLZQ:5:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VCLZ/VCLZQ:6:result_uint32x2 [] = { 5, 5,  }
+VCLZ/VCLZQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VCLZ/VCLZQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLZ/VCLZQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCLZ/VCLZQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VCLZ/VCLZQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VCLZ/VCLZQ:12:result_int8x16 [] = { 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,  }
+VCLZ/VCLZQ:13:result_int16x8 [] = { 3, 3, 3, 3, 3, 3, 3, 3,  }
+VCLZ/VCLZQ:14:result_int32x4 [] = { 3, 3, 3, 3,  }
+VCLZ/VCLZQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCLZ/VCLZQ:16:result_uint8x16 [] = { 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,  }
+VCLZ/VCLZQ:17:result_uint16x8 [] = { d, d, d, d, d, d, d, d,  }
+VCLZ/VCLZQ:18:result_uint32x4 [] = { 1f, 1f, 1f, 1f,  }
+VCLZ/VCLZQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCLZ/VCLZQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLZ/VCLZQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCLZ/VCLZQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCLZ/VCLZQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VCLZ/VCLZQ (input=0) output:
+VCLZ/VCLZQ:24:result_int8x8 [] = { 8, 8, 8, 8, 8, 8, 8, 8,  }
+VCLZ/VCLZQ:25:result_int16x4 [] = { 10, 10, 10, 10,  }
+VCLZ/VCLZQ:26:result_int32x2 [] = { 20, 20,  }
+VCLZ/VCLZQ:27:result_int64x1 [] = { 3333333333333333,  }
+VCLZ/VCLZQ:28:result_uint8x8 [] = { 8, 8, 8, 8, 8, 8, 8, 8,  }
+VCLZ/VCLZQ:29:result_uint16x4 [] = { 10, 10, 10, 10,  }
+VCLZ/VCLZQ:30:result_uint32x2 [] = { 20, 20,  }
+VCLZ/VCLZQ:31:result_uint64x1 [] = { 3333333333333333,  }
+VCLZ/VCLZQ:32:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLZ/VCLZQ:33:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCLZ/VCLZQ:34:result_float32x2 [] = { 33333333, 33333333,  }
+VCLZ/VCLZQ:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VCLZ/VCLZQ:36:result_int8x16 [] = { 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,  }
+VCLZ/VCLZQ:37:result_int16x8 [] = { 10, 10, 10, 10, 10, 10, 10, 10,  }
+VCLZ/VCLZQ:38:result_int32x4 [] = { 20, 20, 20, 20,  }
+VCLZ/VCLZQ:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCLZ/VCLZQ:40:result_uint8x16 [] = { 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,  }
+VCLZ/VCLZQ:41:result_uint16x8 [] = { 10, 10, 10, 10, 10, 10, 10, 10,  }
+VCLZ/VCLZQ:42:result_uint32x4 [] = { 20, 20, 20, 20,  }
+VCLZ/VCLZQ:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCLZ/VCLZQ:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLZ/VCLZQ:45:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCLZ/VCLZQ:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCLZ/VCLZQ:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VCLS/VCLSQ (positive input) output:
+VCLS/VCLSQ:0:result_int8x8 [] = { 6, 6, 6, 6, 6, 6, 6, 6,  }
+VCLS/VCLSQ:1:result_int16x4 [] = { 2, 2, 2, 2,  }
+VCLS/VCLSQ:2:result_int32x2 [] = { 19, 19,  }
+VCLS/VCLSQ:3:result_int64x1 [] = { 3333333333333333,  }
+VCLS/VCLSQ:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLS/VCLSQ:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCLS/VCLSQ:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VCLS/VCLSQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VCLS/VCLSQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLS/VCLSQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCLS/VCLSQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VCLS/VCLSQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VCLS/VCLSQ:12:result_int8x16 [] = { 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,  }
+VCLS/VCLSQ:13:result_int16x8 [] = { 2, 2, 2, 2, 2, 2, 2, 2,  }
+VCLS/VCLSQ:14:result_int32x4 [] = { 14, 14, 14, 14,  }
+VCLS/VCLSQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCLS/VCLSQ:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLS/VCLSQ:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCLS/VCLSQ:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCLS/VCLSQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCLS/VCLSQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLS/VCLSQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCLS/VCLSQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCLS/VCLSQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VCLS/VCLSQ (negative input) output:
+VCLS/VCLSQ:24:result_int8x8 [] = { 7, 7, 7, 7, 7, 7, 7, 7,  }
+VCLS/VCLSQ:25:result_int16x4 [] = { 1, 1, 1, 1,  }
+VCLS/VCLSQ:26:result_int32x2 [] = { 1, 1,  }
+VCLS/VCLSQ:27:result_int64x1 [] = { 3333333333333333,  }
+VCLS/VCLSQ:28:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLS/VCLSQ:29:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCLS/VCLSQ:30:result_uint32x2 [] = { 33333333, 33333333,  }
+VCLS/VCLSQ:31:result_uint64x1 [] = { 3333333333333333,  }
+VCLS/VCLSQ:32:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLS/VCLSQ:33:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCLS/VCLSQ:34:result_float32x2 [] = { 33333333, 33333333,  }
+VCLS/VCLSQ:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VCLS/VCLSQ:36:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VCLS/VCLSQ:37:result_int16x8 [] = { 2, 2, 2, 2, 2, 2, 2, 2,  }
+VCLS/VCLSQ:38:result_int32x4 [] = { 0, 0, 0, 0,  }
+VCLS/VCLSQ:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCLS/VCLSQ:40:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLS/VCLSQ:41:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCLS/VCLSQ:42:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCLS/VCLSQ:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCLS/VCLSQ:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLS/VCLSQ:45:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCLS/VCLSQ:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCLS/VCLSQ:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VCNT/VCNTQ output:
+VCNT/VCNTQ:0:result_int8x8 [] = { 8, 8, 8, 8, 8, 8, 8, 8,  }
+VCNT/VCNTQ:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCNT/VCNTQ:2:result_int32x2 [] = { 33333333, 33333333,  }
+VCNT/VCNTQ:3:result_int64x1 [] = { 3333333333333333,  }
+VCNT/VCNTQ:4:result_uint8x8 [] = { 4, 4, 4, 4, 4, 4, 4, 4,  }
+VCNT/VCNTQ:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCNT/VCNTQ:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VCNT/VCNTQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VCNT/VCNTQ:8:result_poly8x8 [] = { 4, 4, 4, 4, 4, 4, 4, 4,  }
+VCNT/VCNTQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCNT/VCNTQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VCNT/VCNTQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VCNT/VCNTQ:12:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VCNT/VCNTQ:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCNT/VCNTQ:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCNT/VCNTQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCNT/VCNTQ:16:result_uint8x16 [] = { 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,  }
+VCNT/VCNTQ:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCNT/VCNTQ:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCNT/VCNTQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCNT/VCNTQ:20:result_poly8x16 [] = { 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,  }
+VCNT/VCNTQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCNT/VCNTQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCNT/VCNTQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHRN_N cumulative saturation output:
+VQSHRN_N:0:vqshrn_n_s16 Neon cumulative saturation 0
+VQSHRN_N:1:vqshrn_n_s32 Neon cumulative saturation 0
+VQSHRN_N:2:vqshrn_n_s64 Neon cumulative saturation 0
+VQSHRN_N:3:vqshrn_n_u16 Neon cumulative saturation 1
+VQSHRN_N:4:vqshrn_n_u32 Neon cumulative saturation 1
+VQSHRN_N:5:vqshrn_n_u64 Neon cumulative saturation 1
+
+VQSHRN_N output:
+VQSHRN_N:6:result_int8x8 [] = { fffffff8, fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb,  }
+VQSHRN_N:7:result_int16x4 [] = { fffffff8, fffffff8, fffffff9, fffffff9,  }
+VQSHRN_N:8:result_int32x2 [] = { fffffffc, fffffffc,  }
+VQSHRN_N:9:result_int64x1 [] = { 3333333333333333,  }
+VQSHRN_N:10:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHRN_N:11:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHRN_N:12:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHRN_N:13:result_uint64x1 [] = { 3333333333333333,  }
+VQSHRN_N:14:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:15:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRN_N:16:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHRN_N:17:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHRN_N:18:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:19:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:20:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRN_N:21:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRN_N:22:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:23:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:24:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRN_N:25:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRN_N:26:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:27:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:28:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRN_N:29:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHRN_N (check saturation: shift by 3) cumulative saturation output:
+VQSHRN_N:30:vqshrn_n_s16 Neon cumulative saturation 1
+VQSHRN_N:31:vqshrn_n_s32 Neon cumulative saturation 1
+VQSHRN_N:32:vqshrn_n_s64 Neon cumulative saturation 1
+VQSHRN_N:33:vqshrn_n_u16 Neon cumulative saturation 1
+VQSHRN_N:34:vqshrn_n_u32 Neon cumulative saturation 1
+VQSHRN_N:35:vqshrn_n_u64 Neon cumulative saturation 1
+
+VQSHRN_N (check saturation: shift by 3) output:
+VQSHRN_N:36:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHRN_N:37:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQSHRN_N:38:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQSHRN_N:39:result_int64x1 [] = { 3333333333333333,  }
+VQSHRN_N:40:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHRN_N:41:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHRN_N:42:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHRN_N:43:result_uint64x1 [] = { 3333333333333333,  }
+VQSHRN_N:44:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:45:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRN_N:46:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHRN_N:47:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHRN_N:48:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:49:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:50:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRN_N:51:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRN_N:52:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:53:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:54:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRN_N:55:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRN_N:56:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:57:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:58:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRN_N:59:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHRN_N (check saturation: shift by max) cumulative saturation output:
+VQSHRN_N:60:vqshrn_n_s16 Neon cumulative saturation 0
+VQSHRN_N:61:vqshrn_n_s32 Neon cumulative saturation 0
+VQSHRN_N:62:vqshrn_n_s64 Neon cumulative saturation 0
+VQSHRN_N:63:vqshrn_n_u16 Neon cumulative saturation 0
+VQSHRN_N:64:vqshrn_n_u32 Neon cumulative saturation 0
+VQSHRN_N:65:vqshrn_n_u64 Neon cumulative saturation 0
+
+VQSHRN_N (check saturation: shift by max) output:
+VQSHRN_N:66:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHRN_N:67:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQSHRN_N:68:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQSHRN_N:69:result_int64x1 [] = { 3333333333333333,  }
+VQSHRN_N:70:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHRN_N:71:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHRN_N:72:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHRN_N:73:result_uint64x1 [] = { 3333333333333333,  }
+VQSHRN_N:74:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:75:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRN_N:76:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHRN_N:77:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHRN_N:78:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:79:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:80:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRN_N:81:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRN_N:82:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:83:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:84:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRN_N:85:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRN_N:86:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:87:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:88:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRN_N:89:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VPMAX output:
+VPMAX:0:result_int8x8 [] = { fffffff1, fffffff3, fffffff5, fffffff7, fffffff1, fffffff3, fffffff5, fffffff7,  }
+VPMAX:1:result_int16x4 [] = { fffffff1, fffffff3, fffffff1, fffffff3,  }
+VPMAX:2:result_int32x2 [] = { fffffff1, fffffff1,  }
+VPMAX:3:result_int64x1 [] = { 3333333333333333,  }
+VPMAX:4:result_uint8x8 [] = { f1, f3, f5, f7, f1, f3, f5, f7,  }
+VPMAX:5:result_uint16x4 [] = { fff1, fff3, fff1, fff3,  }
+VPMAX:6:result_uint32x2 [] = { fffffff1, fffffff1,  }
+VPMAX:7:result_uint64x1 [] = { 3333333333333333,  }
+VPMAX:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPMAX:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VPMAX:10:result_float32x2 [] = { c1700000, c1700000,  }
+VPMAX:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VPMAX:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPMAX:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPMAX:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPMAX:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VPMAX:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPMAX:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPMAX:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPMAX:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VPMAX:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPMAX:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPMAX:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPMAX:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VPMIN output:
+VPMIN:0:result_int8x8 [] = { fffffff0, fffffff2, fffffff4, fffffff6, fffffff0, fffffff2, fffffff4, fffffff6,  }
+VPMIN:1:result_int16x4 [] = { fffffff0, fffffff2, fffffff0, fffffff2,  }
+VPMIN:2:result_int32x2 [] = { fffffff0, fffffff0,  }
+VPMIN:3:result_int64x1 [] = { 3333333333333333,  }
+VPMIN:4:result_uint8x8 [] = { f0, f2, f4, f6, f0, f2, f4, f6,  }
+VPMIN:5:result_uint16x4 [] = { fff0, fff2, fff0, fff2,  }
+VPMIN:6:result_uint32x2 [] = { fffffff0, fffffff0,  }
+VPMIN:7:result_uint64x1 [] = { 3333333333333333,  }
+VPMIN:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPMIN:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VPMIN:10:result_float32x2 [] = { c1800000, c1800000,  }
+VPMIN:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VPMIN:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPMIN:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPMIN:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPMIN:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VPMIN:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPMIN:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPMIN:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPMIN:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VPMIN:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPMIN:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPMIN:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPMIN:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHRUN_N (negative input) cumulative saturation output:
+VQSHRUN_N:0:vqshrun_n_s16 Neon cumulative saturation 1
+VQSHRUN_N:1:vqshrun_n_s32 Neon cumulative saturation 1
+VQSHRUN_N:2:vqshrun_n_s64 Neon cumulative saturation 1
+
+VQSHRUN_N (negative input) output:
+VQSHRUN_N:3:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:4:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:5:result_int32x2 [] = { 33333333, 33333333,  }
+VQSHRUN_N:6:result_int64x1 [] = { 3333333333333333,  }
+VQSHRUN_N:7:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHRUN_N:8:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQSHRUN_N:9:result_uint32x2 [] = { 0, 0,  }
+VQSHRUN_N:10:result_uint64x1 [] = { 3333333333333333,  }
+VQSHRUN_N:11:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:12:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:13:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHRUN_N:14:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHRUN_N:15:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:16:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:17:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRUN_N:18:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRUN_N:19:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:20:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:21:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRUN_N:22:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRUN_N:23:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:24:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:25:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRUN_N:26:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHRUN_N (check cumulative saturation) cumulative saturation output:
+VQSHRUN_N:27:vqshrun_n_s16 Neon cumulative saturation 1
+VQSHRUN_N:28:vqshrun_n_s32 Neon cumulative saturation 1
+VQSHRUN_N:29:vqshrun_n_s64 Neon cumulative saturation 1
+
+VQSHRUN_N (check cumulative saturation) output:
+VQSHRUN_N:30:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:31:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:32:result_int32x2 [] = { 33333333, 33333333,  }
+VQSHRUN_N:33:result_int64x1 [] = { 3333333333333333,  }
+VQSHRUN_N:34:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHRUN_N:35:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHRUN_N:36:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHRUN_N:37:result_uint64x1 [] = { 3333333333333333,  }
+VQSHRUN_N:38:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:39:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:40:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHRUN_N:41:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHRUN_N:42:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:43:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:44:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRUN_N:45:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRUN_N:46:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:47:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:48:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRUN_N:49:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRUN_N:50:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:51:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:52:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRUN_N:53:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHRUN_N cumulative saturation output:
+VQSHRUN_N:54:vqshrun_n_s16 Neon cumulative saturation 0
+VQSHRUN_N:55:vqshrun_n_s32 Neon cumulative saturation 1
+VQSHRUN_N:56:vqshrun_n_s64 Neon cumulative saturation 0
+
+VQSHRUN_N output:
+VQSHRUN_N:57:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:58:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:59:result_int32x2 [] = { 33333333, 33333333,  }
+VQSHRUN_N:60:result_int64x1 [] = { 3333333333333333,  }
+VQSHRUN_N:61:result_uint8x8 [] = { 48, 48, 48, 48, 48, 48, 48, 48,  }
+VQSHRUN_N:62:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQSHRUN_N:63:result_uint32x2 [] = { deadbe, deadbe,  }
+VQSHRUN_N:64:result_uint64x1 [] = { 3333333333333333,  }
+VQSHRUN_N:65:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:66:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:67:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHRUN_N:68:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHRUN_N:69:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:70:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:71:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRUN_N:72:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRUN_N:73:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:74:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:75:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRUN_N:76:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRUN_N:77:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:78:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:79:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRUN_N:80:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHRUN_N (negative input) cumulative saturation output:
+VQRSHRUN_N:0:vqrshrun_n_s16 Neon cumulative saturation 0
+VQRSHRUN_N:1:vqrshrun_n_s32 Neon cumulative saturation 0
+VQRSHRUN_N:2:vqrshrun_n_s64 Neon cumulative saturation 1
+
+VQRSHRUN_N (negative input) output:
+VQRSHRUN_N:3:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:4:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:5:result_int32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:6:result_int64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:7:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHRUN_N:8:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRUN_N:9:result_uint32x2 [] = { 0, 0,  }
+VQRSHRUN_N:10:result_uint64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:11:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:12:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:13:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:14:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRUN_N:15:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:16:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:17:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:18:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:19:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:20:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:21:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:22:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:23:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:24:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:25:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:26:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHRUN_N (check cumulative saturation: shift by 1) cumulative saturation output:
+VQRSHRUN_N:27:vqrshrun_n_s16 Neon cumulative saturation 1
+VQRSHRUN_N:28:vqrshrun_n_s32 Neon cumulative saturation 1
+VQRSHRUN_N:29:vqrshrun_n_s64 Neon cumulative saturation 1
+
+VQRSHRUN_N (check cumulative saturation: shift by 1) output:
+VQRSHRUN_N:30:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:31:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:32:result_int32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:33:result_int64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:34:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHRUN_N:35:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQRSHRUN_N:36:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQRSHRUN_N:37:result_uint64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:38:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:39:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:40:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:41:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRUN_N:42:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:43:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:44:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:45:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:46:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:47:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:48:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:49:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:50:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:51:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:52:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:53:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHRUN_N (check cumulative saturation: shift by max, positive input) cumulative saturation output:
+VQRSHRUN_N:54:vqrshrun_n_s16 Neon cumulative saturation 0
+VQRSHRUN_N:55:vqrshrun_n_s32 Neon cumulative saturation 0
+VQRSHRUN_N:56:vqrshrun_n_s64 Neon cumulative saturation 0
+
+VQRSHRUN_N (check cumulative saturation: shift by max, positive input) output:
+VQRSHRUN_N:57:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:58:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:59:result_int32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:60:result_int64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:61:result_uint8x8 [] = { 80, 80, 80, 80, 80, 80, 80, 80,  }
+VQRSHRUN_N:62:result_uint16x4 [] = { 8000, 8000, 8000, 8000,  }
+VQRSHRUN_N:63:result_uint32x2 [] = { 80000000, 80000000,  }
+VQRSHRUN_N:64:result_uint64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:65:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:66:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:67:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:68:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRUN_N:69:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:70:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:71:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:72:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:73:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:74:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:75:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:76:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:77:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:78:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:79:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:80:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHRUN_N (check cumulative saturation: shift by max, negative input) cumulative saturation output:
+VQRSHRUN_N:81:vqrshrun_n_s16 Neon cumulative saturation 1
+VQRSHRUN_N:82:vqrshrun_n_s32 Neon cumulative saturation 1
+VQRSHRUN_N:83:vqrshrun_n_s64 Neon cumulative saturation 1
+
+VQRSHRUN_N (check cumulative saturation: shift by max, negative input) output:
+VQRSHRUN_N:84:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:85:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:86:result_int32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:87:result_int64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:88:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHRUN_N:89:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRUN_N:90:result_uint32x2 [] = { 0, 0,  }
+VQRSHRUN_N:91:result_uint64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:92:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:93:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:94:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:95:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRUN_N:96:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:97:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:98:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:99:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:100:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:101:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:102:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:103:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:104:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:105:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:106:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:107:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHRUN_N cumulative saturation output:
+VQRSHRUN_N:108:vqrshrun_n_s16 Neon cumulative saturation 0
+VQRSHRUN_N:109:vqrshrun_n_s32 Neon cumulative saturation 1
+VQRSHRUN_N:110:vqrshrun_n_s64 Neon cumulative saturation 0
+
+VQRSHRUN_N output:
+VQRSHRUN_N:111:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:112:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:113:result_int32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:114:result_int64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:115:result_uint8x8 [] = { 49, 49, 49, 49, 49, 49, 49, 49,  }
+VQRSHRUN_N:116:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRUN_N:117:result_uint32x2 [] = { deadbf, deadbf,  }
+VQRSHRUN_N:118:result_uint64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:119:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:120:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:121:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:122:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRUN_N:123:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:124:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:125:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:126:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:127:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:128:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:129:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:130:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:131:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:132:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:133:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:134:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VST2_LANE/VST2Q_LANE chunk 0 output:
+VST2_LANE/VST2Q_LANE:0:result_int8x8 [] = { fffffff0, fffffff1, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:1:result_int16x4 [] = { fffffff0, fffffff1, 0, 0,  }
+VST2_LANE/VST2Q_LANE:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VST2_LANE/VST2Q_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VST2_LANE/VST2Q_LANE:4:result_uint8x8 [] = { f0, f1, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:5:result_uint16x4 [] = { fff0, fff1, 0, 0,  }
+VST2_LANE/VST2Q_LANE:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VST2_LANE/VST2Q_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VST2_LANE/VST2Q_LANE:8:result_poly8x8 [] = { f0, f1, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:9:result_poly16x4 [] = { fff0, fff1, 0, 0,  }
+VST2_LANE/VST2Q_LANE:10:result_float32x2 [] = { c1800000, c1700000,  }
+VST2_LANE/VST2Q_LANE:11:result_float16x4 [] = { cc00, cb80, 0, 0,  }
+VST2_LANE/VST2Q_LANE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST2_LANE/VST2Q_LANE:13:result_int16x8 [] = { fffffff0, fffffff1, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:14:result_int32x4 [] = { fffffff0, fffffff1, 0, 0,  }
+VST2_LANE/VST2Q_LANE:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST2_LANE/VST2Q_LANE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST2_LANE/VST2Q_LANE:17:result_uint16x8 [] = { fff0, fff1, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:18:result_uint32x4 [] = { fffffff0, fffffff1, 0, 0,  }
+VST2_LANE/VST2Q_LANE:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST2_LANE/VST2Q_LANE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST2_LANE/VST2Q_LANE:21:result_poly16x8 [] = { fff0, fff1, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:22:result_float32x4 [] = { c1800000, c1700000, 0, 0,  }
+VST2_LANE/VST2Q_LANE:23:result_float16x8 [] = { cc00, cb80, 0, 0, 0, 0, 0, 0,  }
+
+VST2_LANE/VST2Q_LANE chunk 1 output:
+VST2_LANE/VST2Q_LANE:24:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:25:result_int16x4 [] = { 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:26:result_int32x2 [] = { 0, 0,  }
+VST2_LANE/VST2Q_LANE:27:result_int64x1 [] = { 3333333333333333,  }
+VST2_LANE/VST2Q_LANE:28:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:29:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:30:result_uint32x2 [] = { 0, 0,  }
+VST2_LANE/VST2Q_LANE:31:result_uint64x1 [] = { 3333333333333333,  }
+VST2_LANE/VST2Q_LANE:32:result_poly8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:33:result_poly16x4 [] = { 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:34:result_float32x2 [] = { 0, 0,  }
+VST2_LANE/VST2Q_LANE:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:36:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST2_LANE/VST2Q_LANE:37:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:38:result_int32x4 [] = { 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST2_LANE/VST2Q_LANE:40:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST2_LANE/VST2Q_LANE:41:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:42:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST2_LANE/VST2Q_LANE:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST2_LANE/VST2Q_LANE:45:result_poly16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:46:result_float32x4 [] = { 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VST3_LANE/VST3Q_LANE chunk 0 output:
+VST3_LANE/VST3Q_LANE:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, 0,  }
+VST3_LANE/VST3Q_LANE:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VST3_LANE/VST3Q_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:4:result_uint8x8 [] = { f0, f1, f2, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:5:result_uint16x4 [] = { fff0, fff1, fff2, 0,  }
+VST3_LANE/VST3Q_LANE:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VST3_LANE/VST3Q_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:8:result_poly8x8 [] = { f0, f1, f2, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:9:result_poly16x4 [] = { fff0, fff1, fff2, 0,  }
+VST3_LANE/VST3Q_LANE:10:result_float32x2 [] = { c1800000, c1700000,  }
+VST3_LANE/VST3Q_LANE:11:result_float16x4 [] = { cc00, cb80, cb00, 0,  }
+VST3_LANE/VST3Q_LANE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:14:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, 0,  }
+VST3_LANE/VST3Q_LANE:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:17:result_uint16x8 [] = { fff0, fff1, fff2, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, 0,  }
+VST3_LANE/VST3Q_LANE:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:21:result_poly16x8 [] = { fff0, fff1, fff2, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:22:result_float32x4 [] = { c1800000, c1700000, c1600000, 0,  }
+VST3_LANE/VST3Q_LANE:23:result_float16x8 [] = { cc00, cb80, cb00, 0, 0, 0, 0, 0,  }
+
+VST3_LANE/VST3Q_LANE chunk 1 output:
+VST3_LANE/VST3Q_LANE:24:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:25:result_int16x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:26:result_int32x2 [] = { fffffff2, 0,  }
+VST3_LANE/VST3Q_LANE:27:result_int64x1 [] = { 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:28:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:29:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:30:result_uint32x2 [] = { fffffff2, 0,  }
+VST3_LANE/VST3Q_LANE:31:result_uint64x1 [] = { 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:32:result_poly8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:33:result_poly16x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:34:result_float32x2 [] = { c1600000, 0,  }
+VST3_LANE/VST3Q_LANE:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:36:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:37:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:38:result_int32x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:40:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:41:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:42:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:45:result_poly16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:46:result_float32x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VST3_LANE/VST3Q_LANE chunk 2 output:
+VST3_LANE/VST3Q_LANE:48:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:49:result_int16x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:50:result_int32x2 [] = { 0, 0,  }
+VST3_LANE/VST3Q_LANE:51:result_int64x1 [] = { 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:52:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:53:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:54:result_uint32x2 [] = { 0, 0,  }
+VST3_LANE/VST3Q_LANE:55:result_uint64x1 [] = { 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:56:result_poly8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:57:result_poly16x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:58:result_float32x2 [] = { 0, 0,  }
+VST3_LANE/VST3Q_LANE:59:result_float16x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:60:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:61:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:62:result_int32x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:63:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:64:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:65:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:66:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:67:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:68:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:69:result_poly16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:70:result_float32x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:71:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VST4_LANE/VST4Q_LANE chunk 0 output:
+VST4_LANE/VST4Q_LANE:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VST4_LANE/VST4Q_LANE:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VST4_LANE/VST4Q_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:4:result_uint8x8 [] = { f0, f1, f2, f3, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VST4_LANE/VST4Q_LANE:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VST4_LANE/VST4Q_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:8:result_poly8x8 [] = { f0, f1, f2, f3, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VST4_LANE/VST4Q_LANE:10:result_float32x2 [] = { c1800000, c1700000,  }
+VST4_LANE/VST4Q_LANE:11:result_float16x4 [] = { cc00, cb80, cb00, ca80,  }
+VST4_LANE/VST4Q_LANE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:14:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VST4_LANE/VST4Q_LANE:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:17:result_uint16x8 [] = { fff0, fff1, fff2, fff3, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VST4_LANE/VST4Q_LANE:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:21:result_poly16x8 [] = { fff0, fff1, fff2, fff3, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:22:result_float32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+VST4_LANE/VST4Q_LANE:23:result_float16x8 [] = { cc00, cb80, cb00, ca80, 0, 0, 0, 0,  }
+
+VST4_LANE/VST4Q_LANE chunk 1 output:
+VST4_LANE/VST4Q_LANE:24:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:25:result_int16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:26:result_int32x2 [] = { fffffff2, fffffff3,  }
+VST4_LANE/VST4Q_LANE:27:result_int64x1 [] = { 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:28:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:29:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:30:result_uint32x2 [] = { fffffff2, fffffff3,  }
+VST4_LANE/VST4Q_LANE:31:result_uint64x1 [] = { 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:32:result_poly8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:33:result_poly16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:34:result_float32x2 [] = { c1600000, c1500000,  }
+VST4_LANE/VST4Q_LANE:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:36:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:37:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:38:result_int32x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:40:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:41:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:42:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:45:result_poly16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:46:result_float32x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VST4_LANE/VST4Q_LANE chunk 2 output:
+VST4_LANE/VST4Q_LANE:48:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:49:result_int16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:50:result_int32x2 [] = { 0, 0,  }
+VST4_LANE/VST4Q_LANE:51:result_int64x1 [] = { 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:52:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:53:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:54:result_uint32x2 [] = { 0, 0,  }
+VST4_LANE/VST4Q_LANE:55:result_uint64x1 [] = { 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:56:result_poly8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:57:result_poly16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:58:result_float32x2 [] = { 0, 0,  }
+VST4_LANE/VST4Q_LANE:59:result_float16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:60:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:61:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:62:result_int32x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:63:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:64:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:65:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:66:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:67:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:68:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:69:result_poly16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:70:result_float32x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:71:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VST4_LANE/VST4Q_LANE chunk 3 output:
+VST4_LANE/VST4Q_LANE:72:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:73:result_int16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:74:result_int32x2 [] = { 0, 0,  }
+VST4_LANE/VST4Q_LANE:75:result_int64x1 [] = { 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:76:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:77:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:78:result_uint32x2 [] = { 0, 0,  }
+VST4_LANE/VST4Q_LANE:79:result_uint64x1 [] = { 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:80:result_poly8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:81:result_poly16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:82:result_float32x2 [] = { 0, 0,  }
+VST4_LANE/VST4Q_LANE:83:result_float16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:84:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:85:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:86:result_int32x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:87:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:88:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:89:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:90:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:91:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:92:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:93:result_poly16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:94:result_float32x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:95:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VTBL1 output:
+VTBL1:0:result_int8x8 [] = { 0, fffffff2, fffffff2, fffffff2, 0, 0, fffffff2, fffffff2,  }
+VTBL1:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL1:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTBL1:3:result_int64x1 [] = { 3333333333333333,  }
+VTBL1:4:result_uint8x8 [] = { 0, f3, f3, f3, 0, 0, f3, f3,  }
+VTBL1:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL1:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VTBL1:7:result_uint64x1 [] = { 3333333333333333,  }
+VTBL1:8:result_poly8x8 [] = { 0, f3, f3, f3, 0, 0, f3, f3,  }
+VTBL1:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL1:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTBL1:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VTBL1:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL1:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL1:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL1:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBL1:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL1:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL1:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL1:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBL1:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL1:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL1:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL1:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VTBL2 output:
+VTBL2:0:result_int8x8 [] = { fffffff6, fffffff3, fffffff3, fffffff3, 0, 0, fffffff3, fffffff3,  }
+VTBL2:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL2:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTBL2:3:result_int64x1 [] = { 3333333333333333,  }
+VTBL2:4:result_uint8x8 [] = { f6, f5, f5, f5, 0, 0, f5, f5,  }
+VTBL2:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL2:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VTBL2:7:result_uint64x1 [] = { 3333333333333333,  }
+VTBL2:8:result_poly8x8 [] = { f6, f5, f5, f5, 0, 0, f5, f5,  }
+VTBL2:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL2:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTBL2:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VTBL2:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL2:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL2:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL2:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBL2:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL2:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL2:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL2:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBL2:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL2:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL2:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL2:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VTBL3 output:
+VTBL3:0:result_int8x8 [] = { fffffff8, fffffff4, fffffff4, fffffff4, ffffffff, 0, fffffff4, fffffff4,  }
+VTBL3:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL3:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTBL3:3:result_int64x1 [] = { 3333333333333333,  }
+VTBL3:4:result_uint8x8 [] = { f8, f7, f7, f7, ff, 0, f7, f7,  }
+VTBL3:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL3:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VTBL3:7:result_uint64x1 [] = { 3333333333333333,  }
+VTBL3:8:result_poly8x8 [] = { f8, f7, f7, f7, ff, 0, f7, f7,  }
+VTBL3:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL3:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTBL3:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VTBL3:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL3:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL3:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL3:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBL3:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL3:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL3:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL3:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBL3:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL3:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL3:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL3:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VTBL4 output:
+VTBL4:0:result_int8x8 [] = { fffffffa, fffffff5, fffffff5, fffffff5, 3, 0, fffffff5, fffffff5,  }
+VTBL4:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL4:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTBL4:3:result_int64x1 [] = { 3333333333333333,  }
+VTBL4:4:result_uint8x8 [] = { fa, f9, f9, f9, 3, 0, f9, f9,  }
+VTBL4:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL4:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VTBL4:7:result_uint64x1 [] = { 3333333333333333,  }
+VTBL4:8:result_poly8x8 [] = { fa, f9, f9, f9, 3, 0, f9, f9,  }
+VTBL4:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL4:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTBL4:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VTBL4:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL4:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL4:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL4:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBL4:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL4:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL4:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL4:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBL4:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL4:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL4:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL4:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VTBX1 output:
+VTBX1:0:result_int8x8 [] = { 33, fffffff2, fffffff2, fffffff2, 33, 33, fffffff2, fffffff2,  }
+VTBX1:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX1:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTBX1:3:result_int64x1 [] = { 3333333333333333,  }
+VTBX1:4:result_uint8x8 [] = { cc, f3, f3, f3, cc, cc, f3, f3,  }
+VTBX1:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX1:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VTBX1:7:result_uint64x1 [] = { 3333333333333333,  }
+VTBX1:8:result_poly8x8 [] = { cc, f3, f3, f3, cc, cc, f3, f3,  }
+VTBX1:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX1:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTBX1:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VTBX1:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX1:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX1:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX1:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBX1:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX1:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX1:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX1:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBX1:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX1:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX1:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX1:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VTBX2 output:
+VTBX2:0:result_int8x8 [] = { fffffff6, fffffff3, fffffff3, fffffff3, 33, 33, fffffff3, fffffff3,  }
+VTBX2:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX2:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTBX2:3:result_int64x1 [] = { 3333333333333333,  }
+VTBX2:4:result_uint8x8 [] = { f6, f5, f5, f5, cc, cc, f5, f5,  }
+VTBX2:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX2:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VTBX2:7:result_uint64x1 [] = { 3333333333333333,  }
+VTBX2:8:result_poly8x8 [] = { f6, f5, f5, f5, cc, cc, f5, f5,  }
+VTBX2:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX2:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTBX2:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VTBX2:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX2:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX2:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX2:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBX2:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX2:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX2:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX2:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBX2:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX2:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX2:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX2:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VTBX3 output:
+VTBX3:0:result_int8x8 [] = { fffffff8, fffffff4, fffffff4, fffffff4, ffffffff, 33, fffffff4, fffffff4,  }
+VTBX3:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX3:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTBX3:3:result_int64x1 [] = { 3333333333333333,  }
+VTBX3:4:result_uint8x8 [] = { f8, f7, f7, f7, ff, cc, f7, f7,  }
+VTBX3:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX3:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VTBX3:7:result_uint64x1 [] = { 3333333333333333,  }
+VTBX3:8:result_poly8x8 [] = { f8, f7, f7, f7, ff, cc, f7, f7,  }
+VTBX3:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX3:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTBX3:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VTBX3:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX3:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX3:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX3:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBX3:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX3:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX3:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX3:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBX3:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX3:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX3:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX3:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VTBX4 output:
+VTBX4:0:result_int8x8 [] = { fffffffa, fffffff5, fffffff5, fffffff5, 3, 33, fffffff5, fffffff5,  }
+VTBX4:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX4:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTBX4:3:result_int64x1 [] = { 3333333333333333,  }
+VTBX4:4:result_uint8x8 [] = { fa, f9, f9, f9, 3, cc, f9, f9,  }
+VTBX4:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX4:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VTBX4:7:result_uint64x1 [] = { 3333333333333333,  }
+VTBX4:8:result_poly8x8 [] = { fa, f9, f9, f9, 3, cc, f9, f9,  }
+VTBX4:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX4:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTBX4:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VTBX4:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX4:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX4:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX4:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBX4:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX4:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX4:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX4:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBX4:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX4:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX4:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX4:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRECPE/VRECPEQ  (positive input) output:
+VRECPE/VRECPEQ:0:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VRECPE/VRECPEQ:1:result_uint32x4 [] = { bf000000, bf000000, bf000000, bf000000,  }
+VRECPE/VRECPEQ:2:result_float32x2 [] = { 3f068000, 3f068000,  }
+VRECPE/VRECPEQ:3:result_float32x4 [] = { 3c030000, 3c030000, 3c030000, 3c030000,  }
+
+VRECPE/VRECPEQ  (negative input) output:
+VRECPE/VRECPEQ:4:result_uint32x2 [] = { 80000000, 80000000,  }
+VRECPE/VRECPEQ:5:result_uint32x4 [] = { ee800000, ee800000, ee800000, ee800000,  }
+VRECPE/VRECPEQ:6:result_float32x2 [] = { bdcc8000, bdcc8000,  }
+VRECPE/VRECPEQ:7:result_float32x4 [] = { bc030000, bc030000, bc030000, bc030000,  }
+
+VRECPE/VRECPEQ  FP special (NaN, infinity) output:
+VRECPE/VRECPEQ:8:result_float32x2 [] = { 7fc00000, 7fc00000,  }
+VRECPE/VRECPEQ:9:result_float32x4 [] = { 0, 0, 0, 0,  }
+
+VRECPE/VRECPEQ  FP special (zero, large value) output:
+VRECPE/VRECPEQ:10:result_float32x2 [] = { 7f800000, 7f800000,  }
+VRECPE/VRECPEQ:11:result_float32x4 [] = { 0, 0, 0, 0,  }
+
+VRECPE/VRECPEQ  FP special (-0, -infinity) output:
+VRECPE/VRECPEQ:12:result_float32x2 [] = { ff800000, ff800000,  }
+VRECPE/VRECPEQ:13:result_float32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+
+VRECPE/VRECPEQ  FP special (large negative value) output:
+VRECPE/VRECPEQ:14:result_float32x2 [] = { 80000000, 80000000,  }
+
+VRSQRTE/VRSQRTEQ output:
+VRSQRTE/VRSQRTEQ:0:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VRSQRTE/VRSQRTEQ:1:result_uint32x4 [] = { 9c800000, 9c800000, 9c800000, 9c800000,  }
+VRSQRTE/VRSQRTEQ:2:result_float32x2 [] = { 3e498000, 3e498000,  }
+VRSQRTE/VRSQRTEQ:3:result_float32x4 [] = { 3e700000, 3e700000, 3e700000, 3e700000,  }
+
+VRSQRTE/VRSQRTEQ (2) output:
+VRSQRTE/VRSQRTEQ:4:result_uint32x2 [] = { 80000000, 80000000,  }
+VRSQRTE/VRSQRTEQ:5:result_uint32x4 [] = { ae800000, ae800000, ae800000, ae800000,  }
+
+VRSQRTE/VRSQRTEQ (3) output:
+VRSQRTE/VRSQRTEQ:6:result_uint32x2 [] = { b4800000, b4800000,  }
+VRSQRTE/VRSQRTEQ:7:result_uint32x4 [] = { ed000000, ed000000, ed000000, ed000000,  }
+
+VRSQRTE/VRSQRTEQ FP special (NaN, 0) output:
+VRSQRTE/VRSQRTEQ:8:result_float32x2 [] = { 7fc00000, 7fc00000,  }
+VRSQRTE/VRSQRTEQ:9:result_float32x4 [] = { 7f800000, 7f800000, 7f800000, 7f800000,  }
+
+VRSQRTE/VRSQRTEQ FP special (negative, infinity) output:
+VRSQRTE/VRSQRTEQ:10:result_float32x2 [] = { 7fc00000, 7fc00000,  }
+VRSQRTE/VRSQRTEQ:11:result_float32x4 [] = { 0, 0, 0, 0,  }
+
+VRSQRTE/VRSQRTEQ FP special (-0, -infinity) output:
+VRSQRTE/VRSQRTEQ:12:result_float32x2 [] = { ff800000, ff800000,  }
+VRSQRTE/VRSQRTEQ:13:result_float32x4 [] = { 7fc00000, 7fc00000, 7fc00000, 7fc00000,  }
+
+VCAGE/VCAGEQ output:
+VCAGE/VCAGEQ:0:result_uint32x2 [] = { ffffffff, 0,  }
+VCAGE/VCAGEQ:1:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, 0,  }
+
+VCAGE/VCAGEQ output:
+VCAGE/VCAGEQ:2:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCAGE/VCAGEQ:3:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+
+VCALE/VCALEQ output:
+VCALE/VCALEQ:0:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCALE/VCALEQ:1:result_uint32x4 [] = { 0, 0, ffffffff, ffffffff,  }
+
+VCALE/VCALEQ output:
+VCALE/VCALEQ:2:result_uint32x2 [] = { 0, 0,  }
+VCALE/VCALEQ:3:result_uint32x4 [] = { 0, 0, 0, 0,  }
+
+VCAGT/VCAGTQ output:
+VCAGT/VCAGTQ:0:result_uint32x2 [] = { 0, 0,  }
+VCAGT/VCAGTQ:1:result_uint32x4 [] = { ffffffff, ffffffff, 0, 0,  }
+
+VCAGT/VCAGTQ output:
+VCAGT/VCAGTQ:2:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCAGT/VCAGTQ:3:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+
+VCALT/VCALTQ output:
+VCALT/VCALTQ:0:result_uint32x2 [] = { 0, ffffffff,  }
+VCALT/VCALTQ:1:result_uint32x4 [] = { 0, 0, 0, ffffffff,  }
+
+VCALT/VCALTQ output:
+VCALT/VCALTQ:2:result_uint32x2 [] = { 0, 0,  }
+VCALT/VCALTQ:3:result_uint32x4 [] = { 0, 0, 0, 0,  }
+
+VCVT/VCVTQ output:
+VCVT/VCVTQ:0:result_float32x2 [] = { c1800000, c1700000,  }
+VCVT/VCVTQ:1:result_float32x2 [] = { 4f800000, 4f800000,  }
+VCVT/VCVTQ:2:result_float32x4 [] = { 41720000, c1720000, 0, 80000000,  }
+VCVT/VCVTQ:3:result_float32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+VCVT/VCVTQ:4:result_float32x4 [] = { 4f800000, 4f800000, 4f800000, 4f800000,  }
+VCVT/VCVTQ:5:result_int32x2 [] = { fffffff1, 5,  }
+VCVT/VCVTQ:6:result_uint32x2 [] = { 0, 5,  }
+VCVT/VCVTQ:7:result_float16x4 [] = { 0, 8000, 4b8f, cb8f,  }
+VCVT/VCVTQ:8:result_int32x4 [] = { 0, 0, f, fffffff1,  }
+VCVT/VCVTQ:9:result_uint32x4 [] = { 0, 0, f, 0,  }
+
+VCVT_N/VCVTQ_N output:
+VCVT_N/VCVTQ_N:10:result_float32x2 [] = { c0800000, c0700000,  }
+VCVT_N/VCVTQ_N:11:result_float32x2 [] = { 4c000000, 4c000000,  }
+VCVT_N/VCVTQ_N:12:result_float32x4 [] = { b2800000, b2700000, b2600000, b2500000,  }
+VCVT_N/VCVTQ_N:13:result_float32x4 [] = { 49800000, 49800000, 49800000, 49800000,  }
+VCVT_N/VCVTQ_N:14:result_int32x2 [] = { ff0b3333, 54cccd,  }
+VCVT_N/VCVTQ_N:15:result_uint32x2 [] = { 0, 15,  }
+VCVT_N/VCVTQ_N:16:result_int32x4 [] = { 0, 0, 1e3d7, fffe1c29,  }
+VCVT_N/VCVTQ_N:17:result_uint32x4 [] = { 0, 0, 1e, 0,  }
+
+VCVT/VCVTQ (check rounding) output:
+VCVT/VCVTQ:18:result_int32x2 [] = { a, a,  }
+VCVT/VCVTQ:19:result_uint32x2 [] = { a, a,  }
+VCVT/VCVTQ:20:result_int32x4 [] = { 7d, 7d, 7d, 7d,  }
+VCVT/VCVTQ:21:result_uint32x4 [] = { 7d, 7d, 7d, 7d,  }
+
+VCVT_N/VCVTQ_N (check rounding) output:
+VCVT_N/VCVTQ_N:22:result_int32x2 [] = { a66666, a66666,  }
+VCVT_N/VCVTQ_N:23:result_uint32x2 [] = { a66666, a66666,  }
+VCVT_N/VCVTQ_N:24:result_int32x4 [] = { fbccc, fbccc, fbccc, fbccc,  }
+VCVT_N/VCVTQ_N:25:result_uint32x4 [] = { fbccc, fbccc, fbccc, fbccc,  }
+
+VCVT_N/VCVTQ_N (check saturation) output:
+VCVT_N/VCVTQ_N:26:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VCVT_N/VCVTQ_N:27:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+
+VCVT FP16 (check fp16-fp32 inf/nan/denormal) output:
+VCVT FP16:28:result_float32x4 [] = { 38640000, 7f800000, 7fc00000, ff800000,  }
+
+VCVT FP16 (check fp32-fp16 inf/nan) output:
+VCVT FP16:29:result_float16x4 [] = { 7e00, 7c00, fc00, 8000,  }
+
+VRECPS/VRECPSQ output:
+VRECPS/VRECPSQ:0:result_float32x2 [] = { c2e19eb7, c2e19eb7,  }
+VRECPS/VRECPSQ:1:result_float32x4 [] = { c1db851f, c1db851f, c1db851f, c1db851f,  }
+
+VRECPS/VRECPSQ FP special (NAN) and normal values output:
+VRECPS/VRECPSQ:2:result_float32x2 [] = { 7fc00000, 7fc00000,  }
+VRECPS/VRECPSQ:3:result_float32x4 [] = { 7fc00000, 7fc00000, 7fc00000, 7fc00000,  }
+
+VRECPS/VRECPSQ FP special (infinity, 0) and normal values output:
+VRECPS/VRECPSQ:4:result_float32x2 [] = { ff800000, ff800000,  }
+VRECPS/VRECPSQ:5:result_float32x4 [] = { 40000000, 40000000, 40000000, 40000000,  }
+
+VRECPS/VRECPSQ FP special (infinity, 0) output:
+VRECPS/VRECPSQ:6:result_float32x2 [] = { 40000000, 40000000,  }
+VRECPS/VRECPSQ:7:result_float32x4 [] = { 40000000, 40000000, 40000000, 40000000,  }
+
+VRSQRTS/VRSQRTSQ output:
+VRSQRTS/VRSQRTSQ:0:result_float32x2 [] = { c2796b84, c2796b84,  }
+VRSQRTS/VRSQRTSQ:1:result_float32x4 [] = { c0e4a3d8, c0e4a3d8, c0e4a3d8, c0e4a3d8,  }
+
+VRSQRTS/VRSQRTSQ FP special (NAN) and normal values output:
+VRSQRTS/VRSQRTSQ:2:result_float32x2 [] = { 7fc00000, 7fc00000,  }
+VRSQRTS/VRSQRTSQ:3:result_float32x4 [] = { 7fc00000, 7fc00000, 7fc00000, 7fc00000,  }
+
+VRSQRTS/VRSQRTSQ FP special (infinity, 0) and normal values output:
+VRSQRTS/VRSQRTSQ:4:result_float32x2 [] = { ff800000, ff800000,  }
+VRSQRTS/VRSQRTSQ:5:result_float32x4 [] = { 3fc00000, 3fc00000, 3fc00000, 3fc00000,  }
+
+VRSQRTS/VRSQRTSQ FP special (infinity, 0) output:
+VRSQRTS/VRSQRTSQ:6:result_float32x2 [] = { 3fc00000, 3fc00000,  }
+VRSQRTS/VRSQRTSQ:7:result_float32x4 [] = { 3fc00000, 3fc00000, 3fc00000, 3fc00000,  }
+
+
+Integer (non-NEON) intrinsics
+__clz(0xffffffff) = 0
+__clz(0x7fffffff) = 1
+__clz(0x3fffffff) = 2
+__clz(0x1fffffff) = 3
+__clz(0xfffffff) = 4
+__clz(0x7ffffff) = 5
+__clz(0x3ffffff) = 6
+__clz(0x1ffffff) = 7
+__clz(0xffffff) = 8
+__clz(0x7fffff) = 9
+__clz(0x3fffff) = 10
+__clz(0x1fffff) = 11
+__clz(0xfffff) = 12
+__clz(0x7ffff) = 13
+__clz(0x3ffff) = 14
+__clz(0x1ffff) = 15
+__clz(0xffff) = 16
+__clz(0x7fff) = 17
+__clz(0x3fff) = 18
+__clz(0x1fff) = 19
+__clz(0xfff) = 20
+__clz(0x7ff) = 21
+__clz(0x3ff) = 22
+__clz(0x1ff) = 23
+__clz(0xff) = 24
+__clz(0x7f) = 25
+__clz(0x3f) = 26
+__clz(0x1f) = 27
+__clz(0xf) = 28
+__clz(0x7) = 29
+__clz(0x3) = 30
+__clz(0x1) = 31
+__clz(0) = 32
+__qadd(0x1, 0x2) = 0x3 sat 0
+__qadd(0xffffffff, 0xfffffffe) = 0xfffffffd sat 0
+__qadd(0xffffffff, 0x2) = 0x1 sat 0
+__qadd(0x7000, 0x7000) = 0xe000 sat 0
+__qadd(0x8fff, 0x8fff) = 0x11ffe sat 0
+__qadd(0x70000000, 0x70000000) = 0x7fffffff sat 1
+__qadd(0x8fffffff, 0x8fffffff) = 0x80000000 sat 1
+__qdbl(0x1) = 0x2 sat 0
+__qdbl(0x70000000) = 0x7fffffff sat 1
+__qdbl(0x8fffffff) = 0x80000000 sat 1
+__qdbl(0xefffffff) = 0xdffffffe sat 0
+__qsub(0x1, 0x2) = 0xffffffff sat 0
+__qsub(0xffffffff, 0xfffffffe) = 0x1 sat 0
+__qsub(0xffffffff, 0x2) = 0xfffffffd sat 0
+__qsub(0x7000, 0xffff9000) = 0xe000 sat 0
+__qsub(0x8fff, 0xffff7001) = 0x11ffe sat 0
+__qsub(0x70000000, 0x90000000) = 0x7fffffff sat 1
+__qsub(0x8fffffff, 0x70000001) = 0x80000000 sat 1
+__qsub(0, 0x80000000) = 0x7fffffff sat 1
+__rbit(0x12345678) = 0x1e6a2c48
+__rev(0x12345678) = 0x78563412
+__ssat(0x12345678, 30) = 0x12345678 sat 0
+__ssat(0x12345678, 19) = 0x3ffff sat 1
+__ssat(0x87654321, 29) = 0xf0000000 sat 1
+__ssat(0x87654321, 12) = 0xfffff800 sat 1
+__ssat(0x87654321, 32) = 0x87654321 sat 0
+__ssat(0x87654321, 1) = 0xffffffff sat 1
+__usat(0x12345678, 30) = 0x12345678 sat 0
+__usat(0x12345678, 19) = 0x7ffff sat 1
+__usat(0x87654321, 29) = 0 sat 1
+__usat(0x87654321, 12) = 0 sat 1
+__usat(0x87654321, 31) = 0 sat 1
+__usat(0x87654321, 0) = 0 sat 1
+
+
+DSP (non-NEON) intrinsics
+qadd(0x1, 0x2) = 0x3 sat 0
+qadd(0xffffffff, 0xfffffffe) = 0xfffffffd sat 0
+qadd(0xffffffff, 0x2) = 0x1 sat 0
+qadd(0x7000, 0x7000) = 0xe000 sat 0
+qadd(0x8fff, 0x8fff) = 0x11ffe sat 0
+qadd(0x70000000, 0x70000000) = 0x7fffffff sat 1
+qadd(0x8fffffff, 0x8fffffff) = 0x80000000 sat 1
+qsub(0x1, 0x2) = 0xffffffff sat 0
+qsub(0xffffffff, 0xfffffffe) = 0x1 sat 0
+qsub(0xffffffff, 0x2) = 0xfffffffd sat 0
+qsub(0x7000, 0xffff9000) = 0xe000 sat 0
+qsub(0x8fff, 0xffff7001) = 0x11ffe sat 0
+qsub(0x70000000, 0x90000000) = 0x7fffffff sat 1
+qsub(0x8fffffff, 0x70000001) = 0x80000000 sat 1
+qsub(0, 0x80000000) = 0x7fffffff sat 1
+qdadd(0x1, 0x2) = 0x5 sat 0
+qdadd(0xffffffff, 0xfffffffe) = 0xfffffffb sat 0
+qdadd(0xffffffff, 0x2) = 0x3 sat 0
+qdadd(0x7000, 0x7000) = 0x15000 sat 0
+qdadd(0x8fff, 0x8fff) = 0x1affd sat 0
+qdadd(0x70000000, 0x70000000) = 0x7fffffff sat 1
+qdadd(0, 0x70000000) = 0x7fffffff sat 1
+qdadd(0x8fffffff, 0x8fffffff) = 0x80000000 sat 1
+qdadd(0, 0x8fffffff) = 0x80000000 sat 1
+qdsub(0x1, 0x2) = 0xfffffffd sat 0
+qdsub(0xffffffff, 0xfffffffe) = 0x3 sat 0
+qdsub(0xffffffff, 0x2) = 0xfffffffb sat 0
+qdsub(0x7000, 0xffff9000) = 0x15000 sat 0
+qdsub(0x8fff, 0xffff7001) = 0x1affd sat 0
+qdsub(0x70000000, 0x90000000) = 0x7fffffff sat 1
+qdsub(0, 0x90000000) = 0x7fffffff sat 1
+qdsub(0x8fffffff, 0x70000001) = 0x80000000 sat 1
+qdsub(0, 0x70000001) = 0x80000001 sat 1
+smulbb(0x12345678, 0x12345678) = 0x1d34d840
+smulbt(0x12345678, 0x12345678) = 0x6260060
+smultb(0x12345678, 0x12345678) = 0x6260060
+smultt(0x12345678, 0x12345678) = 0x14b5a90
+smulbb(0xf123f456, 0xf123f456) = 0x880ce4
+smulbt(0xf123f456, 0xf123f456) = 0xad5dc2
+smultb(0xf123f456, 0xf123f456) = 0xad5dc2
+smultt(0xf123f456, 0xf123f456) = 0xdceac9
+smlabb(0x12345678, 0x12345678, 0x1020304) = 0x1e36db44
+smlabt(0x12345678, 0x12345678, 0x1020304) = 0x7280364
+smlatb(0x12345678, 0x12345678, 0x1020304) = 0x7280364
+smlatt(0x12345678, 0x12345678, 0x1020304) = 0x24d5d94
+smlabb(0xf123f456, 0xf123f456, 0x1020304) = 0x18a0fe8
+smlabt(0xf123f456, 0xf123f456, 0x1020304) = 0x1af60c6
+smlatb(0xf123f456, 0xf123f456, 0x1020304) = 0x1af60c6
+smlatt(0xf123f456, 0xf123f456, 0x1020304) = 0x1deedcd
+smlalbb(&0x9abcdef0, &0x12345678, 0x12345678, 0x12345678) = 0x123456780xb7f1b730
+smlalbt(&0x9abcdef0, &0x12345678, 0x12345678, 0x12345678) = 0x123456780xa0e2df50
+smlaltb(&0x9abcdef0, &0x12345678, 0x12345678, 0x12345678) = 0x123456780xa0e2df50
+smlaltt(&0x9abcdef0, &0x12345678, 0x12345678, 0x12345678) = 0x123456780x9c083980
+smlalbb(&0x9abcdef0, &0x12345678, 0xf123f456, 0xf123f456) = 0x123456780x9b44ebd4
+smlalbt(&0x9abcdef0, &0x12345678, 0xf123f456, 0xf123f456) = 0x123456780x9b6a3cb2
+smlaltb(&0x9abcdef0, &0x12345678, 0xf123f456, 0xf123f456) = 0x123456780x9b6a3cb2
+smlaltt(&0x9abcdef0, &0x12345678, 0xf123f456, 0xf123f456) = 0x123456780x9b99c9b9
+smlalbb(&0xffffffff, &0x12345678, 0x7fff7fff, 0x7fff7fff) = 0x123456790x3fff0000
+smlalbt(&0xffffffff, &0x12345678, 0x7fff7fff, 0x7fff7fff) = 0x123456790x3fff0000
+smlaltb(&0xffffffff, &0x12345678, 0x7fff7fff, 0x7fff7fff) = 0x123456790x3fff0000
+smlaltt(&0xffffffff, &0x12345678, 0x7fff7fff, 0x7fff7fff) = 0x123456790x3fff0000
+smulwb(0x12345678, 0x12345678) = 0x6261d94
+smulwt(0x12345678, 0x12345678) = 0x14b60b6
+smulwb(0xf123f456, 0xf123f456) = 0xad52a0
+smulwt(0xf123f456, 0xf123f456) = 0xdcdc99
+smlawb(0x12345678, 0x12345678, 0x1020304) = 0x7282098
+smlawt(0x12345678, 0x12345678, 0x1020304) = 0x24d63ba
+smlawb(0xf123f456, 0xf123f456, 0x1020304) = 0x1af55a4
+smlawt(0xf123f456, 0xf123f456, 0X1020304) = 0x1dedf9d
+
+
+DSP FNS (non-NEON/ITU) intrinsics with input Overflow=0 and input Carry=0
+Checking saturate with input Overflow=0 and input Carry=0
+saturate(0x1) = 0x1 overflow 0 carry 0
+saturate(0xffffffff) = 0xffffffff overflow 0 carry 0
+saturate(0x8000) = 0x7fff overflow 1 carry 0
+saturate(0xffff8000) = 0xffff8000 overflow 0 carry 0
+saturate(0xffff7fff) = 0xffff8000 overflow 1 carry 0
+add(0x1, 0x1) = 0x2 overflow 0 carry 0
+add(0xffffffff, 0xffffffff) = 0xfffffffe overflow 0 carry 0
+add(0x4e20, 0x4e20) = 0x7fff overflow 1 carry 0
+add(0xffffb1e0, 0xffffb1e0) = 0xffff8000 overflow 1 carry 0
+sub(0x1, 0x1) = 0 overflow 0 carry 0
+sub(0xffffffff, 0xffffffff) = 0 overflow 0 carry 0
+sub(0x4e20, 0x4e20) = 0 overflow 0 carry 0
+sub(0xffffb1e0, 0xffffb1e0) = 0 overflow 0 carry 0
+sub(0, 0xffff8000) = 0x7fff overflow 1 carry 0
+abs_s(0x1) = 0x1 overflow 0 carry 0
+abs_s(0xffffffff) = 0x1 overflow 0 carry 0
+abs_s(0xffff8000) = 0x7fff overflow 0 carry 0
+shl(0x1, 1) = 0x2 overflow 0 carry 0
+shl(0xa, 1) = 0x14 overflow 0 carry 0
+shl(0xfff, 10) = 0x7fff overflow 1 carry 0
+shl(0xfff, 20) = 0x7fff overflow 1 carry 0
+shl(0x1, -1) = 0 overflow 0 carry 0
+shl(0x14, -1) = 0xa overflow 0 carry 0
+shl(0xfff, -10) = 0x3 overflow 0 carry 0
+shl(0xfff, -64) = 0 overflow 0 carry 0
+shr(0x1, -1) = 0x2 overflow 0 carry 0
+shr(0xa, -1) = 0x14 overflow 0 carry 0
+shr(0xfff, -10) = 0x7fff overflow 1 carry 0
+shr(0xfff, -20) = 0x7fff overflow 1 carry 0
+shr(0x1, 1) = 0 overflow 0 carry 0
+shr(0x14, 1) = 0xa overflow 0 carry 0
+shr(0xfff, 10) = 0x3 overflow 0 carry 0
+shr(0xfff, 64) = 0 overflow 0 carry 0
+mult(0x2, 0x2) = 0 overflow 0 carry 0
+mult(0xffffffff, 0xffffffff) = 0 overflow 0 carry 0
+mult(0xffff8000, 0xffff8000) = 0x7fff overflow 1 carry 0
+L_mult(0x2, 0x2) = 0x8 overflow 0 carry 0
+L_mult(0xffffffff, 0xffffffff) = 0x2 overflow 0 carry 0
+L_mult(0xffff8000, 0xffff8000) = 0x7fffffff overflow 1 carry 0
+negate(0x1) = 0xffffffff overflow 0 carry 0
+negate(0xffffffff) = 0x1 overflow 0 carry 0
+negate(0xffff8000) = 0x7fff overflow 0 carry 0
+extract_h(0x1) = 0 overflow 0 carry 0
+extract_h(0xffffffff) = 0xffffffff overflow 0 carry 0
+extract_h(0xffff8000) = 0xffffffff overflow 0 carry 0
+extract_h(0x12345678) = 0x1234 overflow 0 carry 0
+extract_l(0x1) = 0x1 overflow 0 carry 0
+extract_l(0xffffffff) = 0xffffffff overflow 0 carry 0
+extract_l(0xffff8000) = 0xffff8000 overflow 0 carry 0
+extract_l(0x43218765) = 0xffff8765 overflow 0 carry 0
+round(0x1) = 0 overflow 0 carry 0
+round(0xffffffff) = 0 overflow 0 carry 0
+round(0xffff8000) = 0 overflow 0 carry 0
+round(0x43218765) = 0x4322 overflow 0 carry 0
+round(0x87654321) = 0xffff8765 overflow 0 carry 0
+L_mac(0x1234, 0x2, 0x2) = 0x123c overflow 0 carry 0
+L_mac(0x1234, 0xffffffff, 0xffffffff) = 0x1236 overflow 0 carry 0
+L_mac(0x1234, 0xffff8000, 0xffff8000) = 0x7fffffff overflow 1 carry 0
+L_mac(0xffffffff, 0xffff8000, 0xffff8000) = 0x7ffffffe overflow 1 carry 0
+L_msu(0x1234, 0x2, 0x2) = 0x122c overflow 0 carry 0
+L_msu(0x1234, 0xffffffff, 0xffffffff) = 0x1232 overflow 0 carry 0
+L_msu(0x1234, 0xffff8000, 0xffff8000) = 0x80001235 overflow 1 carry 0
+L_msu(0x1, 0xffff8000, 0xffff8000) = 0x80000002 overflow 1 carry 0
+L_add(0x1, 0x2) = 0x3 overflow 0 carry 0
+L_add(0xffffffff, 0xfffffffe) = 0xfffffffd overflow 0 carry 0
+L_add(0xffffffff, 0x2) = 0x1 overflow 0 carry 0
+L_add(0x7000, 0x7000) = 0xe000 overflow 0 carry 0
+L_add(0x8fff, 0x8fff) = 0x11ffe overflow 0 carry 0
+L_add(0x70000000, 0x70000000) = 0x7fffffff overflow 1 carry 0
+L_add(0x8fffffff, 0x8fffffff) = 0x80000000 overflow 1 carry 0
+L_sub(0x1, 0x2) = 0xffffffff overflow 0 carry 0
+L_sub(0xffffffff, 0xfffffffe) = 0x1 overflow 0 carry 0
+L_sub(0xffffffff, 0x2) = 0xfffffffd overflow 0 carry 0
+L_sub(0x7000, 0xffff9000) = 0xe000 overflow 0 carry 0
+L_sub(0x8fff, 0xffff7001) = 0x11ffe overflow 0 carry 0
+L_sub(0x70000000, 0x90000000) = 0x7fffffff overflow 1 carry 0
+L_sub(0x8fffffff, 0x70000001) = 0x80000000 overflow 1 carry 0
+L_sub(0, 0x80000000) = 0x7fffffff overflow 1 carry 0
+Checking L_add_c with input Overflow=0 and input Carry=0
+L_add_c(0x1, 0x2) = 0x3 overflow 0 carry 0
+L_add_c(0xffffffff, 0xfffffffe) = 0xfffffffd overflow 0 carry 1
+L_add_c(0xffffffff, 0x2) = 0x1 overflow 0 carry 1
+L_add_c(0x7000, 0x7000) = 0xe000 overflow 0 carry 0
+L_add_c(0x8fff, 0x8fff) = 0x11ffe overflow 0 carry 0
+L_add_c(0x70000000, 0x70000000) = 0xe0000000 overflow 1 carry 0
+L_add_c(0x8fffffff, 0x8fffffff) = 0x1ffffffe overflow 1 carry 1
+L_add_c(0x8fffffff, 0xffffffff) = 0x8ffffffe overflow 0 carry 1
+L_sub_c(0x1, 0x2) = 0xfffffffe overflow 0 carry 0
+L_sub_c(0xffffffff, 0xfffffffe) = 0 overflow 0 carry 1
+L_sub_c(0xffffffff, 0x2) = 0xfffffffc overflow 0 carry 1
+L_sub_c(0x7000, 0x7000) = 0xffffffff overflow 0 carry 0
+L_sub_c(0x8fff, 0x8fff) = 0xffffffff overflow 0 carry 0
+L_sub_c(0x70000000, 0x70000000) = 0xffffffff overflow 0 carry 0
+L_sub_c(0x8fffffff, 0x8fffffff) = 0xffffffff overflow 0 carry 0
+L_sub_c(0x1, 0x80000000) = 0x80000000 overflow 1 carry 0
+L_sub_c(0xffffffff, 0x7fffffff) = 0x7fffffff overflow 1 carry 1
+Checking L_macNs with input Overflow=0 and input Carry=0
+L_macNs(0x1234, 0x2, 0x2) = 0x123c overflow 0 carry 0
+L_macNs(0x1234, 0xffffffff, 0xffffffff) = 0x1236 overflow 0 carry 0
+L_macNs(0x1234, 0xffff8000, 0xffff8000) = 0x80001233 overflow 1 carry 0
+L_macNs(0xffffffff, 0xffff8000, 0xffff8000) = 0x7ffffffe overflow 1 carry 1
+Checking L_msuNs with input Overflow=0 and input Carry=0
+L_msuNs(0x1234, 0x2, 0x2) = 0x122b overflow 0 carry 1
+L_msuNs(0x1234, 0xffffffff, 0xffffffff) = 0x1231 overflow 0 carry 1
+L_msuNs(0x1234, 0xffff8000, 0xffff8000) = 0x80001234 overflow 1 carry 0
+L_msuNs(0xffffffff, 0xffff8000, 0xffff8000) = 0x7fffffff overflow 1 carry 1
+negate(0x1) = 0xffffffff overflow 0 carry 0
+negate(0xffffffff) = 0x1 overflow 0 carry 0
+negate(0xffff8000) = 0x7fff overflow 0 carry 0
+mult_r(0x2, 0x2) = 0 overflow 0 carry 0
+mult_r(0xffffffff, 0xffffffff) = 0 overflow 0 carry 0
+mult_r(0xffff8000, 0xffff8000) = 0x7fff overflow 1 carry 0
+norm_s(0x1) = 0xe overflow 0 carry 0
+norm_s(0xffffffff) = 0xf overflow 0 carry 0
+norm_s(0xffff8000) = 0 overflow 0 carry 0
+norm_s(0x2ee0) = 0x1 overflow 0 carry 0
+norm_l(0x1) = 0x1e overflow 0 carry 0
+norm_l(0xffffffff) = 0x1f overflow 0 carry 0
+norm_l(0xffff8000) = 0x10 overflow 0 carry 0
+norm_l(0x2ee0) = 0x11 overflow 0 carry 0
+norm_l(0x123456) = 0xa overflow 0 carry 0
+norm_l(0xabcdef) = 0x7 overflow 0 carry 0
+L_shl(0x1, 1) = 0x2 overflow 0 carry 0
+L_shl(0xa, 1) = 0x14 overflow 0 carry 0
+L_shl(0xfff, 10) = 0x3ffc00 overflow 0 carry 0
+L_shl(0xfff, 20) = 0x7fffffff overflow 1 carry 0
+L_shl(0x12345678, 2) = 0x48d159e0 overflow 0 carry 0
+L_shl(0x12345678, 40) = 0x7fffffff overflow 1 carry 0
+L_shl(0x1, -1) = 0 overflow 0 carry 0
+L_shl(0x14, -1) = 0xa overflow 0 carry 0
+L_shl(0xfff, -10) = 0x3 overflow 0 carry 0
+L_shl(0xfff, -64) = 0 overflow 0 carry 0
+L_shl(0x12345678, -10) = 0x48d15 overflow 0 carry 0
+L_shl(0x12345678, -64) = 0 overflow 0 carry 0
+L_shr(0x1, -1) = 0x2 overflow 0 carry 0
+L_shr(0xa, -1) = 0x14 overflow 0 carry 0
+L_shr(0xfff, -10) = 0x3ffc00 overflow 0 carry 0
+L_shr(0xfff, -20) = 0x7fffffff overflow 1 carry 0
+L_shr(0x12345678, -10) = 0x7fffffff overflow 1 carry 0
+L_shr(0x12345678, -40) = 0x7fffffff overflow 1 carry 0
+L_shr(0x1, 1) = 0 overflow 0 carry 0
+L_shr(0x14, 1) = 0xa overflow 0 carry 0
+L_shr(0xfff, 10) = 0x3 overflow 0 carry 0
+L_shr(0xfff, 64) = 0 overflow 0 carry 0
+L_shr(0x12345678, 10) = 0x48d15 overflow 0 carry 0
+L_shr(0x12345678, 64) = 0 overflow 0 carry 0
+shr_r(0x1, -1) = 0x2 overflow 0 carry 0
+shr_r(0xa, -1) = 0x14 overflow 0 carry 0
+shr_r(0xfff, -10) = 0x7fff overflow 1 carry 0
+shr_r(0xfff, -20) = 0x7fff overflow 1 carry 0
+shr_r(0x1, 1) = 0x1 overflow 0 carry 0
+shr_r(0x14, 1) = 0xa overflow 0 carry 0
+shr_r(0xfff, 10) = 0x4 overflow 0 carry 0
+shr_r(0xfff, 64) = 0 overflow 0 carry 0
+mac_r(0x1234, 0x2, 0x2) = 0 overflow 0 carry 0
+mac_r(0x1234, 0xffffffff, 0xffffffff) = 0 overflow 0 carry 0
+mac_r(0x1234, 0xffff8000, 0xffff8000) = 0x7fff overflow 1 carry 0
+mac_r(0xffffffff, 0xffff8000, 0xffff8000) = 0x7fff overflow 1 carry 0
+mac_r(0x123456, 0x244, 0x522) = 0x29 overflow 0 carry 0
+msu_r(0x1234, 0x2, 0x2) = 0 overflow 0 carry 0
+msu_r(0x1234, 0xffffffff, 0xffffffff) = 0 overflow 0 carry 0
+msu_r(0x1234, 0xffff8000, 0xffff8000) = 0xffff8000 overflow 1 carry 0
+msu_r(0x1, 0xffff8000, 0xffff8000) = 0xffff8000 overflow 1 carry 0
+msu_r(0x123456, 0x321, 0x243) = 0x4 overflow 0 carry 0
+L_deposit_h(0x1) = 0x10000 overflow 0 carry 0
+L_deposit_h(0xffffffff) = 0xffff0000 overflow 0 carry 0
+L_deposit_h(0xffff8000) = 0x80000000 overflow 0 carry 0
+L_deposit_h(0x1234) = 0x12340000 overflow 0 carry 0
+L_deposit_l(0x1) = 0x1 overflow 0 carry 0
+L_deposit_l(0xffffffff) = 0xffffffff overflow 0 carry 0
+L_deposit_l(0xffff8000) = 0xffff8000 overflow 0 carry 0
+L_deposit_l(0x1234) = 0x1234 overflow 0 carry 0
+L_shr_r(0x1, -1) = 0x2 overflow 0 carry 0
+L_shr_r(0xa, -1) = 0x14 overflow 0 carry 0
+L_shr_r(0xfff, -10) = 0x3ffc00 overflow 0 carry 0
+L_shr_r(0xfff, -20) = 0x7fffffff overflow 1 carry 0
+L_shr_r(0x12345678, -10) = 0x7fffffff overflow 1 carry 0
+L_shr_r(0x12345678, -40) = 0x7fffffff overflow 1 carry 0
+L_shr_r(0x1, 1) = 0x1 overflow 0 carry 0
+L_shr_r(0x14, 1) = 0xa overflow 0 carry 0
+L_shr_r(0xfff, 10) = 0x4 overflow 0 carry 0
+L_shr_r(0xfff, 64) = 0 overflow 0 carry 0
+L_shr_r(0x12345678, 10) = 0x48d16 overflow 0 carry 0
+L_shr_r(0x12345678, 64) = 0 overflow 0 carry 0
+L_abs(0x1) = 0x1 overflow 0 carry 0
+L_abs(0xffffffff) = 0x1 overflow 0 carry 0
+L_abs(0x80000000) = 0x7fffffff overflow 1 carry 0
+L_sat(0x1) = 0x1 overflow 0 carry 0
+L_sat(0xffffffff) = 0xffffffff overflow 0 carry 0
+L_sat(0xffff8000) = 0xffff8000 overflow 0 carry 0
+L_sat(0x8000) = 0x8000 overflow 0 carry 0
+div_s(0x1, 0x1) = 0x7fff overflow 0 carry 0
+div_s(0x2710, 0x4e20) = 0x4000 overflow 0 carry 0
+div_s(0x2710, 0x4e20) = 0x4000 overflow 0 carry 0
+
+
+DSP FNS (non-NEON/ITU) intrinsics with input Overflow=0 and input Carry=1
+Checking saturate with input Overflow=0 and input Carry=1
+saturate(0x1) = 0x1 overflow 0 carry 1
+saturate(0xffffffff) = 0xffffffff overflow 0 carry 1
+saturate(0x8000) = 0x7fff overflow 1 carry 1
+saturate(0xffff8000) = 0xffff8000 overflow 0 carry 1
+saturate(0xffff7fff) = 0xffff8000 overflow 1 carry 1
+add(0x1, 0x1) = 0x2 overflow 0 carry 1
+add(0xffffffff, 0xffffffff) = 0xfffffffe overflow 0 carry 1
+add(0x4e20, 0x4e20) = 0x7fff overflow 1 carry 1
+add(0xffffb1e0, 0xffffb1e0) = 0xffff8000 overflow 1 carry 1
+sub(0x1, 0x1) = 0 overflow 0 carry 1
+sub(0xffffffff, 0xffffffff) = 0 overflow 0 carry 1
+sub(0x4e20, 0x4e20) = 0 overflow 0 carry 1
+sub(0xffffb1e0, 0xffffb1e0) = 0 overflow 0 carry 1
+sub(0, 0xffff8000) = 0x7fff overflow 1 carry 1
+abs_s(0x1) = 0x1 overflow 0 carry 1
+abs_s(0xffffffff) = 0x1 overflow 0 carry 1
+abs_s(0xffff8000) = 0x7fff overflow 0 carry 1
+shl(0x1, 1) = 0x2 overflow 0 carry 1
+shl(0xa, 1) = 0x14 overflow 0 carry 1
+shl(0xfff, 10) = 0x7fff overflow 1 carry 1
+shl(0xfff, 20) = 0x7fff overflow 1 carry 1
+shl(0x1, -1) = 0 overflow 0 carry 1
+shl(0x14, -1) = 0xa overflow 0 carry 1
+shl(0xfff, -10) = 0x3 overflow 0 carry 1
+shl(0xfff, -64) = 0 overflow 0 carry 1
+shr(0x1, -1) = 0x2 overflow 0 carry 1
+shr(0xa, -1) = 0x14 overflow 0 carry 1
+shr(0xfff, -10) = 0x7fff overflow 1 carry 1
+shr(0xfff, -20) = 0x7fff overflow 1 carry 1
+shr(0x1, 1) = 0 overflow 0 carry 1
+shr(0x14, 1) = 0xa overflow 0 carry 1
+shr(0xfff, 10) = 0x3 overflow 0 carry 1
+shr(0xfff, 64) = 0 overflow 0 carry 1
+mult(0x2, 0x2) = 0 overflow 0 carry 1
+mult(0xffffffff, 0xffffffff) = 0 overflow 0 carry 1
+mult(0xffff8000, 0xffff8000) = 0x7fff overflow 1 carry 1
+L_mult(0x2, 0x2) = 0x8 overflow 0 carry 1
+L_mult(0xffffffff, 0xffffffff) = 0x2 overflow 0 carry 1
+L_mult(0xffff8000, 0xffff8000) = 0x7fffffff overflow 1 carry 1
+negate(0x1) = 0xffffffff overflow 0 carry 1
+negate(0xffffffff) = 0x1 overflow 0 carry 1
+negate(0xffff8000) = 0x7fff overflow 0 carry 1
+extract_h(0x1) = 0 overflow 0 carry 1
+extract_h(0xffffffff) = 0xffffffff overflow 0 carry 1
+extract_h(0xffff8000) = 0xffffffff overflow 0 carry 1
+extract_h(0x12345678) = 0x1234 overflow 0 carry 1
+extract_l(0x1) = 0x1 overflow 0 carry 1
+extract_l(0xffffffff) = 0xffffffff overflow 0 carry 1
+extract_l(0xffff8000) = 0xffff8000 overflow 0 carry 1
+extract_l(0x43218765) = 0xffff8765 overflow 0 carry 1
+round(0x1) = 0 overflow 0 carry 1
+round(0xffffffff) = 0 overflow 0 carry 1
+round(0xffff8000) = 0 overflow 0 carry 1
+round(0x43218765) = 0x4322 overflow 0 carry 1
+round(0x87654321) = 0xffff8765 overflow 0 carry 1
+L_mac(0x1234, 0x2, 0x2) = 0x123c overflow 0 carry 1
+L_mac(0x1234, 0xffffffff, 0xffffffff) = 0x1236 overflow 0 carry 1
+L_mac(0x1234, 0xffff8000, 0xffff8000) = 0x7fffffff overflow 1 carry 1
+L_mac(0xffffffff, 0xffff8000, 0xffff8000) = 0x7ffffffe overflow 1 carry 1
+L_msu(0x1234, 0x2, 0x2) = 0x122c overflow 0 carry 1
+L_msu(0x1234, 0xffffffff, 0xffffffff) = 0x1232 overflow 0 carry 1
+L_msu(0x1234, 0xffff8000, 0xffff8000) = 0x80001235 overflow 1 carry 1
+L_msu(0x1, 0xffff8000, 0xffff8000) = 0x80000002 overflow 1 carry 1
+L_add(0x1, 0x2) = 0x3 overflow 0 carry 1
+L_add(0xffffffff, 0xfffffffe) = 0xfffffffd overflow 0 carry 1
+L_add(0xffffffff, 0x2) = 0x1 overflow 0 carry 1
+L_add(0x7000, 0x7000) = 0xe000 overflow 0 carry 1
+L_add(0x8fff, 0x8fff) = 0x11ffe overflow 0 carry 1
+L_add(0x70000000, 0x70000000) = 0x7fffffff overflow 1 carry 1
+L_add(0x8fffffff, 0x8fffffff) = 0x80000000 overflow 1 carry 1
+L_sub(0x1, 0x2) = 0xffffffff overflow 0 carry 1
+L_sub(0xffffffff, 0xfffffffe) = 0x1 overflow 0 carry 1
+L_sub(0xffffffff, 0x2) = 0xfffffffd overflow 0 carry 1
+L_sub(0x7000, 0xffff9000) = 0xe000 overflow 0 carry 1
+L_sub(0x8fff, 0xffff7001) = 0x11ffe overflow 0 carry 1
+L_sub(0x70000000, 0x90000000) = 0x7fffffff overflow 1 carry 1
+L_sub(0x8fffffff, 0x70000001) = 0x80000000 overflow 1 carry 1
+L_sub(0, 0x80000000) = 0x7fffffff overflow 1 carry 1
+Checking L_add_c with input Overflow=0 and input Carry=1
+L_add_c(0x1, 0x2) = 0x4 overflow 0 carry 0
+L_add_c(0xffffffff, 0xfffffffe) = 0xfffffffe overflow 0 carry 1
+L_add_c(0xffffffff, 0x2) = 0x2 overflow 0 carry 1
+L_add_c(0x7000, 0x7000) = 0xe001 overflow 0 carry 0
+L_add_c(0x8fff, 0x8fff) = 0x11fff overflow 0 carry 0
+L_add_c(0x70000000, 0x70000000) = 0xe0000001 overflow 1 carry 0
+L_add_c(0x8fffffff, 0x8fffffff) = 0x1fffffff overflow 1 carry 1
+L_add_c(0x8fffffff, 0xffffffff) = 0x8fffffff overflow 0 carry 1
+L_sub_c(0x1, 0x2) = 0xffffffff overflow 0 carry 0
+L_sub_c(0xffffffff, 0xfffffffe) = 0x1 overflow 0 carry 1
+L_sub_c(0xffffffff, 0x2) = 0xfffffffd overflow 0 carry 1
+L_sub_c(0x7000, 0x7000) = 0 overflow 0 carry 1
+L_sub_c(0x8fff, 0x8fff) = 0 overflow 0 carry 1
+L_sub_c(0x70000000, 0x70000000) = 0 overflow 0 carry 1
+L_sub_c(0x8fffffff, 0x8fffffff) = 0 overflow 0 carry 1
+L_sub_c(0x1, 0x80000000) = 0x80000001 overflow 1 carry 0
+L_sub_c(0xffffffff, 0x7fffffff) = 0x80000000 overflow 0 carry 1
+Checking L_macNs with input Overflow=0 and input Carry=1
+L_macNs(0x1234, 0x2, 0x2) = 0x123d overflow 0 carry 0
+L_macNs(0x1234, 0xffffffff, 0xffffffff) = 0x1237 overflow 0 carry 0
+L_macNs(0x1234, 0xffff8000, 0xffff8000) = 0x80001234 overflow 1 carry 0
+L_macNs(0xffffffff, 0xffff8000, 0xffff8000) = 0x7fffffff overflow 1 carry 1
+Checking L_msuNs with input Overflow=0 and input Carry=1
+L_msuNs(0x1234, 0x2, 0x2) = 0x122c overflow 0 carry 1
+L_msuNs(0x1234, 0xffffffff, 0xffffffff) = 0x1232 overflow 0 carry 1
+L_msuNs(0x1234, 0xffff8000, 0xffff8000) = 0x80001235 overflow 1 carry 0
+L_msuNs(0xffffffff, 0xffff8000, 0xffff8000) = 0x80000000 overflow 1 carry 1
+negate(0x1) = 0xffffffff overflow 0 carry 1
+negate(0xffffffff) = 0x1 overflow 0 carry 1
+negate(0xffff8000) = 0x7fff overflow 0 carry 1
+mult_r(0x2, 0x2) = 0 overflow 0 carry 1
+mult_r(0xffffffff, 0xffffffff) = 0 overflow 0 carry 1
+mult_r(0xffff8000, 0xffff8000) = 0x7fff overflow 1 carry 1
+norm_s(0x1) = 0xe overflow 0 carry 1
+norm_s(0xffffffff) = 0xf overflow 0 carry 1
+norm_s(0xffff8000) = 0 overflow 0 carry 1
+norm_s(0x2ee0) = 0x1 overflow 0 carry 1
+norm_l(0x1) = 0x1e overflow 0 carry 1
+norm_l(0xffffffff) = 0x1f overflow 0 carry 1
+norm_l(0xffff8000) = 0x10 overflow 0 carry 1
+norm_l(0x2ee0) = 0x11 overflow 0 carry 1
+norm_l(0x123456) = 0xa overflow 0 carry 1
+norm_l(0xabcdef) = 0x7 overflow 0 carry 1
+L_shl(0x1, 1) = 0x2 overflow 0 carry 1
+L_shl(0xa, 1) = 0x14 overflow 0 carry 1
+L_shl(0xfff, 10) = 0x3ffc00 overflow 0 carry 1
+L_shl(0xfff, 20) = 0x7fffffff overflow 1 carry 1
+L_shl(0x12345678, 2) = 0x48d159e0 overflow 0 carry 1
+L_shl(0x12345678, 40) = 0x7fffffff overflow 1 carry 1
+L_shl(0x1, -1) = 0 overflow 0 carry 1
+L_shl(0x14, -1) = 0xa overflow 0 carry 1
+L_shl(0xfff, -10) = 0x3 overflow 0 carry 1
+L_shl(0xfff, -64) = 0 overflow 0 carry 1
+L_shl(0x12345678, -10) = 0x48d15 overflow 0 carry 1
+L_shl(0x12345678, -64) = 0 overflow 0 carry 1
+L_shr(0x1, -1) = 0x2 overflow 0 carry 1
+L_shr(0xa, -1) = 0x14 overflow 0 carry 1
+L_shr(0xfff, -10) = 0x3ffc00 overflow 0 carry 1
+L_shr(0xfff, -20) = 0x7fffffff overflow 1 carry 1
+L_shr(0x12345678, -10) = 0x7fffffff overflow 1 carry 1
+L_shr(0x12345678, -40) = 0x7fffffff overflow 1 carry 1
+L_shr(0x1, 1) = 0 overflow 0 carry 1
+L_shr(0x14, 1) = 0xa overflow 0 carry 1
+L_shr(0xfff, 10) = 0x3 overflow 0 carry 1
+L_shr(0xfff, 64) = 0 overflow 0 carry 1
+L_shr(0x12345678, 10) = 0x48d15 overflow 0 carry 1
+L_shr(0x12345678, 64) = 0 overflow 0 carry 1
+shr_r(0x1, -1) = 0x2 overflow 0 carry 1
+shr_r(0xa, -1) = 0x14 overflow 0 carry 1
+shr_r(0xfff, -10) = 0x7fff overflow 1 carry 1
+shr_r(0xfff, -20) = 0x7fff overflow 1 carry 1
+shr_r(0x1, 1) = 0x1 overflow 0 carry 1
+shr_r(0x14, 1) = 0xa overflow 0 carry 1
+shr_r(0xfff, 10) = 0x4 overflow 0 carry 1
+shr_r(0xfff, 64) = 0 overflow 0 carry 1
+mac_r(0x1234, 0x2, 0x2) = 0 overflow 0 carry 1
+mac_r(0x1234, 0xffffffff, 0xffffffff) = 0 overflow 0 carry 1
+mac_r(0x1234, 0xffff8000, 0xffff8000) = 0x7fff overflow 1 carry 1
+mac_r(0xffffffff, 0xffff8000, 0xffff8000) = 0x7fff overflow 1 carry 1
+mac_r(0x123456, 0x244, 0x522) = 0x29 overflow 0 carry 1
+msu_r(0x1234, 0x2, 0x2) = 0 overflow 0 carry 1
+msu_r(0x1234, 0xffffffff, 0xffffffff) = 0 overflow 0 carry 1
+msu_r(0x1234, 0xffff8000, 0xffff8000) = 0xffff8000 overflow 1 carry 1
+msu_r(0x1, 0xffff8000, 0xffff8000) = 0xffff8000 overflow 1 carry 1
+msu_r(0x123456, 0x321, 0x243) = 0x4 overflow 0 carry 1
+L_deposit_h(0x1) = 0x10000 overflow 0 carry 1
+L_deposit_h(0xffffffff) = 0xffff0000 overflow 0 carry 1
+L_deposit_h(0xffff8000) = 0x80000000 overflow 0 carry 1
+L_deposit_h(0x1234) = 0x12340000 overflow 0 carry 1
+L_deposit_l(0x1) = 0x1 overflow 0 carry 1
+L_deposit_l(0xffffffff) = 0xffffffff overflow 0 carry 1
+L_deposit_l(0xffff8000) = 0xffff8000 overflow 0 carry 1
+L_deposit_l(0x1234) = 0x1234 overflow 0 carry 1
+L_shr_r(0x1, -1) = 0x2 overflow 0 carry 1
+L_shr_r(0xa, -1) = 0x14 overflow 0 carry 1
+L_shr_r(0xfff, -10) = 0x3ffc00 overflow 0 carry 1
+L_shr_r(0xfff, -20) = 0x7fffffff overflow 1 carry 1
+L_shr_r(0x12345678, -10) = 0x7fffffff overflow 1 carry 1
+L_shr_r(0x12345678, -40) = 0x7fffffff overflow 1 carry 1
+L_shr_r(0x1, 1) = 0x1 overflow 0 carry 1
+L_shr_r(0x14, 1) = 0xa overflow 0 carry 1
+L_shr_r(0xfff, 10) = 0x4 overflow 0 carry 1
+L_shr_r(0xfff, 64) = 0 overflow 0 carry 1
+L_shr_r(0x12345678, 10) = 0x48d16 overflow 0 carry 1
+L_shr_r(0x12345678, 64) = 0 overflow 0 carry 1
+L_abs(0x1) = 0x1 overflow 0 carry 1
+L_abs(0xffffffff) = 0x1 overflow 0 carry 1
+L_abs(0x80000000) = 0x7fffffff overflow 1 carry 1
+L_sat(0x1) = 0x1 overflow 0 carry 1
+L_sat(0xffffffff) = 0xffffffff overflow 0 carry 1
+L_sat(0xffff8000) = 0xffff8000 overflow 0 carry 1
+L_sat(0x8000) = 0x8000 overflow 0 carry 1
+div_s(0x1, 0x1) = 0x7fff overflow 0 carry 1
+div_s(0x2710, 0x4e20) = 0x4000 overflow 0 carry 1
+div_s(0x2710, 0x4e20) = 0x4000 overflow 0 carry 1
+
+
+DSP FNS (non-NEON/ITU) intrinsics with input Overflow=1 and input Carry=0
+Checking saturate with input Overflow=1 and input Carry=0
+saturate(0x1) = 0x1 overflow 1 carry 0
+saturate(0xffffffff) = 0xffffffff overflow 1 carry 0
+saturate(0x8000) = 0x7fff overflow 1 carry 0
+saturate(0xffff8000) = 0xffff8000 overflow 1 carry 0
+saturate(0xffff7fff) = 0xffff8000 overflow 1 carry 0
+add(0x1, 0x1) = 0x2 overflow 1 carry 0
+add(0xffffffff, 0xffffffff) = 0xfffffffe overflow 1 carry 0
+add(0x4e20, 0x4e20) = 0x7fff overflow 1 carry 0
+add(0xffffb1e0, 0xffffb1e0) = 0xffff8000 overflow 1 carry 0
+sub(0x1, 0x1) = 0 overflow 1 carry 0
+sub(0xffffffff, 0xffffffff) = 0 overflow 1 carry 0
+sub(0x4e20, 0x4e20) = 0 overflow 1 carry 0
+sub(0xffffb1e0, 0xffffb1e0) = 0 overflow 1 carry 0
+sub(0, 0xffff8000) = 0x7fff overflow 1 carry 0
+abs_s(0x1) = 0x1 overflow 1 carry 0
+abs_s(0xffffffff) = 0x1 overflow 1 carry 0
+abs_s(0xffff8000) = 0x7fff overflow 1 carry 0
+shl(0x1, 1) = 0x2 overflow 1 carry 0
+shl(0xa, 1) = 0x14 overflow 1 carry 0
+shl(0xfff, 10) = 0x7fff overflow 1 carry 0
+shl(0xfff, 20) = 0x7fff overflow 1 carry 0
+shl(0x1, -1) = 0 overflow 1 carry 0
+shl(0x14, -1) = 0xa overflow 1 carry 0
+shl(0xfff, -10) = 0x3 overflow 1 carry 0
+shl(0xfff, -64) = 0 overflow 1 carry 0
+shr(0x1, -1) = 0x2 overflow 1 carry 0
+shr(0xa, -1) = 0x14 overflow 1 carry 0
+shr(0xfff, -10) = 0x7fff overflow 1 carry 0
+shr(0xfff, -20) = 0x7fff overflow 1 carry 0
+shr(0x1, 1) = 0 overflow 1 carry 0
+shr(0x14, 1) = 0xa overflow 1 carry 0
+shr(0xfff, 10) = 0x3 overflow 1 carry 0
+shr(0xfff, 64) = 0 overflow 1 carry 0
+mult(0x2, 0x2) = 0 overflow 1 carry 0
+mult(0xffffffff, 0xffffffff) = 0 overflow 1 carry 0
+mult(0xffff8000, 0xffff8000) = 0x7fff overflow 1 carry 0
+L_mult(0x2, 0x2) = 0x8 overflow 1 carry 0
+L_mult(0xffffffff, 0xffffffff) = 0x2 overflow 1 carry 0
+L_mult(0xffff8000, 0xffff8000) = 0x7fffffff overflow 1 carry 0
+negate(0x1) = 0xffffffff overflow 1 carry 0
+negate(0xffffffff) = 0x1 overflow 1 carry 0
+negate(0xffff8000) = 0x7fff overflow 1 carry 0
+extract_h(0x1) = 0 overflow 1 carry 0
+extract_h(0xffffffff) = 0xffffffff overflow 1 carry 0
+extract_h(0xffff8000) = 0xffffffff overflow 1 carry 0
+extract_h(0x12345678) = 0x1234 overflow 1 carry 0
+extract_l(0x1) = 0x1 overflow 1 carry 0
+extract_l(0xffffffff) = 0xffffffff overflow 1 carry 0
+extract_l(0xffff8000) = 0xffff8000 overflow 1 carry 0
+extract_l(0x43218765) = 0xffff8765 overflow 1 carry 0
+round(0x1) = 0 overflow 1 carry 0
+round(0xffffffff) = 0 overflow 1 carry 0
+round(0xffff8000) = 0 overflow 1 carry 0
+round(0x43218765) = 0x4322 overflow 1 carry 0
+round(0x87654321) = 0xffff8765 overflow 1 carry 0
+L_mac(0x1234, 0x2, 0x2) = 0x123c overflow 1 carry 0
+L_mac(0x1234, 0xffffffff, 0xffffffff) = 0x1236 overflow 1 carry 0
+L_mac(0x1234, 0xffff8000, 0xffff8000) = 0x7fffffff overflow 1 carry 0
+L_mac(0xffffffff, 0xffff8000, 0xffff8000) = 0x7ffffffe overflow 1 carry 0
+L_msu(0x1234, 0x2, 0x2) = 0x122c overflow 1 carry 0
+L_msu(0x1234, 0xffffffff, 0xffffffff) = 0x1232 overflow 1 carry 0
+L_msu(0x1234, 0xffff8000, 0xffff8000) = 0x80001235 overflow 1 carry 0
+L_msu(0x1, 0xffff8000, 0xffff8000) = 0x80000002 overflow 1 carry 0
+L_add(0x1, 0x2) = 0x3 overflow 1 carry 0
+L_add(0xffffffff, 0xfffffffe) = 0xfffffffd overflow 1 carry 0
+L_add(0xffffffff, 0x2) = 0x1 overflow 1 carry 0
+L_add(0x7000, 0x7000) = 0xe000 overflow 1 carry 0
+L_add(0x8fff, 0x8fff) = 0x11ffe overflow 1 carry 0
+L_add(0x70000000, 0x70000000) = 0x7fffffff overflow 1 carry 0
+L_add(0x8fffffff, 0x8fffffff) = 0x80000000 overflow 1 carry 0
+L_sub(0x1, 0x2) = 0xffffffff overflow 1 carry 0
+L_sub(0xffffffff, 0xfffffffe) = 0x1 overflow 1 carry 0
+L_sub(0xffffffff, 0x2) = 0xfffffffd overflow 1 carry 0
+L_sub(0x7000, 0xffff9000) = 0xe000 overflow 1 carry 0
+L_sub(0x8fff, 0xffff7001) = 0x11ffe overflow 1 carry 0
+L_sub(0x70000000, 0x90000000) = 0x7fffffff overflow 1 carry 0
+L_sub(0x8fffffff, 0x70000001) = 0x80000000 overflow 1 carry 0
+L_sub(0, 0x80000000) = 0x7fffffff overflow 1 carry 0
+Checking L_add_c with input Overflow=1 and input Carry=0
+L_add_c(0x1, 0x2) = 0x3 overflow 1 carry 0
+L_add_c(0xffffffff, 0xfffffffe) = 0xfffffffd overflow 1 carry 1
+L_add_c(0xffffffff, 0x2) = 0x1 overflow 1 carry 1
+L_add_c(0x7000, 0x7000) = 0xe000 overflow 1 carry 0
+L_add_c(0x8fff, 0x8fff) = 0x11ffe overflow 1 carry 0
+L_add_c(0x70000000, 0x70000000) = 0xe0000000 overflow 1 carry 0
+L_add_c(0x8fffffff, 0x8fffffff) = 0x1ffffffe overflow 1 carry 1
+L_add_c(0x8fffffff, 0xffffffff) = 0x8ffffffe overflow 1 carry 1
+L_sub_c(0x1, 0x2) = 0xfffffffe overflow 1 carry 0
+L_sub_c(0xffffffff, 0xfffffffe) = 0 overflow 1 carry 1
+L_sub_c(0xffffffff, 0x2) = 0xfffffffc overflow 1 carry 1
+L_sub_c(0x7000, 0x7000) = 0xffffffff overflow 1 carry 0
+L_sub_c(0x8fff, 0x8fff) = 0xffffffff overflow 1 carry 0
+L_sub_c(0x70000000, 0x70000000) = 0xffffffff overflow 1 carry 0
+L_sub_c(0x8fffffff, 0x8fffffff) = 0xffffffff overflow 1 carry 0
+L_sub_c(0x1, 0x80000000) = 0x80000000 overflow 1 carry 0
+L_sub_c(0xffffffff, 0x7fffffff) = 0x7fffffff overflow 1 carry 1
+Checking L_macNs with input Overflow=1 and input Carry=0
+L_macNs(0x1234, 0x2, 0x2) = 0x123c overflow 0 carry 0
+L_macNs(0x1234, 0xffffffff, 0xffffffff) = 0x1236 overflow 0 carry 0
+L_macNs(0x1234, 0xffff8000, 0xffff8000) = 0x80001233 overflow 1 carry 0
+L_macNs(0xffffffff, 0xffff8000, 0xffff8000) = 0x7ffffffe overflow 1 carry 1
+Checking L_msuNs with input Overflow=1 and input Carry=0
+L_msuNs(0x1234, 0x2, 0x2) = 0x122b overflow 0 carry 1
+L_msuNs(0x1234, 0xffffffff, 0xffffffff) = 0x1231 overflow 0 carry 1
+L_msuNs(0x1234, 0xffff8000, 0xffff8000) = 0x80001234 overflow 1 carry 0
+L_msuNs(0xffffffff, 0xffff8000, 0xffff8000) = 0x7fffffff overflow 1 carry 1
+negate(0x1) = 0xffffffff overflow 1 carry 0
+negate(0xffffffff) = 0x1 overflow 1 carry 0
+negate(0xffff8000) = 0x7fff overflow 1 carry 0
+mult_r(0x2, 0x2) = 0 overflow 1 carry 0
+mult_r(0xffffffff, 0xffffffff) = 0 overflow 1 carry 0
+mult_r(0xffff8000, 0xffff8000) = 0x7fff overflow 1 carry 0
+norm_s(0x1) = 0xe overflow 1 carry 0
+norm_s(0xffffffff) = 0xf overflow 1 carry 0
+norm_s(0xffff8000) = 0 overflow 1 carry 0
+norm_s(0x2ee0) = 0x1 overflow 1 carry 0
+norm_l(0x1) = 0x1e overflow 1 carry 0
+norm_l(0xffffffff) = 0x1f overflow 1 carry 0
+norm_l(0xffff8000) = 0x10 overflow 1 carry 0
+norm_l(0x2ee0) = 0x11 overflow 1 carry 0
+norm_l(0x123456) = 0xa overflow 1 carry 0
+norm_l(0xabcdef) = 0x7 overflow 1 carry 0
+L_shl(0x1, 1) = 0x2 overflow 1 carry 0
+L_shl(0xa, 1) = 0x14 overflow 1 carry 0
+L_shl(0xfff, 10) = 0x3ffc00 overflow 1 carry 0
+L_shl(0xfff, 20) = 0x7fffffff overflow 1 carry 0
+L_shl(0x12345678, 2) = 0x48d159e0 overflow 1 carry 0
+L_shl(0x12345678, 40) = 0x7fffffff overflow 1 carry 0
+L_shl(0x1, -1) = 0 overflow 1 carry 0
+L_shl(0x14, -1) = 0xa overflow 1 carry 0
+L_shl(0xfff, -10) = 0x3 overflow 1 carry 0
+L_shl(0xfff, -64) = 0 overflow 1 carry 0
+L_shl(0x12345678, -10) = 0x48d15 overflow 1 carry 0
+L_shl(0x12345678, -64) = 0 overflow 1 carry 0
+L_shr(0x1, -1) = 0x2 overflow 1 carry 0
+L_shr(0xa, -1) = 0x14 overflow 1 carry 0
+L_shr(0xfff, -10) = 0x3ffc00 overflow 1 carry 0
+L_shr(0xfff, -20) = 0x7fffffff overflow 1 carry 0
+L_shr(0x12345678, -10) = 0x7fffffff overflow 1 carry 0
+L_shr(0x12345678, -40) = 0x7fffffff overflow 1 carry 0
+L_shr(0x1, 1) = 0 overflow 1 carry 0
+L_shr(0x14, 1) = 0xa overflow 1 carry 0
+L_shr(0xfff, 10) = 0x3 overflow 1 carry 0
+L_shr(0xfff, 64) = 0 overflow 1 carry 0
+L_shr(0x12345678, 10) = 0x48d15 overflow 1 carry 0
+L_shr(0x12345678, 64) = 0 overflow 1 carry 0
+shr_r(0x1, -1) = 0x2 overflow 1 carry 0
+shr_r(0xa, -1) = 0x14 overflow 1 carry 0
+shr_r(0xfff, -10) = 0x7fff overflow 1 carry 0
+shr_r(0xfff, -20) = 0x7fff overflow 1 carry 0
+shr_r(0x1, 1) = 0x1 overflow 1 carry 0
+shr_r(0x14, 1) = 0xa overflow 1 carry 0
+shr_r(0xfff, 10) = 0x4 overflow 1 carry 0
+shr_r(0xfff, 64) = 0 overflow 1 carry 0
+mac_r(0x1234, 0x2, 0x2) = 0 overflow 1 carry 0
+mac_r(0x1234, 0xffffffff, 0xffffffff) = 0 overflow 1 carry 0
+mac_r(0x1234, 0xffff8000, 0xffff8000) = 0x7fff overflow 1 carry 0
+mac_r(0xffffffff, 0xffff8000, 0xffff8000) = 0x7fff overflow 1 carry 0
+mac_r(0x123456, 0x244, 0x522) = 0x29 overflow 1 carry 0
+msu_r(0x1234, 0x2, 0x2) = 0 overflow 1 carry 0
+msu_r(0x1234, 0xffffffff, 0xffffffff) = 0 overflow 1 carry 0
+msu_r(0x1234, 0xffff8000, 0xffff8000) = 0xffff8000 overflow 1 carry 0
+msu_r(0x1, 0xffff8000, 0xffff8000) = 0xffff8000 overflow 1 carry 0
+msu_r(0x123456, 0x321, 0x243) = 0x4 overflow 1 carry 0
+L_deposit_h(0x1) = 0x10000 overflow 1 carry 0
+L_deposit_h(0xffffffff) = 0xffff0000 overflow 1 carry 0
+L_deposit_h(0xffff8000) = 0x80000000 overflow 1 carry 0
+L_deposit_h(0x1234) = 0x12340000 overflow 1 carry 0
+L_deposit_l(0x1) = 0x1 overflow 1 carry 0
+L_deposit_l(0xffffffff) = 0xffffffff overflow 1 carry 0
+L_deposit_l(0xffff8000) = 0xffff8000 overflow 1 carry 0
+L_deposit_l(0x1234) = 0x1234 overflow 1 carry 0
+L_shr_r(0x1, -1) = 0x2 overflow 1 carry 0
+L_shr_r(0xa, -1) = 0x14 overflow 1 carry 0
+L_shr_r(0xfff, -10) = 0x3ffc00 overflow 1 carry 0
+L_shr_r(0xfff, -20) = 0x7fffffff overflow 1 carry 0
+L_shr_r(0x12345678, -10) = 0x7fffffff overflow 1 carry 0
+L_shr_r(0x12345678, -40) = 0x7fffffff overflow 1 carry 0
+L_shr_r(0x1, 1) = 0x1 overflow 1 carry 0
+L_shr_r(0x14, 1) = 0xa overflow 1 carry 0
+L_shr_r(0xfff, 10) = 0x4 overflow 1 carry 0
+L_shr_r(0xfff, 64) = 0 overflow 1 carry 0
+L_shr_r(0x12345678, 10) = 0x48d16 overflow 1 carry 0
+L_shr_r(0x12345678, 64) = 0 overflow 1 carry 0
+L_abs(0x1) = 0x1 overflow 1 carry 0
+L_abs(0xffffffff) = 0x1 overflow 1 carry 0
+L_abs(0x80000000) = 0x7fffffff overflow 1 carry 0
+L_sat(0x1) = 0x7fffffff overflow 0 carry 0
+L_sat(0xffffffff) = 0x7fffffff overflow 0 carry 0
+L_sat(0xffff8000) = 0x7fffffff overflow 0 carry 0
+L_sat(0x8000) = 0x7fffffff overflow 0 carry 0
+div_s(0x1, 0x1) = 0x7fff overflow 1 carry 0
+div_s(0x2710, 0x4e20) = 0x4000 overflow 1 carry 0
+div_s(0x2710, 0x4e20) = 0x4000 overflow 1 carry 0
+
+
+DSP FNS (non-NEON/ITU) intrinsics with input Overflow=1 and input Carry=1
+Checking saturate with input Overflow=1 and input Carry=1
+saturate(0x1) = 0x1 overflow 1 carry 1
+saturate(0xffffffff) = 0xffffffff overflow 1 carry 1
+saturate(0x8000) = 0x7fff overflow 1 carry 1
+saturate(0xffff8000) = 0xffff8000 overflow 1 carry 1
+saturate(0xffff7fff) = 0xffff8000 overflow 1 carry 1
+add(0x1, 0x1) = 0x2 overflow 1 carry 1
+add(0xffffffff, 0xffffffff) = 0xfffffffe overflow 1 carry 1
+add(0x4e20, 0x4e20) = 0x7fff overflow 1 carry 1
+add(0xffffb1e0, 0xffffb1e0) = 0xffff8000 overflow 1 carry 1
+sub(0x1, 0x1) = 0 overflow 1 carry 1
+sub(0xffffffff, 0xffffffff) = 0 overflow 1 carry 1
+sub(0x4e20, 0x4e20) = 0 overflow 1 carry 1
+sub(0xffffb1e0, 0xffffb1e0) = 0 overflow 1 carry 1
+sub(0, 0xffff8000) = 0x7fff overflow 1 carry 1
+abs_s(0x1) = 0x1 overflow 1 carry 1
+abs_s(0xffffffff) = 0x1 overflow 1 carry 1
+abs_s(0xffff8000) = 0x7fff overflow 1 carry 1
+shl(0x1, 1) = 0x2 overflow 1 carry 1
+shl(0xa, 1) = 0x14 overflow 1 carry 1
+shl(0xfff, 10) = 0x7fff overflow 1 carry 1
+shl(0xfff, 20) = 0x7fff overflow 1 carry 1
+shl(0x1, -1) = 0 overflow 1 carry 1
+shl(0x14, -1) = 0xa overflow 1 carry 1
+shl(0xfff, -10) = 0x3 overflow 1 carry 1
+shl(0xfff, -64) = 0 overflow 1 carry 1
+shr(0x1, -1) = 0x2 overflow 1 carry 1
+shr(0xa, -1) = 0x14 overflow 1 carry 1
+shr(0xfff, -10) = 0x7fff overflow 1 carry 1
+shr(0xfff, -20) = 0x7fff overflow 1 carry 1
+shr(0x1, 1) = 0 overflow 1 carry 1
+shr(0x14, 1) = 0xa overflow 1 carry 1
+shr(0xfff, 10) = 0x3 overflow 1 carry 1
+shr(0xfff, 64) = 0 overflow 1 carry 1
+mult(0x2, 0x2) = 0 overflow 1 carry 1
+mult(0xffffffff, 0xffffffff) = 0 overflow 1 carry 1
+mult(0xffff8000, 0xffff8000) = 0x7fff overflow 1 carry 1
+L_mult(0x2, 0x2) = 0x8 overflow 1 carry 1
+L_mult(0xffffffff, 0xffffffff) = 0x2 overflow 1 carry 1
+L_mult(0xffff8000, 0xffff8000) = 0x7fffffff overflow 1 carry 1
+negate(0x1) = 0xffffffff overflow 1 carry 1
+negate(0xffffffff) = 0x1 overflow 1 carry 1
+negate(0xffff8000) = 0x7fff overflow 1 carry 1
+extract_h(0x1) = 0 overflow 1 carry 1
+extract_h(0xffffffff) = 0xffffffff overflow 1 carry 1
+extract_h(0xffff8000) = 0xffffffff overflow 1 carry 1
+extract_h(0x12345678) = 0x1234 overflow 1 carry 1
+extract_l(0x1) = 0x1 overflow 1 carry 1
+extract_l(0xffffffff) = 0xffffffff overflow 1 carry 1
+extract_l(0xffff8000) = 0xffff8000 overflow 1 carry 1
+extract_l(0x43218765) = 0xffff8765 overflow 1 carry 1
+round(0x1) = 0 overflow 1 carry 1
+round(0xffffffff) = 0 overflow 1 carry 1
+round(0xffff8000) = 0 overflow 1 carry 1
+round(0x43218765) = 0x4322 overflow 1 carry 1
+round(0x87654321) = 0xffff8765 overflow 1 carry 1
+L_mac(0x1234, 0x2, 0x2) = 0x123c overflow 1 carry 1
+L_mac(0x1234, 0xffffffff, 0xffffffff) = 0x1236 overflow 1 carry 1
+L_mac(0x1234, 0xffff8000, 0xffff8000) = 0x7fffffff overflow 1 carry 1
+L_mac(0xffffffff, 0xffff8000, 0xffff8000) = 0x7ffffffe overflow 1 carry 1
+L_msu(0x1234, 0x2, 0x2) = 0x122c overflow 1 carry 1
+L_msu(0x1234, 0xffffffff, 0xffffffff) = 0x1232 overflow 1 carry 1
+L_msu(0x1234, 0xffff8000, 0xffff8000) = 0x80001235 overflow 1 carry 1
+L_msu(0x1, 0xffff8000, 0xffff8000) = 0x80000002 overflow 1 carry 1
+L_add(0x1, 0x2) = 0x3 overflow 1 carry 1
+L_add(0xffffffff, 0xfffffffe) = 0xfffffffd overflow 1 carry 1
+L_add(0xffffffff, 0x2) = 0x1 overflow 1 carry 1
+L_add(0x7000, 0x7000) = 0xe000 overflow 1 carry 1
+L_add(0x8fff, 0x8fff) = 0x11ffe overflow 1 carry 1
+L_add(0x70000000, 0x70000000) = 0x7fffffff overflow 1 carry 1
+L_add(0x8fffffff, 0x8fffffff) = 0x80000000 overflow 1 carry 1
+L_sub(0x1, 0x2) = 0xffffffff overflow 1 carry 1
+L_sub(0xffffffff, 0xfffffffe) = 0x1 overflow 1 carry 1
+L_sub(0xffffffff, 0x2) = 0xfffffffd overflow 1 carry 1
+L_sub(0x7000, 0xffff9000) = 0xe000 overflow 1 carry 1
+L_sub(0x8fff, 0xffff7001) = 0x11ffe overflow 1 carry 1
+L_sub(0x70000000, 0x90000000) = 0x7fffffff overflow 1 carry 1
+L_sub(0x8fffffff, 0x70000001) = 0x80000000 overflow 1 carry 1
+L_sub(0, 0x80000000) = 0x7fffffff overflow 1 carry 1
+Checking L_add_c with input Overflow=1 and input Carry=1
+L_add_c(0x1, 0x2) = 0x4 overflow 1 carry 0
+L_add_c(0xffffffff, 0xfffffffe) = 0xfffffffe overflow 1 carry 1
+L_add_c(0xffffffff, 0x2) = 0x2 overflow 1 carry 1
+L_add_c(0x7000, 0x7000) = 0xe001 overflow 1 carry 0
+L_add_c(0x8fff, 0x8fff) = 0x11fff overflow 1 carry 0
+L_add_c(0x70000000, 0x70000000) = 0xe0000001 overflow 1 carry 0
+L_add_c(0x8fffffff, 0x8fffffff) = 0x1fffffff overflow 1 carry 1
+L_add_c(0x8fffffff, 0xffffffff) = 0x8fffffff overflow 1 carry 1
+L_sub_c(0x1, 0x2) = 0xffffffff overflow 1 carry 0
+L_sub_c(0xffffffff, 0xfffffffe) = 0x1 overflow 1 carry 1
+L_sub_c(0xffffffff, 0x2) = 0xfffffffd overflow 1 carry 1
+L_sub_c(0x7000, 0x7000) = 0 overflow 1 carry 1
+L_sub_c(0x8fff, 0x8fff) = 0 overflow 1 carry 1
+L_sub_c(0x70000000, 0x70000000) = 0 overflow 1 carry 1
+L_sub_c(0x8fffffff, 0x8fffffff) = 0 overflow 1 carry 1
+L_sub_c(0x1, 0x80000000) = 0x80000001 overflow 1 carry 0
+L_sub_c(0xffffffff, 0x7fffffff) = 0x80000000 overflow 1 carry 1
+Checking L_macNs with input Overflow=1 and input Carry=1
+L_macNs(0x1234, 0x2, 0x2) = 0x123d overflow 0 carry 0
+L_macNs(0x1234, 0xffffffff, 0xffffffff) = 0x1237 overflow 0 carry 0
+L_macNs(0x1234, 0xffff8000, 0xffff8000) = 0x80001234 overflow 1 carry 0
+L_macNs(0xffffffff, 0xffff8000, 0xffff8000) = 0x7fffffff overflow 1 carry 1
+Checking L_msuNs with input Overflow=1 and input Carry=1
+L_msuNs(0x1234, 0x2, 0x2) = 0x122c overflow 0 carry 1
+L_msuNs(0x1234, 0xffffffff, 0xffffffff) = 0x1232 overflow 0 carry 1
+L_msuNs(0x1234, 0xffff8000, 0xffff8000) = 0x80001235 overflow 1 carry 0
+L_msuNs(0xffffffff, 0xffff8000, 0xffff8000) = 0x80000000 overflow 1 carry 1
+negate(0x1) = 0xffffffff overflow 1 carry 1
+negate(0xffffffff) = 0x1 overflow 1 carry 1
+negate(0xffff8000) = 0x7fff overflow 1 carry 1
+mult_r(0x2, 0x2) = 0 overflow 1 carry 1
+mult_r(0xffffffff, 0xffffffff) = 0 overflow 1 carry 1
+mult_r(0xffff8000, 0xffff8000) = 0x7fff overflow 1 carry 1
+norm_s(0x1) = 0xe overflow 1 carry 1
+norm_s(0xffffffff) = 0xf overflow 1 carry 1
+norm_s(0xffff8000) = 0 overflow 1 carry 1
+norm_s(0x2ee0) = 0x1 overflow 1 carry 1
+norm_l(0x1) = 0x1e overflow 1 carry 1
+norm_l(0xffffffff) = 0x1f overflow 1 carry 1
+norm_l(0xffff8000) = 0x10 overflow 1 carry 1
+norm_l(0x2ee0) = 0x11 overflow 1 carry 1
+norm_l(0x123456) = 0xa overflow 1 carry 1
+norm_l(0xabcdef) = 0x7 overflow 1 carry 1
+L_shl(0x1, 1) = 0x2 overflow 1 carry 1
+L_shl(0xa, 1) = 0x14 overflow 1 carry 1
+L_shl(0xfff, 10) = 0x3ffc00 overflow 1 carry 1
+L_shl(0xfff, 20) = 0x7fffffff overflow 1 carry 1
+L_shl(0x12345678, 2) = 0x48d159e0 overflow 1 carry 1
+L_shl(0x12345678, 40) = 0x7fffffff overflow 1 carry 1
+L_shl(0x1, -1) = 0 overflow 1 carry 1
+L_shl(0x14, -1) = 0xa overflow 1 carry 1
+L_shl(0xfff, -10) = 0x3 overflow 1 carry 1
+L_shl(0xfff, -64) = 0 overflow 1 carry 1
+L_shl(0x12345678, -10) = 0x48d15 overflow 1 carry 1
+L_shl(0x12345678, -64) = 0 overflow 1 carry 1
+L_shr(0x1, -1) = 0x2 overflow 1 carry 1
+L_shr(0xa, -1) = 0x14 overflow 1 carry 1
+L_shr(0xfff, -10) = 0x3ffc00 overflow 1 carry 1
+L_shr(0xfff, -20) = 0x7fffffff overflow 1 carry 1
+L_shr(0x12345678, -10) = 0x7fffffff overflow 1 carry 1
+L_shr(0x12345678, -40) = 0x7fffffff overflow 1 carry 1
+L_shr(0x1, 1) = 0 overflow 1 carry 1
+L_shr(0x14, 1) = 0xa overflow 1 carry 1
+L_shr(0xfff, 10) = 0x3 overflow 1 carry 1
+L_shr(0xfff, 64) = 0 overflow 1 carry 1
+L_shr(0x12345678, 10) = 0x48d15 overflow 1 carry 1
+L_shr(0x12345678, 64) = 0 overflow 1 carry 1
+shr_r(0x1, -1) = 0x2 overflow 1 carry 1
+shr_r(0xa, -1) = 0x14 overflow 1 carry 1
+shr_r(0xfff, -10) = 0x7fff overflow 1 carry 1
+shr_r(0xfff, -20) = 0x7fff overflow 1 carry 1
+shr_r(0x1, 1) = 0x1 overflow 1 carry 1
+shr_r(0x14, 1) = 0xa overflow 1 carry 1
+shr_r(0xfff, 10) = 0x4 overflow 1 carry 1
+shr_r(0xfff, 64) = 0 overflow 1 carry 1
+mac_r(0x1234, 0x2, 0x2) = 0 overflow 1 carry 1
+mac_r(0x1234, 0xffffffff, 0xffffffff) = 0 overflow 1 carry 1
+mac_r(0x1234, 0xffff8000, 0xffff8000) = 0x7fff overflow 1 carry 1
+mac_r(0xffffffff, 0xffff8000, 0xffff8000) = 0x7fff overflow 1 carry 1
+mac_r(0x123456, 0x244, 0x522) = 0x29 overflow 1 carry 1
+msu_r(0x1234, 0x2, 0x2) = 0 overflow 1 carry 1
+msu_r(0x1234, 0xffffffff, 0xffffffff) = 0 overflow 1 carry 1
+msu_r(0x1234, 0xffff8000, 0xffff8000) = 0xffff8000 overflow 1 carry 1
+msu_r(0x1, 0xffff8000, 0xffff8000) = 0xffff8000 overflow 1 carry 1
+msu_r(0x123456, 0x321, 0x243) = 0x4 overflow 1 carry 1
+L_deposit_h(0x1) = 0x10000 overflow 1 carry 1
+L_deposit_h(0xffffffff) = 0xffff0000 overflow 1 carry 1
+L_deposit_h(0xffff8000) = 0x80000000 overflow 1 carry 1
+L_deposit_h(0x1234) = 0x12340000 overflow 1 carry 1
+L_deposit_l(0x1) = 0x1 overflow 1 carry 1
+L_deposit_l(0xffffffff) = 0xffffffff overflow 1 carry 1
+L_deposit_l(0xffff8000) = 0xffff8000 overflow 1 carry 1
+L_deposit_l(0x1234) = 0x1234 overflow 1 carry 1
+L_shr_r(0x1, -1) = 0x2 overflow 1 carry 1
+L_shr_r(0xa, -1) = 0x14 overflow 1 carry 1
+L_shr_r(0xfff, -10) = 0x3ffc00 overflow 1 carry 1
+L_shr_r(0xfff, -20) = 0x7fffffff overflow 1 carry 1
+L_shr_r(0x12345678, -10) = 0x7fffffff overflow 1 carry 1
+L_shr_r(0x12345678, -40) = 0x7fffffff overflow 1 carry 1
+L_shr_r(0x1, 1) = 0x1 overflow 1 carry 1
+L_shr_r(0x14, 1) = 0xa overflow 1 carry 1
+L_shr_r(0xfff, 10) = 0x4 overflow 1 carry 1
+L_shr_r(0xfff, 64) = 0 overflow 1 carry 1
+L_shr_r(0x12345678, 10) = 0x48d16 overflow 1 carry 1
+L_shr_r(0x12345678, 64) = 0 overflow 1 carry 1
+L_abs(0x1) = 0x1 overflow 1 carry 1
+L_abs(0xffffffff) = 0x1 overflow 1 carry 1
+L_abs(0x80000000) = 0x7fffffff overflow 1 carry 1
+L_sat(0x1) = 0x80000000 overflow 0 carry 0
+L_sat(0xffffffff) = 0x80000000 overflow 0 carry 0
+L_sat(0xffff8000) = 0x80000000 overflow 0 carry 0
+L_sat(0x8000) = 0x80000000 overflow 0 carry 0
+div_s(0x1, 0x1) = 0x7fff overflow 1 carry 1
+div_s(0x2710, 0x4e20) = 0x4000 overflow 1 carry 1
+div_s(0x2710, 0x4e20) = 0x4000 overflow 1 carry 1
diff --git a/ref-rvct-neon-nofp16.txt b/ref-rvct-neon-nofp16.txt
new file mode 100644
index 0000000..f3656db
--- /dev/null
+++ b/ref-rvct-neon-nofp16.txt
@@ -0,0 +1,7356 @@
+
+VLD1/VLD1Q output:
+VLD1/VLD1Q:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD1/VLD1Q:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD1/VLD1Q:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD1/VLD1Q:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD1/VLD1Q:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VLD1/VLD1Q:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD1/VLD1Q:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD1/VLD1Q:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD1/VLD1Q:8:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VLD1/VLD1Q:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD1/VLD1Q:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD1/VLD1Q:11:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD1/VLD1Q:12:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD1/VLD1Q:13:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD1/VLD1Q:14:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VLD1/VLD1Q:15:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD1/VLD1Q:16:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VLD1/VLD1Q:17:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD1/VLD1Q:18:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VLD1/VLD1Q:19:result_poly8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD1/VLD1Q:20:result_poly16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VLD1/VLD1Q:21:result_float32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+
+VADD/VADDQ output:
+VADD/VADDQ:0:result_int8x8 [] = { fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9,  }
+VADD/VADDQ:1:result_int16x4 [] = { ffffffec, ffffffed, ffffffee, ffffffef,  }
+VADD/VADDQ:2:result_int32x2 [] = { fffffff3, fffffff4,  }
+VADD/VADDQ:3:result_int64x1 [] = { 54,  }
+VADD/VADDQ:4:result_uint8x8 [] = { 4, 5, 6, 7, 8, 9, a, b,  }
+VADD/VADDQ:5:result_uint16x4 [] = { e, f, 10, 11,  }
+VADD/VADDQ:6:result_uint32x2 [] = { 18, 19,  }
+VADD/VADDQ:7:result_uint64x1 [] = { fffffffffffffff2,  }
+VADD/VADDQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADD/VADDQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VADD/VADDQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VADD/VADDQ:11:result_int8x16 [] = { ffffffe6, ffffffe7, ffffffe8, ffffffe9, ffffffea, ffffffeb, ffffffec, ffffffed, ffffffee, ffffffef, fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5,  }
+VADD/VADDQ:12:result_int16x8 [] = { ffffffdc, ffffffdd, ffffffde, ffffffdf, ffffffe0, ffffffe1, ffffffe2, ffffffe3,  }
+VADD/VADDQ:13:result_int32x4 [] = { ffffffd2, ffffffd3, ffffffd4, ffffffd5,  }
+VADD/VADDQ:14:result_int64x2 [] = { 8, 9,  }
+VADD/VADDQ:15:result_uint8x16 [] = { fc, fd, fe, ff, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b,  }
+VADD/VADDQ:16:result_uint16x8 [] = { fff3, fff4, fff5, fff6, fff7, fff8, fff9, fffa,  }
+VADD/VADDQ:17:result_uint32x4 [] = { 27, 28, 29, 2a,  }
+VADD/VADDQ:18:result_uint64x2 [] = { fffffffffffffff3, fffffffffffffff4,  }
+VADD/VADDQ:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADD/VADDQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VADD/VADDQ:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+float32:
+VADD/VADDQ:22:result_float32x2 [] = { 40d9999a, 40d9999a,  }
+VADD/VADDQ:23:result_float32x4 [] = { 41100000, 41100000, 41100000, 41100000,  }
+
+VLD1_LANE/VLD1_LANEQ output:
+VLD1_LANE/VLD1_LANEQ:0:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, fffffff0, ffffffaa,  }
+VLD1_LANE/VLD1_LANEQ:1:result_int16x4 [] = { ffffaaaa, ffffaaaa, ffffaaaa, fffffff0,  }
+VLD1_LANE/VLD1_LANEQ:2:result_int32x2 [] = { aaaaaaaa, fffffff0,  }
+VLD1_LANE/VLD1_LANEQ:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD1_LANE/VLD1_LANEQ:4:result_uint8x8 [] = { aa, aa, aa, aa, aa, aa, aa, f0,  }
+VLD1_LANE/VLD1_LANEQ:5:result_uint16x4 [] = { aaaa, aaaa, aaaa, fff0,  }
+VLD1_LANE/VLD1_LANEQ:6:result_uint32x2 [] = { aaaaaaaa, fffffff0,  }
+VLD1_LANE/VLD1_LANEQ:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD1_LANE/VLD1_LANEQ:8:result_poly8x8 [] = { aa, aa, aa, aa, aa, aa, aa, f0,  }
+VLD1_LANE/VLD1_LANEQ:9:result_poly16x4 [] = { aaaa, aaaa, aaaa, fff0,  }
+VLD1_LANE/VLD1_LANEQ:10:result_float32x2 [] = { aaaaaaaa, c1800000,  }
+VLD1_LANE/VLD1_LANEQ:11:result_int8x16 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, fffffff0,  }
+VLD1_LANE/VLD1_LANEQ:12:result_int16x8 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, fffffff0, ffffaaaa, ffffaaaa,  }
+VLD1_LANE/VLD1_LANEQ:13:result_int32x4 [] = { aaaaaaaa, aaaaaaaa, fffffff0, aaaaaaaa,  }
+VLD1_LANE/VLD1_LANEQ:14:result_int64x2 [] = { aaaaaaaaaaaaaaaa, fffffffffffffff0,  }
+VLD1_LANE/VLD1_LANEQ:15:result_uint8x16 [] = { aa, aa, aa, aa, aa, aa, aa, aa, aa, aa, aa, aa, f0, aa, aa, aa,  }
+VLD1_LANE/VLD1_LANEQ:16:result_uint16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, fff0, aaaa,  }
+VLD1_LANE/VLD1_LANEQ:17:result_uint32x4 [] = { aaaaaaaa, aaaaaaaa, fffffff0, aaaaaaaa,  }
+VLD1_LANE/VLD1_LANEQ:18:result_uint64x2 [] = { fffffffffffffff0, aaaaaaaaaaaaaaaa,  }
+VLD1_LANE/VLD1_LANEQ:19:result_poly8x16 [] = { aa, aa, aa, aa, aa, aa, aa, aa, aa, aa, aa, aa, f0, aa, aa, aa,  }
+VLD1_LANE/VLD1_LANEQ:20:result_poly16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, fff0, aaaa,  }
+VLD1_LANE/VLD1_LANEQ:21:result_float32x4 [] = { aaaaaaaa, aaaaaaaa, c1800000, aaaaaaaa,  }
+
+VLD1_DUP/VLD1_DUPQ output:
+VLD1_DUP/VLD1_DUPQ:0:result_int8x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VLD1_DUP/VLD1_DUPQ:1:result_int16x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VLD1_DUP/VLD1_DUPQ:2:result_int32x2 [] = { fffffff0, fffffff0,  }
+VLD1_DUP/VLD1_DUPQ:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD1_DUP/VLD1_DUPQ:4:result_uint8x8 [] = { f0, f0, f0, f0, f0, f0, f0, f0,  }
+VLD1_DUP/VLD1_DUPQ:5:result_uint16x4 [] = { fff0, fff0, fff0, fff0,  }
+VLD1_DUP/VLD1_DUPQ:6:result_uint32x2 [] = { fffffff0, fffffff0,  }
+VLD1_DUP/VLD1_DUPQ:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD1_DUP/VLD1_DUPQ:8:result_poly8x8 [] = { f0, f0, f0, f0, f0, f0, f0, f0,  }
+VLD1_DUP/VLD1_DUPQ:9:result_poly16x4 [] = { fff0, fff0, fff0, fff0,  }
+VLD1_DUP/VLD1_DUPQ:10:result_float32x2 [] = { c1800000, c1800000,  }
+VLD1_DUP/VLD1_DUPQ:11:result_int8x16 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VLD1_DUP/VLD1_DUPQ:12:result_int16x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VLD1_DUP/VLD1_DUPQ:13:result_int32x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VLD1_DUP/VLD1_DUPQ:14:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VLD1_DUP/VLD1_DUPQ:15:result_uint8x16 [] = { f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0,  }
+VLD1_DUP/VLD1_DUPQ:16:result_uint16x8 [] = { fff0, fff0, fff0, fff0, fff0, fff0, fff0, fff0,  }
+VLD1_DUP/VLD1_DUPQ:17:result_uint32x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VLD1_DUP/VLD1_DUPQ:18:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VLD1_DUP/VLD1_DUPQ:19:result_poly8x16 [] = { f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0,  }
+VLD1_DUP/VLD1_DUPQ:20:result_poly16x8 [] = { fff0, fff0, fff0, fff0, fff0, fff0, fff0, fff0,  }
+VLD1_DUP/VLD1_DUPQ:21:result_float32x4 [] = { c1800000, c1800000, c1800000, c1800000,  }
+
+VLD1_DUP/VLD1_DUPQ output:
+VLD1_DUP/VLD1_DUPQ:0:result_int8x8 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VLD1_DUP/VLD1_DUPQ:1:result_int16x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VLD1_DUP/VLD1_DUPQ:2:result_int32x2 [] = { fffffff1, fffffff1,  }
+VLD1_DUP/VLD1_DUPQ:3:result_int64x1 [] = { fffffffffffffff1,  }
+VLD1_DUP/VLD1_DUPQ:4:result_uint8x8 [] = { f1, f1, f1, f1, f1, f1, f1, f1,  }
+VLD1_DUP/VLD1_DUPQ:5:result_uint16x4 [] = { fff1, fff1, fff1, fff1,  }
+VLD1_DUP/VLD1_DUPQ:6:result_uint32x2 [] = { fffffff1, fffffff1,  }
+VLD1_DUP/VLD1_DUPQ:7:result_uint64x1 [] = { fffffffffffffff1,  }
+VLD1_DUP/VLD1_DUPQ:8:result_poly8x8 [] = { f1, f1, f1, f1, f1, f1, f1, f1,  }
+VLD1_DUP/VLD1_DUPQ:9:result_poly16x4 [] = { fff1, fff1, fff1, fff1,  }
+VLD1_DUP/VLD1_DUPQ:10:result_float32x2 [] = { c1700000, c1700000,  }
+VLD1_DUP/VLD1_DUPQ:11:result_int8x16 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VLD1_DUP/VLD1_DUPQ:12:result_int16x8 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VLD1_DUP/VLD1_DUPQ:13:result_int32x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VLD1_DUP/VLD1_DUPQ:14:result_int64x2 [] = { fffffffffffffff1, fffffffffffffff1,  }
+VLD1_DUP/VLD1_DUPQ:15:result_uint8x16 [] = { f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1,  }
+VLD1_DUP/VLD1_DUPQ:16:result_uint16x8 [] = { fff1, fff1, fff1, fff1, fff1, fff1, fff1, fff1,  }
+VLD1_DUP/VLD1_DUPQ:17:result_uint32x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VLD1_DUP/VLD1_DUPQ:18:result_uint64x2 [] = { fffffffffffffff1, fffffffffffffff1,  }
+VLD1_DUP/VLD1_DUPQ:19:result_poly8x16 [] = { f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1,  }
+VLD1_DUP/VLD1_DUPQ:20:result_poly16x8 [] = { fff1, fff1, fff1, fff1, fff1, fff1, fff1, fff1,  }
+VLD1_DUP/VLD1_DUPQ:21:result_float32x4 [] = { c1700000, c1700000, c1700000, c1700000,  }
+
+VLD1_DUP/VLD1_DUPQ output:
+VLD1_DUP/VLD1_DUPQ:0:result_int8x8 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VLD1_DUP/VLD1_DUPQ:1:result_int16x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VLD1_DUP/VLD1_DUPQ:2:result_int32x2 [] = { fffffff2, fffffff2,  }
+VLD1_DUP/VLD1_DUPQ:3:result_int64x1 [] = { fffffffffffffff2,  }
+VLD1_DUP/VLD1_DUPQ:4:result_uint8x8 [] = { f2, f2, f2, f2, f2, f2, f2, f2,  }
+VLD1_DUP/VLD1_DUPQ:5:result_uint16x4 [] = { fff2, fff2, fff2, fff2,  }
+VLD1_DUP/VLD1_DUPQ:6:result_uint32x2 [] = { fffffff2, fffffff2,  }
+VLD1_DUP/VLD1_DUPQ:7:result_uint64x1 [] = { fffffffffffffff2,  }
+VLD1_DUP/VLD1_DUPQ:8:result_poly8x8 [] = { f2, f2, f2, f2, f2, f2, f2, f2,  }
+VLD1_DUP/VLD1_DUPQ:9:result_poly16x4 [] = { fff2, fff2, fff2, fff2,  }
+VLD1_DUP/VLD1_DUPQ:10:result_float32x2 [] = { c1600000, c1600000,  }
+VLD1_DUP/VLD1_DUPQ:11:result_int8x16 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VLD1_DUP/VLD1_DUPQ:12:result_int16x8 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VLD1_DUP/VLD1_DUPQ:13:result_int32x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VLD1_DUP/VLD1_DUPQ:14:result_int64x2 [] = { fffffffffffffff2, fffffffffffffff2,  }
+VLD1_DUP/VLD1_DUPQ:15:result_uint8x16 [] = { f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2,  }
+VLD1_DUP/VLD1_DUPQ:16:result_uint16x8 [] = { fff2, fff2, fff2, fff2, fff2, fff2, fff2, fff2,  }
+VLD1_DUP/VLD1_DUPQ:17:result_uint32x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VLD1_DUP/VLD1_DUPQ:18:result_uint64x2 [] = { fffffffffffffff2, fffffffffffffff2,  }
+VLD1_DUP/VLD1_DUPQ:19:result_poly8x16 [] = { f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2,  }
+VLD1_DUP/VLD1_DUPQ:20:result_poly16x8 [] = { fff2, fff2, fff2, fff2, fff2, fff2, fff2, fff2,  }
+VLD1_DUP/VLD1_DUPQ:21:result_float32x4 [] = { c1600000, c1600000, c1600000, c1600000,  }
+
+VDUP/VDUPQ output:
+VDUP/VDUPQ:0:result_int8x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VDUP/VDUPQ:1:result_int16x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VDUP/VDUPQ:2:result_int32x2 [] = { fffffff0, fffffff0,  }
+VDUP/VDUPQ:3:result_int64x1 [] = { fffffffffffffff0,  }
+VDUP/VDUPQ:4:result_uint8x8 [] = { f0, f0, f0, f0, f0, f0, f0, f0,  }
+VDUP/VDUPQ:5:result_uint16x4 [] = { fff0, fff0, fff0, fff0,  }
+VDUP/VDUPQ:6:result_uint32x2 [] = { fffffff0, fffffff0,  }
+VDUP/VDUPQ:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VDUP/VDUPQ:8:result_poly8x8 [] = { f0, f0, f0, f0, f0, f0, f0, f0,  }
+VDUP/VDUPQ:9:result_poly16x4 [] = { fff0, fff0, fff0, fff0,  }
+VDUP/VDUPQ:10:result_float32x2 [] = { c1800000, c1800000,  }
+VDUP/VDUPQ:11:result_int8x16 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VDUP/VDUPQ:12:result_int16x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VDUP/VDUPQ:13:result_int32x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VDUP/VDUPQ:14:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VDUP/VDUPQ:15:result_uint8x16 [] = { f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0,  }
+VDUP/VDUPQ:16:result_uint16x8 [] = { fff0, fff0, fff0, fff0, fff0, fff0, fff0, fff0,  }
+VDUP/VDUPQ:17:result_uint32x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VDUP/VDUPQ:18:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VDUP/VDUPQ:19:result_poly8x16 [] = { f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0,  }
+VDUP/VDUPQ:20:result_poly16x8 [] = { fff0, fff0, fff0, fff0, fff0, fff0, fff0, fff0,  }
+VDUP/VDUPQ:21:result_float32x4 [] = { c1800000, c1800000, c1800000, c1800000,  }
+
+VDUP/VDUPQ output:
+VDUP/VDUPQ:0:result_int8x8 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VDUP/VDUPQ:1:result_int16x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VDUP/VDUPQ:2:result_int32x2 [] = { fffffff1, fffffff1,  }
+VDUP/VDUPQ:3:result_int64x1 [] = { fffffffffffffff1,  }
+VDUP/VDUPQ:4:result_uint8x8 [] = { f1, f1, f1, f1, f1, f1, f1, f1,  }
+VDUP/VDUPQ:5:result_uint16x4 [] = { fff1, fff1, fff1, fff1,  }
+VDUP/VDUPQ:6:result_uint32x2 [] = { fffffff1, fffffff1,  }
+VDUP/VDUPQ:7:result_uint64x1 [] = { fffffffffffffff1,  }
+VDUP/VDUPQ:8:result_poly8x8 [] = { f1, f1, f1, f1, f1, f1, f1, f1,  }
+VDUP/VDUPQ:9:result_poly16x4 [] = { fff1, fff1, fff1, fff1,  }
+VDUP/VDUPQ:10:result_float32x2 [] = { c1700000, c1700000,  }
+VDUP/VDUPQ:11:result_int8x16 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VDUP/VDUPQ:12:result_int16x8 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VDUP/VDUPQ:13:result_int32x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VDUP/VDUPQ:14:result_int64x2 [] = { fffffffffffffff1, fffffffffffffff1,  }
+VDUP/VDUPQ:15:result_uint8x16 [] = { f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1,  }
+VDUP/VDUPQ:16:result_uint16x8 [] = { fff1, fff1, fff1, fff1, fff1, fff1, fff1, fff1,  }
+VDUP/VDUPQ:17:result_uint32x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VDUP/VDUPQ:18:result_uint64x2 [] = { fffffffffffffff1, fffffffffffffff1,  }
+VDUP/VDUPQ:19:result_poly8x16 [] = { f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1,  }
+VDUP/VDUPQ:20:result_poly16x8 [] = { fff1, fff1, fff1, fff1, fff1, fff1, fff1, fff1,  }
+VDUP/VDUPQ:21:result_float32x4 [] = { c1700000, c1700000, c1700000, c1700000,  }
+
+VDUP/VDUPQ output:
+VDUP/VDUPQ:0:result_int8x8 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VDUP/VDUPQ:1:result_int16x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VDUP/VDUPQ:2:result_int32x2 [] = { fffffff2, fffffff2,  }
+VDUP/VDUPQ:3:result_int64x1 [] = { fffffffffffffff2,  }
+VDUP/VDUPQ:4:result_uint8x8 [] = { f2, f2, f2, f2, f2, f2, f2, f2,  }
+VDUP/VDUPQ:5:result_uint16x4 [] = { fff2, fff2, fff2, fff2,  }
+VDUP/VDUPQ:6:result_uint32x2 [] = { fffffff2, fffffff2,  }
+VDUP/VDUPQ:7:result_uint64x1 [] = { fffffffffffffff2,  }
+VDUP/VDUPQ:8:result_poly8x8 [] = { f2, f2, f2, f2, f2, f2, f2, f2,  }
+VDUP/VDUPQ:9:result_poly16x4 [] = { fff2, fff2, fff2, fff2,  }
+VDUP/VDUPQ:10:result_float32x2 [] = { c1600000, c1600000,  }
+VDUP/VDUPQ:11:result_int8x16 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VDUP/VDUPQ:12:result_int16x8 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VDUP/VDUPQ:13:result_int32x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VDUP/VDUPQ:14:result_int64x2 [] = { fffffffffffffff2, fffffffffffffff2,  }
+VDUP/VDUPQ:15:result_uint8x16 [] = { f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2,  }
+VDUP/VDUPQ:16:result_uint16x8 [] = { fff2, fff2, fff2, fff2, fff2, fff2, fff2, fff2,  }
+VDUP/VDUPQ:17:result_uint32x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VDUP/VDUPQ:18:result_uint64x2 [] = { fffffffffffffff2, fffffffffffffff2,  }
+VDUP/VDUPQ:19:result_poly8x16 [] = { f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2,  }
+VDUP/VDUPQ:20:result_poly16x8 [] = { fff2, fff2, fff2, fff2, fff2, fff2, fff2, fff2,  }
+VDUP/VDUPQ:21:result_float32x4 [] = { c1600000, c1600000, c1600000, c1600000,  }
+
+VMOV/VMOVQ output:
+VMOV/VMOVQ:0:result_int8x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VMOV/VMOVQ:1:result_int16x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VMOV/VMOVQ:2:result_int32x2 [] = { fffffff0, fffffff0,  }
+VMOV/VMOVQ:3:result_int64x1 [] = { fffffffffffffff0,  }
+VMOV/VMOVQ:4:result_uint8x8 [] = { f0, f0, f0, f0, f0, f0, f0, f0,  }
+VMOV/VMOVQ:5:result_uint16x4 [] = { fff0, fff0, fff0, fff0,  }
+VMOV/VMOVQ:6:result_uint32x2 [] = { fffffff0, fffffff0,  }
+VMOV/VMOVQ:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VMOV/VMOVQ:8:result_poly8x8 [] = { f0, f0, f0, f0, f0, f0, f0, f0,  }
+VMOV/VMOVQ:9:result_poly16x4 [] = { fff0, fff0, fff0, fff0,  }
+VMOV/VMOVQ:10:result_float32x2 [] = { c1800000, c1800000,  }
+VMOV/VMOVQ:11:result_int8x16 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VMOV/VMOVQ:12:result_int16x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VMOV/VMOVQ:13:result_int32x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VMOV/VMOVQ:14:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VMOV/VMOVQ:15:result_uint8x16 [] = { f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0,  }
+VMOV/VMOVQ:16:result_uint16x8 [] = { fff0, fff0, fff0, fff0, fff0, fff0, fff0, fff0,  }
+VMOV/VMOVQ:17:result_uint32x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VMOV/VMOVQ:18:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VMOV/VMOVQ:19:result_poly8x16 [] = { f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0,  }
+VMOV/VMOVQ:20:result_poly16x8 [] = { fff0, fff0, fff0, fff0, fff0, fff0, fff0, fff0,  }
+VMOV/VMOVQ:21:result_float32x4 [] = { c1800000, c1800000, c1800000, c1800000,  }
+
+VMOV/VMOVQ output:
+VMOV/VMOVQ:0:result_int8x8 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VMOV/VMOVQ:1:result_int16x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VMOV/VMOVQ:2:result_int32x2 [] = { fffffff1, fffffff1,  }
+VMOV/VMOVQ:3:result_int64x1 [] = { fffffffffffffff1,  }
+VMOV/VMOVQ:4:result_uint8x8 [] = { f1, f1, f1, f1, f1, f1, f1, f1,  }
+VMOV/VMOVQ:5:result_uint16x4 [] = { fff1, fff1, fff1, fff1,  }
+VMOV/VMOVQ:6:result_uint32x2 [] = { fffffff1, fffffff1,  }
+VMOV/VMOVQ:7:result_uint64x1 [] = { fffffffffffffff1,  }
+VMOV/VMOVQ:8:result_poly8x8 [] = { f1, f1, f1, f1, f1, f1, f1, f1,  }
+VMOV/VMOVQ:9:result_poly16x4 [] = { fff1, fff1, fff1, fff1,  }
+VMOV/VMOVQ:10:result_float32x2 [] = { c1700000, c1700000,  }
+VMOV/VMOVQ:11:result_int8x16 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VMOV/VMOVQ:12:result_int16x8 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VMOV/VMOVQ:13:result_int32x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VMOV/VMOVQ:14:result_int64x2 [] = { fffffffffffffff1, fffffffffffffff1,  }
+VMOV/VMOVQ:15:result_uint8x16 [] = { f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1,  }
+VMOV/VMOVQ:16:result_uint16x8 [] = { fff1, fff1, fff1, fff1, fff1, fff1, fff1, fff1,  }
+VMOV/VMOVQ:17:result_uint32x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VMOV/VMOVQ:18:result_uint64x2 [] = { fffffffffffffff1, fffffffffffffff1,  }
+VMOV/VMOVQ:19:result_poly8x16 [] = { f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1,  }
+VMOV/VMOVQ:20:result_poly16x8 [] = { fff1, fff1, fff1, fff1, fff1, fff1, fff1, fff1,  }
+VMOV/VMOVQ:21:result_float32x4 [] = { c1700000, c1700000, c1700000, c1700000,  }
+
+VMOV/VMOVQ output:
+VMOV/VMOVQ:0:result_int8x8 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VMOV/VMOVQ:1:result_int16x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VMOV/VMOVQ:2:result_int32x2 [] = { fffffff2, fffffff2,  }
+VMOV/VMOVQ:3:result_int64x1 [] = { fffffffffffffff2,  }
+VMOV/VMOVQ:4:result_uint8x8 [] = { f2, f2, f2, f2, f2, f2, f2, f2,  }
+VMOV/VMOVQ:5:result_uint16x4 [] = { fff2, fff2, fff2, fff2,  }
+VMOV/VMOVQ:6:result_uint32x2 [] = { fffffff2, fffffff2,  }
+VMOV/VMOVQ:7:result_uint64x1 [] = { fffffffffffffff2,  }
+VMOV/VMOVQ:8:result_poly8x8 [] = { f2, f2, f2, f2, f2, f2, f2, f2,  }
+VMOV/VMOVQ:9:result_poly16x4 [] = { fff2, fff2, fff2, fff2,  }
+VMOV/VMOVQ:10:result_float32x2 [] = { c1600000, c1600000,  }
+VMOV/VMOVQ:11:result_int8x16 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VMOV/VMOVQ:12:result_int16x8 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VMOV/VMOVQ:13:result_int32x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VMOV/VMOVQ:14:result_int64x2 [] = { fffffffffffffff2, fffffffffffffff2,  }
+VMOV/VMOVQ:15:result_uint8x16 [] = { f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2,  }
+VMOV/VMOVQ:16:result_uint16x8 [] = { fff2, fff2, fff2, fff2, fff2, fff2, fff2, fff2,  }
+VMOV/VMOVQ:17:result_uint32x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VMOV/VMOVQ:18:result_uint64x2 [] = { fffffffffffffff2, fffffffffffffff2,  }
+VMOV/VMOVQ:19:result_poly8x16 [] = { f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2,  }
+VMOV/VMOVQ:20:result_poly16x8 [] = { fff2, fff2, fff2, fff2, fff2, fff2, fff2, fff2,  }
+VMOV/VMOVQ:21:result_float32x4 [] = { c1600000, c1600000, c1600000, c1600000,  }
+
+VGET_HIGH output:
+VGET_HIGH:0:result_int8x8 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VGET_HIGH:1:result_int16x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VGET_HIGH:2:result_int32x2 [] = { fffffff2, fffffff3,  }
+VGET_HIGH:3:result_int64x1 [] = { fffffffffffffff1,  }
+VGET_HIGH:4:result_uint8x8 [] = { f8, f9, fa, fb, fc, fd, fe, ff,  }
+VGET_HIGH:5:result_uint16x4 [] = { fff4, fff5, fff6, fff7,  }
+VGET_HIGH:6:result_uint32x2 [] = { fffffff2, fffffff3,  }
+VGET_HIGH:7:result_uint64x1 [] = { fffffffffffffff1,  }
+VGET_HIGH:8:result_poly8x8 [] = { f8, f9, fa, fb, fc, fd, fe, ff,  }
+VGET_HIGH:9:result_poly16x4 [] = { fff4, fff5, fff6, fff7,  }
+VGET_HIGH:10:result_float32x2 [] = { c1600000, c1500000,  }
+VGET_HIGH:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VGET_HIGH:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VGET_HIGH:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VGET_HIGH:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VGET_HIGH:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VGET_HIGH:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VGET_HIGH:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VGET_HIGH:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VGET_HIGH:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VGET_HIGH:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VGET_HIGH:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VGET_LOW output:
+VGET_LOW:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VGET_LOW:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VGET_LOW:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VGET_LOW:3:result_int64x1 [] = { fffffffffffffff0,  }
+VGET_LOW:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VGET_LOW:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VGET_LOW:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VGET_LOW:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VGET_LOW:8:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VGET_LOW:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VGET_LOW:10:result_float32x2 [] = { c1800000, c1700000,  }
+VGET_LOW:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VGET_LOW:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VGET_LOW:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VGET_LOW:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VGET_LOW:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VGET_LOW:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VGET_LOW:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VGET_LOW:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VGET_LOW:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VGET_LOW:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VGET_LOW:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQDMLAL_LANE cumulative saturation output:
+VQDMLAL_LANE:0:vqdmlal_lane_s16 Neon cumulative saturation 0
+VQDMLAL_LANE:1:vqdmlal_lane_s32 Neon cumulative saturation 0
+
+VQDMLAL_LANE output:
+VQDMLAL_LANE:2:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:3:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:4:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:5:result_int64x1 [] = { 3333333333333333,  }
+VQDMLAL_LANE:6:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:7:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:8:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:9:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLAL_LANE:10:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:11:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:12:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:13:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:14:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:15:result_int32x4 [] = { 7c1e, 7c1f, 7c20, 7c21,  }
+VQDMLAL_LANE:16:result_int64x2 [] = { 7c1e, 7c1f,  }
+VQDMLAL_LANE:17:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:18:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:19:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_LANE:20:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLAL_LANE:21:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:22:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:23:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQDMLAL_LANE (mul with input=0) cumulative saturation output:
+VQDMLAL_LANE:24:vqdmlal_lane_s16 Neon cumulative saturation 0
+VQDMLAL_LANE:25:vqdmlal_lane_s32 Neon cumulative saturation 0
+
+VQDMLAL_LANE (mul with input=0) output:
+VQDMLAL_LANE:26:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:27:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:28:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:29:result_int64x1 [] = { 3333333333333333,  }
+VQDMLAL_LANE:30:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:31:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:32:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:33:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLAL_LANE:34:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:35:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:36:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:37:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:38:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:39:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VQDMLAL_LANE:40:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VQDMLAL_LANE:41:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:42:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:43:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_LANE:44:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLAL_LANE:45:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:46:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:47:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQDMLAL_LANE (check mul cumulative saturation) cumulative saturation output:
+VQDMLAL_LANE:48:vqdmlal_lane_s16 Neon cumulative saturation 1
+VQDMLAL_LANE:49:vqdmlal_lane_s32 Neon cumulative saturation 1
+
+VQDMLAL_LANE (check mul cumulative saturation) output:
+VQDMLAL_LANE:50:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:51:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:52:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:53:result_int64x1 [] = { 3333333333333333,  }
+VQDMLAL_LANE:54:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:55:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:56:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:57:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLAL_LANE:58:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:59:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:60:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:61:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:62:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:63:result_int32x4 [] = { 7fffffef, 7ffffff0, 7ffffff1, 7ffffff2,  }
+VQDMLAL_LANE:64:result_int64x2 [] = { 7fffffffffffffef, 7ffffffffffffff0,  }
+VQDMLAL_LANE:65:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:66:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:67:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_LANE:68:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLAL_LANE:69:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:70:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:71:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQDMLSL_LANE cumulative saturation output:
+VQDMLSL_LANE:0:vqdmlsl_lane_s16 Neon cumulative saturation 0
+VQDMLSL_LANE:1:vqdmlsl_lane_s32 Neon cumulative saturation 0
+
+VQDMLSL_LANE output:
+VQDMLSL_LANE:2:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:3:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:4:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:5:result_int64x1 [] = { 3333333333333333,  }
+VQDMLSL_LANE:6:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:7:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:8:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:9:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLSL_LANE:10:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:11:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:12:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:13:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:14:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:15:result_int32x4 [] = { ffff83c2, ffff83c3, ffff83c4, ffff83c5,  }
+VQDMLSL_LANE:16:result_int64x2 [] = { ffffffffffff83c2, ffffffffffff83c3,  }
+VQDMLSL_LANE:17:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:18:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:19:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_LANE:20:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLSL_LANE:21:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:22:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:23:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQDMLSL_LANE (mul with input=0) cumulative saturation output:
+VQDMLSL_LANE:24:vqdmlsl_lane_s16 Neon cumulative saturation 0
+VQDMLSL_LANE:25:vqdmlsl_lane_s32 Neon cumulative saturation 0
+
+VQDMLSL_LANE (mul with input=0) output:
+VQDMLSL_LANE:26:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:27:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:28:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:29:result_int64x1 [] = { 3333333333333333,  }
+VQDMLSL_LANE:30:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:31:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:32:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:33:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLSL_LANE:34:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:35:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:36:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:37:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:38:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:39:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VQDMLSL_LANE:40:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VQDMLSL_LANE:41:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:42:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:43:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_LANE:44:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLSL_LANE:45:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:46:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:47:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQDMLSL_LANE (check mul cumulative saturation) cumulative saturation output:
+VQDMLSL_LANE:48:vqdmlsl_lane_s16 Neon cumulative saturation 1
+VQDMLSL_LANE:49:vqdmlsl_lane_s32 Neon cumulative saturation 1
+
+VQDMLSL_LANE (check mul cumulative saturation) output:
+VQDMLSL_LANE:50:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:51:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:52:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:53:result_int64x1 [] = { 3333333333333333,  }
+VQDMLSL_LANE:54:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:55:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:56:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:57:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLSL_LANE:58:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:59:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:60:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:61:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:62:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:63:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VQDMLSL_LANE:64:result_int64x2 [] = { 8000000000000000, 8000000000000000,  }
+VQDMLSL_LANE:65:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:66:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:67:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_LANE:68:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLSL_LANE:69:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:70:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:71:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQDMLAL_N cumulative saturation output:
+VQDMLAL_N:0:vqdmlal_n_s16 Neon cumulative saturation 0
+VQDMLAL_N:1:vqdmlal_n_s32 Neon cumulative saturation 0
+
+VQDMLAL_N output:
+VQDMLAL_N:2:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:3:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:4:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_N:5:result_int64x1 [] = { 3333333333333333,  }
+VQDMLAL_N:6:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:7:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:8:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_N:9:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLAL_N:10:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:11:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:12:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_N:13:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:14:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:15:result_int32x4 [] = { 1684, 1685, 1686, 1687,  }
+VQDMLAL_N:16:result_int64x2 [] = { 21ce, 21cf,  }
+VQDMLAL_N:17:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:18:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:19:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_N:20:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLAL_N:21:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:22:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:23:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQDMLAL_N (check mul cumulative saturation) cumulative saturation output:
+VQDMLAL_N:24:vqdmlal_n_s16 Neon cumulative saturation 1
+VQDMLAL_N:25:vqdmlal_n_s32 Neon cumulative saturation 1
+
+VQDMLAL_N (check mul cumulative saturation) output:
+VQDMLAL_N:26:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:27:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:28:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_N:29:result_int64x1 [] = { 3333333333333333,  }
+VQDMLAL_N:30:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:31:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:32:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_N:33:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLAL_N:34:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:35:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:36:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_N:37:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:38:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:39:result_int32x4 [] = { 7fffffef, 7ffffff0, 7ffffff1, 7ffffff2,  }
+VQDMLAL_N:40:result_int64x2 [] = { 7fffffffffffffef, 7ffffffffffffff0,  }
+VQDMLAL_N:41:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:42:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:43:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_N:44:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLAL_N:45:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:46:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:47:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQDMLSL_N cumulative saturation output:
+VQDMLSL_N:0:vqdmlsl_n_s16 Neon cumulative saturation 0
+VQDMLSL_N:1:vqdmlsl_n_s32 Neon cumulative saturation 0
+
+VQDMLSL_N output:
+VQDMLSL_N:2:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:3:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:4:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_N:5:result_int64x1 [] = { 3333333333333333,  }
+VQDMLSL_N:6:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:7:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:8:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_N:9:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLSL_N:10:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:11:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:12:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_N:13:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:14:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:15:result_int32x4 [] = { ffffe95c, ffffe95d, ffffe95e, ffffe95f,  }
+VQDMLSL_N:16:result_int64x2 [] = { ffffffffffffde12, ffffffffffffde13,  }
+VQDMLSL_N:17:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:18:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:19:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_N:20:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLSL_N:21:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:22:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:23:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQDMLSL_N (check mul cumulative saturation) cumulative saturation output:
+VQDMLSL_N:24:vqdmlsl_n_s16 Neon cumulative saturation 1
+VQDMLSL_N:25:vqdmlsl_n_s32 Neon cumulative saturation 1
+
+VQDMLSL_N (check mul cumulative saturation) output:
+VQDMLSL_N:26:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:27:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:28:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_N:29:result_int64x1 [] = { 3333333333333333,  }
+VQDMLSL_N:30:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:31:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:32:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_N:33:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLSL_N:34:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:35:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:36:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_N:37:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:38:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:39:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VQDMLSL_N:40:result_int64x2 [] = { 8000000000000000, 8000000000000000,  }
+VQDMLSL_N:41:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:42:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:43:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_N:44:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLSL_N:45:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:46:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:47:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VEXT/VEXTQ output:
+VEXT/VEXTQ:0:result_int8x8 [] = { fffffff7, 11, 11, 11, 11, 11, 11, 11,  }
+VEXT/VEXTQ:1:result_int16x4 [] = { fffffff3, 22, 22, 22,  }
+VEXT/VEXTQ:2:result_int32x2 [] = { fffffff1, 33,  }
+VEXT/VEXTQ:3:result_int64x1 [] = { fffffffffffffff0,  }
+VEXT/VEXTQ:4:result_uint8x8 [] = { f6, f7, 55, 55, 55, 55, 55, 55,  }
+VEXT/VEXTQ:5:result_uint16x4 [] = { fff2, fff3, 66, 66,  }
+VEXT/VEXTQ:6:result_uint32x2 [] = { fffffff1, 77,  }
+VEXT/VEXTQ:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VEXT/VEXTQ:8:result_poly8x8 [] = { f6, f7, 55, 55, 55, 55, 55, 55,  }
+VEXT/VEXTQ:9:result_poly16x4 [] = { fff2, fff3, 66, 66,  }
+VEXT/VEXTQ:10:result_float32x2 [] = { c1700000, 42066666,  }
+VEXT/VEXTQ:11:result_int8x16 [] = { fffffffe, ffffffff, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11,  }
+VEXT/VEXTQ:12:result_int16x8 [] = { fffffff7, 22, 22, 22, 22, 22, 22, 22,  }
+VEXT/VEXTQ:13:result_int32x4 [] = { fffffff3, 33, 33, 33,  }
+VEXT/VEXTQ:14:result_int64x2 [] = { fffffffffffffff1, 44,  }
+VEXT/VEXTQ:15:result_uint8x16 [] = { fc, fd, fe, ff, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55,  }
+VEXT/VEXTQ:16:result_uint16x8 [] = { fff6, fff7, 66, 66, 66, 66, 66, 66,  }
+VEXT/VEXTQ:17:result_uint32x4 [] = { fffffff3, 77, 77, 77,  }
+VEXT/VEXTQ:18:result_uint64x2 [] = { fffffffffffffff1, 88,  }
+VEXT/VEXTQ:19:result_poly8x16 [] = { fc, fd, fe, ff, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55,  }
+VEXT/VEXTQ:20:result_poly16x8 [] = { fff6, fff7, 66, 66, 66, 66, 66, 66,  }
+VEXT/VEXTQ:21:result_float32x4 [] = { c1500000, 4204cccd, 4204cccd, 4204cccd,  }
+
+VSHR_N output:
+VSHR_N:0:result_int8x8 [] = { fffffff8, fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb,  }
+VSHR_N:1:result_int16x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VSHR_N:2:result_int32x2 [] = { fffffffc, fffffffc,  }
+VSHR_N:3:result_int64x1 [] = { ffffffffffffffff,  }
+VSHR_N:4:result_uint8x8 [] = { 3c, 3c, 3c, 3c, 3d, 3d, 3d, 3d,  }
+VSHR_N:5:result_uint16x4 [] = { 1ffe, 1ffe, 1ffe, 1ffe,  }
+VSHR_N:6:result_uint32x2 [] = { 7ffffff, 7ffffff,  }
+VSHR_N:7:result_uint64x1 [] = { 7fffffff,  }
+VSHR_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHR_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHR_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSHR_N:11:result_int8x16 [] = { fffffff8, fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb, fffffffc, fffffffc, fffffffd, fffffffd, fffffffe, fffffffe, ffffffff, ffffffff,  }
+VSHR_N:12:result_int16x8 [] = { ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VSHR_N:13:result_int32x4 [] = { fffffffc, fffffffc, fffffffc, fffffffc,  }
+VSHR_N:14:result_int64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VSHR_N:15:result_uint8x16 [] = { 3c, 3c, 3c, 3c, 3d, 3d, 3d, 3d, 3e, 3e, 3e, 3e, 3f, 3f, 3f, 3f,  }
+VSHR_N:16:result_uint16x8 [] = { 1ffe, 1ffe, 1ffe, 1ffe, 1ffe, 1ffe, 1ffe, 1ffe,  }
+VSHR_N:17:result_uint32x4 [] = { 7ffffff, 7ffffff, 7ffffff, 7ffffff,  }
+VSHR_N:18:result_uint64x2 [] = { 7fffffff, 7fffffff,  }
+VSHR_N:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHR_N:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHR_N:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VSHRN_N output:
+VSHRN_N:0:result_int8x8 [] = { fffffff8, fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb,  }
+VSHRN_N:1:result_int16x4 [] = { fffffff8, fffffff8, fffffff9, fffffff9,  }
+VSHRN_N:2:result_int32x2 [] = { fffffffc, fffffffc,  }
+VSHRN_N:3:result_int64x1 [] = { 3333333333333333,  }
+VSHRN_N:4:result_uint8x8 [] = { fc, fc, fc, fc, fd, fd, fd, fd,  }
+VSHRN_N:5:result_uint16x4 [] = { fffe, fffe, fffe, fffe,  }
+VSHRN_N:6:result_uint32x2 [] = { fffffffe, fffffffe,  }
+VSHRN_N:7:result_uint64x1 [] = { 3333333333333333,  }
+VSHRN_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHRN_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHRN_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSHRN_N:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHRN_N:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHRN_N:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSHRN_N:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VSHRN_N:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHRN_N:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHRN_N:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSHRN_N:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VSHRN_N:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHRN_N:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHRN_N:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSHRN_N (with input = 0) output:
+VRSHRN_N:0:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHRN_N:1:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHRN_N:2:result_int32x2 [] = { 0, 0,  }
+VRSHRN_N:3:result_int64x1 [] = { 3333333333333333,  }
+VRSHRN_N:4:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHRN_N:5:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VRSHRN_N:6:result_uint32x2 [] = { 0, 0,  }
+VRSHRN_N:7:result_uint64x1 [] = { 3333333333333333,  }
+VRSHRN_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHRN_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHRN_N:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHRN_N:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRSHRN_N:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHRN_N:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRSHRN_N:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSHRN_N output:
+VRSHRN_N:22:result_int8x8 [] = { fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb, fffffffc,  }
+VRSHRN_N:23:result_int16x4 [] = { fffffff8, fffffff9, fffffff9, fffffffa,  }
+VRSHRN_N:24:result_int32x2 [] = { fffffffc, fffffffc,  }
+VRSHRN_N:25:result_int64x1 [] = { 3333333333333333,  }
+VRSHRN_N:26:result_uint8x8 [] = { fc, fc, fd, fd, fd, fd, fe, fe,  }
+VRSHRN_N:27:result_uint16x4 [] = { fffe, fffe, fffe, fffe,  }
+VRSHRN_N:28:result_uint32x2 [] = { fffffffe, fffffffe,  }
+VRSHRN_N:29:result_uint64x1 [] = { 3333333333333333,  }
+VRSHRN_N:30:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:31:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHRN_N:32:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHRN_N:33:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:34:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:35:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHRN_N:36:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRSHRN_N:37:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:38:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:39:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHRN_N:40:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRSHRN_N:41:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:42:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:43:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSHRN_N (with large shift amount) output:
+VRSHRN_N:44:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHRN_N:45:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHRN_N:46:result_int32x2 [] = { 0, 0,  }
+VRSHRN_N:47:result_int64x1 [] = { 3333333333333333,  }
+VRSHRN_N:48:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHRN_N:49:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VRSHRN_N:50:result_uint32x2 [] = { 0, 0,  }
+VRSHRN_N:51:result_uint64x1 [] = { 3333333333333333,  }
+VRSHRN_N:52:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:53:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHRN_N:54:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHRN_N:55:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:56:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:57:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHRN_N:58:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRSHRN_N:59:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:60:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:61:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHRN_N:62:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRSHRN_N:63:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:64:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:65:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRSHRN_N cumulative saturation output:
+VQRSHRN_N:0:vqrshrn_n_s16 Neon cumulative saturation 0
+VQRSHRN_N:1:vqrshrn_n_s32 Neon cumulative saturation 0
+VQRSHRN_N:2:vqrshrn_n_s64 Neon cumulative saturation 0
+VQRSHRN_N:3:vqrshrn_n_u16 Neon cumulative saturation 1
+VQRSHRN_N:4:vqrshrn_n_u32 Neon cumulative saturation 1
+VQRSHRN_N:5:vqrshrn_n_u64 Neon cumulative saturation 1
+
+VQRSHRN_N output:
+VQRSHRN_N:6:result_int8x8 [] = { fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb, fffffffc,  }
+VQRSHRN_N:7:result_int16x4 [] = { fffffff8, fffffff9, fffffff9, fffffffa,  }
+VQRSHRN_N:8:result_int32x2 [] = { fffffffc, fffffffc,  }
+VQRSHRN_N:9:result_int64x1 [] = { 3333333333333333,  }
+VQRSHRN_N:10:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHRN_N:11:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQRSHRN_N:12:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQRSHRN_N:13:result_uint64x1 [] = { 3333333333333333,  }
+VQRSHRN_N:14:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:15:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:16:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHRN_N:17:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:18:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:19:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRN_N:20:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRN_N:21:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:22:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:23:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRN_N:24:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRN_N:25:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:26:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:27:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRSHRN_N (check saturation: shift by 3) cumulative saturation output:
+VQRSHRN_N:28:vqrshrn_n_s16 Neon cumulative saturation 1
+VQRSHRN_N:29:vqrshrn_n_s32 Neon cumulative saturation 1
+VQRSHRN_N:30:vqrshrn_n_s64 Neon cumulative saturation 1
+VQRSHRN_N:31:vqrshrn_n_u16 Neon cumulative saturation 1
+VQRSHRN_N:32:vqrshrn_n_u32 Neon cumulative saturation 1
+VQRSHRN_N:33:vqrshrn_n_u64 Neon cumulative saturation 1
+
+VQRSHRN_N (check saturation: shift by 3) output:
+VQRSHRN_N:34:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQRSHRN_N:35:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRSHRN_N:36:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRSHRN_N:37:result_int64x1 [] = { 3333333333333333,  }
+VQRSHRN_N:38:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHRN_N:39:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQRSHRN_N:40:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQRSHRN_N:41:result_uint64x1 [] = { 3333333333333333,  }
+VQRSHRN_N:42:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:43:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:44:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHRN_N:45:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:46:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:47:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRN_N:48:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRN_N:49:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:50:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:51:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRN_N:52:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRN_N:53:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:54:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:55:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRSHRN_N (check saturation: shift by max) cumulative saturation output:
+VQRSHRN_N:56:vqrshrn_n_s16 Neon cumulative saturation 1
+VQRSHRN_N:57:vqrshrn_n_s32 Neon cumulative saturation 1
+VQRSHRN_N:58:vqrshrn_n_s64 Neon cumulative saturation 1
+VQRSHRN_N:59:vqrshrn_n_u16 Neon cumulative saturation 1
+VQRSHRN_N:60:vqrshrn_n_u32 Neon cumulative saturation 1
+VQRSHRN_N:61:vqrshrn_n_u64 Neon cumulative saturation 1
+
+VQRSHRN_N (check saturation: shift by max) output:
+VQRSHRN_N:62:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQRSHRN_N:63:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRSHRN_N:64:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRSHRN_N:65:result_int64x1 [] = { 3333333333333333,  }
+VQRSHRN_N:66:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHRN_N:67:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQRSHRN_N:68:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQRSHRN_N:69:result_uint64x1 [] = { 3333333333333333,  }
+VQRSHRN_N:70:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:71:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:72:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHRN_N:73:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:74:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:75:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRN_N:76:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRN_N:77:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:78:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:79:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRN_N:80:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRN_N:81:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:82:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:83:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VSET_LANE/VSET_LANEQ output:
+VSET_LANE/VSET_LANEQ:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, 11,  }
+VSET_LANE/VSET_LANEQ:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, 22,  }
+VSET_LANE/VSET_LANEQ:2:result_int32x2 [] = { fffffff0, 33,  }
+VSET_LANE/VSET_LANEQ:3:result_int64x1 [] = { 44,  }
+VSET_LANE/VSET_LANEQ:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, 55, f7,  }
+VSET_LANE/VSET_LANEQ:5:result_uint16x4 [] = { fff0, fff1, 66, fff3,  }
+VSET_LANE/VSET_LANEQ:6:result_uint32x2 [] = { fffffff0, 77,  }
+VSET_LANE/VSET_LANEQ:7:result_uint64x1 [] = { 88,  }
+VSET_LANE/VSET_LANEQ:8:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, 55, f7,  }
+VSET_LANE/VSET_LANEQ:9:result_poly16x4 [] = { fff0, fff1, 66, fff3,  }
+VSET_LANE/VSET_LANEQ:10:result_float32x2 [] = { c1800000, 4204cccd,  }
+VSET_LANE/VSET_LANEQ:11:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffff99,  }
+VSET_LANE/VSET_LANEQ:12:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, aa, fffffff6, fffffff7,  }
+VSET_LANE/VSET_LANEQ:13:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, bb,  }
+VSET_LANE/VSET_LANEQ:14:result_int64x2 [] = { fffffffffffffff0, cc,  }
+VSET_LANE/VSET_LANEQ:15:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, dd, ff,  }
+VSET_LANE/VSET_LANEQ:16:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, ee, fff7,  }
+VSET_LANE/VSET_LANEQ:17:result_uint32x4 [] = { fffffff0, fffffff1, ff, fffffff3,  }
+VSET_LANE/VSET_LANEQ:18:result_uint64x2 [] = { fffffffffffffff0, 11,  }
+VSET_LANE/VSET_LANEQ:19:result_poly8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, dd, ff,  }
+VSET_LANE/VSET_LANEQ:20:result_poly16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, ee, fff7,  }
+VSET_LANE/VSET_LANEQ:21:result_float32x4 [] = { c1800000, c1700000, c1600000, 41333333,  }
+
+VGET_LANE/VGETQ_LANE output:
+vget_lane_s8: fffffff7
+vget_lane_s16: fffffff3
+vget_lane_s32: fffffff1
+vget_lane_s64: fffffffffffffff0
+vget_lane_u8: f6
+vget_lane_u16: fff2
+vget_lane_u32: fffffff1
+vget_lane_u64: fffffffffffffff0
+vget_lane_p8: f6
+vget_lane_p16: fff2
+vget_lane_f32: c1700000
+vgetq_lane_s8: ffffffff
+vgetq_lane_s16: fffffff5
+vgetq_lane_s32: fffffff3
+vgetq_lane_s64: fffffffffffffff1
+vgetq_lane_u8: fe
+vgetq_lane_u16: fff6
+vgetq_lane_u32: fffffff2
+vgetq_lane_u64: fffffffffffffff1
+vgetq_lane_p8: fe
+vgetq_lane_p16: fff6
+vgetq_lane_f32: c1500000
+
+
+VQSUB/VQSUBQ cumulative saturation output:
+VQSUB/VQSUBQ:0:vqsub_s8 Neon cumulative saturation 0
+VQSUB/VQSUBQ:1:vqsub_s16 Neon cumulative saturation 0
+VQSUB/VQSUBQ:2:vqsub_s32 Neon cumulative saturation 0
+VQSUB/VQSUBQ:3:vqsub_s64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:4:vqsub_u8 Neon cumulative saturation 0
+VQSUB/VQSUBQ:5:vqsub_u16 Neon cumulative saturation 0
+VQSUB/VQSUBQ:6:vqsub_u32 Neon cumulative saturation 0
+VQSUB/VQSUBQ:7:vqsub_u64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:8:vqsubq_s8 Neon cumulative saturation 0
+VQSUB/VQSUBQ:9:vqsubq_s16 Neon cumulative saturation 0
+VQSUB/VQSUBQ:10:vqsubq_s32 Neon cumulative saturation 0
+VQSUB/VQSUBQ:11:vqsubq_s64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:12:vqsubq_u8 Neon cumulative saturation 0
+VQSUB/VQSUBQ:13:vqsubq_u16 Neon cumulative saturation 0
+VQSUB/VQSUBQ:14:vqsubq_u32 Neon cumulative saturation 0
+VQSUB/VQSUBQ:15:vqsubq_u64 Neon cumulative saturation 0
+
+VQSUB/VQSUBQ output:
+VQSUB/VQSUBQ:16:result_int8x8 [] = { ffffffdf, ffffffe0, ffffffe1, ffffffe2, ffffffe3, ffffffe4, ffffffe5, ffffffe6,  }
+VQSUB/VQSUBQ:17:result_int16x4 [] = { ffffffce, ffffffcf, ffffffd0, ffffffd1,  }
+VQSUB/VQSUBQ:18:result_int32x2 [] = { ffffffbd, ffffffbe,  }
+VQSUB/VQSUBQ:19:result_int64x1 [] = { ffffffffffffffac,  }
+VQSUB/VQSUBQ:20:result_uint8x8 [] = { 9b, 9c, 9d, 9e, 9f, a0, a1, a2,  }
+VQSUB/VQSUBQ:21:result_uint16x4 [] = { ff8a, ff8b, ff8c, ff8d,  }
+VQSUB/VQSUBQ:22:result_uint32x2 [] = { ffffff79, ffffff7a,  }
+VQSUB/VQSUBQ:23:result_uint64x1 [] = { ffffffffffffff68,  }
+VQSUB/VQSUBQ:24:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSUB/VQSUBQ:25:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSUB/VQSUBQ:26:result_float32x2 [] = { 33333333, 33333333,  }
+VQSUB/VQSUBQ:27:result_int8x16 [] = { ffffffdf, ffffffe0, ffffffe1, ffffffe2, ffffffe3, ffffffe4, ffffffe5, ffffffe6, ffffffe7, ffffffe8, ffffffe9, ffffffea, ffffffeb, ffffffec, ffffffed, ffffffee,  }
+VQSUB/VQSUBQ:28:result_int16x8 [] = { ffffffce, ffffffcf, ffffffd0, ffffffd1, ffffffd2, ffffffd3, ffffffd4, ffffffd5,  }
+VQSUB/VQSUBQ:29:result_int32x4 [] = { ffffffbd, ffffffbe, ffffffbf, ffffffc0,  }
+VQSUB/VQSUBQ:30:result_int64x2 [] = { ffffffffffffffac, ffffffffffffffad,  }
+VQSUB/VQSUBQ:31:result_uint8x16 [] = { 9b, 9c, 9d, 9e, 9f, a0, a1, a2, a3, a4, a5, a6, a7, a8, a9, aa,  }
+VQSUB/VQSUBQ:32:result_uint16x8 [] = { ff8a, ff8b, ff8c, ff8d, ff8e, ff8f, ff90, ff91,  }
+VQSUB/VQSUBQ:33:result_uint32x4 [] = { ffffff79, ffffff7a, ffffff7b, ffffff7c,  }
+VQSUB/VQSUBQ:34:result_uint64x2 [] = { ffffffffffffff68, ffffffffffffff69,  }
+VQSUB/VQSUBQ:35:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSUB/VQSUBQ:36:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSUB/VQSUBQ:37:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQSUB/VQSUBQ 64 bits saturation cumulative saturation output:
+VQSUB/VQSUBQ:38:vqsub_s64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:39:vqsub_u64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:40:vqsubq_s64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:41:vqsubq_u64 Neon cumulative saturation 0
+
+64 bits saturation:
+VQSUB/VQSUBQ:42:result_int64x1 [] = { fffffffffffffff0,  }
+VQSUB/VQSUBQ:43:result_uint64x1 [] = { fffffffffffffff0,  }
+VQSUB/VQSUBQ:44:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VQSUB/VQSUBQ:45:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+
+VQSUB/VQSUBQ 64 bits saturation cumulative saturation output:
+VQSUB/VQSUBQ:46:vqsub_s64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:47:vqsub_u64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:48:vqsubq_s64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:49:vqsubq_u64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:50:result_int64x1 [] = { ffffffffffffffac,  }
+VQSUB/VQSUBQ:51:result_uint64x1 [] = { ffffffffffffff68,  }
+VQSUB/VQSUBQ:52:result_int64x2 [] = { ffffffffffffffac, ffffffffffffffad,  }
+VQSUB/VQSUBQ:53:result_uint64x2 [] = { ffffffffffffff68, ffffffffffffff69,  }
+
+VQSUB/VQSUBQ 64 bits saturation cumulative saturation output:
+VQSUB/VQSUBQ:54:vqsub_s64 Neon cumulative saturation 1
+VQSUB/VQSUBQ:55:vqsub_u64 Neon cumulative saturation 1
+VQSUB/VQSUBQ:56:vqsubq_s64 Neon cumulative saturation 1
+VQSUB/VQSUBQ:57:vqsubq_u64 Neon cumulative saturation 1
+VQSUB/VQSUBQ:58:result_int64x1 [] = { 8000000000000000,  }
+VQSUB/VQSUBQ:59:result_uint64x1 [] = { 0,  }
+VQSUB/VQSUBQ:60:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+VQSUB/VQSUBQ:61:result_uint64x2 [] = { 0, 0,  }
+
+less than 64 bits saturation:
+VQSUB/VQSUBQ:62:vqsub_s8 Neon cumulative saturation 1
+VQSUB/VQSUBQ:63:vqsub_s16 Neon cumulative saturation 1
+VQSUB/VQSUBQ:64:vqsub_s32 Neon cumulative saturation 1
+VQSUB/VQSUBQ:65:vqsubq_s8 Neon cumulative saturation 1
+VQSUB/VQSUBQ:66:vqsubq_s16 Neon cumulative saturation 1
+VQSUB/VQSUBQ:67:vqsubq_s32 Neon cumulative saturation 1
+VQSUB/VQSUBQ:68:result_int8x8 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQSUB/VQSUBQ:69:result_int16x4 [] = { ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQSUB/VQSUBQ:70:result_int32x2 [] = { 80000000, 80000000,  }
+VQSUB/VQSUBQ:71:result_int8x16 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQSUB/VQSUBQ:72:result_int16x8 [] = { ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQSUB/VQSUBQ:73:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+
+VQSUB/VQSUBQ less than 64 bits saturation cumulative saturation output:
+VQSUB/VQSUBQ:74:vqsub_u8 Neon cumulative saturation 1
+VQSUB/VQSUBQ:75:vqsub_u16 Neon cumulative saturation 1
+VQSUB/VQSUBQ:76:vqsub_u32 Neon cumulative saturation 1
+VQSUB/VQSUBQ:77:vqsubq_u8 Neon cumulative saturation 1
+VQSUB/VQSUBQ:78:vqsubq_u16 Neon cumulative saturation 1
+VQSUB/VQSUBQ:79:vqsubq_u32 Neon cumulative saturation 1
+VQSUB/VQSUBQ:80:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSUB/VQSUBQ:81:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQSUB/VQSUBQ:82:result_uint32x2 [] = { 0, 0,  }
+VQSUB/VQSUBQ:83:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSUB/VQSUBQ:84:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSUB/VQSUBQ:85:result_uint32x4 [] = { 0, 0, 0, 0,  }
+
+VQDMULH cumulative saturation output:
+VQDMULH:0:vqdmulh_s16 Neon cumulative saturation 0
+VQDMULH:1:vqdmulh_s32 Neon cumulative saturation 0
+VQDMULH:2:vqdmulhq_s16 Neon cumulative saturation 0
+VQDMULH:3:vqdmulhq_s32 Neon cumulative saturation 0
+
+VQDMULH output:
+VQDMULH:4:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:5:result_int16x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQDMULH:6:result_int32x2 [] = { ffffffff, ffffffff,  }
+VQDMULH:7:result_int64x1 [] = { 3333333333333333,  }
+VQDMULH:8:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:9:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH:10:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMULH:11:result_uint64x1 [] = { 3333333333333333,  }
+VQDMULH:12:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:13:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH:14:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMULH:15:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:16:result_int16x8 [] = { ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQDMULH:17:result_int32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQDMULH:18:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH:19:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:20:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH:21:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH:22:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH:23:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:24:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH:25:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQDMULH cumulative saturation output:
+VQDMULH:26:vqdmulh_s16 Neon cumulative saturation 1
+VQDMULH:27:vqdmulh_s32 Neon cumulative saturation 1
+VQDMULH:28:vqdmulhq_s16 Neon cumulative saturation 1
+VQDMULH:29:vqdmulhq_s32 Neon cumulative saturation 1
+
+VQDMULH output:
+VQDMULH:30:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:31:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQDMULH:32:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQDMULH:33:result_int64x1 [] = { 3333333333333333,  }
+VQDMULH:34:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:35:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH:36:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMULH:37:result_uint64x1 [] = { 3333333333333333,  }
+VQDMULH:38:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:39:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH:40:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMULH:41:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:42:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQDMULH:43:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQDMULH:44:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH:45:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:46:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH:47:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH:48:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH:49:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:50:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH:51:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQDMULH_LANE cumulative saturation output:
+VQDMULH_LANE:0:vqdmulh_lane_s16 Neon cumulative saturation 0
+VQDMULH_LANE:1:vqdmulh_lane_s32 Neon cumulative saturation 0
+VQDMULH_LANE:2:vqdmulhq_lane_s16 Neon cumulative saturation 0
+VQDMULH_LANE:3:vqdmulhq_lane_s32 Neon cumulative saturation 0
+
+VQDMULH_LANE output:
+VQDMULH_LANE:4:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:5:result_int16x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQDMULH_LANE:6:result_int32x2 [] = { ffffffff, ffffffff,  }
+VQDMULH_LANE:7:result_int64x1 [] = { 3333333333333333,  }
+VQDMULH_LANE:8:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:9:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH_LANE:10:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMULH_LANE:11:result_uint64x1 [] = { 3333333333333333,  }
+VQDMULH_LANE:12:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:13:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH_LANE:14:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMULH_LANE:15:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:16:result_int16x8 [] = { ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQDMULH_LANE:17:result_int32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQDMULH_LANE:18:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH_LANE:19:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:20:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH_LANE:21:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH_LANE:22:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH_LANE:23:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:24:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH_LANE:25:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQDMULH_LANE (check mul cumulative saturation) cumulative saturation output:
+VQDMULH_LANE:26:vqdmulh_lane_s16 Neon cumulative saturation 1
+VQDMULH_LANE:27:vqdmulh_lane_s32 Neon cumulative saturation 1
+VQDMULH_LANE:28:vqdmulhq_lane_s16 Neon cumulative saturation 1
+VQDMULH_LANE:29:vqdmulhq_lane_s32 Neon cumulative saturation 1
+
+VQDMULH_LANE (check mul cumulative saturation) output:
+VQDMULH_LANE:30:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:31:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQDMULH_LANE:32:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQDMULH_LANE:33:result_int64x1 [] = { 3333333333333333,  }
+VQDMULH_LANE:34:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:35:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH_LANE:36:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMULH_LANE:37:result_uint64x1 [] = { 3333333333333333,  }
+VQDMULH_LANE:38:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:39:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH_LANE:40:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMULH_LANE:41:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:42:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQDMULH_LANE:43:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQDMULH_LANE:44:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH_LANE:45:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:46:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH_LANE:47:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH_LANE:48:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH_LANE:49:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:50:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH_LANE:51:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQDMULH_N cumulative saturation output:
+VQDMULH_N:0:vqdmulh_n_s16 Neon cumulative saturation 0
+VQDMULH_N:1:vqdmulh_n_s32 Neon cumulative saturation 0
+VQDMULH_N:2:vqdmulhq_n_s16 Neon cumulative saturation 0
+VQDMULH_N:3:vqdmulhq_n_s32 Neon cumulative saturation 0
+
+VQDMULH_N output:
+VQDMULH_N:4:result_int16x4 [] = { 19, 19, 19, 19,  }
+VQDMULH_N:5:result_int32x2 [] = { 4, 4,  }
+VQDMULH_N:6:result_int16x8 [] = { 10, 10, 10, 10, 10, 10, 10, 10,  }
+VQDMULH_N:7:result_int32x4 [] = { a, a, a, a,  }
+
+VQDMULH_N (check mul cumulative saturation) cumulative saturation output:
+VQDMULH_N:8:vqdmulh_n_s16 Neon cumulative saturation 1
+VQDMULH_N:9:vqdmulh_n_s32 Neon cumulative saturation 1
+VQDMULH_N:10:vqdmulhq_n_s16 Neon cumulative saturation 1
+VQDMULH_N:11:vqdmulhq_n_s32 Neon cumulative saturation 1
+
+VQDMULH_N (check mul cumulative saturation) output:
+VQDMULH_N:12:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_N:13:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQDMULH_N:14:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQDMULH_N:15:result_int64x1 [] = { 3333333333333333,  }
+VQDMULH_N:16:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_N:17:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH_N:18:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMULH_N:19:result_uint64x1 [] = { 3333333333333333,  }
+VQDMULH_N:20:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_N:21:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH_N:22:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMULH_N:23:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_N:24:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQDMULH_N:25:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQDMULH_N:26:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH_N:27:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_N:28:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH_N:29:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH_N:30:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH_N:31:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_N:32:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH_N:33:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQDMULL cumulative saturation output:
+VQDMULL:0:vqdmull_s16 Neon cumulative saturation 0
+VQDMULL:1:vqdmull_s32 Neon cumulative saturation 0
+
+VQDMULL output:
+VQDMULL:2:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:3:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULL:4:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMULL:5:result_int64x1 [] = { 3333333333333333,  }
+VQDMULL:6:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:7:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULL:8:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMULL:9:result_uint64x1 [] = { 3333333333333333,  }
+VQDMULL:10:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:11:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULL:12:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMULL:13:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:14:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULL:15:result_int32x4 [] = { 200, 1c2, 188, 152,  }
+VQDMULL:16:result_int64x2 [] = { 200, 1c2,  }
+VQDMULL:17:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:18:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULL:19:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULL:20:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULL:21:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:22:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULL:23:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQDMULL (check mul cumulative saturation) cumulative saturation output:
+VQDMULL:24:vqdmull_s16 Neon cumulative saturation 1
+VQDMULL:25:vqdmull_s32 Neon cumulative saturation 1
+
+VQDMULL (check mul cumulative saturation) output:
+VQDMULL:26:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:27:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULL:28:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMULL:29:result_int64x1 [] = { 3333333333333333,  }
+VQDMULL:30:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:31:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULL:32:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMULL:33:result_uint64x1 [] = { 3333333333333333,  }
+VQDMULL:34:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:35:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULL:36:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMULL:37:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:38:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULL:39:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQDMULL:40:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+VQDMULL:41:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:42:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULL:43:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULL:44:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULL:45:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:46:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULL:47:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQDMLAL cumulative saturation output:
+VQDMLAL:0:vqdmlal_s16 Neon cumulative saturation 0
+VQDMLAL:1:vqdmlal_s32 Neon cumulative saturation 0
+
+VQDMLAL output:
+VQDMLAL:2:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:3:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL:4:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLAL:5:result_int64x1 [] = { 3333333333333333,  }
+VQDMLAL:6:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:7:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL:8:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLAL:9:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLAL:10:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:11:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL:12:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLAL:13:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:14:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL:15:result_int32x4 [] = { 7c1e, 7c1f, 7c20, 7c21,  }
+VQDMLAL:16:result_int64x2 [] = { 7c1e, 7c1f,  }
+VQDMLAL:17:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:18:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL:19:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL:20:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLAL:21:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:22:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL:23:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQDMLAL (check mul cumulative saturation) cumulative saturation output:
+VQDMLAL:24:vqdmlal_s16 Neon cumulative saturation 1
+VQDMLAL:25:vqdmlal_s32 Neon cumulative saturation 1
+
+VQDMLAL (check mul cumulative saturation) output:
+VQDMLAL:26:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:27:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL:28:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLAL:29:result_int64x1 [] = { 3333333333333333,  }
+VQDMLAL:30:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:31:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL:32:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLAL:33:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLAL:34:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:35:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL:36:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLAL:37:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:38:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL:39:result_int32x4 [] = { 7fffffef, 7ffffff0, 7ffffff1, 7ffffff2,  }
+VQDMLAL:40:result_int64x2 [] = { 7fffffffffffffef, 7ffffffffffffff0,  }
+VQDMLAL:41:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:42:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL:43:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL:44:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLAL:45:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:46:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL:47:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQDMLSL cumulative saturation output:
+VQDMLSL:0:vqdmlsl_s16 Neon cumulative saturation 0
+VQDMLSL:1:vqdmlsl_s32 Neon cumulative saturation 0
+
+VQDMLSL output:
+VQDMLSL:2:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:3:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL:4:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLSL:5:result_int64x1 [] = { 3333333333333333,  }
+VQDMLSL:6:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:7:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL:8:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLSL:9:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLSL:10:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:11:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL:12:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLSL:13:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:14:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL:15:result_int32x4 [] = { ffff83c2, ffff83c3, ffff83c4, ffff83c5,  }
+VQDMLSL:16:result_int64x2 [] = { ffffffffffff83c2, ffffffffffff83c3,  }
+VQDMLSL:17:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:18:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL:19:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL:20:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLSL:21:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:22:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL:23:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQDMLSL (check mul cumulative saturation) cumulative saturation output:
+VQDMLSL:24:vqdmlsl_s16 Neon cumulative saturation 1
+VQDMLSL:25:vqdmlsl_s32 Neon cumulative saturation 1
+
+VQDMLSL (check mul cumulative saturation) output:
+VQDMLSL:26:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:27:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL:28:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLSL:29:result_int64x1 [] = { 3333333333333333,  }
+VQDMLSL:30:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:31:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL:32:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLSL:33:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLSL:34:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:35:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL:36:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLSL:37:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:38:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL:39:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VQDMLSL:40:result_int64x2 [] = { 8000000000000000, 8000000000000000,  }
+VQDMLSL:41:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:42:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL:43:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL:44:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLSL:45:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:46:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL:47:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VCEQ/VCEQQ output:
+VCEQ/VCEQQ:0:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, ff, 0,  }
+VCEQ/VCEQQ:1:result_uint16x4 [] = { 0, 0, ffff, 0,  }
+VCEQ/VCEQQ:2:result_uint32x2 [] = { ffffffff, 0,  }
+VCEQ/VCEQQ:3:result_uint8x8 [] = { 0, 0, 0, ff, 0, 0, 0, 0,  }
+VCEQ/VCEQQ:4:result_uint16x4 [] = { 0, 0, ffff, 0,  }
+VCEQ/VCEQQ:5:result_uint32x2 [] = { 0, ffffffff,  }
+VCEQ/VCEQQ:6:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ff, 0, 0, 0,  }
+VCEQ/VCEQQ:7:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, ffff, 0,  }
+VCEQ/VCEQQ:8:result_uint32x4 [] = { 0, 0, ffffffff, 0,  }
+VCEQ/VCEQQ:9:result_uint8x16 [] = { 0, 0, 0, 0, ff, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VCEQ/VCEQQ:10:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, ffff, 0,  }
+VCEQ/VCEQQ:11:result_uint32x4 [] = { 0, 0, ffffffff, 0,  }
+VCEQ/VCEQQ:12:result_uint32x2 [] = { 0, ffffffff,  }
+VCEQ/VCEQQ:13:result_uint32x4 [] = { 0, 0, ffffffff, 0,  }
+VCEQ/VCEQQ:14:result_uint32x2 [] = { ffffffff, 0,  }
+VCEQ/VCEQQ:15:result_uint32x2 [] = { 0, ffffffff,  }
+VCEQ/VCEQQ:16:result_uint32x2 [] = { ffffffff, 0,  }
+VCEQ/VCEQQ FP special (NaN):17:result_uint32x2 [] = { 0, 0,  }
+VCEQ/VCEQQ FP special (-NaN):18:result_uint32x2 [] = { 0, 0,  }
+VCEQ/VCEQQ FP special (NaN):19:result_uint32x2 [] = { 0, 0,  }
+VCEQ/VCEQQ FP special (inf):20:result_uint32x2 [] = { 0, 0,  }
+VCEQ/VCEQQ FP special (-inf):21:result_uint32x2 [] = { 0, 0,  }
+VCEQ/VCEQQ FP special (inf):22:result_uint32x2 [] = { 0, 0,  }
+VCEQ/VCEQQ FP special (-0.0):23:result_uint32x2 [] = { ffffffff, ffffffff,  }
+
+VCEQ/VCEQQ p8 output:
+VCEQ/VCEQQ:0:result_uint8x8 [] = { 0, 0, 0, ff, 0, 0, 0, 0,  }
+VCEQ/VCEQQ:1:result_uint8x16 [] = { 0, 0, 0, 0, ff, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VCGE/VCGEQ output:
+VCGE/VCGEQ:0:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, ff, ff,  }
+VCGE/VCGEQ:1:result_uint16x4 [] = { 0, 0, ffff, ffff,  }
+VCGE/VCGEQ:2:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCGE/VCGEQ:3:result_uint8x8 [] = { 0, 0, 0, ff, ff, ff, ff, ff,  }
+VCGE/VCGEQ:4:result_uint16x4 [] = { 0, 0, ffff, ffff,  }
+VCGE/VCGEQ:5:result_uint32x2 [] = { 0, ffffffff,  }
+VCGE/VCGEQ:6:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ff, ff, ff, ff,  }
+VCGE/VCGEQ:7:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, ffff, ffff,  }
+VCGE/VCGEQ:8:result_uint32x4 [] = { 0, 0, ffffffff, ffffffff,  }
+VCGE/VCGEQ:9:result_uint8x16 [] = { 0, 0, 0, 0, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VCGE/VCGEQ:10:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, ffff, ffff,  }
+VCGE/VCGEQ:11:result_uint32x4 [] = { 0, 0, ffffffff, ffffffff,  }
+VCGE/VCGEQ:12:result_uint32x2 [] = { 0, ffffffff,  }
+VCGE/VCGEQ:13:result_uint32x4 [] = { 0, 0, ffffffff, ffffffff,  }
+VCGE/VCGEQ:14:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCGE/VCGEQ:15:result_uint32x2 [] = { 0, ffffffff,  }
+VCGE/VCGEQ:16:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCGE/VCGEQ FP special (NaN):17:result_uint32x2 [] = { 0, 0,  }
+VCGE/VCGEQ FP special (-NaN):18:result_uint32x2 [] = { 0, 0,  }
+VCGE/VCGEQ FP special (NaN):19:result_uint32x2 [] = { 0, 0,  }
+VCGE/VCGEQ FP special (inf):20:result_uint32x2 [] = { 0, 0,  }
+VCGE/VCGEQ FP special (-inf):21:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCGE/VCGEQ FP special (inf):22:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCGE/VCGEQ FP special (-0.0):23:result_uint32x2 [] = { ffffffff, ffffffff,  }
+
+VCLE/VCLEQ output:
+VCLE/VCLEQ:0:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, 0,  }
+VCLE/VCLEQ:1:result_uint16x4 [] = { ffff, ffff, ffff, 0,  }
+VCLE/VCLEQ:2:result_uint32x2 [] = { ffffffff, 0,  }
+VCLE/VCLEQ:3:result_uint8x8 [] = { ff, ff, ff, ff, 0, 0, 0, 0,  }
+VCLE/VCLEQ:4:result_uint16x4 [] = { ffff, ffff, ffff, 0,  }
+VCLE/VCLEQ:5:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCLE/VCLEQ:6:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, 0, 0, 0,  }
+VCLE/VCLEQ:7:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, 0,  }
+VCLE/VCLEQ:8:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, 0,  }
+VCLE/VCLEQ:9:result_uint8x16 [] = { ff, ff, ff, ff, ff, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VCLE/VCLEQ:10:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, 0,  }
+VCLE/VCLEQ:11:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, 0,  }
+VCLE/VCLEQ:12:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCLE/VCLEQ:13:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, 0,  }
+VCLE/VCLEQ:14:result_uint32x2 [] = { ffffffff, 0,  }
+VCLE/VCLEQ:15:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCLE/VCLEQ:16:result_uint32x2 [] = { ffffffff, 0,  }
+VCLE/VCLEQ FP special (NaN):17:result_uint32x2 [] = { 0, 0,  }
+VCLE/VCLEQ FP special (-NaN):18:result_uint32x2 [] = { 0, 0,  }
+VCLE/VCLEQ FP special (NaN):19:result_uint32x2 [] = { 0, 0,  }
+VCLE/VCLEQ FP special (inf):20:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCLE/VCLEQ FP special (-inf):21:result_uint32x2 [] = { 0, 0,  }
+VCLE/VCLEQ FP special (inf):22:result_uint32x2 [] = { 0, 0,  }
+VCLE/VCLEQ FP special (-0.0):23:result_uint32x2 [] = { ffffffff, ffffffff,  }
+
+VCGT/VCGTQ output:
+VCGT/VCGTQ:0:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, ff,  }
+VCGT/VCGTQ:1:result_uint16x4 [] = { 0, 0, 0, ffff,  }
+VCGT/VCGTQ:2:result_uint32x2 [] = { 0, ffffffff,  }
+VCGT/VCGTQ:3:result_uint8x8 [] = { 0, 0, 0, 0, ff, ff, ff, ff,  }
+VCGT/VCGTQ:4:result_uint16x4 [] = { 0, 0, 0, ffff,  }
+VCGT/VCGTQ:5:result_uint32x2 [] = { 0, 0,  }
+VCGT/VCGTQ:6:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ff, ff, ff,  }
+VCGT/VCGTQ:7:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, ffff,  }
+VCGT/VCGTQ:8:result_uint32x4 [] = { 0, 0, 0, ffffffff,  }
+VCGT/VCGTQ:9:result_uint8x16 [] = { 0, 0, 0, 0, 0, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VCGT/VCGTQ:10:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, ffff,  }
+VCGT/VCGTQ:11:result_uint32x4 [] = { 0, 0, 0, ffffffff,  }
+VCGT/VCGTQ:12:result_uint32x2 [] = { 0, 0,  }
+VCGT/VCGTQ:13:result_uint32x4 [] = { 0, 0, 0, ffffffff,  }
+VCGT/VCGTQ:14:result_uint32x2 [] = { 0, ffffffff,  }
+VCGT/VCGTQ:15:result_uint32x2 [] = { 0, 0,  }
+VCGT/VCGTQ:16:result_uint32x2 [] = { 0, ffffffff,  }
+VCGT/VCGTQ FP special (NaN):17:result_uint32x2 [] = { 0, 0,  }
+VCGT/VCGTQ FP special (-NaN):18:result_uint32x2 [] = { 0, 0,  }
+VCGT/VCGTQ FP special (NaN):19:result_uint32x2 [] = { 0, 0,  }
+VCGT/VCGTQ FP special (inf):20:result_uint32x2 [] = { 0, 0,  }
+VCGT/VCGTQ FP special (-inf):21:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCGT/VCGTQ FP special (inf):22:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCGT/VCGTQ FP special (-0.0):23:result_uint32x2 [] = { 0, 0,  }
+
+VCLT/VCLTQ output:
+VCLT/VCLTQ:0:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, 0, 0,  }
+VCLT/VCLTQ:1:result_uint16x4 [] = { ffff, ffff, 0, 0,  }
+VCLT/VCLTQ:2:result_uint32x2 [] = { 0, 0,  }
+VCLT/VCLTQ:3:result_uint8x8 [] = { ff, ff, ff, 0, 0, 0, 0, 0,  }
+VCLT/VCLTQ:4:result_uint16x4 [] = { ffff, ffff, 0, 0,  }
+VCLT/VCLTQ:5:result_uint32x2 [] = { ffffffff, 0,  }
+VCLT/VCLTQ:6:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, 0, 0, 0, 0,  }
+VCLT/VCLTQ:7:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, 0, 0,  }
+VCLT/VCLTQ:8:result_uint32x4 [] = { ffffffff, ffffffff, 0, 0,  }
+VCLT/VCLTQ:9:result_uint8x16 [] = { ff, ff, ff, ff, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VCLT/VCLTQ:10:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, 0, 0,  }
+VCLT/VCLTQ:11:result_uint32x4 [] = { ffffffff, ffffffff, 0, 0,  }
+VCLT/VCLTQ:12:result_uint32x2 [] = { ffffffff, 0,  }
+VCLT/VCLTQ:13:result_uint32x4 [] = { ffffffff, ffffffff, 0, 0,  }
+VCLT/VCLTQ:14:result_uint32x2 [] = { 0, 0,  }
+VCLT/VCLTQ:15:result_uint32x2 [] = { ffffffff, 0,  }
+VCLT/VCLTQ:16:result_uint32x2 [] = { 0, 0,  }
+VCLT/VCLTQ FP special (NaN):17:result_uint32x2 [] = { 0, 0,  }
+VCLT/VCLTQ FP special (-NaN):18:result_uint32x2 [] = { 0, 0,  }
+VCLT/VCLTQ FP special (NaN):19:result_uint32x2 [] = { 0, 0,  }
+VCLT/VCLTQ FP special (inf):20:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCLT/VCLTQ FP special (-inf):21:result_uint32x2 [] = { 0, 0,  }
+VCLT/VCLTQ FP special (inf):22:result_uint32x2 [] = { 0, 0,  }
+VCLT/VCLTQ FP special (-0.0):23:result_uint32x2 [] = { 0, 0,  }
+
+VBSL/VBSLQ output:
+VBSL/VBSLQ:0:result_int8x8 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff6, fffffff6, fffffff6, fffffff6,  }
+VBSL/VBSLQ:1:result_int16x4 [] = { fffffff0, fffffff0, fffffff2, fffffff2,  }
+VBSL/VBSLQ:2:result_int32x2 [] = { fffffff0, fffffff0,  }
+VBSL/VBSLQ:3:result_int64x1 [] = { fffffffffffffffd,  }
+VBSL/VBSLQ:4:result_uint8x8 [] = { f3, f3, f3, f3, f7, f7, f7, f7,  }
+VBSL/VBSLQ:5:result_uint16x4 [] = { fff0, fff0, fff2, fff2,  }
+VBSL/VBSLQ:6:result_uint32x2 [] = { fffffff0, fffffff0,  }
+VBSL/VBSLQ:7:result_uint64x1 [] = { fffffff1,  }
+VBSL/VBSLQ:8:result_poly8x8 [] = { f3, f3, f3, f3, f7, f7, f7, f7,  }
+VBSL/VBSLQ:9:result_poly16x4 [] = { fff0, fff0, fff2, fff2,  }
+VBSL/VBSLQ:10:result_float32x2 [] = { c1800004, c1700004,  }
+VBSL/VBSLQ:11:result_int8x16 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff6, fffffff6, fffffff6, fffffff6, fffffff2, fffffff2, fffffff2, fffffff2, fffffff6, fffffff6, fffffff6, fffffff6,  }
+VBSL/VBSLQ:12:result_int16x8 [] = { fffffff0, fffffff0, fffffff2, fffffff2, fffffff4, fffffff4, fffffff6, fffffff6,  }
+VBSL/VBSLQ:13:result_int32x4 [] = { fffffff0, fffffff0, fffffff2, fffffff2,  }
+VBSL/VBSLQ:14:result_int64x2 [] = { fffffffffffffffd, fffffffffffffffd,  }
+VBSL/VBSLQ:15:result_uint8x16 [] = { f3, f3, f3, f3, f7, f7, f7, f7, f3, f3, f3, f3, f7, f7, f7, f7,  }
+VBSL/VBSLQ:16:result_uint16x8 [] = { fff0, fff0, fff2, fff2, fff4, fff4, fff6, fff6,  }
+VBSL/VBSLQ:17:result_uint32x4 [] = { fffffff0, fffffff0, fffffff2, fffffff2,  }
+VBSL/VBSLQ:18:result_uint64x2 [] = { fffffff1, fffffff1,  }
+VBSL/VBSLQ:19:result_poly8x16 [] = { f3, f3, f3, f3, f7, f7, f7, f7, f3, f3, f3, f3, f7, f7, f7, f7,  }
+VBSL/VBSLQ:20:result_poly16x8 [] = { fff0, fff0, fff2, fff2, fff4, fff4, fff6, fff6,  }
+VBSL/VBSLQ:21:result_float32x4 [] = { c1800001, c1700001, c1600001, c1500001,  }
+
+VSHL/VSHLQ output:
+VSHL/VSHLQ:0:result_int8x8 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6, ffffffe8, ffffffea, ffffffec, ffffffee,  }
+VSHL/VSHLQ:1:result_int16x4 [] = { ffffff80, ffffff88, ffffff90, ffffff98,  }
+VSHL/VSHLQ:2:result_int32x2 [] = { fffff000, fffff100,  }
+VSHL/VSHLQ:3:result_int64x1 [] = { ffffffffffffff80,  }
+VSHL/VSHLQ:4:result_uint8x8 [] = { e0, e2, e4, e6, e8, ea, ec, ee,  }
+VSHL/VSHLQ:5:result_uint16x4 [] = { ff80, ff88, ff90, ff98,  }
+VSHL/VSHLQ:6:result_uint32x2 [] = { fffff000, fffff100,  }
+VSHL/VSHLQ:7:result_uint64x1 [] = { ffffffffffffff80,  }
+VSHL/VSHLQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHL/VSHLQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHL/VSHLQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSHL/VSHLQ:11:result_int8x16 [] = { 0, 20, 40, 60, ffffff80, ffffffa0, ffffffc0, ffffffe0, 0, 20, 40, 60, ffffff80, ffffffa0, ffffffc0, ffffffe0,  }
+VSHL/VSHLQ:12:result_int16x8 [] = { 0, 1000, 2000, 3000, 4000, 5000, 6000, 7000,  }
+VSHL/VSHLQ:13:result_int32x4 [] = { 0, 40000000, 80000000, c0000000,  }
+VSHL/VSHLQ:14:result_int64x2 [] = { 0, 8000000000000000,  }
+VSHL/VSHLQ:15:result_uint8x16 [] = { 0, 20, 40, 60, 80, a0, c0, e0, 0, 20, 40, 60, 80, a0, c0, e0,  }
+VSHL/VSHLQ:16:result_uint16x8 [] = { 0, 1000, 2000, 3000, 4000, 5000, 6000, 7000,  }
+VSHL/VSHLQ:17:result_uint32x4 [] = { 0, 40000000, 80000000, c0000000,  }
+VSHL/VSHLQ:18:result_uint64x2 [] = { 0, 8000000000000000,  }
+VSHL/VSHLQ:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHL/VSHLQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHL/VSHLQ:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VSHL/VSHLQ (large shift amount) output:
+VSHL/VSHLQ:22:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VSHL/VSHLQ:23:result_int16x4 [] = { 0, 0, 0, 0,  }
+VSHL/VSHLQ:24:result_int32x2 [] = { 0, 0,  }
+VSHL/VSHLQ:25:result_int64x1 [] = { 0,  }
+VSHL/VSHLQ:26:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VSHL/VSHLQ:27:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VSHL/VSHLQ:28:result_uint32x2 [] = { 0, 0,  }
+VSHL/VSHLQ:29:result_uint64x1 [] = { 0,  }
+VSHL/VSHLQ:30:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHL/VSHLQ:31:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHL/VSHLQ:32:result_float32x2 [] = { 33333333, 33333333,  }
+VSHL/VSHLQ:33:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VSHL/VSHLQ:34:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VSHL/VSHLQ:35:result_int32x4 [] = { 0, 0, 0, 0,  }
+VSHL/VSHLQ:36:result_int64x2 [] = { 0, 0,  }
+VSHL/VSHLQ:37:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VSHL/VSHLQ:38:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VSHL/VSHLQ:39:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VSHL/VSHLQ:40:result_uint64x2 [] = { 0, 0,  }
+VSHL/VSHLQ:41:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHL/VSHLQ:42:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHL/VSHLQ:43:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VSHL/VSHLQ (negative shift amount) output:
+VSHL/VSHLQ:44:result_int8x8 [] = { fffffff8, fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb,  }
+VSHL/VSHLQ:45:result_int16x4 [] = { fffffff8, fffffff8, fffffff9, fffffff9,  }
+VSHL/VSHLQ:46:result_int32x2 [] = { fffffffc, fffffffc,  }
+VSHL/VSHLQ:47:result_int64x1 [] = { ffffffffffffffff,  }
+VSHL/VSHLQ:48:result_uint8x8 [] = { 78, 78, 79, 79, 7a, 7a, 7b, 7b,  }
+VSHL/VSHLQ:49:result_uint16x4 [] = { 7ff8, 7ff8, 7ff9, 7ff9,  }
+VSHL/VSHLQ:50:result_uint32x2 [] = { 3ffffffc, 3ffffffc,  }
+VSHL/VSHLQ:51:result_uint64x1 [] = { fffffffffffffff,  }
+VSHL/VSHLQ:52:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHL/VSHLQ:53:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHL/VSHLQ:54:result_float32x2 [] = { 33333333, 33333333,  }
+VSHL/VSHLQ:55:result_int8x16 [] = { fffffffc, fffffffc, fffffffc, fffffffc, fffffffd, fffffffd, fffffffd, fffffffd, fffffffe, fffffffe, fffffffe, fffffffe, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VSHL/VSHLQ:56:result_int16x8 [] = { ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VSHL/VSHLQ:57:result_int32x4 [] = { fffffffe, fffffffe, fffffffe, fffffffe,  }
+VSHL/VSHLQ:58:result_int64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VSHL/VSHLQ:59:result_uint8x16 [] = { 3c, 3c, 3c, 3c, 3d, 3d, 3d, 3d, 3e, 3e, 3e, 3e, 3f, 3f, 3f, 3f,  }
+VSHL/VSHLQ:60:result_uint16x8 [] = { 7ff, 7ff, 7ff, 7ff, 7ff, 7ff, 7ff, 7ff,  }
+VSHL/VSHLQ:61:result_uint32x4 [] = { 1ffffffe, 1ffffffe, 1ffffffe, 1ffffffe,  }
+VSHL/VSHLQ:62:result_uint64x2 [] = { 7ffffffffffffff, 7ffffffffffffff,  }
+VSHL/VSHLQ:63:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHL/VSHLQ:64:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHL/VSHLQ:65:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VSHL_N output:
+VSHL_N:0:result_int8x8 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6, ffffffe8, ffffffea, ffffffec, ffffffee,  }
+VSHL_N:1:result_int16x4 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6,  }
+VSHL_N:2:result_int32x2 [] = { ffffff80, ffffff88,  }
+VSHL_N:3:result_int64x1 [] = { ffffffffffffffc0,  }
+VSHL_N:4:result_uint8x8 [] = { c0, c4, c8, cc, d0, d4, d8, dc,  }
+VSHL_N:5:result_uint16x4 [] = { ff00, ff10, ff20, ff30,  }
+VSHL_N:6:result_uint32x2 [] = { ffffff80, ffffff88,  }
+VSHL_N:7:result_uint64x1 [] = { ffffffffffffffe0,  }
+VSHL_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHL_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHL_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSHL_N:11:result_int8x16 [] = { 0, 20, 40, 60, ffffff80, ffffffa0, ffffffc0, ffffffe0, 0, 20, 40, 60, ffffff80, ffffffa0, ffffffc0, ffffffe0,  }
+VSHL_N:12:result_int16x8 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6, ffffffe8, ffffffea, ffffffec, ffffffee,  }
+VSHL_N:13:result_int32x4 [] = { ffffffc0, ffffffc4, ffffffc8, ffffffcc,  }
+VSHL_N:14:result_int64x2 [] = { ffffffffffffffc0, ffffffffffffffc4,  }
+VSHL_N:15:result_uint8x16 [] = { c0, c4, c8, cc, d0, d4, d8, dc, e0, e4, e8, ec, f0, f4, f8, fc,  }
+VSHL_N:16:result_uint16x8 [] = { ff80, ff88, ff90, ff98, ffa0, ffa8, ffb0, ffb8,  }
+VSHL_N:17:result_uint32x4 [] = { ffffffc0, ffffffc4, ffffffc8, ffffffcc,  }
+VSHL_N:18:result_uint64x2 [] = { ffffffffffffffe0, ffffffffffffffe2,  }
+VSHL_N:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHL_N:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHL_N:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQSHL/VQSHLQ (with input = 0) cumulative saturation output:
+VQSHL/VQSHLQ:0:vqshl_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:1:vqshl_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:2:vqshl_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:3:vqshl_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:4:vqshl_u8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:5:vqshl_u16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:6:vqshl_u32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:7:vqshl_u64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:8:vqshlq_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:9:vqshlq_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:10:vqshlq_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:11:vqshlq_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:12:vqshlq_u8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:13:vqshlq_u16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:14:vqshlq_u32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:15:vqshlq_u64 Neon cumulative saturation 0
+
+VQSHL/VQSHLQ (with input = 0) output:
+VQSHL/VQSHLQ:16:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:17:result_int16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:18:result_int32x2 [] = { 0, 0,  }
+VQSHL/VQSHLQ:19:result_int64x1 [] = { 0,  }
+VQSHL/VQSHLQ:20:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:21:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:22:result_uint32x2 [] = { 0, 0,  }
+VQSHL/VQSHLQ:23:result_uint64x1 [] = { 0,  }
+VQSHL/VQSHLQ:24:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:25:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:26:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL/VQSHLQ:27:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:28:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:29:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:30:result_int64x2 [] = { 0, 0,  }
+VQSHL/VQSHLQ:31:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:32:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:33:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:34:result_uint64x2 [] = { 0, 0,  }
+VQSHL/VQSHLQ:35:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:36:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:37:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQSHL/VQSHLQ (input 0 and negative shift amount) cumulative saturation output:
+VQSHL/VQSHLQ:38:vqshl_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:39:vqshl_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:40:vqshl_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:41:vqshl_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:42:vqshl_u8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:43:vqshl_u16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:44:vqshl_u32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:45:vqshl_u64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:46:vqshlq_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:47:vqshlq_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:48:vqshlq_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:49:vqshlq_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:50:vqshlq_u8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:51:vqshlq_u16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:52:vqshlq_u32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:53:vqshlq_u64 Neon cumulative saturation 0
+
+VQSHL/VQSHLQ (input 0 and negative shift amount) output:
+VQSHL/VQSHLQ:54:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:55:result_int16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:56:result_int32x2 [] = { 0, 0,  }
+VQSHL/VQSHLQ:57:result_int64x1 [] = { 0,  }
+VQSHL/VQSHLQ:58:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:59:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:60:result_uint32x2 [] = { 0, 0,  }
+VQSHL/VQSHLQ:61:result_uint64x1 [] = { 0,  }
+VQSHL/VQSHLQ:62:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:63:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:64:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL/VQSHLQ:65:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:66:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:67:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:68:result_int64x2 [] = { 0, 0,  }
+VQSHL/VQSHLQ:69:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:70:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:71:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:72:result_uint64x2 [] = { 0, 0,  }
+VQSHL/VQSHLQ:73:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:74:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:75:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQSHL/VQSHLQ cumulative saturation output:
+VQSHL/VQSHLQ:76:vqshl_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:77:vqshl_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:78:vqshl_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:79:vqshl_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:80:vqshl_u8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:81:vqshl_u16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:82:vqshl_u32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:83:vqshl_u64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:84:vqshlq_s8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:85:vqshlq_s16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:86:vqshlq_s32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:87:vqshlq_s64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:88:vqshlq_u8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:89:vqshlq_u16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:90:vqshlq_u32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:91:vqshlq_u64 Neon cumulative saturation 1
+
+VQSHL/VQSHLQ output:
+VQSHL/VQSHLQ:92:result_int8x8 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6, ffffffe8, ffffffea, ffffffec, ffffffee,  }
+VQSHL/VQSHLQ:93:result_int16x4 [] = { ffffff80, ffffff88, ffffff90, ffffff98,  }
+VQSHL/VQSHLQ:94:result_int32x2 [] = { fffff000, fffff100,  }
+VQSHL/VQSHLQ:95:result_int64x1 [] = { fffffffffffffffe,  }
+VQSHL/VQSHLQ:96:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL/VQSHLQ:97:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHL/VQSHLQ:98:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:99:result_uint64x1 [] = { 1ffffffffffffffe,  }
+VQSHL/VQSHLQ:100:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:101:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:102:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL/VQSHLQ:103:result_int8x16 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQSHL/VQSHLQ:104:result_int16x8 [] = { ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQSHL/VQSHLQ:105:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VQSHL/VQSHLQ:106:result_int64x2 [] = { 8000000000000000, 8000000000000000,  }
+VQSHL/VQSHLQ:107:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL/VQSHLQ:108:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQSHL/VQSHLQ:109:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:110:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQSHL/VQSHLQ:111:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:112:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:113:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQSHL/VQSHLQ (negative shift amount) cumulative saturation output:
+VQSHL/VQSHLQ:114:vqshl_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:115:vqshl_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:116:vqshl_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:117:vqshl_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:118:vqshl_u8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:119:vqshl_u16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:120:vqshl_u32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:121:vqshl_u64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:122:vqshlq_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:123:vqshlq_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:124:vqshlq_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:125:vqshlq_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:126:vqshlq_u8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:127:vqshlq_u16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:128:vqshlq_u32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:129:vqshlq_u64 Neon cumulative saturation 0
+
+VQSHL/VQSHLQ (negative shift amount) output:
+VQSHL/VQSHLQ:130:result_int8x8 [] = { fffffff8, fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb,  }
+VQSHL/VQSHLQ:131:result_int16x4 [] = { fffffffc, fffffffc, fffffffc, fffffffc,  }
+VQSHL/VQSHLQ:132:result_int32x2 [] = { fffffffe, fffffffe,  }
+VQSHL/VQSHLQ:133:result_int64x1 [] = { ffffffffffffffff,  }
+VQSHL/VQSHLQ:134:result_uint8x8 [] = { 78, 78, 79, 79, 7a, 7a, 7b, 7b,  }
+VQSHL/VQSHLQ:135:result_uint16x4 [] = { 3ffc, 3ffc, 3ffc, 3ffc,  }
+VQSHL/VQSHLQ:136:result_uint32x2 [] = { 1ffffffe, 1ffffffe,  }
+VQSHL/VQSHLQ:137:result_uint64x1 [] = { fffffffffffffff,  }
+VQSHL/VQSHLQ:138:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:139:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:140:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL/VQSHLQ:141:result_int8x16 [] = { ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:142:result_int16x8 [] = { ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:143:result_int32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:144:result_int64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQSHL/VQSHLQ:145:result_uint8x16 [] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  }
+VQSHL/VQSHLQ:146:result_uint16x8 [] = { 1f, 1f, 1f, 1f, 1f, 1f, 1f, 1f,  }
+VQSHL/VQSHLQ:147:result_uint32x4 [] = { 7ffff, 7ffff, 7ffff, 7ffff,  }
+VQSHL/VQSHLQ:148:result_uint64x2 [] = { fffffffffff, fffffffffff,  }
+VQSHL/VQSHLQ:149:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:150:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:151:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQSHL/VQSHLQ (large shift amount, negative input) cumulative saturation output:
+VQSHL/VQSHLQ:152:vqshl_s8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:153:vqshl_s16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:154:vqshl_s32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:155:vqshl_s64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:156:vqshl_u8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:157:vqshl_u16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:158:vqshl_u32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:159:vqshl_u64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:160:vqshlq_s8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:161:vqshlq_s16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:162:vqshlq_s32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:163:vqshlq_s64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:164:vqshlq_u8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:165:vqshlq_u16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:166:vqshlq_u32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:167:vqshlq_u64 Neon cumulative saturation 1
+
+VQSHL/VQSHLQ (large shift amount, negative input) output:
+VQSHL/VQSHLQ:168:result_int8x8 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQSHL/VQSHLQ:169:result_int16x4 [] = { ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQSHL/VQSHLQ:170:result_int32x2 [] = { 80000000, 80000000,  }
+VQSHL/VQSHLQ:171:result_int64x1 [] = { 8000000000000000,  }
+VQSHL/VQSHLQ:172:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL/VQSHLQ:173:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHL/VQSHLQ:174:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:175:result_uint64x1 [] = { ffffffffffffffff,  }
+VQSHL/VQSHLQ:176:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:177:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:178:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL/VQSHLQ:179:result_int8x16 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQSHL/VQSHLQ:180:result_int16x8 [] = { ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQSHL/VQSHLQ:181:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VQSHL/VQSHLQ:182:result_int64x2 [] = { 8000000000000000, 8000000000000000,  }
+VQSHL/VQSHLQ:183:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL/VQSHLQ:184:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQSHL/VQSHLQ:185:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:186:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQSHL/VQSHLQ:187:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:188:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:189:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQSHL/VQSHLQ (check cumulative saturation) cumulative saturation output:
+VQSHL/VQSHLQ:190:vqshl_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:191:vqshl_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:192:vqshl_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:193:vqshl_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:194:vqshl_u8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:195:vqshl_u16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:196:vqshl_u32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:197:vqshl_u64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:198:vqshlq_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:199:vqshlq_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:200:vqshlq_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:201:vqshlq_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:202:vqshlq_u8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:203:vqshlq_u16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:204:vqshlq_u32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:205:vqshlq_u64 Neon cumulative saturation 0
+
+VQSHL/VQSHLQ (check cumulative saturation) output:
+VQSHL/VQSHLQ:206:result_int8x8 [] = { 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f,  }
+VQSHL/VQSHLQ:207:result_int16x4 [] = { 3fff, 3fff, 3fff, 3fff,  }
+VQSHL/VQSHLQ:208:result_int32x2 [] = { 3fffffff, 3fffffff,  }
+VQSHL/VQSHLQ:209:result_int64x1 [] = { 3fffffffffffffff,  }
+VQSHL/VQSHLQ:210:result_uint8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHL/VQSHLQ:211:result_uint16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQSHL/VQSHLQ:212:result_uint32x2 [] = { 7fffffff, 7fffffff,  }
+VQSHL/VQSHLQ:213:result_uint64x1 [] = { 7fffffffffffffff,  }
+VQSHL/VQSHLQ:214:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:215:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:216:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL/VQSHLQ:217:result_int8x16 [] = { 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f,  }
+VQSHL/VQSHLQ:218:result_int16x8 [] = { 3fff, 3fff, 3fff, 3fff, 3fff, 3fff, 3fff, 3fff,  }
+VQSHL/VQSHLQ:219:result_int32x4 [] = { 3fffffff, 3fffffff, 3fffffff, 3fffffff,  }
+VQSHL/VQSHLQ:220:result_int64x2 [] = { 3fffffffffffffff, 3fffffffffffffff,  }
+VQSHL/VQSHLQ:221:result_uint8x16 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHL/VQSHLQ:222:result_uint16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQSHL/VQSHLQ:223:result_uint32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQSHL/VQSHLQ:224:result_uint64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+VQSHL/VQSHLQ:225:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:226:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:227:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQSHL/VQSHLQ (large shift amount, positive input) cumulative saturation output:
+VQSHL/VQSHLQ:228:vqshl_s8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:229:vqshl_s16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:230:vqshl_s32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:231:vqshl_s64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:232:vqshl_u8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:233:vqshl_u16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:234:vqshl_u32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:235:vqshl_u64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:236:vqshlq_s8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:237:vqshlq_s16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:238:vqshlq_s32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:239:vqshlq_s64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:240:vqshlq_u8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:241:vqshlq_u16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:242:vqshlq_u32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:243:vqshlq_u64 Neon cumulative saturation 1
+
+VQSHL/VQSHLQ (large shift amount, positive input) output:
+VQSHL/VQSHLQ:244:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHL/VQSHLQ:245:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQSHL/VQSHLQ:246:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQSHL/VQSHLQ:247:result_int64x1 [] = { 7fffffffffffffff,  }
+VQSHL/VQSHLQ:248:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL/VQSHLQ:249:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHL/VQSHLQ:250:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:251:result_uint64x1 [] = { ffffffffffffffff,  }
+VQSHL/VQSHLQ:252:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:253:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:254:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL/VQSHLQ:255:result_int8x16 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHL/VQSHLQ:256:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQSHL/VQSHLQ:257:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQSHL/VQSHLQ:258:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+VQSHL/VQSHLQ:259:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL/VQSHLQ:260:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQSHL/VQSHLQ:261:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:262:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQSHL/VQSHLQ:263:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:264:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:265:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQSHL/VQSHLQ (check saturation on 64 bits) cumulative saturation output:
+VQSHL/VQSHLQ:266:vqshl_s8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:267:vqshl_s16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:268:vqshl_s32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:269:vqshl_s64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:270:vqshl_u8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:271:vqshl_u16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:272:vqshl_u32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:273:vqshl_u64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:274:vqshlq_s8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:275:vqshlq_s16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:276:vqshlq_s32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:277:vqshlq_s64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:278:vqshlq_u8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:279:vqshlq_u16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:280:vqshlq_u32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:281:vqshlq_u64 Neon cumulative saturation 1
+
+VQSHL/VQSHLQ (check saturation on 64 bits) output:
+VQSHL/VQSHLQ:282:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHL/VQSHLQ:283:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQSHL/VQSHLQ:284:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQSHL/VQSHLQ:285:result_int64x1 [] = { 8000000000000000,  }
+VQSHL/VQSHLQ:286:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL/VQSHLQ:287:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHL/VQSHLQ:288:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:289:result_uint64x1 [] = { ffffffffffffffff,  }
+VQSHL/VQSHLQ:290:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:291:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:292:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL/VQSHLQ:293:result_int8x16 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHL/VQSHLQ:294:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQSHL/VQSHLQ:295:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQSHL/VQSHLQ:296:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+VQSHL/VQSHLQ:297:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL/VQSHLQ:298:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQSHL/VQSHLQ:299:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:300:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQSHL/VQSHLQ:301:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:302:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:303:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQSHL_N/VQSHLQ_N cumulative saturation output:
+VQSHL_N/VQSHLQ_N:0:vqshl_n_s8 Neon cumulative saturation 0
+VQSHL_N/VQSHLQ_N:1:vqshl_n_s16 Neon cumulative saturation 0
+VQSHL_N/VQSHLQ_N:2:vqshl_n_s32 Neon cumulative saturation 0
+VQSHL_N/VQSHLQ_N:3:vqshl_n_s64 Neon cumulative saturation 0
+VQSHL_N/VQSHLQ_N:4:vqshl_n_u8 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:5:vqshl_n_u16 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:6:vqshl_n_u32 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:7:vqshl_n_u64 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:8:vqshlq_n_s8 Neon cumulative saturation 0
+VQSHL_N/VQSHLQ_N:9:vqshlq_n_s16 Neon cumulative saturation 0
+VQSHL_N/VQSHLQ_N:10:vqshlq_n_s32 Neon cumulative saturation 0
+VQSHL_N/VQSHLQ_N:11:vqshlq_n_s64 Neon cumulative saturation 0
+VQSHL_N/VQSHLQ_N:12:vqshlq_n_u8 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:13:vqshlq_n_u16 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:14:vqshlq_n_u32 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:15:vqshlq_n_u64 Neon cumulative saturation 1
+
+VQSHL_N/VQSHLQ_N output:
+VQSHL_N/VQSHLQ_N:16:result_int8x8 [] = { ffffffc0, ffffffc4, ffffffc8, ffffffcc, ffffffd0, ffffffd4, ffffffd8, ffffffdc,  }
+VQSHL_N/VQSHLQ_N:17:result_int16x4 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6,  }
+VQSHL_N/VQSHLQ_N:18:result_int32x2 [] = { ffffffe0, ffffffe2,  }
+VQSHL_N/VQSHLQ_N:19:result_int64x1 [] = { ffffffffffffffc0,  }
+VQSHL_N/VQSHLQ_N:20:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL_N/VQSHLQ_N:21:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHL_N/VQSHLQ_N:22:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHL_N/VQSHLQ_N:23:result_uint64x1 [] = { ffffffffffffffff,  }
+VQSHL_N/VQSHLQ_N:24:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL_N/VQSHLQ_N:25:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL_N/VQSHLQ_N:26:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL_N/VQSHLQ_N:27:result_int8x16 [] = { ffffffc0, ffffffc4, ffffffc8, ffffffcc, ffffffd0, ffffffd4, ffffffd8, ffffffdc, ffffffe0, ffffffe4, ffffffe8, ffffffec, fffffff0, fffffff4, fffffff8, fffffffc,  }
+VQSHL_N/VQSHLQ_N:28:result_int16x8 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6, ffffffe8, ffffffea, ffffffec, ffffffee,  }
+VQSHL_N/VQSHLQ_N:29:result_int32x4 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6,  }
+VQSHL_N/VQSHLQ_N:30:result_int64x2 [] = { ffffffffffffffc0, ffffffffffffffc4,  }
+VQSHL_N/VQSHLQ_N:31:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL_N/VQSHLQ_N:32:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQSHL_N/VQSHLQ_N:33:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL_N/VQSHLQ_N:34:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQSHL_N/VQSHLQ_N:35:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL_N/VQSHLQ_N:36:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL_N/VQSHLQ_N:37:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQSHL_N/VQSHLQ_N (check saturation with large positive input) cumulative saturation output:
+VQSHL_N/VQSHLQ_N:38:vqshl_n_s8 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:39:vqshl_n_s16 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:40:vqshl_n_s32 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:41:vqshl_n_s64 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:42:vqshl_n_u8 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:43:vqshl_n_u16 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:44:vqshl_n_u32 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:45:vqshl_n_u64 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:46:vqshlq_n_s8 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:47:vqshlq_n_s16 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:48:vqshlq_n_s32 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:49:vqshlq_n_s64 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:50:vqshlq_n_u8 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:51:vqshlq_n_u16 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:52:vqshlq_n_u32 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:53:vqshlq_n_u64 Neon cumulative saturation 1
+
+VQSHL_N/VQSHLQ_N (check saturation with large positive input) output:
+VQSHL_N/VQSHLQ_N:54:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHL_N/VQSHLQ_N:55:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQSHL_N/VQSHLQ_N:56:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQSHL_N/VQSHLQ_N:57:result_int64x1 [] = { 7fffffffffffffff,  }
+VQSHL_N/VQSHLQ_N:58:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL_N/VQSHLQ_N:59:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHL_N/VQSHLQ_N:60:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHL_N/VQSHLQ_N:61:result_uint64x1 [] = { ffffffffffffffff,  }
+VQSHL_N/VQSHLQ_N:62:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL_N/VQSHLQ_N:63:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL_N/VQSHLQ_N:64:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL_N/VQSHLQ_N:65:result_int8x16 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHL_N/VQSHLQ_N:66:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQSHL_N/VQSHLQ_N:67:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQSHL_N/VQSHLQ_N:68:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+VQSHL_N/VQSHLQ_N:69:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL_N/VQSHLQ_N:70:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQSHL_N/VQSHLQ_N:71:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL_N/VQSHLQ_N:72:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQSHL_N/VQSHLQ_N:73:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL_N/VQSHLQ_N:74:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL_N/VQSHLQ_N:75:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSHL/VRSHLQ (with input = 0) output:
+VRSHL/VRSHLQ:0:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:1:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:2:result_int32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:3:result_int64x1 [] = { 0,  }
+VRSHL/VRSHLQ:4:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:5:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:6:result_uint32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:7:result_uint64x1 [] = { 0,  }
+VRSHL/VRSHLQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:11:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:12:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:13:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:14:result_int64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:15:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:16:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:17:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:18:result_uint64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSHL/VRSHLQ (input 0 and negative shift amount) output:
+VRSHL/VRSHLQ:22:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:23:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:24:result_int32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:25:result_int64x1 [] = { 0,  }
+VRSHL/VRSHLQ:26:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:27:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:28:result_uint32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:29:result_uint64x1 [] = { 0,  }
+VRSHL/VRSHLQ:30:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:31:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:32:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:33:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:34:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:35:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:36:result_int64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:37:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:38:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:39:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:40:result_uint64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:41:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:42:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:43:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSHL/VRSHLQ output:
+VRSHL/VRSHLQ:44:result_int8x8 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6, ffffffe8, ffffffea, ffffffec, ffffffee,  }
+VRSHL/VRSHLQ:45:result_int16x4 [] = { ffffff80, ffffff88, ffffff90, ffffff98,  }
+VRSHL/VRSHLQ:46:result_int32x2 [] = { fffff000, fffff100,  }
+VRSHL/VRSHLQ:47:result_int64x1 [] = { fffffffffffffffe,  }
+VRSHL/VRSHLQ:48:result_uint8x8 [] = { e0, e2, e4, e6, e8, ea, ec, ee,  }
+VRSHL/VRSHLQ:49:result_uint16x4 [] = { ff80, ff88, ff90, ff98,  }
+VRSHL/VRSHLQ:50:result_uint32x2 [] = { fffff000, fffff100,  }
+VRSHL/VRSHLQ:51:result_uint64x1 [] = { 1ffffffffffffffe,  }
+VRSHL/VRSHLQ:52:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:53:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:54:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:55:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:56:result_int16x8 [] = { 0, 1000, 2000, 3000, 4000, 5000, 6000, 7000,  }
+VRSHL/VRSHLQ:57:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:58:result_int64x2 [] = { 0, 8000000000000000,  }
+VRSHL/VRSHLQ:59:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:60:result_uint16x8 [] = { 0, 1000, 2000, 3000, 4000, 5000, 6000, 7000,  }
+VRSHL/VRSHLQ:61:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:62:result_uint64x2 [] = { 0, 8000000000000000,  }
+VRSHL/VRSHLQ:63:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:64:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:65:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSHL/VRSHLQ (negative shift amount) output:
+VRSHL/VRSHLQ:66:result_int8x8 [] = { fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb, fffffffc,  }
+VRSHL/VRSHLQ:67:result_int16x4 [] = { fffffffc, fffffffc, fffffffd, fffffffd,  }
+VRSHL/VRSHLQ:68:result_int32x2 [] = { fffffffe, fffffffe,  }
+VRSHL/VRSHLQ:69:result_int64x1 [] = { ffffffffffffffff,  }
+VRSHL/VRSHLQ:70:result_uint8x8 [] = { 78, 79, 79, 7a, 7a, 7b, 7b, 7c,  }
+VRSHL/VRSHLQ:71:result_uint16x4 [] = { 3ffc, 3ffc, 3ffd, 3ffd,  }
+VRSHL/VRSHLQ:72:result_uint32x2 [] = { 1ffffffe, 1ffffffe,  }
+VRSHL/VRSHLQ:73:result_uint64x1 [] = { fffffffffffffff,  }
+VRSHL/VRSHLQ:74:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:75:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:76:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:77:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:78:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:79:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:80:result_int64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:81:result_uint8x16 [] = { 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,  }
+VRSHL/VRSHLQ:82:result_uint16x8 [] = { 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSHL/VRSHLQ:83:result_uint32x4 [] = { 80000, 80000, 80000, 80000,  }
+VRSHL/VRSHLQ:84:result_uint64x2 [] = { 100000000000, 100000000000,  }
+VRSHL/VRSHLQ:85:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:86:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:87:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSHL/VRSHLQ (checking round_const overflow: shift by -1) output:
+VRSHL/VRSHLQ:88:result_int8x8 [] = { 40, 40, 40, 40, 40, 40, 40, 40,  }
+VRSHL/VRSHLQ:89:result_int16x4 [] = { 4000, 4000, 4000, 4000,  }
+VRSHL/VRSHLQ:90:result_int32x2 [] = { 40000000, 40000000,  }
+VRSHL/VRSHLQ:91:result_int64x1 [] = { 4000000000000000,  }
+VRSHL/VRSHLQ:92:result_uint8x8 [] = { 80, 80, 80, 80, 80, 80, 80, 80,  }
+VRSHL/VRSHLQ:93:result_uint16x4 [] = { 8000, 8000, 8000, 8000,  }
+VRSHL/VRSHLQ:94:result_uint32x2 [] = { 80000000, 80000000,  }
+VRSHL/VRSHLQ:95:result_uint64x1 [] = { 8000000000000000,  }
+VRSHL/VRSHLQ:96:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:97:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:98:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:99:result_int8x16 [] = { 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40,  }
+VRSHL/VRSHLQ:100:result_int16x8 [] = { 4000, 4000, 4000, 4000, 4000, 4000, 4000, 4000,  }
+VRSHL/VRSHLQ:101:result_int32x4 [] = { 40000000, 40000000, 40000000, 40000000,  }
+VRSHL/VRSHLQ:102:result_int64x2 [] = { 4000000000000000, 4000000000000000,  }
+VRSHL/VRSHLQ:103:result_uint8x16 [] = { 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80,  }
+VRSHL/VRSHLQ:104:result_uint16x8 [] = { 8000, 8000, 8000, 8000, 8000, 8000, 8000, 8000,  }
+VRSHL/VRSHLQ:105:result_uint32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VRSHL/VRSHLQ:106:result_uint64x2 [] = { 8000000000000000, 8000000000000000,  }
+VRSHL/VRSHLQ:107:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:108:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:109:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSHL/VRSHLQ (checking round_const overflow: shift by -3) output:
+VRSHL/VRSHLQ:110:result_int8x8 [] = { 10, 10, 10, 10, 10, 10, 10, 10,  }
+VRSHL/VRSHLQ:111:result_int16x4 [] = { 1000, 1000, 1000, 1000,  }
+VRSHL/VRSHLQ:112:result_int32x2 [] = { 10000000, 10000000,  }
+VRSHL/VRSHLQ:113:result_int64x1 [] = { 1000000000000000,  }
+VRSHL/VRSHLQ:114:result_uint8x8 [] = { 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSHL/VRSHLQ:115:result_uint16x4 [] = { 2000, 2000, 2000, 2000,  }
+VRSHL/VRSHLQ:116:result_uint32x2 [] = { 20000000, 20000000,  }
+VRSHL/VRSHLQ:117:result_uint64x1 [] = { 2000000000000000,  }
+VRSHL/VRSHLQ:118:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:119:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:120:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:121:result_int8x16 [] = { 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10,  }
+VRSHL/VRSHLQ:122:result_int16x8 [] = { 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000,  }
+VRSHL/VRSHLQ:123:result_int32x4 [] = { 10000000, 10000000, 10000000, 10000000,  }
+VRSHL/VRSHLQ:124:result_int64x2 [] = { 1000000000000000, 1000000000000000,  }
+VRSHL/VRSHLQ:125:result_uint8x16 [] = { 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSHL/VRSHLQ:126:result_uint16x8 [] = { 2000, 2000, 2000, 2000, 2000, 2000, 2000, 2000,  }
+VRSHL/VRSHLQ:127:result_uint32x4 [] = { 20000000, 20000000, 20000000, 20000000,  }
+VRSHL/VRSHLQ:128:result_uint64x2 [] = { 2000000000000000, 2000000000000000,  }
+VRSHL/VRSHLQ:129:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:130:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:131:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSHL/VRSHLQ (checking negative shift amount as large as input vector width) output:
+VRSHL/VRSHLQ:132:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:133:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:134:result_int32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:135:result_int64x1 [] = { 0,  }
+VRSHL/VRSHLQ:136:result_uint8x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSHL/VRSHLQ:137:result_uint16x4 [] = { 1, 1, 1, 1,  }
+VRSHL/VRSHLQ:138:result_uint32x2 [] = { 1, 1,  }
+VRSHL/VRSHLQ:139:result_uint64x1 [] = { 1,  }
+VRSHL/VRSHLQ:140:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:141:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:142:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:143:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:144:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:145:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:146:result_int64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:147:result_uint8x16 [] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSHL/VRSHLQ:148:result_uint16x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSHL/VRSHLQ:149:result_uint32x4 [] = { 1, 1, 1, 1,  }
+VRSHL/VRSHLQ:150:result_uint64x2 [] = { 1, 1,  }
+VRSHL/VRSHLQ:151:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:152:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:153:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSHL/VRSHLQ (large shift amount) output:
+VRSHL/VRSHLQ:154:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:155:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:156:result_int32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:157:result_int64x1 [] = { 0,  }
+VRSHL/VRSHLQ:158:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:159:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:160:result_uint32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:161:result_uint64x1 [] = { 0,  }
+VRSHL/VRSHLQ:162:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:163:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:164:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:165:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:166:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:167:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:168:result_int64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:169:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:170:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:171:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:172:result_uint64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:173:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:174:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:175:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSHL/VRSHLQ (large negative shift amount) output:
+VRSHL/VRSHLQ:176:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:177:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:178:result_int32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:179:result_int64x1 [] = { 0,  }
+VRSHL/VRSHLQ:180:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:181:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:182:result_uint32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:183:result_uint64x1 [] = { 0,  }
+VRSHL/VRSHLQ:184:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:185:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:186:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:187:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:188:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:189:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:190:result_int64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:191:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:192:result_uint16x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSHL/VRSHLQ:193:result_uint32x4 [] = { 1, 1, 1, 1,  }
+VRSHL/VRSHLQ:194:result_uint64x2 [] = { 1, 1,  }
+VRSHL/VRSHLQ:195:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:196:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:197:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VLD2/VLD2Q chunk 0 output:
+VLD2/VLD2Q:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD2/VLD2Q:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD2/VLD2Q:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD2/VLD2Q:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD2/VLD2Q:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VLD2/VLD2Q:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD2/VLD2Q:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD2/VLD2Q:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD2/VLD2Q:8:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VLD2/VLD2Q:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD2/VLD2Q:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD2/VLD2Q:11:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD2/VLD2Q:12:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD2/VLD2Q:13:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD2/VLD2Q:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2/VLD2Q:15:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD2/VLD2Q:16:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VLD2/VLD2Q:17:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD2/VLD2Q:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2/VLD2Q:19:result_poly8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD2/VLD2Q:20:result_poly16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VLD2/VLD2Q:21:result_float32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+
+VLD2/VLD2Q chunk 1 output:
+VLD2/VLD2Q:22:result_int8x8 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD2/VLD2Q:23:result_int16x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD2/VLD2Q:24:result_int32x2 [] = { fffffff2, fffffff3,  }
+VLD2/VLD2Q:25:result_int64x1 [] = { fffffffffffffff1,  }
+VLD2/VLD2Q:26:result_uint8x8 [] = { f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD2/VLD2Q:27:result_uint16x4 [] = { fff4, fff5, fff6, fff7,  }
+VLD2/VLD2Q:28:result_uint32x2 [] = { fffffff2, fffffff3,  }
+VLD2/VLD2Q:29:result_uint64x1 [] = { fffffffffffffff1,  }
+VLD2/VLD2Q:30:result_poly8x8 [] = { f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD2/VLD2Q:31:result_poly16x4 [] = { fff4, fff5, fff6, fff7,  }
+VLD2/VLD2Q:32:result_float32x2 [] = { c1600000, c1500000,  }
+VLD2/VLD2Q:33:result_int8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD2/VLD2Q:34:result_int16x8 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD2/VLD2Q:35:result_int32x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD2/VLD2Q:36:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2/VLD2Q:37:result_uint8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD2/VLD2Q:38:result_uint16x8 [] = { fff8, fff9, fffa, fffb, fffc, fffd, fffe, ffff,  }
+VLD2/VLD2Q:39:result_uint32x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD2/VLD2Q:40:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2/VLD2Q:41:result_poly8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD2/VLD2Q:42:result_poly16x8 [] = { fff8, fff9, fffa, fffb, fffc, fffd, fffe, ffff,  }
+VLD2/VLD2Q:43:result_float32x4 [] = { c1400000, c1300000, c1200000, c1100000,  }
+
+VLD3/VLD3Q chunk 0 output:
+VLD3/VLD3Q:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD3/VLD3Q:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD3/VLD3Q:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD3/VLD3Q:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD3/VLD3Q:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VLD3/VLD3Q:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD3/VLD3Q:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD3/VLD3Q:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD3/VLD3Q:8:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VLD3/VLD3Q:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD3/VLD3Q:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD3/VLD3Q:11:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD3/VLD3Q:12:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD3/VLD3Q:13:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD3/VLD3Q:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3/VLD3Q:15:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD3/VLD3Q:16:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VLD3/VLD3Q:17:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD3/VLD3Q:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3/VLD3Q:19:result_poly8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD3/VLD3Q:20:result_poly16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VLD3/VLD3Q:21:result_float32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+
+VLD3/VLD3Q chunk 1 output:
+VLD3/VLD3Q:22:result_int8x8 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD3/VLD3Q:23:result_int16x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD3/VLD3Q:24:result_int32x2 [] = { fffffff2, fffffff3,  }
+VLD3/VLD3Q:25:result_int64x1 [] = { fffffffffffffff1,  }
+VLD3/VLD3Q:26:result_uint8x8 [] = { f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD3/VLD3Q:27:result_uint16x4 [] = { fff4, fff5, fff6, fff7,  }
+VLD3/VLD3Q:28:result_uint32x2 [] = { fffffff2, fffffff3,  }
+VLD3/VLD3Q:29:result_uint64x1 [] = { fffffffffffffff1,  }
+VLD3/VLD3Q:30:result_poly8x8 [] = { f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD3/VLD3Q:31:result_poly16x4 [] = { fff4, fff5, fff6, fff7,  }
+VLD3/VLD3Q:32:result_float32x2 [] = { c1600000, c1500000,  }
+VLD3/VLD3Q:33:result_int8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD3/VLD3Q:34:result_int16x8 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD3/VLD3Q:35:result_int32x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD3/VLD3Q:36:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3/VLD3Q:37:result_uint8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD3/VLD3Q:38:result_uint16x8 [] = { fff8, fff9, fffa, fffb, fffc, fffd, fffe, ffff,  }
+VLD3/VLD3Q:39:result_uint32x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD3/VLD3Q:40:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3/VLD3Q:41:result_poly8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD3/VLD3Q:42:result_poly16x8 [] = { fff8, fff9, fffa, fffb, fffc, fffd, fffe, ffff,  }
+VLD3/VLD3Q:43:result_float32x4 [] = { c1400000, c1300000, c1200000, c1100000,  }
+
+VLD3/VLD3Q chunk 2 output:
+VLD3/VLD3Q:44:result_int8x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD3/VLD3Q:45:result_int16x4 [] = { fffffff8, fffffff9, fffffffa, fffffffb,  }
+VLD3/VLD3Q:46:result_int32x2 [] = { fffffff4, fffffff5,  }
+VLD3/VLD3Q:47:result_int64x1 [] = { fffffffffffffff2,  }
+VLD3/VLD3Q:48:result_uint8x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD3/VLD3Q:49:result_uint16x4 [] = { fff8, fff9, fffa, fffb,  }
+VLD3/VLD3Q:50:result_uint32x2 [] = { fffffff4, fffffff5,  }
+VLD3/VLD3Q:51:result_uint64x1 [] = { fffffffffffffff2,  }
+VLD3/VLD3Q:52:result_poly8x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD3/VLD3Q:53:result_poly16x4 [] = { fff8, fff9, fffa, fffb,  }
+VLD3/VLD3Q:54:result_float32x2 [] = { c1400000, c1300000,  }
+VLD3/VLD3Q:55:result_int8x16 [] = { 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 1a, 1b, 1c, 1d, 1e, 1f,  }
+VLD3/VLD3Q:56:result_int16x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD3/VLD3Q:57:result_int32x4 [] = { fffffff8, fffffff9, fffffffa, fffffffb,  }
+VLD3/VLD3Q:58:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3/VLD3Q:59:result_uint8x16 [] = { 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 1a, 1b, 1c, 1d, 1e, 1f,  }
+VLD3/VLD3Q:60:result_uint16x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD3/VLD3Q:61:result_uint32x4 [] = { fffffff8, fffffff9, fffffffa, fffffffb,  }
+VLD3/VLD3Q:62:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3/VLD3Q:63:result_poly8x16 [] = { 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 1a, 1b, 1c, 1d, 1e, 1f,  }
+VLD3/VLD3Q:64:result_poly16x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD3/VLD3Q:65:result_float32x4 [] = { c1000000, c0e00000, c0c00000, c0a00000,  }
+
+VLD4/VLD4Q chunk 0 output:
+VLD4/VLD4Q:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD4/VLD4Q:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4/VLD4Q:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD4/VLD4Q:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD4/VLD4Q:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VLD4/VLD4Q:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4/VLD4Q:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD4/VLD4Q:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD4/VLD4Q:8:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VLD4/VLD4Q:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4/VLD4Q:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD4/VLD4Q:11:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD4/VLD4Q:12:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD4/VLD4Q:13:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4/VLD4Q:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4/VLD4Q:15:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD4/VLD4Q:16:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VLD4/VLD4Q:17:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4/VLD4Q:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4/VLD4Q:19:result_poly8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD4/VLD4Q:20:result_poly16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VLD4/VLD4Q:21:result_float32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+
+VLD4/VLD4Q chunk 1 output:
+VLD4/VLD4Q:22:result_int8x8 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD4/VLD4Q:23:result_int16x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD4/VLD4Q:24:result_int32x2 [] = { fffffff2, fffffff3,  }
+VLD4/VLD4Q:25:result_int64x1 [] = { fffffffffffffff1,  }
+VLD4/VLD4Q:26:result_uint8x8 [] = { f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD4/VLD4Q:27:result_uint16x4 [] = { fff4, fff5, fff6, fff7,  }
+VLD4/VLD4Q:28:result_uint32x2 [] = { fffffff2, fffffff3,  }
+VLD4/VLD4Q:29:result_uint64x1 [] = { fffffffffffffff1,  }
+VLD4/VLD4Q:30:result_poly8x8 [] = { f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD4/VLD4Q:31:result_poly16x4 [] = { fff4, fff5, fff6, fff7,  }
+VLD4/VLD4Q:32:result_float32x2 [] = { c1600000, c1500000,  }
+VLD4/VLD4Q:33:result_int8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:34:result_int16x8 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD4/VLD4Q:35:result_int32x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD4/VLD4Q:36:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4/VLD4Q:37:result_uint8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:38:result_uint16x8 [] = { fff8, fff9, fffa, fffb, fffc, fffd, fffe, ffff,  }
+VLD4/VLD4Q:39:result_uint32x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD4/VLD4Q:40:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4/VLD4Q:41:result_poly8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:42:result_poly16x8 [] = { fff8, fff9, fffa, fffb, fffc, fffd, fffe, ffff,  }
+VLD4/VLD4Q:43:result_float32x4 [] = { c1400000, c1300000, c1200000, c1100000,  }
+
+VLD4/VLD4Q chunk 2 output:
+VLD4/VLD4Q:44:result_int8x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD4/VLD4Q:45:result_int16x4 [] = { fffffff8, fffffff9, fffffffa, fffffffb,  }
+VLD4/VLD4Q:46:result_int32x2 [] = { fffffff4, fffffff5,  }
+VLD4/VLD4Q:47:result_int64x1 [] = { fffffffffffffff2,  }
+VLD4/VLD4Q:48:result_uint8x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD4/VLD4Q:49:result_uint16x4 [] = { fff8, fff9, fffa, fffb,  }
+VLD4/VLD4Q:50:result_uint32x2 [] = { fffffff4, fffffff5,  }
+VLD4/VLD4Q:51:result_uint64x1 [] = { fffffffffffffff2,  }
+VLD4/VLD4Q:52:result_poly8x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD4/VLD4Q:53:result_poly16x4 [] = { fff8, fff9, fffa, fffb,  }
+VLD4/VLD4Q:54:result_float32x2 [] = { c1400000, c1300000,  }
+VLD4/VLD4Q:55:result_int8x16 [] = { 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 1a, 1b, 1c, 1d, 1e, 1f,  }
+VLD4/VLD4Q:56:result_int16x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD4/VLD4Q:57:result_int32x4 [] = { fffffff8, fffffff9, fffffffa, fffffffb,  }
+VLD4/VLD4Q:58:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4/VLD4Q:59:result_uint8x16 [] = { 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 1a, 1b, 1c, 1d, 1e, 1f,  }
+VLD4/VLD4Q:60:result_uint16x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD4/VLD4Q:61:result_uint32x4 [] = { fffffff8, fffffff9, fffffffa, fffffffb,  }
+VLD4/VLD4Q:62:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4/VLD4Q:63:result_poly8x16 [] = { 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 1a, 1b, 1c, 1d, 1e, 1f,  }
+VLD4/VLD4Q:64:result_poly16x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD4/VLD4Q:65:result_float32x4 [] = { c1000000, c0e00000, c0c00000, c0a00000,  }
+
+VLD4/VLD4Q chunk 3 output:
+VLD4/VLD4Q:66:result_int8x8 [] = { 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:67:result_int16x4 [] = { fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD4/VLD4Q:68:result_int32x2 [] = { fffffff6, fffffff7,  }
+VLD4/VLD4Q:69:result_int64x1 [] = { fffffffffffffff3,  }
+VLD4/VLD4Q:70:result_uint8x8 [] = { 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:71:result_uint16x4 [] = { fffc, fffd, fffe, ffff,  }
+VLD4/VLD4Q:72:result_uint32x2 [] = { fffffff6, fffffff7,  }
+VLD4/VLD4Q:73:result_uint64x1 [] = { fffffffffffffff3,  }
+VLD4/VLD4Q:74:result_poly8x8 [] = { 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:75:result_poly16x4 [] = { fffc, fffd, fffe, ffff,  }
+VLD4/VLD4Q:76:result_float32x2 [] = { c1200000, c1100000,  }
+VLD4/VLD4Q:77:result_int8x16 [] = { 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 2a, 2b, 2c, 2d, 2e, 2f,  }
+VLD4/VLD4Q:78:result_int16x8 [] = { 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:79:result_int32x4 [] = { fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD4/VLD4Q:80:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4/VLD4Q:81:result_uint8x16 [] = { 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 2a, 2b, 2c, 2d, 2e, 2f,  }
+VLD4/VLD4Q:82:result_uint16x8 [] = { 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:83:result_uint32x4 [] = { fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD4/VLD4Q:84:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4/VLD4Q:85:result_poly8x16 [] = { 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 2a, 2b, 2c, 2d, 2e, 2f,  }
+VLD4/VLD4Q:86:result_poly16x8 [] = { 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:87:result_float32x4 [] = { c0800000, c0400000, c0000000, bf800000,  }
+
+VDUP_LANE/VDUP_LANEQ output:
+VDUP_LANE/VDUP_LANEQ:0:result_int8x8 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VDUP_LANE/VDUP_LANEQ:1:result_int16x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VDUP_LANE/VDUP_LANEQ:2:result_int32x2 [] = { fffffff1, fffffff1,  }
+VDUP_LANE/VDUP_LANEQ:3:result_int64x1 [] = { fffffffffffffff0,  }
+VDUP_LANE/VDUP_LANEQ:4:result_uint8x8 [] = { f7, f7, f7, f7, f7, f7, f7, f7,  }
+VDUP_LANE/VDUP_LANEQ:5:result_uint16x4 [] = { fff3, fff3, fff3, fff3,  }
+VDUP_LANE/VDUP_LANEQ:6:result_uint32x2 [] = { fffffff1, fffffff1,  }
+VDUP_LANE/VDUP_LANEQ:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VDUP_LANE/VDUP_LANEQ:8:result_poly8x8 [] = { f7, f7, f7, f7, f7, f7, f7, f7,  }
+VDUP_LANE/VDUP_LANEQ:9:result_poly16x4 [] = { fff3, fff3, fff3, fff3,  }
+VDUP_LANE/VDUP_LANEQ:10:result_float32x2 [] = { c1700000, c1700000,  }
+VDUP_LANE/VDUP_LANEQ:11:result_int8x16 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VDUP_LANE/VDUP_LANEQ:12:result_int16x8 [] = { fffffff3, fffffff3, fffffff3, fffffff3, fffffff3, fffffff3, fffffff3, fffffff3,  }
+VDUP_LANE/VDUP_LANEQ:13:result_int32x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VDUP_LANE/VDUP_LANEQ:14:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VDUP_LANE/VDUP_LANEQ:15:result_uint8x16 [] = { f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5,  }
+VDUP_LANE/VDUP_LANEQ:16:result_uint16x8 [] = { fff1, fff1, fff1, fff1, fff1, fff1, fff1, fff1,  }
+VDUP_LANE/VDUP_LANEQ:17:result_uint32x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VDUP_LANE/VDUP_LANEQ:18:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VDUP_LANE/VDUP_LANEQ:19:result_poly8x16 [] = { f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5,  }
+VDUP_LANE/VDUP_LANEQ:20:result_poly16x8 [] = { fff1, fff1, fff1, fff1, fff1, fff1, fff1, fff1,  }
+VDUP_LANE/VDUP_LANEQ:21:result_float32x4 [] = { c1700000, c1700000, c1700000, c1700000,  }
+
+VQDMULL_LANE cumulative saturation output:
+VQDMULL_LANE:0:vqdmull_lane_s16 Neon cumulative saturation 0
+VQDMULL_LANE:1:vqdmull_lane_s32 Neon cumulative saturation 0
+
+VQDMULL_LANE output:
+VQDMULL_LANE:2:result_int32x4 [] = { 8000, 8000, 8000, 8000,  }
+VQDMULL_LANE:3:result_int64x2 [] = { 4000, 4000,  }
+
+VQDMULL_LANE (check mul cumulative saturation) cumulative saturation output:
+VQDMULL_LANE:4:vqdmull_lane_s16 Neon cumulative saturation 1
+VQDMULL_LANE:5:vqdmull_lane_s32 Neon cumulative saturation 1
+
+VQDMULL_LANE (check mul cumulative saturation) output:
+VQDMULL_LANE:6:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQDMULL_LANE:7:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+
+VQDMULL_N cumulative saturation output:
+VQDMULL_N:0:vqdmull_n_s16 Neon cumulative saturation 0
+VQDMULL_N:1:vqdmull_n_s32 Neon cumulative saturation 0
+
+VQDMULL_N output:
+VQDMULL_N:2:result_int32x4 [] = { 44000, 44000, 44000, 44000,  }
+VQDMULL_N:3:result_int64x2 [] = { aa000, aa000,  }
+
+VQDMULL_N (check mul cumulative saturation) cumulative saturation output:
+VQDMULL_N:4:vqdmull_n_s16 Neon cumulative saturation 1
+VQDMULL_N:5:vqdmull_n_s32 Neon cumulative saturation 1
+
+VQDMULL_N (check mul cumulative saturation) output:
+VQDMULL_N:6:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQDMULL_N:7:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+
+VST1_LANE/VST1_LANEQ output:
+VST1_LANE/VST1_LANEQ:0:result_int8x8 [] = { fffffff7, 33, 33, 33, 33, 33, 33, 33,  }
+VST1_LANE/VST1_LANEQ:1:result_int16x4 [] = { fffffff3, 3333, 3333, 3333,  }
+VST1_LANE/VST1_LANEQ:2:result_int32x2 [] = { fffffff1, 33333333,  }
+VST1_LANE/VST1_LANEQ:3:result_int64x1 [] = { fffffffffffffff0,  }
+VST1_LANE/VST1_LANEQ:4:result_uint8x8 [] = { f6, 33, 33, 33, 33, 33, 33, 33,  }
+VST1_LANE/VST1_LANEQ:5:result_uint16x4 [] = { fff2, 3333, 3333, 3333,  }
+VST1_LANE/VST1_LANEQ:6:result_uint32x2 [] = { fffffff0, 33333333,  }
+VST1_LANE/VST1_LANEQ:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VST1_LANE/VST1_LANEQ:8:result_poly8x8 [] = { f6, 33, 33, 33, 33, 33, 33, 33,  }
+VST1_LANE/VST1_LANEQ:9:result_poly16x4 [] = { fff2, 3333, 3333, 3333,  }
+VST1_LANE/VST1_LANEQ:10:result_float32x2 [] = { c1700000, 33333333,  }
+VST1_LANE/VST1_LANEQ:11:result_int8x16 [] = { ffffffff, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST1_LANE/VST1_LANEQ:12:result_int16x8 [] = { fffffff5, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VST1_LANE/VST1_LANEQ:13:result_int32x4 [] = { fffffff1, 33333333, 33333333, 33333333,  }
+VST1_LANE/VST1_LANEQ:14:result_int64x2 [] = { fffffffffffffff1, 3333333333333333,  }
+VST1_LANE/VST1_LANEQ:15:result_uint8x16 [] = { fa, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST1_LANE/VST1_LANEQ:16:result_uint16x8 [] = { fff4, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VST1_LANE/VST1_LANEQ:17:result_uint32x4 [] = { fffffff3, 33333333, 33333333, 33333333,  }
+VST1_LANE/VST1_LANEQ:18:result_uint64x2 [] = { fffffffffffffff0, 3333333333333333,  }
+VST1_LANE/VST1_LANEQ:19:result_poly8x16 [] = { fa, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST1_LANE/VST1_LANEQ:20:result_poly16x8 [] = { fff4, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VST1_LANE/VST1_LANEQ:21:result_float32x4 [] = { c1700000, 33333333, 33333333, 33333333,  }
+
+VSUB/VSUBQ output:
+VSUB/VSUBQ:0:result_int8x8 [] = { ffffffee, ffffffef, fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5,  }
+VSUB/VSUBQ:1:result_int16x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VSUB/VSUBQ:2:result_int32x2 [] = { ffffffed, ffffffee,  }
+VSUB/VSUBQ:3:result_int64x1 [] = { ffffffffffffff8c,  }
+VSUB/VSUBQ:4:result_uint8x8 [] = { dc, dd, de, df, e0, e1, e2, e3,  }
+VSUB/VSUBQ:5:result_uint16x4 [] = { ffd2, ffd3, ffd4, ffd5,  }
+VSUB/VSUBQ:6:result_uint32x2 [] = { ffffffc8, ffffffc9,  }
+VSUB/VSUBQ:7:result_uint64x1 [] = { ffffffffffffffee,  }
+VSUB/VSUBQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUB/VSUBQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSUB/VSUBQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSUB/VSUBQ:11:result_int8x16 [] = { fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9,  }
+VSUB/VSUBQ:12:result_int16x8 [] = { 4, 5, 6, 7, 8, 9, a, b,  }
+VSUB/VSUBQ:13:result_int32x4 [] = { e, f, 10, 11,  }
+VSUB/VSUBQ:14:result_int64x2 [] = { ffffffffffffffd8, ffffffffffffffd9,  }
+VSUB/VSUBQ:15:result_uint8x16 [] = { e4, e5, e6, e7, e8, e9, ea, eb, ec, ed, ee, ef, f0, f1, f2, f3,  }
+VSUB/VSUBQ:16:result_uint16x8 [] = { ffed, ffee, ffef, fff0, fff1, fff2, fff3, fff4,  }
+VSUB/VSUBQ:17:result_uint32x4 [] = { ffffffb9, ffffffba, ffffffbb, ffffffbc,  }
+VSUB/VSUBQ:18:result_uint64x2 [] = { ffffffffffffffed, ffffffffffffffee,  }
+VSUB/VSUBQ:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUB/VSUBQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSUB/VSUBQ:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+float32:
+VSUB/VSUBQ:22:result_float32x2 [] = { c00ccccd, c00ccccd,  }
+VSUB/VSUBQ:23:result_float32x4 [] = { c00ccccc, c00ccccc, c00ccccc, c00ccccc,  }
+
+VQADD/VQADDQ cumulative saturation output:
+VQADD/VQADDQ:0:vqadd_s8 Neon cumulative saturation 0
+VQADD/VQADDQ:1:vqadd_s16 Neon cumulative saturation 0
+VQADD/VQADDQ:2:vqadd_s32 Neon cumulative saturation 0
+VQADD/VQADDQ:3:vqadd_s64 Neon cumulative saturation 0
+VQADD/VQADDQ:4:vqadd_u8 Neon cumulative saturation 1
+VQADD/VQADDQ:5:vqadd_u16 Neon cumulative saturation 1
+VQADD/VQADDQ:6:vqadd_u32 Neon cumulative saturation 1
+VQADD/VQADDQ:7:vqadd_u64 Neon cumulative saturation 1
+VQADD/VQADDQ:8:vqaddq_s8 Neon cumulative saturation 0
+VQADD/VQADDQ:9:vqaddq_s16 Neon cumulative saturation 0
+VQADD/VQADDQ:10:vqaddq_s32 Neon cumulative saturation 0
+VQADD/VQADDQ:11:vqaddq_s64 Neon cumulative saturation 0
+VQADD/VQADDQ:12:vqaddq_u8 Neon cumulative saturation 1
+VQADD/VQADDQ:13:vqaddq_u16 Neon cumulative saturation 1
+VQADD/VQADDQ:14:vqaddq_u32 Neon cumulative saturation 1
+VQADD/VQADDQ:15:vqaddq_u64 Neon cumulative saturation 1
+
+VQADD/VQADDQ output:
+VQADD/VQADDQ:16:result_int8x8 [] = { 1, 2, 3, 4, 5, 6, 7, 8,  }
+VQADD/VQADDQ:17:result_int16x4 [] = { 12, 13, 14, 15,  }
+VQADD/VQADDQ:18:result_int32x2 [] = { 23, 24,  }
+VQADD/VQADDQ:19:result_int64x1 [] = { 34,  }
+VQADD/VQADDQ:20:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQADD/VQADDQ:21:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQADD/VQADDQ:22:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQADD/VQADDQ:23:result_uint64x1 [] = { ffffffffffffffff,  }
+VQADD/VQADDQ:24:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQADD/VQADDQ:25:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQADD/VQADDQ:26:result_float32x2 [] = { 33333333, 33333333,  }
+VQADD/VQADDQ:27:result_int8x16 [] = { 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f, 10,  }
+VQADD/VQADDQ:28:result_int16x8 [] = { 12, 13, 14, 15, 16, 17, 18, 19,  }
+VQADD/VQADDQ:29:result_int32x4 [] = { 23, 24, 25, 26,  }
+VQADD/VQADDQ:30:result_int64x2 [] = { 34, 35,  }
+VQADD/VQADDQ:31:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQADD/VQADDQ:32:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQADD/VQADDQ:33:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQADD/VQADDQ:34:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQADD/VQADDQ:35:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQADD/VQADDQ:36:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQADD/VQADDQ:37:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQADD/VQADDQ 64 bits saturation cumulative saturation output:
+VQADD/VQADDQ:38:vqadd_s64 Neon cumulative saturation 0
+VQADD/VQADDQ:39:vqadd_u64 Neon cumulative saturation 0
+VQADD/VQADDQ:40:vqaddq_s64 Neon cumulative saturation 0
+VQADD/VQADDQ:41:vqaddq_u64 Neon cumulative saturation 0
+
+64 bits saturation:
+VQADD/VQADDQ:42:result_int64x1 [] = { fffffffffffffff0,  }
+VQADD/VQADDQ:43:result_uint64x1 [] = { fffffffffffffff0,  }
+VQADD/VQADDQ:44:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VQADD/VQADDQ:45:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+
+VQADD/VQADDQ 64 bits saturation cumulative saturation output:
+VQADD/VQADDQ:46:vqadd_s64 Neon cumulative saturation 0
+VQADD/VQADDQ:47:vqadd_u64 Neon cumulative saturation 1
+VQADD/VQADDQ:48:vqaddq_s64 Neon cumulative saturation 0
+VQADD/VQADDQ:49:vqaddq_u64 Neon cumulative saturation 1
+VQADD/VQADDQ:50:result_int64x1 [] = { 34,  }
+VQADD/VQADDQ:51:result_uint64x1 [] = { ffffffffffffffff,  }
+VQADD/VQADDQ:52:result_int64x2 [] = { 34, 35,  }
+VQADD/VQADDQ:53:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+
+VQADD/VQADDQ 64 bits saturation cumulative saturation output:
+VQADD/VQADDQ:54:vqadd_s64 Neon cumulative saturation 1
+VQADD/VQADDQ:55:vqadd_u64 Neon cumulative saturation 1
+VQADD/VQADDQ:56:vqaddq_s64 Neon cumulative saturation 1
+VQADD/VQADDQ:57:vqaddq_u64 Neon cumulative saturation 1
+VQADD/VQADDQ:58:result_int64x1 [] = { 8000000000000000,  }
+VQADD/VQADDQ:59:result_uint64x1 [] = { ffffffffffffffff,  }
+VQADD/VQADDQ:60:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+VQADD/VQADDQ:61:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+
+less than 64 bits saturation:
+VQADD/VQADDQ:62:vqadd_s8 Neon cumulative saturation 1
+VQADD/VQADDQ:63:vqadd_s16 Neon cumulative saturation 1
+VQADD/VQADDQ:64:vqadd_s32 Neon cumulative saturation 1
+VQADD/VQADDQ:65:vqaddq_s8 Neon cumulative saturation 1
+VQADD/VQADDQ:66:vqaddq_s16 Neon cumulative saturation 1
+VQADD/VQADDQ:67:vqaddq_s32 Neon cumulative saturation 1
+VQADD/VQADDQ:68:result_int8x8 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQADD/VQADDQ:69:result_int16x4 [] = { ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQADD/VQADDQ:70:result_int32x2 [] = { 80000000, 80000000,  }
+VQADD/VQADDQ:71:result_int8x16 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQADD/VQADDQ:72:result_int16x8 [] = { ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQADD/VQADDQ:73:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+
+VQADD/VQADDQ less than 64 bits saturation cumulative saturation output:
+VQADD/VQADDQ:74:vqadd_u8 Neon cumulative saturation 1
+VQADD/VQADDQ:75:vqadd_u16 Neon cumulative saturation 1
+VQADD/VQADDQ:76:vqadd_u32 Neon cumulative saturation 1
+VQADD/VQADDQ:77:vqaddq_u8 Neon cumulative saturation 1
+VQADD/VQADDQ:78:vqaddq_u16 Neon cumulative saturation 1
+VQADD/VQADDQ:79:vqaddq_u32 Neon cumulative saturation 1
+VQADD/VQADDQ:80:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQADD/VQADDQ:81:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQADD/VQADDQ:82:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQADD/VQADDQ:83:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQADD/VQADDQ:84:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQADD/VQADDQ:85:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+
+VABS/VABSQ output:
+VABS/VABSQ:0:result_int8x8 [] = { 10, f, e, d, c, b, a, 9,  }
+VABS/VABSQ:1:result_int16x4 [] = { 10, f, e, d,  }
+VABS/VABSQ:2:result_int32x2 [] = { 10, f,  }
+VABS/VABSQ:3:result_int64x1 [] = { 3333333333333333,  }
+VABS/VABSQ:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABS/VABSQ:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABS/VABSQ:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VABS/VABSQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VABS/VABSQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABS/VABSQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABS/VABSQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VABS/VABSQ:11:result_int8x16 [] = { 10, f, e, d, c, b, a, 9, 8, 7, 6, 5, 4, 3, 2, 1,  }
+VABS/VABSQ:12:result_int16x8 [] = { 10, f, e, d, c, b, a, 9,  }
+VABS/VABSQ:13:result_int32x4 [] = { 10, f, e, d,  }
+VABS/VABSQ:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VABS/VABSQ:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABS/VABSQ:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VABS/VABSQ:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VABS/VABSQ:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VABS/VABSQ:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABS/VABSQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VABS/VABSQ:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+float32:
+VABS/VABSQ:22:result_float32x2 [] = { 40133333, 40133333,  }
+VABS/VABSQ:23:result_float32x4 [] = { 4059999a, 4059999a, 4059999a, 4059999a,  }
+
+VQABS/VQABSQ cumulative saturation output:
+VQABS/VQABSQ:0:vqabs_s8 Neon cumulative saturation 0
+VQABS/VQABSQ:1:vqabs_s16 Neon cumulative saturation 0
+VQABS/VQABSQ:2:vqabs_s32 Neon cumulative saturation 0
+VQABS/VQABSQ:3:vqabsq_s8 Neon cumulative saturation 0
+VQABS/VQABSQ:4:vqabsq_s16 Neon cumulative saturation 0
+VQABS/VQABSQ:5:vqabsq_s32 Neon cumulative saturation 0
+
+VQABS/VQABSQ output:
+VQABS/VQABSQ:6:result_int8x8 [] = { 10, f, e, d, c, b, a, 9,  }
+VQABS/VQABSQ:7:result_int16x4 [] = { 10, f, e, d,  }
+VQABS/VQABSQ:8:result_int32x2 [] = { 10, f,  }
+VQABS/VQABSQ:9:result_int64x1 [] = { 3333333333333333,  }
+VQABS/VQABSQ:10:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQABS/VQABSQ:11:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQABS/VQABSQ:12:result_uint32x2 [] = { 33333333, 33333333,  }
+VQABS/VQABSQ:13:result_uint64x1 [] = { 3333333333333333,  }
+VQABS/VQABSQ:14:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQABS/VQABSQ:15:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQABS/VQABSQ:16:result_float32x2 [] = { 33333333, 33333333,  }
+VQABS/VQABSQ:17:result_int8x16 [] = { 10, f, e, d, c, b, a, 9, 8, 7, 6, 5, 4, 3, 2, 1,  }
+VQABS/VQABSQ:18:result_int16x8 [] = { 10, f, e, d, c, b, a, 9,  }
+VQABS/VQABSQ:19:result_int32x4 [] = { 10, f, e, d,  }
+VQABS/VQABSQ:20:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQABS/VQABSQ:21:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQABS/VQABSQ:22:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQABS/VQABSQ:23:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQABS/VQABSQ:24:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQABS/VQABSQ:25:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQABS/VQABSQ:26:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQABS/VQABSQ:27:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQABS/VQABSQ cumulative saturation output:
+VQABS/VQABSQ:0:vqabs_s8 Neon cumulative saturation 1
+VQABS/VQABSQ:1:vqabs_s16 Neon cumulative saturation 1
+VQABS/VQABSQ:2:vqabs_s32 Neon cumulative saturation 1
+VQABS/VQABSQ:3:vqabsq_s8 Neon cumulative saturation 1
+VQABS/VQABSQ:4:vqabsq_s16 Neon cumulative saturation 1
+VQABS/VQABSQ:5:vqabsq_s32 Neon cumulative saturation 1
+
+VQABS/VQABSQ output:
+VQABS/VQABSQ:6:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQABS/VQABSQ:7:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQABS/VQABSQ:8:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQABS/VQABSQ:9:result_int64x1 [] = { 3333333333333333,  }
+VQABS/VQABSQ:10:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQABS/VQABSQ:11:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQABS/VQABSQ:12:result_uint32x2 [] = { 33333333, 33333333,  }
+VQABS/VQABSQ:13:result_uint64x1 [] = { 3333333333333333,  }
+VQABS/VQABSQ:14:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQABS/VQABSQ:15:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQABS/VQABSQ:16:result_float32x2 [] = { 33333333, 33333333,  }
+VQABS/VQABSQ:17:result_int8x16 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQABS/VQABSQ:18:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQABS/VQABSQ:19:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQABS/VQABSQ:20:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQABS/VQABSQ:21:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQABS/VQABSQ:22:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQABS/VQABSQ:23:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQABS/VQABSQ:24:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQABS/VQABSQ:25:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQABS/VQABSQ:26:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQABS/VQABSQ:27:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VCOMBINE output:
+VCOMBINE:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCOMBINE:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCOMBINE:2:result_int32x2 [] = { 33333333, 33333333,  }
+VCOMBINE:3:result_int64x1 [] = { 3333333333333333,  }
+VCOMBINE:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCOMBINE:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCOMBINE:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VCOMBINE:7:result_uint64x1 [] = { 3333333333333333,  }
+VCOMBINE:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCOMBINE:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCOMBINE:10:result_float32x2 [] = { 33333333, 33333333,  }
+VCOMBINE:11:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, 11, 11, 11, 11, 11, 11, 11, 11,  }
+VCOMBINE:12:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, 22, 22, 22, 22,  }
+VCOMBINE:13:result_int32x4 [] = { fffffff0, fffffff1, 33, 33,  }
+VCOMBINE:14:result_int64x2 [] = { fffffffffffffff0, 44,  }
+VCOMBINE:15:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, 55, 55, 55, 55, 55, 55, 55, 55,  }
+VCOMBINE:16:result_uint16x8 [] = { fff0, fff1, fff2, fff3, 66, 66, 66, 66,  }
+VCOMBINE:17:result_uint32x4 [] = { fffffff0, fffffff1, 77, 77,  }
+VCOMBINE:18:result_uint64x2 [] = { fffffffffffffff0, 88,  }
+VCOMBINE:19:result_poly8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, 55, 55, 55, 55, 55, 55, 55, 55,  }
+VCOMBINE:20:result_poly16x8 [] = { fff0, fff1, fff2, fff3, 66, 66, 66, 66,  }
+VCOMBINE:21:result_float32x4 [] = { c1800000, c1700000, 40533333, 40533333,  }
+
+VMAX/VMAXQ output:
+VMAX/VMAXQ:0:result_int8x8 [] = { fffffff3, fffffff3, fffffff3, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VMAX/VMAXQ:1:result_int16x4 [] = { fffffff2, fffffff2, fffffff2, fffffff3,  }
+VMAX/VMAXQ:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VMAX/VMAXQ:3:result_int64x1 [] = { 3333333333333333,  }
+VMAX/VMAXQ:4:result_uint8x8 [] = { f3, f3, f3, f3, f4, f5, f6, f7,  }
+VMAX/VMAXQ:5:result_uint16x4 [] = { fff1, fff1, fff2, fff3,  }
+VMAX/VMAXQ:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VMAX/VMAXQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VMAX/VMAXQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMAX/VMAXQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMAX/VMAXQ:10:result_float32x2 [] = { c1780000, c1700000,  }
+VMAX/VMAXQ:11:result_int8x16 [] = { fffffff4, fffffff4, fffffff4, fffffff4, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VMAX/VMAXQ:12:result_int16x8 [] = { fffffff3, fffffff3, fffffff3, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VMAX/VMAXQ:13:result_int32x4 [] = { fffffff1, fffffff1, fffffff2, fffffff3,  }
+VMAX/VMAXQ:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMAX/VMAXQ:15:result_uint8x16 [] = { f9, f9, f9, f9, f9, f9, f9, f9, f9, f9, fa, fb, fc, fd, fe, ff,  }
+VMAX/VMAXQ:16:result_uint16x8 [] = { fff2, fff2, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VMAX/VMAXQ:17:result_uint32x4 [] = { fffffff1, fffffff1, fffffff2, fffffff3,  }
+VMAX/VMAXQ:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMAX/VMAXQ:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMAX/VMAXQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMAX/VMAXQ:21:result_float32x4 [] = { c1680000, c1680000, c1600000, c1500000,  }
+VMAX/VMAXQ FP special (NaN):22:result_float32x4 [] = { 7fc00000, 7fc00000, 7fc00000, 7fc00000,  }
+VMAX/VMAXQ FP special (-NaN):23:result_float32x4 [] = { 7fc00000, 7fc00000, 7fc00000, 7fc00000,  }
+VMAX/VMAXQ FP special (inf):24:result_float32x4 [] = { 7f800000, 7f800000, 7f800000, 7f800000,  }
+VMAX/VMAXQ FP special (-inf):25:result_float32x4 [] = { 3f800000, 3f800000, 3f800000, 3f800000,  }
+VMAX/VMAXQ FP special (-0.0):26:result_float32x4 [] = { 0, 0, 0, 0,  }
+VMAX/VMAXQ FP special (-0.0):27:result_float32x4 [] = { 0, 0, 0, 0,  }
+
+VMIN/VMINQ output:
+VMIN/VMINQ:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff3, fffffff3, fffffff3, fffffff3,  }
+VMIN/VMINQ:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff2,  }
+VMIN/VMINQ:2:result_int32x2 [] = { fffffff0, fffffff0,  }
+VMIN/VMINQ:3:result_int64x1 [] = { 3333333333333333,  }
+VMIN/VMINQ:4:result_uint8x8 [] = { f0, f1, f2, f3, f3, f3, f3, f3,  }
+VMIN/VMINQ:5:result_uint16x4 [] = { fff0, fff1, fff1, fff1,  }
+VMIN/VMINQ:6:result_uint32x2 [] = { fffffff0, fffffff0,  }
+VMIN/VMINQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VMIN/VMINQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMIN/VMINQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMIN/VMINQ:10:result_float32x2 [] = { c1800000, c1780000,  }
+VMIN/VMINQ:11:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff4, fffffff4, fffffff4, fffffff4, fffffff4, fffffff4, fffffff4, fffffff4, fffffff4, fffffff4, fffffff4,  }
+VMIN/VMINQ:12:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff3, fffffff3, fffffff3, fffffff3,  }
+VMIN/VMINQ:13:result_int32x4 [] = { fffffff0, fffffff1, fffffff1, fffffff1,  }
+VMIN/VMINQ:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMIN/VMINQ:15:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, f9, f9, f9, f9, f9, f9,  }
+VMIN/VMINQ:16:result_uint16x8 [] = { fff0, fff1, fff2, fff2, fff2, fff2, fff2, fff2,  }
+VMIN/VMINQ:17:result_uint32x4 [] = { fffffff0, fffffff1, fffffff1, fffffff1,  }
+VMIN/VMINQ:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMIN/VMINQ:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMIN/VMINQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMIN/VMINQ:21:result_float32x4 [] = { c1800000, c1700000, c1680000, c1680000,  }
+VMIN/VMINQ FP special (NaN):22:result_float32x4 [] = { 7fc00000, 7fc00000, 7fc00000, 7fc00000,  }
+VMIN/VMINQ FP special (-NaN):23:result_float32x4 [] = { 7fc00000, 7fc00000, 7fc00000, 7fc00000,  }
+VMIN/VMINQ FP special (inf):24:result_float32x4 [] = { 3f800000, 3f800000, 3f800000, 3f800000,  }
+VMIN/VMINQ FP special (-inf):25:result_float32x4 [] = { ff800000, ff800000, ff800000, ff800000,  }
+VMIN/VMINQ FP special (-0.0):26:result_float32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VMIN/VMINQ FP special (-0.0):27:result_float32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+
+VNEG/VNEGQ output:
+VNEG/VNEGQ:0:result_int8x8 [] = { 10, f, e, d, c, b, a, 9,  }
+VNEG/VNEGQ:1:result_int16x4 [] = { 10, f, e, d,  }
+VNEG/VNEGQ:2:result_int32x2 [] = { 10, f,  }
+VNEG/VNEGQ:3:result_int64x1 [] = { 3333333333333333,  }
+VNEG/VNEGQ:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VNEG/VNEGQ:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VNEG/VNEGQ:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VNEG/VNEGQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VNEG/VNEGQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VNEG/VNEGQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VNEG/VNEGQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VNEG/VNEGQ:11:result_int8x16 [] = { 10, f, e, d, c, b, a, 9, 8, 7, 6, 5, 4, 3, 2, 1,  }
+VNEG/VNEGQ:12:result_int16x8 [] = { 10, f, e, d, c, b, a, 9,  }
+VNEG/VNEGQ:13:result_int32x4 [] = { 10, f, e, d,  }
+VNEG/VNEGQ:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VNEG/VNEGQ:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VNEG/VNEGQ:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VNEG/VNEGQ:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VNEG/VNEGQ:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VNEG/VNEGQ:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VNEG/VNEGQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VNEG/VNEGQ:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+float32:
+VNEG/VNEGQ:22:result_float32x2 [] = { c0133333, c0133333,  }
+VNEG/VNEGQ:23:result_float32x4 [] = { c059999a, c059999a, c059999a, c059999a,  }
+
+VQNEG/VQNEGQ cumulative saturation output:
+VQNEG/VQNEGQ:0:vqneg_s8 Neon cumulative saturation 0
+VQNEG/VQNEGQ:1:vqneg_s16 Neon cumulative saturation 0
+VQNEG/VQNEGQ:2:vqneg_s32 Neon cumulative saturation 0
+VQNEG/VQNEGQ:3:vqnegq_s8 Neon cumulative saturation 0
+VQNEG/VQNEGQ:4:vqnegq_s16 Neon cumulative saturation 0
+VQNEG/VQNEGQ:5:vqnegq_s32 Neon cumulative saturation 0
+
+VQNEG/VQNEGQ output:
+VQNEG/VQNEGQ:6:result_int8x8 [] = { 10, f, e, d, c, b, a, 9,  }
+VQNEG/VQNEGQ:7:result_int16x4 [] = { 10, f, e, d,  }
+VQNEG/VQNEGQ:8:result_int32x2 [] = { 10, f,  }
+VQNEG/VQNEGQ:9:result_int64x1 [] = { 3333333333333333,  }
+VQNEG/VQNEGQ:10:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQNEG/VQNEGQ:11:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQNEG/VQNEGQ:12:result_uint32x2 [] = { 33333333, 33333333,  }
+VQNEG/VQNEGQ:13:result_uint64x1 [] = { 3333333333333333,  }
+VQNEG/VQNEGQ:14:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQNEG/VQNEGQ:15:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQNEG/VQNEGQ:16:result_float32x2 [] = { 33333333, 33333333,  }
+VQNEG/VQNEGQ:17:result_int8x16 [] = { 10, f, e, d, c, b, a, 9, 8, 7, 6, 5, 4, 3, 2, 1,  }
+VQNEG/VQNEGQ:18:result_int16x8 [] = { 10, f, e, d, c, b, a, 9,  }
+VQNEG/VQNEGQ:19:result_int32x4 [] = { 10, f, e, d,  }
+VQNEG/VQNEGQ:20:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQNEG/VQNEGQ:21:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQNEG/VQNEGQ:22:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQNEG/VQNEGQ:23:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQNEG/VQNEGQ:24:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQNEG/VQNEGQ:25:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQNEG/VQNEGQ:26:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQNEG/VQNEGQ:27:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQNEG/VQNEGQ cumulative saturation output:
+VQNEG/VQNEGQ:0:vqneg_s8 Neon cumulative saturation 1
+VQNEG/VQNEGQ:1:vqneg_s16 Neon cumulative saturation 1
+VQNEG/VQNEGQ:2:vqneg_s32 Neon cumulative saturation 1
+VQNEG/VQNEGQ:3:vqnegq_s8 Neon cumulative saturation 1
+VQNEG/VQNEGQ:4:vqnegq_s16 Neon cumulative saturation 1
+VQNEG/VQNEGQ:5:vqnegq_s32 Neon cumulative saturation 1
+
+VQNEG/VQNEGQ output:
+VQNEG/VQNEGQ:6:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQNEG/VQNEGQ:7:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQNEG/VQNEGQ:8:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQNEG/VQNEGQ:9:result_int64x1 [] = { 3333333333333333,  }
+VQNEG/VQNEGQ:10:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQNEG/VQNEGQ:11:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQNEG/VQNEGQ:12:result_uint32x2 [] = { 33333333, 33333333,  }
+VQNEG/VQNEGQ:13:result_uint64x1 [] = { 3333333333333333,  }
+VQNEG/VQNEGQ:14:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQNEG/VQNEGQ:15:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQNEG/VQNEGQ:16:result_float32x2 [] = { 33333333, 33333333,  }
+VQNEG/VQNEGQ:17:result_int8x16 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQNEG/VQNEGQ:18:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQNEG/VQNEGQ:19:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQNEG/VQNEGQ:20:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQNEG/VQNEGQ:21:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQNEG/VQNEGQ:22:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQNEG/VQNEGQ:23:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQNEG/VQNEGQ:24:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQNEG/VQNEGQ:25:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQNEG/VQNEGQ:26:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQNEG/VQNEGQ:27:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VMLAL output:
+VMLAL:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMLAL:3:result_int64x1 [] = { 3333333333333333,  }
+VMLAL:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMLAL:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLAL:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMLAL:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL:12:result_int16x8 [] = { ffffe907, ffffe908, ffffe909, ffffe90a, ffffe90b, ffffe90c, ffffe90d, ffffe90e,  }
+VMLAL:13:result_int32x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLAL:14:result_int64x2 [] = { 3e07, 3e08,  }
+VMLAL:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL:16:result_uint16x8 [] = { 3e07, 3e08, 3e09, 3e0a, 3e0b, 3e0c, 3e0d, 3e0e,  }
+VMLAL:17:result_uint32x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLAL:18:result_uint64x2 [] = { 3e07, 3e08,  }
+VMLAL:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLAL:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VMLSL output:
+VMLSL:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMLSL:3:result_int64x1 [] = { 3333333333333333,  }
+VMLSL:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMLSL:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLSL:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMLSL:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL:12:result_int16x8 [] = { 16d9, 16da, 16db, 16dc, 16dd, 16de, 16df, 16e0,  }
+VMLSL:13:result_int32x4 [] = { ffffc1d9, ffffc1da, ffffc1db, ffffc1dc,  }
+VMLSL:14:result_int64x2 [] = { ffffffffffffc1d9, ffffffffffffc1da,  }
+VMLSL:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL:16:result_uint16x8 [] = { c1d9, c1da, c1db, c1dc, c1dd, c1de, c1df, c1e0,  }
+VMLSL:17:result_uint32x4 [] = { ffffc1d9, ffffc1da, ffffc1db, ffffc1dc,  }
+VMLSL:18:result_uint64x2 [] = { ffffffffffffc1d9, ffffffffffffc1da,  }
+VMLSL:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLSL:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VMLAL_LANE output:
+VMLAL_LANE:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_LANE:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL_LANE:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMLAL_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VMLAL_LANE:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_LANE:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL_LANE:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMLAL_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLAL_LANE:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_LANE:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL_LANE:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMLAL_LANE:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_LANE:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLAL_LANE:13:result_int32x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLAL_LANE:14:result_int64x2 [] = { 3e07, 3e08,  }
+VMLAL_LANE:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_LANE:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLAL_LANE:17:result_uint32x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLAL_LANE:18:result_uint64x2 [] = { 3e07, 3e08,  }
+VMLAL_LANE:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_LANE:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLAL_LANE:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VMLSL_LANE output:
+VMLSL_LANE:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_LANE:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL_LANE:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMLSL_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VMLSL_LANE:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_LANE:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL_LANE:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMLSL_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLSL_LANE:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_LANE:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL_LANE:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMLSL_LANE:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_LANE:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLSL_LANE:13:result_int32x4 [] = { ffffc1d9, ffffc1da, ffffc1db, ffffc1dc,  }
+VMLSL_LANE:14:result_int64x2 [] = { ffffffffffffc1d9, ffffffffffffc1da,  }
+VMLSL_LANE:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_LANE:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLSL_LANE:17:result_uint32x4 [] = { ffffc1d9, ffffc1da, ffffc1db, ffffc1dc,  }
+VMLSL_LANE:18:result_uint64x2 [] = { ffffffffffffc1d9, ffffffffffffc1da,  }
+VMLSL_LANE:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_LANE:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLSL_LANE:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VMLAL_N output:
+VMLAL_N:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_N:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL_N:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMLAL_N:3:result_int64x1 [] = { 3333333333333333,  }
+VMLAL_N:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_N:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL_N:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMLAL_N:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLAL_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMLAL_N:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_N:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLAL_N:13:result_int32x4 [] = { 595, 596, 597, 598,  }
+VMLAL_N:14:result_int64x2 [] = { b3a, b3b,  }
+VMLAL_N:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_N:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLAL_N:17:result_uint32x4 [] = { 10df, 10e0, 10e1, 10e2,  }
+VMLAL_N:18:result_uint64x2 [] = { 10df, 10e0,  }
+VMLAL_N:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_N:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLAL_N:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VMLSL_N output:
+VMLSL_N:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_N:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL_N:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMLSL_N:3:result_int64x1 [] = { 3333333333333333,  }
+VMLSL_N:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_N:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL_N:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMLSL_N:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLSL_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMLSL_N:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_N:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLSL_N:13:result_int32x4 [] = { fffffa4b, fffffa4c, fffffa4d, fffffa4e,  }
+VMLSL_N:14:result_int64x2 [] = { fffffffffffff4a6, fffffffffffff4a7,  }
+VMLSL_N:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_N:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLSL_N:17:result_uint32x4 [] = { ffffef01, ffffef02, ffffef03, ffffef04,  }
+VMLSL_N:18:result_uint64x2 [] = { ffffffffffffef01, ffffffffffffef02,  }
+VMLSL_N:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_N:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLSL_N:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VMOVL output:
+VMOVL:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVL:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMOVL:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMOVL:3:result_int64x1 [] = { 3333333333333333,  }
+VMOVL:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVL:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMOVL:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMOVL:7:result_uint64x1 [] = { 3333333333333333,  }
+VMOVL:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMOVL:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMOVL:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVL:12:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VMOVL:13:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VMOVL:14:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VMOVL:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVL:16:result_uint16x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VMOVL:17:result_uint32x4 [] = { fff0, fff1, fff2, fff3,  }
+VMOVL:18:result_uint64x2 [] = { fffffff0, fffffff1,  }
+VMOVL:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVL:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMOVL:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VMOVN output:
+VMOVN:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VMOVN:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VMOVN:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VMOVN:3:result_int64x1 [] = { 3333333333333333,  }
+VMOVN:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VMOVN:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VMOVN:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VMOVN:7:result_uint64x1 [] = { 3333333333333333,  }
+VMOVN:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVN:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMOVN:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMOVN:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVN:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMOVN:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMOVN:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMOVN:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVN:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMOVN:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMOVN:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMOVN:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVN:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMOVN:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VMULL output:
+VMULL:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMULL:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMULL:3:result_int64x1 [] = { 3333333333333333,  }
+VMULL:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMULL:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMULL:7:result_uint64x1 [] = { 3333333333333333,  }
+VMULL:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMULL:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMULL:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL:12:result_int16x8 [] = { 100, e1, c4, a9, 90, 79, 64, 51,  }
+VMULL:13:result_int32x4 [] = { 100, e1, c4, a9,  }
+VMULL:14:result_int64x2 [] = { 100, e1,  }
+VMULL:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL:16:result_uint16x8 [] = { e100, e2e1, e4c4, e6a9, e890, ea79, ec64, ee51,  }
+VMULL:17:result_uint32x4 [] = { ffe00100, ffe200e1, ffe400c4, ffe600a9,  }
+VMULL:18:result_uint64x2 [] = { ffffffe000000100, ffffffe2000000e1,  }
+VMULL:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL:20:result_poly16x8 [] = { 5500, 5501, 5504, 5505, 5510, 5511, 5514, 5515,  }
+VMULL:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VMULL_LANE output:
+VMULL_LANE:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL_LANE:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMULL_LANE:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMULL_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VMULL_LANE:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL_LANE:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMULL_LANE:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMULL_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VMULL_LANE:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL_LANE:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMULL_LANE:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMULL_LANE:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL_LANE:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMULL_LANE:13:result_int32x4 [] = { 4000, 4000, 4000, 4000,  }
+VMULL_LANE:14:result_int64x2 [] = { 2000, 2000,  }
+VMULL_LANE:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL_LANE:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMULL_LANE:17:result_uint32x4 [] = { 4000, 4000, 4000, 4000,  }
+VMULL_LANE:18:result_uint64x2 [] = { 2000, 2000,  }
+VMULL_LANE:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL_LANE:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMULL_LANE:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VREV16 output:
+VREV16:0:result_int8x8 [] = { fffffff1, fffffff0, fffffff3, fffffff2, fffffff5, fffffff4, fffffff7, fffffff6,  }
+VREV16:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VREV16:2:result_int32x2 [] = { 33333333, 33333333,  }
+VREV16:3:result_int64x1 [] = { 3333333333333333,  }
+VREV16:4:result_uint8x8 [] = { f1, f0, f3, f2, f5, f4, f7, f6,  }
+VREV16:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VREV16:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VREV16:7:result_uint64x1 [] = { 3333333333333333,  }
+VREV16:8:result_poly8x8 [] = { f1, f0, f3, f2, f5, f4, f7, f6,  }
+VREV16:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VREV16:10:result_float32x2 [] = { 33333333, 33333333,  }
+VREV16:11:result_int8x16 [] = { fffffff1, fffffff0, fffffff3, fffffff2, fffffff5, fffffff4, fffffff7, fffffff6, fffffff9, fffffff8, fffffffb, fffffffa, fffffffd, fffffffc, ffffffff, fffffffe,  }
+VREV16:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VREV16:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VREV16:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VREV16:15:result_uint8x16 [] = { f1, f0, f3, f2, f5, f4, f7, f6, f9, f8, fb, fa, fd, fc, ff, fe,  }
+VREV16:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VREV16:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VREV16:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VREV16:19:result_poly8x16 [] = { f1, f0, f3, f2, f5, f4, f7, f6, f9, f8, fb, fa, fd, fc, ff, fe,  }
+VREV16:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VREV16:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VREV32 output:
+VREV32:22:result_int8x8 [] = { fffffff3, fffffff2, fffffff1, fffffff0, fffffff7, fffffff6, fffffff5, fffffff4,  }
+VREV32:23:result_int16x4 [] = { fffffff1, fffffff0, fffffff3, fffffff2,  }
+VREV32:24:result_int32x2 [] = { 33333333, 33333333,  }
+VREV32:25:result_int64x1 [] = { 3333333333333333,  }
+VREV32:26:result_uint8x8 [] = { f3, f2, f1, f0, f7, f6, f5, f4,  }
+VREV32:27:result_uint16x4 [] = { fff1, fff0, fff3, fff2,  }
+VREV32:28:result_uint32x2 [] = { 33333333, 33333333,  }
+VREV32:29:result_uint64x1 [] = { 3333333333333333,  }
+VREV32:30:result_poly8x8 [] = { f3, f2, f1, f0, f7, f6, f5, f4,  }
+VREV32:31:result_poly16x4 [] = { fff1, fff0, fff3, fff2,  }
+VREV32:32:result_float32x2 [] = { 33333333, 33333333,  }
+VREV32:33:result_int8x16 [] = { fffffff3, fffffff2, fffffff1, fffffff0, fffffff7, fffffff6, fffffff5, fffffff4, fffffffb, fffffffa, fffffff9, fffffff8, ffffffff, fffffffe, fffffffd, fffffffc,  }
+VREV32:34:result_int16x8 [] = { fffffff1, fffffff0, fffffff3, fffffff2, fffffff5, fffffff4, fffffff7, fffffff6,  }
+VREV32:35:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VREV32:36:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VREV32:37:result_uint8x16 [] = { f3, f2, f1, f0, f7, f6, f5, f4, fb, fa, f9, f8, ff, fe, fd, fc,  }
+VREV32:38:result_uint16x8 [] = { fff1, fff0, fff3, fff2, fff5, fff4, fff7, fff6,  }
+VREV32:39:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VREV32:40:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VREV32:41:result_poly8x16 [] = { f3, f2, f1, f0, f7, f6, f5, f4, fb, fa, f9, f8, ff, fe, fd, fc,  }
+VREV32:42:result_poly16x8 [] = { fff1, fff0, fff3, fff2, fff5, fff4, fff7, fff6,  }
+VREV32:43:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VREV64 output:
+VREV64:44:result_int8x8 [] = { fffffff7, fffffff6, fffffff5, fffffff4, fffffff3, fffffff2, fffffff1, fffffff0,  }
+VREV64:45:result_int16x4 [] = { fffffff3, fffffff2, fffffff1, fffffff0,  }
+VREV64:46:result_int32x2 [] = { fffffff1, fffffff0,  }
+VREV64:47:result_int64x1 [] = { 3333333333333333,  }
+VREV64:48:result_uint8x8 [] = { f7, f6, f5, f4, f3, f2, f1, f0,  }
+VREV64:49:result_uint16x4 [] = { fff3, fff2, fff1, fff0,  }
+VREV64:50:result_uint32x2 [] = { fffffff1, fffffff0,  }
+VREV64:51:result_uint64x1 [] = { 3333333333333333,  }
+VREV64:52:result_poly8x8 [] = { f7, f6, f5, f4, f3, f2, f1, f0,  }
+VREV64:53:result_poly16x4 [] = { fff3, fff2, fff1, fff0,  }
+VREV64:54:result_float32x2 [] = { c1700000, c1800000,  }
+VREV64:55:result_int8x16 [] = { fffffff7, fffffff6, fffffff5, fffffff4, fffffff3, fffffff2, fffffff1, fffffff0, ffffffff, fffffffe, fffffffd, fffffffc, fffffffb, fffffffa, fffffff9, fffffff8,  }
+VREV64:56:result_int16x8 [] = { fffffff3, fffffff2, fffffff1, fffffff0, fffffff7, fffffff6, fffffff5, fffffff4,  }
+VREV64:57:result_int32x4 [] = { fffffff1, fffffff0, fffffff3, fffffff2,  }
+VREV64:58:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VREV64:59:result_uint8x16 [] = { f7, f6, f5, f4, f3, f2, f1, f0, ff, fe, fd, fc, fb, fa, f9, f8,  }
+VREV64:60:result_uint16x8 [] = { fff3, fff2, fff1, fff0, fff7, fff6, fff5, fff4,  }
+VREV64:61:result_uint32x4 [] = { fffffff1, fffffff0, fffffff3, fffffff2,  }
+VREV64:62:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VREV64:63:result_poly8x16 [] = { f7, f6, f5, f4, f3, f2, f1, f0, ff, fe, fd, fc, fb, fa, f9, f8,  }
+VREV64:64:result_poly16x8 [] = { fff3, fff2, fff1, fff0, fff7, fff6, fff5, fff4,  }
+VREV64:65:result_float32x4 [] = { c1700000, c1800000, c1500000, c1600000,  }
+
+VSRA_N output:
+VSRA_N:0:result_int8x8 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VSRA_N:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VSRA_N:2:result_int32x2 [] = { fffffffc, fffffffd,  }
+VSRA_N:3:result_int64x1 [] = { fffffffffffffff0,  }
+VSRA_N:4:result_uint8x8 [] = { 5, 6, 7, 8, 9, a, b, c,  }
+VSRA_N:5:result_uint16x4 [] = { fffc, fffd, fffe, ffff,  }
+VSRA_N:6:result_uint32x2 [] = { fffffff3, fffffff4,  }
+VSRA_N:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VSRA_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSRA_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSRA_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSRA_N:11:result_int8x16 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff, 0, 1, 2, 3, 4, 5, 6, 7,  }
+VSRA_N:12:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VSRA_N:13:result_int32x4 [] = { fffffffc, fffffffd, fffffffe, ffffffff,  }
+VSRA_N:14:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VSRA_N:15:result_uint8x16 [] = { 5, 6, 7, 8, 9, a, b, c, d, e, f, 10, 11, 12, 13, 14,  }
+VSRA_N:16:result_uint16x8 [] = { fffc, fffd, fffe, ffff, 0, 1, 2, 3,  }
+VSRA_N:17:result_uint32x4 [] = { fffffff3, fffffff4, fffffff5, fffffff6,  }
+VSRA_N:18:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VSRA_N:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSRA_N:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSRA_N:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VTRN/VTRNQ chunk 0 output:
+VTRN/VTRNQ:0:result_int8x8 [] = { fffffff0, fffffff1, 11, 11, fffffff2, fffffff3, 11, 11,  }
+VTRN/VTRNQ:1:result_int16x4 [] = { fffffff0, fffffff1, 22, 22,  }
+VTRN/VTRNQ:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VTRN/VTRNQ:3:result_int64x1 [] = { 3333333333333333,  }
+VTRN/VTRNQ:4:result_uint8x8 [] = { f0, f1, 55, 55, f2, f3, 55, 55,  }
+VTRN/VTRNQ:5:result_uint16x4 [] = { fff0, fff1, 66, 66,  }
+VTRN/VTRNQ:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VTRN/VTRNQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VTRN/VTRNQ:8:result_poly8x8 [] = { f0, f1, 55, 55, f2, f3, 55, 55,  }
+VTRN/VTRNQ:9:result_poly16x4 [] = { fff0, fff1, 66, 66,  }
+VTRN/VTRNQ:10:result_float32x2 [] = { c1800000, c1700000,  }
+VTRN/VTRNQ:11:result_int8x16 [] = { fffffff0, fffffff1, 11, 11, fffffff2, fffffff3, 11, 11, fffffff4, fffffff5, 11, 11, fffffff6, fffffff7, 11, 11,  }
+VTRN/VTRNQ:12:result_int16x8 [] = { fffffff0, fffffff1, 22, 22, fffffff2, fffffff3, 22, 22,  }
+VTRN/VTRNQ:13:result_int32x4 [] = { fffffff0, fffffff1, 33, 33,  }
+VTRN/VTRNQ:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTRN/VTRNQ:15:result_uint8x16 [] = { f0, f1, 55, 55, f2, f3, 55, 55, f4, f5, 55, 55, f6, f7, 55, 55,  }
+VTRN/VTRNQ:16:result_uint16x8 [] = { fff0, fff1, 66, 66, fff2, fff3, 66, 66,  }
+VTRN/VTRNQ:17:result_uint32x4 [] = { fffffff0, fffffff1, 77, 77,  }
+VTRN/VTRNQ:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTRN/VTRNQ:19:result_poly8x16 [] = { f0, f1, 55, 55, f2, f3, 55, 55, f4, f5, 55, 55, f6, f7, 55, 55,  }
+VTRN/VTRNQ:20:result_poly16x8 [] = { fff0, fff1, 66, 66, fff2, fff3, 66, 66,  }
+VTRN/VTRNQ:21:result_float32x4 [] = { c1800000, c1700000, 42073333, 42073333,  }
+
+VTRN/VTRNQ chunk 1 output:
+VTRN/VTRNQ:22:result_int8x8 [] = { fffffff4, fffffff5, 11, 11, fffffff6, fffffff7, 11, 11,  }
+VTRN/VTRNQ:23:result_int16x4 [] = { fffffff2, fffffff3, 22, 22,  }
+VTRN/VTRNQ:24:result_int32x2 [] = { 33, 33,  }
+VTRN/VTRNQ:25:result_int64x1 [] = { 3333333333333333,  }
+VTRN/VTRNQ:26:result_uint8x8 [] = { f4, f5, 55, 55, f6, f7, 55, 55,  }
+VTRN/VTRNQ:27:result_uint16x4 [] = { fff2, fff3, 66, 66,  }
+VTRN/VTRNQ:28:result_uint32x2 [] = { 77, 77,  }
+VTRN/VTRNQ:29:result_uint64x1 [] = { 3333333333333333,  }
+VTRN/VTRNQ:30:result_poly8x8 [] = { f4, f5, 55, 55, f6, f7, 55, 55,  }
+VTRN/VTRNQ:31:result_poly16x4 [] = { fff2, fff3, 66, 66,  }
+VTRN/VTRNQ:32:result_float32x2 [] = { 42066666, 42066666,  }
+VTRN/VTRNQ:33:result_int8x16 [] = { fffffff8, fffffff9, 11, 11, fffffffa, fffffffb, 11, 11, fffffffc, fffffffd, 11, 11, fffffffe, ffffffff, 11, 11,  }
+VTRN/VTRNQ:34:result_int16x8 [] = { fffffff4, fffffff5, 22, 22, fffffff6, fffffff7, 22, 22,  }
+VTRN/VTRNQ:35:result_int32x4 [] = { fffffff2, fffffff3, 33, 33,  }
+VTRN/VTRNQ:36:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTRN/VTRNQ:37:result_uint8x16 [] = { f8, f9, 55, 55, fa, fb, 55, 55, fc, fd, 55, 55, fe, ff, 55, 55,  }
+VTRN/VTRNQ:38:result_uint16x8 [] = { fff4, fff5, 66, 66, fff6, fff7, 66, 66,  }
+VTRN/VTRNQ:39:result_uint32x4 [] = { fffffff2, fffffff3, 77, 77,  }
+VTRN/VTRNQ:40:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTRN/VTRNQ:41:result_poly8x16 [] = { f8, f9, 55, 55, fa, fb, 55, 55, fc, fd, 55, 55, fe, ff, 55, 55,  }
+VTRN/VTRNQ:42:result_poly16x8 [] = { fff4, fff5, 66, 66, fff6, fff7, 66, 66,  }
+VTRN/VTRNQ:43:result_float32x4 [] = { c1600000, c1500000, 42073333, 42073333,  }
+
+VUZP/VUZPQ chunk 0 output:
+VUZP/VUZPQ:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VUZP/VUZPQ:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VUZP/VUZPQ:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VUZP/VUZPQ:3:result_int64x1 [] = { 3333333333333333,  }
+VUZP/VUZPQ:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VUZP/VUZPQ:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VUZP/VUZPQ:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VUZP/VUZPQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VUZP/VUZPQ:8:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VUZP/VUZPQ:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VUZP/VUZPQ:10:result_float32x2 [] = { c1800000, c1700000,  }
+VUZP/VUZPQ:11:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VUZP/VUZPQ:12:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VUZP/VUZPQ:13:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VUZP/VUZPQ:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VUZP/VUZPQ:15:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VUZP/VUZPQ:16:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VUZP/VUZPQ:17:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VUZP/VUZPQ:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VUZP/VUZPQ:19:result_poly8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VUZP/VUZPQ:20:result_poly16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VUZP/VUZPQ:21:result_float32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+
+VUZP/VUZPQ chunk 1 output:
+VUZP/VUZPQ:22:result_int8x8 [] = { 11, 11, 11, 11, 11, 11, 11, 11,  }
+VUZP/VUZPQ:23:result_int16x4 [] = { 22, 22, 22, 22,  }
+VUZP/VUZPQ:24:result_int32x2 [] = { 33, 33,  }
+VUZP/VUZPQ:25:result_int64x1 [] = { 3333333333333333,  }
+VUZP/VUZPQ:26:result_uint8x8 [] = { 55, 55, 55, 55, 55, 55, 55, 55,  }
+VUZP/VUZPQ:27:result_uint16x4 [] = { 66, 66, 66, 66,  }
+VUZP/VUZPQ:28:result_uint32x2 [] = { 77, 77,  }
+VUZP/VUZPQ:29:result_uint64x1 [] = { 3333333333333333,  }
+VUZP/VUZPQ:30:result_poly8x8 [] = { 55, 55, 55, 55, 55, 55, 55, 55,  }
+VUZP/VUZPQ:31:result_poly16x4 [] = { 66, 66, 66, 66,  }
+VUZP/VUZPQ:32:result_float32x2 [] = { 42066666, 42066666,  }
+VUZP/VUZPQ:33:result_int8x16 [] = { 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11,  }
+VUZP/VUZPQ:34:result_int16x8 [] = { 22, 22, 22, 22, 22, 22, 22, 22,  }
+VUZP/VUZPQ:35:result_int32x4 [] = { 33, 33, 33, 33,  }
+VUZP/VUZPQ:36:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VUZP/VUZPQ:37:result_uint8x16 [] = { 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55,  }
+VUZP/VUZPQ:38:result_uint16x8 [] = { 66, 66, 66, 66, 66, 66, 66, 66,  }
+VUZP/VUZPQ:39:result_uint32x4 [] = { 77, 77, 77, 77,  }
+VUZP/VUZPQ:40:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VUZP/VUZPQ:41:result_poly8x16 [] = { 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55,  }
+VUZP/VUZPQ:42:result_poly16x8 [] = { 66, 66, 66, 66, 66, 66, 66, 66,  }
+VUZP/VUZPQ:43:result_float32x4 [] = { 42073333, 42073333, 42073333, 42073333,  }
+
+VZIP/VZIPQ chunk 0 output:
+VZIP/VZIPQ:0:result_int8x8 [] = { fffffff0, fffffff4, 11, 11, fffffff1, fffffff5, 11, 11,  }
+VZIP/VZIPQ:1:result_int16x4 [] = { fffffff0, fffffff2, 22, 22,  }
+VZIP/VZIPQ:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VZIP/VZIPQ:3:result_int64x1 [] = { 3333333333333333,  }
+VZIP/VZIPQ:4:result_uint8x8 [] = { f0, f4, 55, 55, f1, f5, 55, 55,  }
+VZIP/VZIPQ:5:result_uint16x4 [] = { fff0, fff2, 66, 66,  }
+VZIP/VZIPQ:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VZIP/VZIPQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VZIP/VZIPQ:8:result_poly8x8 [] = { f0, f4, 55, 55, f1, f5, 55, 55,  }
+VZIP/VZIPQ:9:result_poly16x4 [] = { fff0, fff2, 66, 66,  }
+VZIP/VZIPQ:10:result_float32x2 [] = { c1800000, c1700000,  }
+VZIP/VZIPQ:11:result_int8x16 [] = { fffffff0, fffffff8, 11, 11, fffffff1, fffffff9, 11, 11, fffffff2, fffffffa, 11, 11, fffffff3, fffffffb, 11, 11,  }
+VZIP/VZIPQ:12:result_int16x8 [] = { fffffff0, fffffff4, 22, 22, fffffff1, fffffff5, 22, 22,  }
+VZIP/VZIPQ:13:result_int32x4 [] = { fffffff0, fffffff2, 33, 33,  }
+VZIP/VZIPQ:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VZIP/VZIPQ:15:result_uint8x16 [] = { f0, f8, 55, 55, f1, f9, 55, 55, f2, fa, 55, 55, f3, fb, 55, 55,  }
+VZIP/VZIPQ:16:result_uint16x8 [] = { fff0, fff4, 66, 66, fff1, fff5, 66, 66,  }
+VZIP/VZIPQ:17:result_uint32x4 [] = { fffffff0, fffffff2, 77, 77,  }
+VZIP/VZIPQ:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VZIP/VZIPQ:19:result_poly8x16 [] = { f0, f8, 55, 55, f1, f9, 55, 55, f2, fa, 55, 55, f3, fb, 55, 55,  }
+VZIP/VZIPQ:20:result_poly16x8 [] = { fff0, fff4, 66, 66, fff1, fff5, 66, 66,  }
+VZIP/VZIPQ:21:result_float32x4 [] = { c1800000, c1600000, 42073333, 42073333,  }
+
+VZIP/VZIPQ chunk 1 output:
+VZIP/VZIPQ:22:result_int8x8 [] = { fffffff2, fffffff6, 11, 11, fffffff3, fffffff7, 11, 11,  }
+VZIP/VZIPQ:23:result_int16x4 [] = { fffffff1, fffffff3, 22, 22,  }
+VZIP/VZIPQ:24:result_int32x2 [] = { 33, 33,  }
+VZIP/VZIPQ:25:result_int64x1 [] = { 3333333333333333,  }
+VZIP/VZIPQ:26:result_uint8x8 [] = { f2, f6, 55, 55, f3, f7, 55, 55,  }
+VZIP/VZIPQ:27:result_uint16x4 [] = { fff1, fff3, 66, 66,  }
+VZIP/VZIPQ:28:result_uint32x2 [] = { 77, 77,  }
+VZIP/VZIPQ:29:result_uint64x1 [] = { 3333333333333333,  }
+VZIP/VZIPQ:30:result_poly8x8 [] = { f2, f6, 55, 55, f3, f7, 55, 55,  }
+VZIP/VZIPQ:31:result_poly16x4 [] = { fff1, fff3, 66, 66,  }
+VZIP/VZIPQ:32:result_float32x2 [] = { 42066666, 42066666,  }
+VZIP/VZIPQ:33:result_int8x16 [] = { fffffff4, fffffffc, 11, 11, fffffff5, fffffffd, 11, 11, fffffff6, fffffffe, 11, 11, fffffff7, ffffffff, 11, 11,  }
+VZIP/VZIPQ:34:result_int16x8 [] = { fffffff2, fffffff6, 22, 22, fffffff3, fffffff7, 22, 22,  }
+VZIP/VZIPQ:35:result_int32x4 [] = { fffffff1, fffffff3, 33, 33,  }
+VZIP/VZIPQ:36:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VZIP/VZIPQ:37:result_uint8x16 [] = { f4, fc, 55, 55, f5, fd, 55, 55, f6, fe, 55, 55, f7, ff, 55, 55,  }
+VZIP/VZIPQ:38:result_uint16x8 [] = { fff2, fff6, 66, 66, fff3, fff7, 66, 66,  }
+VZIP/VZIPQ:39:result_uint32x4 [] = { fffffff1, fffffff3, 77, 77,  }
+VZIP/VZIPQ:40:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VZIP/VZIPQ:41:result_poly8x16 [] = { f4, fc, 55, 55, f5, fd, 55, 55, f6, fe, 55, 55, f7, ff, 55, 55,  }
+VZIP/VZIPQ:42:result_poly16x8 [] = { fff2, fff6, 66, 66, fff3, fff7, 66, 66,  }
+VZIP/VZIPQ:43:result_float32x4 [] = { c1700000, c1500000, 42073333, 42073333,  }
+
+VREINTERPRET/VREINTERPRETQ output:
+VREINTERPRET/VREINTERPRETQ:0:result_int8x8 [] = { fffffff0, ffffffff, fffffff1, ffffffff, fffffff2, ffffffff, fffffff3, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:1:result_int8x8 [] = { fffffff0, ffffffff, ffffffff, ffffffff, fffffff1, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:2:result_int8x8 [] = { fffffff0, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:3:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VREINTERPRET/VREINTERPRETQ:4:result_int8x8 [] = { fffffff0, ffffffff, fffffff1, ffffffff, fffffff2, ffffffff, fffffff3, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:5:result_int8x8 [] = { fffffff0, ffffffff, ffffffff, ffffffff, fffffff1, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:6:result_int8x8 [] = { fffffff0, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:7:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VREINTERPRET/VREINTERPRETQ:8:result_int8x8 [] = { fffffff0, ffffffff, fffffff1, ffffffff, fffffff2, ffffffff, fffffff3, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:9:result_int16x4 [] = { fffff1f0, fffff3f2, fffff5f4, fffff7f6,  }
+VREINTERPRET/VREINTERPRETQ:10:result_int16x4 [] = { fffffff0, ffffffff, fffffff1, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:11:result_int16x4 [] = { fffffff0, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:12:result_int16x4 [] = { fffff1f0, fffff3f2, fffff5f4, fffff7f6,  }
+VREINTERPRET/VREINTERPRETQ:13:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VREINTERPRET/VREINTERPRETQ:14:result_int16x4 [] = { fffffff0, ffffffff, fffffff1, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:15:result_int16x4 [] = { fffffff0, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:16:result_int16x4 [] = { fffff1f0, fffff3f2, fffff5f4, fffff7f6,  }
+VREINTERPRET/VREINTERPRETQ:17:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VREINTERPRET/VREINTERPRETQ:18:result_int32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:19:result_int32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:20:result_int32x2 [] = { fffffff0, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:21:result_int32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:22:result_int32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:23:result_int32x2 [] = { fffffff0, fffffff1,  }
+VREINTERPRET/VREINTERPRETQ:24:result_int32x2 [] = { fffffff0, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:25:result_int32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:26:result_int32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:27:result_int64x1 [] = { f7f6f5f4f3f2f1f0,  }
+VREINTERPRET/VREINTERPRETQ:28:result_int64x1 [] = { fff3fff2fff1fff0,  }
+VREINTERPRET/VREINTERPRETQ:29:result_int64x1 [] = { fffffff1fffffff0,  }
+VREINTERPRET/VREINTERPRETQ:30:result_int64x1 [] = { f7f6f5f4f3f2f1f0,  }
+VREINTERPRET/VREINTERPRETQ:31:result_int64x1 [] = { fff3fff2fff1fff0,  }
+VREINTERPRET/VREINTERPRETQ:32:result_int64x1 [] = { fffffff1fffffff0,  }
+VREINTERPRET/VREINTERPRETQ:33:result_int64x1 [] = { fffffffffffffff0,  }
+VREINTERPRET/VREINTERPRETQ:34:result_int64x1 [] = { f7f6f5f4f3f2f1f0,  }
+VREINTERPRET/VREINTERPRETQ:35:result_int64x1 [] = { fff3fff2fff1fff0,  }
+VREINTERPRET/VREINTERPRETQ:36:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VREINTERPRET/VREINTERPRETQ:37:result_uint8x8 [] = { f0, ff, f1, ff, f2, ff, f3, ff,  }
+VREINTERPRET/VREINTERPRETQ:38:result_uint8x8 [] = { f0, ff, ff, ff, f1, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:39:result_uint8x8 [] = { f0, ff, ff, ff, ff, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:40:result_uint8x8 [] = { f0, ff, f1, ff, f2, ff, f3, ff,  }
+VREINTERPRET/VREINTERPRETQ:41:result_uint8x8 [] = { f0, ff, ff, ff, f1, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:42:result_uint8x8 [] = { f0, ff, ff, ff, ff, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:43:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VREINTERPRET/VREINTERPRETQ:44:result_uint8x8 [] = { f0, ff, f1, ff, f2, ff, f3, ff,  }
+VREINTERPRET/VREINTERPRETQ:45:result_uint16x4 [] = { f1f0, f3f2, f5f4, f7f6,  }
+VREINTERPRET/VREINTERPRETQ:46:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VREINTERPRET/VREINTERPRETQ:47:result_uint16x4 [] = { fff0, ffff, fff1, ffff,  }
+VREINTERPRET/VREINTERPRETQ:48:result_uint16x4 [] = { fff0, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:49:result_uint16x4 [] = { f1f0, f3f2, f5f4, f7f6,  }
+VREINTERPRET/VREINTERPRETQ:50:result_uint16x4 [] = { fff0, ffff, fff1, ffff,  }
+VREINTERPRET/VREINTERPRETQ:51:result_uint16x4 [] = { fff0, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:52:result_uint16x4 [] = { f1f0, f3f2, f5f4, f7f6,  }
+VREINTERPRET/VREINTERPRETQ:53:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VREINTERPRET/VREINTERPRETQ:54:result_uint32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:55:result_uint32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:56:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VREINTERPRET/VREINTERPRETQ:57:result_uint32x2 [] = { fffffff0, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:58:result_uint32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:59:result_uint32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:60:result_uint32x2 [] = { fffffff0, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:61:result_uint32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:62:result_uint32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:63:result_uint64x1 [] = { f7f6f5f4f3f2f1f0,  }
+VREINTERPRET/VREINTERPRETQ:64:result_uint64x1 [] = { fff3fff2fff1fff0,  }
+VREINTERPRET/VREINTERPRETQ:65:result_uint64x1 [] = { fffffff1fffffff0,  }
+VREINTERPRET/VREINTERPRETQ:66:result_uint64x1 [] = { fffffffffffffff0,  }
+VREINTERPRET/VREINTERPRETQ:67:result_uint64x1 [] = { f7f6f5f4f3f2f1f0,  }
+VREINTERPRET/VREINTERPRETQ:68:result_uint64x1 [] = { fff3fff2fff1fff0,  }
+VREINTERPRET/VREINTERPRETQ:69:result_uint64x1 [] = { fffffff1fffffff0,  }
+VREINTERPRET/VREINTERPRETQ:70:result_uint64x1 [] = { f7f6f5f4f3f2f1f0,  }
+VREINTERPRET/VREINTERPRETQ:71:result_uint64x1 [] = { fff3fff2fff1fff0,  }
+VREINTERPRET/VREINTERPRETQ:72:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VREINTERPRET/VREINTERPRETQ:73:result_poly8x8 [] = { f0, ff, f1, ff, f2, ff, f3, ff,  }
+VREINTERPRET/VREINTERPRETQ:74:result_poly8x8 [] = { f0, ff, ff, ff, f1, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:75:result_poly8x8 [] = { f0, ff, ff, ff, ff, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:76:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VREINTERPRET/VREINTERPRETQ:77:result_poly8x8 [] = { f0, ff, f1, ff, f2, ff, f3, ff,  }
+VREINTERPRET/VREINTERPRETQ:78:result_poly8x8 [] = { f0, ff, ff, ff, f1, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:79:result_poly8x8 [] = { f0, ff, ff, ff, ff, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:80:result_poly8x8 [] = { f0, ff, f1, ff, f2, ff, f3, ff,  }
+VREINTERPRET/VREINTERPRETQ:81:result_poly16x4 [] = { f1f0, f3f2, f5f4, f7f6,  }
+VREINTERPRET/VREINTERPRETQ:82:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VREINTERPRET/VREINTERPRETQ:83:result_poly16x4 [] = { fff0, ffff, fff1, ffff,  }
+VREINTERPRET/VREINTERPRETQ:84:result_poly16x4 [] = { fff0, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:85:result_poly16x4 [] = { f1f0, f3f2, f5f4, f7f6,  }
+VREINTERPRET/VREINTERPRETQ:86:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VREINTERPRET/VREINTERPRETQ:87:result_poly16x4 [] = { fff0, ffff, fff1, ffff,  }
+VREINTERPRET/VREINTERPRETQ:88:result_poly16x4 [] = { fff0, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:89:result_poly16x4 [] = { f1f0, f3f2, f5f4, f7f6,  }
+VREINTERPRET/VREINTERPRETQ:90:result_int8x16 [] = { fffffff0, ffffffff, fffffff1, ffffffff, fffffff2, ffffffff, fffffff3, ffffffff, fffffff4, ffffffff, fffffff5, ffffffff, fffffff6, ffffffff, fffffff7, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:91:result_int8x16 [] = { fffffff0, ffffffff, ffffffff, ffffffff, fffffff1, ffffffff, ffffffff, ffffffff, fffffff2, ffffffff, ffffffff, ffffffff, fffffff3, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:92:result_int8x16 [] = { fffffff0, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, fffffff1, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:93:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:94:result_int8x16 [] = { fffffff0, ffffffff, fffffff1, ffffffff, fffffff2, ffffffff, fffffff3, ffffffff, fffffff4, ffffffff, fffffff5, ffffffff, fffffff6, ffffffff, fffffff7, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:95:result_int8x16 [] = { fffffff0, ffffffff, ffffffff, ffffffff, fffffff1, ffffffff, ffffffff, ffffffff, fffffff2, ffffffff, ffffffff, ffffffff, fffffff3, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:96:result_int8x16 [] = { fffffff0, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, fffffff1, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:97:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:98:result_int8x16 [] = { fffffff0, ffffffff, fffffff1, ffffffff, fffffff2, ffffffff, fffffff3, ffffffff, fffffff4, ffffffff, fffffff5, ffffffff, fffffff6, ffffffff, fffffff7, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:99:result_int16x8 [] = { fffff1f0, fffff3f2, fffff5f4, fffff7f6, fffff9f8, fffffbfa, fffffdfc, fffffffe,  }
+VREINTERPRET/VREINTERPRETQ:100:result_int16x8 [] = { fffffff0, ffffffff, fffffff1, ffffffff, fffffff2, ffffffff, fffffff3, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:101:result_int16x8 [] = { fffffff0, ffffffff, ffffffff, ffffffff, fffffff1, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:102:result_int16x8 [] = { fffff1f0, fffff3f2, fffff5f4, fffff7f6, fffff9f8, fffffbfa, fffffdfc, fffffffe,  }
+VREINTERPRET/VREINTERPRETQ:103:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VREINTERPRET/VREINTERPRETQ:104:result_int16x8 [] = { fffffff0, ffffffff, fffffff1, ffffffff, fffffff2, ffffffff, fffffff3, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:105:result_int16x8 [] = { fffffff0, ffffffff, ffffffff, ffffffff, fffffff1, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:106:result_int16x8 [] = { fffff1f0, fffff3f2, fffff5f4, fffff7f6, fffff9f8, fffffbfa, fffffdfc, fffffffe,  }
+VREINTERPRET/VREINTERPRETQ:107:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VREINTERPRET/VREINTERPRETQ:108:result_int32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:109:result_int32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:110:result_int32x4 [] = { fffffff0, ffffffff, fffffff1, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:111:result_int32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:112:result_int32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:113:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VREINTERPRET/VREINTERPRETQ:114:result_int32x4 [] = { fffffff0, ffffffff, fffffff1, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:115:result_int32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:116:result_int32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:117:result_int64x2 [] = { f7f6f5f4f3f2f1f0, fffefdfcfbfaf9f8,  }
+VREINTERPRET/VREINTERPRETQ:118:result_int64x2 [] = { fff3fff2fff1fff0, fff7fff6fff5fff4,  }
+VREINTERPRET/VREINTERPRETQ:119:result_int64x2 [] = { fffffff1fffffff0, fffffff3fffffff2,  }
+VREINTERPRET/VREINTERPRETQ:120:result_int64x2 [] = { f7f6f5f4f3f2f1f0, fffefdfcfbfaf9f8,  }
+VREINTERPRET/VREINTERPRETQ:121:result_int64x2 [] = { fff3fff2fff1fff0, fff7fff6fff5fff4,  }
+VREINTERPRET/VREINTERPRETQ:122:result_int64x2 [] = { fffffff1fffffff0, fffffff3fffffff2,  }
+VREINTERPRET/VREINTERPRETQ:123:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VREINTERPRET/VREINTERPRETQ:124:result_int64x2 [] = { f7f6f5f4f3f2f1f0, fffefdfcfbfaf9f8,  }
+VREINTERPRET/VREINTERPRETQ:125:result_int64x2 [] = { fff3fff2fff1fff0, fff7fff6fff5fff4,  }
+VREINTERPRET/VREINTERPRETQ:126:result_uint16x8 [] = { f1f0, f3f2, f5f4, f7f6, f9f8, fbfa, fdfc, fffe,  }
+VREINTERPRET/VREINTERPRETQ:127:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VREINTERPRET/VREINTERPRETQ:128:result_uint16x8 [] = { fff0, ffff, fff1, ffff, fff2, ffff, fff3, ffff,  }
+VREINTERPRET/VREINTERPRETQ:129:result_uint16x8 [] = { fff0, ffff, ffff, ffff, fff1, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:130:result_uint16x8 [] = { f1f0, f3f2, f5f4, f7f6, f9f8, fbfa, fdfc, fffe,  }
+VREINTERPRET/VREINTERPRETQ:131:result_uint16x8 [] = { fff0, ffff, fff1, ffff, fff2, ffff, fff3, ffff,  }
+VREINTERPRET/VREINTERPRETQ:132:result_uint16x8 [] = { fff0, ffff, ffff, ffff, fff1, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:133:result_uint16x8 [] = { f1f0, f3f2, f5f4, f7f6, f9f8, fbfa, fdfc, fffe,  }
+VREINTERPRET/VREINTERPRETQ:134:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VREINTERPRET/VREINTERPRETQ:135:result_uint32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:136:result_uint32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:137:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VREINTERPRET/VREINTERPRETQ:138:result_uint32x4 [] = { fffffff0, ffffffff, fffffff1, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:139:result_uint32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:140:result_uint32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:141:result_uint32x4 [] = { fffffff0, ffffffff, fffffff1, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:142:result_uint32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:143:result_uint32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:144:result_uint64x2 [] = { f7f6f5f4f3f2f1f0, fffefdfcfbfaf9f8,  }
+VREINTERPRET/VREINTERPRETQ:145:result_uint64x2 [] = { fff3fff2fff1fff0, fff7fff6fff5fff4,  }
+VREINTERPRET/VREINTERPRETQ:146:result_uint64x2 [] = { fffffff1fffffff0, fffffff3fffffff2,  }
+VREINTERPRET/VREINTERPRETQ:147:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VREINTERPRET/VREINTERPRETQ:148:result_uint64x2 [] = { f7f6f5f4f3f2f1f0, fffefdfcfbfaf9f8,  }
+VREINTERPRET/VREINTERPRETQ:149:result_uint64x2 [] = { fff3fff2fff1fff0, fff7fff6fff5fff4,  }
+VREINTERPRET/VREINTERPRETQ:150:result_uint64x2 [] = { fffffff1fffffff0, fffffff3fffffff2,  }
+VREINTERPRET/VREINTERPRETQ:151:result_uint64x2 [] = { f7f6f5f4f3f2f1f0, fffefdfcfbfaf9f8,  }
+VREINTERPRET/VREINTERPRETQ:152:result_uint64x2 [] = { fff3fff2fff1fff0, fff7fff6fff5fff4,  }
+VREINTERPRET/VREINTERPRETQ:153:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VREINTERPRET/VREINTERPRETQ:154:result_uint8x16 [] = { f0, ff, f1, ff, f2, ff, f3, ff, f4, ff, f5, ff, f6, ff, f7, ff,  }
+VREINTERPRET/VREINTERPRETQ:155:result_uint8x16 [] = { f0, ff, ff, ff, f1, ff, ff, ff, f2, ff, ff, ff, f3, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:156:result_uint8x16 [] = { f0, ff, ff, ff, ff, ff, ff, ff, f1, ff, ff, ff, ff, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:157:result_uint8x16 [] = { f0, ff, f1, ff, f2, ff, f3, ff, f4, ff, f5, ff, f6, ff, f7, ff,  }
+VREINTERPRET/VREINTERPRETQ:158:result_uint8x16 [] = { f0, ff, ff, ff, f1, ff, ff, ff, f2, ff, ff, ff, f3, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:159:result_uint8x16 [] = { f0, ff, ff, ff, ff, ff, ff, ff, f1, ff, ff, ff, ff, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:160:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VREINTERPRET/VREINTERPRETQ:161:result_uint8x16 [] = { f0, ff, f1, ff, f2, ff, f3, ff, f4, ff, f5, ff, f6, ff, f7, ff,  }
+VREINTERPRET/VREINTERPRETQ:162:result_float32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:163:result_float32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:164:result_float32x2 [] = { fffffff0, fffffff1,  }
+VREINTERPRET/VREINTERPRETQ:165:result_float32x2 [] = { fffffff0, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:166:result_float32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:167:result_float32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:168:result_float32x2 [] = { fffffff0, fffffff1,  }
+VREINTERPRET/VREINTERPRETQ:169:result_float32x2 [] = { fffffff0, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:170:result_float32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:171:result_float32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:172:result_float32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:173:result_float32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:174:result_float32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VREINTERPRET/VREINTERPRETQ:175:result_float32x4 [] = { fffffff0, ffffffff, fffffff1, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:176:result_float32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:177:result_float32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:178:result_float32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VREINTERPRET/VREINTERPRETQ:179:result_float32x4 [] = { fffffff0, ffffffff, fffffff1, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:180:result_float32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:181:result_float32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:182:result_int8x8 [] = { 0, 0, ffffff80, ffffffc1, 0, 0, 70, ffffffc1,  }
+VREINTERPRET/VREINTERPRETQ:183:result_int16x4 [] = { 0, ffffc180, 0, ffffc170,  }
+VREINTERPRET/VREINTERPRETQ:184:result_int32x2 [] = { c1800000, c1700000,  }
+VREINTERPRET/VREINTERPRETQ:185:result_int64x1 [] = { c1700000c1800000,  }
+VREINTERPRET/VREINTERPRETQ:186:result_uint8x8 [] = { 0, 0, 80, c1, 0, 0, 70, c1,  }
+VREINTERPRET/VREINTERPRETQ:187:result_uint16x4 [] = { 0, c180, 0, c170,  }
+VREINTERPRET/VREINTERPRETQ:188:result_uint32x2 [] = { c1800000, c1700000,  }
+VREINTERPRET/VREINTERPRETQ:189:result_uint64x1 [] = { c1700000c1800000,  }
+VREINTERPRET/VREINTERPRETQ:190:result_poly8x8 [] = { 0, 0, 80, c1, 0, 0, 70, c1,  }
+VREINTERPRET/VREINTERPRETQ:191:result_poly16x4 [] = { 0, c180, 0, c170,  }
+VREINTERPRET/VREINTERPRETQ:192:result_int8x16 [] = { 0, 0, ffffff80, ffffffc1, 0, 0, 70, ffffffc1, 0, 0, 60, ffffffc1, 0, 0, 50, ffffffc1,  }
+VREINTERPRET/VREINTERPRETQ:193:result_int16x8 [] = { 0, ffffc180, 0, ffffc170, 0, ffffc160, 0, ffffc150,  }
+VREINTERPRET/VREINTERPRETQ:194:result_int32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+VREINTERPRET/VREINTERPRETQ:195:result_int64x2 [] = { c1700000c1800000, c1500000c1600000,  }
+VREINTERPRET/VREINTERPRETQ:196:result_uint8x16 [] = { 0, 0, 80, c1, 0, 0, 70, c1, 0, 0, 60, c1, 0, 0, 50, c1,  }
+VREINTERPRET/VREINTERPRETQ:197:result_uint16x8 [] = { 0, c180, 0, c170, 0, c160, 0, c150,  }
+VREINTERPRET/VREINTERPRETQ:198:result_uint32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+VREINTERPRET/VREINTERPRETQ:199:result_uint64x2 [] = { c1700000c1800000, c1500000c1600000,  }
+VREINTERPRET/VREINTERPRETQ:200:result_poly8x16 [] = { 0, 0, 80, c1, 0, 0, 70, c1, 0, 0, 60, c1, 0, 0, 50, c1,  }
+VREINTERPRET/VREINTERPRETQ:201:result_poly16x8 [] = { 0, c180, 0, c170, 0, c160, 0, c150,  }
+
+VQRDMULH cumulative saturation output:
+VQRDMULH:0:vqrdmulh_s16 Neon cumulative saturation 0
+VQRDMULH:1:vqrdmulh_s32 Neon cumulative saturation 0
+VQRDMULH:2:vqrdmulhq_s16 Neon cumulative saturation 0
+VQRDMULH:3:vqrdmulhq_s32 Neon cumulative saturation 0
+
+VQRDMULH output:
+VQRDMULH:4:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:5:result_int16x4 [] = { fffffff5, fffffff6, fffffff7, fffffff7,  }
+VQRDMULH:6:result_int32x2 [] = { 0, 0,  }
+VQRDMULH:7:result_int64x1 [] = { 3333333333333333,  }
+VQRDMULH:8:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:9:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH:10:result_uint32x2 [] = { 33333333, 33333333,  }
+VQRDMULH:11:result_uint64x1 [] = { 3333333333333333,  }
+VQRDMULH:12:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:13:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH:14:result_float32x2 [] = { 33333333, 33333333,  }
+VQRDMULH:15:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:16:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRDMULH:17:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH:18:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH:19:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:20:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH:21:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH:22:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH:23:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:24:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH:25:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRDMULH (check mul cumulative saturation) cumulative saturation output:
+VQRDMULH:26:vqrdmulh_s16 Neon cumulative saturation 1
+VQRDMULH:27:vqrdmulh_s32 Neon cumulative saturation 1
+VQRDMULH:28:vqrdmulhq_s16 Neon cumulative saturation 1
+VQRDMULH:29:vqrdmulhq_s32 Neon cumulative saturation 1
+
+VQRDMULH (check mul cumulative saturation) output:
+VQRDMULH:30:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:31:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH:32:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRDMULH:33:result_int64x1 [] = { 3333333333333333,  }
+VQRDMULH:34:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:35:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH:36:result_uint32x2 [] = { 33333333, 33333333,  }
+VQRDMULH:37:result_uint64x1 [] = { 3333333333333333,  }
+VQRDMULH:38:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:39:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH:40:result_float32x2 [] = { 33333333, 33333333,  }
+VQRDMULH:41:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:42:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH:43:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQRDMULH:44:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH:45:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:46:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH:47:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH:48:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH:49:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:50:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH:51:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRDMULH (check rounding cumulative saturation) cumulative saturation output:
+VQRDMULH:52:vqrdmulh_s16 Neon cumulative saturation 0
+VQRDMULH:53:vqrdmulh_s32 Neon cumulative saturation 0
+VQRDMULH:54:vqrdmulhq_s16 Neon cumulative saturation 0
+VQRDMULH:55:vqrdmulhq_s32 Neon cumulative saturation 0
+
+VQRDMULH (check rounding cumulative saturation) output:
+VQRDMULH:56:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:57:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH:58:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRDMULH:59:result_int64x1 [] = { 3333333333333333,  }
+VQRDMULH:60:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:61:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH:62:result_uint32x2 [] = { 33333333, 33333333,  }
+VQRDMULH:63:result_uint64x1 [] = { 3333333333333333,  }
+VQRDMULH:64:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:65:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH:66:result_float32x2 [] = { 33333333, 33333333,  }
+VQRDMULH:67:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:68:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH:69:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQRDMULH:70:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH:71:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:72:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH:73:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH:74:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH:75:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:76:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH:77:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRDMULH_LANE cumulative saturation output:
+VQRDMULH_LANE:0:vqrdmulh_lane_s16 Neon cumulative saturation 0
+VQRDMULH_LANE:1:vqrdmulh_lane_s32 Neon cumulative saturation 0
+VQRDMULH_LANE:2:vqrdmulhq_lane_s16 Neon cumulative saturation 0
+VQRDMULH_LANE:3:vqrdmulhq_lane_s32 Neon cumulative saturation 0
+
+VQRDMULH_LANE output:
+VQRDMULH_LANE:4:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:5:result_int16x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH_LANE:6:result_int32x2 [] = { 0, 0,  }
+VQRDMULH_LANE:7:result_int64x1 [] = { 3333333333333333,  }
+VQRDMULH_LANE:8:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:9:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:10:result_uint32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_LANE:11:result_uint64x1 [] = { 3333333333333333,  }
+VQRDMULH_LANE:12:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:13:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:14:result_float32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_LANE:15:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:16:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRDMULH_LANE:17:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH_LANE:18:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_LANE:19:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:20:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:21:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_LANE:22:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_LANE:23:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:24:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:25:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRDMULH_LANE (check mul cumulative saturation) cumulative saturation output:
+VQRDMULH_LANE:26:vqrdmulh_lane_s16 Neon cumulative saturation 1
+VQRDMULH_LANE:27:vqrdmulh_lane_s32 Neon cumulative saturation 1
+VQRDMULH_LANE:28:vqrdmulhq_lane_s16 Neon cumulative saturation 1
+VQRDMULH_LANE:29:vqrdmulhq_lane_s32 Neon cumulative saturation 1
+
+VQRDMULH_LANE (check mul cumulative saturation) output:
+VQRDMULH_LANE:30:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:31:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH_LANE:32:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRDMULH_LANE:33:result_int64x1 [] = { 3333333333333333,  }
+VQRDMULH_LANE:34:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:35:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:36:result_uint32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_LANE:37:result_uint64x1 [] = { 3333333333333333,  }
+VQRDMULH_LANE:38:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:39:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:40:result_float32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_LANE:41:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:42:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH_LANE:43:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQRDMULH_LANE:44:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_LANE:45:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:46:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:47:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_LANE:48:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_LANE:49:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:50:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:51:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRDMULH_LANE (check rounding cumulative saturation) cumulative saturation output:
+VQRDMULH_LANE:52:vqrdmulh_lane_s16 Neon cumulative saturation 0
+VQRDMULH_LANE:53:vqrdmulh_lane_s32 Neon cumulative saturation 0
+VQRDMULH_LANE:54:vqrdmulhq_lane_s16 Neon cumulative saturation 0
+VQRDMULH_LANE:55:vqrdmulhq_lane_s32 Neon cumulative saturation 0
+
+VQRDMULH_LANE (check rounding cumulative saturation) output:
+VQRDMULH_LANE:56:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:57:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH_LANE:58:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRDMULH_LANE:59:result_int64x1 [] = { 3333333333333333,  }
+VQRDMULH_LANE:60:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:61:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:62:result_uint32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_LANE:63:result_uint64x1 [] = { 3333333333333333,  }
+VQRDMULH_LANE:64:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:65:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:66:result_float32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_LANE:67:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:68:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH_LANE:69:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQRDMULH_LANE:70:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_LANE:71:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:72:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:73:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_LANE:74:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_LANE:75:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:76:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:77:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRDMULH_N cumulative saturation output:
+VQRDMULH_N:0:vqrdmulh_n_s16 Neon cumulative saturation 0
+VQRDMULH_N:1:vqrdmulh_n_s32 Neon cumulative saturation 0
+VQRDMULH_N:2:vqrdmulhq_n_s16 Neon cumulative saturation 0
+VQRDMULH_N:3:vqrdmulhq_n_s32 Neon cumulative saturation 0
+
+VQRDMULH_N output:
+VQRDMULH_N:4:result_int16x4 [] = { fffffffc, fffffffc, fffffffc, fffffffd,  }
+VQRDMULH_N:5:result_int32x2 [] = { fffffffe, fffffffe,  }
+VQRDMULH_N:6:result_int16x8 [] = { 6, 6, 6, 5, 5, 4, 4, 4,  }
+VQRDMULH_N:7:result_int32x4 [] = { fffffffe, fffffffe, fffffffe, fffffffe,  }
+
+VQRDMULH_N (check mul cumulative saturation) cumulative saturation output:
+VQRDMULH_N:8:vqrdmulh_n_s16 Neon cumulative saturation 1
+VQRDMULH_N:9:vqrdmulh_n_s32 Neon cumulative saturation 1
+VQRDMULH_N:10:vqrdmulhq_n_s16 Neon cumulative saturation 1
+VQRDMULH_N:11:vqrdmulhq_n_s32 Neon cumulative saturation 1
+
+VQRDMULH_N (check mul cumulative saturation) output:
+VQRDMULH_N:12:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:13:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH_N:14:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRDMULH_N:15:result_int64x1 [] = { 3333333333333333,  }
+VQRDMULH_N:16:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:17:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_N:18:result_uint32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_N:19:result_uint64x1 [] = { 3333333333333333,  }
+VQRDMULH_N:20:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:21:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_N:22:result_float32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_N:23:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:24:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH_N:25:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQRDMULH_N:26:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_N:27:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:28:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_N:29:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_N:30:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_N:31:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:32:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_N:33:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRDMULH_N (check rounding cumulative saturation) cumulative saturation output:
+VQRDMULH_N:34:vqrdmulh_n_s16 Neon cumulative saturation 0
+VQRDMULH_N:35:vqrdmulh_n_s32 Neon cumulative saturation 0
+VQRDMULH_N:36:vqrdmulhq_n_s16 Neon cumulative saturation 0
+VQRDMULH_N:37:vqrdmulhq_n_s32 Neon cumulative saturation 0
+
+VQRDMULH_N (check rounding cumulative saturation) output:
+VQRDMULH_N:38:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:39:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH_N:40:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRDMULH_N:41:result_int64x1 [] = { 3333333333333333,  }
+VQRDMULH_N:42:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:43:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_N:44:result_uint32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_N:45:result_uint64x1 [] = { 3333333333333333,  }
+VQRDMULH_N:46:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:47:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_N:48:result_float32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_N:49:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:50:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH_N:51:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQRDMULH_N:52:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_N:53:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:54:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_N:55:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_N:56:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_N:57:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:58:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_N:59:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRSHL/VQRSHLQ (with input = 0) cumulative saturation output:
+VQRSHL/VQRSHLQ:0:vqrshl_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:1:vqrshl_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:2:vqrshl_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:3:vqrshl_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:4:vqrshl_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:5:vqrshl_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:6:vqrshl_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:7:vqrshl_u64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:8:vqrshlq_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:9:vqrshlq_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:10:vqrshlq_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:11:vqrshlq_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:12:vqrshlq_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:13:vqrshlq_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:14:vqrshlq_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:15:vqrshlq_u64 Neon cumulative saturation 0
+
+VQRSHL/VQRSHLQ (with input = 0) output:
+VQRSHL/VQRSHLQ:16:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:17:result_int16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:18:result_int32x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:19:result_int64x1 [] = { 0,  }
+VQRSHL/VQRSHLQ:20:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:21:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:22:result_uint32x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:23:result_uint64x1 [] = { 0,  }
+VQRSHL/VQRSHLQ:24:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:25:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:26:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:27:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:28:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:29:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:30:result_int64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:31:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:32:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:33:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:34:result_uint64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:35:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:36:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:37:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRSHL/VQRSHLQ (input 0 and negative shift amount) cumulative saturation output:
+VQRSHL/VQRSHLQ:38:vqrshl_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:39:vqrshl_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:40:vqrshl_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:41:vqrshl_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:42:vqrshl_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:43:vqrshl_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:44:vqrshl_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:45:vqrshl_u64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:46:vqrshlq_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:47:vqrshlq_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:48:vqrshlq_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:49:vqrshlq_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:50:vqrshlq_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:51:vqrshlq_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:52:vqrshlq_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:53:vqrshlq_u64 Neon cumulative saturation 0
+
+VQRSHL/VQRSHLQ (input 0 and negative shift amount) output:
+VQRSHL/VQRSHLQ:54:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:55:result_int16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:56:result_int32x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:57:result_int64x1 [] = { 0,  }
+VQRSHL/VQRSHLQ:58:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:59:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:60:result_uint32x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:61:result_uint64x1 [] = { 0,  }
+VQRSHL/VQRSHLQ:62:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:63:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:64:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:65:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:66:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:67:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:68:result_int64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:69:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:70:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:71:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:72:result_uint64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:73:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:74:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:75:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRSHL/VQRSHLQ cumulative saturation output:
+VQRSHL/VQRSHLQ:76:vqrshl_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:77:vqrshl_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:78:vqrshl_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:79:vqrshl_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:80:vqrshl_u8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:81:vqrshl_u16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:82:vqrshl_u32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:83:vqrshl_u64 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:84:vqrshlq_s8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:85:vqrshlq_s16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:86:vqrshlq_s32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:87:vqrshlq_s64 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:88:vqrshlq_u8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:89:vqrshlq_u16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:90:vqrshlq_u32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:91:vqrshlq_u64 Neon cumulative saturation 1
+
+VQRSHL/VQRSHLQ output:
+VQRSHL/VQRSHLQ:92:result_int8x8 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6, ffffffe8, ffffffea, ffffffec, ffffffee,  }
+VQRSHL/VQRSHLQ:93:result_int16x4 [] = { ffffff80, ffffff88, ffffff90, ffffff98,  }
+VQRSHL/VQRSHLQ:94:result_int32x2 [] = { fffff000, fffff100,  }
+VQRSHL/VQRSHLQ:95:result_int64x1 [] = { ffffffffffffff80,  }
+VQRSHL/VQRSHLQ:96:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHL/VQRSHLQ:97:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQRSHL/VQRSHLQ:98:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQRSHL/VQRSHLQ:99:result_uint64x1 [] = { ffffffffffffffff,  }
+VQRSHL/VQRSHLQ:100:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:101:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:102:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:103:result_int8x16 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQRSHL/VQRSHLQ:104:result_int16x8 [] = { ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQRSHL/VQRSHLQ:105:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VQRSHL/VQRSHLQ:106:result_int64x2 [] = { 8000000000000000, 8000000000000000,  }
+VQRSHL/VQRSHLQ:107:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHL/VQRSHLQ:108:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQRSHL/VQRSHLQ:109:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQRSHL/VQRSHLQ:110:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQRSHL/VQRSHLQ:111:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:112:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:113:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRSHL/VQRSHLQ (negative shift amount) cumulative saturation output:
+VQRSHL/VQRSHLQ:114:vqrshl_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:115:vqrshl_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:116:vqrshl_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:117:vqrshl_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:118:vqrshl_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:119:vqrshl_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:120:vqrshl_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:121:vqrshl_u64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:122:vqrshlq_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:123:vqrshlq_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:124:vqrshlq_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:125:vqrshlq_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:126:vqrshlq_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:127:vqrshlq_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:128:vqrshlq_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:129:vqrshlq_u64 Neon cumulative saturation 0
+
+VQRSHL/VQRSHLQ (negative shift amount) output:
+VQRSHL/VQRSHLQ:130:result_int8x8 [] = { fffffffc, fffffffc, fffffffd, fffffffd, fffffffd, fffffffd, fffffffe, fffffffe,  }
+VQRSHL/VQRSHLQ:131:result_int16x4 [] = { fffffffc, fffffffc, fffffffd, fffffffd,  }
+VQRSHL/VQRSHLQ:132:result_int32x2 [] = { fffffffe, fffffffe,  }
+VQRSHL/VQRSHLQ:133:result_int64x1 [] = { ffffffffffffffff,  }
+VQRSHL/VQRSHLQ:134:result_uint8x8 [] = { 3c, 3c, 3d, 3d, 3d, 3d, 3e, 3e,  }
+VQRSHL/VQRSHLQ:135:result_uint16x4 [] = { 3ffc, 3ffc, 3ffd, 3ffd,  }
+VQRSHL/VQRSHLQ:136:result_uint32x2 [] = { 1ffffffe, 1ffffffe,  }
+VQRSHL/VQRSHLQ:137:result_uint64x1 [] = { fffffffffffffff,  }
+VQRSHL/VQRSHLQ:138:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:139:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:140:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:141:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:142:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:143:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:144:result_int64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:145:result_uint8x16 [] = { 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,  }
+VQRSHL/VQRSHLQ:146:result_uint16x8 [] = { 20, 20, 20, 20, 20, 20, 20, 20,  }
+VQRSHL/VQRSHLQ:147:result_uint32x4 [] = { 80000, 80000, 80000, 80000,  }
+VQRSHL/VQRSHLQ:148:result_uint64x2 [] = { 100000000000, 100000000000,  }
+VQRSHL/VQRSHLQ:149:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:150:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:151:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: shift by -1) cumulative saturation output:
+VQRSHL/VQRSHLQ:152:vqrshl_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:153:vqrshl_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:154:vqrshl_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:155:vqrshl_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:156:vqrshl_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:157:vqrshl_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:158:vqrshl_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:159:vqrshl_u64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:160:vqrshlq_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:161:vqrshlq_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:162:vqrshlq_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:163:vqrshlq_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:164:vqrshlq_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:165:vqrshlq_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:166:vqrshlq_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:167:vqrshlq_u64 Neon cumulative saturation 0
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: shift by -1) output:
+VQRSHL/VQRSHLQ:168:result_int8x8 [] = { 40, 40, 40, 40, 40, 40, 40, 40,  }
+VQRSHL/VQRSHLQ:169:result_int16x4 [] = { 4000, 4000, 4000, 4000,  }
+VQRSHL/VQRSHLQ:170:result_int32x2 [] = { 40000000, 40000000,  }
+VQRSHL/VQRSHLQ:171:result_int64x1 [] = { 4000000000000000,  }
+VQRSHL/VQRSHLQ:172:result_uint8x8 [] = { 80, 80, 80, 80, 80, 80, 80, 80,  }
+VQRSHL/VQRSHLQ:173:result_uint16x4 [] = { 8000, 8000, 8000, 8000,  }
+VQRSHL/VQRSHLQ:174:result_uint32x2 [] = { 80000000, 80000000,  }
+VQRSHL/VQRSHLQ:175:result_uint64x1 [] = { 8000000000000000,  }
+VQRSHL/VQRSHLQ:176:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:177:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:178:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:179:result_int8x16 [] = { 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40,  }
+VQRSHL/VQRSHLQ:180:result_int16x8 [] = { 4000, 4000, 4000, 4000, 4000, 4000, 4000, 4000,  }
+VQRSHL/VQRSHLQ:181:result_int32x4 [] = { 40000000, 40000000, 40000000, 40000000,  }
+VQRSHL/VQRSHLQ:182:result_int64x2 [] = { 4000000000000000, 4000000000000000,  }
+VQRSHL/VQRSHLQ:183:result_uint8x16 [] = { 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80,  }
+VQRSHL/VQRSHLQ:184:result_uint16x8 [] = { 8000, 8000, 8000, 8000, 8000, 8000, 8000, 8000,  }
+VQRSHL/VQRSHLQ:185:result_uint32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VQRSHL/VQRSHLQ:186:result_uint64x2 [] = { 8000000000000000, 8000000000000000,  }
+VQRSHL/VQRSHLQ:187:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:188:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:189:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: shift by -3) cumulative saturation output:
+VQRSHL/VQRSHLQ:190:vqrshl_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:191:vqrshl_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:192:vqrshl_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:193:vqrshl_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:194:vqrshl_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:195:vqrshl_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:196:vqrshl_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:197:vqrshl_u64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:198:vqrshlq_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:199:vqrshlq_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:200:vqrshlq_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:201:vqrshlq_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:202:vqrshlq_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:203:vqrshlq_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:204:vqrshlq_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:205:vqrshlq_u64 Neon cumulative saturation 0
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: shift by -3) output:
+VQRSHL/VQRSHLQ:206:result_int8x8 [] = { 10, 10, 10, 10, 10, 10, 10, 10,  }
+VQRSHL/VQRSHLQ:207:result_int16x4 [] = { 1000, 1000, 1000, 1000,  }
+VQRSHL/VQRSHLQ:208:result_int32x2 [] = { 10000000, 10000000,  }
+VQRSHL/VQRSHLQ:209:result_int64x1 [] = { 1000000000000000,  }
+VQRSHL/VQRSHLQ:210:result_uint8x8 [] = { 20, 20, 20, 20, 20, 20, 20, 20,  }
+VQRSHL/VQRSHLQ:211:result_uint16x4 [] = { 2000, 2000, 2000, 2000,  }
+VQRSHL/VQRSHLQ:212:result_uint32x2 [] = { 20000000, 20000000,  }
+VQRSHL/VQRSHLQ:213:result_uint64x1 [] = { 2000000000000000,  }
+VQRSHL/VQRSHLQ:214:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:215:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:216:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:217:result_int8x16 [] = { 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10,  }
+VQRSHL/VQRSHLQ:218:result_int16x8 [] = { 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000,  }
+VQRSHL/VQRSHLQ:219:result_int32x4 [] = { 10000000, 10000000, 10000000, 10000000,  }
+VQRSHL/VQRSHLQ:220:result_int64x2 [] = { 1000000000000000, 1000000000000000,  }
+VQRSHL/VQRSHLQ:221:result_uint8x16 [] = { 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20,  }
+VQRSHL/VQRSHLQ:222:result_uint16x8 [] = { 2000, 2000, 2000, 2000, 2000, 2000, 2000, 2000,  }
+VQRSHL/VQRSHLQ:223:result_uint32x4 [] = { 20000000, 20000000, 20000000, 20000000,  }
+VQRSHL/VQRSHLQ:224:result_uint64x2 [] = { 2000000000000000, 2000000000000000,  }
+VQRSHL/VQRSHLQ:225:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:226:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:227:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large shift amount) cumulative saturation output:
+VQRSHL/VQRSHLQ:228:vqrshl_s8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:229:vqrshl_s16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:230:vqrshl_s32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:231:vqrshl_s64 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:232:vqrshl_u8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:233:vqrshl_u16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:234:vqrshl_u32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:235:vqrshl_u64 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:236:vqrshlq_s8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:237:vqrshlq_s16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:238:vqrshlq_s32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:239:vqrshlq_s64 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:240:vqrshlq_u8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:241:vqrshlq_u16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:242:vqrshlq_u32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:243:vqrshlq_u64 Neon cumulative saturation 1
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large shift amount) output:
+VQRSHL/VQRSHLQ:244:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQRSHL/VQRSHLQ:245:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRSHL/VQRSHLQ:246:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRSHL/VQRSHLQ:247:result_int64x1 [] = { 7fffffffffffffff,  }
+VQRSHL/VQRSHLQ:248:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHL/VQRSHLQ:249:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQRSHL/VQRSHLQ:250:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQRSHL/VQRSHLQ:251:result_uint64x1 [] = { ffffffffffffffff,  }
+VQRSHL/VQRSHLQ:252:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:253:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:254:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:255:result_int8x16 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQRSHL/VQRSHLQ:256:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQRSHL/VQRSHLQ:257:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQRSHL/VQRSHLQ:258:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+VQRSHL/VQRSHLQ:259:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHL/VQRSHLQ:260:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQRSHL/VQRSHLQ:261:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQRSHL/VQRSHLQ:262:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQRSHL/VQRSHLQ:263:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:264:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:265:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large shift amount with negative input) cumulative saturation output:
+VQRSHL/VQRSHLQ:266:vqrshl_s8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:267:vqrshl_s16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:268:vqrshl_s32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:269:vqrshl_s64 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:270:vqrshl_u8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:271:vqrshl_u16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:272:vqrshl_u32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:273:vqrshl_u64 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:274:vqrshlq_s8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:275:vqrshlq_s16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:276:vqrshlq_s32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:277:vqrshlq_s64 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:278:vqrshlq_u8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:279:vqrshlq_u16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:280:vqrshlq_u32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:281:vqrshlq_u64 Neon cumulative saturation 1
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large shift amount with negative input) output:
+VQRSHL/VQRSHLQ:282:result_int8x8 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQRSHL/VQRSHLQ:283:result_int16x4 [] = { ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQRSHL/VQRSHLQ:284:result_int32x2 [] = { 80000000, 80000000,  }
+VQRSHL/VQRSHLQ:285:result_int64x1 [] = { 8000000000000000,  }
+VQRSHL/VQRSHLQ:286:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHL/VQRSHLQ:287:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQRSHL/VQRSHLQ:288:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQRSHL/VQRSHLQ:289:result_uint64x1 [] = { ffffffffffffffff,  }
+VQRSHL/VQRSHLQ:290:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:291:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:292:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:293:result_int8x16 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQRSHL/VQRSHLQ:294:result_int16x8 [] = { ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQRSHL/VQRSHLQ:295:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VQRSHL/VQRSHLQ:296:result_int64x2 [] = { 8000000000000000, 8000000000000000,  }
+VQRSHL/VQRSHLQ:297:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHL/VQRSHLQ:298:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQRSHL/VQRSHLQ:299:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQRSHL/VQRSHLQ:300:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQRSHL/VQRSHLQ:301:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:302:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:303:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large negative shift amount) cumulative saturation output:
+VQRSHL/VQRSHLQ:304:vqrshl_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:305:vqrshl_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:306:vqrshl_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:307:vqrshl_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:308:vqrshl_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:309:vqrshl_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:310:vqrshl_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:311:vqrshl_u64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:312:vqrshlq_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:313:vqrshlq_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:314:vqrshlq_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:315:vqrshlq_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:316:vqrshlq_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:317:vqrshlq_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:318:vqrshlq_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:319:vqrshlq_u64 Neon cumulative saturation 0
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large negative shift amount) output:
+VQRSHL/VQRSHLQ:320:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:321:result_int16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:322:result_int32x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:323:result_int64x1 [] = { 0,  }
+VQRSHL/VQRSHLQ:324:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:325:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:326:result_uint32x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:327:result_uint64x1 [] = { 0,  }
+VQRSHL/VQRSHLQ:328:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:329:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:330:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:331:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:332:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:333:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:334:result_int64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:335:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:336:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:337:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:338:result_uint64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:339:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:340:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:341:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large shift amount with 0 input) cumulative saturation output:
+VQRSHL/VQRSHLQ:342:vqrshl_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:343:vqrshl_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:344:vqrshl_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:345:vqrshl_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:346:vqrshl_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:347:vqrshl_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:348:vqrshl_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:349:vqrshl_u64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:350:vqrshlq_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:351:vqrshlq_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:352:vqrshlq_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:353:vqrshlq_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:354:vqrshlq_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:355:vqrshlq_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:356:vqrshlq_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:357:vqrshlq_u64 Neon cumulative saturation 0
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large shift amount with 0 input) output:
+VQRSHL/VQRSHLQ:358:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:359:result_int16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:360:result_int32x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:361:result_int64x1 [] = { 0,  }
+VQRSHL/VQRSHLQ:362:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:363:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:364:result_uint32x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:365:result_uint64x1 [] = { 0,  }
+VQRSHL/VQRSHLQ:366:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:367:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:368:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:369:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:370:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:371:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:372:result_int64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:373:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:374:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:375:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:376:result_uint64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:377:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:378:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:379:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VABA/VABAQ output:
+VABA/VABAQ:0:result_int8x8 [] = { fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd,  }
+VABA/VABAQ:1:result_int16x4 [] = { 16, 17, 18, 19,  }
+VABA/VABAQ:2:result_int32x2 [] = { 20, 21,  }
+VABA/VABAQ:3:result_int64x1 [] = { 3333333333333333,  }
+VABA/VABAQ:4:result_uint8x8 [] = { 53, 54, 55, 56, 57, 58, 59, 5a,  }
+VABA/VABAQ:5:result_uint16x4 [] = { 907, 908, 909, 90a,  }
+VABA/VABAQ:6:result_uint32x2 [] = { ffffffe7, ffffffe8,  }
+VABA/VABAQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VABA/VABAQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABA/VABAQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABA/VABAQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VABA/VABAQ:11:result_int8x16 [] = { 5e, 5f, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 6a, 6b, 6c, 6d,  }
+VABA/VABAQ:12:result_int16x8 [] = { b9c, b9d, b9e, b9f, ba0, ba1, ba2, ba3,  }
+VABA/VABAQ:13:result_int32x4 [] = { 26e0, 26e1, 26e2, 26e3,  }
+VABA/VABAQ:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VABA/VABAQ:15:result_uint8x16 [] = { f8, f9, fa, fb, fc, fd, fe, ff, 0, 1, 2, 3, 4, 5, 6, 7,  }
+VABA/VABAQ:16:result_uint16x8 [] = { fff9, fffa, fffb, fffc, fffd, fffe, ffff, 0,  }
+VABA/VABAQ:17:result_uint32x4 [] = { c, d, e, f,  }
+VABA/VABAQ:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VABA/VABAQ:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABA/VABAQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VABA/VABAQ:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VABAL output:
+VABAL:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABAL:2:result_int32x2 [] = { 33333333, 33333333,  }
+VABAL:3:result_int64x1 [] = { 3333333333333333,  }
+VABAL:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABAL:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VABAL:7:result_uint64x1 [] = { 3333333333333333,  }
+VABAL:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABAL:10:result_float32x2 [] = { 33333333, 33333333,  }
+VABAL:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:12:result_int16x8 [] = { fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd,  }
+VABAL:13:result_int32x4 [] = { 16, 17, 18, 19,  }
+VABAL:14:result_int64x2 [] = { 20, 21,  }
+VABAL:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:16:result_uint16x8 [] = { 53, 54, 55, 56, 57, 58, 59, 5a,  }
+VABAL:17:result_uint32x4 [] = { 907, 908, 909, 90a,  }
+VABAL:18:result_uint64x2 [] = { ffffffe7, ffffffe8,  }
+VABAL:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VABAL:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VABAL test intermediate overflow output:
+VABAL:22:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:23:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABAL:24:result_int32x2 [] = { 33333333, 33333333,  }
+VABAL:25:result_int64x1 [] = { 3333333333333333,  }
+VABAL:26:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:27:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABAL:28:result_uint32x2 [] = { 33333333, 33333333,  }
+VABAL:29:result_uint64x1 [] = { 3333333333333333,  }
+VABAL:30:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:31:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABAL:32:result_float32x2 [] = { 33333333, 33333333,  }
+VABAL:33:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:34:result_int16x8 [] = { ef, f0, f1, f2, f3, f4, f5, f6,  }
+VABAL:35:result_int32x4 [] = { ffef, fff0, fff1, fff2,  }
+VABAL:36:result_int64x2 [] = { ffffffef, fffffff0,  }
+VABAL:37:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:38:result_uint16x8 [] = { ee, ef, f0, f1, f2, f3, f4, f5,  }
+VABAL:39:result_uint32x4 [] = { ffe2, ffe3, ffe4, ffe5,  }
+VABAL:40:result_uint64x2 [] = { ffffffe7, ffffffe8,  }
+VABAL:41:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:42:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VABAL:43:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VABD/VABDQ output:
+VABD/VABDQ:0:result_int8x8 [] = { 11, 10, f, e, d, c, b, a,  }
+VABD/VABDQ:1:result_int16x4 [] = { 3, 2, 1, 0,  }
+VABD/VABDQ:2:result_int32x2 [] = { 18, 17,  }
+VABD/VABDQ:3:result_int64x1 [] = { 3333333333333333,  }
+VABD/VABDQ:4:result_uint8x8 [] = { ef, f0, f1, f2, f3, f4, f5, f6,  }
+VABD/VABDQ:5:result_uint16x4 [] = { ffe3, ffe4, ffe5, ffe6,  }
+VABD/VABDQ:6:result_uint32x2 [] = { ffffffe8, ffffffe9,  }
+VABD/VABDQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VABD/VABDQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABD/VABDQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABD/VABDQ:10:result_float32x2 [] = { 41c26666, 41ba6666,  }
+VABD/VABDQ:11:result_int8x16 [] = { 1a, 19, 18, 17, 16, 15, 14, 13, 12, 11, 10, f, e, d, c, b,  }
+VABD/VABDQ:12:result_int16x8 [] = { 4, 3, 2, 1, 0, 1, 2, 3,  }
+VABD/VABDQ:13:result_int32x4 [] = { 30, 2f, 2e, 2d,  }
+VABD/VABDQ:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VABD/VABDQ:15:result_uint8x16 [] = { e6, e7, e8, e9, ea, eb, ec, ed, ee, ef, f0, f1, f2, f3, f4, f5,  }
+VABD/VABDQ:16:result_uint16x8 [] = { ffe4, ffe5, ffe6, ffe7, ffe8, ffe9, ffea, ffeb,  }
+VABD/VABDQ:17:result_uint32x4 [] = { ffffffd0, ffffffd1, ffffffd2, ffffffd3,  }
+VABD/VABDQ:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VABD/VABDQ:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABD/VABDQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VABD/VABDQ:21:result_float32x4 [] = { 42407ae1, 423c7ae1, 42387ae1, 42347ae1,  }
+VABD/VABDQ FP special (-0.0):22:result_float32x4 [] = { 0, 0, 0, 0,  }
+VABD/VABDQ FP special (-0.0):23:result_float32x4 [] = { 0, 0, 0, 0,  }
+
+VABDL output:
+VABDL:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABDL:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABDL:2:result_int32x2 [] = { 33333333, 33333333,  }
+VABDL:3:result_int64x1 [] = { 3333333333333333,  }
+VABDL:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABDL:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABDL:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VABDL:7:result_uint64x1 [] = { 3333333333333333,  }
+VABDL:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABDL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABDL:10:result_float32x2 [] = { 33333333, 33333333,  }
+VABDL:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABDL:12:result_int16x8 [] = { 11, 10, f, e, d, c, b, a,  }
+VABDL:13:result_int32x4 [] = { 3, 2, 1, 0,  }
+VABDL:14:result_int64x2 [] = { 18, 17,  }
+VABDL:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABDL:16:result_uint16x8 [] = { ef, f0, f1, f2, f3, f4, f5, f6,  }
+VABDL:17:result_uint32x4 [] = { ffe3, ffe4, ffe5, ffe6,  }
+VABDL:18:result_uint64x2 [] = { ffffffe8, ffffffe9,  }
+VABDL:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABDL:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VABDL:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VAND/VANDQ output:
+VAND/VANDQ:0:result_int8x8 [] = { 0, 0, 2, 2, 0, 0, 2, 2,  }
+VAND/VANDQ:1:result_int16x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VAND/VANDQ:2:result_int32x2 [] = { 0, 1,  }
+VAND/VANDQ:3:result_int64x1 [] = { 60,  }
+VAND/VANDQ:4:result_uint8x8 [] = { 10, 10, 10, 10, 14, 14, 14, 14,  }
+VAND/VANDQ:5:result_uint16x4 [] = { 10, 10, 12, 12,  }
+VAND/VANDQ:6:result_uint32x2 [] = { 20, 20,  }
+VAND/VANDQ:7:result_uint64x1 [] = { 0,  }
+VAND/VANDQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VAND/VANDQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VAND/VANDQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VAND/VANDQ:11:result_int8x16 [] = { fffffff0, fffffff0, fffffff2, fffffff2, fffffff4, fffffff4, fffffff6, fffffff6, fffffff0, fffffff0, fffffff2, fffffff2, fffffff4, fffffff4, fffffff6, fffffff6,  }
+VAND/VANDQ:12:result_int16x8 [] = { ffffffe0, ffffffe0, ffffffe0, ffffffe0, ffffffe4, ffffffe4, ffffffe4, ffffffe4,  }
+VAND/VANDQ:13:result_int32x4 [] = { ffffffe0, ffffffe0, ffffffe2, ffffffe2,  }
+VAND/VANDQ:14:result_int64x2 [] = { 10, 10,  }
+VAND/VANDQ:15:result_uint8x16 [] = { 0, 0, 0, 0, 4, 4, 4, 4, 8, 8, 8, 8, c, c, c, c,  }
+VAND/VANDQ:16:result_uint16x8 [] = { 0, 1, 2, 3, 0, 1, 2, 3,  }
+VAND/VANDQ:17:result_uint32x4 [] = { 30, 31, 32, 33,  }
+VAND/VANDQ:18:result_uint64x2 [] = { 0, 1,  }
+VAND/VANDQ:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VAND/VANDQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VAND/VANDQ:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VORR/VORRQ output:
+VORR/VORRQ:0:result_int8x8 [] = { fffffff2, fffffff3, fffffff2, fffffff3, fffffff6, fffffff7, fffffff6, fffffff7,  }
+VORR/VORRQ:1:result_int16x4 [] = { fffffffc, fffffffd, fffffffe, ffffffff,  }
+VORR/VORRQ:2:result_int32x2 [] = { fffffff3, fffffff3,  }
+VORR/VORRQ:3:result_int64x1 [] = { fffffffffffffff4,  }
+VORR/VORRQ:4:result_uint8x8 [] = { f4, f5, f6, f7, f4, f5, f6, f7,  }
+VORR/VORRQ:5:result_uint16x4 [] = { fffe, ffff, fffe, ffff,  }
+VORR/VORRQ:6:result_uint32x2 [] = { fffffff8, fffffff9,  }
+VORR/VORRQ:7:result_uint64x1 [] = { fffffffffffffff2,  }
+VORR/VORRQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VORR/VORRQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VORR/VORRQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VORR/VORRQ:11:result_int8x16 [] = { fffffff6, fffffff7, fffffff6, fffffff7, fffffff6, fffffff7, fffffff6, fffffff7, fffffffe, ffffffff, fffffffe, ffffffff, fffffffe, ffffffff, fffffffe, ffffffff,  }
+VORR/VORRQ:12:result_int16x8 [] = { fffffffc, fffffffd, fffffffe, ffffffff, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VORR/VORRQ:13:result_int32x4 [] = { fffffff2, fffffff3, fffffff2, fffffff3,  }
+VORR/VORRQ:14:result_int64x2 [] = { fffffffffffffff8, fffffffffffffff9,  }
+VORR/VORRQ:15:result_uint8x16 [] = { fc, fd, fe, ff, fc, fd, fe, ff, fc, fd, fe, ff, fc, fd, fe, ff,  }
+VORR/VORRQ:16:result_uint16x8 [] = { fff3, fff3, fff3, fff3, fff7, fff7, fff7, fff7,  }
+VORR/VORRQ:17:result_uint32x4 [] = { fffffff7, fffffff7, fffffff7, fffffff7,  }
+VORR/VORRQ:18:result_uint64x2 [] = { fffffffffffffff3, fffffffffffffff3,  }
+VORR/VORRQ:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VORR/VORRQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VORR/VORRQ:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VORN/VORNQ output:
+VORN/VORNQ:0:result_int8x8 [] = { fffffffd, fffffffd, ffffffff, ffffffff, fffffffd, fffffffd, ffffffff, ffffffff,  }
+VORN/VORNQ:1:result_int16x4 [] = { fffffff3, fffffff3, fffffff3, fffffff3,  }
+VORN/VORNQ:2:result_int32x2 [] = { fffffffc, fffffffd,  }
+VORN/VORNQ:3:result_int64x1 [] = { fffffffffffffffb,  }
+VORN/VORNQ:4:result_uint8x8 [] = { fb, fb, fb, fb, ff, ff, ff, ff,  }
+VORN/VORNQ:5:result_uint16x4 [] = { fff1, fff1, fff3, fff3,  }
+VORN/VORNQ:6:result_uint32x2 [] = { fffffff7, fffffff7,  }
+VORN/VORNQ:7:result_uint64x1 [] = { fffffffffffffffd,  }
+VORN/VORNQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VORN/VORNQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VORN/VORNQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VORN/VORNQ:11:result_int8x16 [] = { fffffff9, fffffff9, fffffffb, fffffffb, fffffffd, fffffffd, ffffffff, ffffffff, fffffff9, fffffff9, fffffffb, fffffffb, fffffffd, fffffffd, ffffffff, ffffffff,  }
+VORN/VORNQ:12:result_int16x8 [] = { fffffff3, fffffff3, fffffff3, fffffff3, fffffff7, fffffff7, fffffff7, fffffff7,  }
+VORN/VORNQ:13:result_int32x4 [] = { fffffffd, fffffffd, ffffffff, ffffffff,  }
+VORN/VORNQ:14:result_int64x2 [] = { fffffffffffffff7, fffffffffffffff7,  }
+VORN/VORNQ:15:result_uint8x16 [] = { f3, f3, f3, f3, f7, f7, f7, f7, fb, fb, fb, fb, ff, ff, ff, ff,  }
+VORN/VORNQ:16:result_uint16x8 [] = { fffc, fffd, fffe, ffff, fffc, fffd, fffe, ffff,  }
+VORN/VORNQ:17:result_uint32x4 [] = { fffffff8, fffffff9, fffffffa, fffffffb,  }
+VORN/VORNQ:18:result_uint64x2 [] = { fffffffffffffffc, fffffffffffffffd,  }
+VORN/VORNQ:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VORN/VORNQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VORN/VORNQ:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VEOR/VEORQ output:
+VEOR/VEORQ:0:result_int8x8 [] = { fffffff2, fffffff3, fffffff0, fffffff1, fffffff6, fffffff7, fffffff4, fffffff5,  }
+VEOR/VEORQ:1:result_int16x4 [] = { c, d, e, f,  }
+VEOR/VEORQ:2:result_int32x2 [] = { fffffff3, fffffff2,  }
+VEOR/VEORQ:3:result_int64x1 [] = { ffffffffffffff94,  }
+VEOR/VEORQ:4:result_uint8x8 [] = { e4, e5, e6, e7, e0, e1, e2, e3,  }
+VEOR/VEORQ:5:result_uint16x4 [] = { ffee, ffef, ffec, ffed,  }
+VEOR/VEORQ:6:result_uint32x2 [] = { ffffffd8, ffffffd9,  }
+VEOR/VEORQ:7:result_uint64x1 [] = { fffffffffffffff2,  }
+VEOR/VEORQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VEOR/VEORQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VEOR/VEORQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VEOR/VEORQ:11:result_int8x16 [] = { 6, 7, 4, 5, 2, 3, 0, 1, e, f, c, d, a, b, 8, 9,  }
+VEOR/VEORQ:12:result_int16x8 [] = { 1c, 1d, 1e, 1f, 18, 19, 1a, 1b,  }
+VEOR/VEORQ:13:result_int32x4 [] = { 12, 13, 10, 11,  }
+VEOR/VEORQ:14:result_int64x2 [] = { ffffffffffffffe8, ffffffffffffffe9,  }
+VEOR/VEORQ:15:result_uint8x16 [] = { fc, fd, fe, ff, f8, f9, fa, fb, f4, f5, f6, f7, f0, f1, f2, f3,  }
+VEOR/VEORQ:16:result_uint16x8 [] = { fff3, fff2, fff1, fff0, fff7, fff6, fff5, fff4,  }
+VEOR/VEORQ:17:result_uint32x4 [] = { ffffffc7, ffffffc6, ffffffc5, ffffffc4,  }
+VEOR/VEORQ:18:result_uint64x2 [] = { fffffffffffffff3, fffffffffffffff2,  }
+VEOR/VEORQ:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VEOR/VEORQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VEOR/VEORQ:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VBIC/VBICQ output:
+VBIC/VBICQ:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff0, fffffff1, fffffff4, fffffff5, fffffff4, fffffff5,  }
+VBIC/VBICQ:1:result_int16x4 [] = { 0, 1, 2, 3,  }
+VBIC/VBICQ:2:result_int32x2 [] = { fffffff0, fffffff0,  }
+VBIC/VBICQ:3:result_int64x1 [] = { ffffffffffffff90,  }
+VBIC/VBICQ:4:result_uint8x8 [] = { e0, e1, e2, e3, e0, e1, e2, e3,  }
+VBIC/VBICQ:5:result_uint16x4 [] = { ffe0, ffe1, ffe0, ffe1,  }
+VBIC/VBICQ:6:result_uint32x2 [] = { ffffffd0, ffffffd1,  }
+VBIC/VBICQ:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VBIC/VBICQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VBIC/VBICQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VBIC/VBICQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VBIC/VBICQ:11:result_int8x16 [] = { 0, 1, 0, 1, 0, 1, 0, 1, 8, 9, 8, 9, 8, 9, 8, 9,  }
+VBIC/VBICQ:12:result_int16x8 [] = { 10, 11, 12, 13, 10, 11, 12, 13,  }
+VBIC/VBICQ:13:result_int32x4 [] = { 10, 11, 10, 11,  }
+VBIC/VBICQ:14:result_int64x2 [] = { ffffffffffffffe0, ffffffffffffffe1,  }
+VBIC/VBICQ:15:result_uint8x16 [] = { f0, f1, f2, f3, f0, f1, f2, f3, f0, f1, f2, f3, f0, f1, f2, f3,  }
+VBIC/VBICQ:16:result_uint16x8 [] = { fff0, fff0, fff0, fff0, fff4, fff4, fff4, fff4,  }
+VBIC/VBICQ:17:result_uint32x4 [] = { ffffffc0, ffffffc0, ffffffc0, ffffffc0,  }
+VBIC/VBICQ:18:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VBIC/VBICQ:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VBIC/VBICQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VBIC/VBICQ:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VCREATE output:
+VCREATE:0:result_int8x8 [] = { fffffff0, ffffffde, ffffffbc, ffffff9a, 78, 56, 34, 12,  }
+VCREATE:1:result_int16x4 [] = { ffffdef0, ffff9abc, 5678, 1234,  }
+VCREATE:2:result_int32x2 [] = { 9abcdef0, 12345678,  }
+VCREATE:3:result_int64x1 [] = { 123456789abcdef0,  }
+VCREATE:4:result_uint8x8 [] = { f0, de, bc, 9a, 78, 56, 34, 12,  }
+VCREATE:5:result_uint16x4 [] = { def0, 9abc, 5678, 1234,  }
+VCREATE:6:result_uint32x2 [] = { 9abcdef0, 12345678,  }
+VCREATE:7:result_uint64x1 [] = { 123456789abcdef0,  }
+VCREATE:8:result_poly8x8 [] = { f0, de, bc, 9a, 78, 56, 34, 12,  }
+VCREATE:9:result_poly16x4 [] = { def0, 9abc, 5678, 1234,  }
+VCREATE:10:result_float32x2 [] = { 9abcdef0, 12345678,  }
+VCREATE:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCREATE:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCREATE:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCREATE:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCREATE:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCREATE:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCREATE:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCREATE:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCREATE:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCREATE:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCREATE:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VLD2_LANE/VLD2Q_LANE chunk 0 output:
+VLD2_LANE/VLD2Q_LANE:0:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa,  }
+VLD2_LANE/VLD2Q_LANE:1:result_int16x4 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD2_LANE/VLD2Q_LANE:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD2_LANE/VLD2Q_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VLD2_LANE/VLD2Q_LANE:4:result_uint8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD2_LANE/VLD2Q_LANE:5:result_uint16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD2_LANE/VLD2Q_LANE:6:result_uint32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VLD2_LANE/VLD2Q_LANE:8:result_poly8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD2_LANE/VLD2Q_LANE:9:result_poly16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD2_LANE/VLD2Q_LANE:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD2_LANE/VLD2Q_LANE:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_LANE/VLD2Q_LANE:12:result_int16x8 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD2_LANE/VLD2Q_LANE:13:result_int32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2_LANE/VLD2Q_LANE:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_LANE/VLD2Q_LANE:16:result_uint16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD2_LANE/VLD2Q_LANE:17:result_uint32x4 [] = { fffffff0, fffffff1, aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2_LANE/VLD2Q_LANE:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_LANE/VLD2Q_LANE:20:result_poly16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD2_LANE/VLD2Q_LANE:21:result_float32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+
+VLD2_LANE/VLD2Q_LANE chunk 1 output:
+VLD2_LANE/VLD2Q_LANE:22:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, fffffff0, fffffff1,  }
+VLD2_LANE/VLD2Q_LANE:23:result_int16x4 [] = { fffffff0, fffffff1, ffffaaaa, ffffaaaa,  }
+VLD2_LANE/VLD2Q_LANE:24:result_int32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:25:result_int64x1 [] = { 3333333333333333,  }
+VLD2_LANE/VLD2Q_LANE:26:result_uint8x8 [] = { f0, f1, aa, aa, aa, aa, aa, aa,  }
+VLD2_LANE/VLD2Q_LANE:27:result_uint16x4 [] = { aaaa, aaaa, fff0, fff1,  }
+VLD2_LANE/VLD2Q_LANE:28:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD2_LANE/VLD2Q_LANE:29:result_uint64x1 [] = { 3333333333333333,  }
+VLD2_LANE/VLD2Q_LANE:30:result_poly8x8 [] = { f0, f1, aa, aa, aa, aa, aa, aa,  }
+VLD2_LANE/VLD2Q_LANE:31:result_poly16x4 [] = { aaaa, aaaa, fff0, fff1,  }
+VLD2_LANE/VLD2Q_LANE:32:result_float32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:33:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_LANE/VLD2Q_LANE:34:result_int16x8 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, fffffff0, fffffff1, ffffaaaa, ffffaaaa,  }
+VLD2_LANE/VLD2Q_LANE:35:result_int32x4 [] = { fffffff0, fffffff1, aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:36:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2_LANE/VLD2Q_LANE:37:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_LANE/VLD2Q_LANE:38:result_uint16x8 [] = { aaaa, aaaa, fff0, fff1, aaaa, aaaa, aaaa, aaaa,  }
+VLD2_LANE/VLD2Q_LANE:39:result_uint32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:40:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2_LANE/VLD2Q_LANE:41:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_LANE/VLD2Q_LANE:42:result_poly16x8 [] = { aaaa, aaaa, fff0, fff1, aaaa, aaaa, aaaa, aaaa,  }
+VLD2_LANE/VLD2Q_LANE:43:result_float32x4 [] = { c1800000, c1700000, aaaaaaaa, aaaaaaaa,  }
+
+VLD3_LANE/VLD3Q_LANE chunk 0 output:
+VLD3_LANE/VLD3Q_LANE:0:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa,  }
+VLD3_LANE/VLD3Q_LANE:1:result_int16x4 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD3_LANE/VLD3Q_LANE:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD3_LANE/VLD3Q_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:4:result_uint8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD3_LANE/VLD3Q_LANE:5:result_uint16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:6:result_uint32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:8:result_poly8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD3_LANE/VLD3Q_LANE:9:result_poly16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD3_LANE/VLD3Q_LANE:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:12:result_int16x8 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD3_LANE/VLD3Q_LANE:13:result_int32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:16:result_uint16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:17:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:20:result_poly16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:21:result_float32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+
+VLD3_LANE/VLD3Q_LANE chunk 1 output:
+VLD3_LANE/VLD3Q_LANE:22:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa,  }
+VLD3_LANE/VLD3Q_LANE:23:result_int16x4 [] = { ffffaaaa, ffffaaaa, fffffff0, fffffff1,  }
+VLD3_LANE/VLD3Q_LANE:24:result_int32x2 [] = { fffffff2, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:25:result_int64x1 [] = { 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:26:result_uint8x8 [] = { aa, aa, aa, aa, f0, f1, f2, aa,  }
+VLD3_LANE/VLD3Q_LANE:27:result_uint16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:28:result_uint32x2 [] = { aaaaaaaa, fffffff0,  }
+VLD3_LANE/VLD3Q_LANE:29:result_uint64x1 [] = { 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:30:result_poly8x8 [] = { aa, aa, aa, aa, f0, f1, f2, aa,  }
+VLD3_LANE/VLD3Q_LANE:31:result_poly16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:32:result_float32x2 [] = { c1600000, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:33:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:34:result_int16x8 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD3_LANE/VLD3Q_LANE:35:result_int32x4 [] = { aaaaaaaa, aaaaaaaa, fffffff0, fffffff1,  }
+VLD3_LANE/VLD3Q_LANE:36:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:37:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:38:result_uint16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, fff0,  }
+VLD3_LANE/VLD3Q_LANE:39:result_uint32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:40:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:41:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:42:result_poly16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, fff0,  }
+VLD3_LANE/VLD3Q_LANE:43:result_float32x4 [] = { aaaaaaaa, aaaaaaaa, c1800000, c1700000,  }
+
+VLD3_LANE/VLD3Q_LANE chunk 2 output:
+VLD3_LANE/VLD3Q_LANE:44:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, fffffff0, fffffff1, fffffff2,  }
+VLD3_LANE/VLD3Q_LANE:45:result_int16x4 [] = { fffffff2, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD3_LANE/VLD3Q_LANE:46:result_int32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:47:result_int64x1 [] = { 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:48:result_uint8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD3_LANE/VLD3Q_LANE:49:result_uint16x4 [] = { aaaa, fff0, fff1, fff2,  }
+VLD3_LANE/VLD3Q_LANE:50:result_uint32x2 [] = { fffffff1, fffffff2,  }
+VLD3_LANE/VLD3Q_LANE:51:result_uint64x1 [] = { 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:52:result_poly8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD3_LANE/VLD3Q_LANE:53:result_poly16x4 [] = { aaaa, fff0, fff1, fff2,  }
+VLD3_LANE/VLD3Q_LANE:54:result_float32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:55:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:56:result_int16x8 [] = { ffffaaaa, ffffaaaa, fffffff0, fffffff1, fffffff2, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD3_LANE/VLD3Q_LANE:57:result_int32x4 [] = { fffffff2, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:58:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:59:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:60:result_uint16x8 [] = { fff1, fff2, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:61:result_uint32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:62:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:63:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:64:result_poly16x8 [] = { fff1, fff2, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:65:result_float32x4 [] = { c1600000, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+
+VLD4_LANE/VLD4Q_LANE chunk 0 output:
+VLD4_LANE/VLD4Q_LANE:0:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa,  }
+VLD4_LANE/VLD4Q_LANE:1:result_int16x4 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD4_LANE/VLD4Q_LANE:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD4_LANE/VLD4Q_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:4:result_uint8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD4_LANE/VLD4Q_LANE:5:result_uint16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:6:result_uint32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:8:result_poly8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD4_LANE/VLD4Q_LANE:9:result_poly16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD4_LANE/VLD4Q_LANE:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:12:result_int16x8 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD4_LANE/VLD4Q_LANE:13:result_int32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:16:result_uint16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:17:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_LANE/VLD4Q_LANE:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:20:result_poly16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:21:result_float32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+
+VLD4_LANE/VLD4Q_LANE chunk 1 output:
+VLD4_LANE/VLD4Q_LANE:22:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa,  }
+VLD4_LANE/VLD4Q_LANE:23:result_int16x4 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD4_LANE/VLD4Q_LANE:24:result_int32x2 [] = { fffffff2, fffffff3,  }
+VLD4_LANE/VLD4Q_LANE:25:result_int64x1 [] = { 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:26:result_uint8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD4_LANE/VLD4Q_LANE:27:result_uint16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:28:result_uint32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:29:result_uint64x1 [] = { 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:30:result_poly8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD4_LANE/VLD4Q_LANE:31:result_poly16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:32:result_float32x2 [] = { c1600000, c1500000,  }
+VLD4_LANE/VLD4Q_LANE:33:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:34:result_int16x8 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD4_LANE/VLD4Q_LANE:35:result_int32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:36:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:37:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:38:result_uint16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:39:result_uint32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:40:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:41:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:42:result_poly16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:43:result_float32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+
+VLD4_LANE/VLD4Q_LANE chunk 2 output:
+VLD4_LANE/VLD4Q_LANE:44:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa,  }
+VLD4_LANE/VLD4Q_LANE:45:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_LANE/VLD4Q_LANE:46:result_int32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:47:result_int64x1 [] = { 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:48:result_uint8x8 [] = { f0, f1, f2, f3, aa, aa, aa, aa,  }
+VLD4_LANE/VLD4Q_LANE:49:result_uint16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:50:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD4_LANE/VLD4Q_LANE:51:result_uint64x1 [] = { 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:52:result_poly8x8 [] = { f0, f1, f2, f3, aa, aa, aa, aa,  }
+VLD4_LANE/VLD4Q_LANE:53:result_poly16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:54:result_float32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:55:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:56:result_int16x8 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD4_LANE/VLD4Q_LANE:57:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_LANE/VLD4Q_LANE:58:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:59:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:60:result_uint16x8 [] = { aaaa, aaaa, aaaa, aaaa, fff0, fff1, fff2, fff3,  }
+VLD4_LANE/VLD4Q_LANE:61:result_uint32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:62:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:63:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:64:result_poly16x8 [] = { aaaa, aaaa, aaaa, aaaa, fff0, fff1, fff2, fff3,  }
+VLD4_LANE/VLD4Q_LANE:65:result_float32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+
+VLD4_LANE/VLD4Q_LANE chunk 3 output:
+VLD4_LANE/VLD4Q_LANE:66:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_LANE/VLD4Q_LANE:67:result_int16x4 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD4_LANE/VLD4Q_LANE:68:result_int32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:69:result_int64x1 [] = { 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:70:result_uint8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD4_LANE/VLD4Q_LANE:71:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_LANE/VLD4Q_LANE:72:result_uint32x2 [] = { fffffff2, fffffff3,  }
+VLD4_LANE/VLD4Q_LANE:73:result_uint64x1 [] = { 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:74:result_poly8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD4_LANE/VLD4Q_LANE:75:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_LANE/VLD4Q_LANE:76:result_float32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:77:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:78:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD4_LANE/VLD4Q_LANE:79:result_int32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:80:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:81:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:82:result_uint16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:83:result_uint32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:84:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:85:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:86:result_poly16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:87:result_float32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+
+VLD2_DUP/VLD2Q_DUP chunk 0 output:
+VLD2_DUP/VLD2Q_DUP:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff0, fffffff1, fffffff0, fffffff1, fffffff0, fffffff1,  }
+VLD2_DUP/VLD2Q_DUP:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff0, fffffff1,  }
+VLD2_DUP/VLD2Q_DUP:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD2_DUP/VLD2Q_DUP:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD2_DUP/VLD2Q_DUP:4:result_uint8x8 [] = { f0, f1, f0, f1, f0, f1, f0, f1,  }
+VLD2_DUP/VLD2Q_DUP:5:result_uint16x4 [] = { fff0, fff1, fff0, fff1,  }
+VLD2_DUP/VLD2Q_DUP:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD2_DUP/VLD2Q_DUP:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD2_DUP/VLD2Q_DUP:8:result_poly8x8 [] = { f0, f1, f0, f1, f0, f1, f0, f1,  }
+VLD2_DUP/VLD2Q_DUP:9:result_poly16x4 [] = { fff0, fff1, fff0, fff1,  }
+VLD2_DUP/VLD2Q_DUP:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD2_DUP/VLD2Q_DUP:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_DUP/VLD2Q_DUP:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD2_DUP/VLD2Q_DUP:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD2_DUP/VLD2Q_DUP:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2_DUP/VLD2Q_DUP:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_DUP/VLD2Q_DUP:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD2_DUP/VLD2Q_DUP:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD2_DUP/VLD2Q_DUP:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2_DUP/VLD2Q_DUP:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_DUP/VLD2Q_DUP:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD2_DUP/VLD2Q_DUP:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VLD2_DUP/VLD2Q_DUP chunk 1 output:
+VLD2_DUP/VLD2Q_DUP:22:result_int8x8 [] = { fffffff0, fffffff1, fffffff0, fffffff1, fffffff0, fffffff1, fffffff0, fffffff1,  }
+VLD2_DUP/VLD2Q_DUP:23:result_int16x4 [] = { fffffff0, fffffff1, fffffff0, fffffff1,  }
+VLD2_DUP/VLD2Q_DUP:24:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD2_DUP/VLD2Q_DUP:25:result_int64x1 [] = { fffffffffffffff1,  }
+VLD2_DUP/VLD2Q_DUP:26:result_uint8x8 [] = { f0, f1, f0, f1, f0, f1, f0, f1,  }
+VLD2_DUP/VLD2Q_DUP:27:result_uint16x4 [] = { fff0, fff1, fff0, fff1,  }
+VLD2_DUP/VLD2Q_DUP:28:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD2_DUP/VLD2Q_DUP:29:result_uint64x1 [] = { fffffffffffffff1,  }
+VLD2_DUP/VLD2Q_DUP:30:result_poly8x8 [] = { f0, f1, f0, f1, f0, f1, f0, f1,  }
+VLD2_DUP/VLD2Q_DUP:31:result_poly16x4 [] = { fff0, fff1, fff0, fff1,  }
+VLD2_DUP/VLD2Q_DUP:32:result_float32x2 [] = { c1800000, c1700000,  }
+VLD2_DUP/VLD2Q_DUP:33:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_DUP/VLD2Q_DUP:34:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD2_DUP/VLD2Q_DUP:35:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD2_DUP/VLD2Q_DUP:36:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2_DUP/VLD2Q_DUP:37:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_DUP/VLD2Q_DUP:38:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD2_DUP/VLD2Q_DUP:39:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD2_DUP/VLD2Q_DUP:40:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2_DUP/VLD2Q_DUP:41:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_DUP/VLD2Q_DUP:42:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD2_DUP/VLD2Q_DUP:43:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VLD3_DUP/VLD3Q_DUP chunk 0 output:
+VLD3_DUP/VLD3Q_DUP:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff0, fffffff1, fffffff2, fffffff0, fffffff1,  }
+VLD3_DUP/VLD3Q_DUP:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff0,  }
+VLD3_DUP/VLD3Q_DUP:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD3_DUP/VLD3Q_DUP:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD3_DUP/VLD3Q_DUP:4:result_uint8x8 [] = { f0, f1, f2, f0, f1, f2, f0, f1,  }
+VLD3_DUP/VLD3Q_DUP:5:result_uint16x4 [] = { fff0, fff1, fff2, fff0,  }
+VLD3_DUP/VLD3Q_DUP:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD3_DUP/VLD3Q_DUP:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD3_DUP/VLD3Q_DUP:8:result_poly8x8 [] = { f0, f1, f2, f0, f1, f2, f0, f1,  }
+VLD3_DUP/VLD3Q_DUP:9:result_poly16x4 [] = { fff0, fff1, fff2, fff0,  }
+VLD3_DUP/VLD3Q_DUP:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD3_DUP/VLD3Q_DUP:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD3_DUP/VLD3Q_DUP:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_DUP/VLD3Q_DUP:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD3_DUP/VLD3Q_DUP:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_DUP/VLD3Q_DUP:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VLD3_DUP/VLD3Q_DUP chunk 1 output:
+VLD3_DUP/VLD3Q_DUP:22:result_int8x8 [] = { fffffff2, fffffff0, fffffff1, fffffff2, fffffff0, fffffff1, fffffff2, fffffff0,  }
+VLD3_DUP/VLD3Q_DUP:23:result_int16x4 [] = { fffffff1, fffffff2, fffffff0, fffffff1,  }
+VLD3_DUP/VLD3Q_DUP:24:result_int32x2 [] = { fffffff2, fffffff0,  }
+VLD3_DUP/VLD3Q_DUP:25:result_int64x1 [] = { fffffffffffffff1,  }
+VLD3_DUP/VLD3Q_DUP:26:result_uint8x8 [] = { f2, f0, f1, f2, f0, f1, f2, f0,  }
+VLD3_DUP/VLD3Q_DUP:27:result_uint16x4 [] = { fff1, fff2, fff0, fff1,  }
+VLD3_DUP/VLD3Q_DUP:28:result_uint32x2 [] = { fffffff2, fffffff0,  }
+VLD3_DUP/VLD3Q_DUP:29:result_uint64x1 [] = { fffffffffffffff1,  }
+VLD3_DUP/VLD3Q_DUP:30:result_poly8x8 [] = { f2, f0, f1, f2, f0, f1, f2, f0,  }
+VLD3_DUP/VLD3Q_DUP:31:result_poly16x4 [] = { fff1, fff2, fff0, fff1,  }
+VLD3_DUP/VLD3Q_DUP:32:result_float32x2 [] = { c1600000, c1800000,  }
+VLD3_DUP/VLD3Q_DUP:33:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:34:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:35:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD3_DUP/VLD3Q_DUP:36:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_DUP/VLD3Q_DUP:37:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:38:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:39:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD3_DUP/VLD3Q_DUP:40:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_DUP/VLD3Q_DUP:41:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:42:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:43:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VLD3_DUP/VLD3Q_DUP chunk 2 output:
+VLD3_DUP/VLD3Q_DUP:44:result_int8x8 [] = { fffffff1, fffffff2, fffffff0, fffffff1, fffffff2, fffffff0, fffffff1, fffffff2,  }
+VLD3_DUP/VLD3Q_DUP:45:result_int16x4 [] = { fffffff2, fffffff0, fffffff1, fffffff2,  }
+VLD3_DUP/VLD3Q_DUP:46:result_int32x2 [] = { fffffff1, fffffff2,  }
+VLD3_DUP/VLD3Q_DUP:47:result_int64x1 [] = { fffffffffffffff2,  }
+VLD3_DUP/VLD3Q_DUP:48:result_uint8x8 [] = { f1, f2, f0, f1, f2, f0, f1, f2,  }
+VLD3_DUP/VLD3Q_DUP:49:result_uint16x4 [] = { fff2, fff0, fff1, fff2,  }
+VLD3_DUP/VLD3Q_DUP:50:result_uint32x2 [] = { fffffff1, fffffff2,  }
+VLD3_DUP/VLD3Q_DUP:51:result_uint64x1 [] = { fffffffffffffff2,  }
+VLD3_DUP/VLD3Q_DUP:52:result_poly8x8 [] = { f1, f2, f0, f1, f2, f0, f1, f2,  }
+VLD3_DUP/VLD3Q_DUP:53:result_poly16x4 [] = { fff2, fff0, fff1, fff2,  }
+VLD3_DUP/VLD3Q_DUP:54:result_float32x2 [] = { c1700000, c1600000,  }
+VLD3_DUP/VLD3Q_DUP:55:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:56:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:57:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD3_DUP/VLD3Q_DUP:58:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_DUP/VLD3Q_DUP:59:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:60:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:61:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD3_DUP/VLD3Q_DUP:62:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_DUP/VLD3Q_DUP:63:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:64:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:65:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VLD4_DUP/VLD4Q_DUP chunk 0 output:
+VLD4_DUP/VLD4Q_DUP:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD4_DUP/VLD4Q_DUP:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD4_DUP/VLD4Q_DUP:4:result_uint8x8 [] = { f0, f1, f2, f3, f0, f1, f2, f3,  }
+VLD4_DUP/VLD4Q_DUP:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_DUP/VLD4Q_DUP:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD4_DUP/VLD4Q_DUP:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD4_DUP/VLD4Q_DUP:8:result_poly8x8 [] = { f0, f1, f2, f3, f0, f1, f2, f3,  }
+VLD4_DUP/VLD4Q_DUP:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_DUP/VLD4Q_DUP:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD4_DUP/VLD4Q_DUP:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_DUP/VLD4Q_DUP:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_DUP/VLD4Q_DUP:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VLD4_DUP/VLD4Q_DUP chunk 1 output:
+VLD4_DUP/VLD4Q_DUP:22:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:23:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:24:result_int32x2 [] = { fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:25:result_int64x1 [] = { fffffffffffffff1,  }
+VLD4_DUP/VLD4Q_DUP:26:result_uint8x8 [] = { f0, f1, f2, f3, f0, f1, f2, f3,  }
+VLD4_DUP/VLD4Q_DUP:27:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_DUP/VLD4Q_DUP:28:result_uint32x2 [] = { fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:29:result_uint64x1 [] = { fffffffffffffff1,  }
+VLD4_DUP/VLD4Q_DUP:30:result_poly8x8 [] = { f0, f1, f2, f3, f0, f1, f2, f3,  }
+VLD4_DUP/VLD4Q_DUP:31:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_DUP/VLD4Q_DUP:32:result_float32x2 [] = { c1600000, c1500000,  }
+VLD4_DUP/VLD4Q_DUP:33:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:34:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:35:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:36:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_DUP/VLD4Q_DUP:37:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:38:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:39:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:40:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_DUP/VLD4Q_DUP:41:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:42:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:43:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VLD4_DUP/VLD4Q_DUP chunk 2 output:
+VLD4_DUP/VLD4Q_DUP:44:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:45:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:46:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD4_DUP/VLD4Q_DUP:47:result_int64x1 [] = { fffffffffffffff2,  }
+VLD4_DUP/VLD4Q_DUP:48:result_uint8x8 [] = { f0, f1, f2, f3, f0, f1, f2, f3,  }
+VLD4_DUP/VLD4Q_DUP:49:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_DUP/VLD4Q_DUP:50:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD4_DUP/VLD4Q_DUP:51:result_uint64x1 [] = { fffffffffffffff2,  }
+VLD4_DUP/VLD4Q_DUP:52:result_poly8x8 [] = { f0, f1, f2, f3, f0, f1, f2, f3,  }
+VLD4_DUP/VLD4Q_DUP:53:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_DUP/VLD4Q_DUP:54:result_float32x2 [] = { c1800000, c1700000,  }
+VLD4_DUP/VLD4Q_DUP:55:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:56:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:57:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:58:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_DUP/VLD4Q_DUP:59:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:60:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:61:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:62:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_DUP/VLD4Q_DUP:63:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:64:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:65:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VLD4_DUP/VLD4Q_DUP chunk 3 output:
+VLD4_DUP/VLD4Q_DUP:66:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:67:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:68:result_int32x2 [] = { fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:69:result_int64x1 [] = { fffffffffffffff3,  }
+VLD4_DUP/VLD4Q_DUP:70:result_uint8x8 [] = { f0, f1, f2, f3, f0, f1, f2, f3,  }
+VLD4_DUP/VLD4Q_DUP:71:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_DUP/VLD4Q_DUP:72:result_uint32x2 [] = { fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:73:result_uint64x1 [] = { fffffffffffffff3,  }
+VLD4_DUP/VLD4Q_DUP:74:result_poly8x8 [] = { f0, f1, f2, f3, f0, f1, f2, f3,  }
+VLD4_DUP/VLD4Q_DUP:75:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_DUP/VLD4Q_DUP:76:result_float32x2 [] = { c1600000, c1500000,  }
+VLD4_DUP/VLD4Q_DUP:77:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:78:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:79:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:80:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_DUP/VLD4Q_DUP:81:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:82:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:83:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:84:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_DUP/VLD4Q_DUP:85:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:86:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:87:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VMLA output:
+VMLA:0:result_int8x8 [] = { ffffffdf, ffffffe0, ffffffe1, ffffffe2, ffffffe3, ffffffe4, ffffffe5, ffffffe6,  }
+VMLA:1:result_int16x4 [] = { 1f8c, 1f8d, 1f8e, 1f8f,  }
+VMLA:2:result_int32x2 [] = { 2bf7, 2bf8,  }
+VMLA:3:result_int64x1 [] = { 3333333333333333,  }
+VMLA:4:result_uint8x8 [] = { 20, 21, 22, 23, 24, 25, 26, 27,  }
+VMLA:5:result_uint16x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLA:6:result_uint32x2 [] = { 43ac, 43ad,  }
+VMLA:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLA:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLA:10:result_float32x2 [] = { 43a14e76, 43a1ce76,  }
+VMLA:11:result_int8x16 [] = { f, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 1a, 1b, 1c, 1d, 1e,  }
+VMLA:12:result_int16x8 [] = { 4830, 4831, 4832, 4833, 4834, 4835, 4836, 4837,  }
+VMLA:13:result_int32x4 [] = { 470f, 4710, 4711, 4712,  }
+VMLA:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLA:15:result_uint8x16 [] = { ac, ad, ae, af, b0, b1, b2, b3, b4, b5, b6, b7, b8, b9, ba, bb,  }
+VMLA:16:result_uint16x8 [] = { 3e07, 3e08, 3e09, 3e0a, 3e0b, 3e0c, 3e0d, 3e0e,  }
+VMLA:17:result_uint32x4 [] = { 3620, 3621, 3622, 3623,  }
+VMLA:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLA:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLA:21:result_float32x4 [] = { 45f0ae15, 45f0b615, 45f0be15, 45f0c615,  }
+
+VMLS output:
+VMLS:0:result_int8x8 [] = { 1, 2, 3, 4, 5, 6, 7, 8,  }
+VMLS:1:result_int16x4 [] = { ffffe054, ffffe055, ffffe056, ffffe057,  }
+VMLS:2:result_int32x2 [] = { ffffd3e9, ffffd3ea,  }
+VMLS:3:result_int64x1 [] = { 3333333333333333,  }
+VMLS:4:result_uint8x8 [] = { c0, c1, c2, c3, c4, c5, c6, c7,  }
+VMLS:5:result_uint16x4 [] = { c1d9, c1da, c1db, c1dc,  }
+VMLS:6:result_uint32x2 [] = { ffffbc34, ffffbc35,  }
+VMLS:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLS:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLS:10:result_float32x2 [] = { c3b14e76, c3b0ce76,  }
+VMLS:11:result_int8x16 [] = { ffffffd1, ffffffd2, ffffffd3, ffffffd4, ffffffd5, ffffffd6, ffffffd7, ffffffd8, ffffffd9, ffffffda, ffffffdb, ffffffdc, ffffffdd, ffffffde, ffffffdf, ffffffe0,  }
+VMLS:12:result_int16x8 [] = { ffffb7b0, ffffb7b1, ffffb7b2, ffffb7b3, ffffb7b4, ffffb7b5, ffffb7b6, ffffb7b7,  }
+VMLS:13:result_int32x4 [] = { ffffb8d1, ffffb8d2, ffffb8d3, ffffb8d4,  }
+VMLS:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLS:15:result_uint8x16 [] = { 34, 35, 36, 37, 38, 39, 3a, 3b, 3c, 3d, 3e, 3f, 40, 41, 42, 43,  }
+VMLS:16:result_uint16x8 [] = { c1d9, c1da, c1db, c1dc, c1dd, c1de, c1df, c1e0,  }
+VMLS:17:result_uint32x4 [] = { ffffc9c0, ffffc9c1, ffffc9c2, ffffc9c3,  }
+VMLS:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLS:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLS:21:result_float32x4 [] = { c5f1ae15, c5f1a615, c5f19e15, c5f19615,  }
+
+VMUL output:
+VMUL:0:result_int8x8 [] = { fffffff0, 1, 12, 23, 34, 45, 56, 67,  }
+VMUL:1:result_int16x4 [] = { fffffde0, fffffe02, fffffe24, fffffe46,  }
+VMUL:2:result_int32x2 [] = { fffffcd0, fffffd03,  }
+VMUL:3:result_int64x1 [] = { 3333333333333333,  }
+VMUL:4:result_uint8x8 [] = { c0, 4, 48, 8c, d0, 14, 58, 9c,  }
+VMUL:5:result_uint16x4 [] = { fab0, fb05, fb5a, fbaf,  }
+VMUL:6:result_uint32x2 [] = { fffff9a0, fffffa06,  }
+VMUL:7:result_uint64x1 [] = { 3333333333333333,  }
+VMUL:8:result_poly8x8 [] = { c0, 84, 48, c, d0, 94, 58, 1c,  }
+VMUL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMUL:10:result_float32x2 [] = { c4053333, c3f9c000,  }
+VMUL:11:result_int8x16 [] = { ffffff90, 7, 7e, fffffff5, 6c, ffffffe3, 5a, ffffffd1, 48, ffffffbf, 36, ffffffad, 24, ffffff9b, 12, ffffff89,  }
+VMUL:12:result_int16x8 [] = { fffff780, fffff808, fffff890, fffff918, fffff9a0, fffffa28, fffffab0, fffffb38,  }
+VMUL:13:result_int32x4 [] = { fffff670, fffff709, fffff7a2, fffff83b,  }
+VMUL:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMUL:15:result_uint8x16 [] = { 60, a, b4, 5e, 8, b2, 5c, 6, b0, 5a, 4, ae, 58, 2, ac, 56,  }
+VMUL:16:result_uint16x8 [] = { f450, f50b, f5c6, f681, f73c, f7f7, f8b2, f96d,  }
+VMUL:17:result_uint32x4 [] = { fffff340, fffff40c, fffff4d8, fffff5a4,  }
+VMUL:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMUL:19:result_poly8x16 [] = { 60, ca, 34, 9e, c8, 62, 9c, 36, 30, 9a, 64, ce, 98, 32, cc, 66,  }
+VMUL:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMUL:21:result_float32x4 [] = { c4c73333, c4bac000, c4ae4ccd, c4a1d999,  }
+
+VMUL_LANE output:
+VMUL_LANE:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_LANE:1:result_int16x4 [] = { ffffffc0, ffffffc4, ffffffc8, ffffffcc,  }
+VMUL_LANE:2:result_int32x2 [] = { fffffde0, fffffe02,  }
+VMUL_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VMUL_LANE:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_LANE:5:result_uint16x4 [] = { bbc0, c004, c448, c88c,  }
+VMUL_LANE:6:result_uint32x2 [] = { fffface0, ffffb212,  }
+VMUL_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VMUL_LANE:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_LANE:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMUL_LANE:10:result_float32x2 [] = { c3b66666, c3ab0000,  }
+VMUL_LANE:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_LANE:12:result_int16x8 [] = { ffffffc0, ffffffc4, ffffffc8, ffffffcc, ffffffd0, ffffffd4, ffffffd8, ffffffdc,  }
+VMUL_LANE:13:result_int32x4 [] = { fffffde0, fffffe02, fffffe24, fffffe46,  }
+VMUL_LANE:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMUL_LANE:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_LANE:16:result_uint16x8 [] = { bbc0, c004, c448, c88c, ccd0, d114, d558, d99c,  }
+VMUL_LANE:17:result_uint32x4 [] = { fffface0, ffffb212, ffffb744, ffffbc76,  }
+VMUL_LANE:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMUL_LANE:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_LANE:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMUL_LANE:21:result_float32x4 [] = { c3b66666, c3ab0000, c39f9999, c3943333,  }
+
+VMUL_N output:
+VMUL_N:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_N:1:result_int16x4 [] = { fffffef0, ffffff01, ffffff12, ffffff23,  }
+VMUL_N:2:result_int32x2 [] = { fffffde0, fffffe02,  }
+VMUL_N:3:result_int64x1 [] = { 3333333333333333,  }
+VMUL_N:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_N:5:result_uint16x4 [] = { fcd0, fd03, fd36, fd69,  }
+VMUL_N:6:result_uint32x2 [] = { fffffbc0, fffffc04,  }
+VMUL_N:7:result_uint64x1 [] = { 3333333333333333,  }
+VMUL_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMUL_N:10:result_float32x2 [] = { c3b26666, c3a74000,  }
+VMUL_N:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_N:12:result_int16x8 [] = { fffffab0, fffffb05, fffffb5a, fffffbaf, fffffc04, fffffc59, fffffcae, fffffd03,  }
+VMUL_N:13:result_int32x4 [] = { fffff9a0, fffffa06, fffffa6c, fffffad2,  }
+VMUL_N:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMUL_N:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_N:16:result_uint16x8 [] = { f890, f907, f97e, f9f5, fa6c, fae3, fb5a, fbd1,  }
+VMUL_N:17:result_uint32x4 [] = { fffff780, fffff808, fffff890, fffff918,  }
+VMUL_N:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMUL_N:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_N:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMUL_N:21:result_float32x4 [] = { c4b1cccd, c4a6b000, c49b9333, c4907667,  }
+
+VMULL_N output:
+VMULL_N:0:result_int32x4 [] = { 11000, 11000, 11000, 11000,  }
+VMULL_N:1:result_int64x2 [] = { 22000, 22000,  }
+VMULL_N:2:result_uint32x4 [] = { 33000, 33000, 33000, 33000,  }
+VMULL_N:3:result_uint64x2 [] = { 44000, 44000,  }
+
+VMLA_LANE output:
+VMLA_LANE:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_LANE:1:result_int16x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLA_LANE:2:result_int32x2 [] = { 3e07, 3e08,  }
+VMLA_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VMLA_LANE:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_LANE:5:result_uint16x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLA_LANE:6:result_uint32x2 [] = { 3e07, 3e08,  }
+VMLA_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLA_LANE:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_LANE:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLA_LANE:10:result_float32x2 [] = { 4418c687, 44190687,  }
+VMLA_LANE:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_LANE:12:result_int16x8 [] = { 3e07, 3e08, 3e09, 3e0a, 3e0b, 3e0c, 3e0d, 3e0e,  }
+VMLA_LANE:13:result_int32x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLA_LANE:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLA_LANE:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_LANE:16:result_uint16x8 [] = { 3e07, 3e08, 3e09, 3e0a, 3e0b, 3e0c, 3e0d, 3e0e,  }
+VMLA_LANE:17:result_uint32x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLA_LANE:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLA_LANE:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_LANE:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLA_LANE:21:result_float32x4 [] = { 441a3168, 441a7168, 441ab168, 441af168,  }
+
+VMLS_LANE output:
+VMLS_LANE:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_LANE:1:result_int16x4 [] = { ffffc1d9, ffffc1da, ffffc1db, ffffc1dc,  }
+VMLS_LANE:2:result_int32x2 [] = { ffffc1d9, ffffc1da,  }
+VMLS_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VMLS_LANE:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_LANE:5:result_uint16x4 [] = { c1d9, c1da, c1db, c1dc,  }
+VMLS_LANE:6:result_uint32x2 [] = { ffffc1d9, ffffc1da,  }
+VMLS_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLS_LANE:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_LANE:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLS_LANE:10:result_float32x2 [] = { c420c687, c4208687,  }
+VMLS_LANE:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_LANE:12:result_int16x8 [] = { ffffc1d9, ffffc1da, ffffc1db, ffffc1dc, ffffc1dd, ffffc1de, ffffc1df, ffffc1e0,  }
+VMLS_LANE:13:result_int32x4 [] = { ffffc1d9, ffffc1da, ffffc1db, ffffc1dc,  }
+VMLS_LANE:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLS_LANE:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_LANE:16:result_uint16x8 [] = { c1d9, c1da, c1db, c1dc, c1dd, c1de, c1df, c1e0,  }
+VMLS_LANE:17:result_uint32x4 [] = { ffffc1d9, ffffc1da, ffffc1db, ffffc1dc,  }
+VMLS_LANE:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLS_LANE:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_LANE:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLS_LANE:21:result_float32x4 [] = { c4223168, c421f168, c421b168, c4217168,  }
+
+VMLA_N output:
+VMLA_N:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_N:1:result_int16x4 [] = { 595, 596, 597, 598,  }
+VMLA_N:2:result_int32x2 [] = { b3a, b3b,  }
+VMLA_N:3:result_int64x1 [] = { 3333333333333333,  }
+VMLA_N:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_N:5:result_uint16x4 [] = { 10df, 10e0, 10e1, 10e2,  }
+VMLA_N:6:result_uint32x2 [] = { 1684, 1685,  }
+VMLA_N:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLA_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLA_N:10:result_float32x2 [] = { 4497deb8, 4497feb8,  }
+VMLA_N:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_N:12:result_int16x8 [] = { 1c29, 1c2a, 1c2b, 1c2c, 1c2d, 1c2e, 1c2f, 1c30,  }
+VMLA_N:13:result_int32x4 [] = { 21ce, 21cf, 21d0, 21d1,  }
+VMLA_N:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLA_N:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_N:16:result_uint16x8 [] = { 2773, 2774, 2775, 2776, 2777, 2778, 2779, 277a,  }
+VMLA_N:17:result_uint32x4 [] = { 2d18, 2d19, 2d1a, 2d1b,  }
+VMLA_N:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLA_N:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_N:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLA_N:21:result_float32x4 [] = { 4568087b, 4568187b, 4568287b, 4568387b,  }
+
+VMLS_N output:
+VMLS_N:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_N:1:result_int16x4 [] = { fffffa4b, fffffa4c, fffffa4d, fffffa4e,  }
+VMLS_N:2:result_int32x2 [] = { fffff4a6, fffff4a7,  }
+VMLS_N:3:result_int64x1 [] = { 3333333333333333,  }
+VMLS_N:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_N:5:result_uint16x4 [] = { ef01, ef02, ef03, ef04,  }
+VMLS_N:6:result_uint32x2 [] = { ffffe95c, ffffe95d,  }
+VMLS_N:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLS_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLS_N:10:result_float32x2 [] = { c49bdeb8, c49bbeb8,  }
+VMLS_N:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_N:12:result_int16x8 [] = { ffffe3b7, ffffe3b8, ffffe3b9, ffffe3ba, ffffe3bb, ffffe3bc, ffffe3bd, ffffe3be,  }
+VMLS_N:13:result_int32x4 [] = { ffffde12, ffffde13, ffffde14, ffffde15,  }
+VMLS_N:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLS_N:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_N:16:result_uint16x8 [] = { d86d, d86e, d86f, d870, d871, d872, d873, d874,  }
+VMLS_N:17:result_uint32x4 [] = { ffffd2c8, ffffd2c9, ffffd2ca, ffffd2cb,  }
+VMLS_N:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLS_N:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_N:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLS_N:21:result_float32x4 [] = { c56a087b, c569f87b, c569e87b, c569d87b,  }
+
+VSLI_N output:
+VSLI_N:0:result_int8x8 [] = { 20, 21, 22, 23, 24, 25, 26, 27,  }
+VSLI_N:1:result_int16x4 [] = { ffffffe0, ffffffe1, ffffffe2, ffffffe3,  }
+VSLI_N:2:result_int32x2 [] = { 6, 7,  }
+VSLI_N:3:result_int64x1 [] = { 64fffffff0,  }
+VSLI_N:4:result_uint8x8 [] = { 50, 51, 52, 53, 50, 51, 52, 53,  }
+VSLI_N:5:result_uint16x4 [] = { 7bf0, 7bf1, 7bf2, 7bf3,  }
+VSLI_N:6:result_uint32x2 [] = { 3ffffff0, 3ffffff1,  }
+VSLI_N:7:result_uint64x1 [] = { 10,  }
+VSLI_N:8:result_poly8x8 [] = { 50, 51, 52, 53, 50, 51, 52, 53,  }
+VSLI_N:9:result_poly16x4 [] = { 7bf0, 7bf1, 7bf2, 7bf3,  }
+VSLI_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSLI_N:11:result_int8x16 [] = { ffffffd0, ffffffd1, ffffffd2, ffffffd3, ffffffd4, ffffffd5, ffffffd6, ffffffd7, ffffffd8, ffffffd9, ffffffda, ffffffdb, ffffffdc, ffffffdd, ffffffde, ffffffdf,  }
+VSLI_N:12:result_int16x8 [] = { ffffff60, ffffff61, ffffff62, ffffff63, ffffff64, ffffff65, ffffff66, ffffff67,  }
+VSLI_N:13:result_int32x4 [] = { fe2ffff0, fe2ffff1, fe2ffff2, fe2ffff3,  }
+VSLI_N:14:result_int64x2 [] = { 18fff0, 18fff1,  }
+VSLI_N:15:result_uint8x16 [] = { 60, 61, 62, 63, 64, 65, 66, 67, 60, 61, 62, 63, 64, 65, 66, 67,  }
+VSLI_N:16:result_uint16x8 [] = { 3ff0, 3ff1, 3ff2, 3ff3, 3ff4, 3ff5, 3ff6, 3ff7,  }
+VSLI_N:17:result_uint32x4 [] = { 1bfffff0, 1bfffff1, 1bfffff2, 1bfffff3,  }
+VSLI_N:18:result_uint64x2 [] = { 7ffffffffffff0, 7ffffffffffff1,  }
+VSLI_N:19:result_poly8x16 [] = { 60, 61, 62, 63, 64, 65, 66, 67, 60, 61, 62, 63, 64, 65, 66, 67,  }
+VSLI_N:20:result_poly16x8 [] = { 3ff0, 3ff1, 3ff2, 3ff3, 3ff4, 3ff5, 3ff6, 3ff7,  }
+VSLI_N:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VSLI_Nmax shift amount output:
+VSLI_N:0:result_int8x8 [] = { 70, 71, 72, 73, 74, 75, 76, 77,  }
+VSLI_N:1:result_int16x4 [] = { 7ff0, 7ff1, 7ff2, 7ff3,  }
+VSLI_N:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VSLI_N:3:result_int64x1 [] = { 7ffffffffffffff0,  }
+VSLI_N:4:result_uint8x8 [] = { 70, 71, 72, 73, 74, 75, 76, 77,  }
+VSLI_N:5:result_uint16x4 [] = { 7ff0, 7ff1, 7ff2, 7ff3,  }
+VSLI_N:6:result_uint32x2 [] = { 7ffffff0, 7ffffff1,  }
+VSLI_N:7:result_uint64x1 [] = { 7ffffffffffffff0,  }
+VSLI_N:8:result_poly8x8 [] = { 70, 71, 72, 73, 74, 75, 76, 77,  }
+VSLI_N:9:result_poly16x4 [] = { 7ff0, 7ff1, 7ff2, 7ff3,  }
+VSLI_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSLI_N:11:result_int8x16 [] = { 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 7a, 7b, 7c, 7d, 7e, 7f,  }
+VSLI_N:12:result_int16x8 [] = { 7ff0, 7ff1, 7ff2, 7ff3, 7ff4, 7ff5, 7ff6, 7ff7,  }
+VSLI_N:13:result_int32x4 [] = { 7ffffff0, 7ffffff1, 7ffffff2, 7ffffff3,  }
+VSLI_N:14:result_int64x2 [] = { 7ffffffffffffff0, 7ffffffffffffff1,  }
+VSLI_N:15:result_uint8x16 [] = { 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 7a, 7b, 7c, 7d, 7e, 7f,  }
+VSLI_N:16:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VSLI_N:17:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VSLI_N:18:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VSLI_N:19:result_poly8x16 [] = { 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 7a, 7b, 7c, 7d, 7e, 7f,  }
+VSLI_N:20:result_poly16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VSLI_N:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VSRI_N output:
+VSRI_N:0:result_int8x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VSRI_N:1:result_int16x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VSRI_N:2:result_int32x2 [] = { 80000001, 80000001,  }
+VSRI_N:3:result_int64x1 [] = { ffffffff00000000,  }
+VSRI_N:4:result_uint8x8 [] = { c5, c5, c5, c5, c5, c5, c5, c5,  }
+VSRI_N:5:result_uint16x4 [] = { ffc0, ffc0, ffc0, ffc0,  }
+VSRI_N:6:result_uint32x2 [] = { fffffff0, fffffff0,  }
+VSRI_N:7:result_uint64x1 [] = { e000000000000000,  }
+VSRI_N:8:result_poly8x8 [] = { c5, c5, c5, c5, c5, c5, c5, c5,  }
+VSRI_N:9:result_poly16x4 [] = { ffc0, ffc0, ffc0, ffc0,  }
+VSRI_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSRI_N:11:result_int8x16 [] = { fffffff7, fffffff7, fffffff7, fffffff7, fffffff7, fffffff7, fffffff7, fffffff7, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VSRI_N:12:result_int16x8 [] = { fffffffd, fffffffd, fffffffd, fffffffd, fffffffd, fffffffd, fffffffd, fffffffd,  }
+VSRI_N:13:result_int32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VSRI_N:14:result_int64x2 [] = { ffff000000000000, ffff000000000000,  }
+VSRI_N:15:result_uint8x16 [] = { e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1,  }
+VSRI_N:16:result_uint16x8 [] = { fff0, fff0, fff0, fff0, fff0, fff0, fff0, fff0,  }
+VSRI_N:17:result_uint32x4 [] = { fffffe00, fffffe00, fffffe00, fffffe00,  }
+VSRI_N:18:result_uint64x2 [] = { fffffffffffff800, fffffffffffff800,  }
+VSRI_N:19:result_poly8x16 [] = { e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1,  }
+VSRI_N:20:result_poly16x8 [] = { fff0, fff0, fff0, fff0, fff0, fff0, fff0, fff0,  }
+VSRI_N:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VSRI_N max shift amount output:
+VSRI_N:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VSRI_N:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VSRI_N:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VSRI_N:3:result_int64x1 [] = { fffffffffffffff0,  }
+VSRI_N:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VSRI_N:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VSRI_N:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VSRI_N:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VSRI_N:8:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VSRI_N:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VSRI_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSRI_N:11:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VSRI_N:12:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VSRI_N:13:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VSRI_N:14:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VSRI_N:15:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VSRI_N:16:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VSRI_N:17:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VSRI_N:18:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VSRI_N:19:result_poly8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VSRI_N:20:result_poly16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VSRI_N:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VTST/VTSTQ (signed input) output:
+VTST/VTSTQ:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTST/VTSTQ:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTST/VTSTQ:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTST/VTSTQ:3:result_int64x1 [] = { 3333333333333333,  }
+VTST/VTSTQ:4:result_uint8x8 [] = { 0, ff, ff, ff, ff, ff, ff, ff,  }
+VTST/VTSTQ:5:result_uint16x4 [] = { 0, ffff, 0, ffff,  }
+VTST/VTSTQ:6:result_uint32x2 [] = { 0, ffffffff,  }
+VTST/VTSTQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VTST/VTSTQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTST/VTSTQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTST/VTSTQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTST/VTSTQ:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTST/VTSTQ:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTST/VTSTQ:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTST/VTSTQ:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTST/VTSTQ:15:result_uint8x16 [] = { 0, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VTST/VTSTQ:16:result_uint16x8 [] = { 0, ffff, 0, ffff, ffff, ffff, ffff, ffff,  }
+VTST/VTSTQ:17:result_uint32x4 [] = { 0, ffffffff, 0, ffffffff,  }
+VTST/VTSTQ:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTST/VTSTQ:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTST/VTSTQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTST/VTSTQ:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VTST/VTSTQ (unsigned input) output:
+VTST/VTSTQ:22:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTST/VTSTQ:23:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTST/VTSTQ:24:result_int32x2 [] = { 33333333, 33333333,  }
+VTST/VTSTQ:25:result_int64x1 [] = { 3333333333333333,  }
+VTST/VTSTQ:26:result_uint8x8 [] = { 0, ff, ff, ff, ff, ff, ff, ff,  }
+VTST/VTSTQ:27:result_uint16x4 [] = { 0, ffff, 0, ffff,  }
+VTST/VTSTQ:28:result_uint32x2 [] = { 0, ffffffff,  }
+VTST/VTSTQ:29:result_uint64x1 [] = { 3333333333333333,  }
+VTST/VTSTQ:30:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTST/VTSTQ:31:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTST/VTSTQ:32:result_float32x2 [] = { 33333333, 33333333,  }
+VTST/VTSTQ:33:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTST/VTSTQ:34:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTST/VTSTQ:35:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTST/VTSTQ:36:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTST/VTSTQ:37:result_uint8x16 [] = { 0, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VTST/VTSTQ:38:result_uint16x8 [] = { 0, ffff, 0, ffff, ffff, ffff, ffff, ffff,  }
+VTST/VTSTQ:39:result_uint32x4 [] = { 0, ffffffff, 0, ffffffff,  }
+VTST/VTSTQ:40:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTST/VTSTQ:41:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTST/VTSTQ:42:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTST/VTSTQ:43:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VADDHN output:
+VADDHN:0:result_int8x8 [] = { 32, 32, 32, 32, 32, 32, 32, 32,  }
+VADDHN:1:result_int16x4 [] = { 32, 32, 32, 32,  }
+VADDHN:2:result_int32x2 [] = { 18, 18,  }
+VADDHN:3:result_int64x1 [] = { 3333333333333333,  }
+VADDHN:4:result_uint8x8 [] = { 3, 3, 3, 3, 3, 3, 3, 3,  }
+VADDHN:5:result_uint16x4 [] = { 37, 37, 37, 37,  }
+VADDHN:6:result_uint32x2 [] = { 3, 3,  }
+VADDHN:7:result_uint64x1 [] = { 3333333333333333,  }
+VADDHN:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDHN:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VADDHN:10:result_float32x2 [] = { 33333333, 33333333,  }
+VADDHN:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDHN:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VADDHN:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VADDHN:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VADDHN:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDHN:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VADDHN:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VADDHN:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VADDHN:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDHN:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VADDHN:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRADDHN output:
+VRADDHN:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRADDHN:1:result_int16x4 [] = { 33, 33, 33, 33,  }
+VRADDHN:2:result_int32x2 [] = { 19, 19,  }
+VRADDHN:3:result_int64x1 [] = { 3333333333333333,  }
+VRADDHN:4:result_uint8x8 [] = { 4, 4, 4, 4, 4, 4, 4, 4,  }
+VRADDHN:5:result_uint16x4 [] = { 38, 38, 38, 38,  }
+VRADDHN:6:result_uint32x2 [] = { 4, 4,  }
+VRADDHN:7:result_uint64x1 [] = { 3333333333333333,  }
+VRADDHN:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRADDHN:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRADDHN:10:result_float32x2 [] = { 33333333, 33333333,  }
+VRADDHN:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRADDHN:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRADDHN:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRADDHN:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRADDHN:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRADDHN:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRADDHN:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRADDHN:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRADDHN:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRADDHN:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRADDHN:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VADDL output:
+VADDL:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDL:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VADDL:2:result_int32x2 [] = { 33333333, 33333333,  }
+VADDL:3:result_int64x1 [] = { 3333333333333333,  }
+VADDL:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDL:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VADDL:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VADDL:7:result_uint64x1 [] = { 3333333333333333,  }
+VADDL:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VADDL:10:result_float32x2 [] = { 33333333, 33333333,  }
+VADDL:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDL:12:result_int16x8 [] = { ffffffe3, ffffffe4, ffffffe5, ffffffe6, ffffffe7, ffffffe8, ffffffe9, ffffffea,  }
+VADDL:13:result_int32x4 [] = { ffffffe2, ffffffe3, ffffffe4, ffffffe5,  }
+VADDL:14:result_int64x2 [] = { ffffffffffffffe0, ffffffffffffffe1,  }
+VADDL:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDL:16:result_uint16x8 [] = { 1e3, 1e4, 1e5, 1e6, 1e7, 1e8, 1e9, 1ea,  }
+VADDL:17:result_uint32x4 [] = { 1ffe1, 1ffe2, 1ffe3, 1ffe4,  }
+VADDL:18:result_uint64x2 [] = { 1ffffffe0, 1ffffffe1,  }
+VADDL:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDL:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VADDL:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VADDW output:
+VADDW:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDW:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VADDW:2:result_int32x2 [] = { 33333333, 33333333,  }
+VADDW:3:result_int64x1 [] = { 3333333333333333,  }
+VADDW:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDW:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VADDW:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VADDW:7:result_uint64x1 [] = { 3333333333333333,  }
+VADDW:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDW:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VADDW:10:result_float32x2 [] = { 33333333, 33333333,  }
+VADDW:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDW:12:result_int16x8 [] = { ffffffe3, ffffffe4, ffffffe5, ffffffe6, ffffffe7, ffffffe8, ffffffe9, ffffffea,  }
+VADDW:13:result_int32x4 [] = { ffffffe2, ffffffe3, ffffffe4, ffffffe5,  }
+VADDW:14:result_int64x2 [] = { ffffffffffffffe0, ffffffffffffffe1,  }
+VADDW:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDW:16:result_uint16x8 [] = { e3, e4, e5, e6, e7, e8, e9, ea,  }
+VADDW:17:result_uint32x4 [] = { ffe1, ffe2, ffe3, ffe4,  }
+VADDW:18:result_uint64x2 [] = { ffffffe0, ffffffe1,  }
+VADDW:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDW:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VADDW:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VHADD/VHADDQ output:
+VHADD/VHADDQ:0:result_int8x8 [] = { fffffff1, fffffff2, fffffff2, fffffff3, fffffff3, fffffff4, fffffff4, fffffff5,  }
+VHADD/VHADDQ:1:result_int16x4 [] = { fffffff1, fffffff1, fffffff2, fffffff2,  }
+VHADD/VHADDQ:2:result_int32x2 [] = { fffffff0, fffffff0,  }
+VHADD/VHADDQ:3:result_int64x1 [] = { 3333333333333333,  }
+VHADD/VHADDQ:4:result_uint8x8 [] = { f1, f2, f2, f3, f3, f4, f4, f5,  }
+VHADD/VHADDQ:5:result_uint16x4 [] = { fff0, fff1, fff1, fff2,  }
+VHADD/VHADDQ:6:result_uint32x2 [] = { fffffff0, fffffff0,  }
+VHADD/VHADDQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VHADD/VHADDQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VHADD/VHADDQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VHADD/VHADDQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VHADD/VHADDQ:11:result_int8x16 [] = { fffffff2, fffffff2, fffffff3, fffffff3, fffffff4, fffffff4, fffffff5, fffffff5, fffffff6, fffffff6, fffffff7, fffffff7, fffffff8, fffffff8, fffffff9, fffffff9,  }
+VHADD/VHADDQ:12:result_int16x8 [] = { fffffff1, fffffff2, fffffff2, fffffff3, fffffff3, fffffff4, fffffff4, fffffff5,  }
+VHADD/VHADDQ:13:result_int32x4 [] = { fffffff0, fffffff1, fffffff1, fffffff2,  }
+VHADD/VHADDQ:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VHADD/VHADDQ:15:result_uint8x16 [] = { f4, f5, f5, f6, f6, f7, f7, f8, f8, f9, f9, fa, fa, fb, fb, fc,  }
+VHADD/VHADDQ:16:result_uint16x8 [] = { fff1, fff1, fff2, fff2, fff3, fff3, fff4, fff4,  }
+VHADD/VHADDQ:17:result_uint32x4 [] = { fffffff0, fffffff1, fffffff1, fffffff2,  }
+VHADD/VHADDQ:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VHADD/VHADDQ:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VHADD/VHADDQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VHADD/VHADDQ:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRHADD/VRHADDQ output:
+VRHADD/VRHADDQ:0:result_int8x8 [] = { fffffff2, fffffff2, fffffff3, fffffff3, fffffff4, fffffff4, fffffff5, fffffff5,  }
+VRHADD/VRHADDQ:1:result_int16x4 [] = { fffffff1, fffffff2, fffffff2, fffffff3,  }
+VRHADD/VRHADDQ:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VRHADD/VRHADDQ:3:result_int64x1 [] = { 3333333333333333,  }
+VRHADD/VRHADDQ:4:result_uint8x8 [] = { f2, f2, f3, f3, f4, f4, f5, f5,  }
+VRHADD/VRHADDQ:5:result_uint16x4 [] = { fff1, fff1, fff2, fff2,  }
+VRHADD/VRHADDQ:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VRHADD/VRHADDQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VRHADD/VRHADDQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRHADD/VRHADDQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRHADD/VRHADDQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VRHADD/VRHADDQ:11:result_int8x16 [] = { fffffff2, fffffff3, fffffff3, fffffff4, fffffff4, fffffff5, fffffff5, fffffff6, fffffff6, fffffff7, fffffff7, fffffff8, fffffff8, fffffff9, fffffff9, fffffffa,  }
+VRHADD/VRHADDQ:12:result_int16x8 [] = { fffffff2, fffffff2, fffffff3, fffffff3, fffffff4, fffffff4, fffffff5, fffffff5,  }
+VRHADD/VRHADDQ:13:result_int32x4 [] = { fffffff1, fffffff1, fffffff2, fffffff2,  }
+VRHADD/VRHADDQ:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRHADD/VRHADDQ:15:result_uint8x16 [] = { f5, f5, f6, f6, f7, f7, f8, f8, f9, f9, fa, fa, fb, fb, fc, fc,  }
+VRHADD/VRHADDQ:16:result_uint16x8 [] = { fff1, fff2, fff2, fff3, fff3, fff4, fff4, fff5,  }
+VRHADD/VRHADDQ:17:result_uint32x4 [] = { fffffff1, fffffff1, fffffff2, fffffff2,  }
+VRHADD/VRHADDQ:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRHADD/VRHADDQ:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRHADD/VRHADDQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRHADD/VRHADDQ:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VHSUB/VHSUBQ output:
+VHSUB/VHSUBQ:0:result_int8x8 [] = { fffffffe, ffffffff, ffffffff, 0, 0, 1, 1, 2,  }
+VHSUB/VHSUBQ:1:result_int16x4 [] = { ffffffff, ffffffff, 0, 0,  }
+VHSUB/VHSUBQ:2:result_int32x2 [] = { 0, 0,  }
+VHSUB/VHSUBQ:3:result_int64x1 [] = { 3333333333333333,  }
+VHSUB/VHSUBQ:4:result_uint8x8 [] = { fe, ff, ff, 0, 0, 1, 1, 2,  }
+VHSUB/VHSUBQ:5:result_uint16x4 [] = { ffff, 0, 0, 1,  }
+VHSUB/VHSUBQ:6:result_uint32x2 [] = { 0, 0,  }
+VHSUB/VHSUBQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VHSUB/VHSUBQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VHSUB/VHSUBQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VHSUB/VHSUBQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VHSUB/VHSUBQ:11:result_int8x16 [] = { fffffffe, fffffffe, ffffffff, ffffffff, 0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5,  }
+VHSUB/VHSUBQ:12:result_int16x8 [] = { fffffffe, ffffffff, ffffffff, 0, 0, 1, 1, 2,  }
+VHSUB/VHSUBQ:13:result_int32x4 [] = { ffffffff, 0, 0, 1,  }
+VHSUB/VHSUBQ:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VHSUB/VHSUBQ:15:result_uint8x16 [] = { fb, fc, fc, fd, fd, fe, fe, ff, ff, 0, 0, 1, 1, 2, 2, 3,  }
+VHSUB/VHSUBQ:16:result_uint16x8 [] = { ffff, ffff, 0, 0, 1, 1, 2, 2,  }
+VHSUB/VHSUBQ:17:result_uint32x4 [] = { ffffffff, 0, 0, 1,  }
+VHSUB/VHSUBQ:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VHSUB/VHSUBQ:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VHSUB/VHSUBQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VHSUB/VHSUBQ:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VSUBL output:
+VSUBL:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBL:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSUBL:2:result_int32x2 [] = { 33333333, 33333333,  }
+VSUBL:3:result_int64x1 [] = { 3333333333333333,  }
+VSUBL:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBL:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSUBL:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VSUBL:7:result_uint64x1 [] = { 3333333333333333,  }
+VSUBL:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSUBL:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSUBL:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBL:12:result_int16x8 [] = { fffffffd, fffffffe, ffffffff, 0, 1, 2, 3, 4,  }
+VSUBL:13:result_int32x4 [] = { fffffffe, ffffffff, 0, 1,  }
+VSUBL:14:result_int64x2 [] = { 0, 1,  }
+VSUBL:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBL:16:result_uint16x8 [] = { fffd, fffe, ffff, 0, 1, 2, 3, 4,  }
+VSUBL:17:result_uint32x4 [] = { ffffffff, 0, 1, 2,  }
+VSUBL:18:result_uint64x2 [] = { 0, 1,  }
+VSUBL:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBL:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSUBL:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VSUBW output:
+VSUBW:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBW:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSUBW:2:result_int32x2 [] = { 33333333, 33333333,  }
+VSUBW:3:result_int64x1 [] = { 3333333333333333,  }
+VSUBW:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBW:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSUBW:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VSUBW:7:result_uint64x1 [] = { 3333333333333333,  }
+VSUBW:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBW:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSUBW:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSUBW:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBW:12:result_int16x8 [] = { fffffffd, fffffffe, ffffffff, 0, 1, 2, 3, 4,  }
+VSUBW:13:result_int32x4 [] = { fffffffe, ffffffff, 0, 1,  }
+VSUBW:14:result_int64x2 [] = { 0, 1,  }
+VSUBW:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBW:16:result_uint16x8 [] = { fefd, fefe, feff, ff00, ff01, ff02, ff03, ff04,  }
+VSUBW:17:result_uint32x4 [] = { fffeffff, ffff0000, ffff0001, ffff0002,  }
+VSUBW:18:result_uint64x2 [] = { ffffffff00000000, ffffffff00000001,  }
+VSUBW:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBW:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSUBW:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VSUBHN output:
+VSUBHN:0:result_int8x8 [] = { 31, 31, 31, 31, 31, 31, 31, 31,  }
+VSUBHN:1:result_int16x4 [] = { 31, 31, 31, 31,  }
+VSUBHN:2:result_int32x2 [] = { 17, 17,  }
+VSUBHN:3:result_int64x1 [] = { 3333333333333333,  }
+VSUBHN:4:result_uint8x8 [] = { 2, 2, 2, 2, 2, 2, 2, 2,  }
+VSUBHN:5:result_uint16x4 [] = { 36, 36, 36, 36,  }
+VSUBHN:6:result_uint32x2 [] = { 2, 2,  }
+VSUBHN:7:result_uint64x1 [] = { 3333333333333333,  }
+VSUBHN:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBHN:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSUBHN:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSUBHN:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBHN:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSUBHN:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSUBHN:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VSUBHN:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBHN:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSUBHN:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSUBHN:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VSUBHN:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBHN:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSUBHN:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSUBHN output:
+VRSUBHN:0:result_int8x8 [] = { 31, 31, 31, 31, 31, 31, 31, 31,  }
+VRSUBHN:1:result_int16x4 [] = { 31, 31, 31, 31,  }
+VRSUBHN:2:result_int32x2 [] = { 17, 17,  }
+VRSUBHN:3:result_int64x1 [] = { 3333333333333333,  }
+VRSUBHN:4:result_uint8x8 [] = { 2, 2, 2, 2, 2, 2, 2, 2,  }
+VRSUBHN:5:result_uint16x4 [] = { 36, 36, 36, 36,  }
+VRSUBHN:6:result_uint32x2 [] = { 2, 2,  }
+VRSUBHN:7:result_uint64x1 [] = { 3333333333333333,  }
+VRSUBHN:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSUBHN:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSUBHN:10:result_float32x2 [] = { 33333333, 33333333,  }
+VRSUBHN:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSUBHN:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSUBHN:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSUBHN:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRSUBHN:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSUBHN:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSUBHN:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSUBHN:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRSUBHN:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSUBHN:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSUBHN:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VMVN/VMVNQ output:
+VMVN/VMVNQ:0:result_int8x8 [] = { f, e, d, c, b, a, 9, 8,  }
+VMVN/VMVNQ:1:result_int16x4 [] = { f, e, d, c,  }
+VMVN/VMVNQ:2:result_int32x2 [] = { f, e,  }
+VMVN/VMVNQ:3:result_int64x1 [] = { 3333333333333333,  }
+VMVN/VMVNQ:4:result_uint8x8 [] = { f, e, d, c, b, a, 9, 8,  }
+VMVN/VMVNQ:5:result_uint16x4 [] = { f, e, d, c,  }
+VMVN/VMVNQ:6:result_uint32x2 [] = { f, e,  }
+VMVN/VMVNQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VMVN/VMVNQ:8:result_poly8x8 [] = { f, e, d, c, b, a, 9, 8,  }
+VMVN/VMVNQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMVN/VMVNQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMVN/VMVNQ:11:result_int8x16 [] = { f, e, d, c, b, a, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0,  }
+VMVN/VMVNQ:12:result_int16x8 [] = { f, e, d, c, b, a, 9, 8,  }
+VMVN/VMVNQ:13:result_int32x4 [] = { f, e, d, c,  }
+VMVN/VMVNQ:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMVN/VMVNQ:15:result_uint8x16 [] = { f, e, d, c, b, a, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0,  }
+VMVN/VMVNQ:16:result_uint16x8 [] = { f, e, d, c, b, a, 9, 8,  }
+VMVN/VMVNQ:17:result_uint32x4 [] = { f, e, d, c,  }
+VMVN/VMVNQ:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMVN/VMVNQ:19:result_poly8x16 [] = { f, e, d, c, b, a, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0,  }
+VMVN/VMVNQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMVN/VMVNQ:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQMOVN cumulative saturation output:
+VQMOVN:0:vqmovn_s16 Neon cumulative saturation 0
+VQMOVN:1:vqmovn_s32 Neon cumulative saturation 0
+VQMOVN:2:vqmovn_s64 Neon cumulative saturation 0
+VQMOVN:3:vqmovn_u16 Neon cumulative saturation 0
+VQMOVN:4:vqmovn_u32 Neon cumulative saturation 0
+VQMOVN:5:vqmovn_u64 Neon cumulative saturation 0
+
+VQMOVN output:
+VQMOVN:6:result_int8x8 [] = { 12, 12, 12, 12, 12, 12, 12, 12,  }
+VQMOVN:7:result_int16x4 [] = { 1278, 1278, 1278, 1278,  }
+VQMOVN:8:result_int32x2 [] = { 12345678, 12345678,  }
+VQMOVN:9:result_int64x1 [] = { 3333333333333333,  }
+VQMOVN:10:result_uint8x8 [] = { 82, 82, 82, 82, 82, 82, 82, 82,  }
+VQMOVN:11:result_uint16x4 [] = { 8765, 8765, 8765, 8765,  }
+VQMOVN:12:result_uint32x2 [] = { 87654321, 87654321,  }
+VQMOVN:13:result_uint64x1 [] = { 3333333333333333,  }
+VQMOVN:14:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVN:15:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQMOVN:16:result_float32x2 [] = { 33333333, 33333333,  }
+VQMOVN:17:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVN:18:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVN:19:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVN:20:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQMOVN:21:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVN:22:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVN:23:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVN:24:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQMOVN:25:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVN:26:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVN:27:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQMOVN cumulative saturation output:
+VQMOVN:28:vqmovn_s16 Neon cumulative saturation 1
+VQMOVN:29:vqmovn_s32 Neon cumulative saturation 1
+VQMOVN:30:vqmovn_s64 Neon cumulative saturation 1
+VQMOVN:31:vqmovn_u16 Neon cumulative saturation 1
+VQMOVN:32:vqmovn_u32 Neon cumulative saturation 1
+VQMOVN:33:vqmovn_u64 Neon cumulative saturation 1
+
+VQMOVN output:
+VQMOVN:34:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQMOVN:35:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQMOVN:36:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQMOVN:37:result_int64x1 [] = { 3333333333333333,  }
+VQMOVN:38:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQMOVN:39:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQMOVN:40:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQMOVN:41:result_uint64x1 [] = { 3333333333333333,  }
+VQMOVN:42:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVN:43:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQMOVN:44:result_float32x2 [] = { 33333333, 33333333,  }
+VQMOVN:45:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVN:46:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVN:47:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVN:48:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQMOVN:49:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVN:50:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVN:51:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVN:52:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQMOVN:53:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVN:54:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVN:55:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQMOVUN cumulative saturation output:
+VQMOVUN:0:vqmovun_s16 Neon cumulative saturation 0
+VQMOVUN:1:vqmovun_s32 Neon cumulative saturation 0
+VQMOVUN:2:vqmovun_s64 Neon cumulative saturation 0
+
+VQMOVUN output:
+VQMOVUN:3:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:4:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQMOVUN:5:result_int32x2 [] = { 33333333, 33333333,  }
+VQMOVUN:6:result_int64x1 [] = { 3333333333333333,  }
+VQMOVUN:7:result_uint8x8 [] = { 34, 34, 34, 34, 34, 34, 34, 34,  }
+VQMOVUN:8:result_uint16x4 [] = { 5678, 5678, 5678, 5678,  }
+VQMOVUN:9:result_uint32x2 [] = { 12345678, 12345678,  }
+VQMOVUN:10:result_uint64x1 [] = { 3333333333333333,  }
+VQMOVUN:11:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:12:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQMOVUN:13:result_float32x2 [] = { 33333333, 33333333,  }
+VQMOVUN:14:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:15:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVUN:16:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVUN:17:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQMOVUN:18:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:19:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVUN:20:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVUN:21:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQMOVUN:22:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:23:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVUN:24:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQMOVUN (negative input) cumulative saturation output:
+VQMOVUN:25:vqmovun_s16 Neon cumulative saturation 1
+VQMOVUN:26:vqmovun_s32 Neon cumulative saturation 1
+VQMOVUN:27:vqmovun_s64 Neon cumulative saturation 1
+
+VQMOVUN (negative input) output:
+VQMOVUN:28:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:29:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQMOVUN:30:result_int32x2 [] = { 33333333, 33333333,  }
+VQMOVUN:31:result_int64x1 [] = { 3333333333333333,  }
+VQMOVUN:32:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQMOVUN:33:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQMOVUN:34:result_uint32x2 [] = { 0, 0,  }
+VQMOVUN:35:result_uint64x1 [] = { 3333333333333333,  }
+VQMOVUN:36:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:37:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQMOVUN:38:result_float32x2 [] = { 33333333, 33333333,  }
+VQMOVUN:39:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:40:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVUN:41:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVUN:42:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQMOVUN:43:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:44:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVUN:45:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVUN:46:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQMOVUN:47:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:48:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVUN:49:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSHR_N output:
+VRSHR_N:0:result_int8x8 [] = { fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb, fffffffc,  }
+VRSHR_N:1:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHR_N:2:result_int32x2 [] = { fffffffc, fffffffc,  }
+VRSHR_N:3:result_int64x1 [] = { 0,  }
+VRSHR_N:4:result_uint8x8 [] = { 3c, 3c, 3d, 3d, 3d, 3d, 3e, 3e,  }
+VRSHR_N:5:result_uint16x4 [] = { 1ffe, 1ffe, 1ffe, 1ffe,  }
+VRSHR_N:6:result_uint32x2 [] = { 8000000, 8000000,  }
+VRSHR_N:7:result_uint64x1 [] = { 80000000,  }
+VRSHR_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHR_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHR_N:11:result_int8x16 [] = { fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb, fffffffc, fffffffc, fffffffd, fffffffd, fffffffe, fffffffe, ffffffff, ffffffff, 0,  }
+VRSHR_N:12:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHR_N:13:result_int32x4 [] = { fffffffc, fffffffc, fffffffd, fffffffd,  }
+VRSHR_N:14:result_int64x2 [] = { 0, 0,  }
+VRSHR_N:15:result_uint8x16 [] = { 3c, 3c, 3d, 3d, 3d, 3d, 3e, 3e, 3e, 3e, 3f, 3f, 3f, 3f, 40, 40,  }
+VRSHR_N:16:result_uint16x8 [] = { 1ffe, 1ffe, 1ffe, 1ffe, 1fff, 1fff, 1fff, 1fff,  }
+VRSHR_N:17:result_uint32x4 [] = { 8000000, 8000000, 8000000, 8000000,  }
+VRSHR_N:18:result_uint64x2 [] = { 80000000, 80000000,  }
+VRSHR_N:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHR_N:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSHR_N (overflow test: max shift amount, positive input) output:
+VRSHR_N:22:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHR_N:23:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHR_N:24:result_int32x2 [] = { 0, 0,  }
+VRSHR_N:25:result_int64x1 [] = { 0,  }
+VRSHR_N:26:result_uint8x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSHR_N:27:result_uint16x4 [] = { 1, 1, 1, 1,  }
+VRSHR_N:28:result_uint32x2 [] = { 1, 1,  }
+VRSHR_N:29:result_uint64x1 [] = { 1,  }
+VRSHR_N:30:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:31:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHR_N:32:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHR_N:33:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHR_N:34:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHR_N:35:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSHR_N:36:result_int64x2 [] = { 0, 0,  }
+VRSHR_N:37:result_uint8x16 [] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSHR_N:38:result_uint16x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSHR_N:39:result_uint32x4 [] = { 1, 1, 1, 1,  }
+VRSHR_N:40:result_uint64x2 [] = { 1, 1,  }
+VRSHR_N:41:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:42:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHR_N:43:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSHR_N (overflow test: shift by 1, with negative input) output:
+VRSHR_N:44:result_int8x8 [] = { 40, 40, 40, 40, 40, 40, 40, 40,  }
+VRSHR_N:45:result_int16x4 [] = { 4000, 4000, 4000, 4000,  }
+VRSHR_N:46:result_int32x2 [] = { 40000000, 40000000,  }
+VRSHR_N:47:result_int64x1 [] = { 4000000000000000,  }
+VRSHR_N:48:result_uint8x8 [] = { 80, 80, 80, 80, 80, 80, 80, 80,  }
+VRSHR_N:49:result_uint16x4 [] = { 8000, 8000, 8000, 8000,  }
+VRSHR_N:50:result_uint32x2 [] = { 80000000, 80000000,  }
+VRSHR_N:51:result_uint64x1 [] = { 8000000000000000,  }
+VRSHR_N:52:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:53:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHR_N:54:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHR_N:55:result_int8x16 [] = { 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40,  }
+VRSHR_N:56:result_int16x8 [] = { 4000, 4000, 4000, 4000, 4000, 4000, 4000, 4000,  }
+VRSHR_N:57:result_int32x4 [] = { 40000000, 40000000, 40000000, 40000000,  }
+VRSHR_N:58:result_int64x2 [] = { 4000000000000000, 4000000000000000,  }
+VRSHR_N:59:result_uint8x16 [] = { 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80,  }
+VRSHR_N:60:result_uint16x8 [] = { 8000, 8000, 8000, 8000, 8000, 8000, 8000, 8000,  }
+VRSHR_N:61:result_uint32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VRSHR_N:62:result_uint64x2 [] = { 8000000000000000, 8000000000000000,  }
+VRSHR_N:63:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:64:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHR_N:65:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSHR_N (overflow test: shift by 3, positive input) output:
+VRSHR_N:66:result_int8x8 [] = { 10, 10, 10, 10, 10, 10, 10, 10,  }
+VRSHR_N:67:result_int16x4 [] = { 1000, 1000, 1000, 1000,  }
+VRSHR_N:68:result_int32x2 [] = { 10000000, 10000000,  }
+VRSHR_N:69:result_int64x1 [] = { 1000000000000000,  }
+VRSHR_N:70:result_uint8x8 [] = { 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSHR_N:71:result_uint16x4 [] = { 2000, 2000, 2000, 2000,  }
+VRSHR_N:72:result_uint32x2 [] = { 20000000, 20000000,  }
+VRSHR_N:73:result_uint64x1 [] = { 2000000000000000,  }
+VRSHR_N:74:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:75:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHR_N:76:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHR_N:77:result_int8x16 [] = { 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10,  }
+VRSHR_N:78:result_int16x8 [] = { 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000,  }
+VRSHR_N:79:result_int32x4 [] = { 10000000, 10000000, 10000000, 10000000,  }
+VRSHR_N:80:result_int64x2 [] = { 1000000000000000, 1000000000000000,  }
+VRSHR_N:81:result_uint8x16 [] = { 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSHR_N:82:result_uint16x8 [] = { 2000, 2000, 2000, 2000, 2000, 2000, 2000, 2000,  }
+VRSHR_N:83:result_uint32x4 [] = { 20000000, 20000000, 20000000, 20000000,  }
+VRSHR_N:84:result_uint64x2 [] = { 2000000000000000, 2000000000000000,  }
+VRSHR_N:85:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:86:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHR_N:87:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSHR_N (overflow test: shift by 1, with negative input) output:
+VRSHR_N:88:result_int8x8 [] = { ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0,  }
+VRSHR_N:89:result_int16x4 [] = { ffffc000, ffffc000, ffffc000, ffffc000,  }
+VRSHR_N:90:result_int32x2 [] = { c0000000, c0000000,  }
+VRSHR_N:91:result_int64x1 [] = { c000000000000000,  }
+VRSHR_N:92:result_uint8x8 [] = { 80, 80, 80, 80, 80, 80, 80, 80,  }
+VRSHR_N:93:result_uint16x4 [] = { 8000, 8000, 8000, 8000,  }
+VRSHR_N:94:result_uint32x2 [] = { 80000000, 80000000,  }
+VRSHR_N:95:result_uint64x1 [] = { 8000000000000000,  }
+VRSHR_N:96:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:97:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHR_N:98:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHR_N:99:result_int8x16 [] = { ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0,  }
+VRSHR_N:100:result_int16x8 [] = { ffffc000, ffffc000, ffffc000, ffffc000, ffffc000, ffffc000, ffffc000, ffffc000,  }
+VRSHR_N:101:result_int32x4 [] = { c0000000, c0000000, c0000000, c0000000,  }
+VRSHR_N:102:result_int64x2 [] = { c000000000000000, c000000000000000,  }
+VRSHR_N:103:result_uint8x16 [] = { 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80,  }
+VRSHR_N:104:result_uint16x8 [] = { 8000, 8000, 8000, 8000, 8000, 8000, 8000, 8000,  }
+VRSHR_N:105:result_uint32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VRSHR_N:106:result_uint64x2 [] = { 8000000000000000, 8000000000000000,  }
+VRSHR_N:107:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:108:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHR_N:109:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSHR_N (overflow test: shift by 3, with negative input) output:
+VRSHR_N:110:result_int8x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VRSHR_N:111:result_int16x4 [] = { fffff000, fffff000, fffff000, fffff000,  }
+VRSHR_N:112:result_int32x2 [] = { f0000000, f0000000,  }
+VRSHR_N:113:result_int64x1 [] = { f000000000000000,  }
+VRSHR_N:114:result_uint8x8 [] = { 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSHR_N:115:result_uint16x4 [] = { 2000, 2000, 2000, 2000,  }
+VRSHR_N:116:result_uint32x2 [] = { 20000000, 20000000,  }
+VRSHR_N:117:result_uint64x1 [] = { 2000000000000000,  }
+VRSHR_N:118:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:119:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHR_N:120:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHR_N:121:result_int8x16 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VRSHR_N:122:result_int16x8 [] = { fffff000, fffff000, fffff000, fffff000, fffff000, fffff000, fffff000, fffff000,  }
+VRSHR_N:123:result_int32x4 [] = { f0000000, f0000000, f0000000, f0000000,  }
+VRSHR_N:124:result_int64x2 [] = { f000000000000000, f000000000000000,  }
+VRSHR_N:125:result_uint8x16 [] = { 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSHR_N:126:result_uint16x8 [] = { 2000, 2000, 2000, 2000, 2000, 2000, 2000, 2000,  }
+VRSHR_N:127:result_uint32x4 [] = { 20000000, 20000000, 20000000, 20000000,  }
+VRSHR_N:128:result_uint64x2 [] = { 2000000000000000, 2000000000000000,  }
+VRSHR_N:129:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:130:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHR_N:131:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSRA_N output:
+VRSRA_N:0:result_int8x8 [] = { fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff, 0,  }
+VRSRA_N:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VRSRA_N:2:result_int32x2 [] = { fffffffd, fffffffe,  }
+VRSRA_N:3:result_int64x1 [] = { fffffffffffffff0,  }
+VRSRA_N:4:result_uint8x8 [] = { 5, 6, 7, 8, 9, a, b, c,  }
+VRSRA_N:5:result_uint16x4 [] = { fffd, fffe, ffff, 0,  }
+VRSRA_N:6:result_uint32x2 [] = { fffffff4, fffffff5,  }
+VRSRA_N:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VRSRA_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSRA_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VRSRA_N:11:result_int8x16 [] = { fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff, 0, 1, 2, 3, 4, 5, 6, 7, 8,  }
+VRSRA_N:12:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VRSRA_N:13:result_int32x4 [] = { fffffffd, fffffffe, ffffffff, 0,  }
+VRSRA_N:14:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VRSRA_N:15:result_uint8x16 [] = { 5, 6, 7, 8, 9, a, b, c, d, e, f, 10, 11, 12, 13, 14,  }
+VRSRA_N:16:result_uint16x8 [] = { fffd, fffe, ffff, 0, 1, 2, 3, 4,  }
+VRSRA_N:17:result_uint32x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VRSRA_N:18:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VRSRA_N:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSRA_N:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSRA_N (checking overflow: shift by 1, positive input) output:
+VRSRA_N:22:result_int8x8 [] = { 40, 40, 40, 40, 40, 40, 40, 40,  }
+VRSRA_N:23:result_int16x4 [] = { 4000, 4000, 4000, 4000,  }
+VRSRA_N:24:result_int32x2 [] = { 40000000, 40000000,  }
+VRSRA_N:25:result_int64x1 [] = { 4000000000000000,  }
+VRSRA_N:26:result_uint8x8 [] = { 80, 80, 80, 80, 80, 80, 80, 80,  }
+VRSRA_N:27:result_uint16x4 [] = { 8000, 8000, 8000, 8000,  }
+VRSRA_N:28:result_uint32x2 [] = { 80000000, 80000000,  }
+VRSRA_N:29:result_uint64x1 [] = { 8000000000000000,  }
+VRSRA_N:30:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:31:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSRA_N:32:result_float32x2 [] = { 33333333, 33333333,  }
+VRSRA_N:33:result_int8x16 [] = { 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40,  }
+VRSRA_N:34:result_int16x8 [] = { 4000, 4000, 4000, 4000, 4000, 4000, 4000, 4000,  }
+VRSRA_N:35:result_int32x4 [] = { 40000000, 40000000, 40000000, 40000000,  }
+VRSRA_N:36:result_int64x2 [] = { 4000000000000000, 4000000000000000,  }
+VRSRA_N:37:result_uint8x16 [] = { 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80,  }
+VRSRA_N:38:result_uint16x8 [] = { 8000, 8000, 8000, 8000, 8000, 8000, 8000, 8000,  }
+VRSRA_N:39:result_uint32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VRSRA_N:40:result_uint64x2 [] = { 8000000000000000, 8000000000000000,  }
+VRSRA_N:41:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:42:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSRA_N:43:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSRA_N (checking overflow: shift by 3, positive input) output:
+VRSRA_N:44:result_int8x8 [] = { 10, 10, 10, 10, 10, 10, 10, 10,  }
+VRSRA_N:45:result_int16x4 [] = { 1000, 1000, 1000, 1000,  }
+VRSRA_N:46:result_int32x2 [] = { 10000000, 10000000,  }
+VRSRA_N:47:result_int64x1 [] = { 1000000000000000,  }
+VRSRA_N:48:result_uint8x8 [] = { 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSRA_N:49:result_uint16x4 [] = { 2000, 2000, 2000, 2000,  }
+VRSRA_N:50:result_uint32x2 [] = { 20000000, 20000000,  }
+VRSRA_N:51:result_uint64x1 [] = { 2000000000000000,  }
+VRSRA_N:52:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:53:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSRA_N:54:result_float32x2 [] = { 33333333, 33333333,  }
+VRSRA_N:55:result_int8x16 [] = { 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10,  }
+VRSRA_N:56:result_int16x8 [] = { 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000,  }
+VRSRA_N:57:result_int32x4 [] = { 10000000, 10000000, 10000000, 10000000,  }
+VRSRA_N:58:result_int64x2 [] = { 1000000000000000, 1000000000000000,  }
+VRSRA_N:59:result_uint8x16 [] = { 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSRA_N:60:result_uint16x8 [] = { 2000, 2000, 2000, 2000, 2000, 2000, 2000, 2000,  }
+VRSRA_N:61:result_uint32x4 [] = { 20000000, 20000000, 20000000, 20000000,  }
+VRSRA_N:62:result_uint64x2 [] = { 2000000000000000, 2000000000000000,  }
+VRSRA_N:63:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:64:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSRA_N:65:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSRA_N (checking overflow: shift by max, positive input) output:
+VRSRA_N:66:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSRA_N:67:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:68:result_int32x2 [] = { 0, 0,  }
+VRSRA_N:69:result_int64x1 [] = { 0,  }
+VRSRA_N:70:result_uint8x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:71:result_uint16x4 [] = { 1, 1, 1, 1,  }
+VRSRA_N:72:result_uint32x2 [] = { 1, 1,  }
+VRSRA_N:73:result_uint64x1 [] = { 1,  }
+VRSRA_N:74:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:75:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSRA_N:76:result_float32x2 [] = { 33333333, 33333333,  }
+VRSRA_N:77:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSRA_N:78:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSRA_N:79:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:80:result_int64x2 [] = { 0, 0,  }
+VRSRA_N:81:result_uint8x16 [] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:82:result_uint16x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:83:result_uint32x4 [] = { 1, 1, 1, 1,  }
+VRSRA_N:84:result_uint64x2 [] = { 1, 1,  }
+VRSRA_N:85:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:86:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSRA_N:87:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSRA_N (checking overflow: shift by 1, negative input) output:
+VRSRA_N:88:result_int8x8 [] = { ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0,  }
+VRSRA_N:89:result_int16x4 [] = { ffffc000, ffffc000, ffffc000, ffffc000,  }
+VRSRA_N:90:result_int32x2 [] = { c0000000, c0000000,  }
+VRSRA_N:91:result_int64x1 [] = { c000000000000000,  }
+VRSRA_N:92:result_uint8x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:93:result_uint16x4 [] = { 1, 1, 1, 1,  }
+VRSRA_N:94:result_uint32x2 [] = { 1, 1,  }
+VRSRA_N:95:result_uint64x1 [] = { 1,  }
+VRSRA_N:96:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:97:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSRA_N:98:result_float32x2 [] = { 33333333, 33333333,  }
+VRSRA_N:99:result_int8x16 [] = { ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0,  }
+VRSRA_N:100:result_int16x8 [] = { ffffc000, ffffc000, ffffc000, ffffc000, ffffc000, ffffc000, ffffc000, ffffc000,  }
+VRSRA_N:101:result_int32x4 [] = { c0000000, c0000000, c0000000, c0000000,  }
+VRSRA_N:102:result_int64x2 [] = { c000000000000000, c000000000000000,  }
+VRSRA_N:103:result_uint8x16 [] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:104:result_uint16x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:105:result_uint32x4 [] = { 1, 1, 1, 1,  }
+VRSRA_N:106:result_uint64x2 [] = { 1, 1,  }
+VRSRA_N:107:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:108:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSRA_N:109:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSRA_N (checking overflow: shift by max, negative input) output:
+VRSRA_N:110:result_int8x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VRSRA_N:111:result_int16x4 [] = { fffff000, fffff000, fffff000, fffff000,  }
+VRSRA_N:112:result_int32x2 [] = { f0000000, f0000000,  }
+VRSRA_N:113:result_int64x1 [] = { f000000000000000,  }
+VRSRA_N:114:result_uint8x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:115:result_uint16x4 [] = { 1, 1, 1, 1,  }
+VRSRA_N:116:result_uint32x2 [] = { 1, 1,  }
+VRSRA_N:117:result_uint64x1 [] = { 1,  }
+VRSRA_N:118:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:119:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSRA_N:120:result_float32x2 [] = { 33333333, 33333333,  }
+VRSRA_N:121:result_int8x16 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VRSRA_N:122:result_int16x8 [] = { fffff000, fffff000, fffff000, fffff000, fffff000, fffff000, fffff000, fffff000,  }
+VRSRA_N:123:result_int32x4 [] = { f0000000, f0000000, f0000000, f0000000,  }
+VRSRA_N:124:result_int64x2 [] = { f000000000000000, f000000000000000,  }
+VRSRA_N:125:result_uint8x16 [] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:126:result_uint16x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:127:result_uint32x4 [] = { 1, 1, 1, 1,  }
+VRSRA_N:128:result_uint64x2 [] = { 1, 1,  }
+VRSRA_N:129:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:130:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSRA_N:131:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRSRA_N (checking overflow: shift by max, negative input) output:
+VRSRA_N:132:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSRA_N:133:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:134:result_int32x2 [] = { 0, 0,  }
+VRSRA_N:135:result_int64x1 [] = { 0,  }
+VRSRA_N:136:result_uint8x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:137:result_uint16x4 [] = { 1, 1, 1, 1,  }
+VRSRA_N:138:result_uint32x2 [] = { 1, 1,  }
+VRSRA_N:139:result_uint64x1 [] = { 1,  }
+VRSRA_N:140:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:141:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSRA_N:142:result_float32x2 [] = { 33333333, 33333333,  }
+VRSRA_N:143:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSRA_N:144:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSRA_N:145:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:146:result_int64x2 [] = { 0, 0,  }
+VRSRA_N:147:result_uint8x16 [] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:148:result_uint16x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:149:result_uint32x4 [] = { 1, 1, 1, 1,  }
+VRSRA_N:150:result_uint64x2 [] = { 1, 1,  }
+VRSRA_N:151:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:152:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSRA_N:153:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VSHLL_N output:
+VSHLL_N:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHLL_N:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHLL_N:2:result_int32x2 [] = { 33333333, 33333333,  }
+VSHLL_N:3:result_int64x1 [] = { 3333333333333333,  }
+VSHLL_N:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHLL_N:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHLL_N:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VSHLL_N:7:result_uint64x1 [] = { 3333333333333333,  }
+VSHLL_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHLL_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHLL_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSHLL_N:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHLL_N:12:result_int16x8 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6, ffffffe8, ffffffea, ffffffec, ffffffee,  }
+VSHLL_N:13:result_int32x4 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6,  }
+VSHLL_N:14:result_int64x2 [] = { ffffffffffffff80, ffffffffffffff88,  }
+VSHLL_N:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHLL_N:16:result_uint16x8 [] = { 3c0, 3c4, 3c8, 3cc, 3d0, 3d4, 3d8, 3dc,  }
+VSHLL_N:17:result_uint32x4 [] = { fff00, fff10, fff20, fff30,  }
+VSHLL_N:18:result_uint64x2 [] = { 7ffffff80, 7ffffff88,  }
+VSHLL_N:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHLL_N:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHLL_N:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VPADDL/VPADDLQ output:
+VPADDL/VPADDLQ:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADDL/VPADDLQ:1:result_int16x4 [] = { ffffffe1, ffffffe5, ffffffe9, ffffffed,  }
+VPADDL/VPADDLQ:2:result_int32x2 [] = { ffffffe1, ffffffe5,  }
+VPADDL/VPADDLQ:3:result_int64x1 [] = { ffffffffffffffe1,  }
+VPADDL/VPADDLQ:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADDL/VPADDLQ:5:result_uint16x4 [] = { 1e1, 1e5, 1e9, 1ed,  }
+VPADDL/VPADDLQ:6:result_uint32x2 [] = { 1ffe1, 1ffe5,  }
+VPADDL/VPADDLQ:7:result_uint64x1 [] = { 1ffffffe1,  }
+VPADDL/VPADDLQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADDL/VPADDLQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VPADDL/VPADDLQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VPADDL/VPADDLQ:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADDL/VPADDLQ:12:result_int16x8 [] = { ffffffe1, ffffffe5, ffffffe9, ffffffed, fffffff1, fffffff5, fffffff9, fffffffd,  }
+VPADDL/VPADDLQ:13:result_int32x4 [] = { ffffffe1, ffffffe5, ffffffe9, ffffffed,  }
+VPADDL/VPADDLQ:14:result_int64x2 [] = { ffffffffffffffe1, ffffffffffffffe5,  }
+VPADDL/VPADDLQ:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADDL/VPADDLQ:16:result_uint16x8 [] = { 1e1, 1e5, 1e9, 1ed, 1f1, 1f5, 1f9, 1fd,  }
+VPADDL/VPADDLQ:17:result_uint32x4 [] = { 1ffe1, 1ffe5, 1ffe9, 1ffed,  }
+VPADDL/VPADDLQ:18:result_uint64x2 [] = { 1ffffffe1, 1ffffffe5,  }
+VPADDL/VPADDLQ:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADDL/VPADDLQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPADDL/VPADDLQ:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VPADD output:
+VPADD:0:result_int8x8 [] = { ffffffe1, ffffffe5, ffffffe9, ffffffed, ffffffe1, ffffffe5, ffffffe9, ffffffed,  }
+VPADD:1:result_int16x4 [] = { ffffffe1, ffffffe5, ffffffe1, ffffffe5,  }
+VPADD:2:result_int32x2 [] = { ffffffe1, ffffffe1,  }
+VPADD:3:result_int64x1 [] = { 3333333333333333,  }
+VPADD:4:result_uint8x8 [] = { e1, e5, e9, ed, e1, e5, e9, ed,  }
+VPADD:5:result_uint16x4 [] = { ffe1, ffe5, ffe1, ffe5,  }
+VPADD:6:result_uint32x2 [] = { ffffffe1, ffffffe1,  }
+VPADD:7:result_uint64x1 [] = { 3333333333333333,  }
+VPADD:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADD:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VPADD:10:result_float32x2 [] = { c1f80000, c1f80000,  }
+VPADD:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADD:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPADD:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPADD:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VPADD:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADD:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPADD:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPADD:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VPADD:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADD:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPADD:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VPADAL/VPADALQ output:
+VPADAL/VPADALQ:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADAL/VPADALQ:1:result_int16x4 [] = { ffffffd1, ffffffd6, ffffffdb, ffffffe0,  }
+VPADAL/VPADALQ:2:result_int32x2 [] = { ffffffd1, ffffffd6,  }
+VPADAL/VPADALQ:3:result_int64x1 [] = { ffffffffffffffd1,  }
+VPADAL/VPADALQ:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADAL/VPADALQ:5:result_uint16x4 [] = { 1d1, 1d6, 1db, 1e0,  }
+VPADAL/VPADALQ:6:result_uint32x2 [] = { 1ffd1, 1ffd6,  }
+VPADAL/VPADALQ:7:result_uint64x1 [] = { 1ffffffd1,  }
+VPADAL/VPADALQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADAL/VPADALQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VPADAL/VPADALQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VPADAL/VPADALQ:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADAL/VPADALQ:12:result_int16x8 [] = { ffffffd1, ffffffd6, ffffffdb, ffffffe0, ffffffe5, ffffffea, ffffffef, fffffff4,  }
+VPADAL/VPADALQ:13:result_int32x4 [] = { ffffffd1, ffffffd6, ffffffdb, ffffffe0,  }
+VPADAL/VPADALQ:14:result_int64x2 [] = { ffffffffffffffd1, ffffffffffffffd6,  }
+VPADAL/VPADALQ:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADAL/VPADALQ:16:result_uint16x8 [] = { 1d1, 1d6, 1db, 1e0, 1e5, 1ea, 1ef, 1f4,  }
+VPADAL/VPADALQ:17:result_uint32x4 [] = { 1ffd1, 1ffd6, 1ffdb, 1ffe0,  }
+VPADAL/VPADALQ:18:result_uint64x2 [] = { 1ffffffd1, 1ffffffd6,  }
+VPADAL/VPADALQ:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADAL/VPADALQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPADAL/VPADALQ:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQSHLU_N/VQSHLUQ_N (negative input) cumulative saturation output:
+VQSHLU_N/VQSHLUQ_N:0:vqshlu_n_s8 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:1:vqshlu_n_s16 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:2:vqshlu_n_s32 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:3:vqshlu_n_s64 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:4:vqshluq_n_s8 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:5:vqshluq_n_s16 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:6:vqshluq_n_s32 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:7:vqshluq_n_s64 Neon cumulative saturation 1
+
+VQSHLU_N/VQSHLUQ_N (negative input) output:
+VQSHLU_N/VQSHLUQ_N:8:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:9:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:10:result_int32x2 [] = { 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:11:result_int64x1 [] = { 3333333333333333,  }
+VQSHLU_N/VQSHLUQ_N:12:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:13:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:14:result_uint32x2 [] = { 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:15:result_uint64x1 [] = { 0,  }
+VQSHLU_N/VQSHLUQ_N:16:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:17:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:18:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:19:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:20:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:21:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:22:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHLU_N/VQSHLUQ_N:23:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:24:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:25:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:26:result_uint64x2 [] = { 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:27:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:28:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:29:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQSHLU_N/VQSHLUQ_N (check cumulative saturation: shift by 1) cumulative saturation output:
+VQSHLU_N/VQSHLUQ_N:30:vqshlu_n_s8 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:31:vqshlu_n_s16 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:32:vqshlu_n_s32 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:33:vqshlu_n_s64 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:34:vqshluq_n_s8 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:35:vqshluq_n_s16 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:36:vqshluq_n_s32 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:37:vqshluq_n_s64 Neon cumulative saturation 0
+
+VQSHLU_N/VQSHLUQ_N (check cumulative saturation: shift by 1) output:
+VQSHLU_N/VQSHLUQ_N:38:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:39:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:40:result_int32x2 [] = { 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:41:result_int64x1 [] = { 3333333333333333,  }
+VQSHLU_N/VQSHLUQ_N:42:result_uint8x8 [] = { fe, fe, fe, fe, fe, fe, fe, fe,  }
+VQSHLU_N/VQSHLUQ_N:43:result_uint16x4 [] = { fffe, fffe, fffe, fffe,  }
+VQSHLU_N/VQSHLUQ_N:44:result_uint32x2 [] = { fffffffe, fffffffe,  }
+VQSHLU_N/VQSHLUQ_N:45:result_uint64x1 [] = { fffffffffffffffe,  }
+VQSHLU_N/VQSHLUQ_N:46:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:47:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:48:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:49:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:50:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:51:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:52:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHLU_N/VQSHLUQ_N:53:result_uint8x16 [] = { fe, fe, fe, fe, fe, fe, fe, fe, fe, fe, fe, fe, fe, fe, fe, fe,  }
+VQSHLU_N/VQSHLUQ_N:54:result_uint16x8 [] = { fffe, fffe, fffe, fffe, fffe, fffe, fffe, fffe,  }
+VQSHLU_N/VQSHLUQ_N:55:result_uint32x4 [] = { fffffffe, fffffffe, fffffffe, fffffffe,  }
+VQSHLU_N/VQSHLUQ_N:56:result_uint64x2 [] = { fffffffffffffffe, fffffffffffffffe,  }
+VQSHLU_N/VQSHLUQ_N:57:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:58:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:59:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQSHLU_N/VQSHLUQ_N (check cumulative saturation: shift by 2) cumulative saturation output:
+VQSHLU_N/VQSHLUQ_N:60:vqshlu_n_s8 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:61:vqshlu_n_s16 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:62:vqshlu_n_s32 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:63:vqshlu_n_s64 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:64:vqshluq_n_s8 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:65:vqshluq_n_s16 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:66:vqshluq_n_s32 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:67:vqshluq_n_s64 Neon cumulative saturation 1
+
+VQSHLU_N/VQSHLUQ_N (check cumulative saturation: shift by 2) output:
+VQSHLU_N/VQSHLUQ_N:68:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:69:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:70:result_int32x2 [] = { 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:71:result_int64x1 [] = { 3333333333333333,  }
+VQSHLU_N/VQSHLUQ_N:72:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHLU_N/VQSHLUQ_N:73:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHLU_N/VQSHLUQ_N:74:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHLU_N/VQSHLUQ_N:75:result_uint64x1 [] = { ffffffffffffffff,  }
+VQSHLU_N/VQSHLUQ_N:76:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:77:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:78:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:79:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:80:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:81:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:82:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHLU_N/VQSHLUQ_N:83:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHLU_N/VQSHLUQ_N:84:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQSHLU_N/VQSHLUQ_N:85:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHLU_N/VQSHLUQ_N:86:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQSHLU_N/VQSHLUQ_N:87:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:88:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:89:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQSHLU_N/VQSHLUQ_N cumulative saturation output:
+VQSHLU_N/VQSHLUQ_N:90:vqshlu_n_s8 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:91:vqshlu_n_s16 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:92:vqshlu_n_s32 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:93:vqshlu_n_s64 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:94:vqshluq_n_s8 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:95:vqshluq_n_s16 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:96:vqshluq_n_s32 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:97:vqshluq_n_s64 Neon cumulative saturation 0
+
+VQSHLU_N/VQSHLUQ_N output:
+VQSHLU_N/VQSHLUQ_N:98:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:99:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:100:result_int32x2 [] = { 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:101:result_int64x1 [] = { 3333333333333333,  }
+VQSHLU_N/VQSHLUQ_N:102:result_uint8x8 [] = { 2, 2, 2, 2, 2, 2, 2, 2,  }
+VQSHLU_N/VQSHLUQ_N:103:result_uint16x4 [] = { 8, 8, 8, 8,  }
+VQSHLU_N/VQSHLUQ_N:104:result_uint32x2 [] = { 18, 18,  }
+VQSHLU_N/VQSHLUQ_N:105:result_uint64x1 [] = { 40,  }
+VQSHLU_N/VQSHLUQ_N:106:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:107:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:108:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:109:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:110:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:111:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:112:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHLU_N/VQSHLUQ_N:113:result_uint8x16 [] = { a0, a0, a0, a0, a0, a0, a0, a0, a0, a0, a0, a0, a0, a0, a0, a0,  }
+VQSHLU_N/VQSHLUQ_N:114:result_uint16x8 [] = { 180, 180, 180, 180, 180, 180, 180, 180,  }
+VQSHLU_N/VQSHLUQ_N:115:result_uint32x4 [] = { 380, 380, 380, 380,  }
+VQSHLU_N/VQSHLUQ_N:116:result_uint64x2 [] = { 800, 800,  }
+VQSHLU_N/VQSHLUQ_N:117:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:118:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:119:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VCLZ/VCLZQ output:
+VCLZ/VCLZQ:0:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VCLZ/VCLZQ:1:result_int16x4 [] = { 3, 3, 3, 3,  }
+VCLZ/VCLZQ:2:result_int32x2 [] = { 11, 11,  }
+VCLZ/VCLZQ:3:result_int64x1 [] = { 3333333333333333,  }
+VCLZ/VCLZQ:4:result_uint8x8 [] = { 2, 2, 2, 2, 2, 2, 2, 2,  }
+VCLZ/VCLZQ:5:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VCLZ/VCLZQ:6:result_uint32x2 [] = { 5, 5,  }
+VCLZ/VCLZQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VCLZ/VCLZQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLZ/VCLZQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCLZ/VCLZQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VCLZ/VCLZQ:11:result_int8x16 [] = { 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,  }
+VCLZ/VCLZQ:12:result_int16x8 [] = { 3, 3, 3, 3, 3, 3, 3, 3,  }
+VCLZ/VCLZQ:13:result_int32x4 [] = { 3, 3, 3, 3,  }
+VCLZ/VCLZQ:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCLZ/VCLZQ:15:result_uint8x16 [] = { 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,  }
+VCLZ/VCLZQ:16:result_uint16x8 [] = { d, d, d, d, d, d, d, d,  }
+VCLZ/VCLZQ:17:result_uint32x4 [] = { 1f, 1f, 1f, 1f,  }
+VCLZ/VCLZQ:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCLZ/VCLZQ:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLZ/VCLZQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCLZ/VCLZQ:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VCLZ/VCLZQ (input=0) output:
+VCLZ/VCLZQ:22:result_int8x8 [] = { 8, 8, 8, 8, 8, 8, 8, 8,  }
+VCLZ/VCLZQ:23:result_int16x4 [] = { 10, 10, 10, 10,  }
+VCLZ/VCLZQ:24:result_int32x2 [] = { 20, 20,  }
+VCLZ/VCLZQ:25:result_int64x1 [] = { 3333333333333333,  }
+VCLZ/VCLZQ:26:result_uint8x8 [] = { 8, 8, 8, 8, 8, 8, 8, 8,  }
+VCLZ/VCLZQ:27:result_uint16x4 [] = { 10, 10, 10, 10,  }
+VCLZ/VCLZQ:28:result_uint32x2 [] = { 20, 20,  }
+VCLZ/VCLZQ:29:result_uint64x1 [] = { 3333333333333333,  }
+VCLZ/VCLZQ:30:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLZ/VCLZQ:31:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCLZ/VCLZQ:32:result_float32x2 [] = { 33333333, 33333333,  }
+VCLZ/VCLZQ:33:result_int8x16 [] = { 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,  }
+VCLZ/VCLZQ:34:result_int16x8 [] = { 10, 10, 10, 10, 10, 10, 10, 10,  }
+VCLZ/VCLZQ:35:result_int32x4 [] = { 20, 20, 20, 20,  }
+VCLZ/VCLZQ:36:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCLZ/VCLZQ:37:result_uint8x16 [] = { 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,  }
+VCLZ/VCLZQ:38:result_uint16x8 [] = { 10, 10, 10, 10, 10, 10, 10, 10,  }
+VCLZ/VCLZQ:39:result_uint32x4 [] = { 20, 20, 20, 20,  }
+VCLZ/VCLZQ:40:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCLZ/VCLZQ:41:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLZ/VCLZQ:42:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCLZ/VCLZQ:43:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VCLS/VCLSQ (positive input) output:
+VCLS/VCLSQ:0:result_int8x8 [] = { 6, 6, 6, 6, 6, 6, 6, 6,  }
+VCLS/VCLSQ:1:result_int16x4 [] = { 2, 2, 2, 2,  }
+VCLS/VCLSQ:2:result_int32x2 [] = { 19, 19,  }
+VCLS/VCLSQ:3:result_int64x1 [] = { 3333333333333333,  }
+VCLS/VCLSQ:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLS/VCLSQ:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCLS/VCLSQ:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VCLS/VCLSQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VCLS/VCLSQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLS/VCLSQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCLS/VCLSQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VCLS/VCLSQ:11:result_int8x16 [] = { 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,  }
+VCLS/VCLSQ:12:result_int16x8 [] = { 2, 2, 2, 2, 2, 2, 2, 2,  }
+VCLS/VCLSQ:13:result_int32x4 [] = { 14, 14, 14, 14,  }
+VCLS/VCLSQ:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCLS/VCLSQ:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLS/VCLSQ:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCLS/VCLSQ:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCLS/VCLSQ:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCLS/VCLSQ:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLS/VCLSQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCLS/VCLSQ:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VCLS/VCLSQ (negative input) output:
+VCLS/VCLSQ:22:result_int8x8 [] = { 7, 7, 7, 7, 7, 7, 7, 7,  }
+VCLS/VCLSQ:23:result_int16x4 [] = { 1, 1, 1, 1,  }
+VCLS/VCLSQ:24:result_int32x2 [] = { 1, 1,  }
+VCLS/VCLSQ:25:result_int64x1 [] = { 3333333333333333,  }
+VCLS/VCLSQ:26:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLS/VCLSQ:27:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCLS/VCLSQ:28:result_uint32x2 [] = { 33333333, 33333333,  }
+VCLS/VCLSQ:29:result_uint64x1 [] = { 3333333333333333,  }
+VCLS/VCLSQ:30:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLS/VCLSQ:31:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCLS/VCLSQ:32:result_float32x2 [] = { 33333333, 33333333,  }
+VCLS/VCLSQ:33:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VCLS/VCLSQ:34:result_int16x8 [] = { 2, 2, 2, 2, 2, 2, 2, 2,  }
+VCLS/VCLSQ:35:result_int32x4 [] = { 0, 0, 0, 0,  }
+VCLS/VCLSQ:36:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCLS/VCLSQ:37:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLS/VCLSQ:38:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCLS/VCLSQ:39:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCLS/VCLSQ:40:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCLS/VCLSQ:41:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLS/VCLSQ:42:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCLS/VCLSQ:43:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VCNT/VCNTQ output:
+VCNT/VCNTQ:0:result_int8x8 [] = { 8, 8, 8, 8, 8, 8, 8, 8,  }
+VCNT/VCNTQ:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCNT/VCNTQ:2:result_int32x2 [] = { 33333333, 33333333,  }
+VCNT/VCNTQ:3:result_int64x1 [] = { 3333333333333333,  }
+VCNT/VCNTQ:4:result_uint8x8 [] = { 4, 4, 4, 4, 4, 4, 4, 4,  }
+VCNT/VCNTQ:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCNT/VCNTQ:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VCNT/VCNTQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VCNT/VCNTQ:8:result_poly8x8 [] = { 4, 4, 4, 4, 4, 4, 4, 4,  }
+VCNT/VCNTQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCNT/VCNTQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VCNT/VCNTQ:11:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VCNT/VCNTQ:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCNT/VCNTQ:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCNT/VCNTQ:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCNT/VCNTQ:15:result_uint8x16 [] = { 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,  }
+VCNT/VCNTQ:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCNT/VCNTQ:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCNT/VCNTQ:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCNT/VCNTQ:19:result_poly8x16 [] = { 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,  }
+VCNT/VCNTQ:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCNT/VCNTQ:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQSHRN_N cumulative saturation output:
+VQSHRN_N:0:vqshrn_n_s16 Neon cumulative saturation 0
+VQSHRN_N:1:vqshrn_n_s32 Neon cumulative saturation 0
+VQSHRN_N:2:vqshrn_n_s64 Neon cumulative saturation 0
+VQSHRN_N:3:vqshrn_n_u16 Neon cumulative saturation 1
+VQSHRN_N:4:vqshrn_n_u32 Neon cumulative saturation 1
+VQSHRN_N:5:vqshrn_n_u64 Neon cumulative saturation 1
+
+VQSHRN_N output:
+VQSHRN_N:6:result_int8x8 [] = { fffffff8, fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb,  }
+VQSHRN_N:7:result_int16x4 [] = { fffffff8, fffffff8, fffffff9, fffffff9,  }
+VQSHRN_N:8:result_int32x2 [] = { fffffffc, fffffffc,  }
+VQSHRN_N:9:result_int64x1 [] = { 3333333333333333,  }
+VQSHRN_N:10:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHRN_N:11:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHRN_N:12:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHRN_N:13:result_uint64x1 [] = { 3333333333333333,  }
+VQSHRN_N:14:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:15:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRN_N:16:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHRN_N:17:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:18:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:19:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRN_N:20:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRN_N:21:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:22:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:23:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRN_N:24:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRN_N:25:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:26:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:27:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQSHRN_N (check saturation: shift by 3) cumulative saturation output:
+VQSHRN_N:28:vqshrn_n_s16 Neon cumulative saturation 1
+VQSHRN_N:29:vqshrn_n_s32 Neon cumulative saturation 1
+VQSHRN_N:30:vqshrn_n_s64 Neon cumulative saturation 1
+VQSHRN_N:31:vqshrn_n_u16 Neon cumulative saturation 1
+VQSHRN_N:32:vqshrn_n_u32 Neon cumulative saturation 1
+VQSHRN_N:33:vqshrn_n_u64 Neon cumulative saturation 1
+
+VQSHRN_N (check saturation: shift by 3) output:
+VQSHRN_N:34:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHRN_N:35:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQSHRN_N:36:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQSHRN_N:37:result_int64x1 [] = { 3333333333333333,  }
+VQSHRN_N:38:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHRN_N:39:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHRN_N:40:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHRN_N:41:result_uint64x1 [] = { 3333333333333333,  }
+VQSHRN_N:42:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:43:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRN_N:44:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHRN_N:45:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:46:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:47:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRN_N:48:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRN_N:49:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:50:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:51:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRN_N:52:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRN_N:53:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:54:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:55:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQSHRN_N (check saturation: shift by max) cumulative saturation output:
+VQSHRN_N:56:vqshrn_n_s16 Neon cumulative saturation 0
+VQSHRN_N:57:vqshrn_n_s32 Neon cumulative saturation 0
+VQSHRN_N:58:vqshrn_n_s64 Neon cumulative saturation 0
+VQSHRN_N:59:vqshrn_n_u16 Neon cumulative saturation 0
+VQSHRN_N:60:vqshrn_n_u32 Neon cumulative saturation 0
+VQSHRN_N:61:vqshrn_n_u64 Neon cumulative saturation 0
+
+VQSHRN_N (check saturation: shift by max) output:
+VQSHRN_N:62:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHRN_N:63:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQSHRN_N:64:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQSHRN_N:65:result_int64x1 [] = { 3333333333333333,  }
+VQSHRN_N:66:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHRN_N:67:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHRN_N:68:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHRN_N:69:result_uint64x1 [] = { 3333333333333333,  }
+VQSHRN_N:70:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:71:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRN_N:72:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHRN_N:73:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:74:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:75:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRN_N:76:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRN_N:77:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:78:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:79:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRN_N:80:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRN_N:81:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:82:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:83:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VPMAX output:
+VPMAX:0:result_int8x8 [] = { fffffff1, fffffff3, fffffff5, fffffff7, fffffff1, fffffff3, fffffff5, fffffff7,  }
+VPMAX:1:result_int16x4 [] = { fffffff1, fffffff3, fffffff1, fffffff3,  }
+VPMAX:2:result_int32x2 [] = { fffffff1, fffffff1,  }
+VPMAX:3:result_int64x1 [] = { 3333333333333333,  }
+VPMAX:4:result_uint8x8 [] = { f1, f3, f5, f7, f1, f3, f5, f7,  }
+VPMAX:5:result_uint16x4 [] = { fff1, fff3, fff1, fff3,  }
+VPMAX:6:result_uint32x2 [] = { fffffff1, fffffff1,  }
+VPMAX:7:result_uint64x1 [] = { 3333333333333333,  }
+VPMAX:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPMAX:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VPMAX:10:result_float32x2 [] = { c1700000, c1700000,  }
+VPMAX:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPMAX:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPMAX:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPMAX:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VPMAX:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPMAX:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPMAX:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPMAX:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VPMAX:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPMAX:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPMAX:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VPMIN output:
+VPMIN:0:result_int8x8 [] = { fffffff0, fffffff2, fffffff4, fffffff6, fffffff0, fffffff2, fffffff4, fffffff6,  }
+VPMIN:1:result_int16x4 [] = { fffffff0, fffffff2, fffffff0, fffffff2,  }
+VPMIN:2:result_int32x2 [] = { fffffff0, fffffff0,  }
+VPMIN:3:result_int64x1 [] = { 3333333333333333,  }
+VPMIN:4:result_uint8x8 [] = { f0, f2, f4, f6, f0, f2, f4, f6,  }
+VPMIN:5:result_uint16x4 [] = { fff0, fff2, fff0, fff2,  }
+VPMIN:6:result_uint32x2 [] = { fffffff0, fffffff0,  }
+VPMIN:7:result_uint64x1 [] = { 3333333333333333,  }
+VPMIN:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPMIN:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VPMIN:10:result_float32x2 [] = { c1800000, c1800000,  }
+VPMIN:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPMIN:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPMIN:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPMIN:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VPMIN:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPMIN:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPMIN:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPMIN:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VPMIN:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPMIN:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPMIN:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQSHRUN_N (negative input) cumulative saturation output:
+VQSHRUN_N:0:vqshrun_n_s16 Neon cumulative saturation 1
+VQSHRUN_N:1:vqshrun_n_s32 Neon cumulative saturation 1
+VQSHRUN_N:2:vqshrun_n_s64 Neon cumulative saturation 1
+
+VQSHRUN_N (negative input) output:
+VQSHRUN_N:3:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:4:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:5:result_int32x2 [] = { 33333333, 33333333,  }
+VQSHRUN_N:6:result_int64x1 [] = { 3333333333333333,  }
+VQSHRUN_N:7:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHRUN_N:8:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQSHRUN_N:9:result_uint32x2 [] = { 0, 0,  }
+VQSHRUN_N:10:result_uint64x1 [] = { 3333333333333333,  }
+VQSHRUN_N:11:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:12:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:13:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHRUN_N:14:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:15:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:16:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRUN_N:17:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRUN_N:18:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:19:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:20:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRUN_N:21:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRUN_N:22:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:23:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:24:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQSHRUN_N (check cumulative saturation) cumulative saturation output:
+VQSHRUN_N:25:vqshrun_n_s16 Neon cumulative saturation 1
+VQSHRUN_N:26:vqshrun_n_s32 Neon cumulative saturation 1
+VQSHRUN_N:27:vqshrun_n_s64 Neon cumulative saturation 1
+
+VQSHRUN_N (check cumulative saturation) output:
+VQSHRUN_N:28:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:29:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:30:result_int32x2 [] = { 33333333, 33333333,  }
+VQSHRUN_N:31:result_int64x1 [] = { 3333333333333333,  }
+VQSHRUN_N:32:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHRUN_N:33:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHRUN_N:34:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHRUN_N:35:result_uint64x1 [] = { 3333333333333333,  }
+VQSHRUN_N:36:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:37:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:38:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHRUN_N:39:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:40:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:41:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRUN_N:42:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRUN_N:43:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:44:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:45:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRUN_N:46:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRUN_N:47:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:48:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:49:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQSHRUN_N cumulative saturation output:
+VQSHRUN_N:50:vqshrun_n_s16 Neon cumulative saturation 0
+VQSHRUN_N:51:vqshrun_n_s32 Neon cumulative saturation 1
+VQSHRUN_N:52:vqshrun_n_s64 Neon cumulative saturation 0
+
+VQSHRUN_N output:
+VQSHRUN_N:53:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:54:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:55:result_int32x2 [] = { 33333333, 33333333,  }
+VQSHRUN_N:56:result_int64x1 [] = { 3333333333333333,  }
+VQSHRUN_N:57:result_uint8x8 [] = { 48, 48, 48, 48, 48, 48, 48, 48,  }
+VQSHRUN_N:58:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQSHRUN_N:59:result_uint32x2 [] = { deadbe, deadbe,  }
+VQSHRUN_N:60:result_uint64x1 [] = { 3333333333333333,  }
+VQSHRUN_N:61:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:62:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:63:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHRUN_N:64:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:65:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:66:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRUN_N:67:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRUN_N:68:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:69:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:70:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRUN_N:71:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRUN_N:72:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:73:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:74:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRSHRUN_N (negative input) cumulative saturation output:
+VQRSHRUN_N:0:vqrshrun_n_s16 Neon cumulative saturation 0
+VQRSHRUN_N:1:vqrshrun_n_s32 Neon cumulative saturation 0
+VQRSHRUN_N:2:vqrshrun_n_s64 Neon cumulative saturation 1
+
+VQRSHRUN_N (negative input) output:
+VQRSHRUN_N:3:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:4:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:5:result_int32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:6:result_int64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:7:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHRUN_N:8:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRUN_N:9:result_uint32x2 [] = { 0, 0,  }
+VQRSHRUN_N:10:result_uint64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:11:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:12:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:13:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:14:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:15:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:16:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:17:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:18:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:19:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:20:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:21:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:22:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:23:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:24:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRSHRUN_N (check cumulative saturation: shift by 1) cumulative saturation output:
+VQRSHRUN_N:25:vqrshrun_n_s16 Neon cumulative saturation 1
+VQRSHRUN_N:26:vqrshrun_n_s32 Neon cumulative saturation 1
+VQRSHRUN_N:27:vqrshrun_n_s64 Neon cumulative saturation 1
+
+VQRSHRUN_N (check cumulative saturation: shift by 1) output:
+VQRSHRUN_N:28:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:29:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:30:result_int32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:31:result_int64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:32:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHRUN_N:33:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQRSHRUN_N:34:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQRSHRUN_N:35:result_uint64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:36:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:37:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:38:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:39:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:40:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:41:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:42:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:43:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:44:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:45:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:46:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:47:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:48:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:49:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRSHRUN_N (check cumulative saturation: shift by max, positive input) cumulative saturation output:
+VQRSHRUN_N:50:vqrshrun_n_s16 Neon cumulative saturation 0
+VQRSHRUN_N:51:vqrshrun_n_s32 Neon cumulative saturation 0
+VQRSHRUN_N:52:vqrshrun_n_s64 Neon cumulative saturation 0
+
+VQRSHRUN_N (check cumulative saturation: shift by max, positive input) output:
+VQRSHRUN_N:53:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:54:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:55:result_int32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:56:result_int64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:57:result_uint8x8 [] = { 80, 80, 80, 80, 80, 80, 80, 80,  }
+VQRSHRUN_N:58:result_uint16x4 [] = { 8000, 8000, 8000, 8000,  }
+VQRSHRUN_N:59:result_uint32x2 [] = { 80000000, 80000000,  }
+VQRSHRUN_N:60:result_uint64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:61:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:62:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:63:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:64:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:65:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:66:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:67:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:68:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:69:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:70:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:71:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:72:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:73:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:74:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRSHRUN_N (check cumulative saturation: shift by max, negative input) cumulative saturation output:
+VQRSHRUN_N:75:vqrshrun_n_s16 Neon cumulative saturation 1
+VQRSHRUN_N:76:vqrshrun_n_s32 Neon cumulative saturation 1
+VQRSHRUN_N:77:vqrshrun_n_s64 Neon cumulative saturation 1
+
+VQRSHRUN_N (check cumulative saturation: shift by max, negative input) output:
+VQRSHRUN_N:78:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:79:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:80:result_int32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:81:result_int64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:82:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHRUN_N:83:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRUN_N:84:result_uint32x2 [] = { 0, 0,  }
+VQRSHRUN_N:85:result_uint64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:86:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:87:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:88:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:89:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:90:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:91:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:92:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:93:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:94:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:95:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:96:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:97:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:98:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:99:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VQRSHRUN_N cumulative saturation output:
+VQRSHRUN_N:100:vqrshrun_n_s16 Neon cumulative saturation 0
+VQRSHRUN_N:101:vqrshrun_n_s32 Neon cumulative saturation 1
+VQRSHRUN_N:102:vqrshrun_n_s64 Neon cumulative saturation 0
+
+VQRSHRUN_N output:
+VQRSHRUN_N:103:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:104:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:105:result_int32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:106:result_int64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:107:result_uint8x8 [] = { 49, 49, 49, 49, 49, 49, 49, 49,  }
+VQRSHRUN_N:108:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRUN_N:109:result_uint32x2 [] = { deadbf, deadbf,  }
+VQRSHRUN_N:110:result_uint64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:111:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:112:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:113:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:114:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:115:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:116:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:117:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:118:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:119:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:120:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:121:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:122:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:123:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:124:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VST2_LANE/VST2Q_LANE chunk 0 output:
+VST2_LANE/VST2Q_LANE:0:result_int8x8 [] = { fffffff0, fffffff1, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:1:result_int16x4 [] = { fffffff0, fffffff1, 0, 0,  }
+VST2_LANE/VST2Q_LANE:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VST2_LANE/VST2Q_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VST2_LANE/VST2Q_LANE:4:result_uint8x8 [] = { f0, f1, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:5:result_uint16x4 [] = { fff0, fff1, 0, 0,  }
+VST2_LANE/VST2Q_LANE:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VST2_LANE/VST2Q_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VST2_LANE/VST2Q_LANE:8:result_poly8x8 [] = { f0, f1, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:9:result_poly16x4 [] = { fff0, fff1, 0, 0,  }
+VST2_LANE/VST2Q_LANE:10:result_float32x2 [] = { c1800000, c1700000,  }
+VST2_LANE/VST2Q_LANE:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST2_LANE/VST2Q_LANE:12:result_int16x8 [] = { fffffff0, fffffff1, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:13:result_int32x4 [] = { fffffff0, fffffff1, 0, 0,  }
+VST2_LANE/VST2Q_LANE:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST2_LANE/VST2Q_LANE:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST2_LANE/VST2Q_LANE:16:result_uint16x8 [] = { fff0, fff1, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:17:result_uint32x4 [] = { fffffff0, fffffff1, 0, 0,  }
+VST2_LANE/VST2Q_LANE:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST2_LANE/VST2Q_LANE:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST2_LANE/VST2Q_LANE:20:result_poly16x8 [] = { fff0, fff1, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:21:result_float32x4 [] = { c1800000, c1700000, 0, 0,  }
+
+VST2_LANE/VST2Q_LANE chunk 1 output:
+VST2_LANE/VST2Q_LANE:22:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:23:result_int16x4 [] = { 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:24:result_int32x2 [] = { 0, 0,  }
+VST2_LANE/VST2Q_LANE:25:result_int64x1 [] = { 3333333333333333,  }
+VST2_LANE/VST2Q_LANE:26:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:27:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:28:result_uint32x2 [] = { 0, 0,  }
+VST2_LANE/VST2Q_LANE:29:result_uint64x1 [] = { 3333333333333333,  }
+VST2_LANE/VST2Q_LANE:30:result_poly8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:31:result_poly16x4 [] = { 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:32:result_float32x2 [] = { 0, 0,  }
+VST2_LANE/VST2Q_LANE:33:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST2_LANE/VST2Q_LANE:34:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:35:result_int32x4 [] = { 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:36:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST2_LANE/VST2Q_LANE:37:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST2_LANE/VST2Q_LANE:38:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:39:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:40:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST2_LANE/VST2Q_LANE:41:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST2_LANE/VST2Q_LANE:42:result_poly16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:43:result_float32x4 [] = { 0, 0, 0, 0,  }
+
+VST3_LANE/VST3Q_LANE chunk 0 output:
+VST3_LANE/VST3Q_LANE:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, 0,  }
+VST3_LANE/VST3Q_LANE:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VST3_LANE/VST3Q_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:4:result_uint8x8 [] = { f0, f1, f2, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:5:result_uint16x4 [] = { fff0, fff1, fff2, 0,  }
+VST3_LANE/VST3Q_LANE:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VST3_LANE/VST3Q_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:8:result_poly8x8 [] = { f0, f1, f2, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:9:result_poly16x4 [] = { fff0, fff1, fff2, 0,  }
+VST3_LANE/VST3Q_LANE:10:result_float32x2 [] = { c1800000, c1700000,  }
+VST3_LANE/VST3Q_LANE:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:12:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:13:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, 0,  }
+VST3_LANE/VST3Q_LANE:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:16:result_uint16x8 [] = { fff0, fff1, fff2, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:17:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, 0,  }
+VST3_LANE/VST3Q_LANE:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:20:result_poly16x8 [] = { fff0, fff1, fff2, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:21:result_float32x4 [] = { c1800000, c1700000, c1600000, 0,  }
+
+VST3_LANE/VST3Q_LANE chunk 1 output:
+VST3_LANE/VST3Q_LANE:22:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:23:result_int16x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:24:result_int32x2 [] = { fffffff2, 0,  }
+VST3_LANE/VST3Q_LANE:25:result_int64x1 [] = { 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:26:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:27:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:28:result_uint32x2 [] = { fffffff2, 0,  }
+VST3_LANE/VST3Q_LANE:29:result_uint64x1 [] = { 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:30:result_poly8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:31:result_poly16x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:32:result_float32x2 [] = { c1600000, 0,  }
+VST3_LANE/VST3Q_LANE:33:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:34:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:35:result_int32x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:36:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:37:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:38:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:39:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:40:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:41:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:42:result_poly16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:43:result_float32x4 [] = { 0, 0, 0, 0,  }
+
+VST3_LANE/VST3Q_LANE chunk 2 output:
+VST3_LANE/VST3Q_LANE:44:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:45:result_int16x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:46:result_int32x2 [] = { 0, 0,  }
+VST3_LANE/VST3Q_LANE:47:result_int64x1 [] = { 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:48:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:49:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:50:result_uint32x2 [] = { 0, 0,  }
+VST3_LANE/VST3Q_LANE:51:result_uint64x1 [] = { 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:52:result_poly8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:53:result_poly16x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:54:result_float32x2 [] = { 0, 0,  }
+VST3_LANE/VST3Q_LANE:55:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:56:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:57:result_int32x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:58:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:59:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:60:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:61:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:62:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:63:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:64:result_poly16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:65:result_float32x4 [] = { 0, 0, 0, 0,  }
+
+VST4_LANE/VST4Q_LANE chunk 0 output:
+VST4_LANE/VST4Q_LANE:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VST4_LANE/VST4Q_LANE:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VST4_LANE/VST4Q_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:4:result_uint8x8 [] = { f0, f1, f2, f3, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VST4_LANE/VST4Q_LANE:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VST4_LANE/VST4Q_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:8:result_poly8x8 [] = { f0, f1, f2, f3, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VST4_LANE/VST4Q_LANE:10:result_float32x2 [] = { c1800000, c1700000,  }
+VST4_LANE/VST4Q_LANE:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:12:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:13:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VST4_LANE/VST4Q_LANE:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:16:result_uint16x8 [] = { fff0, fff1, fff2, fff3, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:17:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VST4_LANE/VST4Q_LANE:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:20:result_poly16x8 [] = { fff0, fff1, fff2, fff3, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:21:result_float32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+
+VST4_LANE/VST4Q_LANE chunk 1 output:
+VST4_LANE/VST4Q_LANE:22:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:23:result_int16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:24:result_int32x2 [] = { fffffff2, fffffff3,  }
+VST4_LANE/VST4Q_LANE:25:result_int64x1 [] = { 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:26:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:27:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:28:result_uint32x2 [] = { fffffff2, fffffff3,  }
+VST4_LANE/VST4Q_LANE:29:result_uint64x1 [] = { 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:30:result_poly8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:31:result_poly16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:32:result_float32x2 [] = { c1600000, c1500000,  }
+VST4_LANE/VST4Q_LANE:33:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:34:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:35:result_int32x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:36:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:37:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:38:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:39:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:40:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:41:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:42:result_poly16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:43:result_float32x4 [] = { 0, 0, 0, 0,  }
+
+VST4_LANE/VST4Q_LANE chunk 2 output:
+VST4_LANE/VST4Q_LANE:44:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:45:result_int16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:46:result_int32x2 [] = { 0, 0,  }
+VST4_LANE/VST4Q_LANE:47:result_int64x1 [] = { 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:48:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:49:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:50:result_uint32x2 [] = { 0, 0,  }
+VST4_LANE/VST4Q_LANE:51:result_uint64x1 [] = { 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:52:result_poly8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:53:result_poly16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:54:result_float32x2 [] = { 0, 0,  }
+VST4_LANE/VST4Q_LANE:55:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:56:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:57:result_int32x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:58:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:59:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:60:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:61:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:62:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:63:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:64:result_poly16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:65:result_float32x4 [] = { 0, 0, 0, 0,  }
+
+VST4_LANE/VST4Q_LANE chunk 3 output:
+VST4_LANE/VST4Q_LANE:66:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:67:result_int16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:68:result_int32x2 [] = { 0, 0,  }
+VST4_LANE/VST4Q_LANE:69:result_int64x1 [] = { 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:70:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:71:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:72:result_uint32x2 [] = { 0, 0,  }
+VST4_LANE/VST4Q_LANE:73:result_uint64x1 [] = { 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:74:result_poly8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:75:result_poly16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:76:result_float32x2 [] = { 0, 0,  }
+VST4_LANE/VST4Q_LANE:77:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:78:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:79:result_int32x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:80:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:81:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:82:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:83:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:84:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:85:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:86:result_poly16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:87:result_float32x4 [] = { 0, 0, 0, 0,  }
+
+VTBL1 output:
+VTBL1:0:result_int8x8 [] = { 0, fffffff2, fffffff2, fffffff2, 0, 0, fffffff2, fffffff2,  }
+VTBL1:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL1:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTBL1:3:result_int64x1 [] = { 3333333333333333,  }
+VTBL1:4:result_uint8x8 [] = { 0, f3, f3, f3, 0, 0, f3, f3,  }
+VTBL1:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL1:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VTBL1:7:result_uint64x1 [] = { 3333333333333333,  }
+VTBL1:8:result_poly8x8 [] = { 0, f3, f3, f3, 0, 0, f3, f3,  }
+VTBL1:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL1:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTBL1:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL1:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL1:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL1:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBL1:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL1:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL1:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL1:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBL1:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL1:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL1:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VTBL2 output:
+VTBL2:0:result_int8x8 [] = { fffffff6, fffffff3, fffffff3, fffffff3, 0, 0, fffffff3, fffffff3,  }
+VTBL2:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL2:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTBL2:3:result_int64x1 [] = { 3333333333333333,  }
+VTBL2:4:result_uint8x8 [] = { f6, f5, f5, f5, 0, 0, f5, f5,  }
+VTBL2:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL2:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VTBL2:7:result_uint64x1 [] = { 3333333333333333,  }
+VTBL2:8:result_poly8x8 [] = { f6, f5, f5, f5, 0, 0, f5, f5,  }
+VTBL2:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL2:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTBL2:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL2:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL2:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL2:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBL2:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL2:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL2:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL2:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBL2:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL2:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL2:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VTBL3 output:
+VTBL3:0:result_int8x8 [] = { fffffff8, fffffff4, fffffff4, fffffff4, ffffffff, 0, fffffff4, fffffff4,  }
+VTBL3:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL3:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTBL3:3:result_int64x1 [] = { 3333333333333333,  }
+VTBL3:4:result_uint8x8 [] = { f8, f7, f7, f7, ff, 0, f7, f7,  }
+VTBL3:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL3:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VTBL3:7:result_uint64x1 [] = { 3333333333333333,  }
+VTBL3:8:result_poly8x8 [] = { f8, f7, f7, f7, ff, 0, f7, f7,  }
+VTBL3:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL3:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTBL3:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL3:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL3:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL3:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBL3:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL3:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL3:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL3:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBL3:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL3:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL3:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VTBL4 output:
+VTBL4:0:result_int8x8 [] = { fffffffa, fffffff5, fffffff5, fffffff5, 3, 0, fffffff5, fffffff5,  }
+VTBL4:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL4:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTBL4:3:result_int64x1 [] = { 3333333333333333,  }
+VTBL4:4:result_uint8x8 [] = { fa, f9, f9, f9, 3, 0, f9, f9,  }
+VTBL4:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL4:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VTBL4:7:result_uint64x1 [] = { 3333333333333333,  }
+VTBL4:8:result_poly8x8 [] = { fa, f9, f9, f9, 3, 0, f9, f9,  }
+VTBL4:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL4:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTBL4:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL4:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL4:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL4:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBL4:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL4:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL4:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL4:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBL4:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL4:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL4:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VTBX1 output:
+VTBX1:0:result_int8x8 [] = { 33, fffffff2, fffffff2, fffffff2, 33, 33, fffffff2, fffffff2,  }
+VTBX1:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX1:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTBX1:3:result_int64x1 [] = { 3333333333333333,  }
+VTBX1:4:result_uint8x8 [] = { cc, f3, f3, f3, cc, cc, f3, f3,  }
+VTBX1:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX1:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VTBX1:7:result_uint64x1 [] = { 3333333333333333,  }
+VTBX1:8:result_poly8x8 [] = { cc, f3, f3, f3, cc, cc, f3, f3,  }
+VTBX1:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX1:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTBX1:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX1:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX1:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX1:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBX1:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX1:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX1:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX1:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBX1:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX1:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX1:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VTBX2 output:
+VTBX2:0:result_int8x8 [] = { fffffff6, fffffff3, fffffff3, fffffff3, 33, 33, fffffff3, fffffff3,  }
+VTBX2:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX2:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTBX2:3:result_int64x1 [] = { 3333333333333333,  }
+VTBX2:4:result_uint8x8 [] = { f6, f5, f5, f5, cc, cc, f5, f5,  }
+VTBX2:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX2:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VTBX2:7:result_uint64x1 [] = { 3333333333333333,  }
+VTBX2:8:result_poly8x8 [] = { f6, f5, f5, f5, cc, cc, f5, f5,  }
+VTBX2:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX2:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTBX2:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX2:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX2:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX2:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBX2:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX2:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX2:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX2:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBX2:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX2:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX2:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VTBX3 output:
+VTBX3:0:result_int8x8 [] = { fffffff8, fffffff4, fffffff4, fffffff4, ffffffff, 33, fffffff4, fffffff4,  }
+VTBX3:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX3:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTBX3:3:result_int64x1 [] = { 3333333333333333,  }
+VTBX3:4:result_uint8x8 [] = { f8, f7, f7, f7, ff, cc, f7, f7,  }
+VTBX3:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX3:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VTBX3:7:result_uint64x1 [] = { 3333333333333333,  }
+VTBX3:8:result_poly8x8 [] = { f8, f7, f7, f7, ff, cc, f7, f7,  }
+VTBX3:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX3:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTBX3:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX3:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX3:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX3:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBX3:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX3:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX3:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX3:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBX3:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX3:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX3:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VTBX4 output:
+VTBX4:0:result_int8x8 [] = { fffffffa, fffffff5, fffffff5, fffffff5, 3, 33, fffffff5, fffffff5,  }
+VTBX4:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX4:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTBX4:3:result_int64x1 [] = { 3333333333333333,  }
+VTBX4:4:result_uint8x8 [] = { fa, f9, f9, f9, 3, cc, f9, f9,  }
+VTBX4:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX4:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VTBX4:7:result_uint64x1 [] = { 3333333333333333,  }
+VTBX4:8:result_poly8x8 [] = { fa, f9, f9, f9, 3, cc, f9, f9,  }
+VTBX4:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX4:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTBX4:11:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX4:12:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX4:13:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX4:14:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBX4:15:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX4:16:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX4:17:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX4:18:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBX4:19:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX4:20:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX4:21:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+
+VRECPE/VRECPEQ  (positive input) output:
+VRECPE/VRECPEQ:0:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VRECPE/VRECPEQ:1:result_uint32x4 [] = { bf000000, bf000000, bf000000, bf000000,  }
+VRECPE/VRECPEQ:2:result_float32x2 [] = { 3f068000, 3f068000,  }
+VRECPE/VRECPEQ:3:result_float32x4 [] = { 3c030000, 3c030000, 3c030000, 3c030000,  }
+
+VRECPE/VRECPEQ  (negative input) output:
+VRECPE/VRECPEQ:4:result_uint32x2 [] = { 80000000, 80000000,  }
+VRECPE/VRECPEQ:5:result_uint32x4 [] = { ee800000, ee800000, ee800000, ee800000,  }
+VRECPE/VRECPEQ:6:result_float32x2 [] = { bdcc8000, bdcc8000,  }
+VRECPE/VRECPEQ:7:result_float32x4 [] = { bc030000, bc030000, bc030000, bc030000,  }
+
+VRECPE/VRECPEQ  FP special (NaN, infinity) output:
+VRECPE/VRECPEQ:8:result_float32x2 [] = { 7fc00000, 7fc00000,  }
+VRECPE/VRECPEQ:9:result_float32x4 [] = { 0, 0, 0, 0,  }
+
+VRECPE/VRECPEQ  FP special (zero, large value) output:
+VRECPE/VRECPEQ:10:result_float32x2 [] = { 7f800000, 7f800000,  }
+VRECPE/VRECPEQ:11:result_float32x4 [] = { 0, 0, 0, 0,  }
+
+VRECPE/VRECPEQ  FP special (-0, -infinity) output:
+VRECPE/VRECPEQ:12:result_float32x2 [] = { ff800000, ff800000,  }
+VRECPE/VRECPEQ:13:result_float32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+
+VRECPE/VRECPEQ  FP special (large negative value) output:
+VRECPE/VRECPEQ:14:result_float32x2 [] = { 80000000, 80000000,  }
+
+VRSQRTE/VRSQRTEQ output:
+VRSQRTE/VRSQRTEQ:0:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VRSQRTE/VRSQRTEQ:1:result_uint32x4 [] = { 9c800000, 9c800000, 9c800000, 9c800000,  }
+VRSQRTE/VRSQRTEQ:2:result_float32x2 [] = { 3e498000, 3e498000,  }
+VRSQRTE/VRSQRTEQ:3:result_float32x4 [] = { 3e700000, 3e700000, 3e700000, 3e700000,  }
+
+VRSQRTE/VRSQRTEQ (2) output:
+VRSQRTE/VRSQRTEQ:4:result_uint32x2 [] = { 80000000, 80000000,  }
+VRSQRTE/VRSQRTEQ:5:result_uint32x4 [] = { ae800000, ae800000, ae800000, ae800000,  }
+
+VRSQRTE/VRSQRTEQ (3) output:
+VRSQRTE/VRSQRTEQ:6:result_uint32x2 [] = { b4800000, b4800000,  }
+VRSQRTE/VRSQRTEQ:7:result_uint32x4 [] = { ed000000, ed000000, ed000000, ed000000,  }
+
+VRSQRTE/VRSQRTEQ FP special (NaN, 0) output:
+VRSQRTE/VRSQRTEQ:8:result_float32x2 [] = { 7fc00000, 7fc00000,  }
+VRSQRTE/VRSQRTEQ:9:result_float32x4 [] = { 7f800000, 7f800000, 7f800000, 7f800000,  }
+
+VRSQRTE/VRSQRTEQ FP special (negative, infinity) output:
+VRSQRTE/VRSQRTEQ:10:result_float32x2 [] = { 7fc00000, 7fc00000,  }
+VRSQRTE/VRSQRTEQ:11:result_float32x4 [] = { 0, 0, 0, 0,  }
+
+VRSQRTE/VRSQRTEQ FP special (-0, -infinity) output:
+VRSQRTE/VRSQRTEQ:12:result_float32x2 [] = { ff800000, ff800000,  }
+VRSQRTE/VRSQRTEQ:13:result_float32x4 [] = { 7fc00000, 7fc00000, 7fc00000, 7fc00000,  }
+
+VCAGE/VCAGEQ output:
+VCAGE/VCAGEQ:0:result_uint32x2 [] = { ffffffff, 0,  }
+VCAGE/VCAGEQ:1:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, 0,  }
+
+VCAGE/VCAGEQ output:
+VCAGE/VCAGEQ:2:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCAGE/VCAGEQ:3:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+
+VCALE/VCALEQ output:
+VCALE/VCALEQ:0:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCALE/VCALEQ:1:result_uint32x4 [] = { 0, 0, ffffffff, ffffffff,  }
+
+VCALE/VCALEQ output:
+VCALE/VCALEQ:2:result_uint32x2 [] = { 0, 0,  }
+VCALE/VCALEQ:3:result_uint32x4 [] = { 0, 0, 0, 0,  }
+
+VCAGT/VCAGTQ output:
+VCAGT/VCAGTQ:0:result_uint32x2 [] = { 0, 0,  }
+VCAGT/VCAGTQ:1:result_uint32x4 [] = { ffffffff, ffffffff, 0, 0,  }
+
+VCAGT/VCAGTQ output:
+VCAGT/VCAGTQ:2:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCAGT/VCAGTQ:3:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+
+VCALT/VCALTQ output:
+VCALT/VCALTQ:0:result_uint32x2 [] = { 0, ffffffff,  }
+VCALT/VCALTQ:1:result_uint32x4 [] = { 0, 0, 0, ffffffff,  }
+
+VCALT/VCALTQ output:
+VCALT/VCALTQ:2:result_uint32x2 [] = { 0, 0,  }
+VCALT/VCALTQ:3:result_uint32x4 [] = { 0, 0, 0, 0,  }
+
+VCVT/VCVTQ output:
+VCVT/VCVTQ:0:result_float32x2 [] = { c1800000, c1700000,  }
+VCVT/VCVTQ:1:result_float32x2 [] = { 4f800000, 4f800000,  }
+VCVT/VCVTQ:2:result_float32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+VCVT/VCVTQ:3:result_float32x4 [] = { 4f800000, 4f800000, 4f800000, 4f800000,  }
+VCVT/VCVTQ:4:result_int32x2 [] = { fffffff1, 5,  }
+VCVT/VCVTQ:5:result_uint32x2 [] = { 0, 5,  }
+VCVT/VCVTQ:6:result_int32x4 [] = { 0, 0, f, fffffff1,  }
+VCVT/VCVTQ:7:result_uint32x4 [] = { 0, 0, f, 0,  }
+
+VCVT_N/VCVTQ_N output:
+VCVT_N/VCVTQ_N:8:result_float32x2 [] = { c0800000, c0700000,  }
+VCVT_N/VCVTQ_N:9:result_float32x2 [] = { 4c000000, 4c000000,  }
+VCVT_N/VCVTQ_N:10:result_float32x4 [] = { b2800000, b2700000, b2600000, b2500000,  }
+VCVT_N/VCVTQ_N:11:result_float32x4 [] = { 49800000, 49800000, 49800000, 49800000,  }
+VCVT_N/VCVTQ_N:12:result_int32x2 [] = { ff0b3333, 54cccd,  }
+VCVT_N/VCVTQ_N:13:result_uint32x2 [] = { 0, 15,  }
+VCVT_N/VCVTQ_N:14:result_int32x4 [] = { 0, 0, 1e3d7, fffe1c29,  }
+VCVT_N/VCVTQ_N:15:result_uint32x4 [] = { 0, 0, 1e, 0,  }
+
+VCVT/VCVTQ (check rounding) output:
+VCVT/VCVTQ:16:result_int32x2 [] = { a, a,  }
+VCVT/VCVTQ:17:result_uint32x2 [] = { a, a,  }
+VCVT/VCVTQ:18:result_int32x4 [] = { 7d, 7d, 7d, 7d,  }
+VCVT/VCVTQ:19:result_uint32x4 [] = { 7d, 7d, 7d, 7d,  }
+
+VCVT_N/VCVTQ_N (check rounding) output:
+VCVT_N/VCVTQ_N:20:result_int32x2 [] = { a66666, a66666,  }
+VCVT_N/VCVTQ_N:21:result_uint32x2 [] = { a66666, a66666,  }
+VCVT_N/VCVTQ_N:22:result_int32x4 [] = { fbccc, fbccc, fbccc, fbccc,  }
+VCVT_N/VCVTQ_N:23:result_uint32x4 [] = { fbccc, fbccc, fbccc, fbccc,  }
+
+VCVT_N/VCVTQ_N (check saturation) output:
+VCVT_N/VCVTQ_N:24:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VCVT_N/VCVTQ_N:25:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+
+VRECPS/VRECPSQ output:
+VRECPS/VRECPSQ:0:result_float32x2 [] = { c2e19eb7, c2e19eb7,  }
+VRECPS/VRECPSQ:1:result_float32x4 [] = { c1db851f, c1db851f, c1db851f, c1db851f,  }
+
+VRECPS/VRECPSQ FP special (NAN) and normal values output:
+VRECPS/VRECPSQ:2:result_float32x2 [] = { 7fc00000, 7fc00000,  }
+VRECPS/VRECPSQ:3:result_float32x4 [] = { 7fc00000, 7fc00000, 7fc00000, 7fc00000,  }
+
+VRECPS/VRECPSQ FP special (infinity, 0) and normal values output:
+VRECPS/VRECPSQ:4:result_float32x2 [] = { ff800000, ff800000,  }
+VRECPS/VRECPSQ:5:result_float32x4 [] = { 40000000, 40000000, 40000000, 40000000,  }
+
+VRECPS/VRECPSQ FP special (infinity, 0) output:
+VRECPS/VRECPSQ:6:result_float32x2 [] = { 40000000, 40000000,  }
+VRECPS/VRECPSQ:7:result_float32x4 [] = { 40000000, 40000000, 40000000, 40000000,  }
+
+VRSQRTS/VRSQRTSQ output:
+VRSQRTS/VRSQRTSQ:0:result_float32x2 [] = { c2796b84, c2796b84,  }
+VRSQRTS/VRSQRTSQ:1:result_float32x4 [] = { c0e4a3d8, c0e4a3d8, c0e4a3d8, c0e4a3d8,  }
+
+VRSQRTS/VRSQRTSQ FP special (NAN) and normal values output:
+VRSQRTS/VRSQRTSQ:2:result_float32x2 [] = { 7fc00000, 7fc00000,  }
+VRSQRTS/VRSQRTSQ:3:result_float32x4 [] = { 7fc00000, 7fc00000, 7fc00000, 7fc00000,  }
+
+VRSQRTS/VRSQRTSQ FP special (infinity, 0) and normal values output:
+VRSQRTS/VRSQRTSQ:4:result_float32x2 [] = { ff800000, ff800000,  }
+VRSQRTS/VRSQRTSQ:5:result_float32x4 [] = { 3fc00000, 3fc00000, 3fc00000, 3fc00000,  }
+
+VRSQRTS/VRSQRTSQ FP special (infinity, 0) output:
+VRSQRTS/VRSQRTSQ:6:result_float32x2 [] = { 3fc00000, 3fc00000,  }
+VRSQRTS/VRSQRTSQ:7:result_float32x4 [] = { 3fc00000, 3fc00000, 3fc00000, 3fc00000,  }
diff --git a/ref-rvct-neon.txt b/ref-rvct-neon.txt
new file mode 100644
index 0000000..0dac13f
--- /dev/null
+++ b/ref-rvct-neon.txt
@@ -0,0 +1,7900 @@
+
+VLD1/VLD1Q output:
+VLD1/VLD1Q:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD1/VLD1Q:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD1/VLD1Q:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD1/VLD1Q:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD1/VLD1Q:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VLD1/VLD1Q:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD1/VLD1Q:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD1/VLD1Q:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD1/VLD1Q:8:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VLD1/VLD1Q:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD1/VLD1Q:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD1/VLD1Q:11:result_float16x4 [] = { cc00, cb80, cb00, ca80,  }
+VLD1/VLD1Q:12:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD1/VLD1Q:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD1/VLD1Q:14:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD1/VLD1Q:15:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VLD1/VLD1Q:16:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD1/VLD1Q:17:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VLD1/VLD1Q:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD1/VLD1Q:19:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VLD1/VLD1Q:20:result_poly8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD1/VLD1Q:21:result_poly16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VLD1/VLD1Q:22:result_float32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+VLD1/VLD1Q:23:result_float16x8 [] = { cc00, cb80, cb00, ca80, ca00, c980, c900, c880,  }
+
+VADD/VADDQ output:
+VADD/VADDQ:0:result_int8x8 [] = { fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9,  }
+VADD/VADDQ:1:result_int16x4 [] = { ffffffec, ffffffed, ffffffee, ffffffef,  }
+VADD/VADDQ:2:result_int32x2 [] = { fffffff3, fffffff4,  }
+VADD/VADDQ:3:result_int64x1 [] = { 54,  }
+VADD/VADDQ:4:result_uint8x8 [] = { 4, 5, 6, 7, 8, 9, a, b,  }
+VADD/VADDQ:5:result_uint16x4 [] = { e, f, 10, 11,  }
+VADD/VADDQ:6:result_uint32x2 [] = { 18, 19,  }
+VADD/VADDQ:7:result_uint64x1 [] = { fffffffffffffff2,  }
+VADD/VADDQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADD/VADDQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VADD/VADDQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VADD/VADDQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VADD/VADDQ:12:result_int8x16 [] = { ffffffe6, ffffffe7, ffffffe8, ffffffe9, ffffffea, ffffffeb, ffffffec, ffffffed, ffffffee, ffffffef, fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5,  }
+VADD/VADDQ:13:result_int16x8 [] = { ffffffdc, ffffffdd, ffffffde, ffffffdf, ffffffe0, ffffffe1, ffffffe2, ffffffe3,  }
+VADD/VADDQ:14:result_int32x4 [] = { ffffffd2, ffffffd3, ffffffd4, ffffffd5,  }
+VADD/VADDQ:15:result_int64x2 [] = { 8, 9,  }
+VADD/VADDQ:16:result_uint8x16 [] = { fc, fd, fe, ff, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b,  }
+VADD/VADDQ:17:result_uint16x8 [] = { fff3, fff4, fff5, fff6, fff7, fff8, fff9, fffa,  }
+VADD/VADDQ:18:result_uint32x4 [] = { 27, 28, 29, 2a,  }
+VADD/VADDQ:19:result_uint64x2 [] = { fffffffffffffff3, fffffffffffffff4,  }
+VADD/VADDQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADD/VADDQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VADD/VADDQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VADD/VADDQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+float32:
+VADD/VADDQ:24:result_float32x2 [] = { 40d9999a, 40d9999a,  }
+VADD/VADDQ:25:result_float32x4 [] = { 41100000, 41100000, 41100000, 41100000,  }
+
+VLD1_LANE/VLD1_LANEQ output:
+VLD1_LANE/VLD1_LANEQ:0:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, fffffff0, ffffffaa,  }
+VLD1_LANE/VLD1_LANEQ:1:result_int16x4 [] = { ffffaaaa, ffffaaaa, ffffaaaa, fffffff0,  }
+VLD1_LANE/VLD1_LANEQ:2:result_int32x2 [] = { aaaaaaaa, fffffff0,  }
+VLD1_LANE/VLD1_LANEQ:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD1_LANE/VLD1_LANEQ:4:result_uint8x8 [] = { aa, aa, aa, aa, aa, aa, aa, f0,  }
+VLD1_LANE/VLD1_LANEQ:5:result_uint16x4 [] = { aaaa, aaaa, aaaa, fff0,  }
+VLD1_LANE/VLD1_LANEQ:6:result_uint32x2 [] = { aaaaaaaa, fffffff0,  }
+VLD1_LANE/VLD1_LANEQ:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD1_LANE/VLD1_LANEQ:8:result_poly8x8 [] = { aa, aa, aa, aa, aa, aa, aa, f0,  }
+VLD1_LANE/VLD1_LANEQ:9:result_poly16x4 [] = { aaaa, aaaa, aaaa, fff0,  }
+VLD1_LANE/VLD1_LANEQ:10:result_float32x2 [] = { aaaaaaaa, c1800000,  }
+VLD1_LANE/VLD1_LANEQ:11:result_float16x4 [] = { aaaa, aaaa, cc00, aaaa,  }
+VLD1_LANE/VLD1_LANEQ:12:result_int8x16 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, fffffff0,  }
+VLD1_LANE/VLD1_LANEQ:13:result_int16x8 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, fffffff0, ffffaaaa, ffffaaaa,  }
+VLD1_LANE/VLD1_LANEQ:14:result_int32x4 [] = { aaaaaaaa, aaaaaaaa, fffffff0, aaaaaaaa,  }
+VLD1_LANE/VLD1_LANEQ:15:result_int64x2 [] = { aaaaaaaaaaaaaaaa, fffffffffffffff0,  }
+VLD1_LANE/VLD1_LANEQ:16:result_uint8x16 [] = { aa, aa, aa, aa, aa, aa, aa, aa, aa, aa, aa, aa, f0, aa, aa, aa,  }
+VLD1_LANE/VLD1_LANEQ:17:result_uint16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, fff0, aaaa,  }
+VLD1_LANE/VLD1_LANEQ:18:result_uint32x4 [] = { aaaaaaaa, aaaaaaaa, fffffff0, aaaaaaaa,  }
+VLD1_LANE/VLD1_LANEQ:19:result_uint64x2 [] = { fffffffffffffff0, aaaaaaaaaaaaaaaa,  }
+VLD1_LANE/VLD1_LANEQ:20:result_poly8x16 [] = { aa, aa, aa, aa, aa, aa, aa, aa, aa, aa, aa, aa, f0, aa, aa, aa,  }
+VLD1_LANE/VLD1_LANEQ:21:result_poly16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, fff0, aaaa,  }
+VLD1_LANE/VLD1_LANEQ:22:result_float32x4 [] = { aaaaaaaa, aaaaaaaa, c1800000, aaaaaaaa,  }
+VLD1_LANE/VLD1_LANEQ:23:result_float16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, cc00, aaaa, aaaa,  }
+
+VLD1_DUP/VLD1_DUPQ output:
+VLD1_DUP/VLD1_DUPQ:0:result_int8x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VLD1_DUP/VLD1_DUPQ:1:result_int16x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VLD1_DUP/VLD1_DUPQ:2:result_int32x2 [] = { fffffff0, fffffff0,  }
+VLD1_DUP/VLD1_DUPQ:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD1_DUP/VLD1_DUPQ:4:result_uint8x8 [] = { f0, f0, f0, f0, f0, f0, f0, f0,  }
+VLD1_DUP/VLD1_DUPQ:5:result_uint16x4 [] = { fff0, fff0, fff0, fff0,  }
+VLD1_DUP/VLD1_DUPQ:6:result_uint32x2 [] = { fffffff0, fffffff0,  }
+VLD1_DUP/VLD1_DUPQ:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD1_DUP/VLD1_DUPQ:8:result_poly8x8 [] = { f0, f0, f0, f0, f0, f0, f0, f0,  }
+VLD1_DUP/VLD1_DUPQ:9:result_poly16x4 [] = { fff0, fff0, fff0, fff0,  }
+VLD1_DUP/VLD1_DUPQ:10:result_float32x2 [] = { c1800000, c1800000,  }
+VLD1_DUP/VLD1_DUPQ:11:result_float16x4 [] = { cc00, cc00, cc00, cc00,  }
+VLD1_DUP/VLD1_DUPQ:12:result_int8x16 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VLD1_DUP/VLD1_DUPQ:13:result_int16x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VLD1_DUP/VLD1_DUPQ:14:result_int32x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VLD1_DUP/VLD1_DUPQ:15:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VLD1_DUP/VLD1_DUPQ:16:result_uint8x16 [] = { f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0,  }
+VLD1_DUP/VLD1_DUPQ:17:result_uint16x8 [] = { fff0, fff0, fff0, fff0, fff0, fff0, fff0, fff0,  }
+VLD1_DUP/VLD1_DUPQ:18:result_uint32x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VLD1_DUP/VLD1_DUPQ:19:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VLD1_DUP/VLD1_DUPQ:20:result_poly8x16 [] = { f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0,  }
+VLD1_DUP/VLD1_DUPQ:21:result_poly16x8 [] = { fff0, fff0, fff0, fff0, fff0, fff0, fff0, fff0,  }
+VLD1_DUP/VLD1_DUPQ:22:result_float32x4 [] = { c1800000, c1800000, c1800000, c1800000,  }
+VLD1_DUP/VLD1_DUPQ:23:result_float16x8 [] = { cc00, cc00, cc00, cc00, cc00, cc00, cc00, cc00,  }
+
+VLD1_DUP/VLD1_DUPQ output:
+VLD1_DUP/VLD1_DUPQ:0:result_int8x8 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VLD1_DUP/VLD1_DUPQ:1:result_int16x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VLD1_DUP/VLD1_DUPQ:2:result_int32x2 [] = { fffffff1, fffffff1,  }
+VLD1_DUP/VLD1_DUPQ:3:result_int64x1 [] = { fffffffffffffff1,  }
+VLD1_DUP/VLD1_DUPQ:4:result_uint8x8 [] = { f1, f1, f1, f1, f1, f1, f1, f1,  }
+VLD1_DUP/VLD1_DUPQ:5:result_uint16x4 [] = { fff1, fff1, fff1, fff1,  }
+VLD1_DUP/VLD1_DUPQ:6:result_uint32x2 [] = { fffffff1, fffffff1,  }
+VLD1_DUP/VLD1_DUPQ:7:result_uint64x1 [] = { fffffffffffffff1,  }
+VLD1_DUP/VLD1_DUPQ:8:result_poly8x8 [] = { f1, f1, f1, f1, f1, f1, f1, f1,  }
+VLD1_DUP/VLD1_DUPQ:9:result_poly16x4 [] = { fff1, fff1, fff1, fff1,  }
+VLD1_DUP/VLD1_DUPQ:10:result_float32x2 [] = { c1700000, c1700000,  }
+VLD1_DUP/VLD1_DUPQ:11:result_float16x4 [] = { cb80, cb80, cb80, cb80,  }
+VLD1_DUP/VLD1_DUPQ:12:result_int8x16 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VLD1_DUP/VLD1_DUPQ:13:result_int16x8 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VLD1_DUP/VLD1_DUPQ:14:result_int32x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VLD1_DUP/VLD1_DUPQ:15:result_int64x2 [] = { fffffffffffffff1, fffffffffffffff1,  }
+VLD1_DUP/VLD1_DUPQ:16:result_uint8x16 [] = { f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1,  }
+VLD1_DUP/VLD1_DUPQ:17:result_uint16x8 [] = { fff1, fff1, fff1, fff1, fff1, fff1, fff1, fff1,  }
+VLD1_DUP/VLD1_DUPQ:18:result_uint32x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VLD1_DUP/VLD1_DUPQ:19:result_uint64x2 [] = { fffffffffffffff1, fffffffffffffff1,  }
+VLD1_DUP/VLD1_DUPQ:20:result_poly8x16 [] = { f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1,  }
+VLD1_DUP/VLD1_DUPQ:21:result_poly16x8 [] = { fff1, fff1, fff1, fff1, fff1, fff1, fff1, fff1,  }
+VLD1_DUP/VLD1_DUPQ:22:result_float32x4 [] = { c1700000, c1700000, c1700000, c1700000,  }
+VLD1_DUP/VLD1_DUPQ:23:result_float16x8 [] = { cb80, cb80, cb80, cb80, cb80, cb80, cb80, cb80,  }
+
+VLD1_DUP/VLD1_DUPQ output:
+VLD1_DUP/VLD1_DUPQ:0:result_int8x8 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VLD1_DUP/VLD1_DUPQ:1:result_int16x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VLD1_DUP/VLD1_DUPQ:2:result_int32x2 [] = { fffffff2, fffffff2,  }
+VLD1_DUP/VLD1_DUPQ:3:result_int64x1 [] = { fffffffffffffff2,  }
+VLD1_DUP/VLD1_DUPQ:4:result_uint8x8 [] = { f2, f2, f2, f2, f2, f2, f2, f2,  }
+VLD1_DUP/VLD1_DUPQ:5:result_uint16x4 [] = { fff2, fff2, fff2, fff2,  }
+VLD1_DUP/VLD1_DUPQ:6:result_uint32x2 [] = { fffffff2, fffffff2,  }
+VLD1_DUP/VLD1_DUPQ:7:result_uint64x1 [] = { fffffffffffffff2,  }
+VLD1_DUP/VLD1_DUPQ:8:result_poly8x8 [] = { f2, f2, f2, f2, f2, f2, f2, f2,  }
+VLD1_DUP/VLD1_DUPQ:9:result_poly16x4 [] = { fff2, fff2, fff2, fff2,  }
+VLD1_DUP/VLD1_DUPQ:10:result_float32x2 [] = { c1600000, c1600000,  }
+VLD1_DUP/VLD1_DUPQ:11:result_float16x4 [] = { cb00, cb00, cb00, cb00,  }
+VLD1_DUP/VLD1_DUPQ:12:result_int8x16 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VLD1_DUP/VLD1_DUPQ:13:result_int16x8 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VLD1_DUP/VLD1_DUPQ:14:result_int32x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VLD1_DUP/VLD1_DUPQ:15:result_int64x2 [] = { fffffffffffffff2, fffffffffffffff2,  }
+VLD1_DUP/VLD1_DUPQ:16:result_uint8x16 [] = { f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2,  }
+VLD1_DUP/VLD1_DUPQ:17:result_uint16x8 [] = { fff2, fff2, fff2, fff2, fff2, fff2, fff2, fff2,  }
+VLD1_DUP/VLD1_DUPQ:18:result_uint32x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VLD1_DUP/VLD1_DUPQ:19:result_uint64x2 [] = { fffffffffffffff2, fffffffffffffff2,  }
+VLD1_DUP/VLD1_DUPQ:20:result_poly8x16 [] = { f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2,  }
+VLD1_DUP/VLD1_DUPQ:21:result_poly16x8 [] = { fff2, fff2, fff2, fff2, fff2, fff2, fff2, fff2,  }
+VLD1_DUP/VLD1_DUPQ:22:result_float32x4 [] = { c1600000, c1600000, c1600000, c1600000,  }
+VLD1_DUP/VLD1_DUPQ:23:result_float16x8 [] = { cb00, cb00, cb00, cb00, cb00, cb00, cb00, cb00,  }
+
+VDUP/VDUPQ output:
+VDUP/VDUPQ:0:result_int8x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VDUP/VDUPQ:1:result_int16x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VDUP/VDUPQ:2:result_int32x2 [] = { fffffff0, fffffff0,  }
+VDUP/VDUPQ:3:result_int64x1 [] = { fffffffffffffff0,  }
+VDUP/VDUPQ:4:result_uint8x8 [] = { f0, f0, f0, f0, f0, f0, f0, f0,  }
+VDUP/VDUPQ:5:result_uint16x4 [] = { fff0, fff0, fff0, fff0,  }
+VDUP/VDUPQ:6:result_uint32x2 [] = { fffffff0, fffffff0,  }
+VDUP/VDUPQ:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VDUP/VDUPQ:8:result_poly8x8 [] = { f0, f0, f0, f0, f0, f0, f0, f0,  }
+VDUP/VDUPQ:9:result_poly16x4 [] = { fff0, fff0, fff0, fff0,  }
+VDUP/VDUPQ:10:result_float32x2 [] = { c1800000, c1800000,  }
+VDUP/VDUPQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VDUP/VDUPQ:12:result_int8x16 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VDUP/VDUPQ:13:result_int16x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VDUP/VDUPQ:14:result_int32x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VDUP/VDUPQ:15:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VDUP/VDUPQ:16:result_uint8x16 [] = { f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0,  }
+VDUP/VDUPQ:17:result_uint16x8 [] = { fff0, fff0, fff0, fff0, fff0, fff0, fff0, fff0,  }
+VDUP/VDUPQ:18:result_uint32x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VDUP/VDUPQ:19:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VDUP/VDUPQ:20:result_poly8x16 [] = { f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0,  }
+VDUP/VDUPQ:21:result_poly16x8 [] = { fff0, fff0, fff0, fff0, fff0, fff0, fff0, fff0,  }
+VDUP/VDUPQ:22:result_float32x4 [] = { c1800000, c1800000, c1800000, c1800000,  }
+VDUP/VDUPQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VDUP/VDUPQ output:
+VDUP/VDUPQ:0:result_int8x8 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VDUP/VDUPQ:1:result_int16x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VDUP/VDUPQ:2:result_int32x2 [] = { fffffff1, fffffff1,  }
+VDUP/VDUPQ:3:result_int64x1 [] = { fffffffffffffff1,  }
+VDUP/VDUPQ:4:result_uint8x8 [] = { f1, f1, f1, f1, f1, f1, f1, f1,  }
+VDUP/VDUPQ:5:result_uint16x4 [] = { fff1, fff1, fff1, fff1,  }
+VDUP/VDUPQ:6:result_uint32x2 [] = { fffffff1, fffffff1,  }
+VDUP/VDUPQ:7:result_uint64x1 [] = { fffffffffffffff1,  }
+VDUP/VDUPQ:8:result_poly8x8 [] = { f1, f1, f1, f1, f1, f1, f1, f1,  }
+VDUP/VDUPQ:9:result_poly16x4 [] = { fff1, fff1, fff1, fff1,  }
+VDUP/VDUPQ:10:result_float32x2 [] = { c1700000, c1700000,  }
+VDUP/VDUPQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VDUP/VDUPQ:12:result_int8x16 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VDUP/VDUPQ:13:result_int16x8 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VDUP/VDUPQ:14:result_int32x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VDUP/VDUPQ:15:result_int64x2 [] = { fffffffffffffff1, fffffffffffffff1,  }
+VDUP/VDUPQ:16:result_uint8x16 [] = { f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1,  }
+VDUP/VDUPQ:17:result_uint16x8 [] = { fff1, fff1, fff1, fff1, fff1, fff1, fff1, fff1,  }
+VDUP/VDUPQ:18:result_uint32x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VDUP/VDUPQ:19:result_uint64x2 [] = { fffffffffffffff1, fffffffffffffff1,  }
+VDUP/VDUPQ:20:result_poly8x16 [] = { f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1,  }
+VDUP/VDUPQ:21:result_poly16x8 [] = { fff1, fff1, fff1, fff1, fff1, fff1, fff1, fff1,  }
+VDUP/VDUPQ:22:result_float32x4 [] = { c1700000, c1700000, c1700000, c1700000,  }
+VDUP/VDUPQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VDUP/VDUPQ output:
+VDUP/VDUPQ:0:result_int8x8 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VDUP/VDUPQ:1:result_int16x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VDUP/VDUPQ:2:result_int32x2 [] = { fffffff2, fffffff2,  }
+VDUP/VDUPQ:3:result_int64x1 [] = { fffffffffffffff2,  }
+VDUP/VDUPQ:4:result_uint8x8 [] = { f2, f2, f2, f2, f2, f2, f2, f2,  }
+VDUP/VDUPQ:5:result_uint16x4 [] = { fff2, fff2, fff2, fff2,  }
+VDUP/VDUPQ:6:result_uint32x2 [] = { fffffff2, fffffff2,  }
+VDUP/VDUPQ:7:result_uint64x1 [] = { fffffffffffffff2,  }
+VDUP/VDUPQ:8:result_poly8x8 [] = { f2, f2, f2, f2, f2, f2, f2, f2,  }
+VDUP/VDUPQ:9:result_poly16x4 [] = { fff2, fff2, fff2, fff2,  }
+VDUP/VDUPQ:10:result_float32x2 [] = { c1600000, c1600000,  }
+VDUP/VDUPQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VDUP/VDUPQ:12:result_int8x16 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VDUP/VDUPQ:13:result_int16x8 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VDUP/VDUPQ:14:result_int32x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VDUP/VDUPQ:15:result_int64x2 [] = { fffffffffffffff2, fffffffffffffff2,  }
+VDUP/VDUPQ:16:result_uint8x16 [] = { f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2,  }
+VDUP/VDUPQ:17:result_uint16x8 [] = { fff2, fff2, fff2, fff2, fff2, fff2, fff2, fff2,  }
+VDUP/VDUPQ:18:result_uint32x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VDUP/VDUPQ:19:result_uint64x2 [] = { fffffffffffffff2, fffffffffffffff2,  }
+VDUP/VDUPQ:20:result_poly8x16 [] = { f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2,  }
+VDUP/VDUPQ:21:result_poly16x8 [] = { fff2, fff2, fff2, fff2, fff2, fff2, fff2, fff2,  }
+VDUP/VDUPQ:22:result_float32x4 [] = { c1600000, c1600000, c1600000, c1600000,  }
+VDUP/VDUPQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMOV/VMOVQ output:
+VMOV/VMOVQ:0:result_int8x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VMOV/VMOVQ:1:result_int16x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VMOV/VMOVQ:2:result_int32x2 [] = { fffffff0, fffffff0,  }
+VMOV/VMOVQ:3:result_int64x1 [] = { fffffffffffffff0,  }
+VMOV/VMOVQ:4:result_uint8x8 [] = { f0, f0, f0, f0, f0, f0, f0, f0,  }
+VMOV/VMOVQ:5:result_uint16x4 [] = { fff0, fff0, fff0, fff0,  }
+VMOV/VMOVQ:6:result_uint32x2 [] = { fffffff0, fffffff0,  }
+VMOV/VMOVQ:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VMOV/VMOVQ:8:result_poly8x8 [] = { f0, f0, f0, f0, f0, f0, f0, f0,  }
+VMOV/VMOVQ:9:result_poly16x4 [] = { fff0, fff0, fff0, fff0,  }
+VMOV/VMOVQ:10:result_float32x2 [] = { c1800000, c1800000,  }
+VMOV/VMOVQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMOV/VMOVQ:12:result_int8x16 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VMOV/VMOVQ:13:result_int16x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VMOV/VMOVQ:14:result_int32x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VMOV/VMOVQ:15:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VMOV/VMOVQ:16:result_uint8x16 [] = { f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0,  }
+VMOV/VMOVQ:17:result_uint16x8 [] = { fff0, fff0, fff0, fff0, fff0, fff0, fff0, fff0,  }
+VMOV/VMOVQ:18:result_uint32x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VMOV/VMOVQ:19:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VMOV/VMOVQ:20:result_poly8x16 [] = { f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0, f0,  }
+VMOV/VMOVQ:21:result_poly16x8 [] = { fff0, fff0, fff0, fff0, fff0, fff0, fff0, fff0,  }
+VMOV/VMOVQ:22:result_float32x4 [] = { c1800000, c1800000, c1800000, c1800000,  }
+VMOV/VMOVQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMOV/VMOVQ output:
+VMOV/VMOVQ:0:result_int8x8 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VMOV/VMOVQ:1:result_int16x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VMOV/VMOVQ:2:result_int32x2 [] = { fffffff1, fffffff1,  }
+VMOV/VMOVQ:3:result_int64x1 [] = { fffffffffffffff1,  }
+VMOV/VMOVQ:4:result_uint8x8 [] = { f1, f1, f1, f1, f1, f1, f1, f1,  }
+VMOV/VMOVQ:5:result_uint16x4 [] = { fff1, fff1, fff1, fff1,  }
+VMOV/VMOVQ:6:result_uint32x2 [] = { fffffff1, fffffff1,  }
+VMOV/VMOVQ:7:result_uint64x1 [] = { fffffffffffffff1,  }
+VMOV/VMOVQ:8:result_poly8x8 [] = { f1, f1, f1, f1, f1, f1, f1, f1,  }
+VMOV/VMOVQ:9:result_poly16x4 [] = { fff1, fff1, fff1, fff1,  }
+VMOV/VMOVQ:10:result_float32x2 [] = { c1700000, c1700000,  }
+VMOV/VMOVQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMOV/VMOVQ:12:result_int8x16 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VMOV/VMOVQ:13:result_int16x8 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VMOV/VMOVQ:14:result_int32x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VMOV/VMOVQ:15:result_int64x2 [] = { fffffffffffffff1, fffffffffffffff1,  }
+VMOV/VMOVQ:16:result_uint8x16 [] = { f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1,  }
+VMOV/VMOVQ:17:result_uint16x8 [] = { fff1, fff1, fff1, fff1, fff1, fff1, fff1, fff1,  }
+VMOV/VMOVQ:18:result_uint32x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VMOV/VMOVQ:19:result_uint64x2 [] = { fffffffffffffff1, fffffffffffffff1,  }
+VMOV/VMOVQ:20:result_poly8x16 [] = { f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1, f1,  }
+VMOV/VMOVQ:21:result_poly16x8 [] = { fff1, fff1, fff1, fff1, fff1, fff1, fff1, fff1,  }
+VMOV/VMOVQ:22:result_float32x4 [] = { c1700000, c1700000, c1700000, c1700000,  }
+VMOV/VMOVQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMOV/VMOVQ output:
+VMOV/VMOVQ:0:result_int8x8 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VMOV/VMOVQ:1:result_int16x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VMOV/VMOVQ:2:result_int32x2 [] = { fffffff2, fffffff2,  }
+VMOV/VMOVQ:3:result_int64x1 [] = { fffffffffffffff2,  }
+VMOV/VMOVQ:4:result_uint8x8 [] = { f2, f2, f2, f2, f2, f2, f2, f2,  }
+VMOV/VMOVQ:5:result_uint16x4 [] = { fff2, fff2, fff2, fff2,  }
+VMOV/VMOVQ:6:result_uint32x2 [] = { fffffff2, fffffff2,  }
+VMOV/VMOVQ:7:result_uint64x1 [] = { fffffffffffffff2,  }
+VMOV/VMOVQ:8:result_poly8x8 [] = { f2, f2, f2, f2, f2, f2, f2, f2,  }
+VMOV/VMOVQ:9:result_poly16x4 [] = { fff2, fff2, fff2, fff2,  }
+VMOV/VMOVQ:10:result_float32x2 [] = { c1600000, c1600000,  }
+VMOV/VMOVQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMOV/VMOVQ:12:result_int8x16 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VMOV/VMOVQ:13:result_int16x8 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VMOV/VMOVQ:14:result_int32x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VMOV/VMOVQ:15:result_int64x2 [] = { fffffffffffffff2, fffffffffffffff2,  }
+VMOV/VMOVQ:16:result_uint8x16 [] = { f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2,  }
+VMOV/VMOVQ:17:result_uint16x8 [] = { fff2, fff2, fff2, fff2, fff2, fff2, fff2, fff2,  }
+VMOV/VMOVQ:18:result_uint32x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VMOV/VMOVQ:19:result_uint64x2 [] = { fffffffffffffff2, fffffffffffffff2,  }
+VMOV/VMOVQ:20:result_poly8x16 [] = { f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2, f2,  }
+VMOV/VMOVQ:21:result_poly16x8 [] = { fff2, fff2, fff2, fff2, fff2, fff2, fff2, fff2,  }
+VMOV/VMOVQ:22:result_float32x4 [] = { c1600000, c1600000, c1600000, c1600000,  }
+VMOV/VMOVQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VGET_HIGH output:
+VGET_HIGH:0:result_int8x8 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VGET_HIGH:1:result_int16x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VGET_HIGH:2:result_int32x2 [] = { fffffff2, fffffff3,  }
+VGET_HIGH:3:result_int64x1 [] = { fffffffffffffff1,  }
+VGET_HIGH:4:result_uint8x8 [] = { f8, f9, fa, fb, fc, fd, fe, ff,  }
+VGET_HIGH:5:result_uint16x4 [] = { fff4, fff5, fff6, fff7,  }
+VGET_HIGH:6:result_uint32x2 [] = { fffffff2, fffffff3,  }
+VGET_HIGH:7:result_uint64x1 [] = { fffffffffffffff1,  }
+VGET_HIGH:8:result_poly8x8 [] = { f8, f9, fa, fb, fc, fd, fe, ff,  }
+VGET_HIGH:9:result_poly16x4 [] = { fff4, fff5, fff6, fff7,  }
+VGET_HIGH:10:result_float32x2 [] = { c1600000, c1500000,  }
+VGET_HIGH:11:result_float16x4 [] = { ca00, c980, c900, c880,  }
+VGET_HIGH:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VGET_HIGH:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VGET_HIGH:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VGET_HIGH:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VGET_HIGH:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VGET_HIGH:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VGET_HIGH:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VGET_HIGH:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VGET_HIGH:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VGET_HIGH:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VGET_HIGH:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VGET_HIGH:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VGET_LOW output:
+VGET_LOW:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VGET_LOW:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VGET_LOW:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VGET_LOW:3:result_int64x1 [] = { fffffffffffffff0,  }
+VGET_LOW:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VGET_LOW:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VGET_LOW:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VGET_LOW:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VGET_LOW:8:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VGET_LOW:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VGET_LOW:10:result_float32x2 [] = { c1800000, c1700000,  }
+VGET_LOW:11:result_float16x4 [] = { cc00, cb80, cb00, ca80,  }
+VGET_LOW:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VGET_LOW:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VGET_LOW:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VGET_LOW:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VGET_LOW:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VGET_LOW:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VGET_LOW:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VGET_LOW:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VGET_LOW:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VGET_LOW:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VGET_LOW:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VGET_LOW:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLAL_LANE cumulative saturation output:
+VQDMLAL_LANE:0:vqdmlal_lane_s16 Neon cumulative saturation 0
+VQDMLAL_LANE:1:vqdmlal_lane_s32 Neon cumulative saturation 0
+
+VQDMLAL_LANE output:
+VQDMLAL_LANE:2:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:3:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:4:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:5:result_int64x1 [] = { 3333333333333333,  }
+VQDMLAL_LANE:6:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:7:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:8:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:9:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLAL_LANE:10:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:11:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:12:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:13:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLAL_LANE:14:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:15:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:16:result_int32x4 [] = { 7c1e, 7c1f, 7c20, 7c21,  }
+VQDMLAL_LANE:17:result_int64x2 [] = { 7c1e, 7c1f,  }
+VQDMLAL_LANE:18:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:19:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:20:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_LANE:21:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLAL_LANE:22:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:23:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:24:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_LANE:25:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLAL_LANE (mul with input=0) cumulative saturation output:
+VQDMLAL_LANE:26:vqdmlal_lane_s16 Neon cumulative saturation 0
+VQDMLAL_LANE:27:vqdmlal_lane_s32 Neon cumulative saturation 0
+
+VQDMLAL_LANE (mul with input=0) output:
+VQDMLAL_LANE:28:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:29:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:30:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:31:result_int64x1 [] = { 3333333333333333,  }
+VQDMLAL_LANE:32:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:33:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:34:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:35:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLAL_LANE:36:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:37:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:38:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:39:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLAL_LANE:40:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:41:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:42:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VQDMLAL_LANE:43:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VQDMLAL_LANE:44:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:45:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:46:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_LANE:47:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLAL_LANE:48:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:49:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:50:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_LANE:51:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLAL_LANE (check mul cumulative saturation) cumulative saturation output:
+VQDMLAL_LANE:52:vqdmlal_lane_s16 Neon cumulative saturation 1
+VQDMLAL_LANE:53:vqdmlal_lane_s32 Neon cumulative saturation 1
+
+VQDMLAL_LANE (check mul cumulative saturation) output:
+VQDMLAL_LANE:54:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:55:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:56:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:57:result_int64x1 [] = { 3333333333333333,  }
+VQDMLAL_LANE:58:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:59:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:60:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:61:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLAL_LANE:62:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:63:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:64:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_LANE:65:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLAL_LANE:66:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:67:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:68:result_int32x4 [] = { 7fffffef, 7ffffff0, 7ffffff1, 7ffffff2,  }
+VQDMLAL_LANE:69:result_int64x2 [] = { 7fffffffffffffef, 7ffffffffffffff0,  }
+VQDMLAL_LANE:70:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:71:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:72:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_LANE:73:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLAL_LANE:74:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_LANE:75:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_LANE:76:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_LANE:77:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLSL_LANE cumulative saturation output:
+VQDMLSL_LANE:0:vqdmlsl_lane_s16 Neon cumulative saturation 0
+VQDMLSL_LANE:1:vqdmlsl_lane_s32 Neon cumulative saturation 0
+
+VQDMLSL_LANE output:
+VQDMLSL_LANE:2:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:3:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:4:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:5:result_int64x1 [] = { 3333333333333333,  }
+VQDMLSL_LANE:6:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:7:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:8:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:9:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLSL_LANE:10:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:11:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:12:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:13:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLSL_LANE:14:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:15:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:16:result_int32x4 [] = { ffff83c2, ffff83c3, ffff83c4, ffff83c5,  }
+VQDMLSL_LANE:17:result_int64x2 [] = { ffffffffffff83c2, ffffffffffff83c3,  }
+VQDMLSL_LANE:18:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:19:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:20:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_LANE:21:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLSL_LANE:22:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:23:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:24:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_LANE:25:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLSL_LANE (mul with input=0) cumulative saturation output:
+VQDMLSL_LANE:26:vqdmlsl_lane_s16 Neon cumulative saturation 0
+VQDMLSL_LANE:27:vqdmlsl_lane_s32 Neon cumulative saturation 0
+
+VQDMLSL_LANE (mul with input=0) output:
+VQDMLSL_LANE:28:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:29:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:30:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:31:result_int64x1 [] = { 3333333333333333,  }
+VQDMLSL_LANE:32:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:33:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:34:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:35:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLSL_LANE:36:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:37:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:38:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:39:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLSL_LANE:40:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:41:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:42:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VQDMLSL_LANE:43:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VQDMLSL_LANE:44:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:45:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:46:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_LANE:47:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLSL_LANE:48:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:49:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:50:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_LANE:51:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLSL_LANE (check mul cumulative saturation) cumulative saturation output:
+VQDMLSL_LANE:52:vqdmlsl_lane_s16 Neon cumulative saturation 1
+VQDMLSL_LANE:53:vqdmlsl_lane_s32 Neon cumulative saturation 1
+
+VQDMLSL_LANE (check mul cumulative saturation) output:
+VQDMLSL_LANE:54:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:55:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:56:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:57:result_int64x1 [] = { 3333333333333333,  }
+VQDMLSL_LANE:58:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:59:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:60:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:61:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLSL_LANE:62:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:63:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:64:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_LANE:65:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLSL_LANE:66:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:67:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:68:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VQDMLSL_LANE:69:result_int64x2 [] = { 8000000000000000, 8000000000000000,  }
+VQDMLSL_LANE:70:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:71:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:72:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_LANE:73:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLSL_LANE:74:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_LANE:75:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_LANE:76:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_LANE:77:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLAL_N cumulative saturation output:
+VQDMLAL_N:0:vqdmlal_n_s16 Neon cumulative saturation 0
+VQDMLAL_N:1:vqdmlal_n_s32 Neon cumulative saturation 0
+
+VQDMLAL_N output:
+VQDMLAL_N:2:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:3:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:4:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_N:5:result_int64x1 [] = { 3333333333333333,  }
+VQDMLAL_N:6:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:7:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:8:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_N:9:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLAL_N:10:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:11:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:12:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_N:13:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLAL_N:14:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:15:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:16:result_int32x4 [] = { 1684, 1685, 1686, 1687,  }
+VQDMLAL_N:17:result_int64x2 [] = { 21ce, 21cf,  }
+VQDMLAL_N:18:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:19:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:20:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_N:21:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLAL_N:22:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:23:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:24:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_N:25:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLAL_N (check mul cumulative saturation) cumulative saturation output:
+VQDMLAL_N:26:vqdmlal_n_s16 Neon cumulative saturation 1
+VQDMLAL_N:27:vqdmlal_n_s32 Neon cumulative saturation 1
+
+VQDMLAL_N (check mul cumulative saturation) output:
+VQDMLAL_N:28:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:29:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:30:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_N:31:result_int64x1 [] = { 3333333333333333,  }
+VQDMLAL_N:32:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:33:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:34:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_N:35:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLAL_N:36:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:37:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:38:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLAL_N:39:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLAL_N:40:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:41:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:42:result_int32x4 [] = { 7fffffef, 7ffffff0, 7ffffff1, 7ffffff2,  }
+VQDMLAL_N:43:result_int64x2 [] = { 7fffffffffffffef, 7ffffffffffffff0,  }
+VQDMLAL_N:44:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:45:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:46:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_N:47:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLAL_N:48:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL_N:49:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL_N:50:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL_N:51:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLSL_N cumulative saturation output:
+VQDMLSL_N:0:vqdmlsl_n_s16 Neon cumulative saturation 0
+VQDMLSL_N:1:vqdmlsl_n_s32 Neon cumulative saturation 0
+
+VQDMLSL_N output:
+VQDMLSL_N:2:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:3:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:4:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_N:5:result_int64x1 [] = { 3333333333333333,  }
+VQDMLSL_N:6:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:7:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:8:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_N:9:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLSL_N:10:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:11:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:12:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_N:13:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLSL_N:14:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:15:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:16:result_int32x4 [] = { ffffe95c, ffffe95d, ffffe95e, ffffe95f,  }
+VQDMLSL_N:17:result_int64x2 [] = { ffffffffffffde12, ffffffffffffde13,  }
+VQDMLSL_N:18:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:19:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:20:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_N:21:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLSL_N:22:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:23:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:24:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_N:25:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLSL_N (check mul cumulative saturation) cumulative saturation output:
+VQDMLSL_N:26:vqdmlsl_n_s16 Neon cumulative saturation 1
+VQDMLSL_N:27:vqdmlsl_n_s32 Neon cumulative saturation 1
+
+VQDMLSL_N (check mul cumulative saturation) output:
+VQDMLSL_N:28:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:29:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:30:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_N:31:result_int64x1 [] = { 3333333333333333,  }
+VQDMLSL_N:32:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:33:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:34:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_N:35:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLSL_N:36:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:37:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:38:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLSL_N:39:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLSL_N:40:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:41:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:42:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VQDMLSL_N:43:result_int64x2 [] = { 8000000000000000, 8000000000000000,  }
+VQDMLSL_N:44:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:45:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:46:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_N:47:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLSL_N:48:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL_N:49:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL_N:50:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL_N:51:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VEXT/VEXTQ output:
+VEXT/VEXTQ:0:result_int8x8 [] = { fffffff7, 11, 11, 11, 11, 11, 11, 11,  }
+VEXT/VEXTQ:1:result_int16x4 [] = { fffffff3, 22, 22, 22,  }
+VEXT/VEXTQ:2:result_int32x2 [] = { fffffff1, 33,  }
+VEXT/VEXTQ:3:result_int64x1 [] = { fffffffffffffff0,  }
+VEXT/VEXTQ:4:result_uint8x8 [] = { f6, f7, 55, 55, 55, 55, 55, 55,  }
+VEXT/VEXTQ:5:result_uint16x4 [] = { fff2, fff3, 66, 66,  }
+VEXT/VEXTQ:6:result_uint32x2 [] = { fffffff1, 77,  }
+VEXT/VEXTQ:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VEXT/VEXTQ:8:result_poly8x8 [] = { f6, f7, 55, 55, 55, 55, 55, 55,  }
+VEXT/VEXTQ:9:result_poly16x4 [] = { fff2, fff3, 66, 66,  }
+VEXT/VEXTQ:10:result_float32x2 [] = { c1700000, 42066666,  }
+VEXT/VEXTQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VEXT/VEXTQ:12:result_int8x16 [] = { fffffffe, ffffffff, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11,  }
+VEXT/VEXTQ:13:result_int16x8 [] = { fffffff7, 22, 22, 22, 22, 22, 22, 22,  }
+VEXT/VEXTQ:14:result_int32x4 [] = { fffffff3, 33, 33, 33,  }
+VEXT/VEXTQ:15:result_int64x2 [] = { fffffffffffffff1, 44,  }
+VEXT/VEXTQ:16:result_uint8x16 [] = { fc, fd, fe, ff, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55,  }
+VEXT/VEXTQ:17:result_uint16x8 [] = { fff6, fff7, 66, 66, 66, 66, 66, 66,  }
+VEXT/VEXTQ:18:result_uint32x4 [] = { fffffff3, 77, 77, 77,  }
+VEXT/VEXTQ:19:result_uint64x2 [] = { fffffffffffffff1, 88,  }
+VEXT/VEXTQ:20:result_poly8x16 [] = { fc, fd, fe, ff, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55,  }
+VEXT/VEXTQ:21:result_poly16x8 [] = { fff6, fff7, 66, 66, 66, 66, 66, 66,  }
+VEXT/VEXTQ:22:result_float32x4 [] = { c1500000, 4204cccd, 4204cccd, 4204cccd,  }
+VEXT/VEXTQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSHR_N output:
+VSHR_N:0:result_int8x8 [] = { fffffff8, fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb,  }
+VSHR_N:1:result_int16x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VSHR_N:2:result_int32x2 [] = { fffffffc, fffffffc,  }
+VSHR_N:3:result_int64x1 [] = { ffffffffffffffff,  }
+VSHR_N:4:result_uint8x8 [] = { 3c, 3c, 3c, 3c, 3d, 3d, 3d, 3d,  }
+VSHR_N:5:result_uint16x4 [] = { 1ffe, 1ffe, 1ffe, 1ffe,  }
+VSHR_N:6:result_uint32x2 [] = { 7ffffff, 7ffffff,  }
+VSHR_N:7:result_uint64x1 [] = { 7fffffff,  }
+VSHR_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHR_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHR_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSHR_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSHR_N:12:result_int8x16 [] = { fffffff8, fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb, fffffffc, fffffffc, fffffffd, fffffffd, fffffffe, fffffffe, ffffffff, ffffffff,  }
+VSHR_N:13:result_int16x8 [] = { ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VSHR_N:14:result_int32x4 [] = { fffffffc, fffffffc, fffffffc, fffffffc,  }
+VSHR_N:15:result_int64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VSHR_N:16:result_uint8x16 [] = { 3c, 3c, 3c, 3c, 3d, 3d, 3d, 3d, 3e, 3e, 3e, 3e, 3f, 3f, 3f, 3f,  }
+VSHR_N:17:result_uint16x8 [] = { 1ffe, 1ffe, 1ffe, 1ffe, 1ffe, 1ffe, 1ffe, 1ffe,  }
+VSHR_N:18:result_uint32x4 [] = { 7ffffff, 7ffffff, 7ffffff, 7ffffff,  }
+VSHR_N:19:result_uint64x2 [] = { 7fffffff, 7fffffff,  }
+VSHR_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHR_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHR_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSHR_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSHRN_N output:
+VSHRN_N:0:result_int8x8 [] = { fffffff8, fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb,  }
+VSHRN_N:1:result_int16x4 [] = { fffffff8, fffffff8, fffffff9, fffffff9,  }
+VSHRN_N:2:result_int32x2 [] = { fffffffc, fffffffc,  }
+VSHRN_N:3:result_int64x1 [] = { 3333333333333333,  }
+VSHRN_N:4:result_uint8x8 [] = { fc, fc, fc, fc, fd, fd, fd, fd,  }
+VSHRN_N:5:result_uint16x4 [] = { fffe, fffe, fffe, fffe,  }
+VSHRN_N:6:result_uint32x2 [] = { fffffffe, fffffffe,  }
+VSHRN_N:7:result_uint64x1 [] = { 3333333333333333,  }
+VSHRN_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHRN_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHRN_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSHRN_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSHRN_N:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHRN_N:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHRN_N:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSHRN_N:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VSHRN_N:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHRN_N:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHRN_N:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSHRN_N:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VSHRN_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHRN_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHRN_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSHRN_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHRN_N (with input = 0) output:
+VRSHRN_N:0:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHRN_N:1:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHRN_N:2:result_int32x2 [] = { 0, 0,  }
+VRSHRN_N:3:result_int64x1 [] = { 3333333333333333,  }
+VRSHRN_N:4:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHRN_N:5:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VRSHRN_N:6:result_uint32x2 [] = { 0, 0,  }
+VRSHRN_N:7:result_uint64x1 [] = { 3333333333333333,  }
+VRSHRN_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHRN_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHRN_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHRN_N:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHRN_N:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRSHRN_N:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHRN_N:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRSHRN_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHRN_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHRN_N output:
+VRSHRN_N:24:result_int8x8 [] = { fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb, fffffffc,  }
+VRSHRN_N:25:result_int16x4 [] = { fffffff8, fffffff9, fffffff9, fffffffa,  }
+VRSHRN_N:26:result_int32x2 [] = { fffffffc, fffffffc,  }
+VRSHRN_N:27:result_int64x1 [] = { 3333333333333333,  }
+VRSHRN_N:28:result_uint8x8 [] = { fc, fc, fd, fd, fd, fd, fe, fe,  }
+VRSHRN_N:29:result_uint16x4 [] = { fffe, fffe, fffe, fffe,  }
+VRSHRN_N:30:result_uint32x2 [] = { fffffffe, fffffffe,  }
+VRSHRN_N:31:result_uint64x1 [] = { 3333333333333333,  }
+VRSHRN_N:32:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:33:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHRN_N:34:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHRN_N:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHRN_N:36:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:37:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:38:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHRN_N:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRSHRN_N:40:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:41:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:42:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHRN_N:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRSHRN_N:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:45:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHRN_N:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHRN_N (with large shift amount) output:
+VRSHRN_N:48:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHRN_N:49:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHRN_N:50:result_int32x2 [] = { 0, 0,  }
+VRSHRN_N:51:result_int64x1 [] = { 3333333333333333,  }
+VRSHRN_N:52:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHRN_N:53:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VRSHRN_N:54:result_uint32x2 [] = { 0, 0,  }
+VRSHRN_N:55:result_uint64x1 [] = { 3333333333333333,  }
+VRSHRN_N:56:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:57:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHRN_N:58:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHRN_N:59:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHRN_N:60:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:61:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:62:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHRN_N:63:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRSHRN_N:64:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:65:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:66:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHRN_N:67:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRSHRN_N:68:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHRN_N:69:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHRN_N:70:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHRN_N:71:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHRN_N cumulative saturation output:
+VQRSHRN_N:0:vqrshrn_n_s16 Neon cumulative saturation 0
+VQRSHRN_N:1:vqrshrn_n_s32 Neon cumulative saturation 0
+VQRSHRN_N:2:vqrshrn_n_s64 Neon cumulative saturation 0
+VQRSHRN_N:3:vqrshrn_n_u16 Neon cumulative saturation 1
+VQRSHRN_N:4:vqrshrn_n_u32 Neon cumulative saturation 1
+VQRSHRN_N:5:vqrshrn_n_u64 Neon cumulative saturation 1
+
+VQRSHRN_N output:
+VQRSHRN_N:6:result_int8x8 [] = { fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb, fffffffc,  }
+VQRSHRN_N:7:result_int16x4 [] = { fffffff8, fffffff9, fffffff9, fffffffa,  }
+VQRSHRN_N:8:result_int32x2 [] = { fffffffc, fffffffc,  }
+VQRSHRN_N:9:result_int64x1 [] = { 3333333333333333,  }
+VQRSHRN_N:10:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHRN_N:11:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQRSHRN_N:12:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQRSHRN_N:13:result_uint64x1 [] = { 3333333333333333,  }
+VQRSHRN_N:14:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:15:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:16:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHRN_N:17:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRN_N:18:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:19:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:20:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRN_N:21:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRN_N:22:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:23:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:24:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRN_N:25:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRN_N:26:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:27:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:28:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRN_N:29:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHRN_N (check saturation: shift by 3) cumulative saturation output:
+VQRSHRN_N:30:vqrshrn_n_s16 Neon cumulative saturation 1
+VQRSHRN_N:31:vqrshrn_n_s32 Neon cumulative saturation 1
+VQRSHRN_N:32:vqrshrn_n_s64 Neon cumulative saturation 1
+VQRSHRN_N:33:vqrshrn_n_u16 Neon cumulative saturation 1
+VQRSHRN_N:34:vqrshrn_n_u32 Neon cumulative saturation 1
+VQRSHRN_N:35:vqrshrn_n_u64 Neon cumulative saturation 1
+
+VQRSHRN_N (check saturation: shift by 3) output:
+VQRSHRN_N:36:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQRSHRN_N:37:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRSHRN_N:38:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRSHRN_N:39:result_int64x1 [] = { 3333333333333333,  }
+VQRSHRN_N:40:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHRN_N:41:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQRSHRN_N:42:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQRSHRN_N:43:result_uint64x1 [] = { 3333333333333333,  }
+VQRSHRN_N:44:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:45:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:46:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHRN_N:47:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRN_N:48:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:49:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:50:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRN_N:51:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRN_N:52:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:53:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:54:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRN_N:55:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRN_N:56:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:57:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:58:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRN_N:59:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHRN_N (check saturation: shift by max) cumulative saturation output:
+VQRSHRN_N:60:vqrshrn_n_s16 Neon cumulative saturation 1
+VQRSHRN_N:61:vqrshrn_n_s32 Neon cumulative saturation 1
+VQRSHRN_N:62:vqrshrn_n_s64 Neon cumulative saturation 1
+VQRSHRN_N:63:vqrshrn_n_u16 Neon cumulative saturation 1
+VQRSHRN_N:64:vqrshrn_n_u32 Neon cumulative saturation 1
+VQRSHRN_N:65:vqrshrn_n_u64 Neon cumulative saturation 1
+
+VQRSHRN_N (check saturation: shift by max) output:
+VQRSHRN_N:66:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQRSHRN_N:67:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRSHRN_N:68:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRSHRN_N:69:result_int64x1 [] = { 3333333333333333,  }
+VQRSHRN_N:70:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHRN_N:71:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQRSHRN_N:72:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQRSHRN_N:73:result_uint64x1 [] = { 3333333333333333,  }
+VQRSHRN_N:74:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:75:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:76:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHRN_N:77:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRN_N:78:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:79:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:80:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRN_N:81:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRN_N:82:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:83:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:84:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRN_N:85:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRN_N:86:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRN_N:87:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRN_N:88:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRN_N:89:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSET_LANE/VSET_LANEQ output:
+VSET_LANE/VSET_LANEQ:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, 11,  }
+VSET_LANE/VSET_LANEQ:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, 22,  }
+VSET_LANE/VSET_LANEQ:2:result_int32x2 [] = { fffffff0, 33,  }
+VSET_LANE/VSET_LANEQ:3:result_int64x1 [] = { 44,  }
+VSET_LANE/VSET_LANEQ:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, 55, f7,  }
+VSET_LANE/VSET_LANEQ:5:result_uint16x4 [] = { fff0, fff1, 66, fff3,  }
+VSET_LANE/VSET_LANEQ:6:result_uint32x2 [] = { fffffff0, 77,  }
+VSET_LANE/VSET_LANEQ:7:result_uint64x1 [] = { 88,  }
+VSET_LANE/VSET_LANEQ:8:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, 55, f7,  }
+VSET_LANE/VSET_LANEQ:9:result_poly16x4 [] = { fff0, fff1, 66, fff3,  }
+VSET_LANE/VSET_LANEQ:10:result_float32x2 [] = { c1800000, 4204cccd,  }
+VSET_LANE/VSET_LANEQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSET_LANE/VSET_LANEQ:12:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffff99,  }
+VSET_LANE/VSET_LANEQ:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, aa, fffffff6, fffffff7,  }
+VSET_LANE/VSET_LANEQ:14:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, bb,  }
+VSET_LANE/VSET_LANEQ:15:result_int64x2 [] = { fffffffffffffff0, cc,  }
+VSET_LANE/VSET_LANEQ:16:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, dd, ff,  }
+VSET_LANE/VSET_LANEQ:17:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, ee, fff7,  }
+VSET_LANE/VSET_LANEQ:18:result_uint32x4 [] = { fffffff0, fffffff1, ff, fffffff3,  }
+VSET_LANE/VSET_LANEQ:19:result_uint64x2 [] = { fffffffffffffff0, 11,  }
+VSET_LANE/VSET_LANEQ:20:result_poly8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, dd, ff,  }
+VSET_LANE/VSET_LANEQ:21:result_poly16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, ee, fff7,  }
+VSET_LANE/VSET_LANEQ:22:result_float32x4 [] = { c1800000, c1700000, c1600000, 41333333,  }
+VSET_LANE/VSET_LANEQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VGET_LANE/VGETQ_LANE output:
+vget_lane_s8: fffffff7
+vget_lane_s16: fffffff3
+vget_lane_s32: fffffff1
+vget_lane_s64: fffffffffffffff0
+vget_lane_u8: f6
+vget_lane_u16: fff2
+vget_lane_u32: fffffff1
+vget_lane_u64: fffffffffffffff0
+vget_lane_p8: f6
+vget_lane_p16: fff2
+vget_lane_f32: c1700000
+vgetq_lane_s8: ffffffff
+vgetq_lane_s16: fffffff5
+vgetq_lane_s32: fffffff3
+vgetq_lane_s64: fffffffffffffff1
+vgetq_lane_u8: fe
+vgetq_lane_u16: fff6
+vgetq_lane_u32: fffffff2
+vgetq_lane_u64: fffffffffffffff1
+vgetq_lane_p8: fe
+vgetq_lane_p16: fff6
+vgetq_lane_f32: c1500000
+
+
+VQSUB/VQSUBQ cumulative saturation output:
+VQSUB/VQSUBQ:0:vqsub_s8 Neon cumulative saturation 0
+VQSUB/VQSUBQ:1:vqsub_s16 Neon cumulative saturation 0
+VQSUB/VQSUBQ:2:vqsub_s32 Neon cumulative saturation 0
+VQSUB/VQSUBQ:3:vqsub_s64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:4:vqsub_u8 Neon cumulative saturation 0
+VQSUB/VQSUBQ:5:vqsub_u16 Neon cumulative saturation 0
+VQSUB/VQSUBQ:6:vqsub_u32 Neon cumulative saturation 0
+VQSUB/VQSUBQ:7:vqsub_u64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:8:vqsubq_s8 Neon cumulative saturation 0
+VQSUB/VQSUBQ:9:vqsubq_s16 Neon cumulative saturation 0
+VQSUB/VQSUBQ:10:vqsubq_s32 Neon cumulative saturation 0
+VQSUB/VQSUBQ:11:vqsubq_s64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:12:vqsubq_u8 Neon cumulative saturation 0
+VQSUB/VQSUBQ:13:vqsubq_u16 Neon cumulative saturation 0
+VQSUB/VQSUBQ:14:vqsubq_u32 Neon cumulative saturation 0
+VQSUB/VQSUBQ:15:vqsubq_u64 Neon cumulative saturation 0
+
+VQSUB/VQSUBQ output:
+VQSUB/VQSUBQ:16:result_int8x8 [] = { ffffffdf, ffffffe0, ffffffe1, ffffffe2, ffffffe3, ffffffe4, ffffffe5, ffffffe6,  }
+VQSUB/VQSUBQ:17:result_int16x4 [] = { ffffffce, ffffffcf, ffffffd0, ffffffd1,  }
+VQSUB/VQSUBQ:18:result_int32x2 [] = { ffffffbd, ffffffbe,  }
+VQSUB/VQSUBQ:19:result_int64x1 [] = { ffffffffffffffac,  }
+VQSUB/VQSUBQ:20:result_uint8x8 [] = { 9b, 9c, 9d, 9e, 9f, a0, a1, a2,  }
+VQSUB/VQSUBQ:21:result_uint16x4 [] = { ff8a, ff8b, ff8c, ff8d,  }
+VQSUB/VQSUBQ:22:result_uint32x2 [] = { ffffff79, ffffff7a,  }
+VQSUB/VQSUBQ:23:result_uint64x1 [] = { ffffffffffffff68,  }
+VQSUB/VQSUBQ:24:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSUB/VQSUBQ:25:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSUB/VQSUBQ:26:result_float32x2 [] = { 33333333, 33333333,  }
+VQSUB/VQSUBQ:27:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSUB/VQSUBQ:28:result_int8x16 [] = { ffffffdf, ffffffe0, ffffffe1, ffffffe2, ffffffe3, ffffffe4, ffffffe5, ffffffe6, ffffffe7, ffffffe8, ffffffe9, ffffffea, ffffffeb, ffffffec, ffffffed, ffffffee,  }
+VQSUB/VQSUBQ:29:result_int16x8 [] = { ffffffce, ffffffcf, ffffffd0, ffffffd1, ffffffd2, ffffffd3, ffffffd4, ffffffd5,  }
+VQSUB/VQSUBQ:30:result_int32x4 [] = { ffffffbd, ffffffbe, ffffffbf, ffffffc0,  }
+VQSUB/VQSUBQ:31:result_int64x2 [] = { ffffffffffffffac, ffffffffffffffad,  }
+VQSUB/VQSUBQ:32:result_uint8x16 [] = { 9b, 9c, 9d, 9e, 9f, a0, a1, a2, a3, a4, a5, a6, a7, a8, a9, aa,  }
+VQSUB/VQSUBQ:33:result_uint16x8 [] = { ff8a, ff8b, ff8c, ff8d, ff8e, ff8f, ff90, ff91,  }
+VQSUB/VQSUBQ:34:result_uint32x4 [] = { ffffff79, ffffff7a, ffffff7b, ffffff7c,  }
+VQSUB/VQSUBQ:35:result_uint64x2 [] = { ffffffffffffff68, ffffffffffffff69,  }
+VQSUB/VQSUBQ:36:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSUB/VQSUBQ:37:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSUB/VQSUBQ:38:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSUB/VQSUBQ:39:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSUB/VQSUBQ 64 bits saturation cumulative saturation output:
+VQSUB/VQSUBQ:40:vqsub_s64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:41:vqsub_u64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:42:vqsubq_s64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:43:vqsubq_u64 Neon cumulative saturation 0
+
+64 bits saturation:
+VQSUB/VQSUBQ:44:result_int64x1 [] = { fffffffffffffff0,  }
+VQSUB/VQSUBQ:45:result_uint64x1 [] = { fffffffffffffff0,  }
+VQSUB/VQSUBQ:46:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VQSUB/VQSUBQ:47:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+
+VQSUB/VQSUBQ 64 bits saturation cumulative saturation output:
+VQSUB/VQSUBQ:48:vqsub_s64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:49:vqsub_u64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:50:vqsubq_s64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:51:vqsubq_u64 Neon cumulative saturation 0
+VQSUB/VQSUBQ:52:result_int64x1 [] = { ffffffffffffffac,  }
+VQSUB/VQSUBQ:53:result_uint64x1 [] = { ffffffffffffff68,  }
+VQSUB/VQSUBQ:54:result_int64x2 [] = { ffffffffffffffac, ffffffffffffffad,  }
+VQSUB/VQSUBQ:55:result_uint64x2 [] = { ffffffffffffff68, ffffffffffffff69,  }
+
+VQSUB/VQSUBQ 64 bits saturation cumulative saturation output:
+VQSUB/VQSUBQ:56:vqsub_s64 Neon cumulative saturation 1
+VQSUB/VQSUBQ:57:vqsub_u64 Neon cumulative saturation 1
+VQSUB/VQSUBQ:58:vqsubq_s64 Neon cumulative saturation 1
+VQSUB/VQSUBQ:59:vqsubq_u64 Neon cumulative saturation 1
+VQSUB/VQSUBQ:60:result_int64x1 [] = { 8000000000000000,  }
+VQSUB/VQSUBQ:61:result_uint64x1 [] = { 0,  }
+VQSUB/VQSUBQ:62:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+VQSUB/VQSUBQ:63:result_uint64x2 [] = { 0, 0,  }
+
+less than 64 bits saturation:
+VQSUB/VQSUBQ:64:vqsub_s8 Neon cumulative saturation 1
+VQSUB/VQSUBQ:65:vqsub_s16 Neon cumulative saturation 1
+VQSUB/VQSUBQ:66:vqsub_s32 Neon cumulative saturation 1
+VQSUB/VQSUBQ:67:vqsubq_s8 Neon cumulative saturation 1
+VQSUB/VQSUBQ:68:vqsubq_s16 Neon cumulative saturation 1
+VQSUB/VQSUBQ:69:vqsubq_s32 Neon cumulative saturation 1
+VQSUB/VQSUBQ:70:result_int8x8 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQSUB/VQSUBQ:71:result_int16x4 [] = { ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQSUB/VQSUBQ:72:result_int32x2 [] = { 80000000, 80000000,  }
+VQSUB/VQSUBQ:73:result_int8x16 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQSUB/VQSUBQ:74:result_int16x8 [] = { ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQSUB/VQSUBQ:75:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+
+VQSUB/VQSUBQ less than 64 bits saturation cumulative saturation output:
+VQSUB/VQSUBQ:76:vqsub_u8 Neon cumulative saturation 1
+VQSUB/VQSUBQ:77:vqsub_u16 Neon cumulative saturation 1
+VQSUB/VQSUBQ:78:vqsub_u32 Neon cumulative saturation 1
+VQSUB/VQSUBQ:79:vqsubq_u8 Neon cumulative saturation 1
+VQSUB/VQSUBQ:80:vqsubq_u16 Neon cumulative saturation 1
+VQSUB/VQSUBQ:81:vqsubq_u32 Neon cumulative saturation 1
+VQSUB/VQSUBQ:82:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSUB/VQSUBQ:83:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQSUB/VQSUBQ:84:result_uint32x2 [] = { 0, 0,  }
+VQSUB/VQSUBQ:85:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSUB/VQSUBQ:86:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSUB/VQSUBQ:87:result_uint32x4 [] = { 0, 0, 0, 0,  }
+
+VQDMULH cumulative saturation output:
+VQDMULH:0:vqdmulh_s16 Neon cumulative saturation 0
+VQDMULH:1:vqdmulh_s32 Neon cumulative saturation 0
+VQDMULH:2:vqdmulhq_s16 Neon cumulative saturation 0
+VQDMULH:3:vqdmulhq_s32 Neon cumulative saturation 0
+
+VQDMULH output:
+VQDMULH:4:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:5:result_int16x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQDMULH:6:result_int32x2 [] = { ffffffff, ffffffff,  }
+VQDMULH:7:result_int64x1 [] = { 3333333333333333,  }
+VQDMULH:8:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:9:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH:10:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMULH:11:result_uint64x1 [] = { 3333333333333333,  }
+VQDMULH:12:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:13:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH:14:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMULH:15:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMULH:16:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:17:result_int16x8 [] = { ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQDMULH:18:result_int32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQDMULH:19:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH:20:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:21:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH:22:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH:23:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH:24:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:25:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH:26:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH:27:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMULH cumulative saturation output:
+VQDMULH:28:vqdmulh_s16 Neon cumulative saturation 1
+VQDMULH:29:vqdmulh_s32 Neon cumulative saturation 1
+VQDMULH:30:vqdmulhq_s16 Neon cumulative saturation 1
+VQDMULH:31:vqdmulhq_s32 Neon cumulative saturation 1
+
+VQDMULH output:
+VQDMULH:32:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:33:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQDMULH:34:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQDMULH:35:result_int64x1 [] = { 3333333333333333,  }
+VQDMULH:36:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:37:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH:38:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMULH:39:result_uint64x1 [] = { 3333333333333333,  }
+VQDMULH:40:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:41:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH:42:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMULH:43:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMULH:44:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:45:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQDMULH:46:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQDMULH:47:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH:48:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:49:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH:50:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH:51:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH:52:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH:53:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH:54:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH:55:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMULH_LANE cumulative saturation output:
+VQDMULH_LANE:0:vqdmulh_lane_s16 Neon cumulative saturation 0
+VQDMULH_LANE:1:vqdmulh_lane_s32 Neon cumulative saturation 0
+VQDMULH_LANE:2:vqdmulhq_lane_s16 Neon cumulative saturation 0
+VQDMULH_LANE:3:vqdmulhq_lane_s32 Neon cumulative saturation 0
+
+VQDMULH_LANE output:
+VQDMULH_LANE:4:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:5:result_int16x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQDMULH_LANE:6:result_int32x2 [] = { ffffffff, ffffffff,  }
+VQDMULH_LANE:7:result_int64x1 [] = { 3333333333333333,  }
+VQDMULH_LANE:8:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:9:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH_LANE:10:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMULH_LANE:11:result_uint64x1 [] = { 3333333333333333,  }
+VQDMULH_LANE:12:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:13:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH_LANE:14:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMULH_LANE:15:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMULH_LANE:16:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:17:result_int16x8 [] = { ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQDMULH_LANE:18:result_int32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQDMULH_LANE:19:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH_LANE:20:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:21:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH_LANE:22:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH_LANE:23:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH_LANE:24:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:25:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH_LANE:26:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH_LANE:27:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMULH_LANE (check mul cumulative saturation) cumulative saturation output:
+VQDMULH_LANE:28:vqdmulh_lane_s16 Neon cumulative saturation 1
+VQDMULH_LANE:29:vqdmulh_lane_s32 Neon cumulative saturation 1
+VQDMULH_LANE:30:vqdmulhq_lane_s16 Neon cumulative saturation 1
+VQDMULH_LANE:31:vqdmulhq_lane_s32 Neon cumulative saturation 1
+
+VQDMULH_LANE (check mul cumulative saturation) output:
+VQDMULH_LANE:32:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:33:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQDMULH_LANE:34:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQDMULH_LANE:35:result_int64x1 [] = { 3333333333333333,  }
+VQDMULH_LANE:36:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:37:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH_LANE:38:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMULH_LANE:39:result_uint64x1 [] = { 3333333333333333,  }
+VQDMULH_LANE:40:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:41:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH_LANE:42:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMULH_LANE:43:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMULH_LANE:44:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:45:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQDMULH_LANE:46:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQDMULH_LANE:47:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH_LANE:48:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:49:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH_LANE:50:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH_LANE:51:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH_LANE:52:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_LANE:53:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH_LANE:54:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH_LANE:55:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMULH_N cumulative saturation output:
+VQDMULH_N:0:vqdmulh_n_s16 Neon cumulative saturation 0
+VQDMULH_N:1:vqdmulh_n_s32 Neon cumulative saturation 0
+VQDMULH_N:2:vqdmulhq_n_s16 Neon cumulative saturation 0
+VQDMULH_N:3:vqdmulhq_n_s32 Neon cumulative saturation 0
+
+VQDMULH_N output:
+VQDMULH_N:4:result_int16x4 [] = { 19, 19, 19, 19,  }
+VQDMULH_N:5:result_int32x2 [] = { 4, 4,  }
+VQDMULH_N:6:result_int16x8 [] = { 10, 10, 10, 10, 10, 10, 10, 10,  }
+VQDMULH_N:7:result_int32x4 [] = { a, a, a, a,  }
+
+VQDMULH_N (check mul cumulative saturation) cumulative saturation output:
+VQDMULH_N:8:vqdmulh_n_s16 Neon cumulative saturation 1
+VQDMULH_N:9:vqdmulh_n_s32 Neon cumulative saturation 1
+VQDMULH_N:10:vqdmulhq_n_s16 Neon cumulative saturation 1
+VQDMULH_N:11:vqdmulhq_n_s32 Neon cumulative saturation 1
+
+VQDMULH_N (check mul cumulative saturation) output:
+VQDMULH_N:12:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_N:13:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQDMULH_N:14:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQDMULH_N:15:result_int64x1 [] = { 3333333333333333,  }
+VQDMULH_N:16:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_N:17:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH_N:18:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMULH_N:19:result_uint64x1 [] = { 3333333333333333,  }
+VQDMULH_N:20:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_N:21:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULH_N:22:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMULH_N:23:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMULH_N:24:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_N:25:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQDMULH_N:26:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQDMULH_N:27:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH_N:28:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_N:29:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH_N:30:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH_N:31:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULH_N:32:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULH_N:33:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULH_N:34:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULH_N:35:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMULL cumulative saturation output:
+VQDMULL:0:vqdmull_s16 Neon cumulative saturation 0
+VQDMULL:1:vqdmull_s32 Neon cumulative saturation 0
+
+VQDMULL output:
+VQDMULL:2:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:3:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULL:4:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMULL:5:result_int64x1 [] = { 3333333333333333,  }
+VQDMULL:6:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:7:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULL:8:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMULL:9:result_uint64x1 [] = { 3333333333333333,  }
+VQDMULL:10:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:11:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULL:12:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMULL:13:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMULL:14:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:15:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULL:16:result_int32x4 [] = { 200, 1c2, 188, 152,  }
+VQDMULL:17:result_int64x2 [] = { 200, 1c2,  }
+VQDMULL:18:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:19:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULL:20:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULL:21:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULL:22:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:23:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULL:24:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULL:25:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMULL (check mul cumulative saturation) cumulative saturation output:
+VQDMULL:26:vqdmull_s16 Neon cumulative saturation 1
+VQDMULL:27:vqdmull_s32 Neon cumulative saturation 1
+
+VQDMULL (check mul cumulative saturation) output:
+VQDMULL:28:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:29:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULL:30:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMULL:31:result_int64x1 [] = { 3333333333333333,  }
+VQDMULL:32:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:33:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULL:34:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMULL:35:result_uint64x1 [] = { 3333333333333333,  }
+VQDMULL:36:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:37:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMULL:38:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMULL:39:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMULL:40:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:41:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULL:42:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQDMULL:43:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+VQDMULL:44:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:45:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULL:46:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULL:47:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMULL:48:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMULL:49:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMULL:50:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMULL:51:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLAL cumulative saturation output:
+VQDMLAL:0:vqdmlal_s16 Neon cumulative saturation 0
+VQDMLAL:1:vqdmlal_s32 Neon cumulative saturation 0
+
+VQDMLAL output:
+VQDMLAL:2:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:3:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL:4:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLAL:5:result_int64x1 [] = { 3333333333333333,  }
+VQDMLAL:6:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:7:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL:8:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLAL:9:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLAL:10:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:11:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL:12:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLAL:13:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLAL:14:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:15:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL:16:result_int32x4 [] = { 7c1e, 7c1f, 7c20, 7c21,  }
+VQDMLAL:17:result_int64x2 [] = { 7c1e, 7c1f,  }
+VQDMLAL:18:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:19:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL:20:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL:21:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLAL:22:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:23:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL:24:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL:25:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLAL (check mul cumulative saturation) cumulative saturation output:
+VQDMLAL:26:vqdmlal_s16 Neon cumulative saturation 1
+VQDMLAL:27:vqdmlal_s32 Neon cumulative saturation 1
+
+VQDMLAL (check mul cumulative saturation) output:
+VQDMLAL:28:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:29:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL:30:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLAL:31:result_int64x1 [] = { 3333333333333333,  }
+VQDMLAL:32:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:33:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL:34:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLAL:35:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLAL:36:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:37:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLAL:38:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLAL:39:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLAL:40:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:41:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL:42:result_int32x4 [] = { 7fffffef, 7ffffff0, 7ffffff1, 7ffffff2,  }
+VQDMLAL:43:result_int64x2 [] = { 7fffffffffffffef, 7ffffffffffffff0,  }
+VQDMLAL:44:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:45:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL:46:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL:47:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLAL:48:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLAL:49:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLAL:50:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLAL:51:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLSL cumulative saturation output:
+VQDMLSL:0:vqdmlsl_s16 Neon cumulative saturation 0
+VQDMLSL:1:vqdmlsl_s32 Neon cumulative saturation 0
+
+VQDMLSL output:
+VQDMLSL:2:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:3:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL:4:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLSL:5:result_int64x1 [] = { 3333333333333333,  }
+VQDMLSL:6:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:7:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL:8:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLSL:9:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLSL:10:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:11:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL:12:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLSL:13:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLSL:14:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:15:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL:16:result_int32x4 [] = { ffff83c2, ffff83c3, ffff83c4, ffff83c5,  }
+VQDMLSL:17:result_int64x2 [] = { ffffffffffff83c2, ffffffffffff83c3,  }
+VQDMLSL:18:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:19:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL:20:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL:21:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLSL:22:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:23:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL:24:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL:25:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMLSL (check mul cumulative saturation) cumulative saturation output:
+VQDMLSL:26:vqdmlsl_s16 Neon cumulative saturation 1
+VQDMLSL:27:vqdmlsl_s32 Neon cumulative saturation 1
+
+VQDMLSL (check mul cumulative saturation) output:
+VQDMLSL:28:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:29:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL:30:result_int32x2 [] = { 33333333, 33333333,  }
+VQDMLSL:31:result_int64x1 [] = { 3333333333333333,  }
+VQDMLSL:32:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:33:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL:34:result_uint32x2 [] = { 33333333, 33333333,  }
+VQDMLSL:35:result_uint64x1 [] = { 3333333333333333,  }
+VQDMLSL:36:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:37:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQDMLSL:38:result_float32x2 [] = { 33333333, 33333333,  }
+VQDMLSL:39:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQDMLSL:40:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:41:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL:42:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VQDMLSL:43:result_int64x2 [] = { 8000000000000000, 8000000000000000,  }
+VQDMLSL:44:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:45:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL:46:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL:47:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQDMLSL:48:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQDMLSL:49:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQDMLSL:50:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQDMLSL:51:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VCEQ/VCEQQ output:
+VCEQ/VCEQQ:0:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, ff, 0,  }
+VCEQ/VCEQQ:1:result_uint16x4 [] = { 0, 0, ffff, 0,  }
+VCEQ/VCEQQ:2:result_uint32x2 [] = { ffffffff, 0,  }
+VCEQ/VCEQQ:3:result_uint8x8 [] = { 0, 0, 0, ff, 0, 0, 0, 0,  }
+VCEQ/VCEQQ:4:result_uint16x4 [] = { 0, 0, ffff, 0,  }
+VCEQ/VCEQQ:5:result_uint32x2 [] = { 0, ffffffff,  }
+VCEQ/VCEQQ:6:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ff, 0, 0, 0,  }
+VCEQ/VCEQQ:7:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, ffff, 0,  }
+VCEQ/VCEQQ:8:result_uint32x4 [] = { 0, 0, ffffffff, 0,  }
+VCEQ/VCEQQ:9:result_uint8x16 [] = { 0, 0, 0, 0, ff, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VCEQ/VCEQQ:10:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, ffff, 0,  }
+VCEQ/VCEQQ:11:result_uint32x4 [] = { 0, 0, ffffffff, 0,  }
+VCEQ/VCEQQ:12:result_uint32x2 [] = { 0, ffffffff,  }
+VCEQ/VCEQQ:13:result_uint32x4 [] = { 0, 0, ffffffff, 0,  }
+VCEQ/VCEQQ:14:result_uint32x2 [] = { ffffffff, 0,  }
+VCEQ/VCEQQ:15:result_uint32x2 [] = { 0, ffffffff,  }
+VCEQ/VCEQQ:16:result_uint32x2 [] = { ffffffff, 0,  }
+VCEQ/VCEQQ FP special (NaN):17:result_uint32x2 [] = { 0, 0,  }
+VCEQ/VCEQQ FP special (-NaN):18:result_uint32x2 [] = { 0, 0,  }
+VCEQ/VCEQQ FP special (NaN):19:result_uint32x2 [] = { 0, 0,  }
+VCEQ/VCEQQ FP special (inf):20:result_uint32x2 [] = { 0, 0,  }
+VCEQ/VCEQQ FP special (-inf):21:result_uint32x2 [] = { 0, 0,  }
+VCEQ/VCEQQ FP special (inf):22:result_uint32x2 [] = { 0, 0,  }
+VCEQ/VCEQQ FP special (-0.0):23:result_uint32x2 [] = { ffffffff, ffffffff,  }
+
+VCEQ/VCEQQ p8 output:
+VCEQ/VCEQQ:0:result_uint8x8 [] = { 0, 0, 0, ff, 0, 0, 0, 0,  }
+VCEQ/VCEQQ:1:result_uint8x16 [] = { 0, 0, 0, 0, ff, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VCGE/VCGEQ output:
+VCGE/VCGEQ:0:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, ff, ff,  }
+VCGE/VCGEQ:1:result_uint16x4 [] = { 0, 0, ffff, ffff,  }
+VCGE/VCGEQ:2:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCGE/VCGEQ:3:result_uint8x8 [] = { 0, 0, 0, ff, ff, ff, ff, ff,  }
+VCGE/VCGEQ:4:result_uint16x4 [] = { 0, 0, ffff, ffff,  }
+VCGE/VCGEQ:5:result_uint32x2 [] = { 0, ffffffff,  }
+VCGE/VCGEQ:6:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ff, ff, ff, ff,  }
+VCGE/VCGEQ:7:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, ffff, ffff,  }
+VCGE/VCGEQ:8:result_uint32x4 [] = { 0, 0, ffffffff, ffffffff,  }
+VCGE/VCGEQ:9:result_uint8x16 [] = { 0, 0, 0, 0, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VCGE/VCGEQ:10:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, ffff, ffff,  }
+VCGE/VCGEQ:11:result_uint32x4 [] = { 0, 0, ffffffff, ffffffff,  }
+VCGE/VCGEQ:12:result_uint32x2 [] = { 0, ffffffff,  }
+VCGE/VCGEQ:13:result_uint32x4 [] = { 0, 0, ffffffff, ffffffff,  }
+VCGE/VCGEQ:14:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCGE/VCGEQ:15:result_uint32x2 [] = { 0, ffffffff,  }
+VCGE/VCGEQ:16:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCGE/VCGEQ FP special (NaN):17:result_uint32x2 [] = { 0, 0,  }
+VCGE/VCGEQ FP special (-NaN):18:result_uint32x2 [] = { 0, 0,  }
+VCGE/VCGEQ FP special (NaN):19:result_uint32x2 [] = { 0, 0,  }
+VCGE/VCGEQ FP special (inf):20:result_uint32x2 [] = { 0, 0,  }
+VCGE/VCGEQ FP special (-inf):21:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCGE/VCGEQ FP special (inf):22:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCGE/VCGEQ FP special (-0.0):23:result_uint32x2 [] = { ffffffff, ffffffff,  }
+
+VCLE/VCLEQ output:
+VCLE/VCLEQ:0:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, 0,  }
+VCLE/VCLEQ:1:result_uint16x4 [] = { ffff, ffff, ffff, 0,  }
+VCLE/VCLEQ:2:result_uint32x2 [] = { ffffffff, 0,  }
+VCLE/VCLEQ:3:result_uint8x8 [] = { ff, ff, ff, ff, 0, 0, 0, 0,  }
+VCLE/VCLEQ:4:result_uint16x4 [] = { ffff, ffff, ffff, 0,  }
+VCLE/VCLEQ:5:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCLE/VCLEQ:6:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, 0, 0, 0,  }
+VCLE/VCLEQ:7:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, 0,  }
+VCLE/VCLEQ:8:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, 0,  }
+VCLE/VCLEQ:9:result_uint8x16 [] = { ff, ff, ff, ff, ff, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VCLE/VCLEQ:10:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, 0,  }
+VCLE/VCLEQ:11:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, 0,  }
+VCLE/VCLEQ:12:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCLE/VCLEQ:13:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, 0,  }
+VCLE/VCLEQ:14:result_uint32x2 [] = { ffffffff, 0,  }
+VCLE/VCLEQ:15:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCLE/VCLEQ:16:result_uint32x2 [] = { ffffffff, 0,  }
+VCLE/VCLEQ FP special (NaN):17:result_uint32x2 [] = { 0, 0,  }
+VCLE/VCLEQ FP special (-NaN):18:result_uint32x2 [] = { 0, 0,  }
+VCLE/VCLEQ FP special (NaN):19:result_uint32x2 [] = { 0, 0,  }
+VCLE/VCLEQ FP special (inf):20:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCLE/VCLEQ FP special (-inf):21:result_uint32x2 [] = { 0, 0,  }
+VCLE/VCLEQ FP special (inf):22:result_uint32x2 [] = { 0, 0,  }
+VCLE/VCLEQ FP special (-0.0):23:result_uint32x2 [] = { ffffffff, ffffffff,  }
+
+VCGT/VCGTQ output:
+VCGT/VCGTQ:0:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, ff,  }
+VCGT/VCGTQ:1:result_uint16x4 [] = { 0, 0, 0, ffff,  }
+VCGT/VCGTQ:2:result_uint32x2 [] = { 0, ffffffff,  }
+VCGT/VCGTQ:3:result_uint8x8 [] = { 0, 0, 0, 0, ff, ff, ff, ff,  }
+VCGT/VCGTQ:4:result_uint16x4 [] = { 0, 0, 0, ffff,  }
+VCGT/VCGTQ:5:result_uint32x2 [] = { 0, 0,  }
+VCGT/VCGTQ:6:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ff, ff, ff,  }
+VCGT/VCGTQ:7:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, ffff,  }
+VCGT/VCGTQ:8:result_uint32x4 [] = { 0, 0, 0, ffffffff,  }
+VCGT/VCGTQ:9:result_uint8x16 [] = { 0, 0, 0, 0, 0, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VCGT/VCGTQ:10:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, ffff,  }
+VCGT/VCGTQ:11:result_uint32x4 [] = { 0, 0, 0, ffffffff,  }
+VCGT/VCGTQ:12:result_uint32x2 [] = { 0, 0,  }
+VCGT/VCGTQ:13:result_uint32x4 [] = { 0, 0, 0, ffffffff,  }
+VCGT/VCGTQ:14:result_uint32x2 [] = { 0, ffffffff,  }
+VCGT/VCGTQ:15:result_uint32x2 [] = { 0, 0,  }
+VCGT/VCGTQ:16:result_uint32x2 [] = { 0, ffffffff,  }
+VCGT/VCGTQ FP special (NaN):17:result_uint32x2 [] = { 0, 0,  }
+VCGT/VCGTQ FP special (-NaN):18:result_uint32x2 [] = { 0, 0,  }
+VCGT/VCGTQ FP special (NaN):19:result_uint32x2 [] = { 0, 0,  }
+VCGT/VCGTQ FP special (inf):20:result_uint32x2 [] = { 0, 0,  }
+VCGT/VCGTQ FP special (-inf):21:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCGT/VCGTQ FP special (inf):22:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCGT/VCGTQ FP special (-0.0):23:result_uint32x2 [] = { 0, 0,  }
+
+VCLT/VCLTQ output:
+VCLT/VCLTQ:0:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, 0, 0,  }
+VCLT/VCLTQ:1:result_uint16x4 [] = { ffff, ffff, 0, 0,  }
+VCLT/VCLTQ:2:result_uint32x2 [] = { 0, 0,  }
+VCLT/VCLTQ:3:result_uint8x8 [] = { ff, ff, ff, 0, 0, 0, 0, 0,  }
+VCLT/VCLTQ:4:result_uint16x4 [] = { ffff, ffff, 0, 0,  }
+VCLT/VCLTQ:5:result_uint32x2 [] = { ffffffff, 0,  }
+VCLT/VCLTQ:6:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, 0, 0, 0, 0,  }
+VCLT/VCLTQ:7:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, 0, 0,  }
+VCLT/VCLTQ:8:result_uint32x4 [] = { ffffffff, ffffffff, 0, 0,  }
+VCLT/VCLTQ:9:result_uint8x16 [] = { ff, ff, ff, ff, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VCLT/VCLTQ:10:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, 0, 0,  }
+VCLT/VCLTQ:11:result_uint32x4 [] = { ffffffff, ffffffff, 0, 0,  }
+VCLT/VCLTQ:12:result_uint32x2 [] = { ffffffff, 0,  }
+VCLT/VCLTQ:13:result_uint32x4 [] = { ffffffff, ffffffff, 0, 0,  }
+VCLT/VCLTQ:14:result_uint32x2 [] = { 0, 0,  }
+VCLT/VCLTQ:15:result_uint32x2 [] = { ffffffff, 0,  }
+VCLT/VCLTQ:16:result_uint32x2 [] = { 0, 0,  }
+VCLT/VCLTQ FP special (NaN):17:result_uint32x2 [] = { 0, 0,  }
+VCLT/VCLTQ FP special (-NaN):18:result_uint32x2 [] = { 0, 0,  }
+VCLT/VCLTQ FP special (NaN):19:result_uint32x2 [] = { 0, 0,  }
+VCLT/VCLTQ FP special (inf):20:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCLT/VCLTQ FP special (-inf):21:result_uint32x2 [] = { 0, 0,  }
+VCLT/VCLTQ FP special (inf):22:result_uint32x2 [] = { 0, 0,  }
+VCLT/VCLTQ FP special (-0.0):23:result_uint32x2 [] = { 0, 0,  }
+
+VBSL/VBSLQ output:
+VBSL/VBSLQ:0:result_int8x8 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff6, fffffff6, fffffff6, fffffff6,  }
+VBSL/VBSLQ:1:result_int16x4 [] = { fffffff0, fffffff0, fffffff2, fffffff2,  }
+VBSL/VBSLQ:2:result_int32x2 [] = { fffffff0, fffffff0,  }
+VBSL/VBSLQ:3:result_int64x1 [] = { fffffffffffffffd,  }
+VBSL/VBSLQ:4:result_uint8x8 [] = { f3, f3, f3, f3, f7, f7, f7, f7,  }
+VBSL/VBSLQ:5:result_uint16x4 [] = { fff0, fff0, fff2, fff2,  }
+VBSL/VBSLQ:6:result_uint32x2 [] = { fffffff0, fffffff0,  }
+VBSL/VBSLQ:7:result_uint64x1 [] = { fffffff1,  }
+VBSL/VBSLQ:8:result_poly8x8 [] = { f3, f3, f3, f3, f7, f7, f7, f7,  }
+VBSL/VBSLQ:9:result_poly16x4 [] = { fff0, fff0, fff2, fff2,  }
+VBSL/VBSLQ:10:result_float32x2 [] = { c1800004, c1700004,  }
+VBSL/VBSLQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VBSL/VBSLQ:12:result_int8x16 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff6, fffffff6, fffffff6, fffffff6, fffffff2, fffffff2, fffffff2, fffffff2, fffffff6, fffffff6, fffffff6, fffffff6,  }
+VBSL/VBSLQ:13:result_int16x8 [] = { fffffff0, fffffff0, fffffff2, fffffff2, fffffff4, fffffff4, fffffff6, fffffff6,  }
+VBSL/VBSLQ:14:result_int32x4 [] = { fffffff0, fffffff0, fffffff2, fffffff2,  }
+VBSL/VBSLQ:15:result_int64x2 [] = { fffffffffffffffd, fffffffffffffffd,  }
+VBSL/VBSLQ:16:result_uint8x16 [] = { f3, f3, f3, f3, f7, f7, f7, f7, f3, f3, f3, f3, f7, f7, f7, f7,  }
+VBSL/VBSLQ:17:result_uint16x8 [] = { fff0, fff0, fff2, fff2, fff4, fff4, fff6, fff6,  }
+VBSL/VBSLQ:18:result_uint32x4 [] = { fffffff0, fffffff0, fffffff2, fffffff2,  }
+VBSL/VBSLQ:19:result_uint64x2 [] = { fffffff1, fffffff1,  }
+VBSL/VBSLQ:20:result_poly8x16 [] = { f3, f3, f3, f3, f7, f7, f7, f7, f3, f3, f3, f3, f7, f7, f7, f7,  }
+VBSL/VBSLQ:21:result_poly16x8 [] = { fff0, fff0, fff2, fff2, fff4, fff4, fff6, fff6,  }
+VBSL/VBSLQ:22:result_float32x4 [] = { c1800001, c1700001, c1600001, c1500001,  }
+VBSL/VBSLQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSHL/VSHLQ output:
+VSHL/VSHLQ:0:result_int8x8 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6, ffffffe8, ffffffea, ffffffec, ffffffee,  }
+VSHL/VSHLQ:1:result_int16x4 [] = { ffffff80, ffffff88, ffffff90, ffffff98,  }
+VSHL/VSHLQ:2:result_int32x2 [] = { fffff000, fffff100,  }
+VSHL/VSHLQ:3:result_int64x1 [] = { ffffffffffffff80,  }
+VSHL/VSHLQ:4:result_uint8x8 [] = { e0, e2, e4, e6, e8, ea, ec, ee,  }
+VSHL/VSHLQ:5:result_uint16x4 [] = { ff80, ff88, ff90, ff98,  }
+VSHL/VSHLQ:6:result_uint32x2 [] = { fffff000, fffff100,  }
+VSHL/VSHLQ:7:result_uint64x1 [] = { ffffffffffffff80,  }
+VSHL/VSHLQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHL/VSHLQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHL/VSHLQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSHL/VSHLQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSHL/VSHLQ:12:result_int8x16 [] = { 0, 20, 40, 60, ffffff80, ffffffa0, ffffffc0, ffffffe0, 0, 20, 40, 60, ffffff80, ffffffa0, ffffffc0, ffffffe0,  }
+VSHL/VSHLQ:13:result_int16x8 [] = { 0, 1000, 2000, 3000, 4000, 5000, 6000, 7000,  }
+VSHL/VSHLQ:14:result_int32x4 [] = { 0, 40000000, 80000000, c0000000,  }
+VSHL/VSHLQ:15:result_int64x2 [] = { 0, 8000000000000000,  }
+VSHL/VSHLQ:16:result_uint8x16 [] = { 0, 20, 40, 60, 80, a0, c0, e0, 0, 20, 40, 60, 80, a0, c0, e0,  }
+VSHL/VSHLQ:17:result_uint16x8 [] = { 0, 1000, 2000, 3000, 4000, 5000, 6000, 7000,  }
+VSHL/VSHLQ:18:result_uint32x4 [] = { 0, 40000000, 80000000, c0000000,  }
+VSHL/VSHLQ:19:result_uint64x2 [] = { 0, 8000000000000000,  }
+VSHL/VSHLQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHL/VSHLQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHL/VSHLQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSHL/VSHLQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSHL/VSHLQ (large shift amount) output:
+VSHL/VSHLQ:24:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VSHL/VSHLQ:25:result_int16x4 [] = { 0, 0, 0, 0,  }
+VSHL/VSHLQ:26:result_int32x2 [] = { 0, 0,  }
+VSHL/VSHLQ:27:result_int64x1 [] = { 0,  }
+VSHL/VSHLQ:28:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VSHL/VSHLQ:29:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VSHL/VSHLQ:30:result_uint32x2 [] = { 0, 0,  }
+VSHL/VSHLQ:31:result_uint64x1 [] = { 0,  }
+VSHL/VSHLQ:32:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHL/VSHLQ:33:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHL/VSHLQ:34:result_float32x2 [] = { 33333333, 33333333,  }
+VSHL/VSHLQ:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSHL/VSHLQ:36:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VSHL/VSHLQ:37:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VSHL/VSHLQ:38:result_int32x4 [] = { 0, 0, 0, 0,  }
+VSHL/VSHLQ:39:result_int64x2 [] = { 0, 0,  }
+VSHL/VSHLQ:40:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VSHL/VSHLQ:41:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VSHL/VSHLQ:42:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VSHL/VSHLQ:43:result_uint64x2 [] = { 0, 0,  }
+VSHL/VSHLQ:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHL/VSHLQ:45:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHL/VSHLQ:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSHL/VSHLQ:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSHL/VSHLQ (negative shift amount) output:
+VSHL/VSHLQ:48:result_int8x8 [] = { fffffff8, fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb,  }
+VSHL/VSHLQ:49:result_int16x4 [] = { fffffff8, fffffff8, fffffff9, fffffff9,  }
+VSHL/VSHLQ:50:result_int32x2 [] = { fffffffc, fffffffc,  }
+VSHL/VSHLQ:51:result_int64x1 [] = { ffffffffffffffff,  }
+VSHL/VSHLQ:52:result_uint8x8 [] = { 78, 78, 79, 79, 7a, 7a, 7b, 7b,  }
+VSHL/VSHLQ:53:result_uint16x4 [] = { 7ff8, 7ff8, 7ff9, 7ff9,  }
+VSHL/VSHLQ:54:result_uint32x2 [] = { 3ffffffc, 3ffffffc,  }
+VSHL/VSHLQ:55:result_uint64x1 [] = { fffffffffffffff,  }
+VSHL/VSHLQ:56:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHL/VSHLQ:57:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHL/VSHLQ:58:result_float32x2 [] = { 33333333, 33333333,  }
+VSHL/VSHLQ:59:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSHL/VSHLQ:60:result_int8x16 [] = { fffffffc, fffffffc, fffffffc, fffffffc, fffffffd, fffffffd, fffffffd, fffffffd, fffffffe, fffffffe, fffffffe, fffffffe, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VSHL/VSHLQ:61:result_int16x8 [] = { ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VSHL/VSHLQ:62:result_int32x4 [] = { fffffffe, fffffffe, fffffffe, fffffffe,  }
+VSHL/VSHLQ:63:result_int64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VSHL/VSHLQ:64:result_uint8x16 [] = { 3c, 3c, 3c, 3c, 3d, 3d, 3d, 3d, 3e, 3e, 3e, 3e, 3f, 3f, 3f, 3f,  }
+VSHL/VSHLQ:65:result_uint16x8 [] = { 7ff, 7ff, 7ff, 7ff, 7ff, 7ff, 7ff, 7ff,  }
+VSHL/VSHLQ:66:result_uint32x4 [] = { 1ffffffe, 1ffffffe, 1ffffffe, 1ffffffe,  }
+VSHL/VSHLQ:67:result_uint64x2 [] = { 7ffffffffffffff, 7ffffffffffffff,  }
+VSHL/VSHLQ:68:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHL/VSHLQ:69:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHL/VSHLQ:70:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSHL/VSHLQ:71:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSHL_N output:
+VSHL_N:0:result_int8x8 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6, ffffffe8, ffffffea, ffffffec, ffffffee,  }
+VSHL_N:1:result_int16x4 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6,  }
+VSHL_N:2:result_int32x2 [] = { ffffff80, ffffff88,  }
+VSHL_N:3:result_int64x1 [] = { ffffffffffffffc0,  }
+VSHL_N:4:result_uint8x8 [] = { c0, c4, c8, cc, d0, d4, d8, dc,  }
+VSHL_N:5:result_uint16x4 [] = { ff00, ff10, ff20, ff30,  }
+VSHL_N:6:result_uint32x2 [] = { ffffff80, ffffff88,  }
+VSHL_N:7:result_uint64x1 [] = { ffffffffffffffe0,  }
+VSHL_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHL_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHL_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSHL_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSHL_N:12:result_int8x16 [] = { 0, 20, 40, 60, ffffff80, ffffffa0, ffffffc0, ffffffe0, 0, 20, 40, 60, ffffff80, ffffffa0, ffffffc0, ffffffe0,  }
+VSHL_N:13:result_int16x8 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6, ffffffe8, ffffffea, ffffffec, ffffffee,  }
+VSHL_N:14:result_int32x4 [] = { ffffffc0, ffffffc4, ffffffc8, ffffffcc,  }
+VSHL_N:15:result_int64x2 [] = { ffffffffffffffc0, ffffffffffffffc4,  }
+VSHL_N:16:result_uint8x16 [] = { c0, c4, c8, cc, d0, d4, d8, dc, e0, e4, e8, ec, f0, f4, f8, fc,  }
+VSHL_N:17:result_uint16x8 [] = { ff80, ff88, ff90, ff98, ffa0, ffa8, ffb0, ffb8,  }
+VSHL_N:18:result_uint32x4 [] = { ffffffc0, ffffffc4, ffffffc8, ffffffcc,  }
+VSHL_N:19:result_uint64x2 [] = { ffffffffffffffe0, ffffffffffffffe2,  }
+VSHL_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHL_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHL_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSHL_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHL/VQSHLQ (with input = 0) cumulative saturation output:
+VQSHL/VQSHLQ:0:vqshl_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:1:vqshl_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:2:vqshl_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:3:vqshl_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:4:vqshl_u8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:5:vqshl_u16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:6:vqshl_u32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:7:vqshl_u64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:8:vqshlq_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:9:vqshlq_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:10:vqshlq_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:11:vqshlq_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:12:vqshlq_u8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:13:vqshlq_u16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:14:vqshlq_u32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:15:vqshlq_u64 Neon cumulative saturation 0
+
+VQSHL/VQSHLQ (with input = 0) output:
+VQSHL/VQSHLQ:16:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:17:result_int16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:18:result_int32x2 [] = { 0, 0,  }
+VQSHL/VQSHLQ:19:result_int64x1 [] = { 0,  }
+VQSHL/VQSHLQ:20:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:21:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:22:result_uint32x2 [] = { 0, 0,  }
+VQSHL/VQSHLQ:23:result_uint64x1 [] = { 0,  }
+VQSHL/VQSHLQ:24:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:25:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:26:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL/VQSHLQ:27:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:28:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:29:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:30:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:31:result_int64x2 [] = { 0, 0,  }
+VQSHL/VQSHLQ:32:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:33:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:34:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:35:result_uint64x2 [] = { 0, 0,  }
+VQSHL/VQSHLQ:36:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:37:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:38:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHL/VQSHLQ:39:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHL/VQSHLQ (input 0 and negative shift amount) cumulative saturation output:
+VQSHL/VQSHLQ:40:vqshl_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:41:vqshl_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:42:vqshl_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:43:vqshl_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:44:vqshl_u8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:45:vqshl_u16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:46:vqshl_u32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:47:vqshl_u64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:48:vqshlq_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:49:vqshlq_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:50:vqshlq_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:51:vqshlq_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:52:vqshlq_u8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:53:vqshlq_u16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:54:vqshlq_u32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:55:vqshlq_u64 Neon cumulative saturation 0
+
+VQSHL/VQSHLQ (input 0 and negative shift amount) output:
+VQSHL/VQSHLQ:56:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:57:result_int16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:58:result_int32x2 [] = { 0, 0,  }
+VQSHL/VQSHLQ:59:result_int64x1 [] = { 0,  }
+VQSHL/VQSHLQ:60:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:61:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:62:result_uint32x2 [] = { 0, 0,  }
+VQSHL/VQSHLQ:63:result_uint64x1 [] = { 0,  }
+VQSHL/VQSHLQ:64:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:65:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:66:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL/VQSHLQ:67:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:68:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:69:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:70:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:71:result_int64x2 [] = { 0, 0,  }
+VQSHL/VQSHLQ:72:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:73:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:74:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:75:result_uint64x2 [] = { 0, 0,  }
+VQSHL/VQSHLQ:76:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:77:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:78:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHL/VQSHLQ:79:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHL/VQSHLQ cumulative saturation output:
+VQSHL/VQSHLQ:80:vqshl_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:81:vqshl_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:82:vqshl_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:83:vqshl_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:84:vqshl_u8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:85:vqshl_u16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:86:vqshl_u32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:87:vqshl_u64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:88:vqshlq_s8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:89:vqshlq_s16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:90:vqshlq_s32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:91:vqshlq_s64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:92:vqshlq_u8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:93:vqshlq_u16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:94:vqshlq_u32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:95:vqshlq_u64 Neon cumulative saturation 1
+
+VQSHL/VQSHLQ output:
+VQSHL/VQSHLQ:96:result_int8x8 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6, ffffffe8, ffffffea, ffffffec, ffffffee,  }
+VQSHL/VQSHLQ:97:result_int16x4 [] = { ffffff80, ffffff88, ffffff90, ffffff98,  }
+VQSHL/VQSHLQ:98:result_int32x2 [] = { fffff000, fffff100,  }
+VQSHL/VQSHLQ:99:result_int64x1 [] = { fffffffffffffffe,  }
+VQSHL/VQSHLQ:100:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL/VQSHLQ:101:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHL/VQSHLQ:102:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:103:result_uint64x1 [] = { 1ffffffffffffffe,  }
+VQSHL/VQSHLQ:104:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:105:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:106:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL/VQSHLQ:107:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:108:result_int8x16 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQSHL/VQSHLQ:109:result_int16x8 [] = { ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQSHL/VQSHLQ:110:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VQSHL/VQSHLQ:111:result_int64x2 [] = { 8000000000000000, 8000000000000000,  }
+VQSHL/VQSHLQ:112:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL/VQSHLQ:113:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQSHL/VQSHLQ:114:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:115:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQSHL/VQSHLQ:116:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:117:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:118:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHL/VQSHLQ:119:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHL/VQSHLQ (negative shift amount) cumulative saturation output:
+VQSHL/VQSHLQ:120:vqshl_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:121:vqshl_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:122:vqshl_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:123:vqshl_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:124:vqshl_u8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:125:vqshl_u16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:126:vqshl_u32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:127:vqshl_u64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:128:vqshlq_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:129:vqshlq_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:130:vqshlq_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:131:vqshlq_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:132:vqshlq_u8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:133:vqshlq_u16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:134:vqshlq_u32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:135:vqshlq_u64 Neon cumulative saturation 0
+
+VQSHL/VQSHLQ (negative shift amount) output:
+VQSHL/VQSHLQ:136:result_int8x8 [] = { fffffff8, fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb,  }
+VQSHL/VQSHLQ:137:result_int16x4 [] = { fffffffc, fffffffc, fffffffc, fffffffc,  }
+VQSHL/VQSHLQ:138:result_int32x2 [] = { fffffffe, fffffffe,  }
+VQSHL/VQSHLQ:139:result_int64x1 [] = { ffffffffffffffff,  }
+VQSHL/VQSHLQ:140:result_uint8x8 [] = { 78, 78, 79, 79, 7a, 7a, 7b, 7b,  }
+VQSHL/VQSHLQ:141:result_uint16x4 [] = { 3ffc, 3ffc, 3ffc, 3ffc,  }
+VQSHL/VQSHLQ:142:result_uint32x2 [] = { 1ffffffe, 1ffffffe,  }
+VQSHL/VQSHLQ:143:result_uint64x1 [] = { fffffffffffffff,  }
+VQSHL/VQSHLQ:144:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:145:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:146:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL/VQSHLQ:147:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:148:result_int8x16 [] = { ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:149:result_int16x8 [] = { ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:150:result_int32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:151:result_int64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQSHL/VQSHLQ:152:result_uint8x16 [] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  }
+VQSHL/VQSHLQ:153:result_uint16x8 [] = { 1f, 1f, 1f, 1f, 1f, 1f, 1f, 1f,  }
+VQSHL/VQSHLQ:154:result_uint32x4 [] = { 7ffff, 7ffff, 7ffff, 7ffff,  }
+VQSHL/VQSHLQ:155:result_uint64x2 [] = { fffffffffff, fffffffffff,  }
+VQSHL/VQSHLQ:156:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:157:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:158:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHL/VQSHLQ:159:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHL/VQSHLQ (large shift amount, negative input) cumulative saturation output:
+VQSHL/VQSHLQ:160:vqshl_s8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:161:vqshl_s16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:162:vqshl_s32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:163:vqshl_s64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:164:vqshl_u8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:165:vqshl_u16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:166:vqshl_u32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:167:vqshl_u64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:168:vqshlq_s8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:169:vqshlq_s16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:170:vqshlq_s32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:171:vqshlq_s64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:172:vqshlq_u8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:173:vqshlq_u16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:174:vqshlq_u32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:175:vqshlq_u64 Neon cumulative saturation 1
+
+VQSHL/VQSHLQ (large shift amount, negative input) output:
+VQSHL/VQSHLQ:176:result_int8x8 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQSHL/VQSHLQ:177:result_int16x4 [] = { ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQSHL/VQSHLQ:178:result_int32x2 [] = { 80000000, 80000000,  }
+VQSHL/VQSHLQ:179:result_int64x1 [] = { 8000000000000000,  }
+VQSHL/VQSHLQ:180:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL/VQSHLQ:181:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHL/VQSHLQ:182:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:183:result_uint64x1 [] = { ffffffffffffffff,  }
+VQSHL/VQSHLQ:184:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:185:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:186:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL/VQSHLQ:187:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:188:result_int8x16 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQSHL/VQSHLQ:189:result_int16x8 [] = { ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQSHL/VQSHLQ:190:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VQSHL/VQSHLQ:191:result_int64x2 [] = { 8000000000000000, 8000000000000000,  }
+VQSHL/VQSHLQ:192:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL/VQSHLQ:193:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQSHL/VQSHLQ:194:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:195:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQSHL/VQSHLQ:196:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:197:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:198:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHL/VQSHLQ:199:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHL/VQSHLQ (check cumulative saturation) cumulative saturation output:
+VQSHL/VQSHLQ:200:vqshl_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:201:vqshl_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:202:vqshl_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:203:vqshl_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:204:vqshl_u8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:205:vqshl_u16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:206:vqshl_u32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:207:vqshl_u64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:208:vqshlq_s8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:209:vqshlq_s16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:210:vqshlq_s32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:211:vqshlq_s64 Neon cumulative saturation 0
+VQSHL/VQSHLQ:212:vqshlq_u8 Neon cumulative saturation 0
+VQSHL/VQSHLQ:213:vqshlq_u16 Neon cumulative saturation 0
+VQSHL/VQSHLQ:214:vqshlq_u32 Neon cumulative saturation 0
+VQSHL/VQSHLQ:215:vqshlq_u64 Neon cumulative saturation 0
+
+VQSHL/VQSHLQ (check cumulative saturation) output:
+VQSHL/VQSHLQ:216:result_int8x8 [] = { 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f,  }
+VQSHL/VQSHLQ:217:result_int16x4 [] = { 3fff, 3fff, 3fff, 3fff,  }
+VQSHL/VQSHLQ:218:result_int32x2 [] = { 3fffffff, 3fffffff,  }
+VQSHL/VQSHLQ:219:result_int64x1 [] = { 3fffffffffffffff,  }
+VQSHL/VQSHLQ:220:result_uint8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHL/VQSHLQ:221:result_uint16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQSHL/VQSHLQ:222:result_uint32x2 [] = { 7fffffff, 7fffffff,  }
+VQSHL/VQSHLQ:223:result_uint64x1 [] = { 7fffffffffffffff,  }
+VQSHL/VQSHLQ:224:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:225:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:226:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL/VQSHLQ:227:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:228:result_int8x16 [] = { 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f, 3f,  }
+VQSHL/VQSHLQ:229:result_int16x8 [] = { 3fff, 3fff, 3fff, 3fff, 3fff, 3fff, 3fff, 3fff,  }
+VQSHL/VQSHLQ:230:result_int32x4 [] = { 3fffffff, 3fffffff, 3fffffff, 3fffffff,  }
+VQSHL/VQSHLQ:231:result_int64x2 [] = { 3fffffffffffffff, 3fffffffffffffff,  }
+VQSHL/VQSHLQ:232:result_uint8x16 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHL/VQSHLQ:233:result_uint16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQSHL/VQSHLQ:234:result_uint32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQSHL/VQSHLQ:235:result_uint64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+VQSHL/VQSHLQ:236:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:237:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:238:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHL/VQSHLQ:239:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHL/VQSHLQ (large shift amount, positive input) cumulative saturation output:
+VQSHL/VQSHLQ:240:vqshl_s8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:241:vqshl_s16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:242:vqshl_s32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:243:vqshl_s64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:244:vqshl_u8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:245:vqshl_u16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:246:vqshl_u32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:247:vqshl_u64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:248:vqshlq_s8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:249:vqshlq_s16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:250:vqshlq_s32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:251:vqshlq_s64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:252:vqshlq_u8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:253:vqshlq_u16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:254:vqshlq_u32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:255:vqshlq_u64 Neon cumulative saturation 1
+
+VQSHL/VQSHLQ (large shift amount, positive input) output:
+VQSHL/VQSHLQ:256:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHL/VQSHLQ:257:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQSHL/VQSHLQ:258:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQSHL/VQSHLQ:259:result_int64x1 [] = { 7fffffffffffffff,  }
+VQSHL/VQSHLQ:260:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL/VQSHLQ:261:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHL/VQSHLQ:262:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:263:result_uint64x1 [] = { ffffffffffffffff,  }
+VQSHL/VQSHLQ:264:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:265:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:266:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL/VQSHLQ:267:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:268:result_int8x16 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHL/VQSHLQ:269:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQSHL/VQSHLQ:270:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQSHL/VQSHLQ:271:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+VQSHL/VQSHLQ:272:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL/VQSHLQ:273:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQSHL/VQSHLQ:274:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:275:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQSHL/VQSHLQ:276:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:277:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:278:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHL/VQSHLQ:279:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHL/VQSHLQ (check saturation on 64 bits) cumulative saturation output:
+VQSHL/VQSHLQ:280:vqshl_s8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:281:vqshl_s16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:282:vqshl_s32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:283:vqshl_s64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:284:vqshl_u8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:285:vqshl_u16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:286:vqshl_u32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:287:vqshl_u64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:288:vqshlq_s8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:289:vqshlq_s16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:290:vqshlq_s32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:291:vqshlq_s64 Neon cumulative saturation 1
+VQSHL/VQSHLQ:292:vqshlq_u8 Neon cumulative saturation 1
+VQSHL/VQSHLQ:293:vqshlq_u16 Neon cumulative saturation 1
+VQSHL/VQSHLQ:294:vqshlq_u32 Neon cumulative saturation 1
+VQSHL/VQSHLQ:295:vqshlq_u64 Neon cumulative saturation 1
+
+VQSHL/VQSHLQ (check saturation on 64 bits) output:
+VQSHL/VQSHLQ:296:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHL/VQSHLQ:297:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQSHL/VQSHLQ:298:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQSHL/VQSHLQ:299:result_int64x1 [] = { 8000000000000000,  }
+VQSHL/VQSHLQ:300:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL/VQSHLQ:301:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHL/VQSHLQ:302:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:303:result_uint64x1 [] = { ffffffffffffffff,  }
+VQSHL/VQSHLQ:304:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:305:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:306:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL/VQSHLQ:307:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHL/VQSHLQ:308:result_int8x16 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHL/VQSHLQ:309:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQSHL/VQSHLQ:310:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQSHL/VQSHLQ:311:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+VQSHL/VQSHLQ:312:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL/VQSHLQ:313:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQSHL/VQSHLQ:314:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL/VQSHLQ:315:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQSHL/VQSHLQ:316:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL/VQSHLQ:317:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL/VQSHLQ:318:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHL/VQSHLQ:319:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHL_N/VQSHLQ_N cumulative saturation output:
+VQSHL_N/VQSHLQ_N:0:vqshl_n_s8 Neon cumulative saturation 0
+VQSHL_N/VQSHLQ_N:1:vqshl_n_s16 Neon cumulative saturation 0
+VQSHL_N/VQSHLQ_N:2:vqshl_n_s32 Neon cumulative saturation 0
+VQSHL_N/VQSHLQ_N:3:vqshl_n_s64 Neon cumulative saturation 0
+VQSHL_N/VQSHLQ_N:4:vqshl_n_u8 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:5:vqshl_n_u16 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:6:vqshl_n_u32 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:7:vqshl_n_u64 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:8:vqshlq_n_s8 Neon cumulative saturation 0
+VQSHL_N/VQSHLQ_N:9:vqshlq_n_s16 Neon cumulative saturation 0
+VQSHL_N/VQSHLQ_N:10:vqshlq_n_s32 Neon cumulative saturation 0
+VQSHL_N/VQSHLQ_N:11:vqshlq_n_s64 Neon cumulative saturation 0
+VQSHL_N/VQSHLQ_N:12:vqshlq_n_u8 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:13:vqshlq_n_u16 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:14:vqshlq_n_u32 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:15:vqshlq_n_u64 Neon cumulative saturation 1
+
+VQSHL_N/VQSHLQ_N output:
+VQSHL_N/VQSHLQ_N:16:result_int8x8 [] = { ffffffc0, ffffffc4, ffffffc8, ffffffcc, ffffffd0, ffffffd4, ffffffd8, ffffffdc,  }
+VQSHL_N/VQSHLQ_N:17:result_int16x4 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6,  }
+VQSHL_N/VQSHLQ_N:18:result_int32x2 [] = { ffffffe0, ffffffe2,  }
+VQSHL_N/VQSHLQ_N:19:result_int64x1 [] = { ffffffffffffffc0,  }
+VQSHL_N/VQSHLQ_N:20:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL_N/VQSHLQ_N:21:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHL_N/VQSHLQ_N:22:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHL_N/VQSHLQ_N:23:result_uint64x1 [] = { ffffffffffffffff,  }
+VQSHL_N/VQSHLQ_N:24:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL_N/VQSHLQ_N:25:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL_N/VQSHLQ_N:26:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL_N/VQSHLQ_N:27:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHL_N/VQSHLQ_N:28:result_int8x16 [] = { ffffffc0, ffffffc4, ffffffc8, ffffffcc, ffffffd0, ffffffd4, ffffffd8, ffffffdc, ffffffe0, ffffffe4, ffffffe8, ffffffec, fffffff0, fffffff4, fffffff8, fffffffc,  }
+VQSHL_N/VQSHLQ_N:29:result_int16x8 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6, ffffffe8, ffffffea, ffffffec, ffffffee,  }
+VQSHL_N/VQSHLQ_N:30:result_int32x4 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6,  }
+VQSHL_N/VQSHLQ_N:31:result_int64x2 [] = { ffffffffffffffc0, ffffffffffffffc4,  }
+VQSHL_N/VQSHLQ_N:32:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL_N/VQSHLQ_N:33:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQSHL_N/VQSHLQ_N:34:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL_N/VQSHLQ_N:35:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQSHL_N/VQSHLQ_N:36:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL_N/VQSHLQ_N:37:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL_N/VQSHLQ_N:38:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHL_N/VQSHLQ_N:39:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHL_N/VQSHLQ_N (check saturation with large positive input) cumulative saturation output:
+VQSHL_N/VQSHLQ_N:40:vqshl_n_s8 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:41:vqshl_n_s16 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:42:vqshl_n_s32 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:43:vqshl_n_s64 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:44:vqshl_n_u8 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:45:vqshl_n_u16 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:46:vqshl_n_u32 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:47:vqshl_n_u64 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:48:vqshlq_n_s8 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:49:vqshlq_n_s16 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:50:vqshlq_n_s32 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:51:vqshlq_n_s64 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:52:vqshlq_n_u8 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:53:vqshlq_n_u16 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:54:vqshlq_n_u32 Neon cumulative saturation 1
+VQSHL_N/VQSHLQ_N:55:vqshlq_n_u64 Neon cumulative saturation 1
+
+VQSHL_N/VQSHLQ_N (check saturation with large positive input) output:
+VQSHL_N/VQSHLQ_N:56:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHL_N/VQSHLQ_N:57:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQSHL_N/VQSHLQ_N:58:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQSHL_N/VQSHLQ_N:59:result_int64x1 [] = { 7fffffffffffffff,  }
+VQSHL_N/VQSHLQ_N:60:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL_N/VQSHLQ_N:61:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHL_N/VQSHLQ_N:62:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHL_N/VQSHLQ_N:63:result_uint64x1 [] = { ffffffffffffffff,  }
+VQSHL_N/VQSHLQ_N:64:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL_N/VQSHLQ_N:65:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHL_N/VQSHLQ_N:66:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHL_N/VQSHLQ_N:67:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHL_N/VQSHLQ_N:68:result_int8x16 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHL_N/VQSHLQ_N:69:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQSHL_N/VQSHLQ_N:70:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQSHL_N/VQSHLQ_N:71:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+VQSHL_N/VQSHLQ_N:72:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHL_N/VQSHLQ_N:73:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQSHL_N/VQSHLQ_N:74:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHL_N/VQSHLQ_N:75:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQSHL_N/VQSHLQ_N:76:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHL_N/VQSHLQ_N:77:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHL_N/VQSHLQ_N:78:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHL_N/VQSHLQ_N:79:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHL/VRSHLQ (with input = 0) output:
+VRSHL/VRSHLQ:0:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:1:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:2:result_int32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:3:result_int64x1 [] = { 0,  }
+VRSHL/VRSHLQ:4:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:5:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:6:result_uint32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:7:result_uint64x1 [] = { 0,  }
+VRSHL/VRSHLQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:12:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:13:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:14:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:15:result_int64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:16:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:17:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:18:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:19:result_uint64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHL/VRSHLQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHL/VRSHLQ (input 0 and negative shift amount) output:
+VRSHL/VRSHLQ:24:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:25:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:26:result_int32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:27:result_int64x1 [] = { 0,  }
+VRSHL/VRSHLQ:28:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:29:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:30:result_uint32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:31:result_uint64x1 [] = { 0,  }
+VRSHL/VRSHLQ:32:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:33:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:34:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:36:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:37:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:38:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:39:result_int64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:40:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:41:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:42:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:43:result_uint64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:45:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHL/VRSHLQ:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHL/VRSHLQ output:
+VRSHL/VRSHLQ:48:result_int8x8 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6, ffffffe8, ffffffea, ffffffec, ffffffee,  }
+VRSHL/VRSHLQ:49:result_int16x4 [] = { ffffff80, ffffff88, ffffff90, ffffff98,  }
+VRSHL/VRSHLQ:50:result_int32x2 [] = { fffff000, fffff100,  }
+VRSHL/VRSHLQ:51:result_int64x1 [] = { fffffffffffffffe,  }
+VRSHL/VRSHLQ:52:result_uint8x8 [] = { e0, e2, e4, e6, e8, ea, ec, ee,  }
+VRSHL/VRSHLQ:53:result_uint16x4 [] = { ff80, ff88, ff90, ff98,  }
+VRSHL/VRSHLQ:54:result_uint32x2 [] = { fffff000, fffff100,  }
+VRSHL/VRSHLQ:55:result_uint64x1 [] = { 1ffffffffffffffe,  }
+VRSHL/VRSHLQ:56:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:57:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:58:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:59:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:60:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:61:result_int16x8 [] = { 0, 1000, 2000, 3000, 4000, 5000, 6000, 7000,  }
+VRSHL/VRSHLQ:62:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:63:result_int64x2 [] = { 0, 8000000000000000,  }
+VRSHL/VRSHLQ:64:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:65:result_uint16x8 [] = { 0, 1000, 2000, 3000, 4000, 5000, 6000, 7000,  }
+VRSHL/VRSHLQ:66:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:67:result_uint64x2 [] = { 0, 8000000000000000,  }
+VRSHL/VRSHLQ:68:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:69:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:70:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHL/VRSHLQ:71:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHL/VRSHLQ (negative shift amount) output:
+VRSHL/VRSHLQ:72:result_int8x8 [] = { fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb, fffffffc,  }
+VRSHL/VRSHLQ:73:result_int16x4 [] = { fffffffc, fffffffc, fffffffd, fffffffd,  }
+VRSHL/VRSHLQ:74:result_int32x2 [] = { fffffffe, fffffffe,  }
+VRSHL/VRSHLQ:75:result_int64x1 [] = { ffffffffffffffff,  }
+VRSHL/VRSHLQ:76:result_uint8x8 [] = { 78, 79, 79, 7a, 7a, 7b, 7b, 7c,  }
+VRSHL/VRSHLQ:77:result_uint16x4 [] = { 3ffc, 3ffc, 3ffd, 3ffd,  }
+VRSHL/VRSHLQ:78:result_uint32x2 [] = { 1ffffffe, 1ffffffe,  }
+VRSHL/VRSHLQ:79:result_uint64x1 [] = { fffffffffffffff,  }
+VRSHL/VRSHLQ:80:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:81:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:82:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:83:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:84:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:85:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:86:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:87:result_int64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:88:result_uint8x16 [] = { 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,  }
+VRSHL/VRSHLQ:89:result_uint16x8 [] = { 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSHL/VRSHLQ:90:result_uint32x4 [] = { 80000, 80000, 80000, 80000,  }
+VRSHL/VRSHLQ:91:result_uint64x2 [] = { 100000000000, 100000000000,  }
+VRSHL/VRSHLQ:92:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:93:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:94:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHL/VRSHLQ:95:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHL/VRSHLQ (checking round_const overflow: shift by -1) output:
+VRSHL/VRSHLQ:96:result_int8x8 [] = { 40, 40, 40, 40, 40, 40, 40, 40,  }
+VRSHL/VRSHLQ:97:result_int16x4 [] = { 4000, 4000, 4000, 4000,  }
+VRSHL/VRSHLQ:98:result_int32x2 [] = { 40000000, 40000000,  }
+VRSHL/VRSHLQ:99:result_int64x1 [] = { 4000000000000000,  }
+VRSHL/VRSHLQ:100:result_uint8x8 [] = { 80, 80, 80, 80, 80, 80, 80, 80,  }
+VRSHL/VRSHLQ:101:result_uint16x4 [] = { 8000, 8000, 8000, 8000,  }
+VRSHL/VRSHLQ:102:result_uint32x2 [] = { 80000000, 80000000,  }
+VRSHL/VRSHLQ:103:result_uint64x1 [] = { 8000000000000000,  }
+VRSHL/VRSHLQ:104:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:105:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:106:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:107:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:108:result_int8x16 [] = { 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40,  }
+VRSHL/VRSHLQ:109:result_int16x8 [] = { 4000, 4000, 4000, 4000, 4000, 4000, 4000, 4000,  }
+VRSHL/VRSHLQ:110:result_int32x4 [] = { 40000000, 40000000, 40000000, 40000000,  }
+VRSHL/VRSHLQ:111:result_int64x2 [] = { 4000000000000000, 4000000000000000,  }
+VRSHL/VRSHLQ:112:result_uint8x16 [] = { 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80,  }
+VRSHL/VRSHLQ:113:result_uint16x8 [] = { 8000, 8000, 8000, 8000, 8000, 8000, 8000, 8000,  }
+VRSHL/VRSHLQ:114:result_uint32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VRSHL/VRSHLQ:115:result_uint64x2 [] = { 8000000000000000, 8000000000000000,  }
+VRSHL/VRSHLQ:116:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:117:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:118:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHL/VRSHLQ:119:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHL/VRSHLQ (checking round_const overflow: shift by -3) output:
+VRSHL/VRSHLQ:120:result_int8x8 [] = { 10, 10, 10, 10, 10, 10, 10, 10,  }
+VRSHL/VRSHLQ:121:result_int16x4 [] = { 1000, 1000, 1000, 1000,  }
+VRSHL/VRSHLQ:122:result_int32x2 [] = { 10000000, 10000000,  }
+VRSHL/VRSHLQ:123:result_int64x1 [] = { 1000000000000000,  }
+VRSHL/VRSHLQ:124:result_uint8x8 [] = { 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSHL/VRSHLQ:125:result_uint16x4 [] = { 2000, 2000, 2000, 2000,  }
+VRSHL/VRSHLQ:126:result_uint32x2 [] = { 20000000, 20000000,  }
+VRSHL/VRSHLQ:127:result_uint64x1 [] = { 2000000000000000,  }
+VRSHL/VRSHLQ:128:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:129:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:130:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:131:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:132:result_int8x16 [] = { 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10,  }
+VRSHL/VRSHLQ:133:result_int16x8 [] = { 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000,  }
+VRSHL/VRSHLQ:134:result_int32x4 [] = { 10000000, 10000000, 10000000, 10000000,  }
+VRSHL/VRSHLQ:135:result_int64x2 [] = { 1000000000000000, 1000000000000000,  }
+VRSHL/VRSHLQ:136:result_uint8x16 [] = { 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSHL/VRSHLQ:137:result_uint16x8 [] = { 2000, 2000, 2000, 2000, 2000, 2000, 2000, 2000,  }
+VRSHL/VRSHLQ:138:result_uint32x4 [] = { 20000000, 20000000, 20000000, 20000000,  }
+VRSHL/VRSHLQ:139:result_uint64x2 [] = { 2000000000000000, 2000000000000000,  }
+VRSHL/VRSHLQ:140:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:141:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:142:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHL/VRSHLQ:143:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHL/VRSHLQ (checking negative shift amount as large as input vector width) output:
+VRSHL/VRSHLQ:144:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:145:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:146:result_int32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:147:result_int64x1 [] = { 0,  }
+VRSHL/VRSHLQ:148:result_uint8x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSHL/VRSHLQ:149:result_uint16x4 [] = { 1, 1, 1, 1,  }
+VRSHL/VRSHLQ:150:result_uint32x2 [] = { 1, 1,  }
+VRSHL/VRSHLQ:151:result_uint64x1 [] = { 1,  }
+VRSHL/VRSHLQ:152:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:153:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:154:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:155:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:156:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:157:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:158:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:159:result_int64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:160:result_uint8x16 [] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSHL/VRSHLQ:161:result_uint16x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSHL/VRSHLQ:162:result_uint32x4 [] = { 1, 1, 1, 1,  }
+VRSHL/VRSHLQ:163:result_uint64x2 [] = { 1, 1,  }
+VRSHL/VRSHLQ:164:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:165:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:166:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHL/VRSHLQ:167:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHL/VRSHLQ (large shift amount) output:
+VRSHL/VRSHLQ:168:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:169:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:170:result_int32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:171:result_int64x1 [] = { 0,  }
+VRSHL/VRSHLQ:172:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:173:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:174:result_uint32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:175:result_uint64x1 [] = { 0,  }
+VRSHL/VRSHLQ:176:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:177:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:178:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:179:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:180:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:181:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:182:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:183:result_int64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:184:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:185:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:186:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:187:result_uint64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:188:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:189:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:190:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHL/VRSHLQ:191:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHL/VRSHLQ (large negative shift amount) output:
+VRSHL/VRSHLQ:192:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:193:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:194:result_int32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:195:result_int64x1 [] = { 0,  }
+VRSHL/VRSHLQ:196:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:197:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:198:result_uint32x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:199:result_uint64x1 [] = { 0,  }
+VRSHL/VRSHLQ:200:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:201:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:202:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHL/VRSHLQ:203:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:204:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:205:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:206:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:207:result_int64x2 [] = { 0, 0,  }
+VRSHL/VRSHLQ:208:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHL/VRSHLQ:209:result_uint16x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSHL/VRSHLQ:210:result_uint32x4 [] = { 1, 1, 1, 1,  }
+VRSHL/VRSHLQ:211:result_uint64x2 [] = { 1, 1,  }
+VRSHL/VRSHLQ:212:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHL/VRSHLQ:213:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHL/VRSHLQ:214:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHL/VRSHLQ:215:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VLD2/VLD2Q chunk 0 output:
+VLD2/VLD2Q:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD2/VLD2Q:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD2/VLD2Q:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD2/VLD2Q:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD2/VLD2Q:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VLD2/VLD2Q:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD2/VLD2Q:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD2/VLD2Q:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD2/VLD2Q:8:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VLD2/VLD2Q:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD2/VLD2Q:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD2/VLD2Q:11:result_float16x4 [] = { cc00, cb80, cb00, ca80,  }
+VLD2/VLD2Q:12:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD2/VLD2Q:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD2/VLD2Q:14:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD2/VLD2Q:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2/VLD2Q:16:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD2/VLD2Q:17:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VLD2/VLD2Q:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD2/VLD2Q:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2/VLD2Q:20:result_poly8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD2/VLD2Q:21:result_poly16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VLD2/VLD2Q:22:result_float32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+VLD2/VLD2Q:23:result_float16x8 [] = { cc00, cb80, cb00, ca80, ca00, c980, c900, c880,  }
+
+VLD2/VLD2Q chunk 1 output:
+VLD2/VLD2Q:24:result_int8x8 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD2/VLD2Q:25:result_int16x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD2/VLD2Q:26:result_int32x2 [] = { fffffff2, fffffff3,  }
+VLD2/VLD2Q:27:result_int64x1 [] = { fffffffffffffff1,  }
+VLD2/VLD2Q:28:result_uint8x8 [] = { f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD2/VLD2Q:29:result_uint16x4 [] = { fff4, fff5, fff6, fff7,  }
+VLD2/VLD2Q:30:result_uint32x2 [] = { fffffff2, fffffff3,  }
+VLD2/VLD2Q:31:result_uint64x1 [] = { fffffffffffffff1,  }
+VLD2/VLD2Q:32:result_poly8x8 [] = { f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD2/VLD2Q:33:result_poly16x4 [] = { fff4, fff5, fff6, fff7,  }
+VLD2/VLD2Q:34:result_float32x2 [] = { c1600000, c1500000,  }
+VLD2/VLD2Q:35:result_float16x4 [] = { ca00, c980, c900, c880,  }
+VLD2/VLD2Q:36:result_int8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD2/VLD2Q:37:result_int16x8 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD2/VLD2Q:38:result_int32x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD2/VLD2Q:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2/VLD2Q:40:result_uint8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD2/VLD2Q:41:result_uint16x8 [] = { fff8, fff9, fffa, fffb, fffc, fffd, fffe, ffff,  }
+VLD2/VLD2Q:42:result_uint32x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD2/VLD2Q:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2/VLD2Q:44:result_poly8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD2/VLD2Q:45:result_poly16x8 [] = { fff8, fff9, fffa, fffb, fffc, fffd, fffe, ffff,  }
+VLD2/VLD2Q:46:result_float32x4 [] = { c1400000, c1300000, c1200000, c1100000,  }
+VLD2/VLD2Q:47:result_float16x8 [] = { c800, c700, c600, c500, c400, c200, c000, bc00,  }
+
+VLD3/VLD3Q chunk 0 output:
+VLD3/VLD3Q:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD3/VLD3Q:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD3/VLD3Q:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD3/VLD3Q:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD3/VLD3Q:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VLD3/VLD3Q:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD3/VLD3Q:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD3/VLD3Q:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD3/VLD3Q:8:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VLD3/VLD3Q:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD3/VLD3Q:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD3/VLD3Q:11:result_float16x4 [] = { cc00, cb80, cb00, ca80,  }
+VLD3/VLD3Q:12:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD3/VLD3Q:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD3/VLD3Q:14:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD3/VLD3Q:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3/VLD3Q:16:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD3/VLD3Q:17:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VLD3/VLD3Q:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD3/VLD3Q:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3/VLD3Q:20:result_poly8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD3/VLD3Q:21:result_poly16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VLD3/VLD3Q:22:result_float32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+VLD3/VLD3Q:23:result_float16x8 [] = { cc00, cb80, cb00, ca80, ca00, c980, c900, c880,  }
+
+VLD3/VLD3Q chunk 1 output:
+VLD3/VLD3Q:24:result_int8x8 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD3/VLD3Q:25:result_int16x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD3/VLD3Q:26:result_int32x2 [] = { fffffff2, fffffff3,  }
+VLD3/VLD3Q:27:result_int64x1 [] = { fffffffffffffff1,  }
+VLD3/VLD3Q:28:result_uint8x8 [] = { f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD3/VLD3Q:29:result_uint16x4 [] = { fff4, fff5, fff6, fff7,  }
+VLD3/VLD3Q:30:result_uint32x2 [] = { fffffff2, fffffff3,  }
+VLD3/VLD3Q:31:result_uint64x1 [] = { fffffffffffffff1,  }
+VLD3/VLD3Q:32:result_poly8x8 [] = { f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD3/VLD3Q:33:result_poly16x4 [] = { fff4, fff5, fff6, fff7,  }
+VLD3/VLD3Q:34:result_float32x2 [] = { c1600000, c1500000,  }
+VLD3/VLD3Q:35:result_float16x4 [] = { ca00, c980, c900, c880,  }
+VLD3/VLD3Q:36:result_int8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD3/VLD3Q:37:result_int16x8 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD3/VLD3Q:38:result_int32x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD3/VLD3Q:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3/VLD3Q:40:result_uint8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD3/VLD3Q:41:result_uint16x8 [] = { fff8, fff9, fffa, fffb, fffc, fffd, fffe, ffff,  }
+VLD3/VLD3Q:42:result_uint32x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD3/VLD3Q:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3/VLD3Q:44:result_poly8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD3/VLD3Q:45:result_poly16x8 [] = { fff8, fff9, fffa, fffb, fffc, fffd, fffe, ffff,  }
+VLD3/VLD3Q:46:result_float32x4 [] = { c1400000, c1300000, c1200000, c1100000,  }
+VLD3/VLD3Q:47:result_float16x8 [] = { c800, c700, c600, c500, c400, c200, c000, bc00,  }
+
+VLD3/VLD3Q chunk 2 output:
+VLD3/VLD3Q:48:result_int8x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD3/VLD3Q:49:result_int16x4 [] = { fffffff8, fffffff9, fffffffa, fffffffb,  }
+VLD3/VLD3Q:50:result_int32x2 [] = { fffffff4, fffffff5,  }
+VLD3/VLD3Q:51:result_int64x1 [] = { fffffffffffffff2,  }
+VLD3/VLD3Q:52:result_uint8x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD3/VLD3Q:53:result_uint16x4 [] = { fff8, fff9, fffa, fffb,  }
+VLD3/VLD3Q:54:result_uint32x2 [] = { fffffff4, fffffff5,  }
+VLD3/VLD3Q:55:result_uint64x1 [] = { fffffffffffffff2,  }
+VLD3/VLD3Q:56:result_poly8x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD3/VLD3Q:57:result_poly16x4 [] = { fff8, fff9, fffa, fffb,  }
+VLD3/VLD3Q:58:result_float32x2 [] = { c1400000, c1300000,  }
+VLD3/VLD3Q:59:result_float16x4 [] = { c800, c700, c600, c500,  }
+VLD3/VLD3Q:60:result_int8x16 [] = { 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 1a, 1b, 1c, 1d, 1e, 1f,  }
+VLD3/VLD3Q:61:result_int16x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD3/VLD3Q:62:result_int32x4 [] = { fffffff8, fffffff9, fffffffa, fffffffb,  }
+VLD3/VLD3Q:63:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3/VLD3Q:64:result_uint8x16 [] = { 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 1a, 1b, 1c, 1d, 1e, 1f,  }
+VLD3/VLD3Q:65:result_uint16x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD3/VLD3Q:66:result_uint32x4 [] = { fffffff8, fffffff9, fffffffa, fffffffb,  }
+VLD3/VLD3Q:67:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3/VLD3Q:68:result_poly8x16 [] = { 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 1a, 1b, 1c, 1d, 1e, 1f,  }
+VLD3/VLD3Q:69:result_poly16x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD3/VLD3Q:70:result_float32x4 [] = { c1000000, c0e00000, c0c00000, c0a00000,  }
+VLD3/VLD3Q:71:result_float16x8 [] = { 0, 3c00, 4000, 4200, 4400, 4500, 4600, 4700,  }
+
+VLD4/VLD4Q chunk 0 output:
+VLD4/VLD4Q:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD4/VLD4Q:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4/VLD4Q:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD4/VLD4Q:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD4/VLD4Q:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VLD4/VLD4Q:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4/VLD4Q:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD4/VLD4Q:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD4/VLD4Q:8:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VLD4/VLD4Q:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4/VLD4Q:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD4/VLD4Q:11:result_float16x4 [] = { cc00, cb80, cb00, ca80,  }
+VLD4/VLD4Q:12:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD4/VLD4Q:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD4/VLD4Q:14:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4/VLD4Q:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4/VLD4Q:16:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD4/VLD4Q:17:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VLD4/VLD4Q:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4/VLD4Q:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4/VLD4Q:20:result_poly8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD4/VLD4Q:21:result_poly16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VLD4/VLD4Q:22:result_float32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+VLD4/VLD4Q:23:result_float16x8 [] = { cc00, cb80, cb00, ca80, ca00, c980, c900, c880,  }
+
+VLD4/VLD4Q chunk 1 output:
+VLD4/VLD4Q:24:result_int8x8 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD4/VLD4Q:25:result_int16x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD4/VLD4Q:26:result_int32x2 [] = { fffffff2, fffffff3,  }
+VLD4/VLD4Q:27:result_int64x1 [] = { fffffffffffffff1,  }
+VLD4/VLD4Q:28:result_uint8x8 [] = { f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD4/VLD4Q:29:result_uint16x4 [] = { fff4, fff5, fff6, fff7,  }
+VLD4/VLD4Q:30:result_uint32x2 [] = { fffffff2, fffffff3,  }
+VLD4/VLD4Q:31:result_uint64x1 [] = { fffffffffffffff1,  }
+VLD4/VLD4Q:32:result_poly8x8 [] = { f8, f9, fa, fb, fc, fd, fe, ff,  }
+VLD4/VLD4Q:33:result_poly16x4 [] = { fff4, fff5, fff6, fff7,  }
+VLD4/VLD4Q:34:result_float32x2 [] = { c1600000, c1500000,  }
+VLD4/VLD4Q:35:result_float16x4 [] = { ca00, c980, c900, c880,  }
+VLD4/VLD4Q:36:result_int8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:37:result_int16x8 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD4/VLD4Q:38:result_int32x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD4/VLD4Q:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4/VLD4Q:40:result_uint8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:41:result_uint16x8 [] = { fff8, fff9, fffa, fffb, fffc, fffd, fffe, ffff,  }
+VLD4/VLD4Q:42:result_uint32x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VLD4/VLD4Q:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4/VLD4Q:44:result_poly8x16 [] = { 0, 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:45:result_poly16x8 [] = { fff8, fff9, fffa, fffb, fffc, fffd, fffe, ffff,  }
+VLD4/VLD4Q:46:result_float32x4 [] = { c1400000, c1300000, c1200000, c1100000,  }
+VLD4/VLD4Q:47:result_float16x8 [] = { c800, c700, c600, c500, c400, c200, c000, bc00,  }
+
+VLD4/VLD4Q chunk 2 output:
+VLD4/VLD4Q:48:result_int8x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD4/VLD4Q:49:result_int16x4 [] = { fffffff8, fffffff9, fffffffa, fffffffb,  }
+VLD4/VLD4Q:50:result_int32x2 [] = { fffffff4, fffffff5,  }
+VLD4/VLD4Q:51:result_int64x1 [] = { fffffffffffffff2,  }
+VLD4/VLD4Q:52:result_uint8x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD4/VLD4Q:53:result_uint16x4 [] = { fff8, fff9, fffa, fffb,  }
+VLD4/VLD4Q:54:result_uint32x2 [] = { fffffff4, fffffff5,  }
+VLD4/VLD4Q:55:result_uint64x1 [] = { fffffffffffffff2,  }
+VLD4/VLD4Q:56:result_poly8x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD4/VLD4Q:57:result_poly16x4 [] = { fff8, fff9, fffa, fffb,  }
+VLD4/VLD4Q:58:result_float32x2 [] = { c1400000, c1300000,  }
+VLD4/VLD4Q:59:result_float16x4 [] = { c800, c700, c600, c500,  }
+VLD4/VLD4Q:60:result_int8x16 [] = { 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 1a, 1b, 1c, 1d, 1e, 1f,  }
+VLD4/VLD4Q:61:result_int16x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD4/VLD4Q:62:result_int32x4 [] = { fffffff8, fffffff9, fffffffa, fffffffb,  }
+VLD4/VLD4Q:63:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4/VLD4Q:64:result_uint8x16 [] = { 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 1a, 1b, 1c, 1d, 1e, 1f,  }
+VLD4/VLD4Q:65:result_uint16x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD4/VLD4Q:66:result_uint32x4 [] = { fffffff8, fffffff9, fffffffa, fffffffb,  }
+VLD4/VLD4Q:67:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4/VLD4Q:68:result_poly8x16 [] = { 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 1a, 1b, 1c, 1d, 1e, 1f,  }
+VLD4/VLD4Q:69:result_poly16x8 [] = { 0, 1, 2, 3, 4, 5, 6, 7,  }
+VLD4/VLD4Q:70:result_float32x4 [] = { c1000000, c0e00000, c0c00000, c0a00000,  }
+VLD4/VLD4Q:71:result_float16x8 [] = { 0, 3c00, 4000, 4200, 4400, 4500, 4600, 4700,  }
+
+VLD4/VLD4Q chunk 3 output:
+VLD4/VLD4Q:72:result_int8x8 [] = { 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:73:result_int16x4 [] = { fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD4/VLD4Q:74:result_int32x2 [] = { fffffff6, fffffff7,  }
+VLD4/VLD4Q:75:result_int64x1 [] = { fffffffffffffff3,  }
+VLD4/VLD4Q:76:result_uint8x8 [] = { 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:77:result_uint16x4 [] = { fffc, fffd, fffe, ffff,  }
+VLD4/VLD4Q:78:result_uint32x2 [] = { fffffff6, fffffff7,  }
+VLD4/VLD4Q:79:result_uint64x1 [] = { fffffffffffffff3,  }
+VLD4/VLD4Q:80:result_poly8x8 [] = { 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:81:result_poly16x4 [] = { fffc, fffd, fffe, ffff,  }
+VLD4/VLD4Q:82:result_float32x2 [] = { c1200000, c1100000,  }
+VLD4/VLD4Q:83:result_float16x4 [] = { c400, c200, c000, bc00,  }
+VLD4/VLD4Q:84:result_int8x16 [] = { 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 2a, 2b, 2c, 2d, 2e, 2f,  }
+VLD4/VLD4Q:85:result_int16x8 [] = { 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:86:result_int32x4 [] = { fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD4/VLD4Q:87:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4/VLD4Q:88:result_uint8x16 [] = { 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 2a, 2b, 2c, 2d, 2e, 2f,  }
+VLD4/VLD4Q:89:result_uint16x8 [] = { 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:90:result_uint32x4 [] = { fffffffc, fffffffd, fffffffe, ffffffff,  }
+VLD4/VLD4Q:91:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4/VLD4Q:92:result_poly8x16 [] = { 20, 21, 22, 23, 24, 25, 26, 27, 28, 29, 2a, 2b, 2c, 2d, 2e, 2f,  }
+VLD4/VLD4Q:93:result_poly16x8 [] = { 8, 9, a, b, c, d, e, f,  }
+VLD4/VLD4Q:94:result_float32x4 [] = { c0800000, c0400000, c0000000, bf800000,  }
+VLD4/VLD4Q:95:result_float16x8 [] = { 4800, 4880, 4900, 4980, 4a00, 4a80, 4b00, 4b80,  }
+
+VDUP_LANE/VDUP_LANEQ output:
+VDUP_LANE/VDUP_LANEQ:0:result_int8x8 [] = { fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1, fffffff1,  }
+VDUP_LANE/VDUP_LANEQ:1:result_int16x4 [] = { fffffff2, fffffff2, fffffff2, fffffff2,  }
+VDUP_LANE/VDUP_LANEQ:2:result_int32x2 [] = { fffffff1, fffffff1,  }
+VDUP_LANE/VDUP_LANEQ:3:result_int64x1 [] = { fffffffffffffff0,  }
+VDUP_LANE/VDUP_LANEQ:4:result_uint8x8 [] = { f7, f7, f7, f7, f7, f7, f7, f7,  }
+VDUP_LANE/VDUP_LANEQ:5:result_uint16x4 [] = { fff3, fff3, fff3, fff3,  }
+VDUP_LANE/VDUP_LANEQ:6:result_uint32x2 [] = { fffffff1, fffffff1,  }
+VDUP_LANE/VDUP_LANEQ:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VDUP_LANE/VDUP_LANEQ:8:result_poly8x8 [] = { f7, f7, f7, f7, f7, f7, f7, f7,  }
+VDUP_LANE/VDUP_LANEQ:9:result_poly16x4 [] = { fff3, fff3, fff3, fff3,  }
+VDUP_LANE/VDUP_LANEQ:10:result_float32x2 [] = { c1700000, c1700000,  }
+VDUP_LANE/VDUP_LANEQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VDUP_LANE/VDUP_LANEQ:12:result_int8x16 [] = { fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2, fffffff2,  }
+VDUP_LANE/VDUP_LANEQ:13:result_int16x8 [] = { fffffff3, fffffff3, fffffff3, fffffff3, fffffff3, fffffff3, fffffff3, fffffff3,  }
+VDUP_LANE/VDUP_LANEQ:14:result_int32x4 [] = { fffffff1, fffffff1, fffffff1, fffffff1,  }
+VDUP_LANE/VDUP_LANEQ:15:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VDUP_LANE/VDUP_LANEQ:16:result_uint8x16 [] = { f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5,  }
+VDUP_LANE/VDUP_LANEQ:17:result_uint16x8 [] = { fff1, fff1, fff1, fff1, fff1, fff1, fff1, fff1,  }
+VDUP_LANE/VDUP_LANEQ:18:result_uint32x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VDUP_LANE/VDUP_LANEQ:19:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VDUP_LANE/VDUP_LANEQ:20:result_poly8x16 [] = { f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5, f5,  }
+VDUP_LANE/VDUP_LANEQ:21:result_poly16x8 [] = { fff1, fff1, fff1, fff1, fff1, fff1, fff1, fff1,  }
+VDUP_LANE/VDUP_LANEQ:22:result_float32x4 [] = { c1700000, c1700000, c1700000, c1700000,  }
+VDUP_LANE/VDUP_LANEQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQDMULL_LANE cumulative saturation output:
+VQDMULL_LANE:0:vqdmull_lane_s16 Neon cumulative saturation 0
+VQDMULL_LANE:1:vqdmull_lane_s32 Neon cumulative saturation 0
+
+VQDMULL_LANE output:
+VQDMULL_LANE:2:result_int32x4 [] = { 8000, 8000, 8000, 8000,  }
+VQDMULL_LANE:3:result_int64x2 [] = { 4000, 4000,  }
+
+VQDMULL_LANE (check mul cumulative saturation) cumulative saturation output:
+VQDMULL_LANE:4:vqdmull_lane_s16 Neon cumulative saturation 1
+VQDMULL_LANE:5:vqdmull_lane_s32 Neon cumulative saturation 1
+
+VQDMULL_LANE (check mul cumulative saturation) output:
+VQDMULL_LANE:6:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQDMULL_LANE:7:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+
+VQDMULL_N cumulative saturation output:
+VQDMULL_N:0:vqdmull_n_s16 Neon cumulative saturation 0
+VQDMULL_N:1:vqdmull_n_s32 Neon cumulative saturation 0
+
+VQDMULL_N output:
+VQDMULL_N:2:result_int32x4 [] = { 44000, 44000, 44000, 44000,  }
+VQDMULL_N:3:result_int64x2 [] = { aa000, aa000,  }
+
+VQDMULL_N (check mul cumulative saturation) cumulative saturation output:
+VQDMULL_N:4:vqdmull_n_s16 Neon cumulative saturation 1
+VQDMULL_N:5:vqdmull_n_s32 Neon cumulative saturation 1
+
+VQDMULL_N (check mul cumulative saturation) output:
+VQDMULL_N:6:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQDMULL_N:7:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+
+VST1_LANE/VST1_LANEQ output:
+VST1_LANE/VST1_LANEQ:0:result_int8x8 [] = { fffffff7, 33, 33, 33, 33, 33, 33, 33,  }
+VST1_LANE/VST1_LANEQ:1:result_int16x4 [] = { fffffff3, 3333, 3333, 3333,  }
+VST1_LANE/VST1_LANEQ:2:result_int32x2 [] = { fffffff1, 33333333,  }
+VST1_LANE/VST1_LANEQ:3:result_int64x1 [] = { fffffffffffffff0,  }
+VST1_LANE/VST1_LANEQ:4:result_uint8x8 [] = { f6, 33, 33, 33, 33, 33, 33, 33,  }
+VST1_LANE/VST1_LANEQ:5:result_uint16x4 [] = { fff2, 3333, 3333, 3333,  }
+VST1_LANE/VST1_LANEQ:6:result_uint32x2 [] = { fffffff0, 33333333,  }
+VST1_LANE/VST1_LANEQ:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VST1_LANE/VST1_LANEQ:8:result_poly8x8 [] = { f6, 33, 33, 33, 33, 33, 33, 33,  }
+VST1_LANE/VST1_LANEQ:9:result_poly16x4 [] = { fff2, 3333, 3333, 3333,  }
+VST1_LANE/VST1_LANEQ:10:result_float32x2 [] = { c1700000, 33333333,  }
+VST1_LANE/VST1_LANEQ:11:result_float16x4 [] = { cb00, 0, 0, 0,  }
+VST1_LANE/VST1_LANEQ:12:result_int8x16 [] = { ffffffff, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST1_LANE/VST1_LANEQ:13:result_int16x8 [] = { fffffff5, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VST1_LANE/VST1_LANEQ:14:result_int32x4 [] = { fffffff1, 33333333, 33333333, 33333333,  }
+VST1_LANE/VST1_LANEQ:15:result_int64x2 [] = { fffffffffffffff1, 3333333333333333,  }
+VST1_LANE/VST1_LANEQ:16:result_uint8x16 [] = { fa, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST1_LANE/VST1_LANEQ:17:result_uint16x8 [] = { fff4, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VST1_LANE/VST1_LANEQ:18:result_uint32x4 [] = { fffffff3, 33333333, 33333333, 33333333,  }
+VST1_LANE/VST1_LANEQ:19:result_uint64x2 [] = { fffffffffffffff0, 3333333333333333,  }
+VST1_LANE/VST1_LANEQ:20:result_poly8x16 [] = { fa, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST1_LANE/VST1_LANEQ:21:result_poly16x8 [] = { fff4, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VST1_LANE/VST1_LANEQ:22:result_float32x4 [] = { c1700000, 33333333, 33333333, 33333333,  }
+VST1_LANE/VST1_LANEQ:23:result_float16x8 [] = { c980, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSUB/VSUBQ output:
+VSUB/VSUBQ:0:result_int8x8 [] = { ffffffee, ffffffef, fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5,  }
+VSUB/VSUBQ:1:result_int16x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VSUB/VSUBQ:2:result_int32x2 [] = { ffffffed, ffffffee,  }
+VSUB/VSUBQ:3:result_int64x1 [] = { ffffffffffffff8c,  }
+VSUB/VSUBQ:4:result_uint8x8 [] = { dc, dd, de, df, e0, e1, e2, e3,  }
+VSUB/VSUBQ:5:result_uint16x4 [] = { ffd2, ffd3, ffd4, ffd5,  }
+VSUB/VSUBQ:6:result_uint32x2 [] = { ffffffc8, ffffffc9,  }
+VSUB/VSUBQ:7:result_uint64x1 [] = { ffffffffffffffee,  }
+VSUB/VSUBQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUB/VSUBQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSUB/VSUBQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSUB/VSUBQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSUB/VSUBQ:12:result_int8x16 [] = { fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff, 0, 1, 2, 3, 4, 5, 6, 7, 8, 9,  }
+VSUB/VSUBQ:13:result_int16x8 [] = { 4, 5, 6, 7, 8, 9, a, b,  }
+VSUB/VSUBQ:14:result_int32x4 [] = { e, f, 10, 11,  }
+VSUB/VSUBQ:15:result_int64x2 [] = { ffffffffffffffd8, ffffffffffffffd9,  }
+VSUB/VSUBQ:16:result_uint8x16 [] = { e4, e5, e6, e7, e8, e9, ea, eb, ec, ed, ee, ef, f0, f1, f2, f3,  }
+VSUB/VSUBQ:17:result_uint16x8 [] = { ffed, ffee, ffef, fff0, fff1, fff2, fff3, fff4,  }
+VSUB/VSUBQ:18:result_uint32x4 [] = { ffffffb9, ffffffba, ffffffbb, ffffffbc,  }
+VSUB/VSUBQ:19:result_uint64x2 [] = { ffffffffffffffed, ffffffffffffffee,  }
+VSUB/VSUBQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUB/VSUBQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSUB/VSUBQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSUB/VSUBQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+float32:
+VSUB/VSUBQ:24:result_float32x2 [] = { c00ccccd, c00ccccd,  }
+VSUB/VSUBQ:25:result_float32x4 [] = { c00ccccc, c00ccccc, c00ccccc, c00ccccc,  }
+
+VQADD/VQADDQ cumulative saturation output:
+VQADD/VQADDQ:0:vqadd_s8 Neon cumulative saturation 0
+VQADD/VQADDQ:1:vqadd_s16 Neon cumulative saturation 0
+VQADD/VQADDQ:2:vqadd_s32 Neon cumulative saturation 0
+VQADD/VQADDQ:3:vqadd_s64 Neon cumulative saturation 0
+VQADD/VQADDQ:4:vqadd_u8 Neon cumulative saturation 1
+VQADD/VQADDQ:5:vqadd_u16 Neon cumulative saturation 1
+VQADD/VQADDQ:6:vqadd_u32 Neon cumulative saturation 1
+VQADD/VQADDQ:7:vqadd_u64 Neon cumulative saturation 1
+VQADD/VQADDQ:8:vqaddq_s8 Neon cumulative saturation 0
+VQADD/VQADDQ:9:vqaddq_s16 Neon cumulative saturation 0
+VQADD/VQADDQ:10:vqaddq_s32 Neon cumulative saturation 0
+VQADD/VQADDQ:11:vqaddq_s64 Neon cumulative saturation 0
+VQADD/VQADDQ:12:vqaddq_u8 Neon cumulative saturation 1
+VQADD/VQADDQ:13:vqaddq_u16 Neon cumulative saturation 1
+VQADD/VQADDQ:14:vqaddq_u32 Neon cumulative saturation 1
+VQADD/VQADDQ:15:vqaddq_u64 Neon cumulative saturation 1
+
+VQADD/VQADDQ output:
+VQADD/VQADDQ:16:result_int8x8 [] = { 1, 2, 3, 4, 5, 6, 7, 8,  }
+VQADD/VQADDQ:17:result_int16x4 [] = { 12, 13, 14, 15,  }
+VQADD/VQADDQ:18:result_int32x2 [] = { 23, 24,  }
+VQADD/VQADDQ:19:result_int64x1 [] = { 34,  }
+VQADD/VQADDQ:20:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQADD/VQADDQ:21:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQADD/VQADDQ:22:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQADD/VQADDQ:23:result_uint64x1 [] = { ffffffffffffffff,  }
+VQADD/VQADDQ:24:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQADD/VQADDQ:25:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQADD/VQADDQ:26:result_float32x2 [] = { 33333333, 33333333,  }
+VQADD/VQADDQ:27:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQADD/VQADDQ:28:result_int8x16 [] = { 1, 2, 3, 4, 5, 6, 7, 8, 9, a, b, c, d, e, f, 10,  }
+VQADD/VQADDQ:29:result_int16x8 [] = { 12, 13, 14, 15, 16, 17, 18, 19,  }
+VQADD/VQADDQ:30:result_int32x4 [] = { 23, 24, 25, 26,  }
+VQADD/VQADDQ:31:result_int64x2 [] = { 34, 35,  }
+VQADD/VQADDQ:32:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQADD/VQADDQ:33:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQADD/VQADDQ:34:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQADD/VQADDQ:35:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQADD/VQADDQ:36:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQADD/VQADDQ:37:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQADD/VQADDQ:38:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQADD/VQADDQ:39:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQADD/VQADDQ 64 bits saturation cumulative saturation output:
+VQADD/VQADDQ:40:vqadd_s64 Neon cumulative saturation 0
+VQADD/VQADDQ:41:vqadd_u64 Neon cumulative saturation 0
+VQADD/VQADDQ:42:vqaddq_s64 Neon cumulative saturation 0
+VQADD/VQADDQ:43:vqaddq_u64 Neon cumulative saturation 0
+
+64 bits saturation:
+VQADD/VQADDQ:44:result_int64x1 [] = { fffffffffffffff0,  }
+VQADD/VQADDQ:45:result_uint64x1 [] = { fffffffffffffff0,  }
+VQADD/VQADDQ:46:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VQADD/VQADDQ:47:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+
+VQADD/VQADDQ 64 bits saturation cumulative saturation output:
+VQADD/VQADDQ:48:vqadd_s64 Neon cumulative saturation 0
+VQADD/VQADDQ:49:vqadd_u64 Neon cumulative saturation 1
+VQADD/VQADDQ:50:vqaddq_s64 Neon cumulative saturation 0
+VQADD/VQADDQ:51:vqaddq_u64 Neon cumulative saturation 1
+VQADD/VQADDQ:52:result_int64x1 [] = { 34,  }
+VQADD/VQADDQ:53:result_uint64x1 [] = { ffffffffffffffff,  }
+VQADD/VQADDQ:54:result_int64x2 [] = { 34, 35,  }
+VQADD/VQADDQ:55:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+
+VQADD/VQADDQ 64 bits saturation cumulative saturation output:
+VQADD/VQADDQ:56:vqadd_s64 Neon cumulative saturation 1
+VQADD/VQADDQ:57:vqadd_u64 Neon cumulative saturation 1
+VQADD/VQADDQ:58:vqaddq_s64 Neon cumulative saturation 1
+VQADD/VQADDQ:59:vqaddq_u64 Neon cumulative saturation 1
+VQADD/VQADDQ:60:result_int64x1 [] = { 8000000000000000,  }
+VQADD/VQADDQ:61:result_uint64x1 [] = { ffffffffffffffff,  }
+VQADD/VQADDQ:62:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+VQADD/VQADDQ:63:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+
+less than 64 bits saturation:
+VQADD/VQADDQ:64:vqadd_s8 Neon cumulative saturation 1
+VQADD/VQADDQ:65:vqadd_s16 Neon cumulative saturation 1
+VQADD/VQADDQ:66:vqadd_s32 Neon cumulative saturation 1
+VQADD/VQADDQ:67:vqaddq_s8 Neon cumulative saturation 1
+VQADD/VQADDQ:68:vqaddq_s16 Neon cumulative saturation 1
+VQADD/VQADDQ:69:vqaddq_s32 Neon cumulative saturation 1
+VQADD/VQADDQ:70:result_int8x8 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQADD/VQADDQ:71:result_int16x4 [] = { ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQADD/VQADDQ:72:result_int32x2 [] = { 80000000, 80000000,  }
+VQADD/VQADDQ:73:result_int8x16 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQADD/VQADDQ:74:result_int16x8 [] = { ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQADD/VQADDQ:75:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+
+VQADD/VQADDQ less than 64 bits saturation cumulative saturation output:
+VQADD/VQADDQ:76:vqadd_u8 Neon cumulative saturation 1
+VQADD/VQADDQ:77:vqadd_u16 Neon cumulative saturation 1
+VQADD/VQADDQ:78:vqadd_u32 Neon cumulative saturation 1
+VQADD/VQADDQ:79:vqaddq_u8 Neon cumulative saturation 1
+VQADD/VQADDQ:80:vqaddq_u16 Neon cumulative saturation 1
+VQADD/VQADDQ:81:vqaddq_u32 Neon cumulative saturation 1
+VQADD/VQADDQ:82:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQADD/VQADDQ:83:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQADD/VQADDQ:84:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQADD/VQADDQ:85:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQADD/VQADDQ:86:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQADD/VQADDQ:87:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+
+VABS/VABSQ output:
+VABS/VABSQ:0:result_int8x8 [] = { 10, f, e, d, c, b, a, 9,  }
+VABS/VABSQ:1:result_int16x4 [] = { 10, f, e, d,  }
+VABS/VABSQ:2:result_int32x2 [] = { 10, f,  }
+VABS/VABSQ:3:result_int64x1 [] = { 3333333333333333,  }
+VABS/VABSQ:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABS/VABSQ:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABS/VABSQ:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VABS/VABSQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VABS/VABSQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABS/VABSQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABS/VABSQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VABS/VABSQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VABS/VABSQ:12:result_int8x16 [] = { 10, f, e, d, c, b, a, 9, 8, 7, 6, 5, 4, 3, 2, 1,  }
+VABS/VABSQ:13:result_int16x8 [] = { 10, f, e, d, c, b, a, 9,  }
+VABS/VABSQ:14:result_int32x4 [] = { 10, f, e, d,  }
+VABS/VABSQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VABS/VABSQ:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABS/VABSQ:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VABS/VABSQ:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VABS/VABSQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VABS/VABSQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABS/VABSQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VABS/VABSQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VABS/VABSQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+float32:
+VABS/VABSQ:24:result_float32x2 [] = { 40133333, 40133333,  }
+VABS/VABSQ:25:result_float32x4 [] = { 4059999a, 4059999a, 4059999a, 4059999a,  }
+
+VQABS/VQABSQ cumulative saturation output:
+VQABS/VQABSQ:0:vqabs_s8 Neon cumulative saturation 0
+VQABS/VQABSQ:1:vqabs_s16 Neon cumulative saturation 0
+VQABS/VQABSQ:2:vqabs_s32 Neon cumulative saturation 0
+VQABS/VQABSQ:3:vqabsq_s8 Neon cumulative saturation 0
+VQABS/VQABSQ:4:vqabsq_s16 Neon cumulative saturation 0
+VQABS/VQABSQ:5:vqabsq_s32 Neon cumulative saturation 0
+
+VQABS/VQABSQ output:
+VQABS/VQABSQ:6:result_int8x8 [] = { 10, f, e, d, c, b, a, 9,  }
+VQABS/VQABSQ:7:result_int16x4 [] = { 10, f, e, d,  }
+VQABS/VQABSQ:8:result_int32x2 [] = { 10, f,  }
+VQABS/VQABSQ:9:result_int64x1 [] = { 3333333333333333,  }
+VQABS/VQABSQ:10:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQABS/VQABSQ:11:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQABS/VQABSQ:12:result_uint32x2 [] = { 33333333, 33333333,  }
+VQABS/VQABSQ:13:result_uint64x1 [] = { 3333333333333333,  }
+VQABS/VQABSQ:14:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQABS/VQABSQ:15:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQABS/VQABSQ:16:result_float32x2 [] = { 33333333, 33333333,  }
+VQABS/VQABSQ:17:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQABS/VQABSQ:18:result_int8x16 [] = { 10, f, e, d, c, b, a, 9, 8, 7, 6, 5, 4, 3, 2, 1,  }
+VQABS/VQABSQ:19:result_int16x8 [] = { 10, f, e, d, c, b, a, 9,  }
+VQABS/VQABSQ:20:result_int32x4 [] = { 10, f, e, d,  }
+VQABS/VQABSQ:21:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQABS/VQABSQ:22:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQABS/VQABSQ:23:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQABS/VQABSQ:24:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQABS/VQABSQ:25:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQABS/VQABSQ:26:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQABS/VQABSQ:27:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQABS/VQABSQ:28:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQABS/VQABSQ:29:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQABS/VQABSQ cumulative saturation output:
+VQABS/VQABSQ:0:vqabs_s8 Neon cumulative saturation 1
+VQABS/VQABSQ:1:vqabs_s16 Neon cumulative saturation 1
+VQABS/VQABSQ:2:vqabs_s32 Neon cumulative saturation 1
+VQABS/VQABSQ:3:vqabsq_s8 Neon cumulative saturation 1
+VQABS/VQABSQ:4:vqabsq_s16 Neon cumulative saturation 1
+VQABS/VQABSQ:5:vqabsq_s32 Neon cumulative saturation 1
+
+VQABS/VQABSQ output:
+VQABS/VQABSQ:6:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQABS/VQABSQ:7:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQABS/VQABSQ:8:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQABS/VQABSQ:9:result_int64x1 [] = { 3333333333333333,  }
+VQABS/VQABSQ:10:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQABS/VQABSQ:11:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQABS/VQABSQ:12:result_uint32x2 [] = { 33333333, 33333333,  }
+VQABS/VQABSQ:13:result_uint64x1 [] = { 3333333333333333,  }
+VQABS/VQABSQ:14:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQABS/VQABSQ:15:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQABS/VQABSQ:16:result_float32x2 [] = { 33333333, 33333333,  }
+VQABS/VQABSQ:17:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQABS/VQABSQ:18:result_int8x16 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQABS/VQABSQ:19:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQABS/VQABSQ:20:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQABS/VQABSQ:21:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQABS/VQABSQ:22:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQABS/VQABSQ:23:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQABS/VQABSQ:24:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQABS/VQABSQ:25:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQABS/VQABSQ:26:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQABS/VQABSQ:27:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQABS/VQABSQ:28:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQABS/VQABSQ:29:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VCOMBINE output:
+VCOMBINE:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCOMBINE:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCOMBINE:2:result_int32x2 [] = { 33333333, 33333333,  }
+VCOMBINE:3:result_int64x1 [] = { 3333333333333333,  }
+VCOMBINE:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCOMBINE:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCOMBINE:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VCOMBINE:7:result_uint64x1 [] = { 3333333333333333,  }
+VCOMBINE:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCOMBINE:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCOMBINE:10:result_float32x2 [] = { 33333333, 33333333,  }
+VCOMBINE:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VCOMBINE:12:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, 11, 11, 11, 11, 11, 11, 11, 11,  }
+VCOMBINE:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, 22, 22, 22, 22,  }
+VCOMBINE:14:result_int32x4 [] = { fffffff0, fffffff1, 33, 33,  }
+VCOMBINE:15:result_int64x2 [] = { fffffffffffffff0, 44,  }
+VCOMBINE:16:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, 55, 55, 55, 55, 55, 55, 55, 55,  }
+VCOMBINE:17:result_uint16x8 [] = { fff0, fff1, fff2, fff3, 66, 66, 66, 66,  }
+VCOMBINE:18:result_uint32x4 [] = { fffffff0, fffffff1, 77, 77,  }
+VCOMBINE:19:result_uint64x2 [] = { fffffffffffffff0, 88,  }
+VCOMBINE:20:result_poly8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, 55, 55, 55, 55, 55, 55, 55, 55,  }
+VCOMBINE:21:result_poly16x8 [] = { fff0, fff1, fff2, fff3, 66, 66, 66, 66,  }
+VCOMBINE:22:result_float32x4 [] = { c1800000, c1700000, 40533333, 40533333,  }
+VCOMBINE:23:result_float16x8 [] = { cc00, cb80, cb00, ca80, 4b80, 4b80, 4b80, 4b80,  }
+
+VMAX/VMAXQ output:
+VMAX/VMAXQ:0:result_int8x8 [] = { fffffff3, fffffff3, fffffff3, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VMAX/VMAXQ:1:result_int16x4 [] = { fffffff2, fffffff2, fffffff2, fffffff3,  }
+VMAX/VMAXQ:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VMAX/VMAXQ:3:result_int64x1 [] = { 3333333333333333,  }
+VMAX/VMAXQ:4:result_uint8x8 [] = { f3, f3, f3, f3, f4, f5, f6, f7,  }
+VMAX/VMAXQ:5:result_uint16x4 [] = { fff1, fff1, fff2, fff3,  }
+VMAX/VMAXQ:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VMAX/VMAXQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VMAX/VMAXQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMAX/VMAXQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMAX/VMAXQ:10:result_float32x2 [] = { c1780000, c1700000,  }
+VMAX/VMAXQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMAX/VMAXQ:12:result_int8x16 [] = { fffffff4, fffffff4, fffffff4, fffffff4, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VMAX/VMAXQ:13:result_int16x8 [] = { fffffff3, fffffff3, fffffff3, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VMAX/VMAXQ:14:result_int32x4 [] = { fffffff1, fffffff1, fffffff2, fffffff3,  }
+VMAX/VMAXQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMAX/VMAXQ:16:result_uint8x16 [] = { f9, f9, f9, f9, f9, f9, f9, f9, f9, f9, fa, fb, fc, fd, fe, ff,  }
+VMAX/VMAXQ:17:result_uint16x8 [] = { fff2, fff2, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VMAX/VMAXQ:18:result_uint32x4 [] = { fffffff1, fffffff1, fffffff2, fffffff3,  }
+VMAX/VMAXQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMAX/VMAXQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMAX/VMAXQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMAX/VMAXQ:22:result_float32x4 [] = { c1680000, c1680000, c1600000, c1500000,  }
+VMAX/VMAXQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VMAX/VMAXQ FP special (NaN):24:result_float32x4 [] = { 7fc00000, 7fc00000, 7fc00000, 7fc00000,  }
+VMAX/VMAXQ FP special (-NaN):25:result_float32x4 [] = { 7fc00000, 7fc00000, 7fc00000, 7fc00000,  }
+VMAX/VMAXQ FP special (inf):26:result_float32x4 [] = { 7f800000, 7f800000, 7f800000, 7f800000,  }
+VMAX/VMAXQ FP special (-inf):27:result_float32x4 [] = { 3f800000, 3f800000, 3f800000, 3f800000,  }
+VMAX/VMAXQ FP special (-0.0):28:result_float32x4 [] = { 0, 0, 0, 0,  }
+VMAX/VMAXQ FP special (-0.0):29:result_float32x4 [] = { 0, 0, 0, 0,  }
+
+VMIN/VMINQ output:
+VMIN/VMINQ:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff3, fffffff3, fffffff3, fffffff3,  }
+VMIN/VMINQ:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff2,  }
+VMIN/VMINQ:2:result_int32x2 [] = { fffffff0, fffffff0,  }
+VMIN/VMINQ:3:result_int64x1 [] = { 3333333333333333,  }
+VMIN/VMINQ:4:result_uint8x8 [] = { f0, f1, f2, f3, f3, f3, f3, f3,  }
+VMIN/VMINQ:5:result_uint16x4 [] = { fff0, fff1, fff1, fff1,  }
+VMIN/VMINQ:6:result_uint32x2 [] = { fffffff0, fffffff0,  }
+VMIN/VMINQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VMIN/VMINQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMIN/VMINQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMIN/VMINQ:10:result_float32x2 [] = { c1800000, c1780000,  }
+VMIN/VMINQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMIN/VMINQ:12:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff4, fffffff4, fffffff4, fffffff4, fffffff4, fffffff4, fffffff4, fffffff4, fffffff4, fffffff4, fffffff4,  }
+VMIN/VMINQ:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff3, fffffff3, fffffff3, fffffff3,  }
+VMIN/VMINQ:14:result_int32x4 [] = { fffffff0, fffffff1, fffffff1, fffffff1,  }
+VMIN/VMINQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMIN/VMINQ:16:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, f9, f9, f9, f9, f9, f9,  }
+VMIN/VMINQ:17:result_uint16x8 [] = { fff0, fff1, fff2, fff2, fff2, fff2, fff2, fff2,  }
+VMIN/VMINQ:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff1, fffffff1,  }
+VMIN/VMINQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMIN/VMINQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMIN/VMINQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMIN/VMINQ:22:result_float32x4 [] = { c1800000, c1700000, c1680000, c1680000,  }
+VMIN/VMINQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VMIN/VMINQ FP special (NaN):24:result_float32x4 [] = { 7fc00000, 7fc00000, 7fc00000, 7fc00000,  }
+VMIN/VMINQ FP special (-NaN):25:result_float32x4 [] = { 7fc00000, 7fc00000, 7fc00000, 7fc00000,  }
+VMIN/VMINQ FP special (inf):26:result_float32x4 [] = { 3f800000, 3f800000, 3f800000, 3f800000,  }
+VMIN/VMINQ FP special (-inf):27:result_float32x4 [] = { ff800000, ff800000, ff800000, ff800000,  }
+VMIN/VMINQ FP special (-0.0):28:result_float32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VMIN/VMINQ FP special (-0.0):29:result_float32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+
+VNEG/VNEGQ output:
+VNEG/VNEGQ:0:result_int8x8 [] = { 10, f, e, d, c, b, a, 9,  }
+VNEG/VNEGQ:1:result_int16x4 [] = { 10, f, e, d,  }
+VNEG/VNEGQ:2:result_int32x2 [] = { 10, f,  }
+VNEG/VNEGQ:3:result_int64x1 [] = { 3333333333333333,  }
+VNEG/VNEGQ:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VNEG/VNEGQ:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VNEG/VNEGQ:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VNEG/VNEGQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VNEG/VNEGQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VNEG/VNEGQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VNEG/VNEGQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VNEG/VNEGQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VNEG/VNEGQ:12:result_int8x16 [] = { 10, f, e, d, c, b, a, 9, 8, 7, 6, 5, 4, 3, 2, 1,  }
+VNEG/VNEGQ:13:result_int16x8 [] = { 10, f, e, d, c, b, a, 9,  }
+VNEG/VNEGQ:14:result_int32x4 [] = { 10, f, e, d,  }
+VNEG/VNEGQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VNEG/VNEGQ:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VNEG/VNEGQ:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VNEG/VNEGQ:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VNEG/VNEGQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VNEG/VNEGQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VNEG/VNEGQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VNEG/VNEGQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VNEG/VNEGQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+float32:
+VNEG/VNEGQ:24:result_float32x2 [] = { c0133333, c0133333,  }
+VNEG/VNEGQ:25:result_float32x4 [] = { c059999a, c059999a, c059999a, c059999a,  }
+
+VQNEG/VQNEGQ cumulative saturation output:
+VQNEG/VQNEGQ:0:vqneg_s8 Neon cumulative saturation 0
+VQNEG/VQNEGQ:1:vqneg_s16 Neon cumulative saturation 0
+VQNEG/VQNEGQ:2:vqneg_s32 Neon cumulative saturation 0
+VQNEG/VQNEGQ:3:vqnegq_s8 Neon cumulative saturation 0
+VQNEG/VQNEGQ:4:vqnegq_s16 Neon cumulative saturation 0
+VQNEG/VQNEGQ:5:vqnegq_s32 Neon cumulative saturation 0
+
+VQNEG/VQNEGQ output:
+VQNEG/VQNEGQ:6:result_int8x8 [] = { 10, f, e, d, c, b, a, 9,  }
+VQNEG/VQNEGQ:7:result_int16x4 [] = { 10, f, e, d,  }
+VQNEG/VQNEGQ:8:result_int32x2 [] = { 10, f,  }
+VQNEG/VQNEGQ:9:result_int64x1 [] = { 3333333333333333,  }
+VQNEG/VQNEGQ:10:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQNEG/VQNEGQ:11:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQNEG/VQNEGQ:12:result_uint32x2 [] = { 33333333, 33333333,  }
+VQNEG/VQNEGQ:13:result_uint64x1 [] = { 3333333333333333,  }
+VQNEG/VQNEGQ:14:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQNEG/VQNEGQ:15:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQNEG/VQNEGQ:16:result_float32x2 [] = { 33333333, 33333333,  }
+VQNEG/VQNEGQ:17:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQNEG/VQNEGQ:18:result_int8x16 [] = { 10, f, e, d, c, b, a, 9, 8, 7, 6, 5, 4, 3, 2, 1,  }
+VQNEG/VQNEGQ:19:result_int16x8 [] = { 10, f, e, d, c, b, a, 9,  }
+VQNEG/VQNEGQ:20:result_int32x4 [] = { 10, f, e, d,  }
+VQNEG/VQNEGQ:21:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQNEG/VQNEGQ:22:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQNEG/VQNEGQ:23:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQNEG/VQNEGQ:24:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQNEG/VQNEGQ:25:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQNEG/VQNEGQ:26:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQNEG/VQNEGQ:27:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQNEG/VQNEGQ:28:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQNEG/VQNEGQ:29:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQNEG/VQNEGQ cumulative saturation output:
+VQNEG/VQNEGQ:0:vqneg_s8 Neon cumulative saturation 1
+VQNEG/VQNEGQ:1:vqneg_s16 Neon cumulative saturation 1
+VQNEG/VQNEGQ:2:vqneg_s32 Neon cumulative saturation 1
+VQNEG/VQNEGQ:3:vqnegq_s8 Neon cumulative saturation 1
+VQNEG/VQNEGQ:4:vqnegq_s16 Neon cumulative saturation 1
+VQNEG/VQNEGQ:5:vqnegq_s32 Neon cumulative saturation 1
+
+VQNEG/VQNEGQ output:
+VQNEG/VQNEGQ:6:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQNEG/VQNEGQ:7:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQNEG/VQNEGQ:8:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQNEG/VQNEGQ:9:result_int64x1 [] = { 3333333333333333,  }
+VQNEG/VQNEGQ:10:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQNEG/VQNEGQ:11:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQNEG/VQNEGQ:12:result_uint32x2 [] = { 33333333, 33333333,  }
+VQNEG/VQNEGQ:13:result_uint64x1 [] = { 3333333333333333,  }
+VQNEG/VQNEGQ:14:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQNEG/VQNEGQ:15:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQNEG/VQNEGQ:16:result_float32x2 [] = { 33333333, 33333333,  }
+VQNEG/VQNEGQ:17:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQNEG/VQNEGQ:18:result_int8x16 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQNEG/VQNEGQ:19:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQNEG/VQNEGQ:20:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQNEG/VQNEGQ:21:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQNEG/VQNEGQ:22:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQNEG/VQNEGQ:23:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQNEG/VQNEGQ:24:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQNEG/VQNEGQ:25:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQNEG/VQNEGQ:26:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQNEG/VQNEGQ:27:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQNEG/VQNEGQ:28:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQNEG/VQNEGQ:29:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMLAL output:
+VMLAL:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMLAL:3:result_int64x1 [] = { 3333333333333333,  }
+VMLAL:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMLAL:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLAL:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMLAL:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMLAL:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL:13:result_int16x8 [] = { ffffe907, ffffe908, ffffe909, ffffe90a, ffffe90b, ffffe90c, ffffe90d, ffffe90e,  }
+VMLAL:14:result_int32x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLAL:15:result_int64x2 [] = { 3e07, 3e08,  }
+VMLAL:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL:17:result_uint16x8 [] = { 3e07, 3e08, 3e09, 3e0a, 3e0b, 3e0c, 3e0d, 3e0e,  }
+VMLAL:18:result_uint32x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLAL:19:result_uint64x2 [] = { 3e07, 3e08,  }
+VMLAL:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLAL:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMLAL:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMLSL output:
+VMLSL:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMLSL:3:result_int64x1 [] = { 3333333333333333,  }
+VMLSL:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMLSL:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLSL:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMLSL:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMLSL:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL:13:result_int16x8 [] = { 16d9, 16da, 16db, 16dc, 16dd, 16de, 16df, 16e0,  }
+VMLSL:14:result_int32x4 [] = { ffffc1d9, ffffc1da, ffffc1db, ffffc1dc,  }
+VMLSL:15:result_int64x2 [] = { ffffffffffffc1d9, ffffffffffffc1da,  }
+VMLSL:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL:17:result_uint16x8 [] = { c1d9, c1da, c1db, c1dc, c1dd, c1de, c1df, c1e0,  }
+VMLSL:18:result_uint32x4 [] = { ffffc1d9, ffffc1da, ffffc1db, ffffc1dc,  }
+VMLSL:19:result_uint64x2 [] = { ffffffffffffc1d9, ffffffffffffc1da,  }
+VMLSL:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLSL:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMLSL:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMLAL_LANE output:
+VMLAL_LANE:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_LANE:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL_LANE:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMLAL_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VMLAL_LANE:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_LANE:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL_LANE:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMLAL_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLAL_LANE:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_LANE:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL_LANE:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMLAL_LANE:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMLAL_LANE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_LANE:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLAL_LANE:14:result_int32x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLAL_LANE:15:result_int64x2 [] = { 3e07, 3e08,  }
+VMLAL_LANE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_LANE:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLAL_LANE:18:result_uint32x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLAL_LANE:19:result_uint64x2 [] = { 3e07, 3e08,  }
+VMLAL_LANE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_LANE:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLAL_LANE:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMLAL_LANE:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMLSL_LANE output:
+VMLSL_LANE:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_LANE:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL_LANE:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMLSL_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VMLSL_LANE:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_LANE:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL_LANE:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMLSL_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLSL_LANE:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_LANE:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL_LANE:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMLSL_LANE:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMLSL_LANE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_LANE:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLSL_LANE:14:result_int32x4 [] = { ffffc1d9, ffffc1da, ffffc1db, ffffc1dc,  }
+VMLSL_LANE:15:result_int64x2 [] = { ffffffffffffc1d9, ffffffffffffc1da,  }
+VMLSL_LANE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_LANE:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLSL_LANE:18:result_uint32x4 [] = { ffffc1d9, ffffc1da, ffffc1db, ffffc1dc,  }
+VMLSL_LANE:19:result_uint64x2 [] = { ffffffffffffc1d9, ffffffffffffc1da,  }
+VMLSL_LANE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_LANE:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLSL_LANE:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMLSL_LANE:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMLAL_N output:
+VMLAL_N:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_N:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL_N:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMLAL_N:3:result_int64x1 [] = { 3333333333333333,  }
+VMLAL_N:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_N:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL_N:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMLAL_N:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLAL_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLAL_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMLAL_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMLAL_N:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_N:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLAL_N:14:result_int32x4 [] = { 595, 596, 597, 598,  }
+VMLAL_N:15:result_int64x2 [] = { b3a, b3b,  }
+VMLAL_N:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_N:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLAL_N:18:result_uint32x4 [] = { 10df, 10e0, 10e1, 10e2,  }
+VMLAL_N:19:result_uint64x2 [] = { 10df, 10e0,  }
+VMLAL_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLAL_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLAL_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMLAL_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMLSL_N output:
+VMLSL_N:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_N:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL_N:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMLSL_N:3:result_int64x1 [] = { 3333333333333333,  }
+VMLSL_N:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_N:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL_N:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMLSL_N:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLSL_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLSL_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMLSL_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMLSL_N:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_N:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLSL_N:14:result_int32x4 [] = { fffffa4b, fffffa4c, fffffa4d, fffffa4e,  }
+VMLSL_N:15:result_int64x2 [] = { fffffffffffff4a6, fffffffffffff4a7,  }
+VMLSL_N:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_N:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLSL_N:18:result_uint32x4 [] = { ffffef01, ffffef02, ffffef03, ffffef04,  }
+VMLSL_N:19:result_uint64x2 [] = { ffffffffffffef01, ffffffffffffef02,  }
+VMLSL_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLSL_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLSL_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMLSL_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMOVL output:
+VMOVL:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVL:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMOVL:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMOVL:3:result_int64x1 [] = { 3333333333333333,  }
+VMOVL:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVL:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMOVL:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMOVL:7:result_uint64x1 [] = { 3333333333333333,  }
+VMOVL:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMOVL:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMOVL:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMOVL:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVL:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VMOVL:14:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VMOVL:15:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VMOVL:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVL:17:result_uint16x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VMOVL:18:result_uint32x4 [] = { fff0, fff1, fff2, fff3,  }
+VMOVL:19:result_uint64x2 [] = { fffffff0, fffffff1,  }
+VMOVL:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVL:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMOVL:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMOVL:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMOVN output:
+VMOVN:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VMOVN:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VMOVN:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VMOVN:3:result_int64x1 [] = { 3333333333333333,  }
+VMOVN:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VMOVN:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VMOVN:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VMOVN:7:result_uint64x1 [] = { 3333333333333333,  }
+VMOVN:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVN:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMOVN:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMOVN:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMOVN:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVN:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMOVN:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMOVN:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMOVN:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVN:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMOVN:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMOVN:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMOVN:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMOVN:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMOVN:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMOVN:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMULL output:
+VMULL:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMULL:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMULL:3:result_int64x1 [] = { 3333333333333333,  }
+VMULL:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMULL:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMULL:7:result_uint64x1 [] = { 3333333333333333,  }
+VMULL:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMULL:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMULL:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMULL:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL:13:result_int16x8 [] = { 100, e1, c4, a9, 90, 79, 64, 51,  }
+VMULL:14:result_int32x4 [] = { 100, e1, c4, a9,  }
+VMULL:15:result_int64x2 [] = { 100, e1,  }
+VMULL:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL:17:result_uint16x8 [] = { e100, e2e1, e4c4, e6a9, e890, ea79, ec64, ee51,  }
+VMULL:18:result_uint32x4 [] = { ffe00100, ffe200e1, ffe400c4, ffe600a9,  }
+VMULL:19:result_uint64x2 [] = { ffffffe000000100, ffffffe2000000e1,  }
+VMULL:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL:21:result_poly16x8 [] = { 5500, 5501, 5504, 5505, 5510, 5511, 5514, 5515,  }
+VMULL:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMULL:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMULL_LANE output:
+VMULL_LANE:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL_LANE:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMULL_LANE:2:result_int32x2 [] = { 33333333, 33333333,  }
+VMULL_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VMULL_LANE:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL_LANE:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMULL_LANE:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VMULL_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VMULL_LANE:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL_LANE:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMULL_LANE:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMULL_LANE:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMULL_LANE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL_LANE:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMULL_LANE:14:result_int32x4 [] = { 4000, 4000, 4000, 4000,  }
+VMULL_LANE:15:result_int64x2 [] = { 2000, 2000,  }
+VMULL_LANE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL_LANE:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMULL_LANE:18:result_uint32x4 [] = { 4000, 4000, 4000, 4000,  }
+VMULL_LANE:19:result_uint64x2 [] = { 2000, 2000,  }
+VMULL_LANE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMULL_LANE:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMULL_LANE:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMULL_LANE:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VREV16 output:
+VREV16:0:result_int8x8 [] = { fffffff1, fffffff0, fffffff3, fffffff2, fffffff5, fffffff4, fffffff7, fffffff6,  }
+VREV16:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VREV16:2:result_int32x2 [] = { 33333333, 33333333,  }
+VREV16:3:result_int64x1 [] = { 3333333333333333,  }
+VREV16:4:result_uint8x8 [] = { f1, f0, f3, f2, f5, f4, f7, f6,  }
+VREV16:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VREV16:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VREV16:7:result_uint64x1 [] = { 3333333333333333,  }
+VREV16:8:result_poly8x8 [] = { f1, f0, f3, f2, f5, f4, f7, f6,  }
+VREV16:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VREV16:10:result_float32x2 [] = { 33333333, 33333333,  }
+VREV16:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VREV16:12:result_int8x16 [] = { fffffff1, fffffff0, fffffff3, fffffff2, fffffff5, fffffff4, fffffff7, fffffff6, fffffff9, fffffff8, fffffffb, fffffffa, fffffffd, fffffffc, ffffffff, fffffffe,  }
+VREV16:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VREV16:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VREV16:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VREV16:16:result_uint8x16 [] = { f1, f0, f3, f2, f5, f4, f7, f6, f9, f8, fb, fa, fd, fc, ff, fe,  }
+VREV16:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VREV16:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VREV16:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VREV16:20:result_poly8x16 [] = { f1, f0, f3, f2, f5, f4, f7, f6, f9, f8, fb, fa, fd, fc, ff, fe,  }
+VREV16:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VREV16:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VREV16:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VREV32 output:
+VREV32:24:result_int8x8 [] = { fffffff3, fffffff2, fffffff1, fffffff0, fffffff7, fffffff6, fffffff5, fffffff4,  }
+VREV32:25:result_int16x4 [] = { fffffff1, fffffff0, fffffff3, fffffff2,  }
+VREV32:26:result_int32x2 [] = { 33333333, 33333333,  }
+VREV32:27:result_int64x1 [] = { 3333333333333333,  }
+VREV32:28:result_uint8x8 [] = { f3, f2, f1, f0, f7, f6, f5, f4,  }
+VREV32:29:result_uint16x4 [] = { fff1, fff0, fff3, fff2,  }
+VREV32:30:result_uint32x2 [] = { 33333333, 33333333,  }
+VREV32:31:result_uint64x1 [] = { 3333333333333333,  }
+VREV32:32:result_poly8x8 [] = { f3, f2, f1, f0, f7, f6, f5, f4,  }
+VREV32:33:result_poly16x4 [] = { fff1, fff0, fff3, fff2,  }
+VREV32:34:result_float32x2 [] = { 33333333, 33333333,  }
+VREV32:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VREV32:36:result_int8x16 [] = { fffffff3, fffffff2, fffffff1, fffffff0, fffffff7, fffffff6, fffffff5, fffffff4, fffffffb, fffffffa, fffffff9, fffffff8, ffffffff, fffffffe, fffffffd, fffffffc,  }
+VREV32:37:result_int16x8 [] = { fffffff1, fffffff0, fffffff3, fffffff2, fffffff5, fffffff4, fffffff7, fffffff6,  }
+VREV32:38:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VREV32:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VREV32:40:result_uint8x16 [] = { f3, f2, f1, f0, f7, f6, f5, f4, fb, fa, f9, f8, ff, fe, fd, fc,  }
+VREV32:41:result_uint16x8 [] = { fff1, fff0, fff3, fff2, fff5, fff4, fff7, fff6,  }
+VREV32:42:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VREV32:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VREV32:44:result_poly8x16 [] = { f3, f2, f1, f0, f7, f6, f5, f4, fb, fa, f9, f8, ff, fe, fd, fc,  }
+VREV32:45:result_poly16x8 [] = { fff1, fff0, fff3, fff2, fff5, fff4, fff7, fff6,  }
+VREV32:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VREV32:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VREV64 output:
+VREV64:48:result_int8x8 [] = { fffffff7, fffffff6, fffffff5, fffffff4, fffffff3, fffffff2, fffffff1, fffffff0,  }
+VREV64:49:result_int16x4 [] = { fffffff3, fffffff2, fffffff1, fffffff0,  }
+VREV64:50:result_int32x2 [] = { fffffff1, fffffff0,  }
+VREV64:51:result_int64x1 [] = { 3333333333333333,  }
+VREV64:52:result_uint8x8 [] = { f7, f6, f5, f4, f3, f2, f1, f0,  }
+VREV64:53:result_uint16x4 [] = { fff3, fff2, fff1, fff0,  }
+VREV64:54:result_uint32x2 [] = { fffffff1, fffffff0,  }
+VREV64:55:result_uint64x1 [] = { 3333333333333333,  }
+VREV64:56:result_poly8x8 [] = { f7, f6, f5, f4, f3, f2, f1, f0,  }
+VREV64:57:result_poly16x4 [] = { fff3, fff2, fff1, fff0,  }
+VREV64:58:result_float32x2 [] = { c1700000, c1800000,  }
+VREV64:59:result_float16x4 [] = { 0, 0, 0, 0,  }
+VREV64:60:result_int8x16 [] = { fffffff7, fffffff6, fffffff5, fffffff4, fffffff3, fffffff2, fffffff1, fffffff0, ffffffff, fffffffe, fffffffd, fffffffc, fffffffb, fffffffa, fffffff9, fffffff8,  }
+VREV64:61:result_int16x8 [] = { fffffff3, fffffff2, fffffff1, fffffff0, fffffff7, fffffff6, fffffff5, fffffff4,  }
+VREV64:62:result_int32x4 [] = { fffffff1, fffffff0, fffffff3, fffffff2,  }
+VREV64:63:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VREV64:64:result_uint8x16 [] = { f7, f6, f5, f4, f3, f2, f1, f0, ff, fe, fd, fc, fb, fa, f9, f8,  }
+VREV64:65:result_uint16x8 [] = { fff3, fff2, fff1, fff0, fff7, fff6, fff5, fff4,  }
+VREV64:66:result_uint32x4 [] = { fffffff1, fffffff0, fffffff3, fffffff2,  }
+VREV64:67:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VREV64:68:result_poly8x16 [] = { f7, f6, f5, f4, f3, f2, f1, f0, ff, fe, fd, fc, fb, fa, f9, f8,  }
+VREV64:69:result_poly16x8 [] = { fff3, fff2, fff1, fff0, fff7, fff6, fff5, fff4,  }
+VREV64:70:result_float32x4 [] = { c1700000, c1800000, c1500000, c1600000,  }
+VREV64:71:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSRA_N output:
+VSRA_N:0:result_int8x8 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VSRA_N:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VSRA_N:2:result_int32x2 [] = { fffffffc, fffffffd,  }
+VSRA_N:3:result_int64x1 [] = { fffffffffffffff0,  }
+VSRA_N:4:result_uint8x8 [] = { 5, 6, 7, 8, 9, a, b, c,  }
+VSRA_N:5:result_uint16x4 [] = { fffc, fffd, fffe, ffff,  }
+VSRA_N:6:result_uint32x2 [] = { fffffff3, fffffff4,  }
+VSRA_N:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VSRA_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSRA_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSRA_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSRA_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSRA_N:12:result_int8x16 [] = { fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff, 0, 1, 2, 3, 4, 5, 6, 7,  }
+VSRA_N:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VSRA_N:14:result_int32x4 [] = { fffffffc, fffffffd, fffffffe, ffffffff,  }
+VSRA_N:15:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VSRA_N:16:result_uint8x16 [] = { 5, 6, 7, 8, 9, a, b, c, d, e, f, 10, 11, 12, 13, 14,  }
+VSRA_N:17:result_uint16x8 [] = { fffc, fffd, fffe, ffff, 0, 1, 2, 3,  }
+VSRA_N:18:result_uint32x4 [] = { fffffff3, fffffff4, fffffff5, fffffff6,  }
+VSRA_N:19:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VSRA_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSRA_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSRA_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSRA_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VTRN/VTRNQ chunk 0 output:
+VTRN/VTRNQ:0:result_int8x8 [] = { fffffff0, fffffff1, 11, 11, fffffff2, fffffff3, 11, 11,  }
+VTRN/VTRNQ:1:result_int16x4 [] = { fffffff0, fffffff1, 22, 22,  }
+VTRN/VTRNQ:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VTRN/VTRNQ:3:result_int64x1 [] = { 3333333333333333,  }
+VTRN/VTRNQ:4:result_uint8x8 [] = { f0, f1, 55, 55, f2, f3, 55, 55,  }
+VTRN/VTRNQ:5:result_uint16x4 [] = { fff0, fff1, 66, 66,  }
+VTRN/VTRNQ:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VTRN/VTRNQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VTRN/VTRNQ:8:result_poly8x8 [] = { f0, f1, 55, 55, f2, f3, 55, 55,  }
+VTRN/VTRNQ:9:result_poly16x4 [] = { fff0, fff1, 66, 66,  }
+VTRN/VTRNQ:10:result_float32x2 [] = { c1800000, c1700000,  }
+VTRN/VTRNQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VTRN/VTRNQ:12:result_int8x16 [] = { fffffff0, fffffff1, 11, 11, fffffff2, fffffff3, 11, 11, fffffff4, fffffff5, 11, 11, fffffff6, fffffff7, 11, 11,  }
+VTRN/VTRNQ:13:result_int16x8 [] = { fffffff0, fffffff1, 22, 22, fffffff2, fffffff3, 22, 22,  }
+VTRN/VTRNQ:14:result_int32x4 [] = { fffffff0, fffffff1, 33, 33,  }
+VTRN/VTRNQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTRN/VTRNQ:16:result_uint8x16 [] = { f0, f1, 55, 55, f2, f3, 55, 55, f4, f5, 55, 55, f6, f7, 55, 55,  }
+VTRN/VTRNQ:17:result_uint16x8 [] = { fff0, fff1, 66, 66, fff2, fff3, 66, 66,  }
+VTRN/VTRNQ:18:result_uint32x4 [] = { fffffff0, fffffff1, 77, 77,  }
+VTRN/VTRNQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTRN/VTRNQ:20:result_poly8x16 [] = { f0, f1, 55, 55, f2, f3, 55, 55, f4, f5, 55, 55, f6, f7, 55, 55,  }
+VTRN/VTRNQ:21:result_poly16x8 [] = { fff0, fff1, 66, 66, fff2, fff3, 66, 66,  }
+VTRN/VTRNQ:22:result_float32x4 [] = { c1800000, c1700000, 42073333, 42073333,  }
+VTRN/VTRNQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VTRN/VTRNQ chunk 1 output:
+VTRN/VTRNQ:24:result_int8x8 [] = { fffffff4, fffffff5, 11, 11, fffffff6, fffffff7, 11, 11,  }
+VTRN/VTRNQ:25:result_int16x4 [] = { fffffff2, fffffff3, 22, 22,  }
+VTRN/VTRNQ:26:result_int32x2 [] = { 33, 33,  }
+VTRN/VTRNQ:27:result_int64x1 [] = { 3333333333333333,  }
+VTRN/VTRNQ:28:result_uint8x8 [] = { f4, f5, 55, 55, f6, f7, 55, 55,  }
+VTRN/VTRNQ:29:result_uint16x4 [] = { fff2, fff3, 66, 66,  }
+VTRN/VTRNQ:30:result_uint32x2 [] = { 77, 77,  }
+VTRN/VTRNQ:31:result_uint64x1 [] = { 3333333333333333,  }
+VTRN/VTRNQ:32:result_poly8x8 [] = { f4, f5, 55, 55, f6, f7, 55, 55,  }
+VTRN/VTRNQ:33:result_poly16x4 [] = { fff2, fff3, 66, 66,  }
+VTRN/VTRNQ:34:result_float32x2 [] = { 42066666, 42066666,  }
+VTRN/VTRNQ:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VTRN/VTRNQ:36:result_int8x16 [] = { fffffff8, fffffff9, 11, 11, fffffffa, fffffffb, 11, 11, fffffffc, fffffffd, 11, 11, fffffffe, ffffffff, 11, 11,  }
+VTRN/VTRNQ:37:result_int16x8 [] = { fffffff4, fffffff5, 22, 22, fffffff6, fffffff7, 22, 22,  }
+VTRN/VTRNQ:38:result_int32x4 [] = { fffffff2, fffffff3, 33, 33,  }
+VTRN/VTRNQ:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTRN/VTRNQ:40:result_uint8x16 [] = { f8, f9, 55, 55, fa, fb, 55, 55, fc, fd, 55, 55, fe, ff, 55, 55,  }
+VTRN/VTRNQ:41:result_uint16x8 [] = { fff4, fff5, 66, 66, fff6, fff7, 66, 66,  }
+VTRN/VTRNQ:42:result_uint32x4 [] = { fffffff2, fffffff3, 77, 77,  }
+VTRN/VTRNQ:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTRN/VTRNQ:44:result_poly8x16 [] = { f8, f9, 55, 55, fa, fb, 55, 55, fc, fd, 55, 55, fe, ff, 55, 55,  }
+VTRN/VTRNQ:45:result_poly16x8 [] = { fff4, fff5, 66, 66, fff6, fff7, 66, 66,  }
+VTRN/VTRNQ:46:result_float32x4 [] = { c1600000, c1500000, 42073333, 42073333,  }
+VTRN/VTRNQ:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VUZP/VUZPQ chunk 0 output:
+VUZP/VUZPQ:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VUZP/VUZPQ:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VUZP/VUZPQ:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VUZP/VUZPQ:3:result_int64x1 [] = { 3333333333333333,  }
+VUZP/VUZPQ:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VUZP/VUZPQ:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VUZP/VUZPQ:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VUZP/VUZPQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VUZP/VUZPQ:8:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VUZP/VUZPQ:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VUZP/VUZPQ:10:result_float32x2 [] = { c1800000, c1700000,  }
+VUZP/VUZPQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VUZP/VUZPQ:12:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VUZP/VUZPQ:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VUZP/VUZPQ:14:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VUZP/VUZPQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VUZP/VUZPQ:16:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VUZP/VUZPQ:17:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VUZP/VUZPQ:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VUZP/VUZPQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VUZP/VUZPQ:20:result_poly8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VUZP/VUZPQ:21:result_poly16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VUZP/VUZPQ:22:result_float32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+VUZP/VUZPQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VUZP/VUZPQ chunk 1 output:
+VUZP/VUZPQ:24:result_int8x8 [] = { 11, 11, 11, 11, 11, 11, 11, 11,  }
+VUZP/VUZPQ:25:result_int16x4 [] = { 22, 22, 22, 22,  }
+VUZP/VUZPQ:26:result_int32x2 [] = { 33, 33,  }
+VUZP/VUZPQ:27:result_int64x1 [] = { 3333333333333333,  }
+VUZP/VUZPQ:28:result_uint8x8 [] = { 55, 55, 55, 55, 55, 55, 55, 55,  }
+VUZP/VUZPQ:29:result_uint16x4 [] = { 66, 66, 66, 66,  }
+VUZP/VUZPQ:30:result_uint32x2 [] = { 77, 77,  }
+VUZP/VUZPQ:31:result_uint64x1 [] = { 3333333333333333,  }
+VUZP/VUZPQ:32:result_poly8x8 [] = { 55, 55, 55, 55, 55, 55, 55, 55,  }
+VUZP/VUZPQ:33:result_poly16x4 [] = { 66, 66, 66, 66,  }
+VUZP/VUZPQ:34:result_float32x2 [] = { 42066666, 42066666,  }
+VUZP/VUZPQ:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VUZP/VUZPQ:36:result_int8x16 [] = { 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11, 11,  }
+VUZP/VUZPQ:37:result_int16x8 [] = { 22, 22, 22, 22, 22, 22, 22, 22,  }
+VUZP/VUZPQ:38:result_int32x4 [] = { 33, 33, 33, 33,  }
+VUZP/VUZPQ:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VUZP/VUZPQ:40:result_uint8x16 [] = { 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55,  }
+VUZP/VUZPQ:41:result_uint16x8 [] = { 66, 66, 66, 66, 66, 66, 66, 66,  }
+VUZP/VUZPQ:42:result_uint32x4 [] = { 77, 77, 77, 77,  }
+VUZP/VUZPQ:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VUZP/VUZPQ:44:result_poly8x16 [] = { 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55, 55,  }
+VUZP/VUZPQ:45:result_poly16x8 [] = { 66, 66, 66, 66, 66, 66, 66, 66,  }
+VUZP/VUZPQ:46:result_float32x4 [] = { 42073333, 42073333, 42073333, 42073333,  }
+VUZP/VUZPQ:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VZIP/VZIPQ chunk 0 output:
+VZIP/VZIPQ:0:result_int8x8 [] = { fffffff0, fffffff4, 11, 11, fffffff1, fffffff5, 11, 11,  }
+VZIP/VZIPQ:1:result_int16x4 [] = { fffffff0, fffffff2, 22, 22,  }
+VZIP/VZIPQ:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VZIP/VZIPQ:3:result_int64x1 [] = { 3333333333333333,  }
+VZIP/VZIPQ:4:result_uint8x8 [] = { f0, f4, 55, 55, f1, f5, 55, 55,  }
+VZIP/VZIPQ:5:result_uint16x4 [] = { fff0, fff2, 66, 66,  }
+VZIP/VZIPQ:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VZIP/VZIPQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VZIP/VZIPQ:8:result_poly8x8 [] = { f0, f4, 55, 55, f1, f5, 55, 55,  }
+VZIP/VZIPQ:9:result_poly16x4 [] = { fff0, fff2, 66, 66,  }
+VZIP/VZIPQ:10:result_float32x2 [] = { c1800000, c1700000,  }
+VZIP/VZIPQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VZIP/VZIPQ:12:result_int8x16 [] = { fffffff0, fffffff8, 11, 11, fffffff1, fffffff9, 11, 11, fffffff2, fffffffa, 11, 11, fffffff3, fffffffb, 11, 11,  }
+VZIP/VZIPQ:13:result_int16x8 [] = { fffffff0, fffffff4, 22, 22, fffffff1, fffffff5, 22, 22,  }
+VZIP/VZIPQ:14:result_int32x4 [] = { fffffff0, fffffff2, 33, 33,  }
+VZIP/VZIPQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VZIP/VZIPQ:16:result_uint8x16 [] = { f0, f8, 55, 55, f1, f9, 55, 55, f2, fa, 55, 55, f3, fb, 55, 55,  }
+VZIP/VZIPQ:17:result_uint16x8 [] = { fff0, fff4, 66, 66, fff1, fff5, 66, 66,  }
+VZIP/VZIPQ:18:result_uint32x4 [] = { fffffff0, fffffff2, 77, 77,  }
+VZIP/VZIPQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VZIP/VZIPQ:20:result_poly8x16 [] = { f0, f8, 55, 55, f1, f9, 55, 55, f2, fa, 55, 55, f3, fb, 55, 55,  }
+VZIP/VZIPQ:21:result_poly16x8 [] = { fff0, fff4, 66, 66, fff1, fff5, 66, 66,  }
+VZIP/VZIPQ:22:result_float32x4 [] = { c1800000, c1600000, 42073333, 42073333,  }
+VZIP/VZIPQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VZIP/VZIPQ chunk 1 output:
+VZIP/VZIPQ:24:result_int8x8 [] = { fffffff2, fffffff6, 11, 11, fffffff3, fffffff7, 11, 11,  }
+VZIP/VZIPQ:25:result_int16x4 [] = { fffffff1, fffffff3, 22, 22,  }
+VZIP/VZIPQ:26:result_int32x2 [] = { 33, 33,  }
+VZIP/VZIPQ:27:result_int64x1 [] = { 3333333333333333,  }
+VZIP/VZIPQ:28:result_uint8x8 [] = { f2, f6, 55, 55, f3, f7, 55, 55,  }
+VZIP/VZIPQ:29:result_uint16x4 [] = { fff1, fff3, 66, 66,  }
+VZIP/VZIPQ:30:result_uint32x2 [] = { 77, 77,  }
+VZIP/VZIPQ:31:result_uint64x1 [] = { 3333333333333333,  }
+VZIP/VZIPQ:32:result_poly8x8 [] = { f2, f6, 55, 55, f3, f7, 55, 55,  }
+VZIP/VZIPQ:33:result_poly16x4 [] = { fff1, fff3, 66, 66,  }
+VZIP/VZIPQ:34:result_float32x2 [] = { 42066666, 42066666,  }
+VZIP/VZIPQ:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VZIP/VZIPQ:36:result_int8x16 [] = { fffffff4, fffffffc, 11, 11, fffffff5, fffffffd, 11, 11, fffffff6, fffffffe, 11, 11, fffffff7, ffffffff, 11, 11,  }
+VZIP/VZIPQ:37:result_int16x8 [] = { fffffff2, fffffff6, 22, 22, fffffff3, fffffff7, 22, 22,  }
+VZIP/VZIPQ:38:result_int32x4 [] = { fffffff1, fffffff3, 33, 33,  }
+VZIP/VZIPQ:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VZIP/VZIPQ:40:result_uint8x16 [] = { f4, fc, 55, 55, f5, fd, 55, 55, f6, fe, 55, 55, f7, ff, 55, 55,  }
+VZIP/VZIPQ:41:result_uint16x8 [] = { fff2, fff6, 66, 66, fff3, fff7, 66, 66,  }
+VZIP/VZIPQ:42:result_uint32x4 [] = { fffffff1, fffffff3, 77, 77,  }
+VZIP/VZIPQ:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VZIP/VZIPQ:44:result_poly8x16 [] = { f4, fc, 55, 55, f5, fd, 55, 55, f6, fe, 55, 55, f7, ff, 55, 55,  }
+VZIP/VZIPQ:45:result_poly16x8 [] = { fff2, fff6, 66, 66, fff3, fff7, 66, 66,  }
+VZIP/VZIPQ:46:result_float32x4 [] = { c1700000, c1500000, 42073333, 42073333,  }
+VZIP/VZIPQ:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VREINTERPRET/VREINTERPRETQ output:
+VREINTERPRET/VREINTERPRETQ:0:result_int8x8 [] = { fffffff0, ffffffff, fffffff1, ffffffff, fffffff2, ffffffff, fffffff3, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:1:result_int8x8 [] = { fffffff0, ffffffff, ffffffff, ffffffff, fffffff1, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:2:result_int8x8 [] = { fffffff0, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:3:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VREINTERPRET/VREINTERPRETQ:4:result_int8x8 [] = { fffffff0, ffffffff, fffffff1, ffffffff, fffffff2, ffffffff, fffffff3, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:5:result_int8x8 [] = { fffffff0, ffffffff, ffffffff, ffffffff, fffffff1, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:6:result_int8x8 [] = { fffffff0, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:7:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VREINTERPRET/VREINTERPRETQ:8:result_int8x8 [] = { fffffff0, ffffffff, fffffff1, ffffffff, fffffff2, ffffffff, fffffff3, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:9:result_int16x4 [] = { fffff1f0, fffff3f2, fffff5f4, fffff7f6,  }
+VREINTERPRET/VREINTERPRETQ:10:result_int16x4 [] = { fffffff0, ffffffff, fffffff1, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:11:result_int16x4 [] = { fffffff0, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:12:result_int16x4 [] = { fffff1f0, fffff3f2, fffff5f4, fffff7f6,  }
+VREINTERPRET/VREINTERPRETQ:13:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VREINTERPRET/VREINTERPRETQ:14:result_int16x4 [] = { fffffff0, ffffffff, fffffff1, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:15:result_int16x4 [] = { fffffff0, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:16:result_int16x4 [] = { fffff1f0, fffff3f2, fffff5f4, fffff7f6,  }
+VREINTERPRET/VREINTERPRETQ:17:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VREINTERPRET/VREINTERPRETQ:18:result_int32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:19:result_int32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:20:result_int32x2 [] = { fffffff0, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:21:result_int32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:22:result_int32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:23:result_int32x2 [] = { fffffff0, fffffff1,  }
+VREINTERPRET/VREINTERPRETQ:24:result_int32x2 [] = { fffffff0, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:25:result_int32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:26:result_int32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:27:result_int64x1 [] = { f7f6f5f4f3f2f1f0,  }
+VREINTERPRET/VREINTERPRETQ:28:result_int64x1 [] = { fff3fff2fff1fff0,  }
+VREINTERPRET/VREINTERPRETQ:29:result_int64x1 [] = { fffffff1fffffff0,  }
+VREINTERPRET/VREINTERPRETQ:30:result_int64x1 [] = { f7f6f5f4f3f2f1f0,  }
+VREINTERPRET/VREINTERPRETQ:31:result_int64x1 [] = { fff3fff2fff1fff0,  }
+VREINTERPRET/VREINTERPRETQ:32:result_int64x1 [] = { fffffff1fffffff0,  }
+VREINTERPRET/VREINTERPRETQ:33:result_int64x1 [] = { fffffffffffffff0,  }
+VREINTERPRET/VREINTERPRETQ:34:result_int64x1 [] = { f7f6f5f4f3f2f1f0,  }
+VREINTERPRET/VREINTERPRETQ:35:result_int64x1 [] = { fff3fff2fff1fff0,  }
+VREINTERPRET/VREINTERPRETQ:36:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VREINTERPRET/VREINTERPRETQ:37:result_uint8x8 [] = { f0, ff, f1, ff, f2, ff, f3, ff,  }
+VREINTERPRET/VREINTERPRETQ:38:result_uint8x8 [] = { f0, ff, ff, ff, f1, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:39:result_uint8x8 [] = { f0, ff, ff, ff, ff, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:40:result_uint8x8 [] = { f0, ff, f1, ff, f2, ff, f3, ff,  }
+VREINTERPRET/VREINTERPRETQ:41:result_uint8x8 [] = { f0, ff, ff, ff, f1, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:42:result_uint8x8 [] = { f0, ff, ff, ff, ff, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:43:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VREINTERPRET/VREINTERPRETQ:44:result_uint8x8 [] = { f0, ff, f1, ff, f2, ff, f3, ff,  }
+VREINTERPRET/VREINTERPRETQ:45:result_uint16x4 [] = { f1f0, f3f2, f5f4, f7f6,  }
+VREINTERPRET/VREINTERPRETQ:46:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VREINTERPRET/VREINTERPRETQ:47:result_uint16x4 [] = { fff0, ffff, fff1, ffff,  }
+VREINTERPRET/VREINTERPRETQ:48:result_uint16x4 [] = { fff0, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:49:result_uint16x4 [] = { f1f0, f3f2, f5f4, f7f6,  }
+VREINTERPRET/VREINTERPRETQ:50:result_uint16x4 [] = { fff0, ffff, fff1, ffff,  }
+VREINTERPRET/VREINTERPRETQ:51:result_uint16x4 [] = { fff0, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:52:result_uint16x4 [] = { f1f0, f3f2, f5f4, f7f6,  }
+VREINTERPRET/VREINTERPRETQ:53:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VREINTERPRET/VREINTERPRETQ:54:result_uint32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:55:result_uint32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:56:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VREINTERPRET/VREINTERPRETQ:57:result_uint32x2 [] = { fffffff0, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:58:result_uint32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:59:result_uint32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:60:result_uint32x2 [] = { fffffff0, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:61:result_uint32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:62:result_uint32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:63:result_uint64x1 [] = { f7f6f5f4f3f2f1f0,  }
+VREINTERPRET/VREINTERPRETQ:64:result_uint64x1 [] = { fff3fff2fff1fff0,  }
+VREINTERPRET/VREINTERPRETQ:65:result_uint64x1 [] = { fffffff1fffffff0,  }
+VREINTERPRET/VREINTERPRETQ:66:result_uint64x1 [] = { fffffffffffffff0,  }
+VREINTERPRET/VREINTERPRETQ:67:result_uint64x1 [] = { f7f6f5f4f3f2f1f0,  }
+VREINTERPRET/VREINTERPRETQ:68:result_uint64x1 [] = { fff3fff2fff1fff0,  }
+VREINTERPRET/VREINTERPRETQ:69:result_uint64x1 [] = { fffffff1fffffff0,  }
+VREINTERPRET/VREINTERPRETQ:70:result_uint64x1 [] = { f7f6f5f4f3f2f1f0,  }
+VREINTERPRET/VREINTERPRETQ:71:result_uint64x1 [] = { fff3fff2fff1fff0,  }
+VREINTERPRET/VREINTERPRETQ:72:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VREINTERPRET/VREINTERPRETQ:73:result_poly8x8 [] = { f0, ff, f1, ff, f2, ff, f3, ff,  }
+VREINTERPRET/VREINTERPRETQ:74:result_poly8x8 [] = { f0, ff, ff, ff, f1, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:75:result_poly8x8 [] = { f0, ff, ff, ff, ff, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:76:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VREINTERPRET/VREINTERPRETQ:77:result_poly8x8 [] = { f0, ff, f1, ff, f2, ff, f3, ff,  }
+VREINTERPRET/VREINTERPRETQ:78:result_poly8x8 [] = { f0, ff, ff, ff, f1, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:79:result_poly8x8 [] = { f0, ff, ff, ff, ff, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:80:result_poly8x8 [] = { f0, ff, f1, ff, f2, ff, f3, ff,  }
+VREINTERPRET/VREINTERPRETQ:81:result_poly16x4 [] = { f1f0, f3f2, f5f4, f7f6,  }
+VREINTERPRET/VREINTERPRETQ:82:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VREINTERPRET/VREINTERPRETQ:83:result_poly16x4 [] = { fff0, ffff, fff1, ffff,  }
+VREINTERPRET/VREINTERPRETQ:84:result_poly16x4 [] = { fff0, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:85:result_poly16x4 [] = { f1f0, f3f2, f5f4, f7f6,  }
+VREINTERPRET/VREINTERPRETQ:86:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VREINTERPRET/VREINTERPRETQ:87:result_poly16x4 [] = { fff0, ffff, fff1, ffff,  }
+VREINTERPRET/VREINTERPRETQ:88:result_poly16x4 [] = { fff0, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:89:result_poly16x4 [] = { f1f0, f3f2, f5f4, f7f6,  }
+VREINTERPRET/VREINTERPRETQ:90:result_int8x16 [] = { fffffff0, ffffffff, fffffff1, ffffffff, fffffff2, ffffffff, fffffff3, ffffffff, fffffff4, ffffffff, fffffff5, ffffffff, fffffff6, ffffffff, fffffff7, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:91:result_int8x16 [] = { fffffff0, ffffffff, ffffffff, ffffffff, fffffff1, ffffffff, ffffffff, ffffffff, fffffff2, ffffffff, ffffffff, ffffffff, fffffff3, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:92:result_int8x16 [] = { fffffff0, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, fffffff1, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:93:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:94:result_int8x16 [] = { fffffff0, ffffffff, fffffff1, ffffffff, fffffff2, ffffffff, fffffff3, ffffffff, fffffff4, ffffffff, fffffff5, ffffffff, fffffff6, ffffffff, fffffff7, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:95:result_int8x16 [] = { fffffff0, ffffffff, ffffffff, ffffffff, fffffff1, ffffffff, ffffffff, ffffffff, fffffff2, ffffffff, ffffffff, ffffffff, fffffff3, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:96:result_int8x16 [] = { fffffff0, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, fffffff1, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:97:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:98:result_int8x16 [] = { fffffff0, ffffffff, fffffff1, ffffffff, fffffff2, ffffffff, fffffff3, ffffffff, fffffff4, ffffffff, fffffff5, ffffffff, fffffff6, ffffffff, fffffff7, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:99:result_int16x8 [] = { fffff1f0, fffff3f2, fffff5f4, fffff7f6, fffff9f8, fffffbfa, fffffdfc, fffffffe,  }
+VREINTERPRET/VREINTERPRETQ:100:result_int16x8 [] = { fffffff0, ffffffff, fffffff1, ffffffff, fffffff2, ffffffff, fffffff3, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:101:result_int16x8 [] = { fffffff0, ffffffff, ffffffff, ffffffff, fffffff1, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:102:result_int16x8 [] = { fffff1f0, fffff3f2, fffff5f4, fffff7f6, fffff9f8, fffffbfa, fffffdfc, fffffffe,  }
+VREINTERPRET/VREINTERPRETQ:103:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VREINTERPRET/VREINTERPRETQ:104:result_int16x8 [] = { fffffff0, ffffffff, fffffff1, ffffffff, fffffff2, ffffffff, fffffff3, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:105:result_int16x8 [] = { fffffff0, ffffffff, ffffffff, ffffffff, fffffff1, ffffffff, ffffffff, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:106:result_int16x8 [] = { fffff1f0, fffff3f2, fffff5f4, fffff7f6, fffff9f8, fffffbfa, fffffdfc, fffffffe,  }
+VREINTERPRET/VREINTERPRETQ:107:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VREINTERPRET/VREINTERPRETQ:108:result_int32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:109:result_int32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:110:result_int32x4 [] = { fffffff0, ffffffff, fffffff1, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:111:result_int32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:112:result_int32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:113:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VREINTERPRET/VREINTERPRETQ:114:result_int32x4 [] = { fffffff0, ffffffff, fffffff1, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:115:result_int32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:116:result_int32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:117:result_int64x2 [] = { f7f6f5f4f3f2f1f0, fffefdfcfbfaf9f8,  }
+VREINTERPRET/VREINTERPRETQ:118:result_int64x2 [] = { fff3fff2fff1fff0, fff7fff6fff5fff4,  }
+VREINTERPRET/VREINTERPRETQ:119:result_int64x2 [] = { fffffff1fffffff0, fffffff3fffffff2,  }
+VREINTERPRET/VREINTERPRETQ:120:result_int64x2 [] = { f7f6f5f4f3f2f1f0, fffefdfcfbfaf9f8,  }
+VREINTERPRET/VREINTERPRETQ:121:result_int64x2 [] = { fff3fff2fff1fff0, fff7fff6fff5fff4,  }
+VREINTERPRET/VREINTERPRETQ:122:result_int64x2 [] = { fffffff1fffffff0, fffffff3fffffff2,  }
+VREINTERPRET/VREINTERPRETQ:123:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VREINTERPRET/VREINTERPRETQ:124:result_int64x2 [] = { f7f6f5f4f3f2f1f0, fffefdfcfbfaf9f8,  }
+VREINTERPRET/VREINTERPRETQ:125:result_int64x2 [] = { fff3fff2fff1fff0, fff7fff6fff5fff4,  }
+VREINTERPRET/VREINTERPRETQ:126:result_uint16x8 [] = { f1f0, f3f2, f5f4, f7f6, f9f8, fbfa, fdfc, fffe,  }
+VREINTERPRET/VREINTERPRETQ:127:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VREINTERPRET/VREINTERPRETQ:128:result_uint16x8 [] = { fff0, ffff, fff1, ffff, fff2, ffff, fff3, ffff,  }
+VREINTERPRET/VREINTERPRETQ:129:result_uint16x8 [] = { fff0, ffff, ffff, ffff, fff1, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:130:result_uint16x8 [] = { f1f0, f3f2, f5f4, f7f6, f9f8, fbfa, fdfc, fffe,  }
+VREINTERPRET/VREINTERPRETQ:131:result_uint16x8 [] = { fff0, ffff, fff1, ffff, fff2, ffff, fff3, ffff,  }
+VREINTERPRET/VREINTERPRETQ:132:result_uint16x8 [] = { fff0, ffff, ffff, ffff, fff1, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:133:result_uint16x8 [] = { f1f0, f3f2, f5f4, f7f6, f9f8, fbfa, fdfc, fffe,  }
+VREINTERPRET/VREINTERPRETQ:134:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VREINTERPRET/VREINTERPRETQ:135:result_uint32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:136:result_uint32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:137:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VREINTERPRET/VREINTERPRETQ:138:result_uint32x4 [] = { fffffff0, ffffffff, fffffff1, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:139:result_uint32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:140:result_uint32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:141:result_uint32x4 [] = { fffffff0, ffffffff, fffffff1, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:142:result_uint32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:143:result_uint32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:144:result_uint64x2 [] = { f7f6f5f4f3f2f1f0, fffefdfcfbfaf9f8,  }
+VREINTERPRET/VREINTERPRETQ:145:result_uint64x2 [] = { fff3fff2fff1fff0, fff7fff6fff5fff4,  }
+VREINTERPRET/VREINTERPRETQ:146:result_uint64x2 [] = { fffffff1fffffff0, fffffff3fffffff2,  }
+VREINTERPRET/VREINTERPRETQ:147:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VREINTERPRET/VREINTERPRETQ:148:result_uint64x2 [] = { f7f6f5f4f3f2f1f0, fffefdfcfbfaf9f8,  }
+VREINTERPRET/VREINTERPRETQ:149:result_uint64x2 [] = { fff3fff2fff1fff0, fff7fff6fff5fff4,  }
+VREINTERPRET/VREINTERPRETQ:150:result_uint64x2 [] = { fffffff1fffffff0, fffffff3fffffff2,  }
+VREINTERPRET/VREINTERPRETQ:151:result_uint64x2 [] = { f7f6f5f4f3f2f1f0, fffefdfcfbfaf9f8,  }
+VREINTERPRET/VREINTERPRETQ:152:result_uint64x2 [] = { fff3fff2fff1fff0, fff7fff6fff5fff4,  }
+VREINTERPRET/VREINTERPRETQ:153:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VREINTERPRET/VREINTERPRETQ:154:result_uint8x16 [] = { f0, ff, f1, ff, f2, ff, f3, ff, f4, ff, f5, ff, f6, ff, f7, ff,  }
+VREINTERPRET/VREINTERPRETQ:155:result_uint8x16 [] = { f0, ff, ff, ff, f1, ff, ff, ff, f2, ff, ff, ff, f3, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:156:result_uint8x16 [] = { f0, ff, ff, ff, ff, ff, ff, ff, f1, ff, ff, ff, ff, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:157:result_uint8x16 [] = { f0, ff, f1, ff, f2, ff, f3, ff, f4, ff, f5, ff, f6, ff, f7, ff,  }
+VREINTERPRET/VREINTERPRETQ:158:result_uint8x16 [] = { f0, ff, ff, ff, f1, ff, ff, ff, f2, ff, ff, ff, f3, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:159:result_uint8x16 [] = { f0, ff, ff, ff, ff, ff, ff, ff, f1, ff, ff, ff, ff, ff, ff, ff,  }
+VREINTERPRET/VREINTERPRETQ:160:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VREINTERPRET/VREINTERPRETQ:161:result_uint8x16 [] = { f0, ff, f1, ff, f2, ff, f3, ff, f4, ff, f5, ff, f6, ff, f7, ff,  }
+VREINTERPRET/VREINTERPRETQ:162:result_float32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:163:result_float32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:164:result_float32x2 [] = { fffffff0, fffffff1,  }
+VREINTERPRET/VREINTERPRETQ:165:result_float32x2 [] = { fffffff0, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:166:result_float32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:167:result_float32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:168:result_float32x2 [] = { fffffff0, fffffff1,  }
+VREINTERPRET/VREINTERPRETQ:169:result_float32x2 [] = { fffffff0, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:170:result_float32x2 [] = { f3f2f1f0, f7f6f5f4,  }
+VREINTERPRET/VREINTERPRETQ:171:result_float32x2 [] = { fff1fff0, fff3fff2,  }
+VREINTERPRET/VREINTERPRETQ:172:result_float32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:173:result_float32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:174:result_float32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VREINTERPRET/VREINTERPRETQ:175:result_float32x4 [] = { fffffff0, ffffffff, fffffff1, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:176:result_float32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:177:result_float32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:178:result_float32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VREINTERPRET/VREINTERPRETQ:179:result_float32x4 [] = { fffffff0, ffffffff, fffffff1, ffffffff,  }
+VREINTERPRET/VREINTERPRETQ:180:result_float32x4 [] = { f3f2f1f0, f7f6f5f4, fbfaf9f8, fffefdfc,  }
+VREINTERPRET/VREINTERPRETQ:181:result_float32x4 [] = { fff1fff0, fff3fff2, fff5fff4, fff7fff6,  }
+VREINTERPRET/VREINTERPRETQ:182:result_int8x8 [] = { 0, 0, ffffff80, ffffffc1, 0, 0, 70, ffffffc1,  }
+VREINTERPRET/VREINTERPRETQ:183:result_int16x4 [] = { 0, ffffc180, 0, ffffc170,  }
+VREINTERPRET/VREINTERPRETQ:184:result_int32x2 [] = { c1800000, c1700000,  }
+VREINTERPRET/VREINTERPRETQ:185:result_int64x1 [] = { c1700000c1800000,  }
+VREINTERPRET/VREINTERPRETQ:186:result_uint8x8 [] = { 0, 0, 80, c1, 0, 0, 70, c1,  }
+VREINTERPRET/VREINTERPRETQ:187:result_uint16x4 [] = { 0, c180, 0, c170,  }
+VREINTERPRET/VREINTERPRETQ:188:result_uint32x2 [] = { c1800000, c1700000,  }
+VREINTERPRET/VREINTERPRETQ:189:result_uint64x1 [] = { c1700000c1800000,  }
+VREINTERPRET/VREINTERPRETQ:190:result_poly8x8 [] = { 0, 0, 80, c1, 0, 0, 70, c1,  }
+VREINTERPRET/VREINTERPRETQ:191:result_poly16x4 [] = { 0, c180, 0, c170,  }
+VREINTERPRET/VREINTERPRETQ:192:result_int8x16 [] = { 0, 0, ffffff80, ffffffc1, 0, 0, 70, ffffffc1, 0, 0, 60, ffffffc1, 0, 0, 50, ffffffc1,  }
+VREINTERPRET/VREINTERPRETQ:193:result_int16x8 [] = { 0, ffffc180, 0, ffffc170, 0, ffffc160, 0, ffffc150,  }
+VREINTERPRET/VREINTERPRETQ:194:result_int32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+VREINTERPRET/VREINTERPRETQ:195:result_int64x2 [] = { c1700000c1800000, c1500000c1600000,  }
+VREINTERPRET/VREINTERPRETQ:196:result_uint8x16 [] = { 0, 0, 80, c1, 0, 0, 70, c1, 0, 0, 60, c1, 0, 0, 50, c1,  }
+VREINTERPRET/VREINTERPRETQ:197:result_uint16x8 [] = { 0, c180, 0, c170, 0, c160, 0, c150,  }
+VREINTERPRET/VREINTERPRETQ:198:result_uint32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+VREINTERPRET/VREINTERPRETQ:199:result_uint64x2 [] = { c1700000c1800000, c1500000c1600000,  }
+VREINTERPRET/VREINTERPRETQ:200:result_poly8x16 [] = { 0, 0, 80, c1, 0, 0, 70, c1, 0, 0, 60, c1, 0, 0, 50, c1,  }
+VREINTERPRET/VREINTERPRETQ:201:result_poly16x8 [] = { 0, c180, 0, c170, 0, c160, 0, c150,  }
+VREINTERPRET/VREINTERPRETQ:202:result_float16x4 [] = { f1f0, f3f2, f5f4, f7f6,  }
+VREINTERPRET/VREINTERPRETQ:203:result_float16x4 [] = { fff0, fff1, fff2, fff3,  }
+VREINTERPRET/VREINTERPRETQ:204:result_float16x4 [] = { fff0, ffff, fff1, ffff,  }
+VREINTERPRET/VREINTERPRETQ:205:result_float16x4 [] = { fff0, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:206:result_float16x4 [] = { f1f0, f3f2, f5f4, f7f6,  }
+VREINTERPRET/VREINTERPRETQ:207:result_float16x4 [] = { fff0, fff1, fff2, fff3,  }
+VREINTERPRET/VREINTERPRETQ:208:result_float16x4 [] = { fff0, ffff, fff1, ffff,  }
+VREINTERPRET/VREINTERPRETQ:209:result_float16x4 [] = { fff0, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:210:result_float16x4 [] = { f1f0, f3f2, f5f4, f7f6,  }
+VREINTERPRET/VREINTERPRETQ:211:result_float16x4 [] = { fff0, fff1, fff2, fff3,  }
+VREINTERPRET/VREINTERPRETQ:212:result_float16x4 [] = { 0, c180, 0, c170,  }
+VREINTERPRET/VREINTERPRETQ:213:result_float16x8 [] = { f1f0, f3f2, f5f4, f7f6, f9f8, fbfa, fdfc, fffe,  }
+VREINTERPRET/VREINTERPRETQ:214:result_float16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VREINTERPRET/VREINTERPRETQ:215:result_float16x8 [] = { fff0, ffff, fff1, ffff, fff2, ffff, fff3, ffff,  }
+VREINTERPRET/VREINTERPRETQ:216:result_float16x8 [] = { fff0, ffff, ffff, ffff, fff1, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:217:result_float16x8 [] = { f1f0, f3f2, f5f4, f7f6, f9f8, fbfa, fdfc, fffe,  }
+VREINTERPRET/VREINTERPRETQ:218:result_float16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VREINTERPRET/VREINTERPRETQ:219:result_float16x8 [] = { fff0, ffff, fff1, ffff, fff2, ffff, fff3, ffff,  }
+VREINTERPRET/VREINTERPRETQ:220:result_float16x8 [] = { fff0, ffff, ffff, ffff, fff1, ffff, ffff, ffff,  }
+VREINTERPRET/VREINTERPRETQ:221:result_float16x8 [] = { f1f0, f3f2, f5f4, f7f6, f9f8, fbfa, fdfc, fffe,  }
+VREINTERPRET/VREINTERPRETQ:222:result_float16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VREINTERPRET/VREINTERPRETQ:223:result_float16x8 [] = { 0, c180, 0, c170, 0, c160, 0, c150,  }
+VREINTERPRET/VREINTERPRETQ:224:result_int8x8 [] = { 0, ffffffcc, ffffff80, ffffffcb, 0, ffffffcb, ffffff80, ffffffca,  }
+VREINTERPRET/VREINTERPRETQ:225:result_int16x4 [] = { ffffcc00, ffffcb80, ffffcb00, ffffca80,  }
+VREINTERPRET/VREINTERPRETQ:226:result_int32x2 [] = { cb80cc00, ca80cb00,  }
+VREINTERPRET/VREINTERPRETQ:227:result_int64x1 [] = { ca80cb00cb80cc00,  }
+VREINTERPRET/VREINTERPRETQ:228:result_uint8x8 [] = { 0, cc, 80, cb, 0, cb, 80, ca,  }
+VREINTERPRET/VREINTERPRETQ:229:result_uint16x4 [] = { cc00, cb80, cb00, ca80,  }
+VREINTERPRET/VREINTERPRETQ:230:result_uint32x2 [] = { cb80cc00, ca80cb00,  }
+VREINTERPRET/VREINTERPRETQ:231:result_uint64x1 [] = { ca80cb00cb80cc00,  }
+VREINTERPRET/VREINTERPRETQ:232:result_poly8x8 [] = { 0, cc, 80, cb, 0, cb, 80, ca,  }
+VREINTERPRET/VREINTERPRETQ:233:result_poly16x4 [] = { cc00, cb80, cb00, ca80,  }
+VREINTERPRET/VREINTERPRETQ:234:result_float32x2 [] = { cb80cc00, ca80cb00,  }
+VREINTERPRET/VREINTERPRETQ:235:result_int8x16 [] = { 0, ffffffcc, ffffff80, ffffffcb, 0, ffffffcb, ffffff80, ffffffca, 0, ffffffca, ffffff80, ffffffc9, 0, ffffffc9, ffffff80, ffffffc8,  }
+VREINTERPRET/VREINTERPRETQ:236:result_int16x8 [] = { ffffcc00, ffffcb80, ffffcb00, ffffca80, ffffca00, ffffc980, ffffc900, ffffc880,  }
+VREINTERPRET/VREINTERPRETQ:237:result_int32x4 [] = { cb80cc00, ca80cb00, c980ca00, c880c900,  }
+VREINTERPRET/VREINTERPRETQ:238:result_int64x2 [] = { ca80cb00cb80cc00, c880c900c980ca00,  }
+VREINTERPRET/VREINTERPRETQ:239:result_uint8x16 [] = { 0, cc, 80, cb, 0, cb, 80, ca, 0, ca, 80, c9, 0, c9, 80, c8,  }
+VREINTERPRET/VREINTERPRETQ:240:result_uint16x8 [] = { cc00, cb80, cb00, ca80, ca00, c980, c900, c880,  }
+VREINTERPRET/VREINTERPRETQ:241:result_uint32x4 [] = { cb80cc00, ca80cb00, c980ca00, c880c900,  }
+VREINTERPRET/VREINTERPRETQ:242:result_uint64x2 [] = { ca80cb00cb80cc00, c880c900c980ca00,  }
+VREINTERPRET/VREINTERPRETQ:243:result_poly8x16 [] = { 0, cc, 80, cb, 0, cb, 80, ca, 0, ca, 80, c9, 0, c9, 80, c8,  }
+VREINTERPRET/VREINTERPRETQ:244:result_poly16x8 [] = { cc00, cb80, cb00, ca80, ca00, c980, c900, c880,  }
+VREINTERPRET/VREINTERPRETQ:245:result_float32x4 [] = { cb80cc00, ca80cb00, c980ca00, c880c900,  }
+
+VQRDMULH cumulative saturation output:
+VQRDMULH:0:vqrdmulh_s16 Neon cumulative saturation 0
+VQRDMULH:1:vqrdmulh_s32 Neon cumulative saturation 0
+VQRDMULH:2:vqrdmulhq_s16 Neon cumulative saturation 0
+VQRDMULH:3:vqrdmulhq_s32 Neon cumulative saturation 0
+
+VQRDMULH output:
+VQRDMULH:4:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:5:result_int16x4 [] = { fffffff5, fffffff6, fffffff7, fffffff7,  }
+VQRDMULH:6:result_int32x2 [] = { 0, 0,  }
+VQRDMULH:7:result_int64x1 [] = { 3333333333333333,  }
+VQRDMULH:8:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:9:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH:10:result_uint32x2 [] = { 33333333, 33333333,  }
+VQRDMULH:11:result_uint64x1 [] = { 3333333333333333,  }
+VQRDMULH:12:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:13:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH:14:result_float32x2 [] = { 33333333, 33333333,  }
+VQRDMULH:15:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH:16:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:17:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRDMULH:18:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH:19:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH:20:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:21:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH:22:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH:23:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH:24:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:25:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH:26:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH:27:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRDMULH (check mul cumulative saturation) cumulative saturation output:
+VQRDMULH:28:vqrdmulh_s16 Neon cumulative saturation 1
+VQRDMULH:29:vqrdmulh_s32 Neon cumulative saturation 1
+VQRDMULH:30:vqrdmulhq_s16 Neon cumulative saturation 1
+VQRDMULH:31:vqrdmulhq_s32 Neon cumulative saturation 1
+
+VQRDMULH (check mul cumulative saturation) output:
+VQRDMULH:32:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:33:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH:34:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRDMULH:35:result_int64x1 [] = { 3333333333333333,  }
+VQRDMULH:36:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:37:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH:38:result_uint32x2 [] = { 33333333, 33333333,  }
+VQRDMULH:39:result_uint64x1 [] = { 3333333333333333,  }
+VQRDMULH:40:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:41:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH:42:result_float32x2 [] = { 33333333, 33333333,  }
+VQRDMULH:43:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH:44:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:45:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH:46:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQRDMULH:47:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH:48:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:49:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH:50:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH:51:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH:52:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:53:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH:54:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH:55:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRDMULH (check rounding cumulative saturation) cumulative saturation output:
+VQRDMULH:56:vqrdmulh_s16 Neon cumulative saturation 0
+VQRDMULH:57:vqrdmulh_s32 Neon cumulative saturation 0
+VQRDMULH:58:vqrdmulhq_s16 Neon cumulative saturation 0
+VQRDMULH:59:vqrdmulhq_s32 Neon cumulative saturation 0
+
+VQRDMULH (check rounding cumulative saturation) output:
+VQRDMULH:60:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:61:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH:62:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRDMULH:63:result_int64x1 [] = { 3333333333333333,  }
+VQRDMULH:64:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:65:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH:66:result_uint32x2 [] = { 33333333, 33333333,  }
+VQRDMULH:67:result_uint64x1 [] = { 3333333333333333,  }
+VQRDMULH:68:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:69:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH:70:result_float32x2 [] = { 33333333, 33333333,  }
+VQRDMULH:71:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH:72:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:73:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH:74:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQRDMULH:75:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH:76:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:77:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH:78:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH:79:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH:80:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH:81:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH:82:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH:83:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRDMULH_LANE cumulative saturation output:
+VQRDMULH_LANE:0:vqrdmulh_lane_s16 Neon cumulative saturation 0
+VQRDMULH_LANE:1:vqrdmulh_lane_s32 Neon cumulative saturation 0
+VQRDMULH_LANE:2:vqrdmulhq_lane_s16 Neon cumulative saturation 0
+VQRDMULH_LANE:3:vqrdmulhq_lane_s32 Neon cumulative saturation 0
+
+VQRDMULH_LANE output:
+VQRDMULH_LANE:4:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:5:result_int16x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH_LANE:6:result_int32x2 [] = { 0, 0,  }
+VQRDMULH_LANE:7:result_int64x1 [] = { 3333333333333333,  }
+VQRDMULH_LANE:8:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:9:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:10:result_uint32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_LANE:11:result_uint64x1 [] = { 3333333333333333,  }
+VQRDMULH_LANE:12:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:13:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:14:result_float32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_LANE:15:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH_LANE:16:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:17:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRDMULH_LANE:18:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH_LANE:19:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_LANE:20:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:21:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:22:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_LANE:23:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_LANE:24:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:25:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:26:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_LANE:27:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRDMULH_LANE (check mul cumulative saturation) cumulative saturation output:
+VQRDMULH_LANE:28:vqrdmulh_lane_s16 Neon cumulative saturation 1
+VQRDMULH_LANE:29:vqrdmulh_lane_s32 Neon cumulative saturation 1
+VQRDMULH_LANE:30:vqrdmulhq_lane_s16 Neon cumulative saturation 1
+VQRDMULH_LANE:31:vqrdmulhq_lane_s32 Neon cumulative saturation 1
+
+VQRDMULH_LANE (check mul cumulative saturation) output:
+VQRDMULH_LANE:32:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:33:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH_LANE:34:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRDMULH_LANE:35:result_int64x1 [] = { 3333333333333333,  }
+VQRDMULH_LANE:36:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:37:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:38:result_uint32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_LANE:39:result_uint64x1 [] = { 3333333333333333,  }
+VQRDMULH_LANE:40:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:41:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:42:result_float32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_LANE:43:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH_LANE:44:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:45:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH_LANE:46:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQRDMULH_LANE:47:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_LANE:48:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:49:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:50:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_LANE:51:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_LANE:52:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:53:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:54:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_LANE:55:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRDMULH_LANE (check rounding cumulative saturation) cumulative saturation output:
+VQRDMULH_LANE:56:vqrdmulh_lane_s16 Neon cumulative saturation 0
+VQRDMULH_LANE:57:vqrdmulh_lane_s32 Neon cumulative saturation 0
+VQRDMULH_LANE:58:vqrdmulhq_lane_s16 Neon cumulative saturation 0
+VQRDMULH_LANE:59:vqrdmulhq_lane_s32 Neon cumulative saturation 0
+
+VQRDMULH_LANE (check rounding cumulative saturation) output:
+VQRDMULH_LANE:60:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:61:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH_LANE:62:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRDMULH_LANE:63:result_int64x1 [] = { 3333333333333333,  }
+VQRDMULH_LANE:64:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:65:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:66:result_uint32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_LANE:67:result_uint64x1 [] = { 3333333333333333,  }
+VQRDMULH_LANE:68:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:69:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:70:result_float32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_LANE:71:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH_LANE:72:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:73:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH_LANE:74:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQRDMULH_LANE:75:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_LANE:76:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:77:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:78:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_LANE:79:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_LANE:80:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_LANE:81:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_LANE:82:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_LANE:83:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRDMULH_N cumulative saturation output:
+VQRDMULH_N:0:vqrdmulh_n_s16 Neon cumulative saturation 0
+VQRDMULH_N:1:vqrdmulh_n_s32 Neon cumulative saturation 0
+VQRDMULH_N:2:vqrdmulhq_n_s16 Neon cumulative saturation 0
+VQRDMULH_N:3:vqrdmulhq_n_s32 Neon cumulative saturation 0
+
+VQRDMULH_N output:
+VQRDMULH_N:4:result_int16x4 [] = { fffffffc, fffffffc, fffffffc, fffffffd,  }
+VQRDMULH_N:5:result_int32x2 [] = { fffffffe, fffffffe,  }
+VQRDMULH_N:6:result_int16x8 [] = { 6, 6, 6, 5, 5, 4, 4, 4,  }
+VQRDMULH_N:7:result_int32x4 [] = { fffffffe, fffffffe, fffffffe, fffffffe,  }
+
+VQRDMULH_N (check mul cumulative saturation) cumulative saturation output:
+VQRDMULH_N:8:vqrdmulh_n_s16 Neon cumulative saturation 1
+VQRDMULH_N:9:vqrdmulh_n_s32 Neon cumulative saturation 1
+VQRDMULH_N:10:vqrdmulhq_n_s16 Neon cumulative saturation 1
+VQRDMULH_N:11:vqrdmulhq_n_s32 Neon cumulative saturation 1
+
+VQRDMULH_N (check mul cumulative saturation) output:
+VQRDMULH_N:12:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:13:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH_N:14:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRDMULH_N:15:result_int64x1 [] = { 3333333333333333,  }
+VQRDMULH_N:16:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:17:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_N:18:result_uint32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_N:19:result_uint64x1 [] = { 3333333333333333,  }
+VQRDMULH_N:20:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:21:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_N:22:result_float32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_N:23:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH_N:24:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:25:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH_N:26:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQRDMULH_N:27:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_N:28:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:29:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_N:30:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_N:31:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_N:32:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:33:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_N:34:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_N:35:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRDMULH_N (check rounding cumulative saturation) cumulative saturation output:
+VQRDMULH_N:36:vqrdmulh_n_s16 Neon cumulative saturation 0
+VQRDMULH_N:37:vqrdmulh_n_s32 Neon cumulative saturation 0
+VQRDMULH_N:38:vqrdmulhq_n_s16 Neon cumulative saturation 0
+VQRDMULH_N:39:vqrdmulhq_n_s32 Neon cumulative saturation 0
+
+VQRDMULH_N (check rounding cumulative saturation) output:
+VQRDMULH_N:40:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:41:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH_N:42:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRDMULH_N:43:result_int64x1 [] = { 3333333333333333,  }
+VQRDMULH_N:44:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:45:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_N:46:result_uint32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_N:47:result_uint64x1 [] = { 3333333333333333,  }
+VQRDMULH_N:48:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:49:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRDMULH_N:50:result_float32x2 [] = { 33333333, 33333333,  }
+VQRDMULH_N:51:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRDMULH_N:52:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:53:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQRDMULH_N:54:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQRDMULH_N:55:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_N:56:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:57:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_N:58:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_N:59:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRDMULH_N:60:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRDMULH_N:61:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRDMULH_N:62:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRDMULH_N:63:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHL/VQRSHLQ (with input = 0) cumulative saturation output:
+VQRSHL/VQRSHLQ:0:vqrshl_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:1:vqrshl_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:2:vqrshl_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:3:vqrshl_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:4:vqrshl_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:5:vqrshl_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:6:vqrshl_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:7:vqrshl_u64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:8:vqrshlq_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:9:vqrshlq_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:10:vqrshlq_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:11:vqrshlq_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:12:vqrshlq_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:13:vqrshlq_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:14:vqrshlq_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:15:vqrshlq_u64 Neon cumulative saturation 0
+
+VQRSHL/VQRSHLQ (with input = 0) output:
+VQRSHL/VQRSHLQ:16:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:17:result_int16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:18:result_int32x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:19:result_int64x1 [] = { 0,  }
+VQRSHL/VQRSHLQ:20:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:21:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:22:result_uint32x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:23:result_uint64x1 [] = { 0,  }
+VQRSHL/VQRSHLQ:24:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:25:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:26:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:27:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:28:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:29:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:30:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:31:result_int64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:32:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:33:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:34:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:35:result_uint64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:36:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:37:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:38:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:39:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHL/VQRSHLQ (input 0 and negative shift amount) cumulative saturation output:
+VQRSHL/VQRSHLQ:40:vqrshl_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:41:vqrshl_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:42:vqrshl_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:43:vqrshl_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:44:vqrshl_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:45:vqrshl_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:46:vqrshl_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:47:vqrshl_u64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:48:vqrshlq_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:49:vqrshlq_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:50:vqrshlq_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:51:vqrshlq_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:52:vqrshlq_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:53:vqrshlq_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:54:vqrshlq_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:55:vqrshlq_u64 Neon cumulative saturation 0
+
+VQRSHL/VQRSHLQ (input 0 and negative shift amount) output:
+VQRSHL/VQRSHLQ:56:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:57:result_int16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:58:result_int32x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:59:result_int64x1 [] = { 0,  }
+VQRSHL/VQRSHLQ:60:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:61:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:62:result_uint32x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:63:result_uint64x1 [] = { 0,  }
+VQRSHL/VQRSHLQ:64:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:65:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:66:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:67:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:68:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:69:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:70:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:71:result_int64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:72:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:73:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:74:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:75:result_uint64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:76:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:77:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:78:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:79:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHL/VQRSHLQ cumulative saturation output:
+VQRSHL/VQRSHLQ:80:vqrshl_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:81:vqrshl_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:82:vqrshl_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:83:vqrshl_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:84:vqrshl_u8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:85:vqrshl_u16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:86:vqrshl_u32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:87:vqrshl_u64 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:88:vqrshlq_s8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:89:vqrshlq_s16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:90:vqrshlq_s32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:91:vqrshlq_s64 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:92:vqrshlq_u8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:93:vqrshlq_u16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:94:vqrshlq_u32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:95:vqrshlq_u64 Neon cumulative saturation 1
+
+VQRSHL/VQRSHLQ output:
+VQRSHL/VQRSHLQ:96:result_int8x8 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6, ffffffe8, ffffffea, ffffffec, ffffffee,  }
+VQRSHL/VQRSHLQ:97:result_int16x4 [] = { ffffff80, ffffff88, ffffff90, ffffff98,  }
+VQRSHL/VQRSHLQ:98:result_int32x2 [] = { fffff000, fffff100,  }
+VQRSHL/VQRSHLQ:99:result_int64x1 [] = { ffffffffffffff80,  }
+VQRSHL/VQRSHLQ:100:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHL/VQRSHLQ:101:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQRSHL/VQRSHLQ:102:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQRSHL/VQRSHLQ:103:result_uint64x1 [] = { ffffffffffffffff,  }
+VQRSHL/VQRSHLQ:104:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:105:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:106:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:107:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:108:result_int8x16 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQRSHL/VQRSHLQ:109:result_int16x8 [] = { ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQRSHL/VQRSHLQ:110:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VQRSHL/VQRSHLQ:111:result_int64x2 [] = { 8000000000000000, 8000000000000000,  }
+VQRSHL/VQRSHLQ:112:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHL/VQRSHLQ:113:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQRSHL/VQRSHLQ:114:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQRSHL/VQRSHLQ:115:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQRSHL/VQRSHLQ:116:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:117:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:118:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:119:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHL/VQRSHLQ (negative shift amount) cumulative saturation output:
+VQRSHL/VQRSHLQ:120:vqrshl_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:121:vqrshl_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:122:vqrshl_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:123:vqrshl_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:124:vqrshl_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:125:vqrshl_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:126:vqrshl_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:127:vqrshl_u64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:128:vqrshlq_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:129:vqrshlq_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:130:vqrshlq_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:131:vqrshlq_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:132:vqrshlq_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:133:vqrshlq_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:134:vqrshlq_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:135:vqrshlq_u64 Neon cumulative saturation 0
+
+VQRSHL/VQRSHLQ (negative shift amount) output:
+VQRSHL/VQRSHLQ:136:result_int8x8 [] = { fffffffc, fffffffc, fffffffd, fffffffd, fffffffd, fffffffd, fffffffe, fffffffe,  }
+VQRSHL/VQRSHLQ:137:result_int16x4 [] = { fffffffc, fffffffc, fffffffd, fffffffd,  }
+VQRSHL/VQRSHLQ:138:result_int32x2 [] = { fffffffe, fffffffe,  }
+VQRSHL/VQRSHLQ:139:result_int64x1 [] = { ffffffffffffffff,  }
+VQRSHL/VQRSHLQ:140:result_uint8x8 [] = { 3c, 3c, 3d, 3d, 3d, 3d, 3e, 3e,  }
+VQRSHL/VQRSHLQ:141:result_uint16x4 [] = { 3ffc, 3ffc, 3ffd, 3ffd,  }
+VQRSHL/VQRSHLQ:142:result_uint32x2 [] = { 1ffffffe, 1ffffffe,  }
+VQRSHL/VQRSHLQ:143:result_uint64x1 [] = { fffffffffffffff,  }
+VQRSHL/VQRSHLQ:144:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:145:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:146:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:147:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:148:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:149:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:150:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:151:result_int64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:152:result_uint8x16 [] = { 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,  }
+VQRSHL/VQRSHLQ:153:result_uint16x8 [] = { 20, 20, 20, 20, 20, 20, 20, 20,  }
+VQRSHL/VQRSHLQ:154:result_uint32x4 [] = { 80000, 80000, 80000, 80000,  }
+VQRSHL/VQRSHLQ:155:result_uint64x2 [] = { 100000000000, 100000000000,  }
+VQRSHL/VQRSHLQ:156:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:157:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:158:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:159:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: shift by -1) cumulative saturation output:
+VQRSHL/VQRSHLQ:160:vqrshl_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:161:vqrshl_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:162:vqrshl_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:163:vqrshl_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:164:vqrshl_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:165:vqrshl_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:166:vqrshl_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:167:vqrshl_u64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:168:vqrshlq_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:169:vqrshlq_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:170:vqrshlq_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:171:vqrshlq_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:172:vqrshlq_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:173:vqrshlq_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:174:vqrshlq_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:175:vqrshlq_u64 Neon cumulative saturation 0
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: shift by -1) output:
+VQRSHL/VQRSHLQ:176:result_int8x8 [] = { 40, 40, 40, 40, 40, 40, 40, 40,  }
+VQRSHL/VQRSHLQ:177:result_int16x4 [] = { 4000, 4000, 4000, 4000,  }
+VQRSHL/VQRSHLQ:178:result_int32x2 [] = { 40000000, 40000000,  }
+VQRSHL/VQRSHLQ:179:result_int64x1 [] = { 4000000000000000,  }
+VQRSHL/VQRSHLQ:180:result_uint8x8 [] = { 80, 80, 80, 80, 80, 80, 80, 80,  }
+VQRSHL/VQRSHLQ:181:result_uint16x4 [] = { 8000, 8000, 8000, 8000,  }
+VQRSHL/VQRSHLQ:182:result_uint32x2 [] = { 80000000, 80000000,  }
+VQRSHL/VQRSHLQ:183:result_uint64x1 [] = { 8000000000000000,  }
+VQRSHL/VQRSHLQ:184:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:185:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:186:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:187:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:188:result_int8x16 [] = { 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40,  }
+VQRSHL/VQRSHLQ:189:result_int16x8 [] = { 4000, 4000, 4000, 4000, 4000, 4000, 4000, 4000,  }
+VQRSHL/VQRSHLQ:190:result_int32x4 [] = { 40000000, 40000000, 40000000, 40000000,  }
+VQRSHL/VQRSHLQ:191:result_int64x2 [] = { 4000000000000000, 4000000000000000,  }
+VQRSHL/VQRSHLQ:192:result_uint8x16 [] = { 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80,  }
+VQRSHL/VQRSHLQ:193:result_uint16x8 [] = { 8000, 8000, 8000, 8000, 8000, 8000, 8000, 8000,  }
+VQRSHL/VQRSHLQ:194:result_uint32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VQRSHL/VQRSHLQ:195:result_uint64x2 [] = { 8000000000000000, 8000000000000000,  }
+VQRSHL/VQRSHLQ:196:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:197:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:198:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:199:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: shift by -3) cumulative saturation output:
+VQRSHL/VQRSHLQ:200:vqrshl_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:201:vqrshl_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:202:vqrshl_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:203:vqrshl_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:204:vqrshl_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:205:vqrshl_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:206:vqrshl_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:207:vqrshl_u64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:208:vqrshlq_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:209:vqrshlq_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:210:vqrshlq_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:211:vqrshlq_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:212:vqrshlq_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:213:vqrshlq_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:214:vqrshlq_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:215:vqrshlq_u64 Neon cumulative saturation 0
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: shift by -3) output:
+VQRSHL/VQRSHLQ:216:result_int8x8 [] = { 10, 10, 10, 10, 10, 10, 10, 10,  }
+VQRSHL/VQRSHLQ:217:result_int16x4 [] = { 1000, 1000, 1000, 1000,  }
+VQRSHL/VQRSHLQ:218:result_int32x2 [] = { 10000000, 10000000,  }
+VQRSHL/VQRSHLQ:219:result_int64x1 [] = { 1000000000000000,  }
+VQRSHL/VQRSHLQ:220:result_uint8x8 [] = { 20, 20, 20, 20, 20, 20, 20, 20,  }
+VQRSHL/VQRSHLQ:221:result_uint16x4 [] = { 2000, 2000, 2000, 2000,  }
+VQRSHL/VQRSHLQ:222:result_uint32x2 [] = { 20000000, 20000000,  }
+VQRSHL/VQRSHLQ:223:result_uint64x1 [] = { 2000000000000000,  }
+VQRSHL/VQRSHLQ:224:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:225:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:226:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:227:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:228:result_int8x16 [] = { 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10,  }
+VQRSHL/VQRSHLQ:229:result_int16x8 [] = { 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000,  }
+VQRSHL/VQRSHLQ:230:result_int32x4 [] = { 10000000, 10000000, 10000000, 10000000,  }
+VQRSHL/VQRSHLQ:231:result_int64x2 [] = { 1000000000000000, 1000000000000000,  }
+VQRSHL/VQRSHLQ:232:result_uint8x16 [] = { 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20,  }
+VQRSHL/VQRSHLQ:233:result_uint16x8 [] = { 2000, 2000, 2000, 2000, 2000, 2000, 2000, 2000,  }
+VQRSHL/VQRSHLQ:234:result_uint32x4 [] = { 20000000, 20000000, 20000000, 20000000,  }
+VQRSHL/VQRSHLQ:235:result_uint64x2 [] = { 2000000000000000, 2000000000000000,  }
+VQRSHL/VQRSHLQ:236:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:237:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:238:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:239:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large shift amount) cumulative saturation output:
+VQRSHL/VQRSHLQ:240:vqrshl_s8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:241:vqrshl_s16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:242:vqrshl_s32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:243:vqrshl_s64 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:244:vqrshl_u8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:245:vqrshl_u16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:246:vqrshl_u32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:247:vqrshl_u64 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:248:vqrshlq_s8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:249:vqrshlq_s16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:250:vqrshlq_s32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:251:vqrshlq_s64 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:252:vqrshlq_u8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:253:vqrshlq_u16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:254:vqrshlq_u32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:255:vqrshlq_u64 Neon cumulative saturation 1
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large shift amount) output:
+VQRSHL/VQRSHLQ:256:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQRSHL/VQRSHLQ:257:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQRSHL/VQRSHLQ:258:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQRSHL/VQRSHLQ:259:result_int64x1 [] = { 7fffffffffffffff,  }
+VQRSHL/VQRSHLQ:260:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHL/VQRSHLQ:261:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQRSHL/VQRSHLQ:262:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQRSHL/VQRSHLQ:263:result_uint64x1 [] = { ffffffffffffffff,  }
+VQRSHL/VQRSHLQ:264:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:265:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:266:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:267:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:268:result_int8x16 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQRSHL/VQRSHLQ:269:result_int16x8 [] = { 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff, 7fff,  }
+VQRSHL/VQRSHLQ:270:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+VQRSHL/VQRSHLQ:271:result_int64x2 [] = { 7fffffffffffffff, 7fffffffffffffff,  }
+VQRSHL/VQRSHLQ:272:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHL/VQRSHLQ:273:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQRSHL/VQRSHLQ:274:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQRSHL/VQRSHLQ:275:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQRSHL/VQRSHLQ:276:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:277:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:278:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:279:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large shift amount with negative input) cumulative saturation output:
+VQRSHL/VQRSHLQ:280:vqrshl_s8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:281:vqrshl_s16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:282:vqrshl_s32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:283:vqrshl_s64 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:284:vqrshl_u8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:285:vqrshl_u16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:286:vqrshl_u32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:287:vqrshl_u64 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:288:vqrshlq_s8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:289:vqrshlq_s16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:290:vqrshlq_s32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:291:vqrshlq_s64 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:292:vqrshlq_u8 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:293:vqrshlq_u16 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:294:vqrshlq_u32 Neon cumulative saturation 1
+VQRSHL/VQRSHLQ:295:vqrshlq_u64 Neon cumulative saturation 1
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large shift amount with negative input) output:
+VQRSHL/VQRSHLQ:296:result_int8x8 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQRSHL/VQRSHLQ:297:result_int16x4 [] = { ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQRSHL/VQRSHLQ:298:result_int32x2 [] = { 80000000, 80000000,  }
+VQRSHL/VQRSHLQ:299:result_int64x1 [] = { 8000000000000000,  }
+VQRSHL/VQRSHLQ:300:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHL/VQRSHLQ:301:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQRSHL/VQRSHLQ:302:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQRSHL/VQRSHLQ:303:result_uint64x1 [] = { ffffffffffffffff,  }
+VQRSHL/VQRSHLQ:304:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:305:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:306:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:307:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:308:result_int8x16 [] = { ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80, ffffff80,  }
+VQRSHL/VQRSHLQ:309:result_int16x8 [] = { ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000, ffff8000,  }
+VQRSHL/VQRSHLQ:310:result_int32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VQRSHL/VQRSHLQ:311:result_int64x2 [] = { 8000000000000000, 8000000000000000,  }
+VQRSHL/VQRSHLQ:312:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHL/VQRSHLQ:313:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQRSHL/VQRSHLQ:314:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQRSHL/VQRSHLQ:315:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQRSHL/VQRSHLQ:316:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:317:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:318:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:319:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large negative shift amount) cumulative saturation output:
+VQRSHL/VQRSHLQ:320:vqrshl_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:321:vqrshl_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:322:vqrshl_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:323:vqrshl_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:324:vqrshl_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:325:vqrshl_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:326:vqrshl_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:327:vqrshl_u64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:328:vqrshlq_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:329:vqrshlq_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:330:vqrshlq_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:331:vqrshlq_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:332:vqrshlq_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:333:vqrshlq_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:334:vqrshlq_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:335:vqrshlq_u64 Neon cumulative saturation 0
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large negative shift amount) output:
+VQRSHL/VQRSHLQ:336:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:337:result_int16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:338:result_int32x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:339:result_int64x1 [] = { 0,  }
+VQRSHL/VQRSHLQ:340:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:341:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:342:result_uint32x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:343:result_uint64x1 [] = { 0,  }
+VQRSHL/VQRSHLQ:344:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:345:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:346:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:347:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:348:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:349:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:350:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:351:result_int64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:352:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:353:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:354:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:355:result_uint64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:356:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:357:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:358:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:359:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large shift amount with 0 input) cumulative saturation output:
+VQRSHL/VQRSHLQ:360:vqrshl_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:361:vqrshl_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:362:vqrshl_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:363:vqrshl_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:364:vqrshl_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:365:vqrshl_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:366:vqrshl_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:367:vqrshl_u64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:368:vqrshlq_s8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:369:vqrshlq_s16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:370:vqrshlq_s32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:371:vqrshlq_s64 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:372:vqrshlq_u8 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:373:vqrshlq_u16 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:374:vqrshlq_u32 Neon cumulative saturation 0
+VQRSHL/VQRSHLQ:375:vqrshlq_u64 Neon cumulative saturation 0
+
+VQRSHL/VQRSHLQ (checking cumulative saturation: large shift amount with 0 input) output:
+VQRSHL/VQRSHLQ:376:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:377:result_int16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:378:result_int32x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:379:result_int64x1 [] = { 0,  }
+VQRSHL/VQRSHLQ:380:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:381:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:382:result_uint32x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:383:result_uint64x1 [] = { 0,  }
+VQRSHL/VQRSHLQ:384:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:385:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:386:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:387:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:388:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:389:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:390:result_int32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:391:result_int64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:392:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:393:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:394:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VQRSHL/VQRSHLQ:395:result_uint64x2 [] = { 0, 0,  }
+VQRSHL/VQRSHLQ:396:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHL/VQRSHLQ:397:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHL/VQRSHLQ:398:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHL/VQRSHLQ:399:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VABA/VABAQ output:
+VABA/VABAQ:0:result_int8x8 [] = { fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd,  }
+VABA/VABAQ:1:result_int16x4 [] = { 16, 17, 18, 19,  }
+VABA/VABAQ:2:result_int32x2 [] = { 20, 21,  }
+VABA/VABAQ:3:result_int64x1 [] = { 3333333333333333,  }
+VABA/VABAQ:4:result_uint8x8 [] = { 53, 54, 55, 56, 57, 58, 59, 5a,  }
+VABA/VABAQ:5:result_uint16x4 [] = { 907, 908, 909, 90a,  }
+VABA/VABAQ:6:result_uint32x2 [] = { ffffffe7, ffffffe8,  }
+VABA/VABAQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VABA/VABAQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABA/VABAQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABA/VABAQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VABA/VABAQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VABA/VABAQ:12:result_int8x16 [] = { 5e, 5f, 60, 61, 62, 63, 64, 65, 66, 67, 68, 69, 6a, 6b, 6c, 6d,  }
+VABA/VABAQ:13:result_int16x8 [] = { b9c, b9d, b9e, b9f, ba0, ba1, ba2, ba3,  }
+VABA/VABAQ:14:result_int32x4 [] = { 26e0, 26e1, 26e2, 26e3,  }
+VABA/VABAQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VABA/VABAQ:16:result_uint8x16 [] = { f8, f9, fa, fb, fc, fd, fe, ff, 0, 1, 2, 3, 4, 5, 6, 7,  }
+VABA/VABAQ:17:result_uint16x8 [] = { fff9, fffa, fffb, fffc, fffd, fffe, ffff, 0,  }
+VABA/VABAQ:18:result_uint32x4 [] = { c, d, e, f,  }
+VABA/VABAQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VABA/VABAQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABA/VABAQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VABA/VABAQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VABA/VABAQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VABAL output:
+VABAL:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABAL:2:result_int32x2 [] = { 33333333, 33333333,  }
+VABAL:3:result_int64x1 [] = { 3333333333333333,  }
+VABAL:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABAL:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VABAL:7:result_uint64x1 [] = { 3333333333333333,  }
+VABAL:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABAL:10:result_float32x2 [] = { 33333333, 33333333,  }
+VABAL:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VABAL:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:13:result_int16x8 [] = { fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd,  }
+VABAL:14:result_int32x4 [] = { 16, 17, 18, 19,  }
+VABAL:15:result_int64x2 [] = { 20, 21,  }
+VABAL:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:17:result_uint16x8 [] = { 53, 54, 55, 56, 57, 58, 59, 5a,  }
+VABAL:18:result_uint32x4 [] = { 907, 908, 909, 90a,  }
+VABAL:19:result_uint64x2 [] = { ffffffe7, ffffffe8,  }
+VABAL:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VABAL:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VABAL:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VABAL test intermediate overflow output:
+VABAL:24:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:25:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABAL:26:result_int32x2 [] = { 33333333, 33333333,  }
+VABAL:27:result_int64x1 [] = { 3333333333333333,  }
+VABAL:28:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:29:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABAL:30:result_uint32x2 [] = { 33333333, 33333333,  }
+VABAL:31:result_uint64x1 [] = { 3333333333333333,  }
+VABAL:32:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:33:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABAL:34:result_float32x2 [] = { 33333333, 33333333,  }
+VABAL:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VABAL:36:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:37:result_int16x8 [] = { ef, f0, f1, f2, f3, f4, f5, f6,  }
+VABAL:38:result_int32x4 [] = { ffef, fff0, fff1, fff2,  }
+VABAL:39:result_int64x2 [] = { ffffffef, fffffff0,  }
+VABAL:40:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:41:result_uint16x8 [] = { ee, ef, f0, f1, f2, f3, f4, f5,  }
+VABAL:42:result_uint32x4 [] = { ffe2, ffe3, ffe4, ffe5,  }
+VABAL:43:result_uint64x2 [] = { ffffffe7, ffffffe8,  }
+VABAL:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABAL:45:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VABAL:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VABAL:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VABD/VABDQ output:
+VABD/VABDQ:0:result_int8x8 [] = { 11, 10, f, e, d, c, b, a,  }
+VABD/VABDQ:1:result_int16x4 [] = { 3, 2, 1, 0,  }
+VABD/VABDQ:2:result_int32x2 [] = { 18, 17,  }
+VABD/VABDQ:3:result_int64x1 [] = { 3333333333333333,  }
+VABD/VABDQ:4:result_uint8x8 [] = { ef, f0, f1, f2, f3, f4, f5, f6,  }
+VABD/VABDQ:5:result_uint16x4 [] = { ffe3, ffe4, ffe5, ffe6,  }
+VABD/VABDQ:6:result_uint32x2 [] = { ffffffe8, ffffffe9,  }
+VABD/VABDQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VABD/VABDQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABD/VABDQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABD/VABDQ:10:result_float32x2 [] = { 41c26666, 41ba6666,  }
+VABD/VABDQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VABD/VABDQ:12:result_int8x16 [] = { 1a, 19, 18, 17, 16, 15, 14, 13, 12, 11, 10, f, e, d, c, b,  }
+VABD/VABDQ:13:result_int16x8 [] = { 4, 3, 2, 1, 0, 1, 2, 3,  }
+VABD/VABDQ:14:result_int32x4 [] = { 30, 2f, 2e, 2d,  }
+VABD/VABDQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VABD/VABDQ:16:result_uint8x16 [] = { e6, e7, e8, e9, ea, eb, ec, ed, ee, ef, f0, f1, f2, f3, f4, f5,  }
+VABD/VABDQ:17:result_uint16x8 [] = { ffe4, ffe5, ffe6, ffe7, ffe8, ffe9, ffea, ffeb,  }
+VABD/VABDQ:18:result_uint32x4 [] = { ffffffd0, ffffffd1, ffffffd2, ffffffd3,  }
+VABD/VABDQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VABD/VABDQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABD/VABDQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VABD/VABDQ:22:result_float32x4 [] = { 42407ae1, 423c7ae1, 42387ae1, 42347ae1,  }
+VABD/VABDQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VABD/VABDQ FP special (-0.0):24:result_float32x4 [] = { 0, 0, 0, 0,  }
+VABD/VABDQ FP special (-0.0):25:result_float32x4 [] = { 0, 0, 0, 0,  }
+
+VABDL output:
+VABDL:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABDL:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABDL:2:result_int32x2 [] = { 33333333, 33333333,  }
+VABDL:3:result_int64x1 [] = { 3333333333333333,  }
+VABDL:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABDL:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABDL:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VABDL:7:result_uint64x1 [] = { 3333333333333333,  }
+VABDL:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABDL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VABDL:10:result_float32x2 [] = { 33333333, 33333333,  }
+VABDL:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VABDL:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABDL:13:result_int16x8 [] = { 11, 10, f, e, d, c, b, a,  }
+VABDL:14:result_int32x4 [] = { 3, 2, 1, 0,  }
+VABDL:15:result_int64x2 [] = { 18, 17,  }
+VABDL:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABDL:17:result_uint16x8 [] = { ef, f0, f1, f2, f3, f4, f5, f6,  }
+VABDL:18:result_uint32x4 [] = { ffe3, ffe4, ffe5, ffe6,  }
+VABDL:19:result_uint64x2 [] = { ffffffe8, ffffffe9,  }
+VABDL:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VABDL:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VABDL:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VABDL:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VAND/VANDQ output:
+VAND/VANDQ:0:result_int8x8 [] = { 0, 0, 2, 2, 0, 0, 2, 2,  }
+VAND/VANDQ:1:result_int16x4 [] = { fffffff0, fffffff0, fffffff0, fffffff0,  }
+VAND/VANDQ:2:result_int32x2 [] = { 0, 1,  }
+VAND/VANDQ:3:result_int64x1 [] = { 60,  }
+VAND/VANDQ:4:result_uint8x8 [] = { 10, 10, 10, 10, 14, 14, 14, 14,  }
+VAND/VANDQ:5:result_uint16x4 [] = { 10, 10, 12, 12,  }
+VAND/VANDQ:6:result_uint32x2 [] = { 20, 20,  }
+VAND/VANDQ:7:result_uint64x1 [] = { 0,  }
+VAND/VANDQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VAND/VANDQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VAND/VANDQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VAND/VANDQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VAND/VANDQ:12:result_int8x16 [] = { fffffff0, fffffff0, fffffff2, fffffff2, fffffff4, fffffff4, fffffff6, fffffff6, fffffff0, fffffff0, fffffff2, fffffff2, fffffff4, fffffff4, fffffff6, fffffff6,  }
+VAND/VANDQ:13:result_int16x8 [] = { ffffffe0, ffffffe0, ffffffe0, ffffffe0, ffffffe4, ffffffe4, ffffffe4, ffffffe4,  }
+VAND/VANDQ:14:result_int32x4 [] = { ffffffe0, ffffffe0, ffffffe2, ffffffe2,  }
+VAND/VANDQ:15:result_int64x2 [] = { 10, 10,  }
+VAND/VANDQ:16:result_uint8x16 [] = { 0, 0, 0, 0, 4, 4, 4, 4, 8, 8, 8, 8, c, c, c, c,  }
+VAND/VANDQ:17:result_uint16x8 [] = { 0, 1, 2, 3, 0, 1, 2, 3,  }
+VAND/VANDQ:18:result_uint32x4 [] = { 30, 31, 32, 33,  }
+VAND/VANDQ:19:result_uint64x2 [] = { 0, 1,  }
+VAND/VANDQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VAND/VANDQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VAND/VANDQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VAND/VANDQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VORR/VORRQ output:
+VORR/VORRQ:0:result_int8x8 [] = { fffffff2, fffffff3, fffffff2, fffffff3, fffffff6, fffffff7, fffffff6, fffffff7,  }
+VORR/VORRQ:1:result_int16x4 [] = { fffffffc, fffffffd, fffffffe, ffffffff,  }
+VORR/VORRQ:2:result_int32x2 [] = { fffffff3, fffffff3,  }
+VORR/VORRQ:3:result_int64x1 [] = { fffffffffffffff4,  }
+VORR/VORRQ:4:result_uint8x8 [] = { f4, f5, f6, f7, f4, f5, f6, f7,  }
+VORR/VORRQ:5:result_uint16x4 [] = { fffe, ffff, fffe, ffff,  }
+VORR/VORRQ:6:result_uint32x2 [] = { fffffff8, fffffff9,  }
+VORR/VORRQ:7:result_uint64x1 [] = { fffffffffffffff2,  }
+VORR/VORRQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VORR/VORRQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VORR/VORRQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VORR/VORRQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VORR/VORRQ:12:result_int8x16 [] = { fffffff6, fffffff7, fffffff6, fffffff7, fffffff6, fffffff7, fffffff6, fffffff7, fffffffe, ffffffff, fffffffe, ffffffff, fffffffe, ffffffff, fffffffe, ffffffff,  }
+VORR/VORRQ:13:result_int16x8 [] = { fffffffc, fffffffd, fffffffe, ffffffff, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VORR/VORRQ:14:result_int32x4 [] = { fffffff2, fffffff3, fffffff2, fffffff3,  }
+VORR/VORRQ:15:result_int64x2 [] = { fffffffffffffff8, fffffffffffffff9,  }
+VORR/VORRQ:16:result_uint8x16 [] = { fc, fd, fe, ff, fc, fd, fe, ff, fc, fd, fe, ff, fc, fd, fe, ff,  }
+VORR/VORRQ:17:result_uint16x8 [] = { fff3, fff3, fff3, fff3, fff7, fff7, fff7, fff7,  }
+VORR/VORRQ:18:result_uint32x4 [] = { fffffff7, fffffff7, fffffff7, fffffff7,  }
+VORR/VORRQ:19:result_uint64x2 [] = { fffffffffffffff3, fffffffffffffff3,  }
+VORR/VORRQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VORR/VORRQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VORR/VORRQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VORR/VORRQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VORN/VORNQ output:
+VORN/VORNQ:0:result_int8x8 [] = { fffffffd, fffffffd, ffffffff, ffffffff, fffffffd, fffffffd, ffffffff, ffffffff,  }
+VORN/VORNQ:1:result_int16x4 [] = { fffffff3, fffffff3, fffffff3, fffffff3,  }
+VORN/VORNQ:2:result_int32x2 [] = { fffffffc, fffffffd,  }
+VORN/VORNQ:3:result_int64x1 [] = { fffffffffffffffb,  }
+VORN/VORNQ:4:result_uint8x8 [] = { fb, fb, fb, fb, ff, ff, ff, ff,  }
+VORN/VORNQ:5:result_uint16x4 [] = { fff1, fff1, fff3, fff3,  }
+VORN/VORNQ:6:result_uint32x2 [] = { fffffff7, fffffff7,  }
+VORN/VORNQ:7:result_uint64x1 [] = { fffffffffffffffd,  }
+VORN/VORNQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VORN/VORNQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VORN/VORNQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VORN/VORNQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VORN/VORNQ:12:result_int8x16 [] = { fffffff9, fffffff9, fffffffb, fffffffb, fffffffd, fffffffd, ffffffff, ffffffff, fffffff9, fffffff9, fffffffb, fffffffb, fffffffd, fffffffd, ffffffff, ffffffff,  }
+VORN/VORNQ:13:result_int16x8 [] = { fffffff3, fffffff3, fffffff3, fffffff3, fffffff7, fffffff7, fffffff7, fffffff7,  }
+VORN/VORNQ:14:result_int32x4 [] = { fffffffd, fffffffd, ffffffff, ffffffff,  }
+VORN/VORNQ:15:result_int64x2 [] = { fffffffffffffff7, fffffffffffffff7,  }
+VORN/VORNQ:16:result_uint8x16 [] = { f3, f3, f3, f3, f7, f7, f7, f7, fb, fb, fb, fb, ff, ff, ff, ff,  }
+VORN/VORNQ:17:result_uint16x8 [] = { fffc, fffd, fffe, ffff, fffc, fffd, fffe, ffff,  }
+VORN/VORNQ:18:result_uint32x4 [] = { fffffff8, fffffff9, fffffffa, fffffffb,  }
+VORN/VORNQ:19:result_uint64x2 [] = { fffffffffffffffc, fffffffffffffffd,  }
+VORN/VORNQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VORN/VORNQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VORN/VORNQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VORN/VORNQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VEOR/VEORQ output:
+VEOR/VEORQ:0:result_int8x8 [] = { fffffff2, fffffff3, fffffff0, fffffff1, fffffff6, fffffff7, fffffff4, fffffff5,  }
+VEOR/VEORQ:1:result_int16x4 [] = { c, d, e, f,  }
+VEOR/VEORQ:2:result_int32x2 [] = { fffffff3, fffffff2,  }
+VEOR/VEORQ:3:result_int64x1 [] = { ffffffffffffff94,  }
+VEOR/VEORQ:4:result_uint8x8 [] = { e4, e5, e6, e7, e0, e1, e2, e3,  }
+VEOR/VEORQ:5:result_uint16x4 [] = { ffee, ffef, ffec, ffed,  }
+VEOR/VEORQ:6:result_uint32x2 [] = { ffffffd8, ffffffd9,  }
+VEOR/VEORQ:7:result_uint64x1 [] = { fffffffffffffff2,  }
+VEOR/VEORQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VEOR/VEORQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VEOR/VEORQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VEOR/VEORQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VEOR/VEORQ:12:result_int8x16 [] = { 6, 7, 4, 5, 2, 3, 0, 1, e, f, c, d, a, b, 8, 9,  }
+VEOR/VEORQ:13:result_int16x8 [] = { 1c, 1d, 1e, 1f, 18, 19, 1a, 1b,  }
+VEOR/VEORQ:14:result_int32x4 [] = { 12, 13, 10, 11,  }
+VEOR/VEORQ:15:result_int64x2 [] = { ffffffffffffffe8, ffffffffffffffe9,  }
+VEOR/VEORQ:16:result_uint8x16 [] = { fc, fd, fe, ff, f8, f9, fa, fb, f4, f5, f6, f7, f0, f1, f2, f3,  }
+VEOR/VEORQ:17:result_uint16x8 [] = { fff3, fff2, fff1, fff0, fff7, fff6, fff5, fff4,  }
+VEOR/VEORQ:18:result_uint32x4 [] = { ffffffc7, ffffffc6, ffffffc5, ffffffc4,  }
+VEOR/VEORQ:19:result_uint64x2 [] = { fffffffffffffff3, fffffffffffffff2,  }
+VEOR/VEORQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VEOR/VEORQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VEOR/VEORQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VEOR/VEORQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VBIC/VBICQ output:
+VBIC/VBICQ:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff0, fffffff1, fffffff4, fffffff5, fffffff4, fffffff5,  }
+VBIC/VBICQ:1:result_int16x4 [] = { 0, 1, 2, 3,  }
+VBIC/VBICQ:2:result_int32x2 [] = { fffffff0, fffffff0,  }
+VBIC/VBICQ:3:result_int64x1 [] = { ffffffffffffff90,  }
+VBIC/VBICQ:4:result_uint8x8 [] = { e0, e1, e2, e3, e0, e1, e2, e3,  }
+VBIC/VBICQ:5:result_uint16x4 [] = { ffe0, ffe1, ffe0, ffe1,  }
+VBIC/VBICQ:6:result_uint32x2 [] = { ffffffd0, ffffffd1,  }
+VBIC/VBICQ:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VBIC/VBICQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VBIC/VBICQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VBIC/VBICQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VBIC/VBICQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VBIC/VBICQ:12:result_int8x16 [] = { 0, 1, 0, 1, 0, 1, 0, 1, 8, 9, 8, 9, 8, 9, 8, 9,  }
+VBIC/VBICQ:13:result_int16x8 [] = { 10, 11, 12, 13, 10, 11, 12, 13,  }
+VBIC/VBICQ:14:result_int32x4 [] = { 10, 11, 10, 11,  }
+VBIC/VBICQ:15:result_int64x2 [] = { ffffffffffffffe0, ffffffffffffffe1,  }
+VBIC/VBICQ:16:result_uint8x16 [] = { f0, f1, f2, f3, f0, f1, f2, f3, f0, f1, f2, f3, f0, f1, f2, f3,  }
+VBIC/VBICQ:17:result_uint16x8 [] = { fff0, fff0, fff0, fff0, fff4, fff4, fff4, fff4,  }
+VBIC/VBICQ:18:result_uint32x4 [] = { ffffffc0, ffffffc0, ffffffc0, ffffffc0,  }
+VBIC/VBICQ:19:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff0,  }
+VBIC/VBICQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VBIC/VBICQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VBIC/VBICQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VBIC/VBICQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VCREATE output:
+VCREATE:0:result_int8x8 [] = { fffffff0, ffffffde, ffffffbc, ffffff9a, 78, 56, 34, 12,  }
+VCREATE:1:result_int16x4 [] = { ffffdef0, ffff9abc, 5678, 1234,  }
+VCREATE:2:result_int32x2 [] = { 9abcdef0, 12345678,  }
+VCREATE:3:result_int64x1 [] = { 123456789abcdef0,  }
+VCREATE:4:result_uint8x8 [] = { f0, de, bc, 9a, 78, 56, 34, 12,  }
+VCREATE:5:result_uint16x4 [] = { def0, 9abc, 5678, 1234,  }
+VCREATE:6:result_uint32x2 [] = { 9abcdef0, 12345678,  }
+VCREATE:7:result_uint64x1 [] = { 123456789abcdef0,  }
+VCREATE:8:result_poly8x8 [] = { f0, de, bc, 9a, 78, 56, 34, 12,  }
+VCREATE:9:result_poly16x4 [] = { def0, 9abc, 5678, 1234,  }
+VCREATE:10:result_float32x2 [] = { 9abcdef0, 12345678,  }
+VCREATE:11:result_float16x4 [] = { def0, 9abc, 5678, 1234,  }
+VCREATE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCREATE:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCREATE:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCREATE:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCREATE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCREATE:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCREATE:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCREATE:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCREATE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCREATE:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCREATE:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCREATE:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VLD2_LANE/VLD2Q_LANE chunk 0 output:
+VLD2_LANE/VLD2Q_LANE:0:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa,  }
+VLD2_LANE/VLD2Q_LANE:1:result_int16x4 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD2_LANE/VLD2Q_LANE:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD2_LANE/VLD2Q_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VLD2_LANE/VLD2Q_LANE:4:result_uint8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD2_LANE/VLD2Q_LANE:5:result_uint16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD2_LANE/VLD2Q_LANE:6:result_uint32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VLD2_LANE/VLD2Q_LANE:8:result_poly8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD2_LANE/VLD2Q_LANE:9:result_poly16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD2_LANE/VLD2Q_LANE:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD2_LANE/VLD2Q_LANE:11:result_float16x4 [] = { cc00, cb80, aaaa, aaaa,  }
+VLD2_LANE/VLD2Q_LANE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_LANE/VLD2Q_LANE:13:result_int16x8 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD2_LANE/VLD2Q_LANE:14:result_int32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2_LANE/VLD2Q_LANE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_LANE/VLD2Q_LANE:17:result_uint16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD2_LANE/VLD2Q_LANE:18:result_uint32x4 [] = { fffffff0, fffffff1, aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2_LANE/VLD2Q_LANE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_LANE/VLD2Q_LANE:21:result_poly16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD2_LANE/VLD2Q_LANE:22:result_float32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:23:result_float16x8 [] = { aaaa, aaaa, aaaa, aaaa, cc00, cb80, aaaa, aaaa,  }
+
+VLD2_LANE/VLD2Q_LANE chunk 1 output:
+VLD2_LANE/VLD2Q_LANE:24:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, fffffff0, fffffff1,  }
+VLD2_LANE/VLD2Q_LANE:25:result_int16x4 [] = { fffffff0, fffffff1, ffffaaaa, ffffaaaa,  }
+VLD2_LANE/VLD2Q_LANE:26:result_int32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:27:result_int64x1 [] = { 3333333333333333,  }
+VLD2_LANE/VLD2Q_LANE:28:result_uint8x8 [] = { f0, f1, aa, aa, aa, aa, aa, aa,  }
+VLD2_LANE/VLD2Q_LANE:29:result_uint16x4 [] = { aaaa, aaaa, fff0, fff1,  }
+VLD2_LANE/VLD2Q_LANE:30:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD2_LANE/VLD2Q_LANE:31:result_uint64x1 [] = { 3333333333333333,  }
+VLD2_LANE/VLD2Q_LANE:32:result_poly8x8 [] = { f0, f1, aa, aa, aa, aa, aa, aa,  }
+VLD2_LANE/VLD2Q_LANE:33:result_poly16x4 [] = { aaaa, aaaa, fff0, fff1,  }
+VLD2_LANE/VLD2Q_LANE:34:result_float32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:35:result_float16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD2_LANE/VLD2Q_LANE:36:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_LANE/VLD2Q_LANE:37:result_int16x8 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, fffffff0, fffffff1, ffffaaaa, ffffaaaa,  }
+VLD2_LANE/VLD2Q_LANE:38:result_int32x4 [] = { fffffff0, fffffff1, aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2_LANE/VLD2Q_LANE:40:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_LANE/VLD2Q_LANE:41:result_uint16x8 [] = { aaaa, aaaa, fff0, fff1, aaaa, aaaa, aaaa, aaaa,  }
+VLD2_LANE/VLD2Q_LANE:42:result_uint32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2_LANE/VLD2Q_LANE:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_LANE/VLD2Q_LANE:45:result_poly16x8 [] = { aaaa, aaaa, fff0, fff1, aaaa, aaaa, aaaa, aaaa,  }
+VLD2_LANE/VLD2Q_LANE:46:result_float32x4 [] = { c1800000, c1700000, aaaaaaaa, aaaaaaaa,  }
+VLD2_LANE/VLD2Q_LANE:47:result_float16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+
+VLD3_LANE/VLD3Q_LANE chunk 0 output:
+VLD3_LANE/VLD3Q_LANE:0:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa,  }
+VLD3_LANE/VLD3Q_LANE:1:result_int16x4 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD3_LANE/VLD3Q_LANE:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD3_LANE/VLD3Q_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:4:result_uint8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD3_LANE/VLD3Q_LANE:5:result_uint16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:6:result_uint32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:8:result_poly8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD3_LANE/VLD3Q_LANE:9:result_poly16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD3_LANE/VLD3Q_LANE:11:result_float16x4 [] = { cc00, cb80, cb00, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:13:result_int16x8 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD3_LANE/VLD3Q_LANE:14:result_int32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:17:result_uint16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:21:result_poly16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:22:result_float32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:23:result_float16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, cc00, cb80,  }
+
+VLD3_LANE/VLD3Q_LANE chunk 1 output:
+VLD3_LANE/VLD3Q_LANE:24:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa,  }
+VLD3_LANE/VLD3Q_LANE:25:result_int16x4 [] = { ffffaaaa, ffffaaaa, fffffff0, fffffff1,  }
+VLD3_LANE/VLD3Q_LANE:26:result_int32x2 [] = { fffffff2, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:27:result_int64x1 [] = { 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:28:result_uint8x8 [] = { aa, aa, aa, aa, f0, f1, f2, aa,  }
+VLD3_LANE/VLD3Q_LANE:29:result_uint16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:30:result_uint32x2 [] = { aaaaaaaa, fffffff0,  }
+VLD3_LANE/VLD3Q_LANE:31:result_uint64x1 [] = { 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:32:result_poly8x8 [] = { aa, aa, aa, aa, f0, f1, f2, aa,  }
+VLD3_LANE/VLD3Q_LANE:33:result_poly16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:34:result_float32x2 [] = { c1600000, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:35:result_float16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:36:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:37:result_int16x8 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD3_LANE/VLD3Q_LANE:38:result_int32x4 [] = { aaaaaaaa, aaaaaaaa, fffffff0, fffffff1,  }
+VLD3_LANE/VLD3Q_LANE:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:40:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:41:result_uint16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, fff0,  }
+VLD3_LANE/VLD3Q_LANE:42:result_uint32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:45:result_poly16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, fff0,  }
+VLD3_LANE/VLD3Q_LANE:46:result_float32x4 [] = { aaaaaaaa, aaaaaaaa, c1800000, c1700000,  }
+VLD3_LANE/VLD3Q_LANE:47:result_float16x8 [] = { cb00, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+
+VLD3_LANE/VLD3Q_LANE chunk 2 output:
+VLD3_LANE/VLD3Q_LANE:48:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, fffffff0, fffffff1, fffffff2,  }
+VLD3_LANE/VLD3Q_LANE:49:result_int16x4 [] = { fffffff2, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD3_LANE/VLD3Q_LANE:50:result_int32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:51:result_int64x1 [] = { 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:52:result_uint8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD3_LANE/VLD3Q_LANE:53:result_uint16x4 [] = { aaaa, fff0, fff1, fff2,  }
+VLD3_LANE/VLD3Q_LANE:54:result_uint32x2 [] = { fffffff1, fffffff2,  }
+VLD3_LANE/VLD3Q_LANE:55:result_uint64x1 [] = { 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:56:result_poly8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD3_LANE/VLD3Q_LANE:57:result_poly16x4 [] = { aaaa, fff0, fff1, fff2,  }
+VLD3_LANE/VLD3Q_LANE:58:result_float32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:59:result_float16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:60:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:61:result_int16x8 [] = { ffffaaaa, ffffaaaa, fffffff0, fffffff1, fffffff2, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD3_LANE/VLD3Q_LANE:62:result_int32x4 [] = { fffffff2, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:63:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:64:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:65:result_uint16x8 [] = { fff1, fff2, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:66:result_uint32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:67:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_LANE/VLD3Q_LANE:68:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_LANE/VLD3Q_LANE:69:result_poly16x8 [] = { fff1, fff2, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD3_LANE/VLD3Q_LANE:70:result_float32x4 [] = { c1600000, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD3_LANE/VLD3Q_LANE:71:result_float16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+
+VLD4_LANE/VLD4Q_LANE chunk 0 output:
+VLD4_LANE/VLD4Q_LANE:0:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa,  }
+VLD4_LANE/VLD4Q_LANE:1:result_int16x4 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD4_LANE/VLD4Q_LANE:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD4_LANE/VLD4Q_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:4:result_uint8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD4_LANE/VLD4Q_LANE:5:result_uint16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:6:result_uint32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:8:result_poly8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD4_LANE/VLD4Q_LANE:9:result_poly16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD4_LANE/VLD4Q_LANE:11:result_float16x4 [] = { cc00, cb80, cb00, ca80,  }
+VLD4_LANE/VLD4Q_LANE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:13:result_int16x8 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD4_LANE/VLD4Q_LANE:14:result_int32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:17:result_uint16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_LANE/VLD4Q_LANE:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:21:result_poly16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:22:result_float32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:23:result_float16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+
+VLD4_LANE/VLD4Q_LANE chunk 1 output:
+VLD4_LANE/VLD4Q_LANE:24:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa,  }
+VLD4_LANE/VLD4Q_LANE:25:result_int16x4 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD4_LANE/VLD4Q_LANE:26:result_int32x2 [] = { fffffff2, fffffff3,  }
+VLD4_LANE/VLD4Q_LANE:27:result_int64x1 [] = { 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:28:result_uint8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD4_LANE/VLD4Q_LANE:29:result_uint16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:30:result_uint32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:31:result_uint64x1 [] = { 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:32:result_poly8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD4_LANE/VLD4Q_LANE:33:result_poly16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:34:result_float32x2 [] = { c1600000, c1500000,  }
+VLD4_LANE/VLD4Q_LANE:35:result_float16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:36:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:37:result_int16x8 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD4_LANE/VLD4Q_LANE:38:result_int32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:40:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:41:result_uint16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:42:result_uint32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:45:result_poly16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:46:result_float32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:47:result_float16x8 [] = { cc00, cb80, cb00, ca80, aaaa, aaaa, aaaa, aaaa,  }
+
+VLD4_LANE/VLD4Q_LANE chunk 2 output:
+VLD4_LANE/VLD4Q_LANE:48:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa, ffffffaa,  }
+VLD4_LANE/VLD4Q_LANE:49:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_LANE/VLD4Q_LANE:50:result_int32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:51:result_int64x1 [] = { 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:52:result_uint8x8 [] = { f0, f1, f2, f3, aa, aa, aa, aa,  }
+VLD4_LANE/VLD4Q_LANE:53:result_uint16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:54:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD4_LANE/VLD4Q_LANE:55:result_uint64x1 [] = { 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:56:result_poly8x8 [] = { f0, f1, f2, f3, aa, aa, aa, aa,  }
+VLD4_LANE/VLD4Q_LANE:57:result_poly16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:58:result_float32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:59:result_float16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:60:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:61:result_int16x8 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD4_LANE/VLD4Q_LANE:62:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_LANE/VLD4Q_LANE:63:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:64:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:65:result_uint16x8 [] = { aaaa, aaaa, aaaa, aaaa, fff0, fff1, fff2, fff3,  }
+VLD4_LANE/VLD4Q_LANE:66:result_uint32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:67:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:68:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:69:result_poly16x8 [] = { aaaa, aaaa, aaaa, aaaa, fff0, fff1, fff2, fff3,  }
+VLD4_LANE/VLD4Q_LANE:70:result_float32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+VLD4_LANE/VLD4Q_LANE:71:result_float16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+
+VLD4_LANE/VLD4Q_LANE chunk 3 output:
+VLD4_LANE/VLD4Q_LANE:72:result_int8x8 [] = { ffffffaa, ffffffaa, ffffffaa, ffffffaa, fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_LANE/VLD4Q_LANE:73:result_int16x4 [] = { ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD4_LANE/VLD4Q_LANE:74:result_int32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:75:result_int64x1 [] = { 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:76:result_uint8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD4_LANE/VLD4Q_LANE:77:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_LANE/VLD4Q_LANE:78:result_uint32x2 [] = { fffffff2, fffffff3,  }
+VLD4_LANE/VLD4Q_LANE:79:result_uint64x1 [] = { 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:80:result_poly8x8 [] = { aa, aa, aa, aa, aa, aa, aa, aa,  }
+VLD4_LANE/VLD4Q_LANE:81:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_LANE/VLD4Q_LANE:82:result_float32x2 [] = { aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:83:result_float16x4 [] = { aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:84:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:85:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, ffffaaaa, ffffaaaa, ffffaaaa, ffffaaaa,  }
+VLD4_LANE/VLD4Q_LANE:86:result_int32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:87:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:88:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:89:result_uint16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:90:result_uint32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:91:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_LANE/VLD4Q_LANE:92:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_LANE/VLD4Q_LANE:93:result_poly16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+VLD4_LANE/VLD4Q_LANE:94:result_float32x4 [] = { aaaaaaaa, aaaaaaaa, aaaaaaaa, aaaaaaaa,  }
+VLD4_LANE/VLD4Q_LANE:95:result_float16x8 [] = { aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa, aaaa,  }
+
+VLD2_DUP/VLD2Q_DUP chunk 0 output:
+VLD2_DUP/VLD2Q_DUP:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff0, fffffff1, fffffff0, fffffff1, fffffff0, fffffff1,  }
+VLD2_DUP/VLD2Q_DUP:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff0, fffffff1,  }
+VLD2_DUP/VLD2Q_DUP:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD2_DUP/VLD2Q_DUP:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD2_DUP/VLD2Q_DUP:4:result_uint8x8 [] = { f0, f1, f0, f1, f0, f1, f0, f1,  }
+VLD2_DUP/VLD2Q_DUP:5:result_uint16x4 [] = { fff0, fff1, fff0, fff1,  }
+VLD2_DUP/VLD2Q_DUP:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD2_DUP/VLD2Q_DUP:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD2_DUP/VLD2Q_DUP:8:result_poly8x8 [] = { f0, f1, f0, f1, f0, f1, f0, f1,  }
+VLD2_DUP/VLD2Q_DUP:9:result_poly16x4 [] = { fff0, fff1, fff0, fff1,  }
+VLD2_DUP/VLD2Q_DUP:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD2_DUP/VLD2Q_DUP:11:result_float16x4 [] = { cc00, cb80, cc00, cb80,  }
+VLD2_DUP/VLD2Q_DUP:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_DUP/VLD2Q_DUP:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD2_DUP/VLD2Q_DUP:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD2_DUP/VLD2Q_DUP:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2_DUP/VLD2Q_DUP:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_DUP/VLD2Q_DUP:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD2_DUP/VLD2Q_DUP:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD2_DUP/VLD2Q_DUP:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2_DUP/VLD2Q_DUP:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_DUP/VLD2Q_DUP:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD2_DUP/VLD2Q_DUP:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD2_DUP/VLD2Q_DUP:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VLD2_DUP/VLD2Q_DUP chunk 1 output:
+VLD2_DUP/VLD2Q_DUP:24:result_int8x8 [] = { fffffff0, fffffff1, fffffff0, fffffff1, fffffff0, fffffff1, fffffff0, fffffff1,  }
+VLD2_DUP/VLD2Q_DUP:25:result_int16x4 [] = { fffffff0, fffffff1, fffffff0, fffffff1,  }
+VLD2_DUP/VLD2Q_DUP:26:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD2_DUP/VLD2Q_DUP:27:result_int64x1 [] = { fffffffffffffff1,  }
+VLD2_DUP/VLD2Q_DUP:28:result_uint8x8 [] = { f0, f1, f0, f1, f0, f1, f0, f1,  }
+VLD2_DUP/VLD2Q_DUP:29:result_uint16x4 [] = { fff0, fff1, fff0, fff1,  }
+VLD2_DUP/VLD2Q_DUP:30:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD2_DUP/VLD2Q_DUP:31:result_uint64x1 [] = { fffffffffffffff1,  }
+VLD2_DUP/VLD2Q_DUP:32:result_poly8x8 [] = { f0, f1, f0, f1, f0, f1, f0, f1,  }
+VLD2_DUP/VLD2Q_DUP:33:result_poly16x4 [] = { fff0, fff1, fff0, fff1,  }
+VLD2_DUP/VLD2Q_DUP:34:result_float32x2 [] = { c1800000, c1700000,  }
+VLD2_DUP/VLD2Q_DUP:35:result_float16x4 [] = { cc00, cb80, cc00, cb80,  }
+VLD2_DUP/VLD2Q_DUP:36:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_DUP/VLD2Q_DUP:37:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD2_DUP/VLD2Q_DUP:38:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD2_DUP/VLD2Q_DUP:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2_DUP/VLD2Q_DUP:40:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_DUP/VLD2Q_DUP:41:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD2_DUP/VLD2Q_DUP:42:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD2_DUP/VLD2Q_DUP:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD2_DUP/VLD2Q_DUP:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD2_DUP/VLD2Q_DUP:45:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD2_DUP/VLD2Q_DUP:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD2_DUP/VLD2Q_DUP:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VLD3_DUP/VLD3Q_DUP chunk 0 output:
+VLD3_DUP/VLD3Q_DUP:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff0, fffffff1, fffffff2, fffffff0, fffffff1,  }
+VLD3_DUP/VLD3Q_DUP:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff0,  }
+VLD3_DUP/VLD3Q_DUP:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD3_DUP/VLD3Q_DUP:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD3_DUP/VLD3Q_DUP:4:result_uint8x8 [] = { f0, f1, f2, f0, f1, f2, f0, f1,  }
+VLD3_DUP/VLD3Q_DUP:5:result_uint16x4 [] = { fff0, fff1, fff2, fff0,  }
+VLD3_DUP/VLD3Q_DUP:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD3_DUP/VLD3Q_DUP:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD3_DUP/VLD3Q_DUP:8:result_poly8x8 [] = { f0, f1, f2, f0, f1, f2, f0, f1,  }
+VLD3_DUP/VLD3Q_DUP:9:result_poly16x4 [] = { fff0, fff1, fff2, fff0,  }
+VLD3_DUP/VLD3Q_DUP:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD3_DUP/VLD3Q_DUP:11:result_float16x4 [] = { cc00, cb80, cb00, cc00,  }
+VLD3_DUP/VLD3Q_DUP:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD3_DUP/VLD3Q_DUP:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_DUP/VLD3Q_DUP:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD3_DUP/VLD3Q_DUP:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_DUP/VLD3Q_DUP:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD3_DUP/VLD3Q_DUP:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VLD3_DUP/VLD3Q_DUP chunk 1 output:
+VLD3_DUP/VLD3Q_DUP:24:result_int8x8 [] = { fffffff2, fffffff0, fffffff1, fffffff2, fffffff0, fffffff1, fffffff2, fffffff0,  }
+VLD3_DUP/VLD3Q_DUP:25:result_int16x4 [] = { fffffff1, fffffff2, fffffff0, fffffff1,  }
+VLD3_DUP/VLD3Q_DUP:26:result_int32x2 [] = { fffffff2, fffffff0,  }
+VLD3_DUP/VLD3Q_DUP:27:result_int64x1 [] = { fffffffffffffff1,  }
+VLD3_DUP/VLD3Q_DUP:28:result_uint8x8 [] = { f2, f0, f1, f2, f0, f1, f2, f0,  }
+VLD3_DUP/VLD3Q_DUP:29:result_uint16x4 [] = { fff1, fff2, fff0, fff1,  }
+VLD3_DUP/VLD3Q_DUP:30:result_uint32x2 [] = { fffffff2, fffffff0,  }
+VLD3_DUP/VLD3Q_DUP:31:result_uint64x1 [] = { fffffffffffffff1,  }
+VLD3_DUP/VLD3Q_DUP:32:result_poly8x8 [] = { f2, f0, f1, f2, f0, f1, f2, f0,  }
+VLD3_DUP/VLD3Q_DUP:33:result_poly16x4 [] = { fff1, fff2, fff0, fff1,  }
+VLD3_DUP/VLD3Q_DUP:34:result_float32x2 [] = { c1600000, c1800000,  }
+VLD3_DUP/VLD3Q_DUP:35:result_float16x4 [] = { cb80, cb00, cc00, cb80,  }
+VLD3_DUP/VLD3Q_DUP:36:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:37:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:38:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD3_DUP/VLD3Q_DUP:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_DUP/VLD3Q_DUP:40:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:41:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:42:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD3_DUP/VLD3Q_DUP:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_DUP/VLD3Q_DUP:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:45:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD3_DUP/VLD3Q_DUP:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VLD3_DUP/VLD3Q_DUP chunk 2 output:
+VLD3_DUP/VLD3Q_DUP:48:result_int8x8 [] = { fffffff1, fffffff2, fffffff0, fffffff1, fffffff2, fffffff0, fffffff1, fffffff2,  }
+VLD3_DUP/VLD3Q_DUP:49:result_int16x4 [] = { fffffff2, fffffff0, fffffff1, fffffff2,  }
+VLD3_DUP/VLD3Q_DUP:50:result_int32x2 [] = { fffffff1, fffffff2,  }
+VLD3_DUP/VLD3Q_DUP:51:result_int64x1 [] = { fffffffffffffff2,  }
+VLD3_DUP/VLD3Q_DUP:52:result_uint8x8 [] = { f1, f2, f0, f1, f2, f0, f1, f2,  }
+VLD3_DUP/VLD3Q_DUP:53:result_uint16x4 [] = { fff2, fff0, fff1, fff2,  }
+VLD3_DUP/VLD3Q_DUP:54:result_uint32x2 [] = { fffffff1, fffffff2,  }
+VLD3_DUP/VLD3Q_DUP:55:result_uint64x1 [] = { fffffffffffffff2,  }
+VLD3_DUP/VLD3Q_DUP:56:result_poly8x8 [] = { f1, f2, f0, f1, f2, f0, f1, f2,  }
+VLD3_DUP/VLD3Q_DUP:57:result_poly16x4 [] = { fff2, fff0, fff1, fff2,  }
+VLD3_DUP/VLD3Q_DUP:58:result_float32x2 [] = { c1700000, c1600000,  }
+VLD3_DUP/VLD3Q_DUP:59:result_float16x4 [] = { cb00, cc00, cb80, cb00,  }
+VLD3_DUP/VLD3Q_DUP:60:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:61:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:62:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD3_DUP/VLD3Q_DUP:63:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_DUP/VLD3Q_DUP:64:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:65:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:66:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD3_DUP/VLD3Q_DUP:67:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD3_DUP/VLD3Q_DUP:68:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD3_DUP/VLD3Q_DUP:69:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD3_DUP/VLD3Q_DUP:70:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD3_DUP/VLD3Q_DUP:71:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VLD4_DUP/VLD4Q_DUP chunk 0 output:
+VLD4_DUP/VLD4Q_DUP:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD4_DUP/VLD4Q_DUP:3:result_int64x1 [] = { fffffffffffffff0,  }
+VLD4_DUP/VLD4Q_DUP:4:result_uint8x8 [] = { f0, f1, f2, f3, f0, f1, f2, f3,  }
+VLD4_DUP/VLD4Q_DUP:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_DUP/VLD4Q_DUP:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD4_DUP/VLD4Q_DUP:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VLD4_DUP/VLD4Q_DUP:8:result_poly8x8 [] = { f0, f1, f2, f3, f0, f1, f2, f3,  }
+VLD4_DUP/VLD4Q_DUP:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_DUP/VLD4Q_DUP:10:result_float32x2 [] = { c1800000, c1700000,  }
+VLD4_DUP/VLD4Q_DUP:11:result_float16x4 [] = { cc00, cb80, cb00, ca80,  }
+VLD4_DUP/VLD4Q_DUP:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_DUP/VLD4Q_DUP:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_DUP/VLD4Q_DUP:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VLD4_DUP/VLD4Q_DUP chunk 1 output:
+VLD4_DUP/VLD4Q_DUP:24:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:25:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:26:result_int32x2 [] = { fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:27:result_int64x1 [] = { fffffffffffffff1,  }
+VLD4_DUP/VLD4Q_DUP:28:result_uint8x8 [] = { f0, f1, f2, f3, f0, f1, f2, f3,  }
+VLD4_DUP/VLD4Q_DUP:29:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_DUP/VLD4Q_DUP:30:result_uint32x2 [] = { fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:31:result_uint64x1 [] = { fffffffffffffff1,  }
+VLD4_DUP/VLD4Q_DUP:32:result_poly8x8 [] = { f0, f1, f2, f3, f0, f1, f2, f3,  }
+VLD4_DUP/VLD4Q_DUP:33:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_DUP/VLD4Q_DUP:34:result_float32x2 [] = { c1600000, c1500000,  }
+VLD4_DUP/VLD4Q_DUP:35:result_float16x4 [] = { cc00, cb80, cb00, ca80,  }
+VLD4_DUP/VLD4Q_DUP:36:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:37:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:38:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_DUP/VLD4Q_DUP:40:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:41:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:42:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_DUP/VLD4Q_DUP:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:45:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VLD4_DUP/VLD4Q_DUP chunk 2 output:
+VLD4_DUP/VLD4Q_DUP:48:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:49:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:50:result_int32x2 [] = { fffffff0, fffffff1,  }
+VLD4_DUP/VLD4Q_DUP:51:result_int64x1 [] = { fffffffffffffff2,  }
+VLD4_DUP/VLD4Q_DUP:52:result_uint8x8 [] = { f0, f1, f2, f3, f0, f1, f2, f3,  }
+VLD4_DUP/VLD4Q_DUP:53:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_DUP/VLD4Q_DUP:54:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VLD4_DUP/VLD4Q_DUP:55:result_uint64x1 [] = { fffffffffffffff2,  }
+VLD4_DUP/VLD4Q_DUP:56:result_poly8x8 [] = { f0, f1, f2, f3, f0, f1, f2, f3,  }
+VLD4_DUP/VLD4Q_DUP:57:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_DUP/VLD4Q_DUP:58:result_float32x2 [] = { c1800000, c1700000,  }
+VLD4_DUP/VLD4Q_DUP:59:result_float16x4 [] = { cc00, cb80, cb00, ca80,  }
+VLD4_DUP/VLD4Q_DUP:60:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:61:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:62:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:63:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_DUP/VLD4Q_DUP:64:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:65:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:66:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:67:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_DUP/VLD4Q_DUP:68:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:69:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:70:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:71:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VLD4_DUP/VLD4Q_DUP chunk 3 output:
+VLD4_DUP/VLD4Q_DUP:72:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:73:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:74:result_int32x2 [] = { fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:75:result_int64x1 [] = { fffffffffffffff3,  }
+VLD4_DUP/VLD4Q_DUP:76:result_uint8x8 [] = { f0, f1, f2, f3, f0, f1, f2, f3,  }
+VLD4_DUP/VLD4Q_DUP:77:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_DUP/VLD4Q_DUP:78:result_uint32x2 [] = { fffffff2, fffffff3,  }
+VLD4_DUP/VLD4Q_DUP:79:result_uint64x1 [] = { fffffffffffffff3,  }
+VLD4_DUP/VLD4Q_DUP:80:result_poly8x8 [] = { f0, f1, f2, f3, f0, f1, f2, f3,  }
+VLD4_DUP/VLD4Q_DUP:81:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VLD4_DUP/VLD4Q_DUP:82:result_float32x2 [] = { c1600000, c1500000,  }
+VLD4_DUP/VLD4Q_DUP:83:result_float16x4 [] = { cc00, cb80, cb00, ca80,  }
+VLD4_DUP/VLD4Q_DUP:84:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:85:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:86:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:87:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_DUP/VLD4Q_DUP:88:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:89:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:90:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:91:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VLD4_DUP/VLD4Q_DUP:92:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VLD4_DUP/VLD4Q_DUP:93:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VLD4_DUP/VLD4Q_DUP:94:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VLD4_DUP/VLD4Q_DUP:95:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMLA output:
+VMLA:0:result_int8x8 [] = { ffffffdf, ffffffe0, ffffffe1, ffffffe2, ffffffe3, ffffffe4, ffffffe5, ffffffe6,  }
+VMLA:1:result_int16x4 [] = { 1f8c, 1f8d, 1f8e, 1f8f,  }
+VMLA:2:result_int32x2 [] = { 2bf7, 2bf8,  }
+VMLA:3:result_int64x1 [] = { 3333333333333333,  }
+VMLA:4:result_uint8x8 [] = { 20, 21, 22, 23, 24, 25, 26, 27,  }
+VMLA:5:result_uint16x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLA:6:result_uint32x2 [] = { 43ac, 43ad,  }
+VMLA:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLA:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLA:10:result_float32x2 [] = { 43a14e76, 43a1ce76,  }
+VMLA:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMLA:12:result_int8x16 [] = { f, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19, 1a, 1b, 1c, 1d, 1e,  }
+VMLA:13:result_int16x8 [] = { 4830, 4831, 4832, 4833, 4834, 4835, 4836, 4837,  }
+VMLA:14:result_int32x4 [] = { 470f, 4710, 4711, 4712,  }
+VMLA:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLA:16:result_uint8x16 [] = { ac, ad, ae, af, b0, b1, b2, b3, b4, b5, b6, b7, b8, b9, ba, bb,  }
+VMLA:17:result_uint16x8 [] = { 3e07, 3e08, 3e09, 3e0a, 3e0b, 3e0c, 3e0d, 3e0e,  }
+VMLA:18:result_uint32x4 [] = { 3620, 3621, 3622, 3623,  }
+VMLA:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLA:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLA:22:result_float32x4 [] = { 45f0ae15, 45f0b615, 45f0be15, 45f0c615,  }
+VMLA:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMLS output:
+VMLS:0:result_int8x8 [] = { 1, 2, 3, 4, 5, 6, 7, 8,  }
+VMLS:1:result_int16x4 [] = { ffffe054, ffffe055, ffffe056, ffffe057,  }
+VMLS:2:result_int32x2 [] = { ffffd3e9, ffffd3ea,  }
+VMLS:3:result_int64x1 [] = { 3333333333333333,  }
+VMLS:4:result_uint8x8 [] = { c0, c1, c2, c3, c4, c5, c6, c7,  }
+VMLS:5:result_uint16x4 [] = { c1d9, c1da, c1db, c1dc,  }
+VMLS:6:result_uint32x2 [] = { ffffbc34, ffffbc35,  }
+VMLS:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLS:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLS:10:result_float32x2 [] = { c3b14e76, c3b0ce76,  }
+VMLS:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMLS:12:result_int8x16 [] = { ffffffd1, ffffffd2, ffffffd3, ffffffd4, ffffffd5, ffffffd6, ffffffd7, ffffffd8, ffffffd9, ffffffda, ffffffdb, ffffffdc, ffffffdd, ffffffde, ffffffdf, ffffffe0,  }
+VMLS:13:result_int16x8 [] = { ffffb7b0, ffffb7b1, ffffb7b2, ffffb7b3, ffffb7b4, ffffb7b5, ffffb7b6, ffffb7b7,  }
+VMLS:14:result_int32x4 [] = { ffffb8d1, ffffb8d2, ffffb8d3, ffffb8d4,  }
+VMLS:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLS:16:result_uint8x16 [] = { 34, 35, 36, 37, 38, 39, 3a, 3b, 3c, 3d, 3e, 3f, 40, 41, 42, 43,  }
+VMLS:17:result_uint16x8 [] = { c1d9, c1da, c1db, c1dc, c1dd, c1de, c1df, c1e0,  }
+VMLS:18:result_uint32x4 [] = { ffffc9c0, ffffc9c1, ffffc9c2, ffffc9c3,  }
+VMLS:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLS:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLS:22:result_float32x4 [] = { c5f1ae15, c5f1a615, c5f19e15, c5f19615,  }
+VMLS:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMUL output:
+VMUL:0:result_int8x8 [] = { fffffff0, 1, 12, 23, 34, 45, 56, 67,  }
+VMUL:1:result_int16x4 [] = { fffffde0, fffffe02, fffffe24, fffffe46,  }
+VMUL:2:result_int32x2 [] = { fffffcd0, fffffd03,  }
+VMUL:3:result_int64x1 [] = { 3333333333333333,  }
+VMUL:4:result_uint8x8 [] = { c0, 4, 48, 8c, d0, 14, 58, 9c,  }
+VMUL:5:result_uint16x4 [] = { fab0, fb05, fb5a, fbaf,  }
+VMUL:6:result_uint32x2 [] = { fffff9a0, fffffa06,  }
+VMUL:7:result_uint64x1 [] = { 3333333333333333,  }
+VMUL:8:result_poly8x8 [] = { c0, 84, 48, c, d0, 94, 58, 1c,  }
+VMUL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMUL:10:result_float32x2 [] = { c4053333, c3f9c000,  }
+VMUL:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMUL:12:result_int8x16 [] = { ffffff90, 7, 7e, fffffff5, 6c, ffffffe3, 5a, ffffffd1, 48, ffffffbf, 36, ffffffad, 24, ffffff9b, 12, ffffff89,  }
+VMUL:13:result_int16x8 [] = { fffff780, fffff808, fffff890, fffff918, fffff9a0, fffffa28, fffffab0, fffffb38,  }
+VMUL:14:result_int32x4 [] = { fffff670, fffff709, fffff7a2, fffff83b,  }
+VMUL:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMUL:16:result_uint8x16 [] = { 60, a, b4, 5e, 8, b2, 5c, 6, b0, 5a, 4, ae, 58, 2, ac, 56,  }
+VMUL:17:result_uint16x8 [] = { f450, f50b, f5c6, f681, f73c, f7f7, f8b2, f96d,  }
+VMUL:18:result_uint32x4 [] = { fffff340, fffff40c, fffff4d8, fffff5a4,  }
+VMUL:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMUL:20:result_poly8x16 [] = { 60, ca, 34, 9e, c8, 62, 9c, 36, 30, 9a, 64, ce, 98, 32, cc, 66,  }
+VMUL:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMUL:22:result_float32x4 [] = { c4c73333, c4bac000, c4ae4ccd, c4a1d999,  }
+VMUL:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMUL_LANE output:
+VMUL_LANE:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_LANE:1:result_int16x4 [] = { ffffffc0, ffffffc4, ffffffc8, ffffffcc,  }
+VMUL_LANE:2:result_int32x2 [] = { fffffde0, fffffe02,  }
+VMUL_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VMUL_LANE:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_LANE:5:result_uint16x4 [] = { bbc0, c004, c448, c88c,  }
+VMUL_LANE:6:result_uint32x2 [] = { fffface0, ffffb212,  }
+VMUL_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VMUL_LANE:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_LANE:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMUL_LANE:10:result_float32x2 [] = { c3b66666, c3ab0000,  }
+VMUL_LANE:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMUL_LANE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_LANE:13:result_int16x8 [] = { ffffffc0, ffffffc4, ffffffc8, ffffffcc, ffffffd0, ffffffd4, ffffffd8, ffffffdc,  }
+VMUL_LANE:14:result_int32x4 [] = { fffffde0, fffffe02, fffffe24, fffffe46,  }
+VMUL_LANE:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMUL_LANE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_LANE:17:result_uint16x8 [] = { bbc0, c004, c448, c88c, ccd0, d114, d558, d99c,  }
+VMUL_LANE:18:result_uint32x4 [] = { fffface0, ffffb212, ffffb744, ffffbc76,  }
+VMUL_LANE:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMUL_LANE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_LANE:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMUL_LANE:22:result_float32x4 [] = { c3b66666, c3ab0000, c39f9999, c3943333,  }
+VMUL_LANE:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMUL_N output:
+VMUL_N:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_N:1:result_int16x4 [] = { fffffef0, ffffff01, ffffff12, ffffff23,  }
+VMUL_N:2:result_int32x2 [] = { fffffde0, fffffe02,  }
+VMUL_N:3:result_int64x1 [] = { 3333333333333333,  }
+VMUL_N:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_N:5:result_uint16x4 [] = { fcd0, fd03, fd36, fd69,  }
+VMUL_N:6:result_uint32x2 [] = { fffffbc0, fffffc04,  }
+VMUL_N:7:result_uint64x1 [] = { 3333333333333333,  }
+VMUL_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMUL_N:10:result_float32x2 [] = { c3b26666, c3a74000,  }
+VMUL_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMUL_N:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_N:13:result_int16x8 [] = { fffffab0, fffffb05, fffffb5a, fffffbaf, fffffc04, fffffc59, fffffcae, fffffd03,  }
+VMUL_N:14:result_int32x4 [] = { fffff9a0, fffffa06, fffffa6c, fffffad2,  }
+VMUL_N:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMUL_N:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_N:17:result_uint16x8 [] = { f890, f907, f97e, f9f5, fa6c, fae3, fb5a, fbd1,  }
+VMUL_N:18:result_uint32x4 [] = { fffff780, fffff808, fffff890, fffff918,  }
+VMUL_N:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMUL_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMUL_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMUL_N:22:result_float32x4 [] = { c4b1cccd, c4a6b000, c49b9333, c4907667,  }
+VMUL_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMULL_N output:
+VMULL_N:0:result_int32x4 [] = { 11000, 11000, 11000, 11000,  }
+VMULL_N:1:result_int64x2 [] = { 22000, 22000,  }
+VMULL_N:2:result_uint32x4 [] = { 33000, 33000, 33000, 33000,  }
+VMULL_N:3:result_uint64x2 [] = { 44000, 44000,  }
+
+VMLA_LANE output:
+VMLA_LANE:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_LANE:1:result_int16x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLA_LANE:2:result_int32x2 [] = { 3e07, 3e08,  }
+VMLA_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VMLA_LANE:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_LANE:5:result_uint16x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLA_LANE:6:result_uint32x2 [] = { 3e07, 3e08,  }
+VMLA_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLA_LANE:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_LANE:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLA_LANE:10:result_float32x2 [] = { 4418c687, 44190687,  }
+VMLA_LANE:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMLA_LANE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_LANE:13:result_int16x8 [] = { 3e07, 3e08, 3e09, 3e0a, 3e0b, 3e0c, 3e0d, 3e0e,  }
+VMLA_LANE:14:result_int32x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLA_LANE:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLA_LANE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_LANE:17:result_uint16x8 [] = { 3e07, 3e08, 3e09, 3e0a, 3e0b, 3e0c, 3e0d, 3e0e,  }
+VMLA_LANE:18:result_uint32x4 [] = { 3e07, 3e08, 3e09, 3e0a,  }
+VMLA_LANE:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLA_LANE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_LANE:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLA_LANE:22:result_float32x4 [] = { 441a3168, 441a7168, 441ab168, 441af168,  }
+VMLA_LANE:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMLS_LANE output:
+VMLS_LANE:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_LANE:1:result_int16x4 [] = { ffffc1d9, ffffc1da, ffffc1db, ffffc1dc,  }
+VMLS_LANE:2:result_int32x2 [] = { ffffc1d9, ffffc1da,  }
+VMLS_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VMLS_LANE:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_LANE:5:result_uint16x4 [] = { c1d9, c1da, c1db, c1dc,  }
+VMLS_LANE:6:result_uint32x2 [] = { ffffc1d9, ffffc1da,  }
+VMLS_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLS_LANE:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_LANE:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLS_LANE:10:result_float32x2 [] = { c420c687, c4208687,  }
+VMLS_LANE:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMLS_LANE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_LANE:13:result_int16x8 [] = { ffffc1d9, ffffc1da, ffffc1db, ffffc1dc, ffffc1dd, ffffc1de, ffffc1df, ffffc1e0,  }
+VMLS_LANE:14:result_int32x4 [] = { ffffc1d9, ffffc1da, ffffc1db, ffffc1dc,  }
+VMLS_LANE:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLS_LANE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_LANE:17:result_uint16x8 [] = { c1d9, c1da, c1db, c1dc, c1dd, c1de, c1df, c1e0,  }
+VMLS_LANE:18:result_uint32x4 [] = { ffffc1d9, ffffc1da, ffffc1db, ffffc1dc,  }
+VMLS_LANE:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLS_LANE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_LANE:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLS_LANE:22:result_float32x4 [] = { c4223168, c421f168, c421b168, c4217168,  }
+VMLS_LANE:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMLA_N output:
+VMLA_N:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_N:1:result_int16x4 [] = { 595, 596, 597, 598,  }
+VMLA_N:2:result_int32x2 [] = { b3a, b3b,  }
+VMLA_N:3:result_int64x1 [] = { 3333333333333333,  }
+VMLA_N:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_N:5:result_uint16x4 [] = { 10df, 10e0, 10e1, 10e2,  }
+VMLA_N:6:result_uint32x2 [] = { 1684, 1685,  }
+VMLA_N:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLA_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLA_N:10:result_float32x2 [] = { 4497deb8, 4497feb8,  }
+VMLA_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMLA_N:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_N:13:result_int16x8 [] = { 1c29, 1c2a, 1c2b, 1c2c, 1c2d, 1c2e, 1c2f, 1c30,  }
+VMLA_N:14:result_int32x4 [] = { 21ce, 21cf, 21d0, 21d1,  }
+VMLA_N:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLA_N:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_N:17:result_uint16x8 [] = { 2773, 2774, 2775, 2776, 2777, 2778, 2779, 277a,  }
+VMLA_N:18:result_uint32x4 [] = { 2d18, 2d19, 2d1a, 2d1b,  }
+VMLA_N:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLA_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLA_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLA_N:22:result_float32x4 [] = { 4568087b, 4568187b, 4568287b, 4568387b,  }
+VMLA_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMLS_N output:
+VMLS_N:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_N:1:result_int16x4 [] = { fffffa4b, fffffa4c, fffffa4d, fffffa4e,  }
+VMLS_N:2:result_int32x2 [] = { fffff4a6, fffff4a7,  }
+VMLS_N:3:result_int64x1 [] = { 3333333333333333,  }
+VMLS_N:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_N:5:result_uint16x4 [] = { ef01, ef02, ef03, ef04,  }
+VMLS_N:6:result_uint32x2 [] = { ffffe95c, ffffe95d,  }
+VMLS_N:7:result_uint64x1 [] = { 3333333333333333,  }
+VMLS_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMLS_N:10:result_float32x2 [] = { c49bdeb8, c49bbeb8,  }
+VMLS_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMLS_N:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_N:13:result_int16x8 [] = { ffffe3b7, ffffe3b8, ffffe3b9, ffffe3ba, ffffe3bb, ffffe3bc, ffffe3bd, ffffe3be,  }
+VMLS_N:14:result_int32x4 [] = { ffffde12, ffffde13, ffffde14, ffffde15,  }
+VMLS_N:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLS_N:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_N:17:result_uint16x8 [] = { d86d, d86e, d86f, d870, d871, d872, d873, d874,  }
+VMLS_N:18:result_uint32x4 [] = { ffffd2c8, ffffd2c9, ffffd2ca, ffffd2cb,  }
+VMLS_N:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMLS_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VMLS_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMLS_N:22:result_float32x4 [] = { c56a087b, c569f87b, c569e87b, c569d87b,  }
+VMLS_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSLI_N output:
+VSLI_N:0:result_int8x8 [] = { 20, 21, 22, 23, 24, 25, 26, 27,  }
+VSLI_N:1:result_int16x4 [] = { ffffffe0, ffffffe1, ffffffe2, ffffffe3,  }
+VSLI_N:2:result_int32x2 [] = { 6, 7,  }
+VSLI_N:3:result_int64x1 [] = { 64fffffff0,  }
+VSLI_N:4:result_uint8x8 [] = { 50, 51, 52, 53, 50, 51, 52, 53,  }
+VSLI_N:5:result_uint16x4 [] = { 7bf0, 7bf1, 7bf2, 7bf3,  }
+VSLI_N:6:result_uint32x2 [] = { 3ffffff0, 3ffffff1,  }
+VSLI_N:7:result_uint64x1 [] = { 10,  }
+VSLI_N:8:result_poly8x8 [] = { 50, 51, 52, 53, 50, 51, 52, 53,  }
+VSLI_N:9:result_poly16x4 [] = { 7bf0, 7bf1, 7bf2, 7bf3,  }
+VSLI_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSLI_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSLI_N:12:result_int8x16 [] = { ffffffd0, ffffffd1, ffffffd2, ffffffd3, ffffffd4, ffffffd5, ffffffd6, ffffffd7, ffffffd8, ffffffd9, ffffffda, ffffffdb, ffffffdc, ffffffdd, ffffffde, ffffffdf,  }
+VSLI_N:13:result_int16x8 [] = { ffffff60, ffffff61, ffffff62, ffffff63, ffffff64, ffffff65, ffffff66, ffffff67,  }
+VSLI_N:14:result_int32x4 [] = { fe2ffff0, fe2ffff1, fe2ffff2, fe2ffff3,  }
+VSLI_N:15:result_int64x2 [] = { 18fff0, 18fff1,  }
+VSLI_N:16:result_uint8x16 [] = { 60, 61, 62, 63, 64, 65, 66, 67, 60, 61, 62, 63, 64, 65, 66, 67,  }
+VSLI_N:17:result_uint16x8 [] = { 3ff0, 3ff1, 3ff2, 3ff3, 3ff4, 3ff5, 3ff6, 3ff7,  }
+VSLI_N:18:result_uint32x4 [] = { 1bfffff0, 1bfffff1, 1bfffff2, 1bfffff3,  }
+VSLI_N:19:result_uint64x2 [] = { 7ffffffffffff0, 7ffffffffffff1,  }
+VSLI_N:20:result_poly8x16 [] = { 60, 61, 62, 63, 64, 65, 66, 67, 60, 61, 62, 63, 64, 65, 66, 67,  }
+VSLI_N:21:result_poly16x8 [] = { 3ff0, 3ff1, 3ff2, 3ff3, 3ff4, 3ff5, 3ff6, 3ff7,  }
+VSLI_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSLI_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSLI_Nmax shift amount output:
+VSLI_N:0:result_int8x8 [] = { 70, 71, 72, 73, 74, 75, 76, 77,  }
+VSLI_N:1:result_int16x4 [] = { 7ff0, 7ff1, 7ff2, 7ff3,  }
+VSLI_N:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VSLI_N:3:result_int64x1 [] = { 7ffffffffffffff0,  }
+VSLI_N:4:result_uint8x8 [] = { 70, 71, 72, 73, 74, 75, 76, 77,  }
+VSLI_N:5:result_uint16x4 [] = { 7ff0, 7ff1, 7ff2, 7ff3,  }
+VSLI_N:6:result_uint32x2 [] = { 7ffffff0, 7ffffff1,  }
+VSLI_N:7:result_uint64x1 [] = { 7ffffffffffffff0,  }
+VSLI_N:8:result_poly8x8 [] = { 70, 71, 72, 73, 74, 75, 76, 77,  }
+VSLI_N:9:result_poly16x4 [] = { 7ff0, 7ff1, 7ff2, 7ff3,  }
+VSLI_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSLI_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSLI_N:12:result_int8x16 [] = { 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 7a, 7b, 7c, 7d, 7e, 7f,  }
+VSLI_N:13:result_int16x8 [] = { 7ff0, 7ff1, 7ff2, 7ff3, 7ff4, 7ff5, 7ff6, 7ff7,  }
+VSLI_N:14:result_int32x4 [] = { 7ffffff0, 7ffffff1, 7ffffff2, 7ffffff3,  }
+VSLI_N:15:result_int64x2 [] = { 7ffffffffffffff0, 7ffffffffffffff1,  }
+VSLI_N:16:result_uint8x16 [] = { 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 7a, 7b, 7c, 7d, 7e, 7f,  }
+VSLI_N:17:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VSLI_N:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VSLI_N:19:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VSLI_N:20:result_poly8x16 [] = { 70, 71, 72, 73, 74, 75, 76, 77, 78, 79, 7a, 7b, 7c, 7d, 7e, 7f,  }
+VSLI_N:21:result_poly16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VSLI_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSLI_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSRI_N output:
+VSRI_N:0:result_int8x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VSRI_N:1:result_int16x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VSRI_N:2:result_int32x2 [] = { 80000001, 80000001,  }
+VSRI_N:3:result_int64x1 [] = { ffffffff00000000,  }
+VSRI_N:4:result_uint8x8 [] = { c5, c5, c5, c5, c5, c5, c5, c5,  }
+VSRI_N:5:result_uint16x4 [] = { ffc0, ffc0, ffc0, ffc0,  }
+VSRI_N:6:result_uint32x2 [] = { fffffff0, fffffff0,  }
+VSRI_N:7:result_uint64x1 [] = { e000000000000000,  }
+VSRI_N:8:result_poly8x8 [] = { c5, c5, c5, c5, c5, c5, c5, c5,  }
+VSRI_N:9:result_poly16x4 [] = { ffc0, ffc0, ffc0, ffc0,  }
+VSRI_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSRI_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSRI_N:12:result_int8x16 [] = { fffffff7, fffffff7, fffffff7, fffffff7, fffffff7, fffffff7, fffffff7, fffffff7, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff, ffffffff,  }
+VSRI_N:13:result_int16x8 [] = { fffffffd, fffffffd, fffffffd, fffffffd, fffffffd, fffffffd, fffffffd, fffffffd,  }
+VSRI_N:14:result_int32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VSRI_N:15:result_int64x2 [] = { ffff000000000000, ffff000000000000,  }
+VSRI_N:16:result_uint8x16 [] = { e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1,  }
+VSRI_N:17:result_uint16x8 [] = { fff0, fff0, fff0, fff0, fff0, fff0, fff0, fff0,  }
+VSRI_N:18:result_uint32x4 [] = { fffffe00, fffffe00, fffffe00, fffffe00,  }
+VSRI_N:19:result_uint64x2 [] = { fffffffffffff800, fffffffffffff800,  }
+VSRI_N:20:result_poly8x16 [] = { e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1, e1,  }
+VSRI_N:21:result_poly16x8 [] = { fff0, fff0, fff0, fff0, fff0, fff0, fff0, fff0,  }
+VSRI_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSRI_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSRI_N max shift amount output:
+VSRI_N:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VSRI_N:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VSRI_N:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VSRI_N:3:result_int64x1 [] = { fffffffffffffff0,  }
+VSRI_N:4:result_uint8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VSRI_N:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VSRI_N:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VSRI_N:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VSRI_N:8:result_poly8x8 [] = { f0, f1, f2, f3, f4, f5, f6, f7,  }
+VSRI_N:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VSRI_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSRI_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSRI_N:12:result_int8x16 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7, fffffff8, fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff,  }
+VSRI_N:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VSRI_N:14:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VSRI_N:15:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VSRI_N:16:result_uint8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VSRI_N:17:result_uint16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VSRI_N:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VSRI_N:19:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VSRI_N:20:result_poly8x16 [] = { f0, f1, f2, f3, f4, f5, f6, f7, f8, f9, fa, fb, fc, fd, fe, ff,  }
+VSRI_N:21:result_poly16x8 [] = { fff0, fff1, fff2, fff3, fff4, fff5, fff6, fff7,  }
+VSRI_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSRI_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VTST/VTSTQ (signed input) output:
+VTST/VTSTQ:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTST/VTSTQ:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTST/VTSTQ:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTST/VTSTQ:3:result_int64x1 [] = { 3333333333333333,  }
+VTST/VTSTQ:4:result_uint8x8 [] = { 0, ff, ff, ff, ff, ff, ff, ff,  }
+VTST/VTSTQ:5:result_uint16x4 [] = { 0, ffff, 0, ffff,  }
+VTST/VTSTQ:6:result_uint32x2 [] = { 0, ffffffff,  }
+VTST/VTSTQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VTST/VTSTQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTST/VTSTQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTST/VTSTQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTST/VTSTQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VTST/VTSTQ:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTST/VTSTQ:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTST/VTSTQ:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTST/VTSTQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTST/VTSTQ:16:result_uint8x16 [] = { 0, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VTST/VTSTQ:17:result_uint16x8 [] = { 0, ffff, 0, ffff, ffff, ffff, ffff, ffff,  }
+VTST/VTSTQ:18:result_uint32x4 [] = { 0, ffffffff, 0, ffffffff,  }
+VTST/VTSTQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTST/VTSTQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTST/VTSTQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTST/VTSTQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTST/VTSTQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VTST/VTSTQ (unsigned input) output:
+VTST/VTSTQ:24:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTST/VTSTQ:25:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTST/VTSTQ:26:result_int32x2 [] = { 33333333, 33333333,  }
+VTST/VTSTQ:27:result_int64x1 [] = { 3333333333333333,  }
+VTST/VTSTQ:28:result_uint8x8 [] = { 0, ff, ff, ff, ff, ff, ff, ff,  }
+VTST/VTSTQ:29:result_uint16x4 [] = { 0, ffff, 0, ffff,  }
+VTST/VTSTQ:30:result_uint32x2 [] = { 0, ffffffff,  }
+VTST/VTSTQ:31:result_uint64x1 [] = { 3333333333333333,  }
+VTST/VTSTQ:32:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTST/VTSTQ:33:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTST/VTSTQ:34:result_float32x2 [] = { 33333333, 33333333,  }
+VTST/VTSTQ:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VTST/VTSTQ:36:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTST/VTSTQ:37:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTST/VTSTQ:38:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTST/VTSTQ:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTST/VTSTQ:40:result_uint8x16 [] = { 0, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VTST/VTSTQ:41:result_uint16x8 [] = { 0, ffff, 0, ffff, ffff, ffff, ffff, ffff,  }
+VTST/VTSTQ:42:result_uint32x4 [] = { 0, ffffffff, 0, ffffffff,  }
+VTST/VTSTQ:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTST/VTSTQ:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTST/VTSTQ:45:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTST/VTSTQ:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTST/VTSTQ:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VADDHN output:
+VADDHN:0:result_int8x8 [] = { 32, 32, 32, 32, 32, 32, 32, 32,  }
+VADDHN:1:result_int16x4 [] = { 32, 32, 32, 32,  }
+VADDHN:2:result_int32x2 [] = { 18, 18,  }
+VADDHN:3:result_int64x1 [] = { 3333333333333333,  }
+VADDHN:4:result_uint8x8 [] = { 3, 3, 3, 3, 3, 3, 3, 3,  }
+VADDHN:5:result_uint16x4 [] = { 37, 37, 37, 37,  }
+VADDHN:6:result_uint32x2 [] = { 3, 3,  }
+VADDHN:7:result_uint64x1 [] = { 3333333333333333,  }
+VADDHN:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDHN:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VADDHN:10:result_float32x2 [] = { 33333333, 33333333,  }
+VADDHN:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VADDHN:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDHN:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VADDHN:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VADDHN:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VADDHN:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDHN:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VADDHN:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VADDHN:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VADDHN:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDHN:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VADDHN:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VADDHN:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRADDHN output:
+VRADDHN:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRADDHN:1:result_int16x4 [] = { 33, 33, 33, 33,  }
+VRADDHN:2:result_int32x2 [] = { 19, 19,  }
+VRADDHN:3:result_int64x1 [] = { 3333333333333333,  }
+VRADDHN:4:result_uint8x8 [] = { 4, 4, 4, 4, 4, 4, 4, 4,  }
+VRADDHN:5:result_uint16x4 [] = { 38, 38, 38, 38,  }
+VRADDHN:6:result_uint32x2 [] = { 4, 4,  }
+VRADDHN:7:result_uint64x1 [] = { 3333333333333333,  }
+VRADDHN:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRADDHN:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRADDHN:10:result_float32x2 [] = { 33333333, 33333333,  }
+VRADDHN:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRADDHN:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRADDHN:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRADDHN:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRADDHN:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRADDHN:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRADDHN:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRADDHN:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRADDHN:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRADDHN:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRADDHN:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRADDHN:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRADDHN:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VADDL output:
+VADDL:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDL:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VADDL:2:result_int32x2 [] = { 33333333, 33333333,  }
+VADDL:3:result_int64x1 [] = { 3333333333333333,  }
+VADDL:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDL:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VADDL:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VADDL:7:result_uint64x1 [] = { 3333333333333333,  }
+VADDL:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VADDL:10:result_float32x2 [] = { 33333333, 33333333,  }
+VADDL:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VADDL:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDL:13:result_int16x8 [] = { ffffffe3, ffffffe4, ffffffe5, ffffffe6, ffffffe7, ffffffe8, ffffffe9, ffffffea,  }
+VADDL:14:result_int32x4 [] = { ffffffe2, ffffffe3, ffffffe4, ffffffe5,  }
+VADDL:15:result_int64x2 [] = { ffffffffffffffe0, ffffffffffffffe1,  }
+VADDL:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDL:17:result_uint16x8 [] = { 1e3, 1e4, 1e5, 1e6, 1e7, 1e8, 1e9, 1ea,  }
+VADDL:18:result_uint32x4 [] = { 1ffe1, 1ffe2, 1ffe3, 1ffe4,  }
+VADDL:19:result_uint64x2 [] = { 1ffffffe0, 1ffffffe1,  }
+VADDL:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDL:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VADDL:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VADDL:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VADDW output:
+VADDW:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDW:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VADDW:2:result_int32x2 [] = { 33333333, 33333333,  }
+VADDW:3:result_int64x1 [] = { 3333333333333333,  }
+VADDW:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDW:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VADDW:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VADDW:7:result_uint64x1 [] = { 3333333333333333,  }
+VADDW:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDW:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VADDW:10:result_float32x2 [] = { 33333333, 33333333,  }
+VADDW:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VADDW:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDW:13:result_int16x8 [] = { ffffffe3, ffffffe4, ffffffe5, ffffffe6, ffffffe7, ffffffe8, ffffffe9, ffffffea,  }
+VADDW:14:result_int32x4 [] = { ffffffe2, ffffffe3, ffffffe4, ffffffe5,  }
+VADDW:15:result_int64x2 [] = { ffffffffffffffe0, ffffffffffffffe1,  }
+VADDW:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDW:17:result_uint16x8 [] = { e3, e4, e5, e6, e7, e8, e9, ea,  }
+VADDW:18:result_uint32x4 [] = { ffe1, ffe2, ffe3, ffe4,  }
+VADDW:19:result_uint64x2 [] = { ffffffe0, ffffffe1,  }
+VADDW:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VADDW:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VADDW:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VADDW:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VHADD/VHADDQ output:
+VHADD/VHADDQ:0:result_int8x8 [] = { fffffff1, fffffff2, fffffff2, fffffff3, fffffff3, fffffff4, fffffff4, fffffff5,  }
+VHADD/VHADDQ:1:result_int16x4 [] = { fffffff1, fffffff1, fffffff2, fffffff2,  }
+VHADD/VHADDQ:2:result_int32x2 [] = { fffffff0, fffffff0,  }
+VHADD/VHADDQ:3:result_int64x1 [] = { 3333333333333333,  }
+VHADD/VHADDQ:4:result_uint8x8 [] = { f1, f2, f2, f3, f3, f4, f4, f5,  }
+VHADD/VHADDQ:5:result_uint16x4 [] = { fff0, fff1, fff1, fff2,  }
+VHADD/VHADDQ:6:result_uint32x2 [] = { fffffff0, fffffff0,  }
+VHADD/VHADDQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VHADD/VHADDQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VHADD/VHADDQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VHADD/VHADDQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VHADD/VHADDQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VHADD/VHADDQ:12:result_int8x16 [] = { fffffff2, fffffff2, fffffff3, fffffff3, fffffff4, fffffff4, fffffff5, fffffff5, fffffff6, fffffff6, fffffff7, fffffff7, fffffff8, fffffff8, fffffff9, fffffff9,  }
+VHADD/VHADDQ:13:result_int16x8 [] = { fffffff1, fffffff2, fffffff2, fffffff3, fffffff3, fffffff4, fffffff4, fffffff5,  }
+VHADD/VHADDQ:14:result_int32x4 [] = { fffffff0, fffffff1, fffffff1, fffffff2,  }
+VHADD/VHADDQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VHADD/VHADDQ:16:result_uint8x16 [] = { f4, f5, f5, f6, f6, f7, f7, f8, f8, f9, f9, fa, fa, fb, fb, fc,  }
+VHADD/VHADDQ:17:result_uint16x8 [] = { fff1, fff1, fff2, fff2, fff3, fff3, fff4, fff4,  }
+VHADD/VHADDQ:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff1, fffffff2,  }
+VHADD/VHADDQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VHADD/VHADDQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VHADD/VHADDQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VHADD/VHADDQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VHADD/VHADDQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRHADD/VRHADDQ output:
+VRHADD/VRHADDQ:0:result_int8x8 [] = { fffffff2, fffffff2, fffffff3, fffffff3, fffffff4, fffffff4, fffffff5, fffffff5,  }
+VRHADD/VRHADDQ:1:result_int16x4 [] = { fffffff1, fffffff2, fffffff2, fffffff3,  }
+VRHADD/VRHADDQ:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VRHADD/VRHADDQ:3:result_int64x1 [] = { 3333333333333333,  }
+VRHADD/VRHADDQ:4:result_uint8x8 [] = { f2, f2, f3, f3, f4, f4, f5, f5,  }
+VRHADD/VRHADDQ:5:result_uint16x4 [] = { fff1, fff1, fff2, fff2,  }
+VRHADD/VRHADDQ:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VRHADD/VRHADDQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VRHADD/VRHADDQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRHADD/VRHADDQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRHADD/VRHADDQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VRHADD/VRHADDQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRHADD/VRHADDQ:12:result_int8x16 [] = { fffffff2, fffffff3, fffffff3, fffffff4, fffffff4, fffffff5, fffffff5, fffffff6, fffffff6, fffffff7, fffffff7, fffffff8, fffffff8, fffffff9, fffffff9, fffffffa,  }
+VRHADD/VRHADDQ:13:result_int16x8 [] = { fffffff2, fffffff2, fffffff3, fffffff3, fffffff4, fffffff4, fffffff5, fffffff5,  }
+VRHADD/VRHADDQ:14:result_int32x4 [] = { fffffff1, fffffff1, fffffff2, fffffff2,  }
+VRHADD/VRHADDQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRHADD/VRHADDQ:16:result_uint8x16 [] = { f5, f5, f6, f6, f7, f7, f8, f8, f9, f9, fa, fa, fb, fb, fc, fc,  }
+VRHADD/VRHADDQ:17:result_uint16x8 [] = { fff1, fff2, fff2, fff3, fff3, fff4, fff4, fff5,  }
+VRHADD/VRHADDQ:18:result_uint32x4 [] = { fffffff1, fffffff1, fffffff2, fffffff2,  }
+VRHADD/VRHADDQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRHADD/VRHADDQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRHADD/VRHADDQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRHADD/VRHADDQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRHADD/VRHADDQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VHSUB/VHSUBQ output:
+VHSUB/VHSUBQ:0:result_int8x8 [] = { fffffffe, ffffffff, ffffffff, 0, 0, 1, 1, 2,  }
+VHSUB/VHSUBQ:1:result_int16x4 [] = { ffffffff, ffffffff, 0, 0,  }
+VHSUB/VHSUBQ:2:result_int32x2 [] = { 0, 0,  }
+VHSUB/VHSUBQ:3:result_int64x1 [] = { 3333333333333333,  }
+VHSUB/VHSUBQ:4:result_uint8x8 [] = { fe, ff, ff, 0, 0, 1, 1, 2,  }
+VHSUB/VHSUBQ:5:result_uint16x4 [] = { ffff, 0, 0, 1,  }
+VHSUB/VHSUBQ:6:result_uint32x2 [] = { 0, 0,  }
+VHSUB/VHSUBQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VHSUB/VHSUBQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VHSUB/VHSUBQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VHSUB/VHSUBQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VHSUB/VHSUBQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VHSUB/VHSUBQ:12:result_int8x16 [] = { fffffffe, fffffffe, ffffffff, ffffffff, 0, 0, 1, 1, 2, 2, 3, 3, 4, 4, 5, 5,  }
+VHSUB/VHSUBQ:13:result_int16x8 [] = { fffffffe, ffffffff, ffffffff, 0, 0, 1, 1, 2,  }
+VHSUB/VHSUBQ:14:result_int32x4 [] = { ffffffff, 0, 0, 1,  }
+VHSUB/VHSUBQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VHSUB/VHSUBQ:16:result_uint8x16 [] = { fb, fc, fc, fd, fd, fe, fe, ff, ff, 0, 0, 1, 1, 2, 2, 3,  }
+VHSUB/VHSUBQ:17:result_uint16x8 [] = { ffff, ffff, 0, 0, 1, 1, 2, 2,  }
+VHSUB/VHSUBQ:18:result_uint32x4 [] = { ffffffff, 0, 0, 1,  }
+VHSUB/VHSUBQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VHSUB/VHSUBQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VHSUB/VHSUBQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VHSUB/VHSUBQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VHSUB/VHSUBQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSUBL output:
+VSUBL:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBL:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSUBL:2:result_int32x2 [] = { 33333333, 33333333,  }
+VSUBL:3:result_int64x1 [] = { 3333333333333333,  }
+VSUBL:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBL:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSUBL:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VSUBL:7:result_uint64x1 [] = { 3333333333333333,  }
+VSUBL:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBL:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSUBL:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSUBL:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSUBL:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBL:13:result_int16x8 [] = { fffffffd, fffffffe, ffffffff, 0, 1, 2, 3, 4,  }
+VSUBL:14:result_int32x4 [] = { fffffffe, ffffffff, 0, 1,  }
+VSUBL:15:result_int64x2 [] = { 0, 1,  }
+VSUBL:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBL:17:result_uint16x8 [] = { fffd, fffe, ffff, 0, 1, 2, 3, 4,  }
+VSUBL:18:result_uint32x4 [] = { ffffffff, 0, 1, 2,  }
+VSUBL:19:result_uint64x2 [] = { 0, 1,  }
+VSUBL:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBL:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSUBL:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSUBL:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSUBW output:
+VSUBW:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBW:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSUBW:2:result_int32x2 [] = { 33333333, 33333333,  }
+VSUBW:3:result_int64x1 [] = { 3333333333333333,  }
+VSUBW:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBW:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSUBW:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VSUBW:7:result_uint64x1 [] = { 3333333333333333,  }
+VSUBW:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBW:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSUBW:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSUBW:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSUBW:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBW:13:result_int16x8 [] = { fffffffd, fffffffe, ffffffff, 0, 1, 2, 3, 4,  }
+VSUBW:14:result_int32x4 [] = { fffffffe, ffffffff, 0, 1,  }
+VSUBW:15:result_int64x2 [] = { 0, 1,  }
+VSUBW:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBW:17:result_uint16x8 [] = { fefd, fefe, feff, ff00, ff01, ff02, ff03, ff04,  }
+VSUBW:18:result_uint32x4 [] = { fffeffff, ffff0000, ffff0001, ffff0002,  }
+VSUBW:19:result_uint64x2 [] = { ffffffff00000000, ffffffff00000001,  }
+VSUBW:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBW:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSUBW:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSUBW:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSUBHN output:
+VSUBHN:0:result_int8x8 [] = { 31, 31, 31, 31, 31, 31, 31, 31,  }
+VSUBHN:1:result_int16x4 [] = { 31, 31, 31, 31,  }
+VSUBHN:2:result_int32x2 [] = { 17, 17,  }
+VSUBHN:3:result_int64x1 [] = { 3333333333333333,  }
+VSUBHN:4:result_uint8x8 [] = { 2, 2, 2, 2, 2, 2, 2, 2,  }
+VSUBHN:5:result_uint16x4 [] = { 36, 36, 36, 36,  }
+VSUBHN:6:result_uint32x2 [] = { 2, 2,  }
+VSUBHN:7:result_uint64x1 [] = { 3333333333333333,  }
+VSUBHN:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBHN:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSUBHN:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSUBHN:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSUBHN:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBHN:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSUBHN:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSUBHN:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VSUBHN:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBHN:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSUBHN:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSUBHN:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VSUBHN:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSUBHN:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSUBHN:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSUBHN:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSUBHN output:
+VRSUBHN:0:result_int8x8 [] = { 31, 31, 31, 31, 31, 31, 31, 31,  }
+VRSUBHN:1:result_int16x4 [] = { 31, 31, 31, 31,  }
+VRSUBHN:2:result_int32x2 [] = { 17, 17,  }
+VRSUBHN:3:result_int64x1 [] = { 3333333333333333,  }
+VRSUBHN:4:result_uint8x8 [] = { 2, 2, 2, 2, 2, 2, 2, 2,  }
+VRSUBHN:5:result_uint16x4 [] = { 36, 36, 36, 36,  }
+VRSUBHN:6:result_uint32x2 [] = { 2, 2,  }
+VRSUBHN:7:result_uint64x1 [] = { 3333333333333333,  }
+VRSUBHN:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSUBHN:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSUBHN:10:result_float32x2 [] = { 33333333, 33333333,  }
+VRSUBHN:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSUBHN:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSUBHN:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSUBHN:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSUBHN:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRSUBHN:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSUBHN:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSUBHN:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSUBHN:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VRSUBHN:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSUBHN:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSUBHN:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSUBHN:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VMVN/VMVNQ output:
+VMVN/VMVNQ:0:result_int8x8 [] = { f, e, d, c, b, a, 9, 8,  }
+VMVN/VMVNQ:1:result_int16x4 [] = { f, e, d, c,  }
+VMVN/VMVNQ:2:result_int32x2 [] = { f, e,  }
+VMVN/VMVNQ:3:result_int64x1 [] = { 3333333333333333,  }
+VMVN/VMVNQ:4:result_uint8x8 [] = { f, e, d, c, b, a, 9, 8,  }
+VMVN/VMVNQ:5:result_uint16x4 [] = { f, e, d, c,  }
+VMVN/VMVNQ:6:result_uint32x2 [] = { f, e,  }
+VMVN/VMVNQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VMVN/VMVNQ:8:result_poly8x8 [] = { f, e, d, c, b, a, 9, 8,  }
+VMVN/VMVNQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VMVN/VMVNQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VMVN/VMVNQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VMVN/VMVNQ:12:result_int8x16 [] = { f, e, d, c, b, a, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0,  }
+VMVN/VMVNQ:13:result_int16x8 [] = { f, e, d, c, b, a, 9, 8,  }
+VMVN/VMVNQ:14:result_int32x4 [] = { f, e, d, c,  }
+VMVN/VMVNQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMVN/VMVNQ:16:result_uint8x16 [] = { f, e, d, c, b, a, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0,  }
+VMVN/VMVNQ:17:result_uint16x8 [] = { f, e, d, c, b, a, 9, 8,  }
+VMVN/VMVNQ:18:result_uint32x4 [] = { f, e, d, c,  }
+VMVN/VMVNQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VMVN/VMVNQ:20:result_poly8x16 [] = { f, e, d, c, b, a, 9, 8, 7, 6, 5, 4, 3, 2, 1, 0,  }
+VMVN/VMVNQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VMVN/VMVNQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VMVN/VMVNQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQMOVN cumulative saturation output:
+VQMOVN:0:vqmovn_s16 Neon cumulative saturation 0
+VQMOVN:1:vqmovn_s32 Neon cumulative saturation 0
+VQMOVN:2:vqmovn_s64 Neon cumulative saturation 0
+VQMOVN:3:vqmovn_u16 Neon cumulative saturation 0
+VQMOVN:4:vqmovn_u32 Neon cumulative saturation 0
+VQMOVN:5:vqmovn_u64 Neon cumulative saturation 0
+
+VQMOVN output:
+VQMOVN:6:result_int8x8 [] = { 12, 12, 12, 12, 12, 12, 12, 12,  }
+VQMOVN:7:result_int16x4 [] = { 1278, 1278, 1278, 1278,  }
+VQMOVN:8:result_int32x2 [] = { 12345678, 12345678,  }
+VQMOVN:9:result_int64x1 [] = { 3333333333333333,  }
+VQMOVN:10:result_uint8x8 [] = { 82, 82, 82, 82, 82, 82, 82, 82,  }
+VQMOVN:11:result_uint16x4 [] = { 8765, 8765, 8765, 8765,  }
+VQMOVN:12:result_uint32x2 [] = { 87654321, 87654321,  }
+VQMOVN:13:result_uint64x1 [] = { 3333333333333333,  }
+VQMOVN:14:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVN:15:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQMOVN:16:result_float32x2 [] = { 33333333, 33333333,  }
+VQMOVN:17:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQMOVN:18:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVN:19:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVN:20:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVN:21:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQMOVN:22:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVN:23:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVN:24:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVN:25:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQMOVN:26:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVN:27:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVN:28:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVN:29:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQMOVN cumulative saturation output:
+VQMOVN:30:vqmovn_s16 Neon cumulative saturation 1
+VQMOVN:31:vqmovn_s32 Neon cumulative saturation 1
+VQMOVN:32:vqmovn_s64 Neon cumulative saturation 1
+VQMOVN:33:vqmovn_u16 Neon cumulative saturation 1
+VQMOVN:34:vqmovn_u32 Neon cumulative saturation 1
+VQMOVN:35:vqmovn_u64 Neon cumulative saturation 1
+
+VQMOVN output:
+VQMOVN:36:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQMOVN:37:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQMOVN:38:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQMOVN:39:result_int64x1 [] = { 3333333333333333,  }
+VQMOVN:40:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQMOVN:41:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQMOVN:42:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQMOVN:43:result_uint64x1 [] = { 3333333333333333,  }
+VQMOVN:44:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVN:45:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQMOVN:46:result_float32x2 [] = { 33333333, 33333333,  }
+VQMOVN:47:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQMOVN:48:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVN:49:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVN:50:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVN:51:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQMOVN:52:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVN:53:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVN:54:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVN:55:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQMOVN:56:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVN:57:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVN:58:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVN:59:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQMOVUN cumulative saturation output:
+VQMOVUN:0:vqmovun_s16 Neon cumulative saturation 0
+VQMOVUN:1:vqmovun_s32 Neon cumulative saturation 0
+VQMOVUN:2:vqmovun_s64 Neon cumulative saturation 0
+
+VQMOVUN output:
+VQMOVUN:3:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:4:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQMOVUN:5:result_int32x2 [] = { 33333333, 33333333,  }
+VQMOVUN:6:result_int64x1 [] = { 3333333333333333,  }
+VQMOVUN:7:result_uint8x8 [] = { 34, 34, 34, 34, 34, 34, 34, 34,  }
+VQMOVUN:8:result_uint16x4 [] = { 5678, 5678, 5678, 5678,  }
+VQMOVUN:9:result_uint32x2 [] = { 12345678, 12345678,  }
+VQMOVUN:10:result_uint64x1 [] = { 3333333333333333,  }
+VQMOVUN:11:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:12:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQMOVUN:13:result_float32x2 [] = { 33333333, 33333333,  }
+VQMOVUN:14:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQMOVUN:15:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:16:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVUN:17:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVUN:18:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQMOVUN:19:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:20:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVUN:21:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVUN:22:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQMOVUN:23:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:24:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVUN:25:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVUN:26:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQMOVUN (negative input) cumulative saturation output:
+VQMOVUN:27:vqmovun_s16 Neon cumulative saturation 1
+VQMOVUN:28:vqmovun_s32 Neon cumulative saturation 1
+VQMOVUN:29:vqmovun_s64 Neon cumulative saturation 1
+
+VQMOVUN (negative input) output:
+VQMOVUN:30:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:31:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQMOVUN:32:result_int32x2 [] = { 33333333, 33333333,  }
+VQMOVUN:33:result_int64x1 [] = { 3333333333333333,  }
+VQMOVUN:34:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQMOVUN:35:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQMOVUN:36:result_uint32x2 [] = { 0, 0,  }
+VQMOVUN:37:result_uint64x1 [] = { 3333333333333333,  }
+VQMOVUN:38:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:39:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQMOVUN:40:result_float32x2 [] = { 33333333, 33333333,  }
+VQMOVUN:41:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQMOVUN:42:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:43:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVUN:44:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVUN:45:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQMOVUN:46:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:47:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVUN:48:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVUN:49:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQMOVUN:50:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQMOVUN:51:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQMOVUN:52:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQMOVUN:53:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHR_N output:
+VRSHR_N:0:result_int8x8 [] = { fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb, fffffffc,  }
+VRSHR_N:1:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHR_N:2:result_int32x2 [] = { fffffffc, fffffffc,  }
+VRSHR_N:3:result_int64x1 [] = { 0,  }
+VRSHR_N:4:result_uint8x8 [] = { 3c, 3c, 3d, 3d, 3d, 3d, 3e, 3e,  }
+VRSHR_N:5:result_uint16x4 [] = { 1ffe, 1ffe, 1ffe, 1ffe,  }
+VRSHR_N:6:result_uint32x2 [] = { 8000000, 8000000,  }
+VRSHR_N:7:result_uint64x1 [] = { 80000000,  }
+VRSHR_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHR_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHR_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHR_N:12:result_int8x16 [] = { fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb, fffffffc, fffffffc, fffffffd, fffffffd, fffffffe, fffffffe, ffffffff, ffffffff, 0,  }
+VRSHR_N:13:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHR_N:14:result_int32x4 [] = { fffffffc, fffffffc, fffffffd, fffffffd,  }
+VRSHR_N:15:result_int64x2 [] = { 0, 0,  }
+VRSHR_N:16:result_uint8x16 [] = { 3c, 3c, 3d, 3d, 3d, 3d, 3e, 3e, 3e, 3e, 3f, 3f, 3f, 3f, 40, 40,  }
+VRSHR_N:17:result_uint16x8 [] = { 1ffe, 1ffe, 1ffe, 1ffe, 1fff, 1fff, 1fff, 1fff,  }
+VRSHR_N:18:result_uint32x4 [] = { 8000000, 8000000, 8000000, 8000000,  }
+VRSHR_N:19:result_uint64x2 [] = { 80000000, 80000000,  }
+VRSHR_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHR_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHR_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHR_N (overflow test: max shift amount, positive input) output:
+VRSHR_N:24:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHR_N:25:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSHR_N:26:result_int32x2 [] = { 0, 0,  }
+VRSHR_N:27:result_int64x1 [] = { 0,  }
+VRSHR_N:28:result_uint8x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSHR_N:29:result_uint16x4 [] = { 1, 1, 1, 1,  }
+VRSHR_N:30:result_uint32x2 [] = { 1, 1,  }
+VRSHR_N:31:result_uint64x1 [] = { 1,  }
+VRSHR_N:32:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:33:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHR_N:34:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHR_N:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHR_N:36:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHR_N:37:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSHR_N:38:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSHR_N:39:result_int64x2 [] = { 0, 0,  }
+VRSHR_N:40:result_uint8x16 [] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSHR_N:41:result_uint16x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSHR_N:42:result_uint32x4 [] = { 1, 1, 1, 1,  }
+VRSHR_N:43:result_uint64x2 [] = { 1, 1,  }
+VRSHR_N:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:45:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHR_N:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHR_N:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHR_N (overflow test: shift by 1, with negative input) output:
+VRSHR_N:48:result_int8x8 [] = { 40, 40, 40, 40, 40, 40, 40, 40,  }
+VRSHR_N:49:result_int16x4 [] = { 4000, 4000, 4000, 4000,  }
+VRSHR_N:50:result_int32x2 [] = { 40000000, 40000000,  }
+VRSHR_N:51:result_int64x1 [] = { 4000000000000000,  }
+VRSHR_N:52:result_uint8x8 [] = { 80, 80, 80, 80, 80, 80, 80, 80,  }
+VRSHR_N:53:result_uint16x4 [] = { 8000, 8000, 8000, 8000,  }
+VRSHR_N:54:result_uint32x2 [] = { 80000000, 80000000,  }
+VRSHR_N:55:result_uint64x1 [] = { 8000000000000000,  }
+VRSHR_N:56:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:57:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHR_N:58:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHR_N:59:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHR_N:60:result_int8x16 [] = { 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40,  }
+VRSHR_N:61:result_int16x8 [] = { 4000, 4000, 4000, 4000, 4000, 4000, 4000, 4000,  }
+VRSHR_N:62:result_int32x4 [] = { 40000000, 40000000, 40000000, 40000000,  }
+VRSHR_N:63:result_int64x2 [] = { 4000000000000000, 4000000000000000,  }
+VRSHR_N:64:result_uint8x16 [] = { 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80,  }
+VRSHR_N:65:result_uint16x8 [] = { 8000, 8000, 8000, 8000, 8000, 8000, 8000, 8000,  }
+VRSHR_N:66:result_uint32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VRSHR_N:67:result_uint64x2 [] = { 8000000000000000, 8000000000000000,  }
+VRSHR_N:68:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:69:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHR_N:70:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHR_N:71:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHR_N (overflow test: shift by 3, positive input) output:
+VRSHR_N:72:result_int8x8 [] = { 10, 10, 10, 10, 10, 10, 10, 10,  }
+VRSHR_N:73:result_int16x4 [] = { 1000, 1000, 1000, 1000,  }
+VRSHR_N:74:result_int32x2 [] = { 10000000, 10000000,  }
+VRSHR_N:75:result_int64x1 [] = { 1000000000000000,  }
+VRSHR_N:76:result_uint8x8 [] = { 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSHR_N:77:result_uint16x4 [] = { 2000, 2000, 2000, 2000,  }
+VRSHR_N:78:result_uint32x2 [] = { 20000000, 20000000,  }
+VRSHR_N:79:result_uint64x1 [] = { 2000000000000000,  }
+VRSHR_N:80:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:81:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHR_N:82:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHR_N:83:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHR_N:84:result_int8x16 [] = { 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10,  }
+VRSHR_N:85:result_int16x8 [] = { 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000,  }
+VRSHR_N:86:result_int32x4 [] = { 10000000, 10000000, 10000000, 10000000,  }
+VRSHR_N:87:result_int64x2 [] = { 1000000000000000, 1000000000000000,  }
+VRSHR_N:88:result_uint8x16 [] = { 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSHR_N:89:result_uint16x8 [] = { 2000, 2000, 2000, 2000, 2000, 2000, 2000, 2000,  }
+VRSHR_N:90:result_uint32x4 [] = { 20000000, 20000000, 20000000, 20000000,  }
+VRSHR_N:91:result_uint64x2 [] = { 2000000000000000, 2000000000000000,  }
+VRSHR_N:92:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:93:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHR_N:94:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHR_N:95:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHR_N (overflow test: shift by 1, with negative input) output:
+VRSHR_N:96:result_int8x8 [] = { ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0,  }
+VRSHR_N:97:result_int16x4 [] = { ffffc000, ffffc000, ffffc000, ffffc000,  }
+VRSHR_N:98:result_int32x2 [] = { c0000000, c0000000,  }
+VRSHR_N:99:result_int64x1 [] = { c000000000000000,  }
+VRSHR_N:100:result_uint8x8 [] = { 80, 80, 80, 80, 80, 80, 80, 80,  }
+VRSHR_N:101:result_uint16x4 [] = { 8000, 8000, 8000, 8000,  }
+VRSHR_N:102:result_uint32x2 [] = { 80000000, 80000000,  }
+VRSHR_N:103:result_uint64x1 [] = { 8000000000000000,  }
+VRSHR_N:104:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:105:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHR_N:106:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHR_N:107:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHR_N:108:result_int8x16 [] = { ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0,  }
+VRSHR_N:109:result_int16x8 [] = { ffffc000, ffffc000, ffffc000, ffffc000, ffffc000, ffffc000, ffffc000, ffffc000,  }
+VRSHR_N:110:result_int32x4 [] = { c0000000, c0000000, c0000000, c0000000,  }
+VRSHR_N:111:result_int64x2 [] = { c000000000000000, c000000000000000,  }
+VRSHR_N:112:result_uint8x16 [] = { 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80,  }
+VRSHR_N:113:result_uint16x8 [] = { 8000, 8000, 8000, 8000, 8000, 8000, 8000, 8000,  }
+VRSHR_N:114:result_uint32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VRSHR_N:115:result_uint64x2 [] = { 8000000000000000, 8000000000000000,  }
+VRSHR_N:116:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:117:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHR_N:118:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHR_N:119:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSHR_N (overflow test: shift by 3, with negative input) output:
+VRSHR_N:120:result_int8x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VRSHR_N:121:result_int16x4 [] = { fffff000, fffff000, fffff000, fffff000,  }
+VRSHR_N:122:result_int32x2 [] = { f0000000, f0000000,  }
+VRSHR_N:123:result_int64x1 [] = { f000000000000000,  }
+VRSHR_N:124:result_uint8x8 [] = { 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSHR_N:125:result_uint16x4 [] = { 2000, 2000, 2000, 2000,  }
+VRSHR_N:126:result_uint32x2 [] = { 20000000, 20000000,  }
+VRSHR_N:127:result_uint64x1 [] = { 2000000000000000,  }
+VRSHR_N:128:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:129:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSHR_N:130:result_float32x2 [] = { 33333333, 33333333,  }
+VRSHR_N:131:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSHR_N:132:result_int8x16 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VRSHR_N:133:result_int16x8 [] = { fffff000, fffff000, fffff000, fffff000, fffff000, fffff000, fffff000, fffff000,  }
+VRSHR_N:134:result_int32x4 [] = { f0000000, f0000000, f0000000, f0000000,  }
+VRSHR_N:135:result_int64x2 [] = { f000000000000000, f000000000000000,  }
+VRSHR_N:136:result_uint8x16 [] = { 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSHR_N:137:result_uint16x8 [] = { 2000, 2000, 2000, 2000, 2000, 2000, 2000, 2000,  }
+VRSHR_N:138:result_uint32x4 [] = { 20000000, 20000000, 20000000, 20000000,  }
+VRSHR_N:139:result_uint64x2 [] = { 2000000000000000, 2000000000000000,  }
+VRSHR_N:140:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSHR_N:141:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSHR_N:142:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSHR_N:143:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSRA_N output:
+VRSRA_N:0:result_int8x8 [] = { fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff, 0,  }
+VRSRA_N:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VRSRA_N:2:result_int32x2 [] = { fffffffd, fffffffe,  }
+VRSRA_N:3:result_int64x1 [] = { fffffffffffffff0,  }
+VRSRA_N:4:result_uint8x8 [] = { 5, 6, 7, 8, 9, a, b, c,  }
+VRSRA_N:5:result_uint16x4 [] = { fffd, fffe, ffff, 0,  }
+VRSRA_N:6:result_uint32x2 [] = { fffffff4, fffffff5,  }
+VRSRA_N:7:result_uint64x1 [] = { fffffffffffffff0,  }
+VRSRA_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSRA_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VRSRA_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:12:result_int8x16 [] = { fffffff9, fffffffa, fffffffb, fffffffc, fffffffd, fffffffe, ffffffff, 0, 1, 2, 3, 4, 5, 6, 7, 8,  }
+VRSRA_N:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, fffffff4, fffffff5, fffffff6, fffffff7,  }
+VRSRA_N:14:result_int32x4 [] = { fffffffd, fffffffe, ffffffff, 0,  }
+VRSRA_N:15:result_int64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VRSRA_N:16:result_uint8x16 [] = { 5, 6, 7, 8, 9, a, b, c, d, e, f, 10, 11, 12, 13, 14,  }
+VRSRA_N:17:result_uint16x8 [] = { fffd, fffe, ffff, 0, 1, 2, 3, 4,  }
+VRSRA_N:18:result_uint32x4 [] = { fffffff4, fffffff5, fffffff6, fffffff7,  }
+VRSRA_N:19:result_uint64x2 [] = { fffffffffffffff0, fffffffffffffff1,  }
+VRSRA_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSRA_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSRA_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSRA_N (checking overflow: shift by 1, positive input) output:
+VRSRA_N:24:result_int8x8 [] = { 40, 40, 40, 40, 40, 40, 40, 40,  }
+VRSRA_N:25:result_int16x4 [] = { 4000, 4000, 4000, 4000,  }
+VRSRA_N:26:result_int32x2 [] = { 40000000, 40000000,  }
+VRSRA_N:27:result_int64x1 [] = { 4000000000000000,  }
+VRSRA_N:28:result_uint8x8 [] = { 80, 80, 80, 80, 80, 80, 80, 80,  }
+VRSRA_N:29:result_uint16x4 [] = { 8000, 8000, 8000, 8000,  }
+VRSRA_N:30:result_uint32x2 [] = { 80000000, 80000000,  }
+VRSRA_N:31:result_uint64x1 [] = { 8000000000000000,  }
+VRSRA_N:32:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:33:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSRA_N:34:result_float32x2 [] = { 33333333, 33333333,  }
+VRSRA_N:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:36:result_int8x16 [] = { 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40, 40,  }
+VRSRA_N:37:result_int16x8 [] = { 4000, 4000, 4000, 4000, 4000, 4000, 4000, 4000,  }
+VRSRA_N:38:result_int32x4 [] = { 40000000, 40000000, 40000000, 40000000,  }
+VRSRA_N:39:result_int64x2 [] = { 4000000000000000, 4000000000000000,  }
+VRSRA_N:40:result_uint8x16 [] = { 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80, 80,  }
+VRSRA_N:41:result_uint16x8 [] = { 8000, 8000, 8000, 8000, 8000, 8000, 8000, 8000,  }
+VRSRA_N:42:result_uint32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+VRSRA_N:43:result_uint64x2 [] = { 8000000000000000, 8000000000000000,  }
+VRSRA_N:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:45:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSRA_N:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSRA_N:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSRA_N (checking overflow: shift by 3, positive input) output:
+VRSRA_N:48:result_int8x8 [] = { 10, 10, 10, 10, 10, 10, 10, 10,  }
+VRSRA_N:49:result_int16x4 [] = { 1000, 1000, 1000, 1000,  }
+VRSRA_N:50:result_int32x2 [] = { 10000000, 10000000,  }
+VRSRA_N:51:result_int64x1 [] = { 1000000000000000,  }
+VRSRA_N:52:result_uint8x8 [] = { 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSRA_N:53:result_uint16x4 [] = { 2000, 2000, 2000, 2000,  }
+VRSRA_N:54:result_uint32x2 [] = { 20000000, 20000000,  }
+VRSRA_N:55:result_uint64x1 [] = { 2000000000000000,  }
+VRSRA_N:56:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:57:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSRA_N:58:result_float32x2 [] = { 33333333, 33333333,  }
+VRSRA_N:59:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:60:result_int8x16 [] = { 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10, 10,  }
+VRSRA_N:61:result_int16x8 [] = { 1000, 1000, 1000, 1000, 1000, 1000, 1000, 1000,  }
+VRSRA_N:62:result_int32x4 [] = { 10000000, 10000000, 10000000, 10000000,  }
+VRSRA_N:63:result_int64x2 [] = { 1000000000000000, 1000000000000000,  }
+VRSRA_N:64:result_uint8x16 [] = { 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20, 20,  }
+VRSRA_N:65:result_uint16x8 [] = { 2000, 2000, 2000, 2000, 2000, 2000, 2000, 2000,  }
+VRSRA_N:66:result_uint32x4 [] = { 20000000, 20000000, 20000000, 20000000,  }
+VRSRA_N:67:result_uint64x2 [] = { 2000000000000000, 2000000000000000,  }
+VRSRA_N:68:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:69:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSRA_N:70:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSRA_N:71:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSRA_N (checking overflow: shift by max, positive input) output:
+VRSRA_N:72:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSRA_N:73:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:74:result_int32x2 [] = { 0, 0,  }
+VRSRA_N:75:result_int64x1 [] = { 0,  }
+VRSRA_N:76:result_uint8x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:77:result_uint16x4 [] = { 1, 1, 1, 1,  }
+VRSRA_N:78:result_uint32x2 [] = { 1, 1,  }
+VRSRA_N:79:result_uint64x1 [] = { 1,  }
+VRSRA_N:80:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:81:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSRA_N:82:result_float32x2 [] = { 33333333, 33333333,  }
+VRSRA_N:83:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:84:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSRA_N:85:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSRA_N:86:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:87:result_int64x2 [] = { 0, 0,  }
+VRSRA_N:88:result_uint8x16 [] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:89:result_uint16x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:90:result_uint32x4 [] = { 1, 1, 1, 1,  }
+VRSRA_N:91:result_uint64x2 [] = { 1, 1,  }
+VRSRA_N:92:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:93:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSRA_N:94:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSRA_N:95:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSRA_N (checking overflow: shift by 1, negative input) output:
+VRSRA_N:96:result_int8x8 [] = { ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0,  }
+VRSRA_N:97:result_int16x4 [] = { ffffc000, ffffc000, ffffc000, ffffc000,  }
+VRSRA_N:98:result_int32x2 [] = { c0000000, c0000000,  }
+VRSRA_N:99:result_int64x1 [] = { c000000000000000,  }
+VRSRA_N:100:result_uint8x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:101:result_uint16x4 [] = { 1, 1, 1, 1,  }
+VRSRA_N:102:result_uint32x2 [] = { 1, 1,  }
+VRSRA_N:103:result_uint64x1 [] = { 1,  }
+VRSRA_N:104:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:105:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSRA_N:106:result_float32x2 [] = { 33333333, 33333333,  }
+VRSRA_N:107:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:108:result_int8x16 [] = { ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0, ffffffc0,  }
+VRSRA_N:109:result_int16x8 [] = { ffffc000, ffffc000, ffffc000, ffffc000, ffffc000, ffffc000, ffffc000, ffffc000,  }
+VRSRA_N:110:result_int32x4 [] = { c0000000, c0000000, c0000000, c0000000,  }
+VRSRA_N:111:result_int64x2 [] = { c000000000000000, c000000000000000,  }
+VRSRA_N:112:result_uint8x16 [] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:113:result_uint16x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:114:result_uint32x4 [] = { 1, 1, 1, 1,  }
+VRSRA_N:115:result_uint64x2 [] = { 1, 1,  }
+VRSRA_N:116:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:117:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSRA_N:118:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSRA_N:119:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSRA_N (checking overflow: shift by max, negative input) output:
+VRSRA_N:120:result_int8x8 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VRSRA_N:121:result_int16x4 [] = { fffff000, fffff000, fffff000, fffff000,  }
+VRSRA_N:122:result_int32x2 [] = { f0000000, f0000000,  }
+VRSRA_N:123:result_int64x1 [] = { f000000000000000,  }
+VRSRA_N:124:result_uint8x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:125:result_uint16x4 [] = { 1, 1, 1, 1,  }
+VRSRA_N:126:result_uint32x2 [] = { 1, 1,  }
+VRSRA_N:127:result_uint64x1 [] = { 1,  }
+VRSRA_N:128:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:129:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSRA_N:130:result_float32x2 [] = { 33333333, 33333333,  }
+VRSRA_N:131:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:132:result_int8x16 [] = { fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0, fffffff0,  }
+VRSRA_N:133:result_int16x8 [] = { fffff000, fffff000, fffff000, fffff000, fffff000, fffff000, fffff000, fffff000,  }
+VRSRA_N:134:result_int32x4 [] = { f0000000, f0000000, f0000000, f0000000,  }
+VRSRA_N:135:result_int64x2 [] = { f000000000000000, f000000000000000,  }
+VRSRA_N:136:result_uint8x16 [] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:137:result_uint16x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:138:result_uint32x4 [] = { 1, 1, 1, 1,  }
+VRSRA_N:139:result_uint64x2 [] = { 1, 1,  }
+VRSRA_N:140:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:141:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSRA_N:142:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSRA_N:143:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRSRA_N (checking overflow: shift by max, negative input) output:
+VRSRA_N:144:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSRA_N:145:result_int16x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:146:result_int32x2 [] = { 0, 0,  }
+VRSRA_N:147:result_int64x1 [] = { 0,  }
+VRSRA_N:148:result_uint8x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:149:result_uint16x4 [] = { 1, 1, 1, 1,  }
+VRSRA_N:150:result_uint32x2 [] = { 1, 1,  }
+VRSRA_N:151:result_uint64x1 [] = { 1,  }
+VRSRA_N:152:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:153:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VRSRA_N:154:result_float32x2 [] = { 33333333, 33333333,  }
+VRSRA_N:155:result_float16x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:156:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSRA_N:157:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VRSRA_N:158:result_int32x4 [] = { 0, 0, 0, 0,  }
+VRSRA_N:159:result_int64x2 [] = { 0, 0,  }
+VRSRA_N:160:result_uint8x16 [] = { 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:161:result_uint16x8 [] = { 1, 1, 1, 1, 1, 1, 1, 1,  }
+VRSRA_N:162:result_uint32x4 [] = { 1, 1, 1, 1,  }
+VRSRA_N:163:result_uint64x2 [] = { 1, 1,  }
+VRSRA_N:164:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VRSRA_N:165:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VRSRA_N:166:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VRSRA_N:167:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VSHLL_N output:
+VSHLL_N:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHLL_N:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHLL_N:2:result_int32x2 [] = { 33333333, 33333333,  }
+VSHLL_N:3:result_int64x1 [] = { 3333333333333333,  }
+VSHLL_N:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHLL_N:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHLL_N:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VSHLL_N:7:result_uint64x1 [] = { 3333333333333333,  }
+VSHLL_N:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHLL_N:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VSHLL_N:10:result_float32x2 [] = { 33333333, 33333333,  }
+VSHLL_N:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VSHLL_N:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHLL_N:13:result_int16x8 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6, ffffffe8, ffffffea, ffffffec, ffffffee,  }
+VSHLL_N:14:result_int32x4 [] = { ffffffe0, ffffffe2, ffffffe4, ffffffe6,  }
+VSHLL_N:15:result_int64x2 [] = { ffffffffffffff80, ffffffffffffff88,  }
+VSHLL_N:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHLL_N:17:result_uint16x8 [] = { 3c0, 3c4, 3c8, 3cc, 3d0, 3d4, 3d8, 3dc,  }
+VSHLL_N:18:result_uint32x4 [] = { fff00, fff10, fff20, fff30,  }
+VSHLL_N:19:result_uint64x2 [] = { 7ffffff80, 7ffffff88,  }
+VSHLL_N:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VSHLL_N:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VSHLL_N:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VSHLL_N:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VPADDL/VPADDLQ output:
+VPADDL/VPADDLQ:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADDL/VPADDLQ:1:result_int16x4 [] = { ffffffe1, ffffffe5, ffffffe9, ffffffed,  }
+VPADDL/VPADDLQ:2:result_int32x2 [] = { ffffffe1, ffffffe5,  }
+VPADDL/VPADDLQ:3:result_int64x1 [] = { ffffffffffffffe1,  }
+VPADDL/VPADDLQ:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADDL/VPADDLQ:5:result_uint16x4 [] = { 1e1, 1e5, 1e9, 1ed,  }
+VPADDL/VPADDLQ:6:result_uint32x2 [] = { 1ffe1, 1ffe5,  }
+VPADDL/VPADDLQ:7:result_uint64x1 [] = { 1ffffffe1,  }
+VPADDL/VPADDLQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADDL/VPADDLQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VPADDL/VPADDLQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VPADDL/VPADDLQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VPADDL/VPADDLQ:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADDL/VPADDLQ:13:result_int16x8 [] = { ffffffe1, ffffffe5, ffffffe9, ffffffed, fffffff1, fffffff5, fffffff9, fffffffd,  }
+VPADDL/VPADDLQ:14:result_int32x4 [] = { ffffffe1, ffffffe5, ffffffe9, ffffffed,  }
+VPADDL/VPADDLQ:15:result_int64x2 [] = { ffffffffffffffe1, ffffffffffffffe5,  }
+VPADDL/VPADDLQ:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADDL/VPADDLQ:17:result_uint16x8 [] = { 1e1, 1e5, 1e9, 1ed, 1f1, 1f5, 1f9, 1fd,  }
+VPADDL/VPADDLQ:18:result_uint32x4 [] = { 1ffe1, 1ffe5, 1ffe9, 1ffed,  }
+VPADDL/VPADDLQ:19:result_uint64x2 [] = { 1ffffffe1, 1ffffffe5,  }
+VPADDL/VPADDLQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADDL/VPADDLQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPADDL/VPADDLQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPADDL/VPADDLQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VPADD output:
+VPADD:0:result_int8x8 [] = { ffffffe1, ffffffe5, ffffffe9, ffffffed, ffffffe1, ffffffe5, ffffffe9, ffffffed,  }
+VPADD:1:result_int16x4 [] = { ffffffe1, ffffffe5, ffffffe1, ffffffe5,  }
+VPADD:2:result_int32x2 [] = { ffffffe1, ffffffe1,  }
+VPADD:3:result_int64x1 [] = { 3333333333333333,  }
+VPADD:4:result_uint8x8 [] = { e1, e5, e9, ed, e1, e5, e9, ed,  }
+VPADD:5:result_uint16x4 [] = { ffe1, ffe5, ffe1, ffe5,  }
+VPADD:6:result_uint32x2 [] = { ffffffe1, ffffffe1,  }
+VPADD:7:result_uint64x1 [] = { 3333333333333333,  }
+VPADD:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADD:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VPADD:10:result_float32x2 [] = { c1f80000, c1f80000,  }
+VPADD:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VPADD:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADD:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPADD:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPADD:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VPADD:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADD:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPADD:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPADD:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VPADD:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADD:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPADD:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPADD:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VPADAL/VPADALQ output:
+VPADAL/VPADALQ:0:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADAL/VPADALQ:1:result_int16x4 [] = { ffffffd1, ffffffd6, ffffffdb, ffffffe0,  }
+VPADAL/VPADALQ:2:result_int32x2 [] = { ffffffd1, ffffffd6,  }
+VPADAL/VPADALQ:3:result_int64x1 [] = { ffffffffffffffd1,  }
+VPADAL/VPADALQ:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADAL/VPADALQ:5:result_uint16x4 [] = { 1d1, 1d6, 1db, 1e0,  }
+VPADAL/VPADALQ:6:result_uint32x2 [] = { 1ffd1, 1ffd6,  }
+VPADAL/VPADALQ:7:result_uint64x1 [] = { 1ffffffd1,  }
+VPADAL/VPADALQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADAL/VPADALQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VPADAL/VPADALQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VPADAL/VPADALQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VPADAL/VPADALQ:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADAL/VPADALQ:13:result_int16x8 [] = { ffffffd1, ffffffd6, ffffffdb, ffffffe0, ffffffe5, ffffffea, ffffffef, fffffff4,  }
+VPADAL/VPADALQ:14:result_int32x4 [] = { ffffffd1, ffffffd6, ffffffdb, ffffffe0,  }
+VPADAL/VPADALQ:15:result_int64x2 [] = { ffffffffffffffd1, ffffffffffffffd6,  }
+VPADAL/VPADALQ:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADAL/VPADALQ:17:result_uint16x8 [] = { 1d1, 1d6, 1db, 1e0, 1e5, 1ea, 1ef, 1f4,  }
+VPADAL/VPADALQ:18:result_uint32x4 [] = { 1ffd1, 1ffd6, 1ffdb, 1ffe0,  }
+VPADAL/VPADALQ:19:result_uint64x2 [] = { 1ffffffd1, 1ffffffd6,  }
+VPADAL/VPADALQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPADAL/VPADALQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPADAL/VPADALQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPADAL/VPADALQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHLU_N/VQSHLUQ_N (negative input) cumulative saturation output:
+VQSHLU_N/VQSHLUQ_N:0:vqshlu_n_s8 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:1:vqshlu_n_s16 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:2:vqshlu_n_s32 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:3:vqshlu_n_s64 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:4:vqshluq_n_s8 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:5:vqshluq_n_s16 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:6:vqshluq_n_s32 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:7:vqshluq_n_s64 Neon cumulative saturation 1
+
+VQSHLU_N/VQSHLUQ_N (negative input) output:
+VQSHLU_N/VQSHLUQ_N:8:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:9:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:10:result_int32x2 [] = { 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:11:result_int64x1 [] = { 3333333333333333,  }
+VQSHLU_N/VQSHLUQ_N:12:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:13:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:14:result_uint32x2 [] = { 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:15:result_uint64x1 [] = { 0,  }
+VQSHLU_N/VQSHLUQ_N:16:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:17:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:18:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:19:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:20:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:21:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:22:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:23:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHLU_N/VQSHLUQ_N:24:result_uint8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:25:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:26:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:27:result_uint64x2 [] = { 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:28:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:29:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:30:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:31:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHLU_N/VQSHLUQ_N (check cumulative saturation: shift by 1) cumulative saturation output:
+VQSHLU_N/VQSHLUQ_N:32:vqshlu_n_s8 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:33:vqshlu_n_s16 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:34:vqshlu_n_s32 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:35:vqshlu_n_s64 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:36:vqshluq_n_s8 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:37:vqshluq_n_s16 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:38:vqshluq_n_s32 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:39:vqshluq_n_s64 Neon cumulative saturation 0
+
+VQSHLU_N/VQSHLUQ_N (check cumulative saturation: shift by 1) output:
+VQSHLU_N/VQSHLUQ_N:40:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:41:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:42:result_int32x2 [] = { 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:43:result_int64x1 [] = { 3333333333333333,  }
+VQSHLU_N/VQSHLUQ_N:44:result_uint8x8 [] = { fe, fe, fe, fe, fe, fe, fe, fe,  }
+VQSHLU_N/VQSHLUQ_N:45:result_uint16x4 [] = { fffe, fffe, fffe, fffe,  }
+VQSHLU_N/VQSHLUQ_N:46:result_uint32x2 [] = { fffffffe, fffffffe,  }
+VQSHLU_N/VQSHLUQ_N:47:result_uint64x1 [] = { fffffffffffffffe,  }
+VQSHLU_N/VQSHLUQ_N:48:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:49:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:50:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:51:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:52:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:53:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:54:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:55:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHLU_N/VQSHLUQ_N:56:result_uint8x16 [] = { fe, fe, fe, fe, fe, fe, fe, fe, fe, fe, fe, fe, fe, fe, fe, fe,  }
+VQSHLU_N/VQSHLUQ_N:57:result_uint16x8 [] = { fffe, fffe, fffe, fffe, fffe, fffe, fffe, fffe,  }
+VQSHLU_N/VQSHLUQ_N:58:result_uint32x4 [] = { fffffffe, fffffffe, fffffffe, fffffffe,  }
+VQSHLU_N/VQSHLUQ_N:59:result_uint64x2 [] = { fffffffffffffffe, fffffffffffffffe,  }
+VQSHLU_N/VQSHLUQ_N:60:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:61:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:62:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:63:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHLU_N/VQSHLUQ_N (check cumulative saturation: shift by 2) cumulative saturation output:
+VQSHLU_N/VQSHLUQ_N:64:vqshlu_n_s8 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:65:vqshlu_n_s16 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:66:vqshlu_n_s32 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:67:vqshlu_n_s64 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:68:vqshluq_n_s8 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:69:vqshluq_n_s16 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:70:vqshluq_n_s32 Neon cumulative saturation 1
+VQSHLU_N/VQSHLUQ_N:71:vqshluq_n_s64 Neon cumulative saturation 1
+
+VQSHLU_N/VQSHLUQ_N (check cumulative saturation: shift by 2) output:
+VQSHLU_N/VQSHLUQ_N:72:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:73:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:74:result_int32x2 [] = { 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:75:result_int64x1 [] = { 3333333333333333,  }
+VQSHLU_N/VQSHLUQ_N:76:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHLU_N/VQSHLUQ_N:77:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHLU_N/VQSHLUQ_N:78:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHLU_N/VQSHLUQ_N:79:result_uint64x1 [] = { ffffffffffffffff,  }
+VQSHLU_N/VQSHLUQ_N:80:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:81:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:82:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:83:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:84:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:85:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:86:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:87:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHLU_N/VQSHLUQ_N:88:result_uint8x16 [] = { ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHLU_N/VQSHLUQ_N:89:result_uint16x8 [] = { ffff, ffff, ffff, ffff, ffff, ffff, ffff, ffff,  }
+VQSHLU_N/VQSHLUQ_N:90:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+VQSHLU_N/VQSHLUQ_N:91:result_uint64x2 [] = { ffffffffffffffff, ffffffffffffffff,  }
+VQSHLU_N/VQSHLUQ_N:92:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:93:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:94:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:95:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHLU_N/VQSHLUQ_N cumulative saturation output:
+VQSHLU_N/VQSHLUQ_N:96:vqshlu_n_s8 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:97:vqshlu_n_s16 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:98:vqshlu_n_s32 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:99:vqshlu_n_s64 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:100:vqshluq_n_s8 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:101:vqshluq_n_s16 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:102:vqshluq_n_s32 Neon cumulative saturation 0
+VQSHLU_N/VQSHLUQ_N:103:vqshluq_n_s64 Neon cumulative saturation 0
+
+VQSHLU_N/VQSHLUQ_N output:
+VQSHLU_N/VQSHLUQ_N:104:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:105:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:106:result_int32x2 [] = { 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:107:result_int64x1 [] = { 3333333333333333,  }
+VQSHLU_N/VQSHLUQ_N:108:result_uint8x8 [] = { 2, 2, 2, 2, 2, 2, 2, 2,  }
+VQSHLU_N/VQSHLUQ_N:109:result_uint16x4 [] = { 8, 8, 8, 8,  }
+VQSHLU_N/VQSHLUQ_N:110:result_uint32x2 [] = { 18, 18,  }
+VQSHLU_N/VQSHLUQ_N:111:result_uint64x1 [] = { 40,  }
+VQSHLU_N/VQSHLUQ_N:112:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:113:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:114:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:115:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHLU_N/VQSHLUQ_N:116:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:117:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:118:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:119:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHLU_N/VQSHLUQ_N:120:result_uint8x16 [] = { a0, a0, a0, a0, a0, a0, a0, a0, a0, a0, a0, a0, a0, a0, a0, a0,  }
+VQSHLU_N/VQSHLUQ_N:121:result_uint16x8 [] = { 180, 180, 180, 180, 180, 180, 180, 180,  }
+VQSHLU_N/VQSHLUQ_N:122:result_uint32x4 [] = { 380, 380, 380, 380,  }
+VQSHLU_N/VQSHLUQ_N:123:result_uint64x2 [] = { 800, 800,  }
+VQSHLU_N/VQSHLUQ_N:124:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHLU_N/VQSHLUQ_N:125:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHLU_N/VQSHLUQ_N:126:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHLU_N/VQSHLUQ_N:127:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VCLZ/VCLZQ output:
+VCLZ/VCLZQ:0:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VCLZ/VCLZQ:1:result_int16x4 [] = { 3, 3, 3, 3,  }
+VCLZ/VCLZQ:2:result_int32x2 [] = { 11, 11,  }
+VCLZ/VCLZQ:3:result_int64x1 [] = { 3333333333333333,  }
+VCLZ/VCLZQ:4:result_uint8x8 [] = { 2, 2, 2, 2, 2, 2, 2, 2,  }
+VCLZ/VCLZQ:5:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VCLZ/VCLZQ:6:result_uint32x2 [] = { 5, 5,  }
+VCLZ/VCLZQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VCLZ/VCLZQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLZ/VCLZQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCLZ/VCLZQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VCLZ/VCLZQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VCLZ/VCLZQ:12:result_int8x16 [] = { 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2, 2,  }
+VCLZ/VCLZQ:13:result_int16x8 [] = { 3, 3, 3, 3, 3, 3, 3, 3,  }
+VCLZ/VCLZQ:14:result_int32x4 [] = { 3, 3, 3, 3,  }
+VCLZ/VCLZQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCLZ/VCLZQ:16:result_uint8x16 [] = { 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3, 3,  }
+VCLZ/VCLZQ:17:result_uint16x8 [] = { d, d, d, d, d, d, d, d,  }
+VCLZ/VCLZQ:18:result_uint32x4 [] = { 1f, 1f, 1f, 1f,  }
+VCLZ/VCLZQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCLZ/VCLZQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLZ/VCLZQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCLZ/VCLZQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCLZ/VCLZQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VCLZ/VCLZQ (input=0) output:
+VCLZ/VCLZQ:24:result_int8x8 [] = { 8, 8, 8, 8, 8, 8, 8, 8,  }
+VCLZ/VCLZQ:25:result_int16x4 [] = { 10, 10, 10, 10,  }
+VCLZ/VCLZQ:26:result_int32x2 [] = { 20, 20,  }
+VCLZ/VCLZQ:27:result_int64x1 [] = { 3333333333333333,  }
+VCLZ/VCLZQ:28:result_uint8x8 [] = { 8, 8, 8, 8, 8, 8, 8, 8,  }
+VCLZ/VCLZQ:29:result_uint16x4 [] = { 10, 10, 10, 10,  }
+VCLZ/VCLZQ:30:result_uint32x2 [] = { 20, 20,  }
+VCLZ/VCLZQ:31:result_uint64x1 [] = { 3333333333333333,  }
+VCLZ/VCLZQ:32:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLZ/VCLZQ:33:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCLZ/VCLZQ:34:result_float32x2 [] = { 33333333, 33333333,  }
+VCLZ/VCLZQ:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VCLZ/VCLZQ:36:result_int8x16 [] = { 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,  }
+VCLZ/VCLZQ:37:result_int16x8 [] = { 10, 10, 10, 10, 10, 10, 10, 10,  }
+VCLZ/VCLZQ:38:result_int32x4 [] = { 20, 20, 20, 20,  }
+VCLZ/VCLZQ:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCLZ/VCLZQ:40:result_uint8x16 [] = { 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,  }
+VCLZ/VCLZQ:41:result_uint16x8 [] = { 10, 10, 10, 10, 10, 10, 10, 10,  }
+VCLZ/VCLZQ:42:result_uint32x4 [] = { 20, 20, 20, 20,  }
+VCLZ/VCLZQ:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCLZ/VCLZQ:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLZ/VCLZQ:45:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCLZ/VCLZQ:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCLZ/VCLZQ:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VCLS/VCLSQ (positive input) output:
+VCLS/VCLSQ:0:result_int8x8 [] = { 6, 6, 6, 6, 6, 6, 6, 6,  }
+VCLS/VCLSQ:1:result_int16x4 [] = { 2, 2, 2, 2,  }
+VCLS/VCLSQ:2:result_int32x2 [] = { 19, 19,  }
+VCLS/VCLSQ:3:result_int64x1 [] = { 3333333333333333,  }
+VCLS/VCLSQ:4:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLS/VCLSQ:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCLS/VCLSQ:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VCLS/VCLSQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VCLS/VCLSQ:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLS/VCLSQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCLS/VCLSQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VCLS/VCLSQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VCLS/VCLSQ:12:result_int8x16 [] = { 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,  }
+VCLS/VCLSQ:13:result_int16x8 [] = { 2, 2, 2, 2, 2, 2, 2, 2,  }
+VCLS/VCLSQ:14:result_int32x4 [] = { 14, 14, 14, 14,  }
+VCLS/VCLSQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCLS/VCLSQ:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLS/VCLSQ:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCLS/VCLSQ:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCLS/VCLSQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCLS/VCLSQ:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLS/VCLSQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCLS/VCLSQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCLS/VCLSQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VCLS/VCLSQ (negative input) output:
+VCLS/VCLSQ:24:result_int8x8 [] = { 7, 7, 7, 7, 7, 7, 7, 7,  }
+VCLS/VCLSQ:25:result_int16x4 [] = { 1, 1, 1, 1,  }
+VCLS/VCLSQ:26:result_int32x2 [] = { 1, 1,  }
+VCLS/VCLSQ:27:result_int64x1 [] = { 3333333333333333,  }
+VCLS/VCLSQ:28:result_uint8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLS/VCLSQ:29:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCLS/VCLSQ:30:result_uint32x2 [] = { 33333333, 33333333,  }
+VCLS/VCLSQ:31:result_uint64x1 [] = { 3333333333333333,  }
+VCLS/VCLSQ:32:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLS/VCLSQ:33:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCLS/VCLSQ:34:result_float32x2 [] = { 33333333, 33333333,  }
+VCLS/VCLSQ:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VCLS/VCLSQ:36:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VCLS/VCLSQ:37:result_int16x8 [] = { 2, 2, 2, 2, 2, 2, 2, 2,  }
+VCLS/VCLSQ:38:result_int32x4 [] = { 0, 0, 0, 0,  }
+VCLS/VCLSQ:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCLS/VCLSQ:40:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLS/VCLSQ:41:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCLS/VCLSQ:42:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCLS/VCLSQ:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCLS/VCLSQ:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VCLS/VCLSQ:45:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCLS/VCLSQ:46:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCLS/VCLSQ:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VCNT/VCNTQ output:
+VCNT/VCNTQ:0:result_int8x8 [] = { 8, 8, 8, 8, 8, 8, 8, 8,  }
+VCNT/VCNTQ:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCNT/VCNTQ:2:result_int32x2 [] = { 33333333, 33333333,  }
+VCNT/VCNTQ:3:result_int64x1 [] = { 3333333333333333,  }
+VCNT/VCNTQ:4:result_uint8x8 [] = { 4, 4, 4, 4, 4, 4, 4, 4,  }
+VCNT/VCNTQ:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCNT/VCNTQ:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VCNT/VCNTQ:7:result_uint64x1 [] = { 3333333333333333,  }
+VCNT/VCNTQ:8:result_poly8x8 [] = { 4, 4, 4, 4, 4, 4, 4, 4,  }
+VCNT/VCNTQ:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VCNT/VCNTQ:10:result_float32x2 [] = { 33333333, 33333333,  }
+VCNT/VCNTQ:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VCNT/VCNTQ:12:result_int8x16 [] = { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,  }
+VCNT/VCNTQ:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCNT/VCNTQ:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCNT/VCNTQ:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCNT/VCNTQ:16:result_uint8x16 [] = { 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,  }
+VCNT/VCNTQ:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCNT/VCNTQ:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCNT/VCNTQ:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VCNT/VCNTQ:20:result_poly8x16 [] = { 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,  }
+VCNT/VCNTQ:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VCNT/VCNTQ:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VCNT/VCNTQ:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHRN_N cumulative saturation output:
+VQSHRN_N:0:vqshrn_n_s16 Neon cumulative saturation 0
+VQSHRN_N:1:vqshrn_n_s32 Neon cumulative saturation 0
+VQSHRN_N:2:vqshrn_n_s64 Neon cumulative saturation 0
+VQSHRN_N:3:vqshrn_n_u16 Neon cumulative saturation 1
+VQSHRN_N:4:vqshrn_n_u32 Neon cumulative saturation 1
+VQSHRN_N:5:vqshrn_n_u64 Neon cumulative saturation 1
+
+VQSHRN_N output:
+VQSHRN_N:6:result_int8x8 [] = { fffffff8, fffffff8, fffffff9, fffffff9, fffffffa, fffffffa, fffffffb, fffffffb,  }
+VQSHRN_N:7:result_int16x4 [] = { fffffff8, fffffff8, fffffff9, fffffff9,  }
+VQSHRN_N:8:result_int32x2 [] = { fffffffc, fffffffc,  }
+VQSHRN_N:9:result_int64x1 [] = { 3333333333333333,  }
+VQSHRN_N:10:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHRN_N:11:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHRN_N:12:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHRN_N:13:result_uint64x1 [] = { 3333333333333333,  }
+VQSHRN_N:14:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:15:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRN_N:16:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHRN_N:17:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHRN_N:18:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:19:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:20:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRN_N:21:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRN_N:22:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:23:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:24:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRN_N:25:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRN_N:26:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:27:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:28:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRN_N:29:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHRN_N (check saturation: shift by 3) cumulative saturation output:
+VQSHRN_N:30:vqshrn_n_s16 Neon cumulative saturation 1
+VQSHRN_N:31:vqshrn_n_s32 Neon cumulative saturation 1
+VQSHRN_N:32:vqshrn_n_s64 Neon cumulative saturation 1
+VQSHRN_N:33:vqshrn_n_u16 Neon cumulative saturation 1
+VQSHRN_N:34:vqshrn_n_u32 Neon cumulative saturation 1
+VQSHRN_N:35:vqshrn_n_u64 Neon cumulative saturation 1
+
+VQSHRN_N (check saturation: shift by 3) output:
+VQSHRN_N:36:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHRN_N:37:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQSHRN_N:38:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQSHRN_N:39:result_int64x1 [] = { 3333333333333333,  }
+VQSHRN_N:40:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHRN_N:41:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHRN_N:42:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHRN_N:43:result_uint64x1 [] = { 3333333333333333,  }
+VQSHRN_N:44:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:45:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRN_N:46:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHRN_N:47:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHRN_N:48:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:49:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:50:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRN_N:51:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRN_N:52:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:53:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:54:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRN_N:55:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRN_N:56:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:57:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:58:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRN_N:59:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHRN_N (check saturation: shift by max) cumulative saturation output:
+VQSHRN_N:60:vqshrn_n_s16 Neon cumulative saturation 0
+VQSHRN_N:61:vqshrn_n_s32 Neon cumulative saturation 0
+VQSHRN_N:62:vqshrn_n_s64 Neon cumulative saturation 0
+VQSHRN_N:63:vqshrn_n_u16 Neon cumulative saturation 0
+VQSHRN_N:64:vqshrn_n_u32 Neon cumulative saturation 0
+VQSHRN_N:65:vqshrn_n_u64 Neon cumulative saturation 0
+
+VQSHRN_N (check saturation: shift by max) output:
+VQSHRN_N:66:result_int8x8 [] = { 7f, 7f, 7f, 7f, 7f, 7f, 7f, 7f,  }
+VQSHRN_N:67:result_int16x4 [] = { 7fff, 7fff, 7fff, 7fff,  }
+VQSHRN_N:68:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VQSHRN_N:69:result_int64x1 [] = { 3333333333333333,  }
+VQSHRN_N:70:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHRN_N:71:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHRN_N:72:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHRN_N:73:result_uint64x1 [] = { 3333333333333333,  }
+VQSHRN_N:74:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:75:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRN_N:76:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHRN_N:77:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHRN_N:78:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:79:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:80:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRN_N:81:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRN_N:82:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:83:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:84:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRN_N:85:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRN_N:86:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRN_N:87:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRN_N:88:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRN_N:89:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VPMAX output:
+VPMAX:0:result_int8x8 [] = { fffffff1, fffffff3, fffffff5, fffffff7, fffffff1, fffffff3, fffffff5, fffffff7,  }
+VPMAX:1:result_int16x4 [] = { fffffff1, fffffff3, fffffff1, fffffff3,  }
+VPMAX:2:result_int32x2 [] = { fffffff1, fffffff1,  }
+VPMAX:3:result_int64x1 [] = { 3333333333333333,  }
+VPMAX:4:result_uint8x8 [] = { f1, f3, f5, f7, f1, f3, f5, f7,  }
+VPMAX:5:result_uint16x4 [] = { fff1, fff3, fff1, fff3,  }
+VPMAX:6:result_uint32x2 [] = { fffffff1, fffffff1,  }
+VPMAX:7:result_uint64x1 [] = { 3333333333333333,  }
+VPMAX:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPMAX:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VPMAX:10:result_float32x2 [] = { c1700000, c1700000,  }
+VPMAX:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VPMAX:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPMAX:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPMAX:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPMAX:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VPMAX:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPMAX:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPMAX:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPMAX:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VPMAX:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPMAX:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPMAX:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPMAX:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VPMIN output:
+VPMIN:0:result_int8x8 [] = { fffffff0, fffffff2, fffffff4, fffffff6, fffffff0, fffffff2, fffffff4, fffffff6,  }
+VPMIN:1:result_int16x4 [] = { fffffff0, fffffff2, fffffff0, fffffff2,  }
+VPMIN:2:result_int32x2 [] = { fffffff0, fffffff0,  }
+VPMIN:3:result_int64x1 [] = { 3333333333333333,  }
+VPMIN:4:result_uint8x8 [] = { f0, f2, f4, f6, f0, f2, f4, f6,  }
+VPMIN:5:result_uint16x4 [] = { fff0, fff2, fff0, fff2,  }
+VPMIN:6:result_uint32x2 [] = { fffffff0, fffffff0,  }
+VPMIN:7:result_uint64x1 [] = { 3333333333333333,  }
+VPMIN:8:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPMIN:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VPMIN:10:result_float32x2 [] = { c1800000, c1800000,  }
+VPMIN:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VPMIN:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPMIN:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPMIN:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPMIN:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VPMIN:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPMIN:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPMIN:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPMIN:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VPMIN:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VPMIN:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VPMIN:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VPMIN:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHRUN_N (negative input) cumulative saturation output:
+VQSHRUN_N:0:vqshrun_n_s16 Neon cumulative saturation 1
+VQSHRUN_N:1:vqshrun_n_s32 Neon cumulative saturation 1
+VQSHRUN_N:2:vqshrun_n_s64 Neon cumulative saturation 1
+
+VQSHRUN_N (negative input) output:
+VQSHRUN_N:3:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:4:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:5:result_int32x2 [] = { 33333333, 33333333,  }
+VQSHRUN_N:6:result_int64x1 [] = { 3333333333333333,  }
+VQSHRUN_N:7:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQSHRUN_N:8:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQSHRUN_N:9:result_uint32x2 [] = { 0, 0,  }
+VQSHRUN_N:10:result_uint64x1 [] = { 3333333333333333,  }
+VQSHRUN_N:11:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:12:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:13:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHRUN_N:14:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHRUN_N:15:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:16:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:17:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRUN_N:18:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRUN_N:19:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:20:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:21:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRUN_N:22:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRUN_N:23:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:24:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:25:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRUN_N:26:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHRUN_N (check cumulative saturation) cumulative saturation output:
+VQSHRUN_N:27:vqshrun_n_s16 Neon cumulative saturation 1
+VQSHRUN_N:28:vqshrun_n_s32 Neon cumulative saturation 1
+VQSHRUN_N:29:vqshrun_n_s64 Neon cumulative saturation 1
+
+VQSHRUN_N (check cumulative saturation) output:
+VQSHRUN_N:30:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:31:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:32:result_int32x2 [] = { 33333333, 33333333,  }
+VQSHRUN_N:33:result_int64x1 [] = { 3333333333333333,  }
+VQSHRUN_N:34:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQSHRUN_N:35:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQSHRUN_N:36:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQSHRUN_N:37:result_uint64x1 [] = { 3333333333333333,  }
+VQSHRUN_N:38:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:39:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:40:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHRUN_N:41:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHRUN_N:42:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:43:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:44:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRUN_N:45:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRUN_N:46:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:47:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:48:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRUN_N:49:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRUN_N:50:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:51:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:52:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRUN_N:53:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQSHRUN_N cumulative saturation output:
+VQSHRUN_N:54:vqshrun_n_s16 Neon cumulative saturation 0
+VQSHRUN_N:55:vqshrun_n_s32 Neon cumulative saturation 1
+VQSHRUN_N:56:vqshrun_n_s64 Neon cumulative saturation 0
+
+VQSHRUN_N output:
+VQSHRUN_N:57:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:58:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:59:result_int32x2 [] = { 33333333, 33333333,  }
+VQSHRUN_N:60:result_int64x1 [] = { 3333333333333333,  }
+VQSHRUN_N:61:result_uint8x8 [] = { 48, 48, 48, 48, 48, 48, 48, 48,  }
+VQSHRUN_N:62:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQSHRUN_N:63:result_uint32x2 [] = { deadbe, deadbe,  }
+VQSHRUN_N:64:result_uint64x1 [] = { 3333333333333333,  }
+VQSHRUN_N:65:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:66:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:67:result_float32x2 [] = { 33333333, 33333333,  }
+VQSHRUN_N:68:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQSHRUN_N:69:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:70:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:71:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRUN_N:72:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRUN_N:73:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:74:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:75:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRUN_N:76:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQSHRUN_N:77:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQSHRUN_N:78:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQSHRUN_N:79:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQSHRUN_N:80:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHRUN_N (negative input) cumulative saturation output:
+VQRSHRUN_N:0:vqrshrun_n_s16 Neon cumulative saturation 0
+VQRSHRUN_N:1:vqrshrun_n_s32 Neon cumulative saturation 0
+VQRSHRUN_N:2:vqrshrun_n_s64 Neon cumulative saturation 1
+
+VQRSHRUN_N (negative input) output:
+VQRSHRUN_N:3:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:4:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:5:result_int32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:6:result_int64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:7:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHRUN_N:8:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRUN_N:9:result_uint32x2 [] = { 0, 0,  }
+VQRSHRUN_N:10:result_uint64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:11:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:12:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:13:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:14:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRUN_N:15:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:16:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:17:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:18:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:19:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:20:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:21:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:22:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:23:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:24:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:25:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:26:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHRUN_N (check cumulative saturation: shift by 1) cumulative saturation output:
+VQRSHRUN_N:27:vqrshrun_n_s16 Neon cumulative saturation 1
+VQRSHRUN_N:28:vqrshrun_n_s32 Neon cumulative saturation 1
+VQRSHRUN_N:29:vqrshrun_n_s64 Neon cumulative saturation 1
+
+VQRSHRUN_N (check cumulative saturation: shift by 1) output:
+VQRSHRUN_N:30:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:31:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:32:result_int32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:33:result_int64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:34:result_uint8x8 [] = { ff, ff, ff, ff, ff, ff, ff, ff,  }
+VQRSHRUN_N:35:result_uint16x4 [] = { ffff, ffff, ffff, ffff,  }
+VQRSHRUN_N:36:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VQRSHRUN_N:37:result_uint64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:38:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:39:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:40:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:41:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRUN_N:42:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:43:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:44:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:45:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:46:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:47:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:48:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:49:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:50:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:51:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:52:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:53:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHRUN_N (check cumulative saturation: shift by max, positive input) cumulative saturation output:
+VQRSHRUN_N:54:vqrshrun_n_s16 Neon cumulative saturation 0
+VQRSHRUN_N:55:vqrshrun_n_s32 Neon cumulative saturation 0
+VQRSHRUN_N:56:vqrshrun_n_s64 Neon cumulative saturation 0
+
+VQRSHRUN_N (check cumulative saturation: shift by max, positive input) output:
+VQRSHRUN_N:57:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:58:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:59:result_int32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:60:result_int64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:61:result_uint8x8 [] = { 80, 80, 80, 80, 80, 80, 80, 80,  }
+VQRSHRUN_N:62:result_uint16x4 [] = { 8000, 8000, 8000, 8000,  }
+VQRSHRUN_N:63:result_uint32x2 [] = { 80000000, 80000000,  }
+VQRSHRUN_N:64:result_uint64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:65:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:66:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:67:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:68:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRUN_N:69:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:70:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:71:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:72:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:73:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:74:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:75:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:76:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:77:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:78:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:79:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:80:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHRUN_N (check cumulative saturation: shift by max, negative input) cumulative saturation output:
+VQRSHRUN_N:81:vqrshrun_n_s16 Neon cumulative saturation 1
+VQRSHRUN_N:82:vqrshrun_n_s32 Neon cumulative saturation 1
+VQRSHRUN_N:83:vqrshrun_n_s64 Neon cumulative saturation 1
+
+VQRSHRUN_N (check cumulative saturation: shift by max, negative input) output:
+VQRSHRUN_N:84:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:85:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:86:result_int32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:87:result_int64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:88:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VQRSHRUN_N:89:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRUN_N:90:result_uint32x2 [] = { 0, 0,  }
+VQRSHRUN_N:91:result_uint64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:92:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:93:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:94:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:95:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRUN_N:96:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:97:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:98:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:99:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:100:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:101:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:102:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:103:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:104:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:105:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:106:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:107:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VQRSHRUN_N cumulative saturation output:
+VQRSHRUN_N:108:vqrshrun_n_s16 Neon cumulative saturation 0
+VQRSHRUN_N:109:vqrshrun_n_s32 Neon cumulative saturation 1
+VQRSHRUN_N:110:vqrshrun_n_s64 Neon cumulative saturation 0
+
+VQRSHRUN_N output:
+VQRSHRUN_N:111:result_int8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:112:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:113:result_int32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:114:result_int64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:115:result_uint8x8 [] = { 49, 49, 49, 49, 49, 49, 49, 49,  }
+VQRSHRUN_N:116:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRUN_N:117:result_uint32x2 [] = { deadbf, deadbf,  }
+VQRSHRUN_N:118:result_uint64x1 [] = { 3333333333333333,  }
+VQRSHRUN_N:119:result_poly8x8 [] = { 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:120:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:121:result_float32x2 [] = { 33333333, 33333333,  }
+VQRSHRUN_N:122:result_float16x4 [] = { 0, 0, 0, 0,  }
+VQRSHRUN_N:123:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:124:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:125:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:126:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:127:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:128:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:129:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:130:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VQRSHRUN_N:131:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VQRSHRUN_N:132:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VQRSHRUN_N:133:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VQRSHRUN_N:134:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VST2_LANE/VST2Q_LANE chunk 0 output:
+VST2_LANE/VST2Q_LANE:0:result_int8x8 [] = { fffffff0, fffffff1, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:1:result_int16x4 [] = { fffffff0, fffffff1, 0, 0,  }
+VST2_LANE/VST2Q_LANE:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VST2_LANE/VST2Q_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VST2_LANE/VST2Q_LANE:4:result_uint8x8 [] = { f0, f1, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:5:result_uint16x4 [] = { fff0, fff1, 0, 0,  }
+VST2_LANE/VST2Q_LANE:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VST2_LANE/VST2Q_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VST2_LANE/VST2Q_LANE:8:result_poly8x8 [] = { f0, f1, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:9:result_poly16x4 [] = { fff0, fff1, 0, 0,  }
+VST2_LANE/VST2Q_LANE:10:result_float32x2 [] = { c1800000, c1700000,  }
+VST2_LANE/VST2Q_LANE:11:result_float16x4 [] = { cc00, cb80, 0, 0,  }
+VST2_LANE/VST2Q_LANE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST2_LANE/VST2Q_LANE:13:result_int16x8 [] = { fffffff0, fffffff1, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:14:result_int32x4 [] = { fffffff0, fffffff1, 0, 0,  }
+VST2_LANE/VST2Q_LANE:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST2_LANE/VST2Q_LANE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST2_LANE/VST2Q_LANE:17:result_uint16x8 [] = { fff0, fff1, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:18:result_uint32x4 [] = { fffffff0, fffffff1, 0, 0,  }
+VST2_LANE/VST2Q_LANE:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST2_LANE/VST2Q_LANE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST2_LANE/VST2Q_LANE:21:result_poly16x8 [] = { fff0, fff1, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:22:result_float32x4 [] = { c1800000, c1700000, 0, 0,  }
+VST2_LANE/VST2Q_LANE:23:result_float16x8 [] = { cc00, cb80, 0, 0, 0, 0, 0, 0,  }
+
+VST2_LANE/VST2Q_LANE chunk 1 output:
+VST2_LANE/VST2Q_LANE:24:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:25:result_int16x4 [] = { 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:26:result_int32x2 [] = { 0, 0,  }
+VST2_LANE/VST2Q_LANE:27:result_int64x1 [] = { 3333333333333333,  }
+VST2_LANE/VST2Q_LANE:28:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:29:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:30:result_uint32x2 [] = { 0, 0,  }
+VST2_LANE/VST2Q_LANE:31:result_uint64x1 [] = { 3333333333333333,  }
+VST2_LANE/VST2Q_LANE:32:result_poly8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:33:result_poly16x4 [] = { 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:34:result_float32x2 [] = { 0, 0,  }
+VST2_LANE/VST2Q_LANE:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:36:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST2_LANE/VST2Q_LANE:37:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:38:result_int32x4 [] = { 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST2_LANE/VST2Q_LANE:40:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST2_LANE/VST2Q_LANE:41:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:42:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST2_LANE/VST2Q_LANE:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST2_LANE/VST2Q_LANE:45:result_poly16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:46:result_float32x4 [] = { 0, 0, 0, 0,  }
+VST2_LANE/VST2Q_LANE:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VST3_LANE/VST3Q_LANE chunk 0 output:
+VST3_LANE/VST3Q_LANE:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, 0,  }
+VST3_LANE/VST3Q_LANE:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VST3_LANE/VST3Q_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:4:result_uint8x8 [] = { f0, f1, f2, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:5:result_uint16x4 [] = { fff0, fff1, fff2, 0,  }
+VST3_LANE/VST3Q_LANE:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VST3_LANE/VST3Q_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:8:result_poly8x8 [] = { f0, f1, f2, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:9:result_poly16x4 [] = { fff0, fff1, fff2, 0,  }
+VST3_LANE/VST3Q_LANE:10:result_float32x2 [] = { c1800000, c1700000,  }
+VST3_LANE/VST3Q_LANE:11:result_float16x4 [] = { cc00, cb80, cb00, 0,  }
+VST3_LANE/VST3Q_LANE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:14:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, 0,  }
+VST3_LANE/VST3Q_LANE:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:17:result_uint16x8 [] = { fff0, fff1, fff2, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, 0,  }
+VST3_LANE/VST3Q_LANE:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:21:result_poly16x8 [] = { fff0, fff1, fff2, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:22:result_float32x4 [] = { c1800000, c1700000, c1600000, 0,  }
+VST3_LANE/VST3Q_LANE:23:result_float16x8 [] = { cc00, cb80, cb00, 0, 0, 0, 0, 0,  }
+
+VST3_LANE/VST3Q_LANE chunk 1 output:
+VST3_LANE/VST3Q_LANE:24:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:25:result_int16x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:26:result_int32x2 [] = { fffffff2, 0,  }
+VST3_LANE/VST3Q_LANE:27:result_int64x1 [] = { 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:28:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:29:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:30:result_uint32x2 [] = { fffffff2, 0,  }
+VST3_LANE/VST3Q_LANE:31:result_uint64x1 [] = { 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:32:result_poly8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:33:result_poly16x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:34:result_float32x2 [] = { c1600000, 0,  }
+VST3_LANE/VST3Q_LANE:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:36:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:37:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:38:result_int32x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:40:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:41:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:42:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:45:result_poly16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:46:result_float32x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VST3_LANE/VST3Q_LANE chunk 2 output:
+VST3_LANE/VST3Q_LANE:48:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:49:result_int16x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:50:result_int32x2 [] = { 0, 0,  }
+VST3_LANE/VST3Q_LANE:51:result_int64x1 [] = { 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:52:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:53:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:54:result_uint32x2 [] = { 0, 0,  }
+VST3_LANE/VST3Q_LANE:55:result_uint64x1 [] = { 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:56:result_poly8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:57:result_poly16x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:58:result_float32x2 [] = { 0, 0,  }
+VST3_LANE/VST3Q_LANE:59:result_float16x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:60:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:61:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:62:result_int32x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:63:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:64:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:65:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:66:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:67:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST3_LANE/VST3Q_LANE:68:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST3_LANE/VST3Q_LANE:69:result_poly16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:70:result_float32x4 [] = { 0, 0, 0, 0,  }
+VST3_LANE/VST3Q_LANE:71:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VST4_LANE/VST4Q_LANE chunk 0 output:
+VST4_LANE/VST4Q_LANE:0:result_int8x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:1:result_int16x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VST4_LANE/VST4Q_LANE:2:result_int32x2 [] = { fffffff0, fffffff1,  }
+VST4_LANE/VST4Q_LANE:3:result_int64x1 [] = { 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:4:result_uint8x8 [] = { f0, f1, f2, f3, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:5:result_uint16x4 [] = { fff0, fff1, fff2, fff3,  }
+VST4_LANE/VST4Q_LANE:6:result_uint32x2 [] = { fffffff0, fffffff1,  }
+VST4_LANE/VST4Q_LANE:7:result_uint64x1 [] = { 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:8:result_poly8x8 [] = { f0, f1, f2, f3, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:9:result_poly16x4 [] = { fff0, fff1, fff2, fff3,  }
+VST4_LANE/VST4Q_LANE:10:result_float32x2 [] = { c1800000, c1700000,  }
+VST4_LANE/VST4Q_LANE:11:result_float16x4 [] = { cc00, cb80, cb00, ca80,  }
+VST4_LANE/VST4Q_LANE:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:13:result_int16x8 [] = { fffffff0, fffffff1, fffffff2, fffffff3, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:14:result_int32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VST4_LANE/VST4Q_LANE:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:17:result_uint16x8 [] = { fff0, fff1, fff2, fff3, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:18:result_uint32x4 [] = { fffffff0, fffffff1, fffffff2, fffffff3,  }
+VST4_LANE/VST4Q_LANE:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:21:result_poly16x8 [] = { fff0, fff1, fff2, fff3, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:22:result_float32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+VST4_LANE/VST4Q_LANE:23:result_float16x8 [] = { cc00, cb80, cb00, ca80, 0, 0, 0, 0,  }
+
+VST4_LANE/VST4Q_LANE chunk 1 output:
+VST4_LANE/VST4Q_LANE:24:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:25:result_int16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:26:result_int32x2 [] = { fffffff2, fffffff3,  }
+VST4_LANE/VST4Q_LANE:27:result_int64x1 [] = { 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:28:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:29:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:30:result_uint32x2 [] = { fffffff2, fffffff3,  }
+VST4_LANE/VST4Q_LANE:31:result_uint64x1 [] = { 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:32:result_poly8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:33:result_poly16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:34:result_float32x2 [] = { c1600000, c1500000,  }
+VST4_LANE/VST4Q_LANE:35:result_float16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:36:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:37:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:38:result_int32x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:39:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:40:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:41:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:42:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:43:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:44:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:45:result_poly16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:46:result_float32x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:47:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VST4_LANE/VST4Q_LANE chunk 2 output:
+VST4_LANE/VST4Q_LANE:48:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:49:result_int16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:50:result_int32x2 [] = { 0, 0,  }
+VST4_LANE/VST4Q_LANE:51:result_int64x1 [] = { 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:52:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:53:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:54:result_uint32x2 [] = { 0, 0,  }
+VST4_LANE/VST4Q_LANE:55:result_uint64x1 [] = { 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:56:result_poly8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:57:result_poly16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:58:result_float32x2 [] = { 0, 0,  }
+VST4_LANE/VST4Q_LANE:59:result_float16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:60:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:61:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:62:result_int32x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:63:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:64:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:65:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:66:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:67:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:68:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:69:result_poly16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:70:result_float32x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:71:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VST4_LANE/VST4Q_LANE chunk 3 output:
+VST4_LANE/VST4Q_LANE:72:result_int8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:73:result_int16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:74:result_int32x2 [] = { 0, 0,  }
+VST4_LANE/VST4Q_LANE:75:result_int64x1 [] = { 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:76:result_uint8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:77:result_uint16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:78:result_uint32x2 [] = { 0, 0,  }
+VST4_LANE/VST4Q_LANE:79:result_uint64x1 [] = { 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:80:result_poly8x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:81:result_poly16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:82:result_float32x2 [] = { 0, 0,  }
+VST4_LANE/VST4Q_LANE:83:result_float16x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:84:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:85:result_int16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:86:result_int32x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:87:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:88:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:89:result_uint16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:90:result_uint32x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:91:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VST4_LANE/VST4Q_LANE:92:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VST4_LANE/VST4Q_LANE:93:result_poly16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:94:result_float32x4 [] = { 0, 0, 0, 0,  }
+VST4_LANE/VST4Q_LANE:95:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VTBL1 output:
+VTBL1:0:result_int8x8 [] = { 0, fffffff2, fffffff2, fffffff2, 0, 0, fffffff2, fffffff2,  }
+VTBL1:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL1:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTBL1:3:result_int64x1 [] = { 3333333333333333,  }
+VTBL1:4:result_uint8x8 [] = { 0, f3, f3, f3, 0, 0, f3, f3,  }
+VTBL1:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL1:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VTBL1:7:result_uint64x1 [] = { 3333333333333333,  }
+VTBL1:8:result_poly8x8 [] = { 0, f3, f3, f3, 0, 0, f3, f3,  }
+VTBL1:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL1:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTBL1:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VTBL1:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL1:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL1:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL1:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBL1:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL1:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL1:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL1:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBL1:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL1:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL1:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL1:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VTBL2 output:
+VTBL2:0:result_int8x8 [] = { fffffff6, fffffff3, fffffff3, fffffff3, 0, 0, fffffff3, fffffff3,  }
+VTBL2:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL2:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTBL2:3:result_int64x1 [] = { 3333333333333333,  }
+VTBL2:4:result_uint8x8 [] = { f6, f5, f5, f5, 0, 0, f5, f5,  }
+VTBL2:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL2:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VTBL2:7:result_uint64x1 [] = { 3333333333333333,  }
+VTBL2:8:result_poly8x8 [] = { f6, f5, f5, f5, 0, 0, f5, f5,  }
+VTBL2:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL2:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTBL2:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VTBL2:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL2:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL2:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL2:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBL2:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL2:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL2:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL2:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBL2:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL2:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL2:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL2:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VTBL3 output:
+VTBL3:0:result_int8x8 [] = { fffffff8, fffffff4, fffffff4, fffffff4, ffffffff, 0, fffffff4, fffffff4,  }
+VTBL3:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL3:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTBL3:3:result_int64x1 [] = { 3333333333333333,  }
+VTBL3:4:result_uint8x8 [] = { f8, f7, f7, f7, ff, 0, f7, f7,  }
+VTBL3:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL3:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VTBL3:7:result_uint64x1 [] = { 3333333333333333,  }
+VTBL3:8:result_poly8x8 [] = { f8, f7, f7, f7, ff, 0, f7, f7,  }
+VTBL3:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL3:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTBL3:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VTBL3:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL3:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL3:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL3:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBL3:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL3:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL3:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL3:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBL3:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL3:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL3:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL3:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VTBL4 output:
+VTBL4:0:result_int8x8 [] = { fffffffa, fffffff5, fffffff5, fffffff5, 3, 0, fffffff5, fffffff5,  }
+VTBL4:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL4:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTBL4:3:result_int64x1 [] = { 3333333333333333,  }
+VTBL4:4:result_uint8x8 [] = { fa, f9, f9, f9, 3, 0, f9, f9,  }
+VTBL4:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL4:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VTBL4:7:result_uint64x1 [] = { 3333333333333333,  }
+VTBL4:8:result_poly8x8 [] = { fa, f9, f9, f9, 3, 0, f9, f9,  }
+VTBL4:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBL4:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTBL4:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VTBL4:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL4:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL4:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL4:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBL4:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL4:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL4:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL4:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBL4:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBL4:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBL4:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBL4:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VTBX1 output:
+VTBX1:0:result_int8x8 [] = { 33, fffffff2, fffffff2, fffffff2, 33, 33, fffffff2, fffffff2,  }
+VTBX1:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX1:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTBX1:3:result_int64x1 [] = { 3333333333333333,  }
+VTBX1:4:result_uint8x8 [] = { cc, f3, f3, f3, cc, cc, f3, f3,  }
+VTBX1:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX1:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VTBX1:7:result_uint64x1 [] = { 3333333333333333,  }
+VTBX1:8:result_poly8x8 [] = { cc, f3, f3, f3, cc, cc, f3, f3,  }
+VTBX1:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX1:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTBX1:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VTBX1:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX1:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX1:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX1:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBX1:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX1:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX1:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX1:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBX1:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX1:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX1:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX1:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VTBX2 output:
+VTBX2:0:result_int8x8 [] = { fffffff6, fffffff3, fffffff3, fffffff3, 33, 33, fffffff3, fffffff3,  }
+VTBX2:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX2:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTBX2:3:result_int64x1 [] = { 3333333333333333,  }
+VTBX2:4:result_uint8x8 [] = { f6, f5, f5, f5, cc, cc, f5, f5,  }
+VTBX2:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX2:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VTBX2:7:result_uint64x1 [] = { 3333333333333333,  }
+VTBX2:8:result_poly8x8 [] = { f6, f5, f5, f5, cc, cc, f5, f5,  }
+VTBX2:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX2:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTBX2:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VTBX2:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX2:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX2:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX2:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBX2:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX2:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX2:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX2:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBX2:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX2:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX2:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX2:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VTBX3 output:
+VTBX3:0:result_int8x8 [] = { fffffff8, fffffff4, fffffff4, fffffff4, ffffffff, 33, fffffff4, fffffff4,  }
+VTBX3:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX3:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTBX3:3:result_int64x1 [] = { 3333333333333333,  }
+VTBX3:4:result_uint8x8 [] = { f8, f7, f7, f7, ff, cc, f7, f7,  }
+VTBX3:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX3:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VTBX3:7:result_uint64x1 [] = { 3333333333333333,  }
+VTBX3:8:result_poly8x8 [] = { f8, f7, f7, f7, ff, cc, f7, f7,  }
+VTBX3:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX3:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTBX3:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VTBX3:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX3:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX3:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX3:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBX3:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX3:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX3:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX3:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBX3:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX3:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX3:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX3:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VTBX4 output:
+VTBX4:0:result_int8x8 [] = { fffffffa, fffffff5, fffffff5, fffffff5, 3, 33, fffffff5, fffffff5,  }
+VTBX4:1:result_int16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX4:2:result_int32x2 [] = { 33333333, 33333333,  }
+VTBX4:3:result_int64x1 [] = { 3333333333333333,  }
+VTBX4:4:result_uint8x8 [] = { fa, f9, f9, f9, 3, cc, f9, f9,  }
+VTBX4:5:result_uint16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX4:6:result_uint32x2 [] = { 33333333, 33333333,  }
+VTBX4:7:result_uint64x1 [] = { 3333333333333333,  }
+VTBX4:8:result_poly8x8 [] = { fa, f9, f9, f9, 3, cc, f9, f9,  }
+VTBX4:9:result_poly16x4 [] = { 3333, 3333, 3333, 3333,  }
+VTBX4:10:result_float32x2 [] = { 33333333, 33333333,  }
+VTBX4:11:result_float16x4 [] = { 0, 0, 0, 0,  }
+VTBX4:12:result_int8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX4:13:result_int16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX4:14:result_int32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX4:15:result_int64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBX4:16:result_uint8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX4:17:result_uint16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX4:18:result_uint32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX4:19:result_uint64x2 [] = { 3333333333333333, 3333333333333333,  }
+VTBX4:20:result_poly8x16 [] = { 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33, 33,  }
+VTBX4:21:result_poly16x8 [] = { 3333, 3333, 3333, 3333, 3333, 3333, 3333, 3333,  }
+VTBX4:22:result_float32x4 [] = { 33333333, 33333333, 33333333, 33333333,  }
+VTBX4:23:result_float16x8 [] = { 0, 0, 0, 0, 0, 0, 0, 0,  }
+
+VRECPE/VRECPEQ  (positive input) output:
+VRECPE/VRECPEQ:0:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VRECPE/VRECPEQ:1:result_uint32x4 [] = { bf000000, bf000000, bf000000, bf000000,  }
+VRECPE/VRECPEQ:2:result_float32x2 [] = { 3f068000, 3f068000,  }
+VRECPE/VRECPEQ:3:result_float32x4 [] = { 3c030000, 3c030000, 3c030000, 3c030000,  }
+
+VRECPE/VRECPEQ  (negative input) output:
+VRECPE/VRECPEQ:4:result_uint32x2 [] = { 80000000, 80000000,  }
+VRECPE/VRECPEQ:5:result_uint32x4 [] = { ee800000, ee800000, ee800000, ee800000,  }
+VRECPE/VRECPEQ:6:result_float32x2 [] = { bdcc8000, bdcc8000,  }
+VRECPE/VRECPEQ:7:result_float32x4 [] = { bc030000, bc030000, bc030000, bc030000,  }
+
+VRECPE/VRECPEQ  FP special (NaN, infinity) output:
+VRECPE/VRECPEQ:8:result_float32x2 [] = { 7fc00000, 7fc00000,  }
+VRECPE/VRECPEQ:9:result_float32x4 [] = { 0, 0, 0, 0,  }
+
+VRECPE/VRECPEQ  FP special (zero, large value) output:
+VRECPE/VRECPEQ:10:result_float32x2 [] = { 7f800000, 7f800000,  }
+VRECPE/VRECPEQ:11:result_float32x4 [] = { 0, 0, 0, 0,  }
+
+VRECPE/VRECPEQ  FP special (-0, -infinity) output:
+VRECPE/VRECPEQ:12:result_float32x2 [] = { ff800000, ff800000,  }
+VRECPE/VRECPEQ:13:result_float32x4 [] = { 80000000, 80000000, 80000000, 80000000,  }
+
+VRECPE/VRECPEQ  FP special (large negative value) output:
+VRECPE/VRECPEQ:14:result_float32x2 [] = { 80000000, 80000000,  }
+
+VRSQRTE/VRSQRTEQ output:
+VRSQRTE/VRSQRTEQ:0:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VRSQRTE/VRSQRTEQ:1:result_uint32x4 [] = { 9c800000, 9c800000, 9c800000, 9c800000,  }
+VRSQRTE/VRSQRTEQ:2:result_float32x2 [] = { 3e498000, 3e498000,  }
+VRSQRTE/VRSQRTEQ:3:result_float32x4 [] = { 3e700000, 3e700000, 3e700000, 3e700000,  }
+
+VRSQRTE/VRSQRTEQ (2) output:
+VRSQRTE/VRSQRTEQ:4:result_uint32x2 [] = { 80000000, 80000000,  }
+VRSQRTE/VRSQRTEQ:5:result_uint32x4 [] = { ae800000, ae800000, ae800000, ae800000,  }
+
+VRSQRTE/VRSQRTEQ (3) output:
+VRSQRTE/VRSQRTEQ:6:result_uint32x2 [] = { b4800000, b4800000,  }
+VRSQRTE/VRSQRTEQ:7:result_uint32x4 [] = { ed000000, ed000000, ed000000, ed000000,  }
+
+VRSQRTE/VRSQRTEQ FP special (NaN, 0) output:
+VRSQRTE/VRSQRTEQ:8:result_float32x2 [] = { 7fc00000, 7fc00000,  }
+VRSQRTE/VRSQRTEQ:9:result_float32x4 [] = { 7f800000, 7f800000, 7f800000, 7f800000,  }
+
+VRSQRTE/VRSQRTEQ FP special (negative, infinity) output:
+VRSQRTE/VRSQRTEQ:10:result_float32x2 [] = { 7fc00000, 7fc00000,  }
+VRSQRTE/VRSQRTEQ:11:result_float32x4 [] = { 0, 0, 0, 0,  }
+
+VRSQRTE/VRSQRTEQ FP special (-0, -infinity) output:
+VRSQRTE/VRSQRTEQ:12:result_float32x2 [] = { ff800000, ff800000,  }
+VRSQRTE/VRSQRTEQ:13:result_float32x4 [] = { 7fc00000, 7fc00000, 7fc00000, 7fc00000,  }
+
+VCAGE/VCAGEQ output:
+VCAGE/VCAGEQ:0:result_uint32x2 [] = { ffffffff, 0,  }
+VCAGE/VCAGEQ:1:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, 0,  }
+
+VCAGE/VCAGEQ output:
+VCAGE/VCAGEQ:2:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCAGE/VCAGEQ:3:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+
+VCALE/VCALEQ output:
+VCALE/VCALEQ:0:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCALE/VCALEQ:1:result_uint32x4 [] = { 0, 0, ffffffff, ffffffff,  }
+
+VCALE/VCALEQ output:
+VCALE/VCALEQ:2:result_uint32x2 [] = { 0, 0,  }
+VCALE/VCALEQ:3:result_uint32x4 [] = { 0, 0, 0, 0,  }
+
+VCAGT/VCAGTQ output:
+VCAGT/VCAGTQ:0:result_uint32x2 [] = { 0, 0,  }
+VCAGT/VCAGTQ:1:result_uint32x4 [] = { ffffffff, ffffffff, 0, 0,  }
+
+VCAGT/VCAGTQ output:
+VCAGT/VCAGTQ:2:result_uint32x2 [] = { ffffffff, ffffffff,  }
+VCAGT/VCAGTQ:3:result_uint32x4 [] = { ffffffff, ffffffff, ffffffff, ffffffff,  }
+
+VCALT/VCALTQ output:
+VCALT/VCALTQ:0:result_uint32x2 [] = { 0, ffffffff,  }
+VCALT/VCALTQ:1:result_uint32x4 [] = { 0, 0, 0, ffffffff,  }
+
+VCALT/VCALTQ output:
+VCALT/VCALTQ:2:result_uint32x2 [] = { 0, 0,  }
+VCALT/VCALTQ:3:result_uint32x4 [] = { 0, 0, 0, 0,  }
+
+VCVT/VCVTQ output:
+VCVT/VCVTQ:0:result_float32x2 [] = { c1800000, c1700000,  }
+VCVT/VCVTQ:1:result_float32x2 [] = { 4f800000, 4f800000,  }
+VCVT/VCVTQ:2:result_float32x4 [] = { 41720000, c1720000, 0, 80000000,  }
+VCVT/VCVTQ:3:result_float32x4 [] = { c1800000, c1700000, c1600000, c1500000,  }
+VCVT/VCVTQ:4:result_float32x4 [] = { 4f800000, 4f800000, 4f800000, 4f800000,  }
+VCVT/VCVTQ:5:result_int32x2 [] = { fffffff1, 5,  }
+VCVT/VCVTQ:6:result_uint32x2 [] = { 0, 5,  }
+VCVT/VCVTQ:7:result_float16x4 [] = { 0, 8000, 4b8f, cb8f,  }
+VCVT/VCVTQ:8:result_int32x4 [] = { 0, 0, f, fffffff1,  }
+VCVT/VCVTQ:9:result_uint32x4 [] = { 0, 0, f, 0,  }
+
+VCVT_N/VCVTQ_N output:
+VCVT_N/VCVTQ_N:10:result_float32x2 [] = { c0800000, c0700000,  }
+VCVT_N/VCVTQ_N:11:result_float32x2 [] = { 4c000000, 4c000000,  }
+VCVT_N/VCVTQ_N:12:result_float32x4 [] = { b2800000, b2700000, b2600000, b2500000,  }
+VCVT_N/VCVTQ_N:13:result_float32x4 [] = { 49800000, 49800000, 49800000, 49800000,  }
+VCVT_N/VCVTQ_N:14:result_int32x2 [] = { ff0b3333, 54cccd,  }
+VCVT_N/VCVTQ_N:15:result_uint32x2 [] = { 0, 15,  }
+VCVT_N/VCVTQ_N:16:result_int32x4 [] = { 0, 0, 1e3d7, fffe1c29,  }
+VCVT_N/VCVTQ_N:17:result_uint32x4 [] = { 0, 0, 1e, 0,  }
+
+VCVT/VCVTQ (check rounding) output:
+VCVT/VCVTQ:18:result_int32x2 [] = { a, a,  }
+VCVT/VCVTQ:19:result_uint32x2 [] = { a, a,  }
+VCVT/VCVTQ:20:result_int32x4 [] = { 7d, 7d, 7d, 7d,  }
+VCVT/VCVTQ:21:result_uint32x4 [] = { 7d, 7d, 7d, 7d,  }
+
+VCVT_N/VCVTQ_N (check rounding) output:
+VCVT_N/VCVTQ_N:22:result_int32x2 [] = { a66666, a66666,  }
+VCVT_N/VCVTQ_N:23:result_uint32x2 [] = { a66666, a66666,  }
+VCVT_N/VCVTQ_N:24:result_int32x4 [] = { fbccc, fbccc, fbccc, fbccc,  }
+VCVT_N/VCVTQ_N:25:result_uint32x4 [] = { fbccc, fbccc, fbccc, fbccc,  }
+
+VCVT_N/VCVTQ_N (check saturation) output:
+VCVT_N/VCVTQ_N:26:result_int32x2 [] = { 7fffffff, 7fffffff,  }
+VCVT_N/VCVTQ_N:27:result_int32x4 [] = { 7fffffff, 7fffffff, 7fffffff, 7fffffff,  }
+
+VCVT FP16 (check fp16-fp32 inf/nan/denormal) output:
+VCVT FP16:28:result_float32x4 [] = { 38640000, 7f800000, 7fc00000, ff800000,  }
+
+VCVT FP16 (check fp32-fp16 inf/nan) output:
+VCVT FP16:29:result_float16x4 [] = { 7e00, 7c00, fc00, 8000,  }
+
+VRECPS/VRECPSQ output:
+VRECPS/VRECPSQ:0:result_float32x2 [] = { c2e19eb7, c2e19eb7,  }
+VRECPS/VRECPSQ:1:result_float32x4 [] = { c1db851f, c1db851f, c1db851f, c1db851f,  }
+
+VRECPS/VRECPSQ FP special (NAN) and normal values output:
+VRECPS/VRECPSQ:2:result_float32x2 [] = { 7fc00000, 7fc00000,  }
+VRECPS/VRECPSQ:3:result_float32x4 [] = { 7fc00000, 7fc00000, 7fc00000, 7fc00000,  }
+
+VRECPS/VRECPSQ FP special (infinity, 0) and normal values output:
+VRECPS/VRECPSQ:4:result_float32x2 [] = { ff800000, ff800000,  }
+VRECPS/VRECPSQ:5:result_float32x4 [] = { 40000000, 40000000, 40000000, 40000000,  }
+
+VRECPS/VRECPSQ FP special (infinity, 0) output:
+VRECPS/VRECPSQ:6:result_float32x2 [] = { 40000000, 40000000,  }
+VRECPS/VRECPSQ:7:result_float32x4 [] = { 40000000, 40000000, 40000000, 40000000,  }
+
+VRSQRTS/VRSQRTSQ output:
+VRSQRTS/VRSQRTSQ:0:result_float32x2 [] = { c2796b84, c2796b84,  }
+VRSQRTS/VRSQRTSQ:1:result_float32x4 [] = { c0e4a3d8, c0e4a3d8, c0e4a3d8, c0e4a3d8,  }
+
+VRSQRTS/VRSQRTSQ FP special (NAN) and normal values output:
+VRSQRTS/VRSQRTSQ:2:result_float32x2 [] = { 7fc00000, 7fc00000,  }
+VRSQRTS/VRSQRTSQ:3:result_float32x4 [] = { 7fc00000, 7fc00000, 7fc00000, 7fc00000,  }
+
+VRSQRTS/VRSQRTSQ FP special (infinity, 0) and normal values output:
+VRSQRTS/VRSQRTSQ:4:result_float32x2 [] = { ff800000, ff800000,  }
+VRSQRTS/VRSQRTSQ:5:result_float32x4 [] = { 3fc00000, 3fc00000, 3fc00000, 3fc00000,  }
+
+VRSQRTS/VRSQRTSQ FP special (infinity, 0) output:
+VRSQRTS/VRSQRTSQ:6:result_float32x2 [] = { 3fc00000, 3fc00000,  }
+VRSQRTS/VRSQRTSQ:7:result_float32x4 [] = { 3fc00000, 3fc00000, 3fc00000, 3fc00000,  }
diff --git a/ref_dsp.c b/ref_dsp.c
new file mode 100644
index 0000000..124f6b7
--- /dev/null
+++ b/ref_dsp.c
@@ -0,0 +1,421 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__cplusplus)
+#include <cstdio>
+#include <cstdint>
+#else
+#include <stdio.h>
+#if defined(_MSC_VER)
+#include "msstdint.h"
+#else
+#include <stdint.h>
+#endif
+#endif
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <armdsp.h>
+#include <dspfns.h> /* For Overflow */
+#else
+#include "stm-armdsp.h"
+#include "stm-dspfns.h" /* For Overflow */
+#endif
+
+extern FILE* ref_file;
+
+void exec_dsp (void)
+{
+  int32_t svar1, svar2, sacc, sres;
+  int32_t lo, hi;
+
+
+  fprintf(ref_file, "\n\nDSP (non-NEON) intrinsics\n");
+
+  /* qadd */
+  /* int32_t qadd(int32_t val1, int32_t val2); */
+  svar1 = 1;
+  svar2 = 2;
+  Overflow = 0;
+  sres = qadd(svar1, svar2);
+  fprintf(ref_file, "qadd(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = -1;
+  svar2 = -2;
+  Overflow = 0;
+  sres = qadd(svar1, svar2);
+  fprintf(ref_file, "qadd(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = -1;
+  svar2 = 2;
+  Overflow = 0;
+  sres = qadd(svar1, svar2);
+  fprintf(ref_file, "qadd(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = 0x7000;
+  svar2 = 0x7000;
+  Overflow = 0;
+  sres = qadd(svar1, svar2);
+  fprintf(ref_file, "qadd(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = 0x8FFF;
+  svar2 = 0x8FFF;
+  Overflow = 0;
+  sres = qadd(svar1, svar2);
+  fprintf(ref_file, "qadd(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = 0x70000000;
+  svar2 = 0x70000000;
+  Overflow = 0;
+  sres = qadd(svar1, svar2);
+  fprintf(ref_file, "qadd(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = 0x8FFFFFFF;
+  svar2 = 0x8FFFFFFF;
+  Overflow = 0;
+  sres = qadd(svar1, svar2);
+  fprintf(ref_file, "qadd(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  /* qsub */
+  /* int32_t qsub(int32_t val1, int32_t val2); */
+  svar1 = 1;
+  svar2 = 2;
+  Overflow = 0;
+  sres = qsub(svar1, svar2);
+  fprintf(ref_file, "qsub(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = -1;
+  svar2 = -2;
+  Overflow = 0;
+  sres = qsub(svar1, svar2);
+  fprintf(ref_file, "qsub(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = -1;
+  svar2 = 2;
+  Overflow = 0;
+  sres = qsub(svar1, svar2);
+  fprintf(ref_file, "qsub(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = 0x7000;
+  svar2 = 0xFFFF9000;
+  Overflow = 0;
+  sres = qsub(svar1, svar2);
+  fprintf(ref_file, "qsub(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = 0x8FFF;
+  svar2 = 0xFFFF7001;
+  Overflow = 0;
+  sres = qsub(svar1, svar2);
+  fprintf(ref_file, "qsub(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = 0x70000000;
+  svar2 = 0x90000000;
+  Overflow = 0;
+  sres = qsub(svar1, svar2);
+  fprintf(ref_file, "qsub(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = 0x8FFFFFFF;
+  svar2 = 0x70000001;
+  Overflow = 0;
+  sres = qsub(svar1, svar2);
+  fprintf(ref_file, "qsub(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = 0;
+  svar2 = 0x80000000;
+  Overflow = 0;
+  sres = qsub(svar1, svar2);
+  fprintf(ref_file, "qsub(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+
+  /* qdadd */
+  /* int32_t qdadd(int32_t val1, int32_t val2); */
+  svar1 = 1;
+  svar2 = 2;
+  Overflow = 0;
+  sres = qdadd(svar1, svar2);
+  fprintf(ref_file, "qdadd(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = -1;
+  svar2 = -2;
+  Overflow = 0;
+  sres = qdadd(svar1, svar2);
+  fprintf(ref_file, "qdadd(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = -1;
+  svar2 = 2;
+  Overflow = 0;
+  sres = qdadd(svar1, svar2);
+  fprintf(ref_file, "qdadd(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = 0x7000;
+  svar2 = 0x7000;
+  Overflow = 0;
+  sres = qdadd(svar1, svar2);
+  fprintf(ref_file, "qdadd(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = 0x8FFF;
+  svar2 = 0x8FFF;
+  Overflow = 0;
+  sres = qdadd(svar1, svar2);
+  fprintf(ref_file, "qdadd(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = 0x70000000;
+  svar2 = 0x70000000;
+  Overflow = 0;
+  sres = qdadd(svar1, svar2);
+  fprintf(ref_file, "qdadd(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = 0;
+  svar2 = 0x70000000;
+  Overflow = 0;
+  sres = qdadd(svar1, svar2);
+  fprintf(ref_file, "qdadd(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = 0x8FFFFFFF;
+  svar2 = 0x8FFFFFFF;
+  Overflow = 0;
+  sres = qdadd(svar1, svar2);
+  fprintf(ref_file, "qdadd(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = 0;
+  svar2 = 0x8FFFFFFF;
+  Overflow = 0;
+  sres = qdadd(svar1, svar2);
+  fprintf(ref_file, "qdadd(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  /* qdsub */
+  /* int32_t qdsub(int32_t val1, int32_t val2); */
+  svar1 = 1;
+  svar2 = 2;
+  Overflow = 0;
+  sres = qdsub(svar1, svar2);
+  fprintf(ref_file, "qdsub(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = -1;
+  svar2 = -2;
+  Overflow = 0;
+  sres = qdsub(svar1, svar2);
+  fprintf(ref_file, "qdsub(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = -1;
+  svar2 = 2;
+  Overflow = 0;
+  sres = qdsub(svar1, svar2);
+  fprintf(ref_file, "qdsub(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = 0x7000;
+  svar2 = 0xFFFF9000;
+  Overflow = 0;
+  sres = qdsub(svar1, svar2);
+  fprintf(ref_file, "qdsub(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = 0x8FFF;
+  svar2 = 0xFFFF7001;
+  Overflow = 0;
+  sres = qdsub(svar1, svar2);
+  fprintf(ref_file, "qdsub(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = 0x70000000;
+  svar2 = 0x90000000;
+  Overflow = 0;
+  sres = qdsub(svar1, svar2);
+  fprintf(ref_file, "qdsub(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = 0;
+  svar2 = 0x90000000;
+  Overflow = 0;
+  sres = qdsub(svar1, svar2);
+  fprintf(ref_file, "qdsub(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = 0x8FFFFFFF;
+  svar2 = 0x70000001;
+  Overflow = 0;
+  sres = qdsub(svar1, svar2);
+  fprintf(ref_file, "qdsub(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+  svar1 = 0;
+  svar2 = 0x70000001;
+  Overflow = 0;
+  sres = qdsub(svar1, svar2);
+  fprintf(ref_file, "qdsub(%#x, %#x) = %#x sat %d\n", svar1, svar2, sres, Overflow);
+
+
+  /* smulbb, smulbt, smultb, smultt */
+  /* int32_t smulbb(int32_t val1, int32_t val2); */
+  svar1 = 0x12345678;
+  svar2 = 0x12345678;
+  sres = smulbb(svar1, svar2);
+  fprintf(ref_file, "smulbb(%#x, %#x) = %#x\n", svar1, svar2, sres);
+  sres = smulbt(svar1, svar2);
+  fprintf(ref_file, "smulbt(%#x, %#x) = %#x\n", svar1, svar2, sres);
+  sres = smultb(svar1, svar2);
+  fprintf(ref_file, "smultb(%#x, %#x) = %#x\n", svar1, svar2, sres);
+  sres = smultt(svar1, svar2);
+  fprintf(ref_file, "smultt(%#x, %#x) = %#x\n", svar1, svar2, sres);
+
+  svar1 = 0xF123F456;
+  svar2 = 0xF123F456;
+  sres = smulbb(svar1, svar2);
+  fprintf(ref_file, "smulbb(%#x, %#x) = %#x\n", svar1, svar2, sres);
+  sres = smulbt(svar1, svar2);
+  fprintf(ref_file, "smulbt(%#x, %#x) = %#x\n", svar1, svar2, sres);
+  sres = smultb(svar1, svar2);
+  fprintf(ref_file, "smultb(%#x, %#x) = %#x\n", svar1, svar2, sres);
+  sres = smultt(svar1, svar2);
+  fprintf(ref_file, "smultt(%#x, %#x) = %#x\n", svar1, svar2, sres);
+
+
+  /* smlabb, smlabt, smlatb, smlatt */
+  /* int32_t smlabb(int32_t val1, int32_t val2, int32_t acc); */
+  sacc = 0x01020304;
+  svar1 = 0x12345678;
+  svar2 = 0x12345678;
+  sres = smlabb(svar1, svar2, sacc);
+  fprintf(ref_file, "smlabb(%#x, %#x, %#x) = %#x\n", svar1, svar2, sacc, sres);
+  sres = smlabt(svar1, svar2, sacc);
+  fprintf(ref_file, "smlabt(%#x, %#x, %#x) = %#x\n", svar1, svar2, sacc, sres);
+  sres = smlatb(svar1, svar2, sacc);
+  fprintf(ref_file, "smlatb(%#x, %#x, %#x) = %#x\n", svar1, svar2, sacc, sres);
+  sres = smlatt(svar1, svar2, sacc);
+  fprintf(ref_file, "smlatt(%#x, %#x, %#x) = %#x\n", svar1, svar2, sacc, sres);
+
+  svar1 = 0xF123F456;
+  svar2 = 0xF123F456;
+  sres = smlabb(svar1, svar2, sacc);
+  fprintf(ref_file, "smlabb(%#x, %#x, %#x) = %#x\n", svar1, svar2, sacc, sres);
+  sres = smlabt(svar1, svar2, sacc);
+  fprintf(ref_file, "smlabt(%#x, %#x, %#x) = %#x\n", svar1, svar2, sacc, sres);
+  sres = smlatb(svar1, svar2, sacc);
+  fprintf(ref_file, "smlatb(%#x, %#x, %#x) = %#x\n", svar1, svar2, sacc, sres);
+  sres = smlatt(svar1, svar2, sacc);
+  fprintf(ref_file, "smlatt(%#x, %#x, %#x) = %#x\n", svar1, svar2, sacc, sres);
+
+
+  /* smlalbb, smlalbt, smlaltb, smlaltt */
+  /* int32_t smlalbb(int32_t *lo, int32_t *hi, int32_t val1, int32_t val2); */
+  svar1 = 0x12345678;
+  svar2 = 0x12345678;
+  hi = 0x12345678;
+  lo = 0x9ABCDEF0;
+  fprintf(ref_file, "smlalbb(&%#x, &%#x, %#x, %#x) = ", lo, hi, svar1, svar2);
+  smlalbb(&lo, &hi, svar1, svar2);
+  fprintf(ref_file, "%#x%#x\n", hi, lo);
+  hi = 0x12345678;
+  lo = 0x9ABCDEF0;
+  fprintf(ref_file, "smlalbt(&%#x, &%#x, %#x, %#x) = ", lo, hi, svar1, svar2);
+  smlalbt(&lo, &hi, svar1, svar2);
+  fprintf(ref_file, "%#x%#x\n", hi, lo);
+  hi = 0x12345678;
+  lo = 0x9ABCDEF0;
+  fprintf(ref_file, "smlaltb(&%#x, &%#x, %#x, %#x) = ", lo, hi, svar1, svar2);
+  smlaltb(&lo, &hi, svar1, svar2);
+  fprintf(ref_file, "%#x%#x\n", hi, lo);
+  hi = 0x12345678;
+  lo = 0x9ABCDEF0;
+  fprintf(ref_file, "smlaltt(&%#x, &%#x, %#x, %#x) = ", lo, hi, svar1, svar2);
+  smlaltt(&lo, &hi, svar1, svar2);
+  fprintf(ref_file, "%#x%#x\n", hi, lo);
+
+  svar1 = 0xF123F456;
+  svar2 = 0xF123F456;
+  hi = 0x12345678;
+  lo = 0x9ABCDEF0;
+  fprintf(ref_file, "smlalbb(&%#x, &%#x, %#x, %#x) = ", lo, hi, svar1, svar2);
+  smlalbb(&lo, &hi, svar1, svar2);
+  fprintf(ref_file, "%#x%#x\n", hi, lo);
+  hi = 0x12345678;
+  lo = 0x9ABCDEF0;
+  fprintf(ref_file, "smlalbt(&%#x, &%#x, %#x, %#x) = ", lo, hi, svar1, svar2);
+  smlalbt(&lo, &hi, svar1, svar2);
+  fprintf(ref_file, "%#x%#x\n", hi, lo);
+  hi = 0x12345678;
+  lo = 0x9ABCDEF0;
+  fprintf(ref_file, "smlaltb(&%#x, &%#x, %#x, %#x) = ", lo, hi, svar1, svar2);
+  smlaltb(&lo, &hi, svar1, svar2);
+  fprintf(ref_file, "%#x%#x\n", hi, lo);
+  hi = 0x12345678;
+  lo = 0x9ABCDEF0;
+  fprintf(ref_file, "smlaltt(&%#x, &%#x, %#x, %#x) = ", lo, hi, svar1, svar2);
+  smlaltt(&lo, &hi, svar1, svar2);
+  fprintf(ref_file, "%#x%#x\n", hi, lo);
+
+  svar1 = 0x7FFF7FFF;
+  svar2 = 0x7FFF7FFF;
+  hi = 0x12345678;
+  lo = 0xFFFFFFFF;
+  fprintf(ref_file, "smlalbb(&%#x, &%#x, %#x, %#x) = ", lo, hi, svar1, svar2);
+  smlalbb(&lo, &hi, svar1, svar2);
+  fprintf(ref_file, "%#x%#x\n", hi, lo);
+  hi = 0x12345678;
+  lo = 0xFFFFFFFF;
+  fprintf(ref_file, "smlalbt(&%#x, &%#x, %#x, %#x) = ", lo, hi, svar1, svar2);
+  smlalbt(&lo, &hi, svar1, svar2);
+  fprintf(ref_file, "%#x%#x\n", hi, lo);
+  hi = 0x12345678;
+  lo = 0xFFFFFFFF;
+  fprintf(ref_file, "smlaltb(&%#x, &%#x, %#x, %#x) = ", lo, hi, svar1, svar2);
+  smlaltb(&lo, &hi, svar1, svar2);
+  fprintf(ref_file, "%#x%#x\n", hi, lo);
+  hi = 0x12345678;
+  lo = 0xFFFFFFFF;
+  fprintf(ref_file, "smlaltt(&%#x, &%#x, %#x, %#x) = ", lo, hi, svar1, svar2);
+  smlaltt(&lo, &hi, svar1, svar2);
+  fprintf(ref_file, "%#x%#x\n", hi, lo);
+
+
+  /* smulwb, smulwt */
+  /* int32_t smulwb(int32_t val1, int32_t val2); */
+  svar1 = 0x12345678;
+  svar2 = 0x12345678;
+  sres = smulwb(svar1, svar2);
+  fprintf(ref_file, "smulwb(%#x, %#x) = %#x\n", svar1, svar2, sres);
+  sres = smulwt(svar1, svar2);
+  fprintf(ref_file, "smulwt(%#x, %#x) = %#x\n", svar1, svar2, sres);
+
+  svar1 = 0xF123F456;
+  svar2 = 0xF123F456;
+  sres = smulwb(svar1, svar2);
+  fprintf(ref_file, "smulwb(%#x, %#x) = %#x\n", svar1, svar2, sres);
+  sres = smulwt(svar1, svar2);
+  fprintf(ref_file, "smulwt(%#x, %#x) = %#x\n", svar1, svar2, sres);
+
+
+  /* smlawb, smlawt */
+  /* int32_t smlawb(int32_t val1, int32_t val2, int32_t acc); */
+  sacc = 0x01020304;
+  svar1 = 0x12345678;
+  svar2 = 0x12345678;
+  sres = smlawb(svar1, svar2, sacc);
+  fprintf(ref_file, "smlawb(%#x, %#x, %#x) = %#x\n", svar1, svar2, sacc, sres);
+  sres = smlawt(svar1, svar2, sacc);
+  fprintf(ref_file, "smlawt(%#x, %#x, %#x) = %#x\n", svar1, svar2, sacc, sres);
+
+  svar1 = 0xF123F456;
+  svar2 = 0xF123F456;
+  sres = smlawb(svar1, svar2, sacc);
+  fprintf(ref_file, "smlawb(%#x, %#x, %#x) = %#x\n", svar1, svar2, sacc, sres);
+  sres = smlawt(svar1, svar2, sacc);
+  fprintf(ref_file, "smlawt(%#x, %#x, %#X) = %#x\n", svar1, svar2, sacc, sres);
+
+}
diff --git a/ref_dspfns.c b/ref_dspfns.c
new file mode 100644
index 0000000..a8409c6
--- /dev/null
+++ b/ref_dspfns.c
@@ -0,0 +1,1502 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__cplusplus)
+#include <cstdio>
+#include <cstdint>
+#else
+#include <stdio.h>
+#if defined(_MSC_VER)
+#include "msstdint.h"
+#else
+#include <stdint.h>
+#endif
+#endif
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <dspfns.h>
+#else
+#include "stm-dspfns.h"
+#endif
+
+extern FILE* ref_file;
+
+#define __xSTR(X) #X
+#define __STR(X) __xSTR(X)
+
+#define FN(X) X, __STR(X)
+
+typedef int32_t func32_32_32_ptr(int32_t, int32_t);
+typedef int16_t func16_32_ptr(int32_t);
+typedef int32_t func32_32_16_16_ptr(int32_t, int16_t, int16_t);
+
+void test_16_fn_32(func16_32_ptr func, const char* func_name,
+		   int init_Overflow, int init_Carry)
+{
+  int32_t svar32_a;
+  int16_t svar16_a;
+
+  fprintf(ref_file, "Checking %s with input Overflow=%d and input Carry=%d\n",
+	  func_name, init_Overflow, init_Carry);
+
+  svar32_a = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = func(svar32_a);
+  fprintf(ref_file, "%s(%#x) = %#x overflow %d carry %d\n",
+	  func_name, svar32_a, svar16_a, Overflow, Carry);
+
+  svar32_a = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = func(svar32_a);
+  fprintf(ref_file, "%s(%#x) = %#x overflow %d carry %d\n",
+	  func_name, svar32_a, svar16_a, Overflow, Carry);
+
+  svar32_a = 32768;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = func(svar32_a);
+  fprintf(ref_file, "%s(%#x) = %#x overflow %d carry %d\n",
+	  func_name, svar32_a, svar16_a, Overflow, Carry);
+
+  svar32_a = -32768;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = func(svar32_a);
+  fprintf(ref_file, "%s(%#x) = %#x overflow %d carry %d\n",
+	  func_name, svar32_a, svar16_a, Overflow, Carry);
+
+  svar32_a = -32769;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = func(svar32_a);
+  fprintf(ref_file, "%s(%#x) = %#x overflow %d carry %d\n",
+	  func_name, svar32_a, svar16_a, Overflow, Carry);
+}
+
+void test_32_fn_32_32(func32_32_32_ptr func, const char* func_name,
+		      int init_Overflow, int init_Carry)
+{
+  int32_t svar32_a, svar32_b, svar32_c;
+
+  fprintf(ref_file, "Checking %s with input Overflow=%d and input Carry=%d\n",
+	  func_name, init_Overflow, init_Carry);
+
+  svar32_a = 1;
+  svar32_b = 2;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = func(svar32_a, svar32_b);
+  fprintf(ref_file, "%s(%#x, %#x) = %#x overflow %d carry %d\n",
+	  func_name, svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = -1;
+  svar32_b = -2;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = func(svar32_a, svar32_b);
+  fprintf(ref_file, "%s(%#x, %#x) = %#x overflow %d carry %d\n",
+	  func_name, svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = -1;
+  svar32_b = 2;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = func(svar32_a, svar32_b);
+  fprintf(ref_file, "%s(%#x, %#x) = %#x overflow %d carry %d\n",
+	  func_name, svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x7000;
+  svar32_b = 0x7000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = func(svar32_a, svar32_b);
+  fprintf(ref_file, "%s(%#x, %#x) = %#x overflow %d carry %d\n",
+	  func_name, svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x8FFF;
+  svar32_b = 0x8FFF;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = func(svar32_a, svar32_b);
+  fprintf(ref_file, "%s(%#x, %#x) = %#x overflow %d carry %d\n",
+	  func_name, svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x70000000;
+  svar32_b = 0x70000000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = func(svar32_a, svar32_b);
+  fprintf(ref_file, "%s(%#x, %#x) = %#x overflow %d carry %d\n",
+	  func_name, svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x8FFFFFFF;
+  svar32_b = 0x8FFFFFFF;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = func(svar32_a, svar32_b);
+  fprintf(ref_file, "%s(%#x, %#x) = %#x overflow %d carry %d\n",
+	  func_name, svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x8FFFFFFF;
+  svar32_b = 0xFFFFFFFF;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = func(svar32_a, svar32_b);
+  fprintf(ref_file, "%s(%#x, %#x) = %#x overflow %d carry %d\n",
+	  func_name, svar32_a, svar32_b, svar32_c, Overflow, Carry);
+}
+
+void test_32_fn_32_16_16(func32_32_16_16_ptr func, const char* func_name,
+		      int init_Overflow, int init_Carry)
+{
+  int32_t svar32_a, svar32_b;
+  int16_t svar16_a, svar16_b;
+
+  fprintf(ref_file, "Checking %s with input Overflow=%d and input Carry=%d\n",
+	  func_name, init_Overflow, init_Carry);
+
+  svar16_a = 2;
+  svar16_b = 2;
+  svar32_a = 0x1234;
+  Overflow = 0;
+  Carry = init_Carry;
+  svar32_b = func(svar32_a, svar16_a, svar16_b);
+  fprintf(ref_file, "%s(%#x, %#x, %#x) = %#x overflow %d carry %d\n",
+	  func_name, svar32_a, svar16_a, svar16_b, svar32_b, Overflow, Carry);
+
+  svar16_a = -1;
+  svar16_b = -1;
+  Overflow = 0;
+  Carry = init_Carry;
+  svar32_b = func(svar32_a, svar16_a, svar16_b);
+  fprintf(ref_file, "%s(%#x, %#x, %#x) = %#x overflow %d carry %d\n",
+	  func_name, svar32_a, svar16_a, svar16_b, svar32_b, Overflow, Carry);
+
+  svar16_a = 0x8000;
+  svar16_b = 0x8000;
+  Overflow = 0;
+  Carry = init_Carry;
+  svar32_b = func(svar32_a, svar16_a, svar16_b);
+  fprintf(ref_file, "%s(%#x, %#x, %#x) = %#x overflow %d carry %d\n",
+	  func_name, svar32_a, svar16_a, svar16_b, svar32_b, Overflow, Carry);
+
+  svar16_a = 0x8000;
+  svar16_b = 0x8000;
+  Overflow = 0;
+  Carry = init_Carry;
+  svar32_a = -1;
+  svar32_b = func(svar32_a, svar16_a, svar16_b);
+  fprintf(ref_file, "%s(%#x, %#x, %#x) = %#x overflow %d carry %d\n",
+	  func_name, svar32_a, svar16_a, svar16_b, svar32_b, Overflow, Carry);
+}
+
+void exec_dspfns1 (int init_Overflow, int init_Carry)
+{
+  int32_t svar32_a, svar32_b, svar32_c;
+  int16_t svar16_a, svar16_b, svar16_c;
+
+
+  fprintf(ref_file, "\n\nDSP FNS (non-NEON/ITU) intrinsics with input Overflow=%d and input Carry=%d\n", init_Overflow, init_Carry);
+
+  /* saturate */
+  /* int16_t saturate(int32_t x) */
+  test_16_fn_32(FN(saturate), init_Overflow, init_Carry);
+
+
+  /* add */
+  /* int16_t add(int16_t x, int16_t y) */
+  svar16_a = 1;
+  svar16_b = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = add(svar16_a, svar16_b);
+  fprintf(ref_file, "add(%#x, %#x) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = -1;
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = add(svar16_a, svar16_b);
+  fprintf(ref_file, "add(%#x, %#x) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 20000;
+  svar16_b = 20000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = add(svar16_a, svar16_b);
+  fprintf(ref_file, "add(%#x, %#x) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = -20000;
+  svar16_b = -20000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = add(svar16_a, svar16_b);
+  fprintf(ref_file, "add(%#x, %#x) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+
+  /* sub */
+  /* int16_t sub(int16_t x, int16_t y) */
+  svar16_a = 1;
+  svar16_b = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = sub(svar16_a, svar16_b);
+  fprintf(ref_file, "sub(%#x, %#x) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = -1;
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = sub(svar16_a, svar16_b);
+  fprintf(ref_file, "sub(%#x, %#x) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 20000;
+  svar16_b = 20000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = sub(svar16_a, svar16_b);
+  fprintf(ref_file, "sub(%#x, %#x) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = -20000;
+  svar16_b = -20000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = sub(svar16_a, svar16_b);
+  fprintf(ref_file, "sub(%#x, %#x) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 0;
+  svar16_b = -32768;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = sub(svar16_a, svar16_b);
+  fprintf(ref_file, "sub(%#x, %#x) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+
+  /* abs_s */
+  /* int16_t abs_s(int16_t x) */
+  svar16_b = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = abs_s(svar16_b);
+  fprintf(ref_file, "abs_s(%#x) = %#x overflow %d carry %d\n", svar16_b, svar16_a, Overflow, Carry);
+
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = abs_s(svar16_b);
+  fprintf(ref_file, "abs_s(%#x) = %#x overflow %d carry %d\n", svar16_b, svar16_a, Overflow, Carry);
+
+  svar16_b = -32768;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = abs_s(svar16_b);
+  fprintf(ref_file, "abs_s(%#x) = %#x overflow %d carry %d\n", svar16_b, svar16_a, Overflow, Carry);
+
+
+  /* shl */
+  /* int16_t shl(int16_t x, int16_t y) */
+  svar16_a = 1;
+  svar16_b = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = shl(svar16_a, svar16_b);
+  fprintf(ref_file, "shl(%#x, %d) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 10;
+  svar16_b = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = shl(svar16_a, svar16_b);
+  fprintf(ref_file, "shl(%#x, %d) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 0xFFF;
+  svar16_b = 10;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = shl(svar16_a, svar16_b);
+  fprintf(ref_file, "shl(%#x, %d) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 0xFFF;
+  svar16_b = 20;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = shl(svar16_a, svar16_b);
+  fprintf(ref_file, "shl(%#x, %d) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 1;
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = shl(svar16_a, svar16_b);
+  fprintf(ref_file, "shl(%#x, %d) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 20;
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = shl(svar16_a, svar16_b);
+  fprintf(ref_file, "shl(%#x, %d) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 0xFFF;
+  svar16_b = -10;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = shl(svar16_a, svar16_b);
+  fprintf(ref_file, "shl(%#x, %d) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 0xFFF;
+  svar16_b = -64;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = shl(svar16_a, svar16_b);
+  fprintf(ref_file, "shl(%#x, %d) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+
+  /* shr */
+  /* int16_t shr(int16_t x, int16_t y) */
+  svar16_a = 1;
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = shr(svar16_a, svar16_b);
+  fprintf(ref_file, "shr(%#x, %d) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 10;
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = shr(svar16_a, svar16_b);
+  fprintf(ref_file, "shr(%#x, %d) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 0xFFF;
+  svar16_b = -10;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = shr(svar16_a, svar16_b);
+  fprintf(ref_file, "shr(%#x, %d) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 0xFFF;
+  svar16_b = -20;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = shr(svar16_a, svar16_b);
+  fprintf(ref_file, "shr(%#x, %d) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 1;
+  svar16_b = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = shr(svar16_a, svar16_b);
+  fprintf(ref_file, "shr(%#x, %d) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 20;
+  svar16_b = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = shr(svar16_a, svar16_b);
+  fprintf(ref_file, "shr(%#x, %d) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 0xFFF;
+  svar16_b = 10;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = shr(svar16_a, svar16_b);
+  fprintf(ref_file, "shr(%#x, %d) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 0xFFF;
+  svar16_b = 64;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = shr(svar16_a, svar16_b);
+  fprintf(ref_file, "shr(%#x, %d) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+
+  /* mult */
+  /* int16_t mult(int16_t x, int16_t y) */
+  svar16_a = 2;
+  svar16_b = 2;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = mult(svar16_a, svar16_b);
+  fprintf(ref_file, "mult(%#x, %#x) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = -1;
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = mult(svar16_a, svar16_b);
+  fprintf(ref_file, "mult(%#x, %#x) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 0x8000;
+  svar16_b = 0x8000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = mult(svar16_a, svar16_b);
+  fprintf(ref_file, "mult(%#x, %#x) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+
+  /* L_mult */
+  /* int32_t L_mult(int16_t x, int16_t y) */
+  svar16_a = 2;
+  svar16_b = 2;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_a = L_mult(svar16_a, svar16_b);
+  fprintf(ref_file, "L_mult(%#x, %#x) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar32_a, Overflow, Carry);
+
+  svar16_a = -1;
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_a = L_mult(svar16_a, svar16_b);
+  fprintf(ref_file, "L_mult(%#x, %#x) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar32_a, Overflow, Carry);
+
+  svar16_a = 0x8000;
+  svar16_b = 0x8000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_a = L_mult(svar16_a, svar16_b);
+  fprintf(ref_file, "L_mult(%#x, %#x) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar32_a, Overflow, Carry);
+
+
+  /* negate */
+  /* int16_t negate(int16_t x) */
+  svar16_b = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = negate(svar16_b);
+  fprintf(ref_file, "negate(%#x) = %#x overflow %d carry %d\n", svar16_b, svar16_a, Overflow, Carry);
+
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = negate(svar16_b);
+  fprintf(ref_file, "negate(%#x) = %#x overflow %d carry %d\n", svar16_b, svar16_a, Overflow, Carry);
+
+  svar16_b = -32768;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = negate(svar16_b);
+  fprintf(ref_file, "negate(%#x) = %#x overflow %d carry %d\n", svar16_b, svar16_a, Overflow, Carry);
+
+
+  /* extract_h */
+  /* int16_t extract_h(int32_t x) */
+  svar32_a = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = extract_h(svar32_a);
+  fprintf(ref_file, "extract_h(%#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, Overflow, Carry);
+
+  svar32_a = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = extract_h(svar32_a);
+  fprintf(ref_file, "extract_h(%#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, Overflow, Carry);
+
+  svar32_a = -32768;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = extract_h(svar32_a);
+  fprintf(ref_file, "extract_h(%#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, Overflow, Carry);
+
+  svar32_a = 0x12345678;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = extract_h(svar32_a);
+  fprintf(ref_file, "extract_h(%#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, Overflow, Carry);
+
+
+  /* extract_l */
+  /* int16_t extract_l(int32_t x) */
+  svar32_a = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = extract_l(svar32_a);
+  fprintf(ref_file, "extract_l(%#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, Overflow, Carry);
+
+  svar32_a = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = extract_l(svar32_a);
+  fprintf(ref_file, "extract_l(%#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, Overflow, Carry);
+
+  svar32_a = -32768;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = extract_l(svar32_a);
+  fprintf(ref_file, "extract_l(%#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, Overflow, Carry);
+
+  svar32_a = 0x43218765;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = extract_l(svar32_a);
+  fprintf(ref_file, "extract_l(%#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, Overflow, Carry);
+
+
+  /* round */
+  /* int16_t round(int32_t x) */
+  svar32_a = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = round(svar32_a);
+  fprintf(ref_file, "round(%#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, Overflow, Carry);
+
+  svar32_a = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = round(svar32_a);
+  fprintf(ref_file, "round(%#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, Overflow, Carry);
+
+  svar32_a = -32768;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = round(svar32_a);
+  fprintf(ref_file, "round(%#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, Overflow, Carry);
+
+  svar32_a = 0x43218765;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = round(svar32_a);
+  fprintf(ref_file, "round(%#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, Overflow, Carry);
+
+  svar32_a = 0x87654321;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = round(svar32_a);
+  fprintf(ref_file, "round(%#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, Overflow, Carry);
+
+
+  /* L_mac */
+  /* int32_t L_mac(int32_t acc, int16_t x, int16_t y) */
+  svar16_a = 2;
+  svar16_b = 2;
+  svar32_a = 0x1234;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_b = L_mac(svar32_a, svar16_a, svar16_b);
+  fprintf(ref_file, "L_mac(%#x, %#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, svar16_b, svar32_b, Overflow, Carry);
+
+  svar16_a = -1;
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_b = L_mac(svar32_a, svar16_a, svar16_b);
+  fprintf(ref_file, "L_mac(%#x, %#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, svar16_b, svar32_b, Overflow, Carry);
+
+  svar16_a = 0x8000;
+  svar16_b = 0x8000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_b = L_mac(svar32_a, svar16_a, svar16_b);
+  fprintf(ref_file, "L_mac(%#x, %#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, svar16_b, svar32_b, Overflow, Carry);
+
+  svar16_a = 0x8000;
+  svar16_b = 0x8000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_a = -1;
+  svar32_b = L_mac(svar32_a, svar16_a, svar16_b);
+  fprintf(ref_file, "L_mac(%#x, %#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, svar16_b, svar32_b, Overflow, Carry);
+
+
+  /* L_msu */
+  /* int32_t L_msu(int32_t acc, int16_t x, int16_t y) */
+  svar16_a = 2;
+  svar16_b = 2;
+  svar32_a = 0x1234;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_b = L_msu(svar32_a, svar16_a, svar16_b);
+  fprintf(ref_file, "L_msu(%#x, %#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, svar16_b, svar32_b, Overflow, Carry);
+
+  svar16_a = -1;
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_b = L_msu(svar32_a, svar16_a, svar16_b);
+  fprintf(ref_file, "L_msu(%#x, %#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, svar16_b, svar32_b, Overflow, Carry);
+
+  svar16_a = 0x8000;
+  svar16_b = 0x8000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_b = L_msu(svar32_a, svar16_a, svar16_b);
+  fprintf(ref_file, "L_msu(%#x, %#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, svar16_b, svar32_b, Overflow, Carry);
+
+  svar16_a = 0x8000;
+  svar16_b = 0x8000;
+  svar32_a = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_b = L_msu(svar32_a, svar16_a, svar16_b);
+  fprintf(ref_file, "L_msu(%#x, %#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, svar16_b, svar32_b, Overflow, Carry);
+
+
+  /* L_add */
+  /* int32_t L_add(int32_t val1, int32_t val2); */
+  svar32_a = 1;
+  svar32_b = 2;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_add(svar32_a, svar32_b);
+  fprintf(ref_file, "L_add(%#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = -1;
+  svar32_b = -2;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_add(svar32_a, svar32_b);
+  fprintf(ref_file, "L_add(%#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = -1;
+  svar32_b = 2;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_add(svar32_a, svar32_b);
+  fprintf(ref_file, "L_add(%#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x7000;
+  svar32_b = 0x7000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_add(svar32_a, svar32_b);
+  fprintf(ref_file, "L_add(%#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x8FFF;
+  svar32_b = 0x8FFF;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_add(svar32_a, svar32_b);
+  fprintf(ref_file, "L_add(%#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x70000000;
+  svar32_b = 0x70000000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_add(svar32_a, svar32_b);
+  fprintf(ref_file, "L_add(%#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x8FFFFFFF;
+  svar32_b = 0x8FFFFFFF;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_add(svar32_a, svar32_b);
+  fprintf(ref_file, "L_add(%#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  /* L_sub */
+  /* int32_t L_sub(int32_t val1, int32_t val2); */
+  svar32_a = 1;
+  svar32_b = 2;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_sub(svar32_a, svar32_b);
+  fprintf(ref_file, "L_sub(%#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = -1;
+  svar32_b = -2;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_sub(svar32_a, svar32_b);
+  fprintf(ref_file, "L_sub(%#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = -1;
+  svar32_b = 2;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_sub(svar32_a, svar32_b);
+  fprintf(ref_file, "L_sub(%#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x7000;
+  svar32_b = 0xFFFF9000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_sub(svar32_a, svar32_b);
+  fprintf(ref_file, "L_sub(%#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x8FFF;
+  svar32_b = 0xFFFF7001;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_sub(svar32_a, svar32_b);
+  fprintf(ref_file, "L_sub(%#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x70000000;
+  svar32_b = 0x90000000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_sub(svar32_a, svar32_b);
+  fprintf(ref_file, "L_sub(%#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x8FFFFFFF;
+  svar32_b = 0x70000001;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_sub(svar32_a, svar32_b);
+  fprintf(ref_file, "L_sub(%#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0;
+  svar32_b = 0x80000000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_sub(svar32_a, svar32_b);
+  fprintf(ref_file, "L_sub(%#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+
+  /* L_add_c */
+  /* int32_t L_add_c(int32_t val1, int32_t val2); */
+  test_32_fn_32_32(FN(L_add_c), init_Overflow, init_Carry);
+
+
+
+  /* L_sub_c */
+  /* int32_t L_sub_c(int32_t val1, int32_t val2); */
+#undef MYFN
+#define MYFN L_sub_c
+  svar32_a = 1;
+  svar32_b = 2;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = MYFN(svar32_a, svar32_b);
+  fprintf(ref_file, __STR(MYFN) "(%#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = -1;
+  svar32_b = -2;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = MYFN(svar32_a, svar32_b);
+  fprintf(ref_file, __STR(MYFN) "(%#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = -1;
+  svar32_b = 2;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = MYFN(svar32_a, svar32_b);
+  fprintf(ref_file, __STR(MYFN) "(%#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x7000;
+  svar32_b = 0x7000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = MYFN(svar32_a, svar32_b);
+  fprintf(ref_file, __STR(MYFN) "(%#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x8FFF;
+  svar32_b = 0x8FFF;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = MYFN(svar32_a, svar32_b);
+  fprintf(ref_file, __STR(MYFN) "(%#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x70000000;
+  svar32_b = 0x70000000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = MYFN(svar32_a, svar32_b);
+  fprintf(ref_file, __STR(MYFN) "(%#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x8FFFFFFF;
+  svar32_b = 0x8FFFFFFF;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = MYFN(svar32_a, svar32_b);
+  fprintf(ref_file, __STR(MYFN) "(%#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x1;
+  svar32_b = 0x80000000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = MYFN(svar32_a, svar32_b);
+  fprintf(ref_file, __STR(MYFN) "(%#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0xFFFFFFFF;
+  svar32_b = 0x7FFFFFFF;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = MYFN(svar32_a, svar32_b);
+  fprintf(ref_file, __STR(MYFN) "(%#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar32_b, svar32_c, Overflow, Carry);
+
+
+  /* L_macNs */
+  /* int32_t L_macNs(int32_t acc, int16_t x, int16_t y) */
+  test_32_fn_32_16_16(FN(L_macNs), init_Overflow, init_Carry);
+
+  /* L_msuNs */
+  /* int32_t L_msuNs(int32_t acc, int16_t x, int16_t y) */
+  test_32_fn_32_16_16(FN(L_msuNs), init_Overflow, init_Carry);
+
+
+  /* negate */
+  /* int32_t negate(int32_t x) */
+  svar32_b = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_a = negate(svar32_b);
+  fprintf(ref_file, "negate(%#x) = %#x overflow %d carry %d\n", svar32_b, svar32_a, Overflow, Carry);
+
+  svar32_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_a = negate(svar32_b);
+  fprintf(ref_file, "negate(%#x) = %#x overflow %d carry %d\n", svar32_b, svar32_a, Overflow, Carry);
+
+  svar32_b = -32768;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_a = negate(svar32_b);
+  fprintf(ref_file, "negate(%#x) = %#x overflow %d carry %d\n", svar32_b, svar32_a, Overflow, Carry);
+
+
+  /* mult_r */
+  /* int16_t mult_r(int16_t x, int16_t y) */
+  svar16_a = 2;
+  svar16_b = 2;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = mult_r(svar16_a, svar16_b);
+  fprintf(ref_file, "mult_r(%#x, %#x) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = -1;
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = mult_r(svar16_a, svar16_b);
+  fprintf(ref_file, "mult_r(%#x, %#x) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 0x8000;
+  svar16_b = 0x8000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = mult_r(svar16_a, svar16_b);
+  fprintf(ref_file, "mult_r(%#x, %#x) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+
+  /* norm_s */
+  /* int16_t norm_s(int32_t x) */
+  svar32_a = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = norm_s(svar32_a);
+  fprintf(ref_file, "norm_s(%#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, Overflow, Carry);
+
+  svar32_a = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = norm_s(svar32_a);
+  fprintf(ref_file, "norm_s(%#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, Overflow, Carry);
+
+  svar32_a = -32768;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = norm_s(svar32_a);
+  fprintf(ref_file, "norm_s(%#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, Overflow, Carry);
+
+  svar32_a = 12000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = norm_s(svar32_a);
+  fprintf(ref_file, "norm_s(%#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, Overflow, Carry);
+
+
+  /* norm_l */
+  /* int16_t norm_l(int16_t x) */
+  svar32_a = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = norm_l(svar32_a);
+  fprintf(ref_file, "norm_l(%#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, Overflow, Carry);
+
+  svar32_a = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = norm_l(svar32_a);
+  fprintf(ref_file, "norm_l(%#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, Overflow, Carry);
+
+  svar32_a = -32768;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = norm_l(svar32_a);
+  fprintf(ref_file, "norm_l(%#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, Overflow, Carry);
+
+  svar32_a = 12000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = norm_l(svar32_a);
+  fprintf(ref_file, "norm_l(%#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, Overflow, Carry);
+
+  svar32_a = 0x123456;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = norm_l(svar32_a);
+  fprintf(ref_file, "norm_l(%#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, Overflow, Carry);
+
+  svar32_a = 0xABCDEF;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_a = norm_l(svar32_a);
+  fprintf(ref_file, "norm_l(%#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, Overflow, Carry);
+
+
+  /* L_shl */
+  /* int32_t L_shl(int32_t x, int16_t y) */
+  svar32_a = 1;
+  svar16_b = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shl(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shl(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 10;
+  svar16_b = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shl(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shl(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0xFFF;
+  svar16_b = 10;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shl(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shl(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0xFFF;
+  svar16_b = 20;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shl(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shl(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x12345678;
+  svar16_b = 2;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shl(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shl(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x12345678;
+  svar16_b = 40;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shl(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shl(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 1;
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shl(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shl(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 20;
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shl(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shl(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0xFFF;
+  svar16_b = -10;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shl(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shl(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0xFFF;
+  svar16_b = -64;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shl(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shl(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x12345678;
+  svar16_b = -10;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shl(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shl(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x12345678;
+  svar16_b = -64;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shl(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shl(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+
+  /* L_shr */
+  /* int32_t L_shr(int32_t x, int16_t y) */
+  svar32_a = 1;
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shr(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shr(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 10;
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shr(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shr(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0xFFF;
+  svar16_b = -10;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shr(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shr(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0xFFF;
+  svar16_b = -20;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shr(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shr(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x12345678;
+  svar16_b = -10;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shr(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shr(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x12345678;
+  svar16_b = -40;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shr(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shr(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 1;
+  svar16_b = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shr(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shr(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 20;
+  svar16_b = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shr(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shr(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0xFFF;
+  svar16_b = 10;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shr(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shr(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0xFFF;
+  svar16_b = 64;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shr(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shr(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x12345678;
+  svar16_b = 10;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shr(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shr(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x12345678;
+  svar16_b = 64;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shr(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shr(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+
+  /* shr_r */
+  /* int16_t shr_r(int16_t x, int16_t y) */
+  svar16_a = 1;
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = shr_r(svar16_a, svar16_b);
+  fprintf(ref_file, "shr_r(%#x, %d) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 10;
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = shr_r(svar16_a, svar16_b);
+  fprintf(ref_file, "shr_r(%#x, %d) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 0xFFF;
+  svar16_b = -10;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = shr_r(svar16_a, svar16_b);
+  fprintf(ref_file, "shr_r(%#x, %d) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 0xFFF;
+  svar16_b = -20;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = shr_r(svar16_a, svar16_b);
+  fprintf(ref_file, "shr_r(%#x, %d) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 1;
+  svar16_b = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = shr_r(svar16_a, svar16_b);
+  fprintf(ref_file, "shr_r(%#x, %d) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 20;
+  svar16_b = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = shr_r(svar16_a, svar16_b);
+  fprintf(ref_file, "shr_r(%#x, %d) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 0xFFF;
+  svar16_b = 10;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = shr_r(svar16_a, svar16_b);
+  fprintf(ref_file, "shr_r(%#x, %d) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 0xFFF;
+  svar16_b = 64;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = shr_r(svar16_a, svar16_b);
+  fprintf(ref_file, "shr_r(%#x, %d) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+
+  /* mac_r */
+  /* int16_t mac_r(int32_t acc, int16_t x, int16_t y) */
+  svar16_a = 2;
+  svar16_b = 2;
+  svar32_a = 0x1234;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = mac_r(svar32_a, svar16_a, svar16_b);
+  fprintf(ref_file, "mac_r(%#x, %#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = -1;
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = mac_r(svar32_a, svar16_a, svar16_b);
+  fprintf(ref_file, "mac_r(%#x, %#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 0x8000;
+  svar16_b = 0x8000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = mac_r(svar32_a, svar16_a, svar16_b);
+  fprintf(ref_file, "mac_r(%#x, %#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 0x8000;
+  svar16_b = 0x8000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_a = -1;
+  svar16_c = mac_r(svar32_a, svar16_a, svar16_b);
+  fprintf(ref_file, "mac_r(%#x, %#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 0x244;
+  svar16_b = 0x522;
+  svar32_a = 0x123456;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = mac_r(svar32_a, svar16_a, svar16_b);
+  fprintf(ref_file, "mac_r(%#x, %#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+
+  /* msu_r */
+  /* int32_t msu_r(int32_t acc, int16_t x, int16_t y) */
+  svar16_a = 2;
+  svar16_b = 2;
+  svar32_a = 0x1234;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = msu_r(svar32_a, svar16_a, svar16_b);
+  fprintf(ref_file, "msu_r(%#x, %#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = -1;
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = msu_r(svar32_a, svar16_a, svar16_b);
+  fprintf(ref_file, "msu_r(%#x, %#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 0x8000;
+  svar16_b = 0x8000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = msu_r(svar32_a, svar16_a, svar16_b);
+  fprintf(ref_file, "msu_r(%#x, %#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 0x8000;
+  svar16_b = 0x8000;
+  svar32_a = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = msu_r(svar32_a, svar16_a, svar16_b);
+  fprintf(ref_file, "msu_r(%#x, %#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 0x321;
+  svar16_b = 0x243;
+  svar32_a = 0x123456;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = msu_r(svar32_a, svar16_a, svar16_b);
+  fprintf(ref_file, "msu_r(%#x, %#x, %#x) = %#x overflow %d carry %d\n", svar32_a, svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+
+  /* L_deposit_h */
+  /* int32_t L_deposit_h(int16_t x) */
+  svar16_b = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_a = L_deposit_h(svar16_b);
+  fprintf(ref_file, "L_deposit_h(%#x) = %#x overflow %d carry %d\n", svar16_b, svar32_a, Overflow, Carry);
+
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_a = L_deposit_h(svar16_b);
+  fprintf(ref_file, "L_deposit_h(%#x) = %#x overflow %d carry %d\n", svar16_b, svar32_a, Overflow, Carry);
+
+  svar16_b = -32768;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_a = L_deposit_h(svar16_b);
+  fprintf(ref_file, "L_deposit_h(%#x) = %#x overflow %d carry %d\n", svar16_b, svar32_a, Overflow, Carry);
+
+  svar16_b = 0x1234;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_a = L_deposit_h(svar16_b);
+  fprintf(ref_file, "L_deposit_h(%#x) = %#x overflow %d carry %d\n", svar16_b, svar32_a, Overflow, Carry);
+
+
+  /* L_deposit_l */
+  /* int32_t L_deposit_l(int16_t x) */
+  svar16_b = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_a = L_deposit_l(svar16_b);
+  fprintf(ref_file, "L_deposit_l(%#x) = %#x overflow %d carry %d\n", svar16_b, svar32_a, Overflow, Carry);
+
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_a = L_deposit_l(svar16_b);
+  fprintf(ref_file, "L_deposit_l(%#x) = %#x overflow %d carry %d\n", svar16_b, svar32_a, Overflow, Carry);
+
+  svar16_b = -32768;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_a = L_deposit_l(svar16_b);
+  fprintf(ref_file, "L_deposit_l(%#x) = %#x overflow %d carry %d\n", svar16_b, svar32_a, Overflow, Carry);
+
+  svar16_b = 0x1234;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_a = L_deposit_l(svar16_b);
+  fprintf(ref_file, "L_deposit_l(%#x) = %#x overflow %d carry %d\n", svar16_b, svar32_a, Overflow, Carry);
+
+
+  /* L_shr_r */
+  /* int32_t L_shr_r(int32_t x, int16_t y) */
+  svar32_a = 1;
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shr_r(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shr_r(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 10;
+  svar16_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shr_r(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shr_r(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0xFFF;
+  svar16_b = -10;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shr_r(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shr_r(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0xFFF;
+  svar16_b = -20;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shr_r(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shr_r(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x12345678;
+  svar16_b = -10;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shr_r(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shr_r(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x12345678;
+  svar16_b = -40;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shr_r(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shr_r(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 1;
+  svar16_b = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shr_r(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shr_r(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 20;
+  svar16_b = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shr_r(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shr_r(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0xFFF;
+  svar16_b = 10;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shr_r(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shr_r(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0xFFF;
+  svar16_b = 64;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shr_r(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shr_r(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x12345678;
+  svar16_b = 10;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shr_r(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shr_r(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+  svar32_a = 0x12345678;
+  svar16_b = 64;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_c = L_shr_r(svar32_a, svar16_b);
+  fprintf(ref_file, "L_shr_r(%#x, %d) = %#x overflow %d carry %d\n", svar32_a, svar16_b, svar32_c, Overflow, Carry);
+
+
+  /* L_abs */
+  /* int32_t L_abs(int32_t x) */
+  svar32_b = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_a = L_abs(svar32_b);
+  fprintf(ref_file, "L_abs(%#x) = %#x overflow %d carry %d\n", svar32_b, svar32_a, Overflow, Carry);
+
+  svar32_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_a = L_abs(svar32_b);
+  fprintf(ref_file, "L_abs(%#x) = %#x overflow %d carry %d\n", svar32_b, svar32_a, Overflow, Carry);
+
+  svar32_b = 0x80000000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_a = L_abs(svar32_b);
+  fprintf(ref_file, "L_abs(%#x) = %#x overflow %d carry %d\n", svar32_b, svar32_a, Overflow, Carry);
+
+
+  /* L_sat */
+  /* int32_t L_sat(int32_t x) */
+  svar32_b = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_a = L_sat(svar32_b);
+  fprintf(ref_file, "L_sat(%#x) = %#x overflow %d carry %d\n", svar32_b, svar32_a, Overflow, Carry);
+
+  svar32_b = -1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_a = L_sat(svar32_b);
+  fprintf(ref_file, "L_sat(%#x) = %#x overflow %d carry %d\n", svar32_b, svar32_a, Overflow, Carry);
+
+  svar32_b = -32768;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_a = L_sat(svar32_b);
+  fprintf(ref_file, "L_sat(%#x) = %#x overflow %d carry %d\n", svar32_b, svar32_a, Overflow, Carry);
+
+  svar32_b = 32768;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar32_a = L_sat(svar32_b);
+  fprintf(ref_file, "L_sat(%#x) = %#x overflow %d carry %d\n", svar32_b, svar32_a, Overflow, Carry);
+
+
+  /* div_s */
+  /* int16_t div_s(int16_t x, int16_t y) */
+  svar16_a = 1;
+  svar16_b = 1;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = div_s(svar16_a, svar16_b);
+  fprintf(ref_file, "div_s(%#x, %#x) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+  svar16_a = 10000;
+  svar16_b = 20000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = div_s(svar16_a, svar16_b);
+  fprintf(ref_file, "div_s(%#x, %#x) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+
+  svar16_a = 10000;
+  svar16_b = 20000;
+  Overflow = init_Overflow;
+  Carry = init_Carry;
+  svar16_c = div_s(svar16_a, svar16_b);
+  fprintf(ref_file, "div_s(%#x, %#x) = %#x overflow %d carry %d\n", svar16_a, svar16_b, svar16_c, Overflow, Carry);
+
+}
+
+void exec_dspfns(void)
+{
+  Overflow = 0;
+
+  exec_dspfns1(0, 0);
+  exec_dspfns1(0, 1);
+  exec_dspfns1(1, 0);
+  exec_dspfns1(1, 1);
+}
diff --git a/ref_integer.c b/ref_integer.c
new file mode 100644
index 0000000..27bb58a
--- /dev/null
+++ b/ref_integer.c
@@ -0,0 +1,290 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__cplusplus)
+#include <cstdio>
+#include <cstdint>
+#else
+#include <stdio.h>
+#if defined(_MSC_VER)
+#include "msstdint.h"
+#else
+#include <stdint.h>
+#endif
+#endif
+
+#ifndef __arm__
+#include "stm-arm.h"
+#include "stm-dspfns.h" /* For Overflow */
+#else
+#include <dspfns.h> /* For Overflow */
+#endif
+
+extern FILE* ref_file;
+
+void exec_integer (void)
+{
+  int i;
+  uint32_t uvar, ures;
+  int32_t svar1, svar2, sres;
+
+  uint8_t clz;
+
+  fprintf(ref_file, "\n\nInteger (non-NEON) intrinsics\n");
+
+  /* __clz */
+  /* uint8_t __clz(uint32_t val); */
+  uvar = 0xFFFFFFFF;
+  for(i=0; i<=32; i++) {
+    clz = __clz(uvar);
+    fprintf(ref_file, "__clz(%#x) = %d\n", (unsigned int)uvar, clz);
+    uvar >>= 1;
+  }
+
+  /* __qadd */
+  /* int32_t __qadd(int32_t val1, int32_t val2); */
+  svar1 = 1;
+  svar2 = 2;
+  Overflow = 0;
+  sres = __qadd(svar1, svar2);
+  fprintf(ref_file, "__qadd(%#x, %#x) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)svar2, (unsigned int)sres, Overflow);
+
+  svar1 = -1;
+  svar2 = -2;
+  Overflow = 0;
+  sres = __qadd(svar1, svar2);
+  fprintf(ref_file, "__qadd(%#x, %#x) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)svar2, (unsigned int)sres, Overflow);
+
+  svar1 = -1;
+  svar2 = 2;
+  Overflow = 0;
+  sres = __qadd(svar1, svar2);
+  fprintf(ref_file, "__qadd(%#x, %#x) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)svar2, (unsigned int)sres, Overflow);
+
+  svar1 = 0x7000;
+  svar2 = 0x7000;
+  Overflow = 0;
+  sres = __qadd(svar1, svar2);
+  fprintf(ref_file, "__qadd(%#x, %#x) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)svar2, (unsigned int)sres, Overflow);
+
+  svar1 = 0x8FFF;
+  svar2 = 0x8FFF;
+  Overflow = 0;
+  sres = __qadd(svar1, svar2);
+  fprintf(ref_file, "__qadd(%#x, %#x) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)svar2, (unsigned int)sres, Overflow);
+
+  svar1 = 0x70000000;
+  svar2 = 0x70000000;
+  Overflow = 0;
+  sres = __qadd(svar1, svar2);
+  fprintf(ref_file, "__qadd(%#x, %#x) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)svar2, (unsigned int)sres, Overflow);
+
+  svar1 = 0x8FFFFFFF;
+  svar2 = 0x8FFFFFFF;
+  Overflow = 0;
+  sres = __qadd(svar1, svar2);
+  fprintf(ref_file, "__qadd(%#x, %#x) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)svar2, (unsigned int)sres, Overflow);
+
+  /* __qdbl */
+  /* int32_t __qdbl(int32_t val); */
+  svar1 = 1;
+  Overflow = 0;
+  sres = __qdbl(svar1);
+  fprintf(ref_file, "__qdbl(%#x) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)sres, Overflow);
+
+  svar1 = 0x70000000;
+  Overflow = 0;
+  sres = __qdbl(svar1);
+  fprintf(ref_file, "__qdbl(%#x) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)sres, Overflow);
+
+  svar1 = 0x8FFFFFFF;
+  Overflow = 0;
+  sres = __qdbl(svar1);
+  fprintf(ref_file, "__qdbl(%#x) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)sres, Overflow);
+
+  svar1 = 0xEFFFFFFF;
+  Overflow = 0;
+  sres = __qdbl(svar1);
+  fprintf(ref_file, "__qdbl(%#x) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)sres, Overflow);
+
+  /* __qsub */
+  /* int32_t __qsub(int32_t val1, int32_t val2); */
+  svar1 = 1;
+  svar2 = 2;
+  Overflow = 0;
+  sres = __qsub(svar1, svar2);
+  fprintf(ref_file, "__qsub(%#x, %#x) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)svar2, (unsigned int)sres, Overflow);
+
+  svar1 = -1;
+  svar2 = -2;
+  Overflow = 0;
+  sres = __qsub(svar1, svar2);
+  fprintf(ref_file, "__qsub(%#x, %#x) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)svar2, (unsigned int)sres, Overflow);
+
+  svar1 = -1;
+  svar2 = 2;
+  Overflow = 0;
+  sres = __qsub(svar1, svar2);
+  fprintf(ref_file, "__qsub(%#x, %#x) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)svar2, (unsigned int)sres, Overflow);
+
+  svar1 = 0x7000;
+  svar2 = 0xFFFF9000;
+  Overflow = 0;
+  sres = __qsub(svar1, svar2);
+  fprintf(ref_file, "__qsub(%#x, %#x) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)svar2, (unsigned int)sres, Overflow);
+
+  svar1 = 0x8FFF;
+  svar2 = 0xFFFF7001;
+  Overflow = 0;
+  sres = __qsub(svar1, svar2);
+  fprintf(ref_file, "__qsub(%#x, %#x) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)svar2, (unsigned int)sres, Overflow);
+
+  svar1 = 0x70000000;
+  svar2 = 0x90000000;
+  Overflow = 0;
+  sres = __qsub(svar1, svar2);
+  fprintf(ref_file, "__qsub(%#x, %#x) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)svar2, (unsigned int)sres, Overflow);
+
+  svar1 = 0x8FFFFFFF;
+  svar2 = 0x70000001;
+  Overflow = 0;
+  sres = __qsub(svar1, svar2);
+  fprintf(ref_file, "__qsub(%#x, %#x) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)svar2, (unsigned int)sres, Overflow);
+
+  svar1 = 0;
+  svar2 = 0x80000000;
+  Overflow = 0;
+  sres = __qsub(svar1, svar2);
+  fprintf(ref_file, "__qsub(%#x, %#x) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)svar2, (unsigned int)sres, Overflow);
+
+  /* __rbit */
+  /* uint32_t __rbit(uint32_t val); */
+  uvar = 0x12345678;
+  ures = __rbit(uvar);
+  fprintf(ref_file, "__rbit(%#x) = %#x\n",
+          (unsigned int)uvar, (unsigned int)ures);
+
+  /* __rev */
+  /* uint32_t __rev(uint32_t val); */
+  uvar = 0x12345678;
+  ures = __rev(uvar);
+  fprintf(ref_file, "__rev(%#x) = %#x\n",
+          (unsigned int)uvar, (unsigned int)ures);
+
+  /* __ssat */
+  /* int32_t __ssat(int32_t val, uint32_t sat); */
+  svar1 = 0x12345678;
+  Overflow = 0;
+  sres = __ssat(svar1, 30);
+  fprintf(ref_file, "__ssat(%#x, 30) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)sres, Overflow);
+
+  svar1 = 0x12345678;
+  Overflow = 0;
+  sres = __ssat(svar1, 19);
+  fprintf(ref_file, "__ssat(%#x, 19) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)sres, Overflow);
+
+  svar1 = 0x87654321;
+  Overflow = 0;
+  sres = __ssat(svar1, 29);
+  fprintf(ref_file, "__ssat(%#x, 29) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)sres, Overflow);
+
+  svar1 = 0x87654321;
+  Overflow = 0;
+  sres = __ssat(svar1, 12);
+  fprintf(ref_file, "__ssat(%#x, 12) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)sres, Overflow);
+
+  svar1 = 0x87654321;
+  Overflow = 0;
+  sres = __ssat(svar1, 32);
+  fprintf(ref_file, "__ssat(%#x, 32) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)sres, Overflow);
+
+  svar1 = 0x87654321;
+  Overflow = 0;
+  sres = __ssat(svar1, 1);
+  fprintf(ref_file, "__ssat(%#x, 1) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)sres, Overflow);
+
+  /* __usat */
+  /* int32_t __usat(uint32_t val, uint32_t sat); */
+  svar1 = 0x12345678;
+  Overflow = 0;
+  sres = __usat(svar1, 30);
+  fprintf(ref_file, "__usat(%#x, 30) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)sres, Overflow);
+
+  svar1 = 0x12345678;
+  Overflow = 0;
+  sres = __usat(svar1, 19);
+  fprintf(ref_file, "__usat(%#x, 19) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)sres, Overflow);
+
+  svar1 = 0x87654321;
+  Overflow = 0;
+  sres = __usat(svar1, 29);
+  fprintf(ref_file, "__usat(%#x, 29) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)sres, Overflow);
+
+  svar1 = 0x87654321;
+  Overflow = 0;
+  sres = __usat(svar1, 12);
+  fprintf(ref_file, "__usat(%#x, 12) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)sres, Overflow);
+
+  svar1 = 0x87654321;
+  Overflow = 0;
+  sres = __usat(svar1, 31);
+  fprintf(ref_file, "__usat(%#x, 31) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)sres, Overflow);
+
+  svar1 = 0x87654321;
+  Overflow = 0;
+  sres = __usat(svar1, 0);
+  fprintf(ref_file, "__usat(%#x, 0) = %#x sat %d\n",
+          (unsigned int)svar1, (unsigned int)sres, Overflow);
+}
diff --git a/ref_v_binary_op.c b/ref_v_binary_op.c
new file mode 100644
index 0000000..bb4a723
--- /dev/null
+++ b/ref_v_binary_op.c
@@ -0,0 +1,88 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+/* Template file for binary operator validation */
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* Basic test: y=OP(x,x), then store the result.  */
+#define TEST_BINARY_OP1(INSN, Q, T1, T2, W, N)				\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    INSN##Q##_##T2##W(VECT_VAR(vector, T1, W, N),			\
+		      VECT_VAR(vector2, T1, W, N));			\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+#define TEST_BINARY_OP(INSN, Q, T1, T2, W, N)				\
+  TEST_BINARY_OP1(INSN, Q, T1, T2, W, N)				\
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement  */
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+  DECL_VARIABLE_ALL_VARIANTS(vector2);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+
+  /* Fill input vector2 with arbitrary values */
+  VDUP(vector2, , int, s, 8, 8, 2);
+  VDUP(vector2, , int, s, 16, 4, -4);
+  VDUP(vector2, , int, s, 32, 2, 3);
+  VDUP(vector2, , int, s, 64, 1, 100);
+  VDUP(vector2, , uint, u, 8, 8, 20);
+  VDUP(vector2, , uint, u, 16, 4, 30);
+  VDUP(vector2, , uint, u, 32, 2, 40);
+  VDUP(vector2, , uint, u, 64, 1, 2);
+  VDUP(vector2, q, int, s, 8, 16, -10);
+  VDUP(vector2, q, int, s, 16, 8, -20);
+  VDUP(vector2, q, int, s, 32, 4, -30);
+  VDUP(vector2, q, int, s, 64, 2, 24);
+  VDUP(vector2, q, uint, u, 8, 16, 12);
+  VDUP(vector2, q, uint, u, 16, 8, 3);
+  VDUP(vector2, q, uint, u, 32, 4, 55);
+  VDUP(vector2, q, uint, u, 64, 2, 3);
+
+  /* Apply a binary operator named INSN_NAME  */
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_BINARY_OP, INSN_NAME);
+
+  dump_results_hex (TEST_MSG);
+
+#ifdef EXTRA_TESTS
+  EXTRA_TESTS();
+#endif
+}
diff --git a/ref_v_binary_sat_op.c b/ref_v_binary_sat_op.c
new file mode 100644
index 0000000..532da16
--- /dev/null
+++ b/ref_v_binary_sat_op.c
@@ -0,0 +1,110 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2012 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+/* Template file for binary saturating operator validation */
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* vector_res = OP(vector1,vector2), then store the result.  */
+
+#define TEST_BINARY_SAT_OP1(INSN, Q, T1, T2, W, N)		\
+  Set_Neon_Cumulative_Sat(0, VECT_VAR(vector_res, T1, W, N));	\
+  VECT_VAR(vector_res, T1, W, N) =				\
+    INSN##Q##_##T2##W(VECT_VAR(vector1, T1, W, N),		\
+		      VECT_VAR(vector2, T1, W, N));		\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),			\
+		    VECT_VAR(vector_res, T1, W, N));		\
+  dump_neon_cumulative_sat(TEST_MSG, xSTR(INSN##Q##_##T2##W),	\
+			   xSTR(T1), W, N)
+
+#define TEST_BINARY_SAT_OP(INSN, Q, T1, T2, W, N)	\
+  TEST_BINARY_SAT_OP1(INSN, Q, T1, T2, W, N)
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_ALL_VARIANTS(vector1);
+  DECL_VARIABLE_ALL_VARIANTS(vector2);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+  clean_results ();
+
+  /* Initialize input "vector1" from "buffer"  */
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector1, buffer);
+
+  /* Choose arbitrary initialization values */
+  VDUP(vector2, , int, s, 8, 8, 0x11);
+  VDUP(vector2, , int, s, 16, 4, 0x22);
+  VDUP(vector2, , int, s, 32, 2, 0x33);
+  VDUP(vector2, , int, s, 64, 1, 0x44);
+  VDUP(vector2, , uint, u, 8, 8, 0x55);
+  VDUP(vector2, , uint, u, 16, 4, 0x66);
+  VDUP(vector2, , uint, u, 32, 2, 0x77);
+  VDUP(vector2, , uint, u, 64, 1, 0x88);
+
+  VDUP(vector2, q, int, s, 8, 16, 0x11);
+  VDUP(vector2, q, int, s, 16, 8, 0x22);
+  VDUP(vector2, q, int, s, 32, 4, 0x33);
+  VDUP(vector2, q, int, s, 64, 2, 0x44);
+  VDUP(vector2, q, uint, u, 8, 16, 0x55);
+  VDUP(vector2, q, uint, u, 16, 8, 0x66);
+  VDUP(vector2, q, uint, u, 32, 4, 0x77);
+  VDUP(vector2, q, uint, u, 64, 2, 0x88);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 8, 8);
+  TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 16, 4);
+  TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 32, 2);
+  TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 64, 1);
+  TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 8, 8);
+  TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 16, 4);
+  TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 32, 2);
+  TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 64, 1);
+
+  TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 8, 16);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 16, 8);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 32, 4);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 64, 2);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 8, 16);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 16, 8);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 32, 4);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 64, 2);
+
+  dump_results_hex (TEST_MSG);
+
+#ifdef EXTRA_TESTS
+  EXTRA_TESTS();
+#endif
+}
diff --git a/ref_v_comp_f_op.c b/ref_v_comp_f_op.c
new file mode 100644
index 0000000..9d07c23
--- /dev/null
+++ b/ref_v_comp_f_op.c
@@ -0,0 +1,89 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  int i;
+
+  /* Basic test: y=vcomp(x,x), then store the result.  */
+#define TEST_VCOMP1(INSN, Q, T1, T2, T3, W, N)				\
+  VECT_VAR(vector_res, T3, W, N) =					\
+    INSN##Q##_##T2##W(VECT_VAR(vector, T1, W, N),			\
+		      VECT_VAR(vector2, T1, W, N));			\
+  vst1##Q##_u##W(VECT_VAR(result, T3, W, N), VECT_VAR(vector_res, T3, W, N))
+
+#define TEST_VCOMP(INSN, Q, T1, T2, T3, W, N)				\
+  TEST_VCOMP1(INSN, Q, T1, T2, T3, W, N)
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE(vector, float, 32, 2);
+  DECL_VARIABLE(vector, float, 32, 4);
+  DECL_VARIABLE(vector2, float, 32, 2);
+  DECL_VARIABLE(vector2, float, 32, 4);
+  DECL_VARIABLE(vector_res, uint, 32, 2);
+  DECL_VARIABLE(vector_res, uint, 32, 4);
+
+  clean_results ();
+
+  VLOAD(vector, buffer, , float, f, 32, 2);
+  VLOAD(vector, buffer, q, float, f, 32, 4);
+
+  /* Choose init value arbitrarily, will be used for vector
+     comparison */
+  VDUP(vector2, , float, f, 32, 2, -16.0f);
+  VDUP(vector2, q, float, f, 32, 4, -14.0f);
+
+  fprintf(ref_file, "\n%s output:\n", TEST_MSG);
+  fprintf(gcc_tests_file, "\n%s output:\n", TEST_MSG);
+  TEST_VCOMP(INSN_NAME, , float, f, uint, 32, 2);
+  DUMP(TEST_MSG, uint, 32, 2, PRIx32);
+
+  TEST_VCOMP(INSN_NAME, q, float, f, uint, 32, 4);
+  DUMP(TEST_MSG, uint, 32, 4, PRIx32);
+
+  VDUP(vector2, , float, f, 32, 2, -10.0f);
+  VDUP(vector2, q, float, f, 32, 4, 10.0f);
+
+  fprintf(ref_file, "\n%s output:\n", TEST_MSG);
+  fprintf(gcc_tests_file, "\n%s output:\n", TEST_MSG);
+  TEST_VCOMP(INSN_NAME, , float, f, uint, 32, 2);
+  DUMP(TEST_MSG, uint, 32, 2, PRIx32);
+
+  TEST_VCOMP(INSN_NAME, q, float, f, uint, 32, 4);
+  DUMP(TEST_MSG, uint, 32, 4, PRIx32);
+}
diff --git a/ref_v_comp_op.c b/ref_v_comp_op.c
new file mode 100644
index 0000000..9ca5038
--- /dev/null
+++ b/ref_v_comp_op.c
@@ -0,0 +1,221 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+#include <math.h>
+
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  int i;
+
+  /* Basic test: y=vcomp(x,x), then store the result.  */
+#define TEST_VCOMP1(INSN, Q, T1, T2, T3, W, N)				\
+  VECT_VAR(vector_res, T3, W, N) =					\
+    INSN##Q##_##T2##W(VECT_VAR(vector, T1, W, N),			\
+		      VECT_VAR(vector2, T1, W, N));			\
+  vst1##Q##_u##W(VECT_VAR(result, T3, W, N), VECT_VAR(vector_res, T3, W, N))
+
+#define TEST_VCOMP(INSN, Q, T1, T2, T3, W, N)				\
+  TEST_VCOMP1(INSN, Q, T1, T2, T3, W, N)
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  /* No need for 64 bits elements */
+  DECL_VARIABLE(vector, int, 8, 8);
+  DECL_VARIABLE(vector, int, 16, 4);
+  DECL_VARIABLE(vector, int, 32, 2);
+  DECL_VARIABLE(vector, uint, 8, 8);
+  DECL_VARIABLE(vector, uint, 16, 4);
+  DECL_VARIABLE(vector, uint, 32, 2);
+  DECL_VARIABLE(vector, float, 32, 2);
+  DECL_VARIABLE(vector, int, 8, 16);
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+  DECL_VARIABLE(vector, uint, 8, 16);
+  DECL_VARIABLE(vector, uint, 16, 8);
+  DECL_VARIABLE(vector, uint, 32, 4);
+  DECL_VARIABLE(vector, float, 32, 4);
+
+  DECL_VARIABLE(vector2, int, 8, 8);
+  DECL_VARIABLE(vector2, int, 16, 4);
+  DECL_VARIABLE(vector2, int, 32, 2);
+  DECL_VARIABLE(vector2, uint, 8, 8);
+  DECL_VARIABLE(vector2, uint, 16, 4);
+  DECL_VARIABLE(vector2, uint, 32, 2);
+  DECL_VARIABLE(vector2, float, 32, 2);
+  DECL_VARIABLE(vector2, int, 8, 16);
+  DECL_VARIABLE(vector2, int, 16, 8);
+  DECL_VARIABLE(vector2, int, 32, 4);
+  DECL_VARIABLE(vector2, uint, 8, 16);
+  DECL_VARIABLE(vector2, uint, 16, 8);
+  DECL_VARIABLE(vector2, uint, 32, 4);
+  DECL_VARIABLE(vector2, float, 32, 4);
+
+  DECL_VARIABLE(vector_res, uint, 8, 8);
+  DECL_VARIABLE(vector_res, uint, 16, 4);
+  DECL_VARIABLE(vector_res, uint, 32, 2);
+  DECL_VARIABLE(vector_res, uint, 8, 16);
+  DECL_VARIABLE(vector_res, uint, 16, 8);
+  DECL_VARIABLE(vector_res, uint, 32, 4);
+
+  clean_results ();
+
+  /* There is no 64 bits variant, we can't use the generic initializer  */
+  VLOAD(vector, buffer, , int, s, 8, 8);
+  VLOAD(vector, buffer, , int, s, 16, 4);
+  VLOAD(vector, buffer, , int, s, 32, 2);
+  VLOAD(vector, buffer, , uint, u, 8, 8);
+  VLOAD(vector, buffer, , uint, u, 16, 4);
+  VLOAD(vector, buffer, , uint, u, 32, 2);
+  VLOAD(vector, buffer, , float, f, 32, 2);
+
+  VLOAD(vector, buffer, q, int, s, 8, 16);
+  VLOAD(vector, buffer, q, int, s, 16, 8);
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+  VLOAD(vector, buffer, q, uint, u, 8, 16);
+  VLOAD(vector, buffer, q, uint, u, 16, 8);
+  VLOAD(vector, buffer, q, uint, u, 32, 4);
+  VLOAD(vector, buffer, q, float, f, 32, 4);
+
+  /* Choose init value arbitrarily, will be used for vector
+     comparison */
+  VDUP(vector2, , int, s, 8, 8, -10);
+  VDUP(vector2, , int, s, 16, 4, -14);
+  VDUP(vector2, , int, s, 32, 2, -16);
+  VDUP(vector2, , uint, u, 8, 8, 0xF3);
+  VDUP(vector2, , uint, u, 16, 4, 0xFFF2);
+  VDUP(vector2, , uint, u, 32, 2, 0xFFFFFFF1);
+  VDUP(vector2, , float, f, 32, 2, -15.0f);
+
+  VDUP(vector2, q, int, s, 8, 16, -4);
+  VDUP(vector2, q, int, s, 16, 8, -10);
+  VDUP(vector2, q, int, s, 32, 4, -14);
+  VDUP(vector2, q, uint, u, 8, 16, 0xF4);
+  VDUP(vector2, q, uint, u, 16, 8, 0xFFF6);
+  VDUP(vector2, q, uint, u, 32, 4, 0xFFFFFFF2);
+  VDUP(vector2, q, float, f, 32, 4, -14.0f);
+
+  /* The same result buffers are used multiple times, so output them
+     before overwriting them  */
+  fprintf(ref_file, "\n%s output:\n", TEST_MSG);
+  fprintf(gcc_tests_file, "\n%s output:\n", TEST_MSG);
+  TEST_VCOMP(INSN_NAME, , int, s, uint, 8, 8);
+  TEST_VCOMP(INSN_NAME, , int, s, uint, 16, 4);
+  TEST_VCOMP(INSN_NAME, , int, s, uint, 32, 2);
+  DUMP(TEST_MSG, uint, 8, 8, PRIx8);
+  DUMP(TEST_MSG, uint, 16, 4, PRIx16);
+  DUMP(TEST_MSG, uint, 32, 2, PRIx32);
+
+  TEST_VCOMP(INSN_NAME, , uint, u, uint, 8, 8);
+  TEST_VCOMP(INSN_NAME, , uint, u, uint, 16, 4);
+  TEST_VCOMP(INSN_NAME, , uint, u, uint, 32, 2);
+  DUMP(TEST_MSG, uint, 8, 8, PRIx8);
+  DUMP(TEST_MSG, uint, 16, 4, PRIx16);
+  DUMP(TEST_MSG, uint, 32, 2, PRIx32);
+
+  TEST_VCOMP(INSN_NAME, q, int, s, uint, 8, 16);
+  TEST_VCOMP(INSN_NAME, q, int, s, uint, 16, 8);
+  TEST_VCOMP(INSN_NAME, q, int, s, uint, 32, 4);
+  DUMP(TEST_MSG, uint, 8, 16, PRIx8);
+  DUMP(TEST_MSG, uint, 16, 8, PRIx16);
+  DUMP(TEST_MSG, uint, 32, 4, PRIx32);
+
+  TEST_VCOMP(INSN_NAME, q, uint, u, uint, 8, 16);
+  TEST_VCOMP(INSN_NAME, q, uint, u, uint, 16, 8);
+  TEST_VCOMP(INSN_NAME, q, uint, u, uint, 32, 4);
+  DUMP(TEST_MSG, uint, 8, 16, PRIx8);
+  DUMP(TEST_MSG, uint, 16, 8, PRIx16);
+  DUMP(TEST_MSG, uint, 32, 4, PRIx32);
+
+  TEST_VCOMP(INSN_NAME, , float, f, uint, 32, 2);
+  DUMP(TEST_MSG, uint, 32, 2, PRIx32);
+
+  TEST_VCOMP(INSN_NAME, q, float, f, uint, 32, 4);
+  DUMP(TEST_MSG, uint, 32, 4, PRIx32);
+
+  /* Extra tests to have 100% coverage on all the variants */
+  VDUP(vector2, , uint, u, 32, 2, 0xFFFFFFF0);
+  TEST_VCOMP(INSN_NAME, , uint, u, uint, 32, 2);
+  DUMP(TEST_MSG, uint, 32, 2, PRIx32);
+
+  VDUP(vector2, , int, s, 32, 2, -15);
+  TEST_VCOMP(INSN_NAME, , int, s, uint, 32, 2);
+  DUMP(TEST_MSG, uint, 32, 2, PRIx32);
+
+  VDUP(vector2, , float, f, 32, 2, -16.0f);
+  TEST_VCOMP(INSN_NAME, , float, f, uint, 32, 2);
+  DUMP(TEST_MSG, uint, 32, 2, PRIx32);
+
+
+  /* Extra FP tests with special values (NaN, ....) */
+  VDUP(vector, , float, f, 32, 2, 1.0);
+  VDUP(vector2, , float, f, 32, 2, NAN);
+  TEST_VCOMP(INSN_NAME, , float, f, uint, 32, 2);
+  DUMP(TEST_MSG " FP special (NaN)", uint, 32, 2, PRIx32);
+
+  VDUP(vector, , float, f, 32, 2, 1.0);
+  VDUP(vector2, , float, f, 32, 2, -NAN);
+  TEST_VCOMP(INSN_NAME, , float, f, uint, 32, 2);
+  DUMP(TEST_MSG " FP special (-NaN)", uint, 32, 2, PRIx32);
+
+  VDUP(vector, , float, f, 32, 2, NAN);
+  VDUP(vector2, , float, f, 32, 2, 1.0);
+  TEST_VCOMP(INSN_NAME, , float, f, uint, 32, 2);
+  DUMP(TEST_MSG " FP special (NaN)", uint, 32, 2, PRIx32);
+
+  VDUP(vector, , float, f, 32, 2, 1.0);
+  VDUP(vector2, , float, f, 32, 2, HUGE_VALF);
+  TEST_VCOMP(INSN_NAME, , float, f, uint, 32, 2);
+  DUMP(TEST_MSG " FP special (inf)", uint, 32, 2, PRIx32);
+
+  VDUP(vector, , float, f, 32, 2, 1.0);
+  VDUP(vector2, , float, f, 32, 2, -HUGE_VALF);
+  TEST_VCOMP(INSN_NAME, , float, f, uint, 32, 2);
+  DUMP(TEST_MSG " FP special (-inf)", uint, 32, 2, PRIx32);
+
+  VDUP(vector, , float, f, 32, 2, HUGE_VALF);
+  VDUP(vector2, , float, f, 32, 2, 1.0);
+  TEST_VCOMP(INSN_NAME, , float, f, uint, 32, 2);
+  DUMP(TEST_MSG " FP special (inf)", uint, 32, 2, PRIx32);
+
+  VDUP(vector, , float, f, 32, 2, -0.0);
+  VDUP(vector2, , float, f, 32, 2, 0.0);
+  TEST_VCOMP(INSN_NAME, , float, f, uint, 32, 2);
+  DUMP(TEST_MSG " FP special (-0.0)", uint, 32, 2, PRIx32);
+
+#ifdef EXTRA_TESTS
+  EXTRA_TESTS();
+#endif
+}
diff --git a/ref_v_unary_op.c b/ref_v_unary_op.c
new file mode 100644
index 0000000..18a4450
--- /dev/null
+++ b/ref_v_unary_op.c
@@ -0,0 +1,91 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+/* Template file for unary operator validation */
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* Basic test: y=OP(x), then store the result.  */
+#define TEST_UNARY_OP1(INSN, Q, T1, T2, W, N)				\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    INSN##Q##_##T2##W(VECT_VAR(vector, T1, W, N));			\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+#define TEST_UNARY_OP(INSN, Q, T1, T2, W, N)				\
+  TEST_UNARY_OP1(INSN, Q, T1, T2, W, N)					\
+
+    /* With ARM RVCT, we need to declare variables before any executable
+       statement  */
+
+  /* No need for 64 bits variants */
+  DECL_VARIABLE(vector, int, 8, 8);
+  DECL_VARIABLE(vector, int, 16, 4);
+  DECL_VARIABLE(vector, int, 32, 2);
+  DECL_VARIABLE(vector, int, 8, 16);
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+
+  DECL_VARIABLE(vector_res, int, 8, 8);
+  DECL_VARIABLE(vector_res, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 2);
+  DECL_VARIABLE(vector_res, int, 8, 16);
+  DECL_VARIABLE(vector_res, int, 16, 8);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  VLOAD(vector, buffer, , int, s, 8, 8);
+  VLOAD(vector, buffer, , int, s, 16, 4);
+  VLOAD(vector, buffer, , int, s, 32, 2);
+  VLOAD(vector, buffer, q, int, s, 8, 16);
+  VLOAD(vector, buffer, q, int, s, 16, 8);
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+
+  /* Apply a unary operator named INSN_NAME  */
+  TEST_UNARY_OP(INSN_NAME, , int, s, 8, 8);
+  TEST_UNARY_OP(INSN_NAME, , int, s, 16, 4);
+  TEST_UNARY_OP(INSN_NAME, , int, s, 32, 2);
+  TEST_UNARY_OP(INSN_NAME, q, int, s, 8, 16);
+  TEST_UNARY_OP(INSN_NAME, q, int, s, 16, 8);
+  TEST_UNARY_OP(INSN_NAME, q, int, s, 32, 4);
+
+  dump_results_hex (TEST_MSG);
+
+#ifdef EXTRA_TESTS
+  EXTRA_TESTS();
+#endif
+}
diff --git a/ref_v_unary_sat_op.c b/ref_v_unary_sat_op.c
new file mode 100644
index 0000000..b9fea48
--- /dev/null
+++ b/ref_v_unary_sat_op.c
@@ -0,0 +1,96 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2012 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+/* Template file for unary saturating operator validation */
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* Basic test: y=OP(x), then store the result.  */
+#define TEST_UNARY_SAT_OP1(INSN, Q, T1, T2, W, N)		\
+  Set_Neon_Cumulative_Sat(0, VECT_VAR(vector_res, T1, W, N));	\
+  VECT_VAR(vector_res, T1, W, N) =				\
+    INSN##Q##_##T2##W(VECT_VAR(vector, T1, W, N));		\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),			\
+		    VECT_VAR(vector_res, T1, W, N));		\
+  dump_neon_cumulative_sat(TEST_MSG, xSTR(INSN##Q##_##T2##W),	\
+			   xSTR(T1), W, N)
+
+#define TEST_UNARY_SAT_OP(INSN, Q, T1, T2, W, N)	\
+  TEST_UNARY_SAT_OP1(INSN, Q, T1, T2, W, N)
+
+    /* With ARM RVCT, we need to declare variables before any executable
+       statement  */
+
+  /* No need for 64 bits variants */
+  DECL_VARIABLE(vector, int, 8, 8);
+  DECL_VARIABLE(vector, int, 16, 4);
+  DECL_VARIABLE(vector, int, 32, 2);
+  DECL_VARIABLE(vector, int, 8, 16);
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+
+  DECL_VARIABLE(vector_res, int, 8, 8);
+  DECL_VARIABLE(vector_res, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 2);
+  DECL_VARIABLE(vector_res, int, 8, 16);
+  DECL_VARIABLE(vector_res, int, 16, 8);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  VLOAD(vector, buffer, , int, s, 8, 8);
+  VLOAD(vector, buffer, , int, s, 16, 4);
+  VLOAD(vector, buffer, , int, s, 32, 2);
+  VLOAD(vector, buffer, q, int, s, 8, 16);
+  VLOAD(vector, buffer, q, int, s, 16, 8);
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+
+  /* Apply a unary operator named INSN_NAME  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_UNARY_SAT_OP(INSN_NAME, , int, s, 8, 8);
+  TEST_UNARY_SAT_OP(INSN_NAME, , int, s, 16, 4);
+  TEST_UNARY_SAT_OP(INSN_NAME, , int, s, 32, 2);
+  TEST_UNARY_SAT_OP(INSN_NAME, q, int, s, 8, 16);
+  TEST_UNARY_SAT_OP(INSN_NAME, q, int, s, 16, 8);
+  TEST_UNARY_SAT_OP(INSN_NAME, q, int, s, 32, 4);
+
+  dump_results_hex (TEST_MSG);
+
+#ifdef EXTRA_TESTS
+  EXTRA_TESTS();
+#endif
+}
diff --git a/ref_vaba.c b/ref_vaba.c
new file mode 100644
index 0000000..5f2ff76
--- /dev/null
+++ b/ref_vaba.c
@@ -0,0 +1,125 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VABA/VABAQ"
+void exec_vaba (void)
+{
+  /* Basic test: v4=vaba(v1,v2,v3), then store the result.  */
+#define TEST_VABA(Q, T1, T2, W, N)					\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vaba##Q##_##T2##W(VECT_VAR(vector1, T1, W, N),			\
+		      VECT_VAR(vector2, T1, W, N),			\
+		      VECT_VAR(vector3, T1, W, N));			\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+#define DECL_VABA_VAR(VAR)			\
+  DECL_VARIABLE(VAR, int, 8, 8);		\
+  DECL_VARIABLE(VAR, int, 16, 4);		\
+  DECL_VARIABLE(VAR, int, 32, 2);		\
+  DECL_VARIABLE(VAR, uint, 8, 8);		\
+  DECL_VARIABLE(VAR, uint, 16, 4);		\
+  DECL_VARIABLE(VAR, uint, 32, 2);		\
+  DECL_VARIABLE(VAR, int, 8, 16);		\
+  DECL_VARIABLE(VAR, int, 16, 8);		\
+  DECL_VARIABLE(VAR, int, 32, 4);		\
+  DECL_VARIABLE(VAR, uint, 8, 16);		\
+  DECL_VARIABLE(VAR, uint, 16, 8);		\
+  DECL_VARIABLE(VAR, uint, 32, 4)
+
+  DECL_VABA_VAR(vector1);
+  DECL_VABA_VAR(vector2);
+  DECL_VABA_VAR(vector3);
+  DECL_VABA_VAR(vector_res);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  VLOAD(vector1, buffer, , int, s, 8, 8);
+  VLOAD(vector1, buffer, , int, s, 16, 4);
+  VLOAD(vector1, buffer, , int, s, 32, 2);
+  VLOAD(vector1, buffer, , uint, u, 8, 8);
+  VLOAD(vector1, buffer, , uint, u, 16, 4);
+  VLOAD(vector1, buffer, , uint, u, 32, 2);
+  VLOAD(vector1, buffer, q, int, s, 8, 16);
+  VLOAD(vector1, buffer, q, int, s, 16, 8);
+  VLOAD(vector1, buffer, q, int, s, 32, 4);
+  VLOAD(vector1, buffer, q, uint, u, 8, 16);
+  VLOAD(vector1, buffer, q, uint, u, 16, 8);
+  VLOAD(vector1, buffer, q, uint, u, 32, 4);
+
+
+  /* Choose init value arbitrarily */
+  VDUP(vector2, , int, s, 8, 8, 1);
+  VDUP(vector2, , int, s, 16, 4, -13);
+  VDUP(vector2, , int, s, 32, 2, 8);
+  VDUP(vector2, , uint, u, 8, 8, 1);
+  VDUP(vector2, , uint, u, 16, 4, 13);
+  VDUP(vector2, , uint, u, 32, 2, 8);
+  VDUP(vector2, q, int, s, 8, 16, 10);
+  VDUP(vector2, q, int, s, 16, 8, -12);
+  VDUP(vector2, q, int, s, 32, 4, 32);
+  VDUP(vector2, q, uint, u, 8, 16, 10);
+  VDUP(vector2, q, uint, u, 16, 8, 12);
+  VDUP(vector2, q, uint, u, 32, 4, 32);
+
+  /* Choose init value arbitrarily */
+  VDUP(vector3, , int, s, 8, 8, -5);
+  VDUP(vector3, , int, s, 16, 4, 25);
+  VDUP(vector3, , int, s, 32, 2, -40);
+  VDUP(vector3, , uint, u, 8, 8, 100);
+  VDUP(vector3, , uint, u, 16, 4, 2340);
+  VDUP(vector3, , uint, u, 32, 2, 0xffffffff);
+  VDUP(vector3, q, int, s, 8, 16, -100);
+  VDUP(vector3, q, int, s, 16, 8, -3000);
+  VDUP(vector3, q, int, s, 32, 4, 10000);
+  VDUP(vector3, q, uint, u, 8, 16, 2);
+  VDUP(vector3, q, uint, u, 16, 8, 3);
+  VDUP(vector3, q, uint, u, 32, 4, 4);
+
+  TEST_VABA(, int, s, 8, 8);
+  TEST_VABA(, int, s, 16, 4);
+  TEST_VABA(, int, s, 32, 2);
+  TEST_VABA(, uint, u, 8, 8);
+  TEST_VABA(, uint, u, 16, 4);
+  TEST_VABA(, uint, u, 32, 2);
+  TEST_VABA(q, int, s, 8, 16);
+  TEST_VABA(q, int, s, 16, 8);
+  TEST_VABA(q, int, s, 32, 4);
+  TEST_VABA(q, uint, u, 8, 16);
+  TEST_VABA(q, uint, u, 16, 8);
+  TEST_VABA(q, uint, u, 32, 4);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vabal.c b/ref_vabal.c
new file mode 100644
index 0000000..e9ec975
--- /dev/null
+++ b/ref_vabal.c
@@ -0,0 +1,128 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VABAL"
+void exec_vabal (void)
+{
+  /* Basic test: v4=vabal(v1,v2,v3), then store the result.  */
+#define TEST_VABAL(T1, T2, W, W2, N)					\
+  VECT_VAR(vector_res, T1, W2, N) =					\
+    vabal_##T2##W(VECT_VAR(vector1, T1, W2, N),				\
+		  VECT_VAR(vector2, T1, W, N),				\
+		  VECT_VAR(vector3, T1, W, N));				\
+  vst1q_##T2##W2(VECT_VAR(result, T1, W2, N), VECT_VAR(vector_res, T1, W2, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+#define DECL_VABAL_VAR_LONG(VAR)		\
+  DECL_VARIABLE(VAR, int, 16, 8);		\
+  DECL_VARIABLE(VAR, int, 32, 4);		\
+  DECL_VARIABLE(VAR, int, 64, 2);		\
+  DECL_VARIABLE(VAR, uint, 16, 8);		\
+  DECL_VARIABLE(VAR, uint, 32, 4);		\
+  DECL_VARIABLE(VAR, uint, 64, 2)
+
+#define DECL_VABAL_VAR_SHORT(VAR)		\
+  DECL_VARIABLE(VAR, int, 8, 8);		\
+  DECL_VARIABLE(VAR, int, 16, 4);		\
+  DECL_VARIABLE(VAR, int, 32, 2);		\
+  DECL_VARIABLE(VAR, uint, 8, 8);		\
+  DECL_VARIABLE(VAR, uint, 16, 4);		\
+  DECL_VARIABLE(VAR, uint, 32, 2)
+
+  DECL_VABAL_VAR_LONG(vector1);
+  DECL_VABAL_VAR_SHORT(vector2);
+  DECL_VABAL_VAR_SHORT(vector3);
+  DECL_VABAL_VAR_LONG(vector_res);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  VLOAD(vector1, buffer, q, int, s, 16, 8);
+  VLOAD(vector1, buffer, q, int, s, 32, 4);
+  VLOAD(vector1, buffer, q, int, s, 64, 2);
+  VLOAD(vector1, buffer, q, uint, u, 16, 8);
+  VLOAD(vector1, buffer, q, uint, u, 32, 4);
+  VLOAD(vector1, buffer, q, uint, u, 64, 2);
+
+
+  /* Choose init value arbitrarily */
+  VDUP(vector2, , int, s, 8, 8, 1);
+  VDUP(vector2, , int, s, 16, 4, -13);
+  VDUP(vector2, , int, s, 32, 2, 8);
+  VDUP(vector2, , uint, u, 8, 8, 1);
+  VDUP(vector2, , uint, u, 16, 4, 13);
+  VDUP(vector2, , uint, u, 32, 2, 8);
+
+  /* Choose init value arbitrarily */
+  VDUP(vector3, , int, s, 8, 8, -5);
+  VDUP(vector3, , int, s, 16, 4, 25);
+  VDUP(vector3, , int, s, 32, 2, -40);
+  VDUP(vector3, , uint, u, 8, 8, 100);
+  VDUP(vector3, , uint, u, 16, 4, 2340);
+  VDUP(vector3, , uint, u, 32, 2, 0xffffffff);
+
+  TEST_VABAL(int, s, 8, 16, 8);
+  TEST_VABAL(int, s, 16, 32, 4);
+  TEST_VABAL(int, s, 32, 64, 2);
+  TEST_VABAL(uint, u, 8, 16, 8);
+  TEST_VABAL(uint, u, 16, 32, 4);
+  TEST_VABAL(uint, u, 32, 64, 2);
+
+  dump_results_hex (TEST_MSG);
+
+  /* Use values that could lead to overflow intermediate
+   * calculations.  */
+  VDUP(vector2, , int, s, 8, 8, 0x80);
+  VDUP(vector2, , int, s, 16, 4, 0x8000);
+  VDUP(vector2, , int, s, 32, 2, 0x80000000);
+  VDUP(vector2, , uint, u, 8, 8, 1);
+  VDUP(vector2, , uint, u, 16, 4, 13);
+  VDUP(vector2, , uint, u, 32, 2, 8);
+
+  VDUP(vector3, , int, s, 8, 8, 0x7f);
+  VDUP(vector3, , int, s, 16, 4, 0x7fff);
+  VDUP(vector3, , int, s, 32, 2, 0x7fffffff);
+  VDUP(vector3, , uint, u, 8, 8, 0xff);
+  VDUP(vector3, , uint, u, 16, 4, 0xffff);
+  VDUP(vector3, , uint, u, 32, 2, 0xffffffff);
+
+  TEST_VABAL(int, s, 8, 16, 8);
+  TEST_VABAL(int, s, 16, 32, 4);
+  TEST_VABAL(int, s, 32, 64, 2);
+  TEST_VABAL(uint, u, 8, 16, 8);
+  TEST_VABAL(uint, u, 16, 32, 4);
+  TEST_VABAL(uint, u, 32, 64, 2);
+
+  dump_results_hex2 (TEST_MSG, " test intermediate overflow");
+}
diff --git a/ref_vabd.c b/ref_vabd.c
new file mode 100644
index 0000000..ef843e5
--- /dev/null
+++ b/ref_vabd.c
@@ -0,0 +1,133 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+#include <math.h>
+
+#define TEST_MSG "VABD/VABDQ"
+void exec_vabd (void)
+{
+  int i;
+
+  /* Basic test: v4=vabd(v1,v2), then store the result.  */
+#define TEST_VABD(Q, T1, T2, W, N)					\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vabd##Q##_##T2##W(VECT_VAR(vector1, T1, W, N),			\
+		      VECT_VAR(vector2, T1, W, N));			\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+#define DECL_VABD_VAR(VAR)			\
+  DECL_VARIABLE(VAR, int, 8, 8);		\
+  DECL_VARIABLE(VAR, int, 16, 4);		\
+  DECL_VARIABLE(VAR, int, 32, 2);		\
+  DECL_VARIABLE(VAR, uint, 8, 8);		\
+  DECL_VARIABLE(VAR, uint, 16, 4);		\
+  DECL_VARIABLE(VAR, uint, 32, 2);		\
+  DECL_VARIABLE(VAR, float, 32, 2);		\
+  DECL_VARIABLE(VAR, int, 8, 16);		\
+  DECL_VARIABLE(VAR, int, 16, 8);		\
+  DECL_VARIABLE(VAR, int, 32, 4);		\
+  DECL_VARIABLE(VAR, uint, 8, 16);		\
+  DECL_VARIABLE(VAR, uint, 16, 8);		\
+  DECL_VARIABLE(VAR, uint, 32, 4);		\
+  DECL_VARIABLE(VAR, float, 32, 4)
+
+  DECL_VABD_VAR(vector1);
+  DECL_VABD_VAR(vector2);
+  DECL_VABD_VAR(vector_res);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  VLOAD(vector1, buffer, , int, s, 8, 8);
+  VLOAD(vector1, buffer, , int, s, 16, 4);
+  VLOAD(vector1, buffer, , int, s, 32, 2);
+  VLOAD(vector1, buffer, , uint, u, 8, 8);
+  VLOAD(vector1, buffer, , uint, u, 16, 4);
+  VLOAD(vector1, buffer, , uint, u, 32, 2);
+  VLOAD(vector1, buffer, , float, f, 32, 2);
+  VLOAD(vector1, buffer, q, int, s, 8, 16);
+  VLOAD(vector1, buffer, q, int, s, 16, 8);
+  VLOAD(vector1, buffer, q, int, s, 32, 4);
+  VLOAD(vector1, buffer, q, uint, u, 8, 16);
+  VLOAD(vector1, buffer, q, uint, u, 16, 8);
+  VLOAD(vector1, buffer, q, uint, u, 32, 4);
+  VLOAD(vector1, buffer, q, float, f, 32, 4);
+
+  /* Choose init value arbitrarily */
+  VDUP(vector2, , int, s, 8, 8, 1);
+  VDUP(vector2, , int, s, 16, 4, -13);
+  VDUP(vector2, , int, s, 32, 2, 8);
+  VDUP(vector2, , uint, u, 8, 8, 1);
+  VDUP(vector2, , uint, u, 16, 4, 13);
+  VDUP(vector2, , uint, u, 32, 2, 8);
+  VDUP(vector2, , float, f, 32, 2, 8.3f);
+  VDUP(vector2, q, int, s, 8, 16, 10);
+  VDUP(vector2, q, int, s, 16, 8, -12);
+  VDUP(vector2, q, int, s, 32, 4, 32);
+  VDUP(vector2, q, uint, u, 8, 16, 10);
+  VDUP(vector2, q, uint, u, 16, 8, 12);
+  VDUP(vector2, q, uint, u, 32, 4, 32);
+  VDUP(vector2, q, float, f, 32, 4, 32.12f);
+
+  TEST_VABD(, int, s, 8, 8);
+  TEST_VABD(, int, s, 16, 4);
+  TEST_VABD(, int, s, 32, 2);
+  TEST_VABD(, uint, u, 8, 8);
+  TEST_VABD(, uint, u, 16, 4);
+  TEST_VABD(, uint, u, 32, 2);
+  TEST_VABD(, float, f, 32, 2);
+  TEST_VABD(q, int, s, 8, 16);
+  TEST_VABD(q, int, s, 16, 8);
+  TEST_VABD(q, int, s, 32, 4);
+  TEST_VABD(q, uint, u, 8, 16);
+  TEST_VABD(q, uint, u, 16, 8);
+  TEST_VABD(q, uint, u, 32, 4);
+  TEST_VABD(q, float, f, 32, 4);
+
+  dump_results_hex (TEST_MSG);
+
+
+  /* Extra FP tests with special values (-0.0, ....) */
+  VDUP(vector1, q, float, f, 32, 4, -0.0f);
+  VDUP(vector2, q, float, f, 32, 4, 0.0);
+  TEST_VABD(q, float, f, 32, 4);
+  DUMP_FP(TEST_MSG " FP special (-0.0)", float, 32, 4, PRIx32);
+
+
+  /* Extra FP tests with special values (-0.0, ....) */
+  VDUP(vector1, q, float, f, 32, 4, 0.0f);
+  VDUP(vector2, q, float, f, 32, 4, -0.0);
+  TEST_VABD(q, float, f, 32, 4);
+  DUMP_FP(TEST_MSG " FP special (-0.0)", float, 32, 4, PRIx32);
+}
diff --git a/ref_vabdl.c b/ref_vabdl.c
new file mode 100644
index 0000000..fec375e
--- /dev/null
+++ b/ref_vabdl.c
@@ -0,0 +1,93 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VABDL"
+void exec_vabdl (void)
+{
+  /* Basic test: v4=vabdl(v1,v2), then store the result.  */
+#define TEST_VABDL(T1, T2, W, W2, N)					\
+  VECT_VAR(vector_res, T1, W2, N) =					\
+    vabdl_##T2##W(VECT_VAR(vector1, T1, W, N),				\
+		  VECT_VAR(vector2, T1, W, N));				\
+  vst1q_##T2##W2(VECT_VAR(result, T1, W2, N), VECT_VAR(vector_res, T1, W2, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+#define DECL_VABDL_VAR_LONG(VAR)		\
+  DECL_VARIABLE(VAR, int, 16, 8);		\
+  DECL_VARIABLE(VAR, int, 32, 4);		\
+  DECL_VARIABLE(VAR, int, 64, 2);		\
+  DECL_VARIABLE(VAR, uint, 16, 8);		\
+  DECL_VARIABLE(VAR, uint, 32, 4);		\
+  DECL_VARIABLE(VAR, uint, 64, 2)
+
+#define DECL_VABDL_VAR_SHORT(VAR)		\
+  DECL_VARIABLE(VAR, int, 8, 8);		\
+  DECL_VARIABLE(VAR, int, 16, 4);		\
+  DECL_VARIABLE(VAR, int, 32, 2);		\
+  DECL_VARIABLE(VAR, uint, 8, 8);		\
+  DECL_VARIABLE(VAR, uint, 16, 4);		\
+  DECL_VARIABLE(VAR, uint, 32, 2)
+
+  DECL_VABDL_VAR_SHORT(vector1);
+  DECL_VABDL_VAR_SHORT(vector2);
+  DECL_VABDL_VAR_LONG(vector_res);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  VLOAD(vector1, buffer, , int, s, 8, 8);
+  VLOAD(vector1, buffer, , int, s, 16, 4);
+  VLOAD(vector1, buffer, , int, s, 32, 2);
+  VLOAD(vector1, buffer, , uint, u, 8, 8);
+  VLOAD(vector1, buffer, , uint, u, 16, 4);
+  VLOAD(vector1, buffer, , uint, u, 32, 2);
+
+
+  /* Choose init value arbitrarily */
+  VDUP(vector2, , int, s, 8, 8, 1);
+  VDUP(vector2, , int, s, 16, 4, -13);
+  VDUP(vector2, , int, s, 32, 2, 8);
+  VDUP(vector2, , uint, u, 8, 8, 1);
+  VDUP(vector2, , uint, u, 16, 4, 13);
+  VDUP(vector2, , uint, u, 32, 2, 8);
+
+  TEST_VABDL(int, s, 8, 16, 8);
+  TEST_VABDL(int, s, 16, 32, 4);
+  TEST_VABDL(int, s, 32, 64, 2);
+  TEST_VABDL(uint, u, 8, 16, 8);
+  TEST_VABDL(uint, u, 16, 32, 4);
+  TEST_VABDL(uint, u, 32, 64, 2);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vabs.c b/ref_vabs.c
new file mode 100644
index 0000000..b191391
--- /dev/null
+++ b/ref_vabs.c
@@ -0,0 +1,54 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vabs
+#define TEST_MSG "VABS/VABSQ"
+
+/* Extra tests for functions requiring floating-point types */
+void exec_vabs_f32(void);
+#define EXTRA_TESTS exec_vabs_f32
+
+#include "ref_v_unary_op.c"
+
+void exec_vabs_f32(void)
+{
+  int i;
+
+  DECL_VARIABLE(vector, float, 32, 2);
+  DECL_VARIABLE(vector, float, 32, 4);
+
+  DECL_VARIABLE(vector_res, float, 32, 2);
+  DECL_VARIABLE(vector_res, float, 32, 4);
+
+  VDUP(vector, , float, f, 32, 2, -2.3f);
+  VDUP(vector, q, float, f, 32, 4, 3.4f);
+
+  TEST_UNARY_OP(INSN_NAME, , float, f, 32, 2);
+  TEST_UNARY_OP(INSN_NAME, q, float, f, 32, 4);
+
+  fprintf(ref_file, "\nfloat32:\n");
+  DUMP_FP(TEST_MSG, float, 32, 2, PRIx32);
+  DUMP_FP(TEST_MSG, float, 32, 4, PRIx32);
+}
diff --git a/ref_vadd.c b/ref_vadd.c
new file mode 100644
index 0000000..918c70f
--- /dev/null
+++ b/ref_vadd.c
@@ -0,0 +1,60 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vadd
+#define TEST_MSG "VADD/VADDQ"
+
+/* Extra tests for functions requiring floating-point types */
+void exec_vadd_f32(void);
+#define EXTRA_TESTS exec_vadd_f32
+
+#include "ref_v_binary_op.c"
+
+void exec_vadd_f32(void)
+{
+  int i;
+
+  DECL_VARIABLE(vector, float, 32, 2);
+  DECL_VARIABLE(vector, float, 32, 4);
+
+  DECL_VARIABLE(vector2, float, 32, 2);
+  DECL_VARIABLE(vector2, float, 32, 4);
+
+  DECL_VARIABLE(vector_res, float, 32, 2);
+  DECL_VARIABLE(vector_res, float, 32, 4);
+
+  VDUP(vector, , float, f, 32, 2, 2.3f);
+  VDUP(vector, q, float, f, 32, 4, 3.4f);
+
+  VDUP(vector2, , float, f, 32, 2, 4.5f);
+  VDUP(vector2, q, float, f, 32, 4, 5.6f);
+
+  TEST_BINARY_OP(INSN_NAME, , float, f, 32, 2);
+  TEST_BINARY_OP(INSN_NAME, q, float, f, 32, 4);
+
+  fprintf(ref_file, "\nfloat32:\n");
+  DUMP_FP(TEST_MSG, float, 32, 2, PRIx32);
+  DUMP_FP(TEST_MSG, float, 32, 4, PRIx32);
+}
diff --git a/ref_vaddhn.c b/ref_vaddhn.c
new file mode 100644
index 0000000..39c238b
--- /dev/null
+++ b/ref_vaddhn.c
@@ -0,0 +1,94 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#if defined(__cplusplus)
+#include <cstdint>
+#else
+#if defined(_MSC_VER)
+#include "msstdint.h"
+#else
+#include <stdint.h>
+#endif
+#endif
+
+#ifndef INSN_NAME
+#define INSN_NAME vaddhn
+#define TEST_MSG "VADDHN"
+#endif
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* Basic test: vec64=vaddhn(vec128_a, vec128_b), then store the result.  */
+#define TEST_VADDHN1(INSN, T1, T2, W, W2, N)				\
+  VECT_VAR(vector64, T1, W2, N) = INSN##_##T2##W(VECT_VAR(vector1, T1, W, N), \
+						 VECT_VAR(vector2, T1, W, N)); \
+  vst1_##T2##W2(VECT_VAR(result, T1, W2, N), VECT_VAR(vector64, T1, W2, N))
+
+#define TEST_VADDHN(INSN, T1, T2, W, W2, N)				\
+  TEST_VADDHN1(INSN, T1, T2, W, W2, N)
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_64BITS_VARIANTS(vector64);
+  DECL_VARIABLE_128BITS_VARIANTS(vector1);
+  DECL_VARIABLE_128BITS_VARIANTS(vector2);
+
+  clean_results ();
+
+  /* Fill input vector1 and vector2 with arbitrary values */
+  VDUP(vector1, q, int, s, 16, 8, 50*(UINT8_MAX+1));
+  VDUP(vector1, q, int, s, 32, 4, 50*(UINT16_MAX+1));
+  VDUP(vector1, q, int, s, 64, 2, 24*((uint64_t)UINT32_MAX+1));
+  VDUP(vector1, q, uint, u, 16, 8, 3*(UINT8_MAX+1));
+  VDUP(vector1, q, uint, u, 32, 4, 55*(UINT16_MAX+1));
+  VDUP(vector1, q, uint, u, 64, 2, 3*((uint64_t)UINT32_MAX+1));
+
+  VDUP(vector2, q, int, s, 16, 8, (uint16_t)UINT8_MAX);
+  VDUP(vector2, q, int, s, 32, 4, (uint32_t)UINT16_MAX);
+  VDUP(vector2, q, int, s, 64, 2, (uint64_t)UINT32_MAX);
+  VDUP(vector2, q, uint, u, 16, 8, (uint16_t)UINT8_MAX);
+  VDUP(vector2, q, uint, u, 32, 4, (uint32_t)UINT16_MAX);
+  VDUP(vector2, q, uint, u, 64, 2, (uint64_t)UINT32_MAX);
+
+  TEST_VADDHN(INSN_NAME, int, s, 16, 8, 8);
+  TEST_VADDHN(INSN_NAME, int, s, 32, 16, 4);
+  TEST_VADDHN(INSN_NAME, int, s, 64, 32, 2);
+  TEST_VADDHN(INSN_NAME, uint, u, 16, 8, 8);
+  TEST_VADDHN(INSN_NAME, uint, u, 32, 16, 4);
+  TEST_VADDHN(INSN_NAME, uint, u, 64, 32, 2);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vaddl.c b/ref_vaddl.c
new file mode 100644
index 0000000..0856433
--- /dev/null
+++ b/ref_vaddl.c
@@ -0,0 +1,104 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#ifndef INSN_NAME
+#define INSN_NAME vaddl
+#define TEST_MSG "VADDL"
+#endif
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* Basic test: y=vaddl(x,x), then store the result.  */
+#define TEST_VADDL1(INSN, T1, T2, W, W2, N)				\
+  VECT_VAR(vector_res, T1, W2, N) =					\
+    INSN##_##T2##W(VECT_VAR(vector, T1, W, N),				\
+		   VECT_VAR(vector2, T1, W, N));			\
+  vst1q_##T2##W2(VECT_VAR(result, T1, W2, N), VECT_VAR(vector_res, T1, W2, N))
+
+#define TEST_VADDL(INSN, T1, T2, W, W2, N)	\
+  TEST_VADDL1(INSN, T1, T2, W, W2, N)
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE(vector, int, 8, 8);
+  DECL_VARIABLE(vector, int, 16, 4);
+  DECL_VARIABLE(vector, int, 32, 2);
+  DECL_VARIABLE(vector, uint, 8, 8);
+  DECL_VARIABLE(vector, uint, 16, 4);
+  DECL_VARIABLE(vector, uint, 32, 2);
+
+  DECL_VARIABLE(vector2, int, 8, 8);
+  DECL_VARIABLE(vector2, int, 16, 4);
+  DECL_VARIABLE(vector2, int, 32, 2);
+  DECL_VARIABLE(vector2, uint, 8, 8);
+  DECL_VARIABLE(vector2, uint, 16, 4);
+  DECL_VARIABLE(vector2, uint, 32, 2);
+
+  DECL_VARIABLE(vector_res, int, 16, 8);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+  DECL_VARIABLE(vector_res, int, 64, 2);
+  DECL_VARIABLE(vector_res, uint, 16, 8);
+  DECL_VARIABLE(vector_res, uint, 32, 4);
+  DECL_VARIABLE(vector_res, uint, 64, 2);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  VLOAD(vector, buffer, , int, s, 8, 8);
+  VLOAD(vector, buffer, , int, s, 16, 4);
+  VLOAD(vector, buffer, , int, s, 32, 2);
+  VLOAD(vector, buffer, , uint, u, 8, 8);
+  VLOAD(vector, buffer, , uint, u, 16, 4);
+  VLOAD(vector, buffer, , uint, u, 32, 2);
+
+  /* Choose init value arbitrarily */
+  VDUP(vector2, , int, s, 8, 8, -13);
+  VDUP(vector2, , int, s, 16, 4, -14);
+  VDUP(vector2, , int, s, 32, 2, -16);
+  VDUP(vector2, , uint, u, 8, 8, 0xf3);
+  VDUP(vector2, , uint, u, 16, 4, 0xfff1);
+  VDUP(vector2, , uint, u, 32, 2, 0xfffffff0);
+
+  TEST_VADDL(INSN_NAME, int, s, 8, 16, 8);
+  TEST_VADDL(INSN_NAME, int, s, 16, 32, 4);
+  TEST_VADDL(INSN_NAME, int, s, 32, 64, 2);
+  TEST_VADDL(INSN_NAME, uint, u, 8, 16, 8);
+  TEST_VADDL(INSN_NAME, uint, u, 16, 32, 4);
+  TEST_VADDL(INSN_NAME, uint, u, 32, 64, 2);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vaddw.c b/ref_vaddw.c
new file mode 100644
index 0000000..638785c
--- /dev/null
+++ b/ref_vaddw.c
@@ -0,0 +1,104 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#ifndef INSN_NAME
+#define INSN_NAME vaddw
+#define TEST_MSG "VADDW"
+#endif
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* Basic test: y=vaddw(x,x), then store the result.  */
+#define TEST_VADDW1(INSN, T1, T2, W, W2, N)				\
+  VECT_VAR(vector_res, T1, W2, N) =					\
+    INSN##_##T2##W(VECT_VAR(vector, T1, W2, N),				\
+		   VECT_VAR(vector2, T1, W, N));			\
+  vst1q_##T2##W2(VECT_VAR(result, T1, W2, N), VECT_VAR(vector_res, T1, W2, N))
+
+#define TEST_VADDW(INSN, T1, T2, W, W2, N)	\
+  TEST_VADDW1(INSN, T1, T2, W, W2, N)
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+  DECL_VARIABLE(vector, int, 64, 2);
+  DECL_VARIABLE(vector, uint, 16, 8);
+  DECL_VARIABLE(vector, uint, 32, 4);
+  DECL_VARIABLE(vector, uint, 64, 2);
+
+  DECL_VARIABLE(vector2, int, 8, 8);
+  DECL_VARIABLE(vector2, int, 16, 4);
+  DECL_VARIABLE(vector2, int, 32, 2);
+  DECL_VARIABLE(vector2, uint, 8, 8);
+  DECL_VARIABLE(vector2, uint, 16, 4);
+  DECL_VARIABLE(vector2, uint, 32, 2);
+
+  DECL_VARIABLE(vector_res, int, 16, 8);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+  DECL_VARIABLE(vector_res, int, 64, 2);
+  DECL_VARIABLE(vector_res, uint, 16, 8);
+  DECL_VARIABLE(vector_res, uint, 32, 4);
+  DECL_VARIABLE(vector_res, uint, 64, 2);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  VLOAD(vector, buffer, q, int, s, 16, 8);
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+  VLOAD(vector, buffer, q, int, s, 64, 2);
+  VLOAD(vector, buffer, q, uint, u, 16, 8);
+  VLOAD(vector, buffer, q, uint, u, 32, 4);
+  VLOAD(vector, buffer, q, uint, u, 64, 2);
+
+  /* Choose init value arbitrarily */
+  VDUP(vector2, , int, s, 8, 8, -13);
+  VDUP(vector2, , int, s, 16, 4, -14);
+  VDUP(vector2, , int, s, 32, 2, -16);
+  VDUP(vector2, , uint, u, 8, 8, 0xf3);
+  VDUP(vector2, , uint, u, 16, 4, 0xfff1);
+  VDUP(vector2, , uint, u, 32, 2, 0xfffffff0);
+
+  TEST_VADDW(INSN_NAME, int, s, 8, 16, 8);
+  TEST_VADDW(INSN_NAME, int, s, 16, 32, 4);
+  TEST_VADDW(INSN_NAME, int, s, 32, 64, 2);
+  TEST_VADDW(INSN_NAME, uint, u, 8, 16, 8);
+  TEST_VADDW(INSN_NAME, uint, u, 16, 32, 4);
+  TEST_VADDW(INSN_NAME, uint, u, 32, 64, 2);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vand.c b/ref_vand.c
new file mode 100644
index 0000000..57e9013
--- /dev/null
+++ b/ref_vand.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vand
+#define TEST_MSG "VAND/VANDQ"
+
+#include "ref_v_binary_op.c"
diff --git a/ref_vbic.c b/ref_vbic.c
new file mode 100644
index 0000000..0d033ac
--- /dev/null
+++ b/ref_vbic.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vbic
+#define TEST_MSG "VBIC/VBICQ"
+
+#include "ref_v_binary_op.c"
diff --git a/ref_vbsl.c b/ref_vbsl.c
new file mode 100644
index 0000000..4ede2d5
--- /dev/null
+++ b/ref_vbsl.c
@@ -0,0 +1,104 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VBSL/VBSLQ"
+void exec_vbsl (void)
+{
+  /* Basic test: y=vbsl(unsigned_vec,x,x), then store the result.  */
+#define TEST_VBSL(T3, Q, T1, T2, W, N)					\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vbsl##Q##_##T2##W(VECT_VAR(vector_first, T3, W, N),			\
+		      VECT_VAR(vector, T1, W, N),			\
+		      VECT_VAR(vector2, T1, W, N));			\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+  DECL_VARIABLE_ALL_VARIANTS(vector2);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+  DECL_VARIABLE_UNSIGNED_VARIANTS(vector_first);
+
+  clean_results ();
+
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+  VLOAD(vector, buffer, , float, f, 32, 2);
+  VLOAD(vector, buffer, q, float, f, 32, 4);
+
+  /* Choose init value arbitrarily, will be used for vector
+     comparison. As we want different values for each type variant, we
+     can't use generic initialization macros.  */
+  VDUP(vector2, , int, s, 8, 8, -10);
+  VDUP(vector2, , int, s, 16, 4, -14);
+  VDUP(vector2, , int, s, 32, 2, -30);
+  VDUP(vector2, , int, s, 64, 1, -33);
+  VDUP(vector2, , uint, u, 8, 8, 0xF3);
+  VDUP(vector2, , uint, u, 16, 4, 0xFFF2);
+  VDUP(vector2, , uint, u, 32, 2, 0xFFFFFFF0);
+  VDUP(vector2, , uint, u, 64, 1, 0xFFFFFFF3);
+  VDUP(vector2, , float, f, 32, 2, -30.3f);
+  VDUP(vector2, , poly, p, 8, 8, 0xF3);
+  VDUP(vector2, , poly, p, 16, 4, 0xFFF2);
+
+  VDUP(vector2, q, int, s, 8, 16, -10);
+  VDUP(vector2, q, int, s, 16, 8, -14);
+  VDUP(vector2, q, int, s, 32, 4, -30);
+  VDUP(vector2, q, int, s, 64, 2, -33);
+  VDUP(vector2, q, uint, u, 8, 16, 0xF3);
+  VDUP(vector2, q, uint, u, 16, 8, 0xFFF2);
+  VDUP(vector2, q, uint, u, 32, 4, 0xFFFFFFF0);
+  VDUP(vector2, q, uint, u, 64, 2, 0xFFFFFFF3);
+  VDUP(vector2, q, poly, p, 8, 16, 0xF3);
+  VDUP(vector2, q, poly, p, 16, 8, 0xFFF2);
+  VDUP(vector2, q, float, f, 32, 4, -30.4f);
+
+  VDUP(vector_first, , uint, u, 8, 8, 0xF4);
+  VDUP(vector_first, , uint, u, 16, 4, 0xFFF6);
+  VDUP(vector_first, , uint, u, 32, 2, 0xFFFFFFF2);
+  VDUP(vector_first, , uint, u, 64, 1, 0xFFFFFFF2);
+  VDUP(vector_first, q, uint, u, 8, 16, 0xF4);
+  VDUP(vector_first, q, uint, u, 16, 8, 0xFFF6);
+  VDUP(vector_first, q, uint, u, 32, 4, 0xFFFFFFF2);
+  VDUP(vector_first, q, uint, u, 64, 2, 0xFFFFFFF2);
+
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VBSL, uint);
+  TEST_VBSL(uint, , poly, p, 8, 8);
+  TEST_VBSL(uint, , poly, p, 16, 4);
+  TEST_VBSL(uint, q, poly, p, 8, 16);
+  TEST_VBSL(uint, q, poly, p, 16, 8);
+  TEST_VBSL(uint, , float, f, 32, 2);
+  TEST_VBSL(uint, q, float, f, 32, 4);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vcage.c b/ref_vcage.c
new file mode 100644
index 0000000..b9919f9
--- /dev/null
+++ b/ref_vcage.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vcage
+#define TEST_MSG "VCAGE/VCAGEQ"
+
+#include "ref_v_comp_f_op.c"
diff --git a/ref_vcagt.c b/ref_vcagt.c
new file mode 100644
index 0000000..edb6fa0
--- /dev/null
+++ b/ref_vcagt.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vcagt
+#define TEST_MSG "VCAGT/VCAGTQ"
+
+#include "ref_v_comp_f_op.c"
diff --git a/ref_vcale.c b/ref_vcale.c
new file mode 100644
index 0000000..b221f79
--- /dev/null
+++ b/ref_vcale.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vcale
+#define TEST_MSG "VCALE/VCALEQ"
+
+#include "ref_v_comp_f_op.c"
diff --git a/ref_vcalt.c b/ref_vcalt.c
new file mode 100644
index 0000000..189a9ae
--- /dev/null
+++ b/ref_vcalt.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vcalt
+#define TEST_MSG "VCALT/VCALTQ"
+
+#include "ref_v_comp_f_op.c"
diff --git a/ref_vceq.c b/ref_vceq.c
new file mode 100644
index 0000000..30d8aba
--- /dev/null
+++ b/ref_vceq.c
@@ -0,0 +1,63 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vceq
+#define TEST_MSG "VCEQ/VCEQQ"
+
+/* Extra tests for _p8 variants, which exist only for vceq */
+void exec_vceq_p8(void);
+#define EXTRA_TESTS exec_vceq_p8
+
+#include "ref_v_comp_op.c"
+
+void exec_vceq_p8(void)
+{
+  int i;  /* Used by DUMP() */
+
+  DECL_VARIABLE(vector, poly, 8, 8);
+  DECL_VARIABLE(vector, poly, 8, 16);
+
+  DECL_VARIABLE(vector2, poly, 8, 8);
+  DECL_VARIABLE(vector2, poly, 8, 16);
+
+  DECL_VARIABLE(vector_res, uint, 8, 8);
+  DECL_VARIABLE(vector_res, uint, 8, 16);
+
+  clean_results ();
+
+  VLOAD(vector, buffer, , poly, p, 8, 8);
+  VLOAD(vector, buffer, q, poly, p, 8, 16);
+
+  VDUP(vector2, , poly, p, 8, 8, 0xF3);
+  VDUP(vector2, q, poly, p, 8, 16, 0xF4);
+
+  fprintf(ref_file, "\n%s output:\n", TEST_MSG " p8");
+  TEST_VCOMP(INSN_NAME, , poly, p, uint, 8, 8);
+  TEST_VCOMP(INSN_NAME, q, poly, p, uint, 8, 16);
+
+  DUMP(TEST_MSG, uint, 8, 8, PRIx8);
+  DUMP(TEST_MSG, uint, 8, 16, PRIx8);
+
+}
diff --git a/ref_vcge.c b/ref_vcge.c
new file mode 100644
index 0000000..9e1fdea
--- /dev/null
+++ b/ref_vcge.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vcge
+#define TEST_MSG "VCGE/VCGEQ"
+
+#include "ref_v_comp_op.c"
diff --git a/ref_vcgt.c b/ref_vcgt.c
new file mode 100644
index 0000000..afd8fe5
--- /dev/null
+++ b/ref_vcgt.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vcgt
+#define TEST_MSG "VCGT/VCGTQ"
+
+#include "ref_v_comp_op.c"
diff --git a/ref_vcle.c b/ref_vcle.c
new file mode 100644
index 0000000..3da8d1a
--- /dev/null
+++ b/ref_vcle.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vcle
+#define TEST_MSG "VCLE/VCLEQ"
+
+#include "ref_v_comp_op.c"
diff --git a/ref_vcls.c b/ref_vcls.c
new file mode 100644
index 0000000..e3efd64
--- /dev/null
+++ b/ref_vcls.c
@@ -0,0 +1,107 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN_NAME vcls
+#define TEST_MSG "VCLS/VCLSQ"
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* Basic test: y=OP(x), then store the result.  */
+#define TEST_UNARY_OP1(INSN, Q, T1, T2, W, N)				\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    INSN##Q##_##T2##W(VECT_VAR(vector, T1, W, N));			\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+#define TEST_UNARY_OP(INSN, Q, T1, T2, W, N)	\
+  TEST_UNARY_OP1(INSN, Q, T1, T2, W, N)		\
+
+    /* With ARM RVCT, we need to declare variables before any executable
+       statement  */
+
+  /* No need for 64 bits variants */
+  DECL_VARIABLE(vector, int, 8, 8);
+  DECL_VARIABLE(vector, int, 16, 4);
+  DECL_VARIABLE(vector, int, 32, 2);
+  DECL_VARIABLE(vector, int, 8, 16);
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+
+  DECL_VARIABLE(vector_res, int, 8, 8);
+  DECL_VARIABLE(vector_res, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 2);
+  DECL_VARIABLE(vector_res, int, 8, 16);
+  DECL_VARIABLE(vector_res, int, 16, 8);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+
+  clean_results ();
+
+  /* Fill input vector with arbitrary values */
+  VDUP(vector, , int, s, 8, 8, 0x1);
+  VDUP(vector, , int, s, 16, 4, 0x1234);
+  VDUP(vector, , int, s, 32, 2, 0x34);
+  VDUP(vector, q, int, s, 8, 16, 0);
+  VDUP(vector, q, int, s, 16, 8, 0x1234);
+  VDUP(vector, q, int, s, 32, 4, 0x678);
+
+  /* Apply a unary operator named INSN_NAME  */
+  TEST_UNARY_OP(INSN_NAME, , int, s, 8, 8);
+  TEST_UNARY_OP(INSN_NAME, , int, s, 16, 4);
+  TEST_UNARY_OP(INSN_NAME, , int, s, 32, 2);
+  TEST_UNARY_OP(INSN_NAME, q, int, s, 8, 16);
+  TEST_UNARY_OP(INSN_NAME, q, int, s, 16, 8);
+  TEST_UNARY_OP(INSN_NAME, q, int, s, 32, 4);
+
+  dump_results_hex2 (TEST_MSG, " (positive input)");
+
+
+  /* Fill input vector with arbitrary values (negative) */
+  VDUP(vector, , int, s, 8, 8, 0xFF);
+  VDUP(vector, , int, s, 16, 4, 0xC234);
+  VDUP(vector, , int, s, 32, 2, 0xDEAD0034);
+  VDUP(vector, q, int, s, 8, 16, 0x80);
+  VDUP(vector, q, int, s, 16, 8, 0xE234);
+  VDUP(vector, q, int, s, 32, 4, 0xBEEF0678);
+
+  /* Apply a unary operator named INSN_NAME  */
+  TEST_UNARY_OP(INSN_NAME, , int, s, 8, 8);
+  TEST_UNARY_OP(INSN_NAME, , int, s, 16, 4);
+  TEST_UNARY_OP(INSN_NAME, , int, s, 32, 2);
+  TEST_UNARY_OP(INSN_NAME, q, int, s, 8, 16);
+  TEST_UNARY_OP(INSN_NAME, q, int, s, 16, 8);
+  TEST_UNARY_OP(INSN_NAME, q, int, s, 32, 4);
+
+  dump_results_hex2 (TEST_MSG, " (negative input)");
+}
diff --git a/ref_vclt.c b/ref_vclt.c
new file mode 100644
index 0000000..ce974d9
--- /dev/null
+++ b/ref_vclt.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vclt
+#define TEST_MSG "VCLT/VCLTQ"
+
+#include "ref_v_comp_op.c"
diff --git a/ref_vclz.c b/ref_vclz.c
new file mode 100644
index 0000000..aaa799f
--- /dev/null
+++ b/ref_vclz.c
@@ -0,0 +1,142 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN_NAME vclz
+#define TEST_MSG "VCLZ/VCLZQ"
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* Basic test: y=OP(x), then store the result.  */
+#define TEST_UNARY_OP1(INSN, Q, T1, T2, W, N)				\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    INSN##Q##_##T2##W(VECT_VAR(vector, T1, W, N));			\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+#define TEST_UNARY_OP(INSN, Q, T1, T2, W, N)	\
+  TEST_UNARY_OP1(INSN, Q, T1, T2, W, N)		\
+
+    /* With ARM RVCT, we need to declare variables before any executable
+       statement  */
+
+  /* No need for 64 bits variants */
+  DECL_VARIABLE(vector, int, 8, 8);
+  DECL_VARIABLE(vector, int, 16, 4);
+  DECL_VARIABLE(vector, int, 32, 2);
+  DECL_VARIABLE(vector, uint, 8, 8);
+  DECL_VARIABLE(vector, uint, 16, 4);
+  DECL_VARIABLE(vector, uint, 32, 2);
+  DECL_VARIABLE(vector, int, 8, 16);
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+  DECL_VARIABLE(vector, uint, 8, 16);
+  DECL_VARIABLE(vector, uint, 16, 8);
+  DECL_VARIABLE(vector, uint, 32, 4);
+
+  DECL_VARIABLE(vector_res, int, 8, 8);
+  DECL_VARIABLE(vector_res, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 2);
+  DECL_VARIABLE(vector_res, uint, 8, 8);
+  DECL_VARIABLE(vector_res, uint, 16, 4);
+  DECL_VARIABLE(vector_res, uint, 32, 2);
+  DECL_VARIABLE(vector_res, int, 8, 16);
+  DECL_VARIABLE(vector_res, int, 16, 8);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+  DECL_VARIABLE(vector_res, uint, 8, 16);
+  DECL_VARIABLE(vector_res, uint, 16, 8);
+  DECL_VARIABLE(vector_res, uint, 32, 4);
+
+  clean_results ();
+
+  /* Fill input vector with arbitrary values */
+  VDUP(vector, , int, s, 8, 8, 0x84);
+  VDUP(vector, , int, s, 16, 4, 0x1234);
+  VDUP(vector, , int, s, 32, 2, 0x5678);
+  VDUP(vector, , uint, u, 8, 8, 0x34);
+  VDUP(vector, , uint, u, 16, 4, 0x8234);
+  VDUP(vector, , uint, u, 32, 2, 0x7654321);
+  VDUP(vector, q, int, s, 8, 16, 0x34);
+  VDUP(vector, q, int, s, 16, 8, 0x1234);
+  VDUP(vector, q, int, s, 32, 4, 0x12345678);
+  VDUP(vector, q, uint, u, 8, 16, 0x13);
+  VDUP(vector, q, uint, u, 16, 8, 0x4);
+  VDUP(vector, q, uint, u, 32, 4, 0x1);
+
+  /* Apply a unary operator named INSN_NAME  */
+  TEST_UNARY_OP(INSN_NAME, , int, s, 8, 8);
+  TEST_UNARY_OP(INSN_NAME, , int, s, 16, 4);
+  TEST_UNARY_OP(INSN_NAME, , int, s, 32, 2);
+  TEST_UNARY_OP(INSN_NAME, , uint, u, 8, 8);
+  TEST_UNARY_OP(INSN_NAME, , uint, u, 16, 4);
+  TEST_UNARY_OP(INSN_NAME, , uint, u, 32, 2);
+  TEST_UNARY_OP(INSN_NAME, q, int, s, 8, 16);
+  TEST_UNARY_OP(INSN_NAME, q, int, s, 16, 8);
+  TEST_UNARY_OP(INSN_NAME, q, int, s, 32, 4);
+  TEST_UNARY_OP(INSN_NAME, q, uint, u, 8, 16);
+  TEST_UNARY_OP(INSN_NAME, q, uint, u, 16, 8);
+  TEST_UNARY_OP(INSN_NAME, q, uint, u, 32, 4);
+
+  dump_results_hex (TEST_MSG);
+
+  /* Test with zero as input.  */
+  VDUP(vector, , int, s, 8, 8, 0);
+  VDUP(vector, , int, s, 16, 4, 0);
+  VDUP(vector, , int, s, 32, 2, 0);
+  VDUP(vector, , uint, u, 8, 8, 0);
+  VDUP(vector, , uint, u, 16, 4, 0);
+  VDUP(vector, , uint, u, 32, 2, 0);
+  VDUP(vector, q, int, s, 8, 16, 0);
+  VDUP(vector, q, int, s, 16, 8, 0);
+  VDUP(vector, q, int, s, 32, 4, 0);
+  VDUP(vector, q, uint, u, 8, 16, 0);
+  VDUP(vector, q, uint, u, 16, 8, 0);
+  VDUP(vector, q, uint, u, 32, 4, 0);
+
+  /* Apply a unary operator named INSN_NAME  */
+  TEST_UNARY_OP(INSN_NAME, , int, s, 8, 8);
+  TEST_UNARY_OP(INSN_NAME, , int, s, 16, 4);
+  TEST_UNARY_OP(INSN_NAME, , int, s, 32, 2);
+  TEST_UNARY_OP(INSN_NAME, , uint, u, 8, 8);
+  TEST_UNARY_OP(INSN_NAME, , uint, u, 16, 4);
+  TEST_UNARY_OP(INSN_NAME, , uint, u, 32, 2);
+  TEST_UNARY_OP(INSN_NAME, q, int, s, 8, 16);
+  TEST_UNARY_OP(INSN_NAME, q, int, s, 16, 8);
+  TEST_UNARY_OP(INSN_NAME, q, int, s, 32, 4);
+  TEST_UNARY_OP(INSN_NAME, q, uint, u, 8, 16);
+  TEST_UNARY_OP(INSN_NAME, q, uint, u, 16, 8);
+  TEST_UNARY_OP(INSN_NAME, q, uint, u, 32, 4);
+
+  dump_results_hex2 (TEST_MSG, " (input=0)");
+}
diff --git a/ref_vcnt.c b/ref_vcnt.c
new file mode 100644
index 0000000..e781760
--- /dev/null
+++ b/ref_vcnt.c
@@ -0,0 +1,88 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN_NAME vcnt
+#define TEST_MSG "VCNT/VCNTQ"
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* Basic test: y=OP(x), then store the result.  */
+#define TEST_UNARY_OP1(INSN, Q, T1, T2, W, N)				\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    INSN##Q##_##T2##W(VECT_VAR(vector, T1, W, N));			\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+#define TEST_UNARY_OP(INSN, Q, T1, T2, W, N)	\
+  TEST_UNARY_OP1(INSN, Q, T1, T2, W, N)		\
+
+    /* With ARM RVCT, we need to declare variables before any executable
+       statement  */
+
+  /* No need for 64 bits variants */
+  DECL_VARIABLE(vector, int, 8, 8);
+  DECL_VARIABLE(vector, uint, 8, 8);
+  DECL_VARIABLE(vector, poly, 8, 8);
+  DECL_VARIABLE(vector, int, 8, 16);
+  DECL_VARIABLE(vector, uint, 8, 16);
+  DECL_VARIABLE(vector, poly, 8, 16);
+
+  DECL_VARIABLE(vector_res, int, 8, 8);
+  DECL_VARIABLE(vector_res, uint, 8, 8);
+  DECL_VARIABLE(vector_res, poly, 8, 8);
+  DECL_VARIABLE(vector_res, int, 8, 16);
+  DECL_VARIABLE(vector_res, uint, 8, 16);
+  DECL_VARIABLE(vector_res, poly, 8, 16);
+
+  clean_results ();
+
+  /* Fill input vector with arbitrary values */
+  VDUP(vector, , int, s, 8, 8, 0xFF);
+  VDUP(vector, , uint, u, 8, 8, 0x35);
+  VDUP(vector, , poly, p, 8, 8, 0x35);
+  VDUP(vector, q, int, s, 8, 16, 0);
+  VDUP(vector, q, uint, u, 8, 16, 0xBD);
+  VDUP(vector, q, poly, p, 8, 16, 0xBD);
+
+  /* Apply a unary operator named INSN_NAME  */
+  TEST_UNARY_OP(INSN_NAME, , int, s, 8, 8);
+  TEST_UNARY_OP(INSN_NAME, , uint, u, 8, 8);
+  TEST_UNARY_OP(INSN_NAME, , poly, p, 8, 8);
+  TEST_UNARY_OP(INSN_NAME, q, int, s, 8, 16);
+  TEST_UNARY_OP(INSN_NAME, q, uint, u, 8, 16);
+  TEST_UNARY_OP(INSN_NAME, q, poly, p, 8, 16);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vcombine.c b/ref_vcombine.c
new file mode 100644
index 0000000..cfe5c1a
--- /dev/null
+++ b/ref_vcombine.c
@@ -0,0 +1,100 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VCOMBINE"
+void exec_vcombine (void)
+{
+  /* Basic test: vec128=vcombine(vec64_a, vec64_b), then store the result.  */
+#define TEST_VCOMBINE(T1, T2, W, N, N2)					\
+  VECT_VAR(vector128, T1, W, N2) =					\
+    vcombine_##T2##W(VECT_VAR(vector64_a, T1, W, N),			\
+		     VECT_VAR(vector64_b, T1, W, N));			\
+  vst1q_##T2##W(VECT_VAR(result, T1, W, N2), VECT_VAR(vector128, T1, W, N2))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_64BITS_VARIANTS(vector64_a);
+  DECL_VARIABLE_64BITS_VARIANTS(vector64_b);
+  DECL_VARIABLE_128BITS_VARIANTS(vector128);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  DECL_VARIABLE(vector64_a, float, 16, 4);
+  DECL_VARIABLE(vector64_b, float, 16, 4);
+  DECL_VARIABLE(vector64_b_init, uint, 16, 4);
+  DECL_VARIABLE(vector128, float, 16, 8);
+#endif
+
+  TEST_MACRO_64BITS_VARIANTS_2_5(VLOAD, vector64_a, buffer);
+  VLOAD(vector64_a, buffer, , float, f, 32, 2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  VLOAD(vector64_a, buffer, , float, f, 16, 4);
+#endif
+
+  VDUP(vector64_b, , int, s, 8, 8, 0x11);
+  VDUP(vector64_b, , int, s, 16, 4, 0x22);
+  VDUP(vector64_b, , int, s, 32, 2, 0x33);
+  VDUP(vector64_b, , int, s, 64, 1, 0x44);
+  VDUP(vector64_b, , uint, u, 8, 8, 0x55);
+  VDUP(vector64_b, , uint, u, 16, 4, 0x66);
+  VDUP(vector64_b, , uint, u, 32, 2, 0x77);
+  VDUP(vector64_b, , uint, u, 64, 1, 0x88);
+  VDUP(vector64_b, , poly, p, 8, 8, 0x55);
+  VDUP(vector64_b, , poly, p, 16, 4, 0x66);
+  VDUP(vector64_b, , float, f, 32, 2, 3.3f);
+
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  /* There is no vdup_n_f16, so we need another initialization
+     method.  */
+  VDUP(vector64_b_init, , uint, u, 16, 4, 0x4b80 /* 15 */);
+  VECT_VAR(vector64_b, float, 16, 4) =
+    vreinterpret_f16_u16(VECT_VAR(vector64_b_init, uint, 16, 4));
+#endif
+
+  clean_results ();
+
+  TEST_VCOMBINE(int, s, 8, 8, 16);
+  TEST_VCOMBINE(int, s, 16, 4, 8);
+  TEST_VCOMBINE(int, s, 32, 2, 4);
+  TEST_VCOMBINE(int, s, 64, 1, 2);
+  TEST_VCOMBINE(uint, u, 8, 8, 16);
+  TEST_VCOMBINE(uint, u, 16, 4, 8);
+  TEST_VCOMBINE(uint, u, 32, 2, 4);
+  TEST_VCOMBINE(uint, u, 64, 1, 2);
+  TEST_VCOMBINE(poly, p, 8, 8, 16);
+  TEST_VCOMBINE(poly, p, 16, 4, 8);
+  TEST_VCOMBINE(float, f, 32, 2, 4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_VCOMBINE(float, f, 16, 4, 8);
+#endif
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vcreate.c b/ref_vcreate.c
new file mode 100644
index 0000000..cfd50d7
--- /dev/null
+++ b/ref_vcreate.c
@@ -0,0 +1,119 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+/* Template file for unary operator validation */
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN_NAME vcreate
+#define TEST_MSG "VCREATE"
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* Basic test: y=vcreate(x), then store the result.  */
+#define TEST_VCREATE(T1, T2, W, N)					\
+  VECT_VAR(vector_res, T1, W, N) = vcreate_##T2##W(VECT_VAR(val, T1, W, N)); \
+  vst1_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+    /* With ARM RVCT, we need to declare variables before any executable
+       statement  */
+
+#define DECL_VAL(VAR, T1, W, N)			\
+  uint64_t VECT_VAR(VAR, T1, W, N)
+
+  DECL_VAL(val, int, 8, 8);
+  DECL_VAL(val, int, 16, 4);
+  DECL_VAL(val, int, 32, 2);
+  DECL_VAL(val, int, 64, 1);
+  DECL_VAL(val, float, 32, 2);
+  DECL_VAL(val, uint, 8, 8);
+  DECL_VAL(val, uint, 16, 4);
+  DECL_VAL(val, uint, 32, 2);
+  DECL_VAL(val, uint, 64, 1);
+  DECL_VAL(val, poly, 8, 8);
+  DECL_VAL(val, poly, 16, 4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  DECL_VAL(val, float, 16, 4);
+#endif
+
+  DECL_VARIABLE(vector_res, int, 8, 8);
+  DECL_VARIABLE(vector_res, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 2);
+  DECL_VARIABLE(vector_res, int, 64, 1);
+  DECL_VARIABLE(vector_res, float, 32, 2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  DECL_VARIABLE(vector_res, float, 16, 4);
+#endif
+  DECL_VARIABLE(vector_res, uint, 8, 8);
+  DECL_VARIABLE(vector_res, uint, 16, 4);
+  DECL_VARIABLE(vector_res, uint, 32, 2);
+  DECL_VARIABLE(vector_res, uint, 64, 1);
+  DECL_VARIABLE(vector_res, poly, 8, 8);
+  DECL_VARIABLE(vector_res, poly, 16, 4);
+
+  clean_results ();
+
+  /* Initialize input values arbitrarily */
+  VECT_VAR(val, int, 8, 8) = 0x123456789abcdef0LL;
+  VECT_VAR(val, int, 16, 4) = 0x123456789abcdef0LL;
+  VECT_VAR(val, int, 32, 2) = 0x123456789abcdef0LL;
+  VECT_VAR(val, int, 64, 1) = 0x123456789abcdef0LL;
+  VECT_VAR(val, float, 32, 2) = 0x123456789abcdef0LL;
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  VECT_VAR(val, float, 16, 4) = 0x123456789abcdef0LL;
+#endif
+  VECT_VAR(val, uint, 8, 8) = 0x123456789abcdef0ULL;
+  VECT_VAR(val, uint, 16, 4) = 0x123456789abcdef0ULL;
+  VECT_VAR(val, uint, 32, 2) = 0x123456789abcdef0ULL;
+  VECT_VAR(val, uint, 64, 1) = 0x123456789abcdef0ULL;
+  VECT_VAR(val, poly, 8, 8) = 0x123456789abcdef0ULL;
+  VECT_VAR(val, poly, 16, 4) = 0x123456789abcdef0ULL;
+
+  TEST_VCREATE(int, s, 8, 8);
+  TEST_VCREATE(int, s, 16, 4);
+  TEST_VCREATE(int, s, 32, 2);
+  TEST_VCREATE(float, f, 32, 2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_VCREATE(float, f, 16, 4);
+#endif
+  TEST_VCREATE(int, s, 64, 1);
+  TEST_VCREATE(uint, u, 8, 8);
+  TEST_VCREATE(uint, u, 16, 4);
+  TEST_VCREATE(uint, u, 32, 2);
+  TEST_VCREATE(uint, u, 64, 1);
+  TEST_VCREATE(poly, p, 8, 8);
+  TEST_VCREATE(poly, p, 16, 4);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vcvt.c b/ref_vcvt.c
new file mode 100644
index 0000000..a22613f
--- /dev/null
+++ b/ref_vcvt.c
@@ -0,0 +1,236 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+#include <math.h>
+
+#define TEST_MSG "VCVT/VCVTQ"
+void exec_vcvt (void)
+{
+  int i;
+
+  /* Basic test: y=vcvt(x), then store the result.  */
+#define TEST_VCVT(Q, T1, T2, W, N, TS1, TS2)			\
+  VECT_VAR(vector_res, T1, W, N) =				\
+    vcvt##Q##_##T2##W##_##TS2##W(VECT_VAR(vector, TS1, W, N));	\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),			\
+		    VECT_VAR(vector_res, T1, W, N));		\
+  DUMP(TEST_MSG, T1, W, N, PRIx##W);
+
+#define TEST_VCVT_FP(Q, T1, T2, W, N, TS1, TS2)			\
+  VECT_VAR(vector_res, T1, W, N) =				\
+    vcvt##Q##_##T2##W##_##TS2##W(VECT_VAR(vector, TS1, W, N));	\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),			\
+		    VECT_VAR(vector_res, T1, W, N));		\
+  DUMP_FP(TEST_MSG, T1, W, N, PRIx##W);
+
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#define TEST_VCVT_FP16(T1, T2, W1, W2, N)			\
+  VECT_VAR(vector_res, T1, W1, N) =				\
+    vcvt_##T2##W1##_##T2##W2(VECT_VAR(vector, T1, W2, N));	\
+  vst1q_##T2##W1(VECT_VAR(result, T1, W1, N),			\
+		 VECT_VAR(vector_res, T1, W1, N));		\
+  DUMP_FP(TEST_MSG, T1, W1, N, PRIx##W1);
+
+#define TEST_VCVT_2FP16(T1, T2, W1, W2, N)			\
+  VECT_VAR(vector_res, T1, W1, N) =				\
+    vcvt_##T2##W1##_##T2##W2(VECT_VAR(vector, T1, W2, N));	\
+  vst1_##T2##W1(VECT_VAR(result, T1, W1, N),			\
+		 VECT_VAR(vector_res, T1, W1, N));		\
+  DUMP_FP16(TEST_MSG, T1, W1, N, PRIx##W1);
+#endif
+
+#define TEST_VCVT_N(Q, T1, T2, W, N, TS1, TS2, V)			\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vcvt##Q##_n_##T2##W##_##TS2##W(VECT_VAR(vector, TS1, W, N), V);	\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),				\
+		    VECT_VAR(vector_res, T1, W, N));			\
+  DUMP(TEST_MSG, T1, W, N, PRIx##W);
+
+#define TEST_VCVT_N_FP(Q, T1, T2, W, N, TS1, TS2, V)			\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vcvt##Q##_n_##T2##W##_##TS2##W(VECT_VAR(vector, TS1, W, N), V);	\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),				\
+		    VECT_VAR(vector_res, T1, W, N));			\
+  DUMP_FP(TEST_MSG, T1, W, N, PRIx##W);
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  DECL_VARIABLE(vector_init, uint, 16, 4);
+  DECL_VARIABLE(vector_init, uint, 16, 8);
+  DECL_VARIABLE(vector, float, 16, 4);
+  DECL_VARIABLE(vector, float, 16, 8);
+  DECL_VARIABLE(vector_res, float, 16, 4);
+  DECL_VARIABLE(vector_res, float, 16, 8);
+#endif
+
+  clean_results ();
+
+
+  /* Initialize input "vector" from "buffer"  */
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+  VLOAD(vector, buffer, , float, f, 32, 2);
+  VLOAD(vector, buffer, q, float, f, 32, 4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  VLOAD(vector, buffer, , float, f, 16, 4);
+  VLOAD(vector, buffer, q, float, f, 16, 8);
+#endif
+
+  /* Make sure some elements have a fractional part, to exercise
+     integer conversions */
+  TEST_VSET_LANE(vector, , float, f, 32, 2, 0, -15.3f);
+  TEST_VSET_LANE(vector, , float, f, 32, 2, 1, 5.3f);
+  TEST_VSET_LANE(vector, q, float, f, 32, 4, 2, -15.3f);
+  TEST_VSET_LANE(vector, q, float, f, 32, 4, 3, 5.3f);
+
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  /* FP16 tests.  */
+  /* There is no vdup_n_f16, so we need another initialization
+     method.  */
+  /* Use all lanes with values of different types: first, a "standard"
+     positive number, a "standard" negative one, and +0 and -0.  */
+  TEST_VSET_LANE(vector_init, , uint, u, 16, 4, 0, 0x4b90 /* 15.125 */);
+  TEST_VSET_LANE(vector_init, , uint, u, 16, 4, 1, 0xcb90 /* -15.125 */);
+  TEST_VSET_LANE(vector_init, , uint, u, 16, 4, 2, 0 /* 0 */);
+  TEST_VSET_LANE(vector_init, , uint, u, 16, 4, 3, 0x8000 /* -0 */);
+  VECT_VAR(vector, float, 16, 4) =
+    vreinterpret_f16_u16(VECT_VAR(vector_init, uint, 16, 4));
+#endif
+
+  /* The same result buffers are used multiple times, so we output
+     them before overwriting them  */
+  fprintf(ref_file, "\n%s output:\n", TEST_MSG);
+  fprintf(gcc_tests_file, "\n%s output:\n", TEST_MSG);
+
+  /* vcvt_f32_xx */
+  TEST_VCVT_FP(, float, f, 32, 2, int, s);
+  TEST_VCVT_FP(, float, f, 32, 2, uint, u);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_VCVT_FP16(float, f, 32, 16, 4);
+#endif
+
+  /* vcvtq_f32_xx */
+  TEST_VCVT_FP(q, float, f, 32, 4, int, s);
+  TEST_VCVT_FP(q, float, f, 32, 4, uint, u);
+
+  /* vcvt_xx_f32 */
+  TEST_VCVT(, int, s, 32, 2, float, f);
+  TEST_VCVT(, uint, u, 32, 2, float, f);
+
+  TEST_VSET_LANE(vector, q, float, f, 32, 4, 0, 0.0f);
+  TEST_VSET_LANE(vector, q, float, f, 32, 4, 1, -0.0f);
+  TEST_VSET_LANE(vector, q, float, f, 32, 4, 2, 15.12f);
+  TEST_VSET_LANE(vector, q, float, f, 32, 4, 3, -15.12f);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_VCVT_2FP16(float, f, 16, 32, 4);
+#endif
+
+  /* vcvtq_xx_f32 */
+  TEST_VCVT(q, int, s, 32, 4, float, f);
+  TEST_VCVT(q, uint, u, 32, 4, float, f);
+
+  /* The same result buffers are used multiple times, so output them
+     before overwriting them  */
+#undef TEST_MSG
+#define TEST_MSG "VCVT_N/VCVTQ_N"
+  fprintf(ref_file, "\n%s output:\n", TEST_MSG);
+  fprintf(gcc_tests_file, "\n%s output:\n", TEST_MSG);
+
+  /* vcvt_n_f32_xx */
+  TEST_VCVT_N_FP(, float, f, 32, 2, int, s, 2);
+  TEST_VCVT_N_FP(, float, f, 32, 2, uint, u, 7);
+
+  /* vcvtq_n_f32_xx */
+  TEST_VCVT_N_FP(q, float, f, 32, 4, int, s, 30);
+  TEST_VCVT_N_FP(q, float, f, 32, 4, uint, u, 12);
+
+  /* vcvt_n_xx_f32 */
+  TEST_VCVT_N(, int, s, 32, 2, float, f, 20);
+  TEST_VCVT_N(, uint, u, 32, 2, float, f, 2);
+
+  /* vcvtq_n_xx_f32 */
+  TEST_VCVT_N(q, int, s, 32, 4, float, f, 13);
+  TEST_VCVT_N(q, uint, u, 32, 4, float, f, 1);
+
+  /* Check rounding */
+#undef TEST_MSG
+#define TEST_MSG "VCVT/VCVTQ"
+  fprintf(ref_file, "\n%s output:\n", TEST_MSG " (check rounding)");
+  VDUP(vector, , float, f, 32, 2, 10.4f);
+  VDUP(vector, q, float, f, 32, 4, 125.9f);
+  /* vcvt_xx_f32 */
+  TEST_VCVT(, int, s, 32, 2, float, f);
+  TEST_VCVT(, uint, u, 32, 2, float, f);
+  /* vcvtq_xx_f32 */
+  TEST_VCVT(q, int, s, 32, 4, float, f);
+  TEST_VCVT(q, uint, u, 32, 4, float, f);
+
+#undef TEST_MSG
+#define TEST_MSG "VCVT_N/VCVTQ_N"
+  fprintf(ref_file, "\n%s output:\n", TEST_MSG " (check rounding)");
+  /* vcvt_n_xx_f32 */
+  TEST_VCVT_N(, int, s, 32, 2, float, f, 20);
+  TEST_VCVT_N(, uint, u, 32, 2, float, f, 20);
+  /* vcvtq_n_xx_f32 */
+  TEST_VCVT_N(q, int, s, 32, 4, float, f, 13);
+  TEST_VCVT_N(q, uint, u, 32, 4, float, f, 13);
+
+#undef TEST_MSG
+#define TEST_MSG "VCVT_N/VCVTQ_N"
+  fprintf(ref_file, "\n%s output:\n", TEST_MSG " (check saturation)");
+  /* vcvt_n_xx_f32 */
+  TEST_VCVT_N(, int, s, 32, 2, float, f, 31);
+  /* vcvtq_n_xx_f32 */
+  TEST_VCVT_N(q, int, s, 32, 4, float, f, 31);
+
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#undef TEST_MSG
+#define TEST_MSG "VCVT FP16"
+  fprintf(ref_file, "\n%s output:\n", TEST_MSG " (check fp16-fp32 inf/nan/denormal)");
+  TEST_VSET_LANE(vector_init, , uint, u, 16, 4, 0, 0x0390 /* DENORMAL */);
+  TEST_VSET_LANE(vector_init, , uint, u, 16, 4, 1, 0x7c00 /* inf */);
+  TEST_VSET_LANE(vector_init, , uint, u, 16, 4, 2, 0x7e00 /* nan */);
+  TEST_VSET_LANE(vector_init, , uint, u, 16, 4, 3, 0xfc00 /* -inf */);
+  VECT_VAR(vector, float, 16, 4) =
+    vreinterpret_f16_u16(VECT_VAR(vector_init, uint, 16, 4));
+  TEST_VCVT_FP16(float, f, 32, 16, 4);
+
+  fprintf(ref_file, "\n%s output:\n", TEST_MSG " (check fp32-fp16 inf/nan)");
+  TEST_VSET_LANE(vector, q, float, f, 32, 4, 0, NAN);
+  TEST_VSET_LANE(vector, q, float, f, 32, 4, 1, HUGE_VALF);
+  TEST_VSET_LANE(vector, q, float, f, 32, 4, 2, -HUGE_VALF);
+  TEST_VSET_LANE(vector, q, float, f, 32, 4, 3, -0.0f);
+  TEST_VCVT_2FP16(float, f, 16, 32, 4);
+#endif
+}
diff --git a/ref_vdup.c b/ref_vdup.c
new file mode 100644
index 0000000..286a8ae
--- /dev/null
+++ b/ref_vdup.c
@@ -0,0 +1,116 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VDUP/VDUPQ"
+void exec_vdup (void)
+{
+  int i;
+
+  /* Basic test: vec=vdup(x), then store the result.  */
+#define TEST_VDUP(Q, T1, T2, W, N)					\
+  VECT_VAR(vector, T1, W, N) =						\
+    vdup##Q##_n_##T2##W(VECT_VAR(buffer_dup, T1, W, N)[i]);		\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector, T1, W, N))
+
+  /* Basic test: vec=vmov(x), then store the result.  */
+#define TEST_VMOV(Q, T1, T2, W, N)					\
+  VECT_VAR(vector, T1, W, N) =						\
+    vmov##Q##_n_##T2##W(VECT_VAR(buffer_dup, T1, W, N)[i]);		\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector, T1, W, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+
+  for (i=0; i< 3; i++) {
+    clean_results ();
+
+    TEST_VDUP(, int, s, 8, 8);
+    TEST_VDUP(, int, s, 16, 4);
+    TEST_VDUP(, int, s, 32, 2);
+    TEST_VDUP(, int, s, 64, 1);
+    TEST_VDUP(, uint, u, 8, 8);
+    TEST_VDUP(, uint, u, 16, 4);
+    TEST_VDUP(, uint, u, 32, 2);
+    TEST_VDUP(, uint, u, 64, 1);
+    TEST_VDUP(, poly, p, 8, 8);
+    TEST_VDUP(, poly, p, 16, 4);
+    TEST_VDUP(, float, f, 32, 2);
+
+    TEST_VDUP(q, int, s, 8, 16);
+    TEST_VDUP(q, int, s, 16, 8);
+    TEST_VDUP(q, int, s, 32, 4);
+    TEST_VDUP(q, int, s, 64, 2);
+    TEST_VDUP(q, uint, u, 8, 16);
+    TEST_VDUP(q, uint, u, 16, 8);
+    TEST_VDUP(q, uint, u, 32, 4);
+    TEST_VDUP(q, uint, u, 64, 2);
+    TEST_VDUP(q, poly, p, 8, 16);
+    TEST_VDUP(q, poly, p, 16, 8);
+    TEST_VDUP(q, float, f, 32, 4);
+
+    dump_results_hex (TEST_MSG);
+  }
+
+#undef TEST_MSG
+#define TEST_MSG "VMOV/VMOVQ"
+  for (i=0; i< 3; i++) {
+    clean_results ();
+
+    TEST_VMOV(, int, s, 8, 8);
+    TEST_VMOV(, int, s, 16, 4);
+    TEST_VMOV(, int, s, 32, 2);
+    TEST_VMOV(, int, s, 64, 1);
+    TEST_VMOV(, uint, u, 8, 8);
+    TEST_VMOV(, uint, u, 16, 4);
+    TEST_VMOV(, uint, u, 32, 2);
+    TEST_VMOV(, uint, u, 64, 1);
+    TEST_VMOV(, poly, p, 8, 8);
+    TEST_VMOV(, poly, p, 16, 4);
+    TEST_VMOV(, float, f, 32, 2);
+
+    TEST_VMOV(q, int, s, 8, 16);
+    TEST_VMOV(q, int, s, 16, 8);
+    TEST_VMOV(q, int, s, 32, 4);
+    TEST_VMOV(q, int, s, 64, 2);
+    TEST_VMOV(q, uint, u, 8, 16);
+    TEST_VMOV(q, uint, u, 16, 8);
+    TEST_VMOV(q, uint, u, 32, 4);
+    TEST_VMOV(q, uint, u, 64, 2);
+    TEST_VMOV(q, poly, p, 8, 16);
+    TEST_VMOV(q, poly, p, 16, 8);
+    TEST_VMOV(q, float, f, 32, 4);
+
+    dump_results_hex (TEST_MSG);
+  }
+}
diff --git a/ref_vdup_lane.c b/ref_vdup_lane.c
new file mode 100644
index 0000000..302fd37
--- /dev/null
+++ b/ref_vdup_lane.c
@@ -0,0 +1,81 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VDUP_LANE/VDUP_LANEQ"
+void exec_vdup_lane (void)
+{
+  /* Basic test: vec1=vdup_lane(vec2, lane), then store the result.  */
+#define TEST_VDUP_LANE(Q, T1, T2, W, N, N2, L)				\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vdup##Q##_lane_##T2##W(VECT_VAR(vector, T1, W, N2), L);		\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  /* Input vector can only have 64 bits */
+  DECL_VARIABLE_64BITS_VARIANTS(vector);
+
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+  clean_results ();
+
+  TEST_MACRO_64BITS_VARIANTS_2_5(VLOAD, vector, buffer);
+  VLOAD(vector, buffer, , float, f, 32, 2);
+
+  /* Choose lane arbitrarily  */
+  TEST_VDUP_LANE(, int, s, 8, 8, 8, 1);
+  TEST_VDUP_LANE(, int, s, 16, 4, 4, 2);
+  TEST_VDUP_LANE(, int, s, 32, 2, 2, 1);
+  TEST_VDUP_LANE(, int, s, 64, 1, 1, 0);
+  TEST_VDUP_LANE(, uint, u, 8, 8, 8, 7);
+  TEST_VDUP_LANE(, uint, u, 16, 4, 4, 3);
+  TEST_VDUP_LANE(, uint, u, 32, 2, 2, 1);
+  TEST_VDUP_LANE(, uint, u, 64, 1, 1, 0);
+  TEST_VDUP_LANE(, poly, p, 8, 8, 8, 7);
+  TEST_VDUP_LANE(, poly, p, 16, 4, 4, 3);
+  TEST_VDUP_LANE(, float, f, 32, 2, 2, 1);
+
+  TEST_VDUP_LANE(q, int, s, 8, 16, 8, 2);
+  TEST_VDUP_LANE(q, int, s, 16, 8, 4, 3);
+  TEST_VDUP_LANE(q, int, s, 32, 4, 2, 1);
+  TEST_VDUP_LANE(q, int, s, 64, 2, 1, 0);
+  TEST_VDUP_LANE(q, uint, u, 8, 16, 8, 5);
+  TEST_VDUP_LANE(q, uint, u, 16, 8, 4, 1);
+  TEST_VDUP_LANE(q, uint, u, 32, 4, 2, 0);
+  TEST_VDUP_LANE(q, uint, u, 64, 2, 1, 0);
+  TEST_VDUP_LANE(q, poly, p, 8, 16, 8, 5);
+  TEST_VDUP_LANE(q, poly, p, 16, 8, 4, 1);
+  TEST_VDUP_LANE(q, float, f, 32, 4, 2, 1);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_veor.c b/ref_veor.c
new file mode 100644
index 0000000..50226ff
--- /dev/null
+++ b/ref_veor.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME veor
+#define TEST_MSG "VEOR/VEORQ"
+
+#include "ref_v_binary_op.c"
diff --git a/ref_vext.c b/ref_vext.c
new file mode 100644
index 0000000..32e84ec
--- /dev/null
+++ b/ref_vext.c
@@ -0,0 +1,108 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VEXT/VEXTQ"
+void exec_vext (void)
+{
+  /* vector_res = vext(vector1,vector2,offset), then store the result.  */
+#define TEST_VEXT(Q, T1, T2, W, N, V)					\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vext##Q##_##T2##W(VECT_VAR(vector1, T1, W, N),			\
+		      VECT_VAR(vector2, T1, W, N),			\
+		      V);						\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_ALL_VARIANTS(vector1);
+  DECL_VARIABLE_ALL_VARIANTS(vector2);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+  clean_results ();
+
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector1, buffer);
+  VLOAD(vector1, buffer, , float, f, 32, 2);
+  VLOAD(vector1, buffer, q, float, f, 32, 4);
+
+  /* Choose arbitrary initialization values */
+  VDUP(vector2, , int, s, 8, 8, 0x11);
+  VDUP(vector2, , int, s, 16, 4, 0x22);
+  VDUP(vector2, , int, s, 32, 2, 0x33);
+  VDUP(vector2, , int, s, 64, 1, 0x44);
+  VDUP(vector2, , uint, u, 8, 8, 0x55);
+  VDUP(vector2, , uint, u, 16, 4, 0x66);
+  VDUP(vector2, , uint, u, 32, 2, 0x77);
+  VDUP(vector2, , uint, u, 64, 1, 0x88);
+  VDUP(vector2, , poly, p, 8, 8, 0x55);
+  VDUP(vector2, , poly, p, 16, 4, 0x66);
+  VDUP(vector2, , float, f, 32, 2, 33.6f);
+
+  VDUP(vector2, q, int, s, 8, 16, 0x11);
+  VDUP(vector2, q, int, s, 16, 8, 0x22);
+  VDUP(vector2, q, int, s, 32, 4, 0x33);
+  VDUP(vector2, q, int, s, 64, 2, 0x44);
+  VDUP(vector2, q, uint, u, 8, 16, 0x55);
+  VDUP(vector2, q, uint, u, 16, 8, 0x66);
+  VDUP(vector2, q, uint, u, 32, 4, 0x77);
+  VDUP(vector2, q, uint, u, 64, 2, 0x88);
+  VDUP(vector2, q, poly, p, 8, 16, 0x55);
+  VDUP(vector2, q, poly, p, 16, 8, 0x66);
+  VDUP(vector2, q, float, f, 32, 4, 33.2f);
+
+  /* Choose arbitrary extract offsets */
+  TEST_VEXT(, int, s, 8, 8, 7);
+  TEST_VEXT(, int, s, 16, 4, 3);
+  TEST_VEXT(, int, s, 32, 2, 1);
+  TEST_VEXT(, int, s, 64, 1, 0);
+  TEST_VEXT(, uint, u, 8, 8, 6);
+  TEST_VEXT(, uint, u, 16, 4, 2);
+  TEST_VEXT(, uint, u, 32, 2, 1);
+  TEST_VEXT(, uint, u, 64, 1, 0);
+  TEST_VEXT(, poly, p, 8, 8, 6);
+  TEST_VEXT(, poly, p, 16, 4, 2);
+  TEST_VEXT(, float, f, 32, 2, 1);
+
+  TEST_VEXT(q, int, s, 8, 16, 14);
+  TEST_VEXT(q, int, s, 16, 8, 7);
+  TEST_VEXT(q, int, s, 32, 4, 3);
+  TEST_VEXT(q, int, s, 64, 2, 1);
+  TEST_VEXT(q, uint, u, 8, 16, 12);
+  TEST_VEXT(q, uint, u, 16, 8, 6);
+  TEST_VEXT(q, uint, u, 32, 4, 3);
+  TEST_VEXT(q, uint, u, 64, 2, 1);
+  TEST_VEXT(q, poly, p, 8, 16, 12);
+  TEST_VEXT(q, poly, p, 16, 8, 6);
+  TEST_VEXT(q, float, f, 32, 4, 3);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vget_high.c b/ref_vget_high.c
new file mode 100644
index 0000000..3c894ae
--- /dev/null
+++ b/ref_vget_high.c
@@ -0,0 +1,76 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VGET_HIGH"
+void exec_vget_high (void)
+{
+  /* Basic test: vec64=vget_high(vec128), then store the result.  */
+#define TEST_VGET_HIGH(T1, T2, W, N, N2)				\
+  VECT_VAR(vector64, T1, W, N) =					\
+    vget_high_##T2##W(VECT_VAR(vector128, T1, W, N2));			\
+  vst1_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector64, T1, W, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_64BITS_VARIANTS(vector64);
+  DECL_VARIABLE_128BITS_VARIANTS(vector128);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  DECL_VARIABLE(vector64, float, 16, 4);
+  DECL_VARIABLE(vector128, float, 16, 8);
+#endif
+
+  TEST_MACRO_128BITS_VARIANTS_2_5(VLOAD, vector128, buffer);
+  VLOAD(vector128, buffer, q, float, f, 32, 4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  VLOAD(vector128, buffer, q, float, f, 16, 8);
+#endif
+
+  clean_results ();
+
+  TEST_VGET_HIGH(int, s, 8, 8, 16);
+  TEST_VGET_HIGH(int, s, 16, 4, 8);
+  TEST_VGET_HIGH(int, s, 32, 2, 4);
+  TEST_VGET_HIGH(int, s, 64, 1, 2);
+  TEST_VGET_HIGH(uint, u, 8, 8, 16);
+  TEST_VGET_HIGH(uint, u, 16, 4, 8);
+  TEST_VGET_HIGH(uint, u, 32, 2, 4);
+  TEST_VGET_HIGH(uint, u, 64, 1, 2);
+  TEST_VGET_HIGH(poly, p, 8, 8, 16);
+  TEST_VGET_HIGH(poly, p, 16, 4, 8);
+  TEST_VGET_HIGH(float, f, 32, 2, 4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_VGET_HIGH(float, f, 16, 4, 8);
+#endif
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vget_lane.c b/ref_vget_lane.c
new file mode 100644
index 0000000..0789d24
--- /dev/null
+++ b/ref_vget_lane.c
@@ -0,0 +1,109 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+void exec_vget_lane (void)
+{
+  /* vec=vget_lane(vec, lane), then store the result.  */
+#define TEST_VGET_LANE(Q, T1, T2, W, N, L)				\
+  VAR(var, T1, W) = vget##Q##_lane_##T2##W(VECT_VAR(vector, T1, W, N), L); \
+  fprintf(ref_file, "%s: %" PRIx##W "\n", "vget"STR(Q)"_lane_"STR(T2##W), VAR(var, T1, W))
+
+  /* Special variant for poly* types, to clear sign bits in output.  */
+#define TEST_VGET_LANE_POLY(Q, T1, T2, W, N, L)				\
+  VAR(var, T1, W) = vget##Q##_lane_##T2##W(VECT_VAR(vector, T1, W, N), L); \
+    fprintf(ref_file, "%s: %" PRIx##W "\n", "vget"STR(Q)"_lane_"STR(T2##W), \
+	    (uint##W##_t)VAR(var, T1, W))
+
+  /* Special variant for floating-point */
+  union {
+    uint32_t var_int32;
+    float var_float32;
+  } var_int32_float32;
+
+#define TEST_VGET_LANE_F(Q, T1, T2, W, N, L)				\
+  VAR(var, T1, W) = vget##Q##_lane_##T2##W(VECT_VAR(vector, T1, W, N), L); \
+  var_int##W##_float##W.var_float##W = VAR(var, T1, W);		\
+  fprintf(ref_file, "%s: %" PRIx##W "\n", "vget"STR(Q)"_lane_"STR(T2##W), var_int##W##_float##W.var_int##W)
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+
+  /* Scalar variables */
+  VAR_DECL(var, int, 8);
+  VAR_DECL(var, int, 16);
+  VAR_DECL(var, int, 32);
+  VAR_DECL(var, int, 64);
+  VAR_DECL(var, uint, 8);
+  VAR_DECL(var, uint, 16);
+  VAR_DECL(var, uint, 32);
+  VAR_DECL(var, uint, 64);
+  VAR_DECL(var, poly, 8);
+  VAR_DECL(var, poly, 16);
+  VAR_DECL(var, float, 32);
+
+  clean_results ();
+
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+  VLOAD(vector, buffer, , float, f, 32, 2);
+  VLOAD(vector, buffer, q, float, f, 32, 4);
+
+  fprintf(ref_file, "\n%s output:\n", "VGET_LANE/VGETQ_LANE");
+
+  /* Choose lane arbitrarily  */
+  TEST_VGET_LANE(, int, s, 8, 8, 7);
+  TEST_VGET_LANE(, int, s, 16, 4, 3);
+  TEST_VGET_LANE(, int, s, 32, 2, 1);
+  TEST_VGET_LANE(, int, s, 64, 1, 0);
+  TEST_VGET_LANE(, uint, u, 8, 8, 6);
+  TEST_VGET_LANE(, uint, u, 16, 4, 2);
+  TEST_VGET_LANE(, uint, u, 32, 2, 1);
+  TEST_VGET_LANE(, uint, u, 64, 1, 0);
+  TEST_VGET_LANE_POLY(, poly, p, 8, 8, 6);
+  TEST_VGET_LANE_POLY(, poly, p, 16, 4, 2);
+  TEST_VGET_LANE_F(, float, f, 32, 2, 1);
+
+  TEST_VGET_LANE(q, int, s, 8, 16, 15);
+  TEST_VGET_LANE(q, int, s, 16, 8, 5);
+  TEST_VGET_LANE(q, int, s, 32, 4, 3);
+  TEST_VGET_LANE(q, int, s, 64, 2, 1);
+  TEST_VGET_LANE(q, uint, u, 8, 16, 14);
+  TEST_VGET_LANE(q, uint, u, 16, 8, 6);
+  TEST_VGET_LANE(q, uint, u, 32, 4, 2);
+  TEST_VGET_LANE(q, uint, u, 64, 2, 1);
+  TEST_VGET_LANE_POLY(q, poly, p, 8, 16, 14);
+  TEST_VGET_LANE_POLY(q, poly, p, 16, 8, 6);
+  TEST_VGET_LANE_F(q, float, f, 32, 4, 3);
+
+  fprintf(ref_file, "\n");
+}
diff --git a/ref_vget_low.c b/ref_vget_low.c
new file mode 100644
index 0000000..1ed87c9
--- /dev/null
+++ b/ref_vget_low.c
@@ -0,0 +1,76 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VGET_LOW"
+void exec_vget_low (void)
+{
+  /* Basic test: vec64=vget_low(vec128), then store the result.  */
+#define TEST_VGET_LOW(T1, T2, W, N, N2)					\
+  VECT_VAR(vector64, T1, W, N) =					\
+    vget_low_##T2##W(VECT_VAR(vector128, T1, W, N2));			\
+  vst1_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector64, T1, W, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_64BITS_VARIANTS(vector64);
+  DECL_VARIABLE_128BITS_VARIANTS(vector128);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  DECL_VARIABLE(vector64, float, 16, 4);
+  DECL_VARIABLE(vector128, float, 16, 8);
+#endif
+
+  TEST_MACRO_128BITS_VARIANTS_2_5(VLOAD, vector128, buffer);
+  VLOAD(vector128, buffer, q, float, f, 32, 4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  VLOAD(vector128, buffer, q, float, f, 16, 8);
+#endif
+
+  clean_results ();
+
+  TEST_VGET_LOW(int, s, 8, 8, 16);
+  TEST_VGET_LOW(int, s, 16, 4, 8);
+  TEST_VGET_LOW(int, s, 32, 2, 4);
+  TEST_VGET_LOW(int, s, 64, 1, 2);
+  TEST_VGET_LOW(uint, u, 8, 8, 16);
+  TEST_VGET_LOW(uint, u, 16, 4, 8);
+  TEST_VGET_LOW(uint, u, 32, 2, 4);
+  TEST_VGET_LOW(uint, u, 64, 1, 2);
+  TEST_VGET_LOW(poly, p, 8, 8, 16);
+  TEST_VGET_LOW(poly, p, 16, 4, 8);
+  TEST_VGET_LOW(float, f, 32, 2, 4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_VGET_LOW(float, f, 16, 4, 8);
+#endif
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vhadd.c b/ref_vhadd.c
new file mode 100644
index 0000000..f7ab21b
--- /dev/null
+++ b/ref_vhadd.c
@@ -0,0 +1,31 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vhadd
+#define TEST_MSG "VHADD/VHADDQ"
+
+#define NO_FLOAT_VARIANT
+
+#include "ref_vmax.c"
diff --git a/ref_vhsub.c b/ref_vhsub.c
new file mode 100644
index 0000000..859df59
--- /dev/null
+++ b/ref_vhsub.c
@@ -0,0 +1,31 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vhsub
+#define TEST_MSG "VHSUB/VHSUBQ"
+
+#define NO_FLOAT_VARIANT
+
+#include "ref_vmax.c"
diff --git a/ref_vld1.c b/ref_vld1.c
new file mode 100644
index 0000000..47c6db3
--- /dev/null
+++ b/ref_vld1.c
@@ -0,0 +1,64 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VLD1/VLD1Q"
+void exec_vld1 (void)
+{
+  /* Basic test vec=vld1(buffer); then store vec: vst1(result, vector) */
+  /* This test actually tests vdl1 and vst1 at the same time */
+#define TEST_VLD1(VAR, BUF, Q, T1, T2, W, N)				\
+  VECT_VAR(VAR, T1, W, N) = vld1##Q##_##T2##W(VECT_VAR(BUF, T1, W, N)); \
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(VAR, T1, W, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  DECL_VARIABLE(vector, float, 16, 4);
+  DECL_VARIABLE(vector, float, 16, 8);
+#endif
+
+  clean_results ();
+
+  TEST_MACRO_ALL_VARIANTS_2_5(TEST_VLD1, vector, buffer);
+
+  TEST_VLD1(vector, buffer, , float, f, 32, 2);
+  TEST_VLD1(vector, buffer, q, float, f, 32, 4);
+
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_VLD1(vector, buffer, , float, f, 16, 4);
+  TEST_VLD1(vector, buffer, q, float, f, 16, 8);
+#endif
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vld1_dup.c b/ref_vld1_dup.c
new file mode 100644
index 0000000..d5eb80d
--- /dev/null
+++ b/ref_vld1_dup.c
@@ -0,0 +1,69 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VLD1_DUP/VLD1_DUPQ"
+void exec_vld1_dup (void)
+{
+  int i;
+
+  /* Fill vector with buffer item #i  */
+#define TEST_VLD1_DUP(VAR, BUF, Q, T1, T2, W, N)			\
+  VECT_VAR(VAR, T1, W, N) =						\
+    vld1##Q##_dup_##T2##W(&VECT_VAR(BUF, T1, W, N)[i]);			\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(VAR, T1, W, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  DECL_VARIABLE(vector, float, 16, 4);
+  DECL_VARIABLE(vector, float, 16, 8);
+#endif
+
+  /* Try to read different places from the input buffer */
+  for (i=0; i<3; i++) {
+    clean_results ();
+
+    TEST_MACRO_ALL_VARIANTS_2_5(TEST_VLD1_DUP, vector, buffer_dup);
+
+    TEST_VLD1_DUP(vector, buffer_dup, , float, f, 32, 2);
+    TEST_VLD1_DUP(vector, buffer_dup, q, float, f, 32, 4);
+
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+    TEST_VLD1_DUP(vector, buffer_dup, , float, f, 16, 4);
+    TEST_VLD1_DUP(vector, buffer_dup, q, float, f, 16, 8);
+#endif
+
+    dump_results_hex (TEST_MSG);
+  }
+}
diff --git a/ref_vld1_lane.c b/ref_vld1_lane.c
new file mode 100644
index 0000000..9736748
--- /dev/null
+++ b/ref_vld1_lane.c
@@ -0,0 +1,130 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VLD1_LANE/VLD1_LANEQ"
+void exec_vld1_lane (void)
+{
+  /* Fill vector_src with 0xAA, then load 1 lane */
+#define TEST_VLD1_LANE(Q, T1, T2, W, N, L)				\
+  memset (VECT_VAR(buffer_src, T1, W, N), 0xAA, W/8*N);			\
+  VECT_VAR(vector_src, T1, W, N) =					\
+    vld1##Q##_##T2##W(VECT_VAR(buffer_src, T1, W, N));			\
+  VECT_VAR(vector, T1, W, N) =						\
+    vld1##Q##_lane_##T2##W(VECT_VAR(buffer, T1, W, N),			\
+			   VECT_VAR(vector_src, T1, W, N), L);		\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector, T1, W, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  DECL_VARIABLE(vector, float, 16, 4);
+  DECL_VARIABLE(vector, float, 16, 8);
+#endif
+  DECL_VARIABLE_ALL_VARIANTS(vector_src);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  DECL_VARIABLE(vector_src, float, 16, 4);
+  DECL_VARIABLE(vector_src, float, 16, 8);
+#endif
+
+  ARRAY(buffer_src, int, 8, 8);
+  ARRAY(buffer_src, int, 16, 4);
+  ARRAY(buffer_src, int, 32, 2);
+  ARRAY(buffer_src, int, 64, 1);
+  ARRAY(buffer_src, uint, 8, 8);
+  ARRAY(buffer_src, uint, 16, 4);
+  ARRAY(buffer_src, uint, 32, 2);
+  ARRAY(buffer_src, uint, 64, 1);
+  ARRAY(buffer_src, poly, 8, 8);
+  ARRAY(buffer_src, poly, 16, 4);
+  ARRAY(buffer_src, float, 32, 2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  ARRAY(buffer_src, float, 16, 4);
+#endif
+
+  ARRAY(buffer_src, int, 8, 16);
+  ARRAY(buffer_src, int, 16, 8);
+  ARRAY(buffer_src, int, 32, 4);
+  ARRAY(buffer_src, int, 64, 2);
+  ARRAY(buffer_src, uint, 8, 16);
+  ARRAY(buffer_src, uint, 16, 8);
+  ARRAY(buffer_src, uint, 32, 4);
+  ARRAY(buffer_src, uint, 64, 2);
+  ARRAY(buffer_src, poly, 8, 16);
+  ARRAY(buffer_src, poly, 16, 8);
+  ARRAY(buffer_src, float, 32, 4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  ARRAY(buffer_src, float, 16, 8);
+#endif
+
+  clean_results ();
+
+  /* Choose lane arbitrarily  */
+  TEST_VLD1_LANE(, int, s, 8, 8, 6);
+  TEST_VLD1_LANE(, int, s, 16, 4, 3);
+  TEST_VLD1_LANE(, int, s, 32, 2, 1);
+  TEST_VLD1_LANE(, int, s, 64, 1, 0);
+  TEST_VLD1_LANE(, uint, u, 8, 8, 7);
+  TEST_VLD1_LANE(, uint, u, 16, 4, 3);
+  TEST_VLD1_LANE(, uint, u, 32, 2, 1);
+  TEST_VLD1_LANE(, uint, u, 64, 1, 0);
+  TEST_VLD1_LANE(, poly, p, 8, 8, 7);
+  TEST_VLD1_LANE(, poly, p, 16, 4, 3);
+  TEST_VLD1_LANE(, float, f, 32, 2, 1);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_VLD1_LANE(, float, f, 16, 4, 2);
+#endif
+
+  TEST_VLD1_LANE(q, int, s, 8, 16, 15);
+  TEST_VLD1_LANE(q, int, s, 16, 8, 5);
+  TEST_VLD1_LANE(q, int, s, 32, 4, 2);
+  TEST_VLD1_LANE(q, int, s, 64, 2, 1);
+  TEST_VLD1_LANE(q, uint, u, 8, 16, 12);
+  TEST_VLD1_LANE(q, uint, u, 16, 8, 6);
+  TEST_VLD1_LANE(q, uint, u, 32, 4, 2);
+  TEST_VLD1_LANE(q, uint, u, 64, 2, 0);
+  TEST_VLD1_LANE(q, poly, p, 8, 16, 12);
+  TEST_VLD1_LANE(q, poly, p, 16, 8, 6);
+  TEST_VLD1_LANE(q, float, f, 32, 4, 2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_VLD1_LANE(q, float, f, 16, 8, 5);
+#endif
+
+#ifndef __CC_ARM
+  /* Check runtime assertions. With RVCT, the check is performed at
+     compile-time */
+  //  TEST_VLD1_LANE(, int, s, 64, 1, 1);
+#endif
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vldX.c b/ref_vldX.c
new file mode 100644
index 0000000..555ea47
--- /dev/null
+++ b/ref_vldX.c
@@ -0,0 +1,221 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+void exec_vldX (void)
+{
+  /* In this case, input variables are arrays of vectors */
+#define DECL_VLDX(T1, W, N, X)						\
+  VECT_ARRAY_TYPE(T1, W, N, X) VECT_ARRAY_VAR(vector, T1, W, N, X);	\
+  VECT_VAR_DECL(result_bis_##X, T1, W, N)[X * N]
+
+  /* We need to use a temporary result buffer (result_bis), because
+     the one used for other tests is not large enough. A subset of the
+     result data is moved from result_bis to result, and it is this
+     subset which is used to check the actual behaviour. The next
+     macro enables to move another chunk of data from result_bis to
+     result.  */
+#define TEST_VLDX(Q, T1, T2, W, N, X)					\
+  VECT_ARRAY_VAR(vector, T1, W, N, X) =					\
+    /* Use dedicated init buffer, of size X */				\
+    vld##X##Q##_##T2##W(VECT_ARRAY_VAR(buffer_vld##X, T1, W, N, X));	\
+  vst##X##Q##_##T2##W(VECT_VAR(result_bis_##X, T1, W, N),		\
+		      VECT_ARRAY_VAR(vector, T1, W, N, X));		\
+  memcpy(VECT_VAR(result, T1, W, N), VECT_VAR(result_bis_##X, T1, W, N), \
+	 sizeof(VECT_VAR(result, T1, W, N)));
+
+  /* Overwrite "result" with the contents of "result_bis"[Y] */
+#define TEST_EXTRA_CHUNK(T1, W, N, X,Y)			\
+  memcpy(VECT_VAR(result, T1, W, N),			\
+	 &(VECT_VAR(result_bis_##X, T1, W, N)[Y*N]),	\
+	 sizeof(VECT_VAR(result, T1, W, N)));
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+
+  /* We need all variants in 64 bits, but there is no 64x2 variant */
+#define DECL_ALL_VLDX(X)			\
+  DECL_VLDX(int, 8, 8, X);			\
+  DECL_VLDX(int, 16, 4, X);			\
+  DECL_VLDX(int, 32, 2, X);			\
+  DECL_VLDX(int, 64, 1, X);			\
+  DECL_VLDX(uint, 8, 8, X);			\
+  DECL_VLDX(uint, 16, 4, X);			\
+  DECL_VLDX(uint, 32, 2, X);			\
+  DECL_VLDX(uint, 64, 1, X);			\
+  DECL_VLDX(poly, 8, 8, X);			\
+  DECL_VLDX(poly, 16, 4, X);			\
+  DECL_VLDX(float, 32, 2, X);			\
+  DECL_VLDX(int, 8, 16, X);			\
+  DECL_VLDX(int, 16, 8, X);			\
+  DECL_VLDX(int, 32, 4, X);			\
+  DECL_VLDX(uint, 8, 16, X);			\
+  DECL_VLDX(uint, 16, 8, X);			\
+  DECL_VLDX(uint, 32, 4, X);			\
+  DECL_VLDX(poly, 8, 16, X);			\
+  DECL_VLDX(poly, 16, 8, X);			\
+  DECL_VLDX(float, 32, 4, X)
+
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#define DECL_ALL_VLDX_FP16(X)			\
+  DECL_VLDX(float, 16, 4, X);			\
+  DECL_VLDX(float, 16, 8, X)
+#endif
+
+#define TEST_ALL_VLDX(X)			\
+  TEST_VLDX(, int, s, 8, 8, X);			\
+  TEST_VLDX(, int, s, 16, 4, X);		\
+  TEST_VLDX(, int, s, 32, 2, X);		\
+  TEST_VLDX(, int, s, 64, 1, X);		\
+  TEST_VLDX(, uint, u, 8, 8, X);		\
+  TEST_VLDX(, uint, u, 16, 4, X);		\
+  TEST_VLDX(, uint, u, 32, 2, X);		\
+  TEST_VLDX(, uint, u, 64, 1, X);		\
+  TEST_VLDX(, poly, p, 8, 8, X);		\
+  TEST_VLDX(, poly, p, 16, 4, X);		\
+  TEST_VLDX(, float, f, 32, 2, X);		\
+  TEST_VLDX(q, int, s, 8, 16, X);		\
+  TEST_VLDX(q, int, s, 16, 8, X);		\
+  TEST_VLDX(q, int, s, 32, 4, X);		\
+  TEST_VLDX(q, uint, u, 8, 16, X);		\
+  TEST_VLDX(q, uint, u, 16, 8, X);		\
+  TEST_VLDX(q, uint, u, 32, 4, X);		\
+  TEST_VLDX(q, poly, p, 8, 16, X);		\
+  TEST_VLDX(q, poly, p, 16, 8, X);		\
+  TEST_VLDX(q, float, f, 32, 4, X)
+
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#define TEST_ALL_VLDX_FP16(X)			\
+  TEST_VLDX(, float, f, 16, 4, X);		\
+  TEST_VLDX(q, float, f, 16, 8, X)
+#endif
+
+#define TEST_ALL_EXTRA_CHUNKS(X, Y)		\
+  TEST_EXTRA_CHUNK(int, 8, 8, X, Y);		\
+  TEST_EXTRA_CHUNK(int, 16, 4, X, Y);		\
+  TEST_EXTRA_CHUNK(int, 32, 2, X, Y);		\
+  TEST_EXTRA_CHUNK(int, 64, 1, X, Y);		\
+  TEST_EXTRA_CHUNK(uint, 8, 8, X, Y);		\
+  TEST_EXTRA_CHUNK(uint, 16, 4, X, Y);		\
+  TEST_EXTRA_CHUNK(uint, 32, 2, X, Y);		\
+  TEST_EXTRA_CHUNK(uint, 64, 1, X, Y);		\
+  TEST_EXTRA_CHUNK(poly, 8, 8, X, Y);		\
+  TEST_EXTRA_CHUNK(poly, 16, 4, X, Y);		\
+  TEST_EXTRA_CHUNK(float, 32, 2, X, Y);		\
+  TEST_EXTRA_CHUNK(int, 8, 16, X, Y);		\
+  TEST_EXTRA_CHUNK(int, 16, 8, X, Y);		\
+  TEST_EXTRA_CHUNK(int, 32, 4, X, Y);		\
+  TEST_EXTRA_CHUNK(uint, 8, 16, X, Y);		\
+  TEST_EXTRA_CHUNK(uint, 16, 8, X, Y);		\
+  TEST_EXTRA_CHUNK(uint, 32, 4, X, Y);		\
+  TEST_EXTRA_CHUNK(poly, 8, 16, X, Y);		\
+  TEST_EXTRA_CHUNK(poly, 16, 8, X, Y);		\
+  TEST_EXTRA_CHUNK(float, 32, 4, X, Y)
+
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#define TEST_ALL_EXTRA_CHUNKS_FP16(X, Y)	\
+  TEST_EXTRA_CHUNK(float, 16, 4, X, Y);		\
+  TEST_EXTRA_CHUNK(float, 16, 8, X, Y)
+#endif
+
+  DECL_ALL_VLDX(2);
+  DECL_ALL_VLDX(3);
+  DECL_ALL_VLDX(4);
+
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  DECL_ALL_VLDX_FP16(2);
+  DECL_ALL_VLDX_FP16(3);
+  DECL_ALL_VLDX_FP16(4);
+#endif
+
+  /* Check vld2/vld2q */
+  clean_results ();
+#define TEST_MSG "VLD2/VLD2Q"
+  TEST_ALL_VLDX(2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_VLDX_FP16(2);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 0");
+
+  TEST_ALL_EXTRA_CHUNKS(2, 1);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_EXTRA_CHUNKS_FP16(2, 1);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 1");
+
+  /* Check vld3/vld3q */
+  clean_results ();
+#undef TEST_MSG
+#define TEST_MSG "VLD3/VLD3Q"
+  TEST_ALL_VLDX(3);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_VLDX_FP16(3);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 0");
+
+  TEST_ALL_EXTRA_CHUNKS(3, 1);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_EXTRA_CHUNKS_FP16(3, 1);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 1");
+  TEST_ALL_EXTRA_CHUNKS(3, 2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_EXTRA_CHUNKS_FP16(3, 2);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 2");
+
+  /* Check vld4/vld4q */
+  clean_results ();
+#undef TEST_MSG
+#define TEST_MSG "VLD4/VLD4Q"
+  TEST_ALL_VLDX(4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_VLDX_FP16(4);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 0");
+
+  TEST_ALL_EXTRA_CHUNKS(4, 1);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_EXTRA_CHUNKS_FP16(4, 1);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 1");
+  TEST_ALL_EXTRA_CHUNKS(4, 2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_EXTRA_CHUNKS_FP16(4, 2);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 2");
+  TEST_ALL_EXTRA_CHUNKS(4, 3);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_EXTRA_CHUNKS_FP16(4, 3);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 3");
+}
diff --git a/ref_vldX_dup.c b/ref_vldX_dup.c
new file mode 100644
index 0000000..15ba2c8
--- /dev/null
+++ b/ref_vldX_dup.c
@@ -0,0 +1,187 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+void exec_vldX_dup (void)
+{
+  /* In this case, input variables are arrays of vectors */
+#define DECL_VLDX_DUP(T1, W, N, X)					\
+  VECT_ARRAY_TYPE(T1, W, N, X) VECT_ARRAY_VAR(vector, T1, W, N, X);	\
+  VECT_VAR_DECL(result_bis_##X, T1, W, N)[X * N]
+
+  /* We need to use a temporary result buffer (result_bis), because
+     the one used for other tests is not large enough. A subset of the
+     result data is moved from result_bis to result, and it is this
+     subset which is used to check the actual behaviour. The next
+     macro enables to move another chunk of data from result_bis to
+     result.  */
+#define TEST_VLDX_DUP(Q, T1, T2, W, N, X)				\
+  VECT_ARRAY_VAR(vector, T1, W, N, X) =					\
+    vld##X##Q##_dup_##T2##W(&VECT_VAR(buffer_dup, T1, W, N)[0]);	\
+									\
+  vst##X##Q##_##T2##W(VECT_VAR(result_bis_##X, T1, W, N),		\
+		      VECT_ARRAY_VAR(vector, T1, W, N, X));		\
+  memcpy(VECT_VAR(result, T1, W, N), VECT_VAR(result_bis_##X, T1, W, N), \
+	 sizeof(VECT_VAR(result, T1, W, N)));
+
+
+  /* Overwrite "result" with the contents of "result_bis"[Y] */
+#define TEST_EXTRA_CHUNK(T1, W, N, X,Y)			\
+  memcpy(VECT_VAR(result, T1, W, N),			\
+	 &(VECT_VAR(result_bis_##X, T1, W, N)[Y*N]),	\
+	 sizeof(VECT_VAR(result, T1, W, N)));
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+#define DECL_ALL_VLDX_DUP(X)			\
+  DECL_VLDX_DUP(int, 8, 8, X);			\
+  DECL_VLDX_DUP(int, 16, 4, X);			\
+  DECL_VLDX_DUP(int, 32, 2, X);			\
+  DECL_VLDX_DUP(int, 64, 1, X);			\
+  DECL_VLDX_DUP(uint, 8, 8, X);			\
+  DECL_VLDX_DUP(uint, 16, 4, X);		\
+  DECL_VLDX_DUP(uint, 32, 2, X);		\
+  DECL_VLDX_DUP(uint, 64, 1, X);		\
+  DECL_VLDX_DUP(poly, 8, 8, X);			\
+  DECL_VLDX_DUP(poly, 16, 4, X);		\
+  DECL_VLDX_DUP(float, 32, 2, X)
+
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#define DECL_ALL_VLDX_DUP_FP16(X)		\
+  DECL_VLDX_DUP(float, 16, 4, X)
+#endif
+
+#define TEST_ALL_VLDX_DUP(X)			\
+  TEST_VLDX_DUP(, int, s, 8, 8, X);		\
+  TEST_VLDX_DUP(, int, s, 16, 4, X);		\
+  TEST_VLDX_DUP(, int, s, 32, 2, X);		\
+  TEST_VLDX_DUP(, int, s, 64, 1, X);		\
+  TEST_VLDX_DUP(, uint, u, 8, 8, X);		\
+  TEST_VLDX_DUP(, uint, u, 16, 4, X);		\
+  TEST_VLDX_DUP(, uint, u, 32, 2, X);		\
+  TEST_VLDX_DUP(, uint, u, 64, 1, X);		\
+  TEST_VLDX_DUP(, poly, p, 8, 8, X);		\
+  TEST_VLDX_DUP(, poly, p, 16, 4, X);		\
+  TEST_VLDX_DUP(, float, f, 32, 2, X)
+
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#define TEST_ALL_VLDX_DUP_FP16(X)		\
+  TEST_VLDX_DUP(, float, f, 16, 4, X)
+#endif
+
+#define TEST_ALL_EXTRA_CHUNKS(X, Y)		\
+  TEST_EXTRA_CHUNK(int, 8, 8, X, Y);		\
+  TEST_EXTRA_CHUNK(int, 16, 4, X, Y);		\
+  TEST_EXTRA_CHUNK(int, 32, 2, X, Y);		\
+  TEST_EXTRA_CHUNK(int, 64, 1, X, Y);		\
+  TEST_EXTRA_CHUNK(uint, 8, 8, X, Y);		\
+  TEST_EXTRA_CHUNK(uint, 16, 4, X, Y);		\
+  TEST_EXTRA_CHUNK(uint, 32, 2, X, Y);		\
+  TEST_EXTRA_CHUNK(uint, 64, 1, X, Y);		\
+  TEST_EXTRA_CHUNK(poly, 8, 8, X, Y);		\
+  TEST_EXTRA_CHUNK(poly, 16, 4, X, Y);		\
+  TEST_EXTRA_CHUNK(float, 32, 2, X, Y)
+
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#define TEST_ALL_EXTRA_CHUNKS_FP16(X, Y)	\
+  TEST_EXTRA_CHUNK(float, 16, 4, X, Y)
+#endif
+
+
+  DECL_ALL_VLDX_DUP(2);
+  DECL_ALL_VLDX_DUP(3);
+  DECL_ALL_VLDX_DUP(4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  DECL_ALL_VLDX_DUP_FP16(2);
+  DECL_ALL_VLDX_DUP_FP16(3);
+  DECL_ALL_VLDX_DUP_FP16(4);
+#endif
+
+  /* Check vld2_dup/vld2q_dup */
+  clean_results ();
+#define TEST_MSG "VLD2_DUP/VLD2Q_DUP"
+  TEST_ALL_VLDX_DUP(2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_VLDX_DUP_FP16(2);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 0");
+  TEST_ALL_EXTRA_CHUNKS(2, 1);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_EXTRA_CHUNKS_FP16(2, 1);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 1");
+
+  /* Check vld3_dup/vld3q_dup */
+  clean_results ();
+#undef TEST_MSG
+#define TEST_MSG "VLD3_DUP/VLD3Q_DUP"
+  TEST_ALL_VLDX_DUP(3);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_VLDX_DUP_FP16(3);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 0");
+  TEST_ALL_EXTRA_CHUNKS(3, 1);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_EXTRA_CHUNKS_FP16(3, 1);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 1");
+  TEST_ALL_EXTRA_CHUNKS(3, 2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_EXTRA_CHUNKS_FP16(3, 2);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 2");
+
+  /* Check vld4_dup/vld4q_dup */
+  clean_results ();
+#undef TEST_MSG
+#define TEST_MSG "VLD4_DUP/VLD4Q_DUP"
+  TEST_ALL_VLDX_DUP(4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_VLDX_DUP_FP16(4);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 0");
+  TEST_ALL_EXTRA_CHUNKS(4, 1);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_EXTRA_CHUNKS_FP16(4, 1);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 1");
+  TEST_ALL_EXTRA_CHUNKS(4, 2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_EXTRA_CHUNKS_FP16(4, 2);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 2");
+  TEST_ALL_EXTRA_CHUNKS(4, 3);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_EXTRA_CHUNKS_FP16(4, 3);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 3");
+}
diff --git a/ref_vldX_lane.c b/ref_vldX_lane.c
new file mode 100644
index 0000000..7a74232
--- /dev/null
+++ b/ref_vldX_lane.c
@@ -0,0 +1,243 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+void exec_vldX_lane (void)
+{
+  /* In this case, input variables are arrays of vectors */
+#define DECL_VLDX_LANE(T1, W, N, X)					\
+  VECT_ARRAY_TYPE(T1, W, N, X) VECT_ARRAY_VAR(vector, T1, W, N, X);	\
+  VECT_ARRAY_TYPE(T1, W, N, X) VECT_ARRAY_VAR(vector_src, T1, W, N, X);	\
+  VECT_VAR_DECL(result_bis_##X, T1, W, N)[X * N]
+
+  /* We need to use a temporary result buffer (result_bis), because
+     the one used for other tests is not large enough. A subset of the
+     result data is moved from result_bis to result, and it is this
+     subset which is used to check the actual behaviour. The next
+     macro enables to move another chunk of data from result_bis to
+     result.  */
+#define TEST_VLDX_LANE(Q, T1, T2, W, N, X, L)				\
+  memset (VECT_VAR(buffer_src, T1, W, N), 0xAA,				\
+	  sizeof(VECT_VAR(buffer_src, T1, W, N)));			\
+									\
+  VECT_ARRAY_VAR(vector_src, T1, W, N, X) =				\
+    vld##X##Q##_##T2##W(VECT_VAR(buffer_src, T1, W, N));		\
+									\
+  VECT_ARRAY_VAR(vector, T1, W, N, X) =					\
+    /* Use dedicated init buffer, of size X */				\
+    vld##X##Q##_lane_##T2##W(VECT_VAR(buffer_vld##X##_lane, T1, W, X),	\
+			     VECT_ARRAY_VAR(vector_src, T1, W, N, X),	\
+			     L);					\
+  vst##X##Q##_##T2##W(VECT_VAR(result_bis_##X, T1, W, N),		\
+		      VECT_ARRAY_VAR(vector, T1, W, N, X));		\
+  memcpy(VECT_VAR(result, T1, W, N), VECT_VAR(result_bis_##X, T1, W, N), \
+	 sizeof(VECT_VAR(result, T1, W, N)))
+
+  /* Overwrite "result" with the contents of "result_bis"[Y] */
+#define TEST_EXTRA_CHUNK(T1, W, N, X, Y)		\
+  memcpy(VECT_VAR(result, T1, W, N),			\
+	 &(VECT_VAR(result_bis_##X, T1, W, N)[Y*N]),	\
+	 sizeof(VECT_VAR(result, T1, W, N)));
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+
+  /* We need all variants in 64 bits, but there is no 64x2 variant */
+#define DECL_ALL_VLDX_LANE(X)			\
+  DECL_VLDX_LANE(int, 8, 8, X);			\
+  DECL_VLDX_LANE(int, 16, 4, X);		\
+  DECL_VLDX_LANE(int, 32, 2, X);		\
+  DECL_VLDX_LANE(uint, 8, 8, X);		\
+  DECL_VLDX_LANE(uint, 16, 4, X);		\
+  DECL_VLDX_LANE(uint, 32, 2, X);		\
+  DECL_VLDX_LANE(poly, 8, 8, X);		\
+  DECL_VLDX_LANE(poly, 16, 4, X);		\
+  DECL_VLDX_LANE(int, 16, 8, X);		\
+  DECL_VLDX_LANE(int, 32, 4, X);		\
+  DECL_VLDX_LANE(uint, 16, 8, X);		\
+  DECL_VLDX_LANE(uint, 32, 4, X);		\
+  DECL_VLDX_LANE(poly, 16, 8, X);		\
+  DECL_VLDX_LANE(float, 32, 2, X);		\
+  DECL_VLDX_LANE(float, 32, 4, X)
+
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#define DECL_ALL_VLDX_LANE_FP16(X)		\
+  DECL_VLDX_LANE(float, 16, 4, X);		\
+  DECL_VLDX_LANE(float, 16, 8, X)
+#endif
+
+  /* Add some padding to try to catch out of bound accesses.  */
+  /* Use an array instead of a plain char to comply with rvct
+     constraints.  */
+#define ARRAY1(V, T, W, N) VECT_VAR_DECL(V,T,W,N)[1]={42}
+#define DUMMY_ARRAY(V, T, W, N, L) \
+  VECT_VAR_DECL(V,T,W,N)[N*L]={0}; \
+  ARRAY1(V##_pad,T,W,N)
+
+  /* Use the same lanes regardless of the size of the array (X), for
+     simplicity */
+#define TEST_ALL_VLDX_LANE(X)			\
+  TEST_VLDX_LANE(, int, s, 8, 8, X, 7);		\
+  TEST_VLDX_LANE(, int, s, 16, 4, X, 2);	\
+  TEST_VLDX_LANE(, int, s, 32, 2, X, 0);	\
+  TEST_VLDX_LANE(, uint, u, 8, 8, X, 4);	\
+  TEST_VLDX_LANE(, uint, u, 16, 4, X, 3);	\
+  TEST_VLDX_LANE(, uint, u, 32, 2, X, 1);	\
+  TEST_VLDX_LANE(, poly, p, 8, 8, X, 4);	\
+  TEST_VLDX_LANE(, poly, p, 16, 4, X, 3);	\
+  TEST_VLDX_LANE(q, int, s, 16, 8, X, 6);	\
+  TEST_VLDX_LANE(q, int, s, 32, 4, X, 2);	\
+  TEST_VLDX_LANE(q, uint, u, 16, 8, X, 5);	\
+  TEST_VLDX_LANE(q, uint, u, 32, 4, X, 0);	\
+  TEST_VLDX_LANE(q, poly, p, 16, 8, X, 5);	\
+  TEST_VLDX_LANE(, float, f, 32, 2, X, 0);	\
+  TEST_VLDX_LANE(q, float, f, 32, 4, X, 2)
+
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#define TEST_ALL_VLDX_LANE_FP16(X)		\
+  TEST_VLDX_LANE(, float, f, 16, 4, X, 0);	\
+  TEST_VLDX_LANE(q, float, f, 16, 8, X, 2)
+#endif
+
+#define TEST_ALL_EXTRA_CHUNKS(X, Y)		\
+  TEST_EXTRA_CHUNK(int, 8, 8, X, Y);		\
+  TEST_EXTRA_CHUNK(int, 16, 4, X, Y);		\
+  TEST_EXTRA_CHUNK(int, 32, 2, X, Y);		\
+  TEST_EXTRA_CHUNK(uint, 8, 8, X, Y);		\
+  TEST_EXTRA_CHUNK(uint, 16, 4, X, Y);		\
+  TEST_EXTRA_CHUNK(uint, 32, 2, X, Y);		\
+  TEST_EXTRA_CHUNK(poly, 8, 8, X, Y);		\
+  TEST_EXTRA_CHUNK(poly, 16, 4, X, Y);		\
+  TEST_EXTRA_CHUNK(int, 16, 8, X, Y);		\
+  TEST_EXTRA_CHUNK(int, 32, 4, X, Y);		\
+  TEST_EXTRA_CHUNK(uint, 16, 8, X, Y);		\
+  TEST_EXTRA_CHUNK(uint, 32, 4, X, Y);		\
+  TEST_EXTRA_CHUNK(poly, 16, 8, X, Y);		\
+  TEST_EXTRA_CHUNK(float, 32, 2, X, Y);		\
+  TEST_EXTRA_CHUNK(float, 32, 4, X, Y)
+
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#define TEST_ALL_EXTRA_CHUNKS_FP16(X, Y)	\
+  TEST_EXTRA_CHUNK(float, 16, 4, X, Y);		\
+  TEST_EXTRA_CHUNK(float, 16, 8, X, Y)
+#endif
+
+  /* Declare the temporary buffers / variables */
+  DECL_ALL_VLDX_LANE(2);
+  DECL_ALL_VLDX_LANE(3);
+  DECL_ALL_VLDX_LANE(4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  DECL_ALL_VLDX_LANE_FP16(2);
+  DECL_ALL_VLDX_LANE_FP16(3);
+  DECL_ALL_VLDX_LANE_FP16(4);
+#endif
+
+  /* Define dummy input arrays, large enough for x4 vectors */
+  DUMMY_ARRAY(buffer_src, int, 8, 8, 4);
+  DUMMY_ARRAY(buffer_src, int, 16, 4, 4);
+  DUMMY_ARRAY(buffer_src, int, 32, 2, 4);
+  DUMMY_ARRAY(buffer_src, uint, 8, 8, 4);
+  DUMMY_ARRAY(buffer_src, uint, 16, 4, 4);
+  DUMMY_ARRAY(buffer_src, uint, 32, 2, 4);
+  DUMMY_ARRAY(buffer_src, poly, 8, 8, 4);
+  DUMMY_ARRAY(buffer_src, poly, 16, 4, 4);
+  DUMMY_ARRAY(buffer_src, int, 16, 8, 4);
+  DUMMY_ARRAY(buffer_src, int, 32, 4, 4);
+  DUMMY_ARRAY(buffer_src, uint, 16, 8, 4);
+  DUMMY_ARRAY(buffer_src, uint, 32, 4, 4);
+  DUMMY_ARRAY(buffer_src, poly, 16, 8, 4);
+  DUMMY_ARRAY(buffer_src, float, 32, 2, 4);
+  DUMMY_ARRAY(buffer_src, float, 32, 4, 4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  DUMMY_ARRAY(buffer_src, float, 16, 4, 4);
+  DUMMY_ARRAY(buffer_src, float, 16, 8, 4);
+#endif
+
+  /* Check vld2_lane/vld2q_lane */
+  clean_results ();
+#define TEST_MSG "VLD2_LANE/VLD2Q_LANE"
+  TEST_ALL_VLDX_LANE(2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_VLDX_LANE_FP16(2);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 0");
+  TEST_ALL_EXTRA_CHUNKS(2, 1);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_EXTRA_CHUNKS_FP16(2, 1);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 1");
+
+  /* Check vld3_lane/vld3q_lane */
+  clean_results ();
+#undef TEST_MSG
+#define TEST_MSG "VLD3_LANE/VLD3Q_LANE"
+  TEST_ALL_VLDX_LANE(3);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_VLDX_LANE_FP16(3);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 0");
+  TEST_ALL_EXTRA_CHUNKS(3, 1);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_EXTRA_CHUNKS_FP16(3, 1);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 1");
+  TEST_ALL_EXTRA_CHUNKS(3, 2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_EXTRA_CHUNKS_FP16(3, 2);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 2");
+
+  /* Check vld4_lane/vld4q_lane */
+  clean_results ();
+#undef TEST_MSG
+#define TEST_MSG "VLD4_LANE/VLD4Q_LANE"
+  TEST_ALL_VLDX_LANE(4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_VLDX_LANE_FP16(4);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 0");
+  TEST_ALL_EXTRA_CHUNKS(4, 1);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_EXTRA_CHUNKS_FP16(4, 1);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 1");
+  TEST_ALL_EXTRA_CHUNKS(4, 2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_EXTRA_CHUNKS_FP16(4, 2);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 2");
+  TEST_ALL_EXTRA_CHUNKS(4, 3);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_EXTRA_CHUNKS_FP16(4, 3);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 3");
+}
diff --git a/ref_vmax.c b/ref_vmax.c
new file mode 100644
index 0000000..d0086e5
--- /dev/null
+++ b/ref_vmax.c
@@ -0,0 +1,153 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+#include <math.h>
+
+#ifndef INSN_NAME
+#define INSN_NAME vmax
+#define TEST_MSG "VMAX/VMAXQ"
+#endif
+
+/* Can't use the standard ref_v_binary_op.c template because vmax has
+   no 64 bits variant */
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  int i;
+
+  /* Basic test: y=OP(x,x), then store the result.  */
+#define TEST_BINARY_OP1(INSN, Q, T1, T2, W, N)				\
+  VECT_VAR(vector_res, T1, W, N) =                                      \
+    INSN##Q##_##T2##W(VECT_VAR(vector, T1, W, N),                       \
+                      VECT_VAR(vector2, T1, W, N));                     \
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+#define TEST_BINARY_OP(INSN, Q, T1, T2, W, N)   \
+  TEST_BINARY_OP1(INSN, Q, T1, T2, W, N)        \
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement  */
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+  DECL_VARIABLE_ALL_VARIANTS(vector2);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+#ifndef NO_FLOAT_VARIANT
+  VLOAD(vector, buffer, , float, f, 32, 2);
+  VLOAD(vector, buffer, q, float, f, 32, 4);
+#endif
+
+  /* Choose init value arbitrarily, will be used as comparison value */
+  VDUP(vector2, , int, s, 8, 8, -13);
+  VDUP(vector2, , int, s, 16, 4, -14);
+  VDUP(vector2, , int, s, 32, 2, -16);
+  VDUP(vector2, , uint, u, 8, 8, 0xf3);
+  VDUP(vector2, , uint, u, 16, 4, 0xfff1);
+  VDUP(vector2, , uint, u, 32, 2, 0xfffffff0);
+  VDUP(vector2, q, int, s, 8, 16, -12);
+  VDUP(vector2, q, int, s, 16, 8, -13);
+  VDUP(vector2, q, int, s, 32, 4, -15);
+  VDUP(vector2, q, uint, u, 8, 16, 0xf9);
+  VDUP(vector2, q, uint, u, 16, 8, 0xfff2);
+  VDUP(vector2, q, uint, u, 32, 4, 0xfffffff1);
+#ifndef NO_FLOAT_VARIANT
+  VDUP(vector2, , float, f, 32, 2, -15.5f);
+  VDUP(vector2, q, float, f, 32, 4, -14.5f);
+#endif
+
+#ifndef NO_FLOAT_VARIANT
+#define FLOAT_VARIANT(MACRO, VAR)			\
+  MACRO(VAR, , float, f, 32, 2);			\
+  MACRO(VAR, q, float, f, 32, 4)
+#else
+#define FLOAT_VARIANT(MACRO, VAR)
+#endif
+
+#define TEST_MACRO_NO64BIT_VARIANT_1_5(MACRO, VAR)	\
+  MACRO(VAR, , int, s, 8, 8);				\
+  MACRO(VAR, , int, s, 16, 4);				\
+  MACRO(VAR, , int, s, 32, 2);				\
+  MACRO(VAR, , uint, u, 8, 8);				\
+  MACRO(VAR, , uint, u, 16, 4);				\
+  MACRO(VAR, , uint, u, 32, 2);				\
+  MACRO(VAR, q, int, s, 8, 16);				\
+  MACRO(VAR, q, int, s, 16, 8);				\
+  MACRO(VAR, q, int, s, 32, 4);				\
+  MACRO(VAR, q, uint, u, 8, 16);			\
+  MACRO(VAR, q, uint, u, 16, 8);			\
+  MACRO(VAR, q, uint, u, 32, 4);			\
+  FLOAT_VARIANT(MACRO, VAR)
+
+  /* Apply a binary operator named INSN_NAME  */
+  TEST_MACRO_NO64BIT_VARIANT_1_5(TEST_BINARY_OP, INSN_NAME);
+
+  dump_results_hex (TEST_MSG);
+
+
+#ifndef NO_FLOAT_VARIANT
+  /* Extra FP tests with special values (NaN, ....) */
+  VDUP(vector, q, float, f, 32, 4, 1.0f);
+  VDUP(vector2, q, float, f, 32, 4, NAN);
+  TEST_BINARY_OP(INSN_NAME, q, float, f, 32, 4);
+  DUMP_FP(TEST_MSG " FP special (NaN)", float, 32, 4, PRIx32);
+
+  VDUP(vector, q, float, f, 32, 4, -NAN);
+  VDUP(vector2, q, float, f, 32, 4, 1.0f);
+  TEST_BINARY_OP(INSN_NAME, q, float, f, 32, 4);
+  DUMP_FP(TEST_MSG " FP special (-NaN)", float, 32, 4, PRIx32);
+
+  VDUP(vector, q, float, f, 32, 4, 1.0f);
+  VDUP(vector2, q, float, f, 32, 4, HUGE_VALF);
+  TEST_BINARY_OP(INSN_NAME, q, float, f, 32, 4);
+  DUMP_FP(TEST_MSG " FP special (inf)", float, 32, 4, PRIx32);
+
+  VDUP(vector, q, float, f, 32, 4, -HUGE_VALF);
+  VDUP(vector2, q, float, f, 32, 4, 1.0f);
+  TEST_BINARY_OP(INSN_NAME, q, float, f, 32, 4);
+  DUMP_FP(TEST_MSG " FP special (-inf)", float, 32, 4, PRIx32);
+
+  VDUP(vector, q, float, f, 32, 4, 0.0f);
+  VDUP(vector2, q, float, f, 32, 4, -0.0f);
+  TEST_BINARY_OP(INSN_NAME, q, float, f, 32, 4);
+  DUMP_FP(TEST_MSG " FP special (-0.0)", float, 32, 4, PRIx32);
+
+  VDUP(vector, q, float, f, 32, 4, -0.0f);
+  VDUP(vector2, q, float, f, 32, 4, 0.0f);
+  TEST_BINARY_OP(INSN_NAME, q, float, f, 32, 4);
+  DUMP_FP(TEST_MSG " FP special (-0.0)", float, 32, 4, PRIx32);
+#endif
+}
diff --git a/ref_vmin.c b/ref_vmin.c
new file mode 100644
index 0000000..496e3ae
--- /dev/null
+++ b/ref_vmin.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vmin
+#define TEST_MSG "VMIN/VMINQ"
+
+#include "ref_vmax.c"
diff --git a/ref_vmla.c b/ref_vmla.c
new file mode 100644
index 0000000..fd4106b
--- /dev/null
+++ b/ref_vmla.c
@@ -0,0 +1,144 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#ifndef INSN_NAME
+#define INSN_NAME vmla
+#define TEST_MSG "VMLA"
+#endif
+
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+#define DECL_VMLX(T, W, N)			\
+  DECL_VARIABLE(vector1, T, W, N);		\
+  DECL_VARIABLE(vector2, T, W, N);		\
+  DECL_VARIABLE(vector3, T, W, N);		\
+  DECL_VARIABLE(vector_res, T, W, N)
+
+  /* vector_res = OP(vector, vector3, vector4),
+     then store the result.  */
+#define TEST_VMLX1(INSN, Q, T1, T2, W, N)				\
+  VECT_VAR(vector_res, T1, W, N) =                                      \
+    INSN##Q##_##T2##W(VECT_VAR(vector1, T1, W, N),			\
+		      VECT_VAR(vector2, T1, W, N),			\
+		      VECT_VAR(vector3, T1, W, N));			\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),                         \
+		    VECT_VAR(vector_res, T1, W, N))
+
+#define TEST_VMLX(INSN, Q, T1, T2, W, N)	\
+  TEST_VMLX1(INSN, Q, T1, T2, W, N)
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VMLX(int, 8, 8);
+  DECL_VMLX(int, 16, 4);
+  DECL_VMLX(int, 32, 2);
+  DECL_VMLX(uint, 8, 8);
+  DECL_VMLX(uint, 16, 4);
+  DECL_VMLX(uint, 32, 2);
+  DECL_VMLX(float, 32, 2);
+  DECL_VMLX(int, 8, 16);
+  DECL_VMLX(int, 16, 8);
+  DECL_VMLX(int, 32, 4);
+  DECL_VMLX(uint, 8, 16);
+  DECL_VMLX(uint, 16, 8);
+  DECL_VMLX(uint, 32, 4);
+  DECL_VMLX(float, 32, 4);
+
+  clean_results ();
+
+  VLOAD(vector1, buffer, , int, s, 8, 8);
+  VLOAD(vector1, buffer, , int, s, 16, 4);
+  VLOAD(vector1, buffer, , int, s, 32, 2);
+  VLOAD(vector1, buffer, , uint, u, 8, 8);
+  VLOAD(vector1, buffer, , uint, u, 16, 4);
+  VLOAD(vector1, buffer, , uint, u, 32, 2);
+  VLOAD(vector1, buffer, , float, f, 32, 2);
+  VLOAD(vector1, buffer, q, int, s, 8, 16);
+  VLOAD(vector1, buffer, q, int, s, 16, 8);
+  VLOAD(vector1, buffer, q, int, s, 32, 4);
+  VLOAD(vector1, buffer, q, uint, u, 8, 16);
+  VLOAD(vector1, buffer, q, uint, u, 16, 8);
+  VLOAD(vector1, buffer, q, uint, u, 32, 4);
+  VLOAD(vector1, buffer, q, float, f, 32, 4);
+
+  VDUP(vector2, , int, s, 8, 8, 0x11);
+  VDUP(vector2, , int, s, 16, 4, 0x22);
+  VDUP(vector2, , int, s, 32, 2, 0x33);
+  VDUP(vector2, , uint, u, 8, 8, 0x44);
+  VDUP(vector2, , uint, u, 16, 4, 0x55);
+  VDUP(vector2, , uint, u, 32, 2, 0x66);
+  VDUP(vector2, , float, f, 32, 2, 33.1f);
+  VDUP(vector2, q, int, s, 8, 16, 0x77);
+  VDUP(vector2, q, int, s, 16, 8, 0x88);
+  VDUP(vector2, q, int, s, 32, 4, 0x99);
+  VDUP(vector2, q, uint, u, 8, 16, 0xAA);
+  VDUP(vector2, q, uint, u, 16, 8, 0xBB);
+  VDUP(vector2, q, uint, u, 32, 4, 0xCC);
+  VDUP(vector2, q, float, f, 32, 4, 99.2f);
+
+  VDUP(vector3, , int, s, 8, 8, 0xFF);
+  VDUP(vector3, , int, s, 16, 4, 0xEE);
+  VDUP(vector3, , int, s, 32, 2, 0xDD);
+  VDUP(vector3, , uint, u, 8, 8, 0xCC);
+  VDUP(vector3, , uint, u, 16, 4, 0xBB);
+  VDUP(vector3, , uint, u, 32, 2, 0xAA);
+  VDUP(vector3, , float, f, 32, 2, 10.23f);
+  VDUP(vector3, q, int, s, 8, 16, 0x99);
+  VDUP(vector3, q, int, s, 16, 8, 0x88);
+  VDUP(vector3, q, int, s, 32, 4, 0x77);
+  VDUP(vector3, q, uint, u, 8, 16, 0x66);
+  VDUP(vector3, q, uint, u, 16, 8, 0x55);
+  VDUP(vector3, q, uint, u, 32, 4, 0x44);
+  VDUP(vector3, q, float, f, 32, 4, 77.8f);
+
+  TEST_VMLX(INSN_NAME, , int, s, 8, 8);
+  TEST_VMLX(INSN_NAME, , int, s, 16, 4);
+  TEST_VMLX(INSN_NAME, , int, s, 32, 2);
+  TEST_VMLX(INSN_NAME, , uint, u, 8, 8);
+  TEST_VMLX(INSN_NAME, , uint, u, 16, 4);
+  TEST_VMLX(INSN_NAME, , uint, u, 32, 2);
+  TEST_VMLX(INSN_NAME, , float, f, 32, 2);
+  TEST_VMLX(INSN_NAME, q, int, s, 8, 16);
+  TEST_VMLX(INSN_NAME, q, int, s, 16, 8);
+  TEST_VMLX(INSN_NAME, q, int, s, 32, 4);
+  TEST_VMLX(INSN_NAME, q, uint, u, 8, 16);
+  TEST_VMLX(INSN_NAME, q, uint, u, 16, 8);
+  TEST_VMLX(INSN_NAME, q, uint, u, 32, 4);
+  TEST_VMLX(INSN_NAME, q, float, f, 32, 4);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vmla_lane.c b/ref_vmla_lane.c
new file mode 100644
index 0000000..290710c
--- /dev/null
+++ b/ref_vmla_lane.c
@@ -0,0 +1,125 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#ifndef INSN_NAME
+#define INSN_NAME vmla
+#define TEST_MSG "VMLA_LANE"
+#endif
+
+#define FNNAME1(NAME) void exec_ ## NAME ##_lane (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+#define DECL_VMLX_LANE(VAR)			\
+  DECL_VARIABLE(VAR, int, 16, 4);		\
+  DECL_VARIABLE(VAR, int, 32, 2);		\
+  DECL_VARIABLE(VAR, uint, 16, 4);		\
+  DECL_VARIABLE(VAR, uint, 32, 2);		\
+  DECL_VARIABLE(VAR, float, 32, 2);		\
+  DECL_VARIABLE(VAR, int, 16, 8);		\
+  DECL_VARIABLE(VAR, int, 32, 4);		\
+  DECL_VARIABLE(VAR, uint, 16, 8);		\
+  DECL_VARIABLE(VAR, uint, 32, 4);		\
+  DECL_VARIABLE(VAR, float, 32, 4)
+
+  /* vector_res = vmlx_lane(vector, vector2, vector3, lane),
+     then store the result.  */
+#define TEST_VMLX_LANE1(INSN, Q, T1, T2, W, N, N2, L)			\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    INSN##Q##_lane_##T2##W(VECT_VAR(vector, T1, W, N),			\
+			   VECT_VAR(vector2, T1, W, N),			\
+			   VECT_VAR(vector3, T1, W, N2),		\
+			   L);						\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), \
+		    VECT_VAR(vector_res, T1, W, N))
+
+#define TEST_VMLX_LANE(INSN, Q, T1, T2, W, N, N2, V)	\
+  TEST_VMLX_LANE1(INSN, Q, T1, T2, W, N, N2, V)
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VMLX_LANE(vector);
+  DECL_VMLX_LANE(vector2);
+  DECL_VMLX_LANE(vector_res);
+
+  DECL_VARIABLE(vector3, int, 16, 4);
+  DECL_VARIABLE(vector3, int, 32, 2);
+  DECL_VARIABLE(vector3, uint, 16, 4);
+  DECL_VARIABLE(vector3, uint, 32, 2);
+  DECL_VARIABLE(vector3, float, 32, 2);
+
+  clean_results ();
+
+  VLOAD(vector, buffer, , int, s, 16, 4);
+  VLOAD(vector, buffer, , int, s, 32, 2);
+  VLOAD(vector, buffer, , uint, u, 16, 4);
+  VLOAD(vector, buffer, , uint, u, 32, 2);
+  VLOAD(vector, buffer, q, int, s, 16, 8);
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+  VLOAD(vector, buffer, q, uint, u, 16, 8);
+  VLOAD(vector, buffer, q, uint, u, 32, 4);
+  VLOAD(vector, buffer, , float, f, 32, 2);
+  VLOAD(vector, buffer, q, float, f, 32, 4);
+
+  VDUP(vector2, , int, s, 16, 4, 0x55);
+  VDUP(vector2, , int, s, 32, 2, 0x55);
+  VDUP(vector2, , uint, u, 16, 4, 0x55);
+  VDUP(vector2, , uint, u, 32, 2, 0x55);
+  VDUP(vector2, , float, f, 32, 2, 55.3f);
+  VDUP(vector2, q, int, s, 16, 8, 0x55);
+  VDUP(vector2, q, int, s, 32, 4, 0x55);
+  VDUP(vector2, q, uint, u, 16, 8, 0x55);
+  VDUP(vector2, q, uint, u, 32, 4, 0x55);
+  VDUP(vector2, q, float, f, 32, 4, 55.8f);
+
+  VDUP(vector3, , int, s, 16, 4, 0xBB);
+  VDUP(vector3, , int, s, 32, 2, 0xBB);
+  VDUP(vector3, , uint, u, 16, 4, 0xBB);
+  VDUP(vector3, , uint, u, 32, 2, 0xBB);
+  VDUP(vector3, , float, f, 32, 2, 11.34f);
+
+  /* Choose lane arbitrarily */
+  TEST_VMLX_LANE(INSN_NAME, , int, s, 16, 4, 4, 2);
+  TEST_VMLX_LANE(INSN_NAME, , int, s, 32, 2, 2, 1);
+  TEST_VMLX_LANE(INSN_NAME, , uint, u, 16, 4, 4, 2);
+  TEST_VMLX_LANE(INSN_NAME, , uint, u, 32, 2, 2, 1);
+  TEST_VMLX_LANE(INSN_NAME, , float, f, 32, 2, 2, 1);
+  TEST_VMLX_LANE(INSN_NAME, q, int, s, 16, 8, 4, 3);
+  TEST_VMLX_LANE(INSN_NAME, q, int, s, 32, 4, 2, 1);
+  TEST_VMLX_LANE(INSN_NAME, q, uint, u, 16, 8, 4, 2);
+  TEST_VMLX_LANE(INSN_NAME, q, uint, u, 32, 4, 2, 1);
+  TEST_VMLX_LANE(INSN_NAME, q, float, f, 32, 4, 2, 1);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vmla_n.c b/ref_vmla_n.c
new file mode 100644
index 0000000..9b9384f
--- /dev/null
+++ b/ref_vmla_n.c
@@ -0,0 +1,112 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#ifndef INSN_NAME
+#define INSN_NAME vmla
+#define TEST_MSG "VMLA_N"
+#endif
+
+#define FNNAME1(NAME) void exec_ ## NAME ##_n (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+#define DECL_VMLX_N(VAR)			\
+  DECL_VARIABLE(VAR, int, 16, 4);		\
+  DECL_VARIABLE(VAR, int, 32, 2);		\
+  DECL_VARIABLE(VAR, uint, 16, 4);		\
+  DECL_VARIABLE(VAR, uint, 32, 2);		\
+  DECL_VARIABLE(VAR, float, 32, 2);		\
+  DECL_VARIABLE(VAR, int, 16, 8);		\
+  DECL_VARIABLE(VAR, int, 32, 4);		\
+  DECL_VARIABLE(VAR, uint, 16, 8);		\
+  DECL_VARIABLE(VAR, float, 32, 4);		\
+  DECL_VARIABLE(VAR, uint, 32, 4)
+
+  /* vector_res = vmlx_n(vector, vector2, val),
+     then store the result.  */
+#define TEST_VMLX_N1(INSN, Q, T1, T2, W, N, V)          \
+  VECT_VAR(vector_res, T1, W, N) =                      \
+    INSN##Q##_n_##T2##W(VECT_VAR(vector, T1, W, N),     \
+			VECT_VAR(vector2, T1, W, N),    \
+			V);                             \
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),         \
+		    VECT_VAR(vector_res, T1, W, N))
+
+#define TEST_VMLX_N(INSN, Q, T1, T2, W, N, V)	\
+  TEST_VMLX_N1(INSN, Q, T1, T2, W, N, V)
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VMLX_N(vector);
+  DECL_VMLX_N(vector2);
+  DECL_VMLX_N(vector_res);
+
+  clean_results ();
+
+  VLOAD(vector, buffer, , int, s, 16, 4);
+  VLOAD(vector, buffer, , int, s, 32, 2);
+  VLOAD(vector, buffer, , uint, u, 16, 4);
+  VLOAD(vector, buffer, , uint, u, 32, 2);
+  VLOAD(vector, buffer, , float, f, 32, 2);
+  VLOAD(vector, buffer, q, int, s, 16, 8);
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+  VLOAD(vector, buffer, q, uint, u, 16, 8);
+  VLOAD(vector, buffer, q, uint, u, 32, 4);
+  VLOAD(vector, buffer, q, float, f, 32, 4);
+
+  VDUP(vector2, , int, s, 16, 4, 0x55);
+  VDUP(vector2, , int, s, 32, 2, 0x55);
+  VDUP(vector2, , uint, u, 16, 4, 0x55);
+  VDUP(vector2, , uint, u, 32, 2, 0x55);
+  VDUP(vector2, , float, f, 32, 2, 55.2f);
+  VDUP(vector2, q, int, s, 16, 8, 0x55);
+  VDUP(vector2, q, int, s, 32, 4, 0x55);
+  VDUP(vector2, q, uint, u, 16, 8, 0x55);
+  VDUP(vector2, q, uint, u, 32, 4, 0x55);
+  VDUP(vector2, q, float, f, 32, 4, 55.9f);
+
+  /* Choose multiplier arbitrarily */
+  TEST_VMLX_N(INSN_NAME, , int, s, 16, 4, 0x11);
+  TEST_VMLX_N(INSN_NAME, , int, s, 32, 2, 0x22);
+  TEST_VMLX_N(INSN_NAME, , uint, u, 16, 4, 0x33);
+  TEST_VMLX_N(INSN_NAME, , uint, u, 32, 2, 0x44);
+  TEST_VMLX_N(INSN_NAME, , float, f, 32, 2, 22.3f);
+  TEST_VMLX_N(INSN_NAME, q, int, s, 16, 8, 0x55);
+  TEST_VMLX_N(INSN_NAME, q, int, s, 32, 4, 0x66);
+  TEST_VMLX_N(INSN_NAME, q, uint, u, 16, 8, 0x77);
+  TEST_VMLX_N(INSN_NAME, q, uint, u, 32, 4, 0x88);
+  TEST_VMLX_N(INSN_NAME, q, float, f, 32, 4, 66.7f);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vmlal.c b/ref_vmlal.c
new file mode 100644
index 0000000..bf0b03b
--- /dev/null
+++ b/ref_vmlal.c
@@ -0,0 +1,119 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#ifndef INSN_NAME
+#define INSN_NAME vmlal
+#define TEST_MSG "VMLAL"
+#endif
+
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* vector_res = OP(vector, vector3, vector4),
+     then store the result.  */
+#define TEST_VMLXL1(INSN, T1, T2, W, W2, N)				\
+  VECT_VAR(vector_res, T1, W, N) =                                      \
+    INSN##_##T2##W2(VECT_VAR(vector, T1, W, N),                         \
+                    VECT_VAR(vector3, T1, W2, N),                       \
+                    VECT_VAR(vector4, T1, W2, N));                      \
+  vst1q_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+#define TEST_VMLXL(INSN, T1, T2, W, W2, N)	\
+  TEST_VMLXL1(INSN, T1, T2, W, W2, N)
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector3, int, 8, 8);
+  DECL_VARIABLE(vector4, int, 8, 8);
+  DECL_VARIABLE(vector_res, int, 16, 8);
+
+  DECL_VARIABLE(vector, int, 32, 4);
+  DECL_VARIABLE(vector3, int, 16, 4);
+  DECL_VARIABLE(vector4, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+
+  DECL_VARIABLE(vector, int, 64, 2);
+  DECL_VARIABLE(vector3, int, 32, 2);
+  DECL_VARIABLE(vector4, int, 32, 2);
+  DECL_VARIABLE(vector_res, int, 64, 2);
+
+  DECL_VARIABLE(vector, uint, 16, 8);
+  DECL_VARIABLE(vector3, uint, 8, 8);
+  DECL_VARIABLE(vector4, uint, 8, 8);
+  DECL_VARIABLE(vector_res, uint, 16, 8);
+
+  DECL_VARIABLE(vector, uint, 32, 4);
+  DECL_VARIABLE(vector3, uint, 16, 4);
+  DECL_VARIABLE(vector4, uint, 16, 4);
+  DECL_VARIABLE(vector_res, uint, 32, 4);
+
+  DECL_VARIABLE(vector, uint, 64, 2);
+  DECL_VARIABLE(vector3, uint, 32, 2);
+  DECL_VARIABLE(vector4, uint, 32, 2);
+  DECL_VARIABLE(vector_res, uint, 64, 2);
+
+  clean_results ();
+
+  VLOAD(vector, buffer, q, int, s, 16, 8);
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+  VLOAD(vector, buffer, q, int, s, 64, 2);
+  VLOAD(vector, buffer, q, uint, u, 16, 8);
+  VLOAD(vector, buffer, q, uint, u, 32, 4);
+  VLOAD(vector, buffer, q, uint, u, 64, 2);
+
+  VDUP(vector3, , int, s, 8, 8, 0x55);
+  VDUP(vector4, , int, s, 8, 8, 0xBB);
+  VDUP(vector3, , int, s, 16, 4, 0x55);
+  VDUP(vector4, , int, s, 16, 4, 0xBB);
+  VDUP(vector3, , int, s, 32, 2, 0x55);
+  VDUP(vector4, , int, s, 32, 2, 0xBB);
+  VDUP(vector3, , uint, u, 8, 8, 0x55);
+  VDUP(vector4, , uint, u, 8, 8, 0xBB);
+  VDUP(vector3, , uint, u, 16, 4, 0x55);
+  VDUP(vector4, , uint, u, 16, 4, 0xBB);
+  VDUP(vector3, , uint, u, 32, 2, 0x55);
+  VDUP(vector4, , uint, u, 32, 2, 0xBB);
+
+  TEST_VMLXL(INSN_NAME, int, s, 16, 8, 8);
+  TEST_VMLXL(INSN_NAME, int, s, 32, 16, 4);
+  TEST_VMLXL(INSN_NAME, int, s, 64, 32, 2);
+  TEST_VMLXL(INSN_NAME, uint, u, 16, 8, 8);
+  TEST_VMLXL(INSN_NAME, uint, u, 32, 16, 4);
+  TEST_VMLXL(INSN_NAME, uint, u, 64, 32, 2);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vmlal_lane.c b/ref_vmlal_lane.c
new file mode 100644
index 0000000..c276fa8
--- /dev/null
+++ b/ref_vmlal_lane.c
@@ -0,0 +1,101 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#ifndef INSN_NAME
+#define INSN_NAME vmlal_lane
+#define TEST_MSG "VMLAL_LANE"
+#endif
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* vector_res = vmlxl_lane(vector, vector3, vector4, lane),
+     then store the result.  */
+#define TEST_VMLXL_LANE1(INSN, T1, T2, W, W2, N, V)			\
+  VECT_VAR(vector_res, T1, W, N) =                                      \
+    INSN##_##T2##W2(VECT_VAR(vector, T1, W, N),                         \
+                    VECT_VAR(vector3, T1, W2, N),                       \
+                    VECT_VAR(vector4, T1, W2, N),                       \
+                    V);                                                 \
+  vst1q_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+#define TEST_VMLXL_LANE(INSN, T1, T2, W, W2, N, V)			\
+  TEST_VMLXL_LANE1(INSN, T1, T2, W, W2, N, V)
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE(vector, int, 32, 4);
+  DECL_VARIABLE(vector3, int, 16, 4);
+  DECL_VARIABLE(vector4, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+
+  DECL_VARIABLE(vector, int, 64, 2);
+  DECL_VARIABLE(vector3, int, 32, 2);
+  DECL_VARIABLE(vector4, int, 32, 2);
+  DECL_VARIABLE(vector_res, int, 64, 2);
+
+  DECL_VARIABLE(vector, uint, 32, 4);
+  DECL_VARIABLE(vector3, uint, 16, 4);
+  DECL_VARIABLE(vector4, uint, 16, 4);
+  DECL_VARIABLE(vector_res, uint, 32, 4);
+
+  DECL_VARIABLE(vector, uint, 64, 2);
+  DECL_VARIABLE(vector3, uint, 32, 2);
+  DECL_VARIABLE(vector4, uint, 32, 2);
+  DECL_VARIABLE(vector_res, uint, 64, 2);
+
+  clean_results ();
+
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+  VLOAD(vector, buffer, q, int, s, 64, 2);
+  VLOAD(vector, buffer, q, uint, u, 32, 4);
+  VLOAD(vector, buffer, q, uint, u, 64, 2);
+
+  VDUP(vector3, , int, s, 16, 4, 0x55);
+  VDUP(vector4, , int, s, 16, 4, 0xBB);
+  VDUP(vector3, , int, s, 32, 2, 0x55);
+  VDUP(vector4, , int, s, 32, 2, 0xBB);
+  VDUP(vector3, , uint, u, 16, 4, 0x55);
+  VDUP(vector4, , uint, u, 16, 4, 0xBB);
+  VDUP(vector3, , uint, u, 32, 2, 0x55);
+  VDUP(vector4, , uint, u, 32, 2, 0xBB);
+
+  TEST_VMLXL_LANE(INSN_NAME, int, s, 32, 16, 4, 2);
+  TEST_VMLXL_LANE(INSN_NAME, int, s, 64, 32, 2, 1);
+  TEST_VMLXL_LANE(INSN_NAME, uint, u, 32, 16, 4, 2);
+  TEST_VMLXL_LANE(INSN_NAME, uint, u, 64, 32, 2, 1);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vmlal_n.c b/ref_vmlal_n.c
new file mode 100644
index 0000000..45979c7
--- /dev/null
+++ b/ref_vmlal_n.c
@@ -0,0 +1,92 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#ifndef INSN_NAME
+#define INSN_NAME vmlal_n
+#define TEST_MSG "VMLAL_N"
+#endif
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* vector_res = vmlxl_n(vector, vector2, val),
+     then store the result.  */
+#define TEST_VMLXL_N1(INSN, T1, T2, W, W2, N, V)			\
+  VECT_VAR(vector_res, T1, W, N) = INSN##_##T2##W2(VECT_VAR(vector, T1, W, N), \
+						   VECT_VAR(vector2, T1, W2, N), \
+						   V);			\
+  vst1q_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+#define TEST_VMLXL_N(INSN, T1, T2, W, W2, N, V)			\
+  TEST_VMLXL_N1(INSN, T1, T2, W, W2, N, V)
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE(vector, int, 32, 4);
+  DECL_VARIABLE(vector2, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+
+  DECL_VARIABLE(vector, int, 64, 2);
+  DECL_VARIABLE(vector2, int, 32, 2);
+  DECL_VARIABLE(vector_res, int, 64, 2);
+
+  DECL_VARIABLE(vector, uint, 32, 4);
+  DECL_VARIABLE(vector2, uint, 16, 4);
+  DECL_VARIABLE(vector_res, uint, 32, 4);
+
+  DECL_VARIABLE(vector, uint, 64, 2);
+  DECL_VARIABLE(vector2, uint, 32, 2);
+  DECL_VARIABLE(vector_res, uint, 64, 2);
+
+  clean_results ();
+
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+  VLOAD(vector, buffer, q, int, s, 64, 2);
+  VLOAD(vector, buffer, q, uint, u, 32, 4);
+  VLOAD(vector, buffer, q, uint, u, 64, 2);
+
+  VDUP(vector2, , int, s, 16, 4, 0x55);
+  VDUP(vector2, , int, s, 32, 2, 0x55);
+  VDUP(vector2, , uint, u, 16, 4, 0x55);
+  VDUP(vector2, , uint, u, 32, 2, 0x55);
+
+  /* Choose multiplier arbitrarily */
+  TEST_VMLXL_N(INSN_NAME, int, s, 32, 16, 4, 0x11);
+  TEST_VMLXL_N(INSN_NAME, int, s, 64, 32, 2, 0x22);
+  TEST_VMLXL_N(INSN_NAME, uint, u, 32, 16, 4, 0x33);
+  TEST_VMLXL_N(INSN_NAME, uint, u, 64, 32, 2, 0x33);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vmls.c b/ref_vmls.c
new file mode 100644
index 0000000..9eacdb2
--- /dev/null
+++ b/ref_vmls.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vmls
+#define TEST_MSG "VMLS"
+
+#include "ref_vmla.c"
diff --git a/ref_vmls_lane.c b/ref_vmls_lane.c
new file mode 100644
index 0000000..68cce02
--- /dev/null
+++ b/ref_vmls_lane.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vmls
+#define TEST_MSG "VMLS_LANE"
+
+#include "ref_vmla_lane.c"
diff --git a/ref_vmls_n.c b/ref_vmls_n.c
new file mode 100644
index 0000000..050a4b9
--- /dev/null
+++ b/ref_vmls_n.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vmls
+#define TEST_MSG "VMLS_N"
+
+#include "ref_vmla_n.c"
diff --git a/ref_vmlsl.c b/ref_vmlsl.c
new file mode 100644
index 0000000..22b11aa
--- /dev/null
+++ b/ref_vmlsl.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vmlsl
+#define TEST_MSG "VMLSL"
+
+#include "ref_vmlal.c"
diff --git a/ref_vmlsl_lane.c b/ref_vmlsl_lane.c
new file mode 100644
index 0000000..a972b93
--- /dev/null
+++ b/ref_vmlsl_lane.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vmlsl_lane
+#define TEST_MSG "VMLSL_LANE"
+
+#include "ref_vmlal_lane.c"
diff --git a/ref_vmlsl_n.c b/ref_vmlsl_n.c
new file mode 100644
index 0000000..b7f7000
--- /dev/null
+++ b/ref_vmlsl_n.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vmlsl_n
+#define TEST_MSG "VMLSL_N"
+
+#include "ref_vmlal_n.c"
diff --git a/ref_vmovl.c b/ref_vmovl.c
new file mode 100644
index 0000000..af48791
--- /dev/null
+++ b/ref_vmovl.c
@@ -0,0 +1,60 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VMOVL"
+void exec_vmovl (void)
+{
+  /* Basic test: vec128=vmovl(vec64), then store the result.  */
+#define TEST_VMOVL(T1, T2, W, W2, N)					\
+  VECT_VAR(vector128, T1, W2, N) =					\
+    vmovl_##T2##W(VECT_VAR(vector64, T1, W, N));			\
+  vst1q_##T2##W2(VECT_VAR(result, T1, W2, N), VECT_VAR(vector128, T1, W2, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_64BITS_VARIANTS(vector64);
+  DECL_VARIABLE_128BITS_VARIANTS(vector128);
+
+  TEST_MACRO_64BITS_VARIANTS_2_5(VLOAD, vector64, buffer);
+
+  clean_results ();
+
+  TEST_VMOVL(int, s, 8, 16, 8);
+  TEST_VMOVL(int, s, 16, 32, 4);
+  TEST_VMOVL(int, s, 32, 64, 2);
+  TEST_VMOVL(uint, u, 8, 16, 8);
+  TEST_VMOVL(uint, u, 16, 32, 4);
+  TEST_VMOVL(uint, u, 32, 64, 2);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vmovn.c b/ref_vmovn.c
new file mode 100644
index 0000000..24aa0af
--- /dev/null
+++ b/ref_vmovn.c
@@ -0,0 +1,60 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VMOVN"
+void exec_vmovn (void)
+{
+  /* Basic test: vec64=vmovn(vec128), then store the result.  */
+#define TEST_VMOVN(T1, T2, W, W2, N)					\
+  VECT_VAR(vector64, T1, W2, N) =					\
+    vmovn_##T2##W(VECT_VAR(vector128, T1, W, N));			\
+  vst1_##T2##W2(VECT_VAR(result, T1, W2, N), VECT_VAR(vector64, T1, W2, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_64BITS_VARIANTS(vector64);
+  DECL_VARIABLE_128BITS_VARIANTS(vector128);
+
+  TEST_MACRO_128BITS_VARIANTS_2_5(VLOAD, vector128, buffer);
+
+  clean_results ();
+
+  TEST_VMOVN(int, s, 16, 8, 8);
+  TEST_VMOVN(int, s, 32, 16, 4);
+  TEST_VMOVN(int, s, 64, 32, 2);
+  TEST_VMOVN(uint, u, 16, 8, 8);
+  TEST_VMOVN(uint, u, 32, 16, 4);
+  TEST_VMOVN(uint, u, 64, 32, 2);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vmul.c b/ref_vmul.c
new file mode 100644
index 0000000..c7b1814
--- /dev/null
+++ b/ref_vmul.c
@@ -0,0 +1,134 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#ifndef INSN_NAME
+#define INSN_NAME vmul
+#define TEST_MSG "VMUL"
+#endif
+
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+#define DECL_VMUL(T, W, N)			\
+  DECL_VARIABLE(vector1, T, W, N);		\
+  DECL_VARIABLE(vector2, T, W, N);		\
+  DECL_VARIABLE(vector_res, T, W, N)
+
+  /* vector_res = OP(vector1, vector2), then store the result.  */
+#define TEST_VMUL1(INSN, Q, T1, T2, W, N)				\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    INSN##Q##_##T2##W(VECT_VAR(vector1, T1, W, N),			\
+		      VECT_VAR(vector2, T1, W, N));			\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),				\
+		    VECT_VAR(vector_res, T1, W, N))
+
+#define TEST_VMUL(INSN, Q, T1, T2, W, N)	\
+  TEST_VMUL1(INSN, Q, T1, T2, W, N)
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VMUL(int, 8, 8);
+  DECL_VMUL(int, 16, 4);
+  DECL_VMUL(int, 32, 2);
+  DECL_VMUL(uint, 8, 8);
+  DECL_VMUL(uint, 16, 4);
+  DECL_VMUL(uint, 32, 2);
+  DECL_VMUL(poly, 8, 8);
+  DECL_VMUL(float, 32, 2);
+  DECL_VMUL(int, 8, 16);
+  DECL_VMUL(int, 16, 8);
+  DECL_VMUL(int, 32, 4);
+  DECL_VMUL(uint, 8, 16);
+  DECL_VMUL(uint, 16, 8);
+  DECL_VMUL(uint, 32, 4);
+  DECL_VMUL(poly, 8, 16);
+  DECL_VMUL(float, 32, 4);
+
+  clean_results ();
+
+  VLOAD(vector1, buffer, , int, s, 8, 8);
+  VLOAD(vector1, buffer, , int, s, 16, 4);
+  VLOAD(vector1, buffer, , int, s, 32, 2);
+  VLOAD(vector1, buffer, , uint, u, 8, 8);
+  VLOAD(vector1, buffer, , uint, u, 16, 4);
+  VLOAD(vector1, buffer, , uint, u, 32, 2);
+  VLOAD(vector1, buffer, , poly, p, 8, 8);
+  VLOAD(vector1, buffer, , float, f, 32, 2);
+  VLOAD(vector1, buffer, q, int, s, 8, 16);
+  VLOAD(vector1, buffer, q, int, s, 16, 8);
+  VLOAD(vector1, buffer, q, int, s, 32, 4);
+  VLOAD(vector1, buffer, q, uint, u, 8, 16);
+  VLOAD(vector1, buffer, q, uint, u, 16, 8);
+  VLOAD(vector1, buffer, q, uint, u, 32, 4);
+  VLOAD(vector1, buffer, q, poly, p, 8, 16);
+  VLOAD(vector1, buffer, q, float, f, 32, 4);
+
+  VDUP(vector2, , int, s, 8, 8, 0x11);
+  VDUP(vector2, , int, s, 16, 4, 0x22);
+  VDUP(vector2, , int, s, 32, 2, 0x33);
+  VDUP(vector2, , uint, u, 8, 8, 0x44);
+  VDUP(vector2, , uint, u, 16, 4, 0x55);
+  VDUP(vector2, , uint, u, 32, 2, 0x66);
+  VDUP(vector2, , poly, p, 8, 8, 0x44);
+  VDUP(vector2, , float, f, 32, 2, 33.3f);
+  VDUP(vector2, q, int, s, 8, 16, 0x77);
+  VDUP(vector2, q, int, s, 16, 8, 0x88);
+  VDUP(vector2, q, int, s, 32, 4, 0x99);
+  VDUP(vector2, q, uint, u, 8, 16, 0xAA);
+  VDUP(vector2, q, uint, u, 16, 8, 0xBB);
+  VDUP(vector2, q, uint, u, 32, 4, 0xCC);
+  VDUP(vector2, q, poly, p, 8, 16, 0xAA);
+  VDUP(vector2, q, float, f, 32, 4, 99.6f);
+
+  TEST_VMUL(INSN_NAME, , int, s, 8, 8);
+  TEST_VMUL(INSN_NAME, , int, s, 16, 4);
+  TEST_VMUL(INSN_NAME, , int, s, 32, 2);
+  TEST_VMUL(INSN_NAME, , uint, u, 8, 8);
+  TEST_VMUL(INSN_NAME, , uint, u, 16, 4);
+  TEST_VMUL(INSN_NAME, , uint, u, 32, 2);
+  TEST_VMUL(INSN_NAME, , poly, p, 8, 8);
+  TEST_VMUL(INSN_NAME, , float, f, 32, 2);
+  TEST_VMUL(INSN_NAME, q, int, s, 8, 16);
+  TEST_VMUL(INSN_NAME, q, int, s, 16, 8);
+  TEST_VMUL(INSN_NAME, q, int, s, 32, 4);
+  TEST_VMUL(INSN_NAME, q, uint, u, 8, 16);
+  TEST_VMUL(INSN_NAME, q, uint, u, 16, 8);
+  TEST_VMUL(INSN_NAME, q, uint, u, 32, 4);
+  TEST_VMUL(INSN_NAME, q, poly, p, 8, 16);
+  TEST_VMUL(INSN_NAME, q, float, f, 32, 4);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vmul_lane.c b/ref_vmul_lane.c
new file mode 100644
index 0000000..f67d68e
--- /dev/null
+++ b/ref_vmul_lane.c
@@ -0,0 +1,105 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VMUL_LANE"
+void exec_vmul_lane (void)
+{
+#define DECL_VMUL(VAR)				\
+  DECL_VARIABLE(VAR, int, 16, 4);		\
+  DECL_VARIABLE(VAR, int, 32, 2);		\
+  DECL_VARIABLE(VAR, uint, 16, 4);		\
+  DECL_VARIABLE(VAR, uint, 32, 2);		\
+  DECL_VARIABLE(VAR, float, 32, 2);		\
+  DECL_VARIABLE(VAR, int, 16, 8);		\
+  DECL_VARIABLE(VAR, int, 32, 4);		\
+  DECL_VARIABLE(VAR, uint, 16, 8);		\
+  DECL_VARIABLE(VAR, uint, 32, 4);		\
+  DECL_VARIABLE(VAR, float, 32, 4)
+
+  /* vector_res = vmul_lane(vector,vector2,lane), then store the result.  */
+#define TEST_VMUL_LANE(Q, T1, T2, W, N, N2, L)				\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vmul##Q##_lane_##T2##W(VECT_VAR(vector, T1, W, N),			\
+			   VECT_VAR(vector2, T1, W, N2),		\
+			   L);						\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),				\
+		    VECT_VAR(vector_res, T1, W, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VMUL(vector);
+  DECL_VMUL(vector_res);
+
+  DECL_VARIABLE(vector2, int, 16, 4);
+  DECL_VARIABLE(vector2, int, 32, 2);
+  DECL_VARIABLE(vector2, uint, 16, 4);
+  DECL_VARIABLE(vector2, uint, 32, 2);
+  DECL_VARIABLE(vector2, float, 32, 2);
+
+  clean_results ();
+
+  /* Initialize vector from pre-initialized values  */
+  VLOAD(vector, buffer, , int, s, 16, 4);
+  VLOAD(vector, buffer, , int, s, 32, 2);
+  VLOAD(vector, buffer, , uint, u, 16, 4);
+  VLOAD(vector, buffer, , uint, u, 32, 2);
+  VLOAD(vector, buffer, , float, f, 32, 2);
+  VLOAD(vector, buffer, q, int, s, 16, 8);
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+  VLOAD(vector, buffer, q, uint, u, 16, 8);
+  VLOAD(vector, buffer, q, uint, u, 32, 4);
+  VLOAD(vector, buffer, q, float, f, 32, 4);
+
+  /* Initialize vector2 */
+  VDUP(vector2, , int, s, 16, 4, 0x4);
+  VDUP(vector2, , int, s, 32, 2, 0x22);
+  VDUP(vector2, , uint, u, 16, 4, 0x444);
+  VDUP(vector2, , uint, u, 32, 2, 0x532);
+  VDUP(vector2, , float, f, 32, 2, 22.8f);
+
+  /* Choose lane arbitrarily */
+  TEST_VMUL_LANE(, int, s, 16, 4, 4, 2);
+  TEST_VMUL_LANE(, int, s, 32, 2, 2, 1);
+  TEST_VMUL_LANE(, uint, u, 16, 4, 4, 2);
+  TEST_VMUL_LANE(, uint, u, 32, 2, 2, 1);
+  TEST_VMUL_LANE(, float, f, 32, 2, 2, 1);
+  TEST_VMUL_LANE(q, int, s, 16, 8, 4, 2);
+  TEST_VMUL_LANE(q, int, s, 32, 4, 2, 0);
+  TEST_VMUL_LANE(q, uint, u, 16, 8, 4, 2);
+  TEST_VMUL_LANE(q, uint, u, 32, 4, 2, 1);
+  TEST_VMUL_LANE(q, float, f, 32, 4, 2, 0);
+
+  /* FIXME: only a subset of the result buffers are used, but we
+     output all of them */
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vmul_n.c b/ref_vmul_n.c
new file mode 100644
index 0000000..1128377
--- /dev/null
+++ b/ref_vmul_n.c
@@ -0,0 +1,91 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VMUL_N"
+void exec_vmul_n (void)
+{
+#define DECL_VMUL(VAR)				\
+  DECL_VARIABLE(VAR, int, 16, 4);		\
+  DECL_VARIABLE(VAR, int, 32, 2);		\
+  DECL_VARIABLE(VAR, uint, 16, 4);		\
+  DECL_VARIABLE(VAR, uint, 32, 2);		\
+  DECL_VARIABLE(VAR, float, 32, 2);		\
+  DECL_VARIABLE(VAR, int, 16, 8);		\
+  DECL_VARIABLE(VAR, int, 32, 4);		\
+  DECL_VARIABLE(VAR, uint, 16, 8);		\
+  DECL_VARIABLE(VAR, uint, 32, 4);		\
+  DECL_VARIABLE(VAR, float, 32, 4)
+
+  /* vector_res = vmul_n(vector,val), then store the result.  */
+#define TEST_VMUL_N(Q, T1, T2, W, N, L)					\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vmul##Q##_n_##T2##W(VECT_VAR(vector, T1, W, N),			\
+			L);						\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),				\
+		    VECT_VAR(vector_res, T1, W, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VMUL(vector);
+  DECL_VMUL(vector_res);
+
+  clean_results ();
+
+  /* Initialize vector from pre-initialized values  */
+  VLOAD(vector, buffer, , int, s, 16, 4);
+  VLOAD(vector, buffer, , int, s, 32, 2);
+  VLOAD(vector, buffer, , uint, u, 16, 4);
+  VLOAD(vector, buffer, , uint, u, 32, 2);
+  VLOAD(vector, buffer, , float, f, 32, 2);
+  VLOAD(vector, buffer, q, int, s, 16, 8);
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+  VLOAD(vector, buffer, q, uint, u, 16, 8);
+  VLOAD(vector, buffer, q, uint, u, 32, 4);
+  VLOAD(vector, buffer, q, float, f, 32, 4);
+
+  /* Choose multiplier arbitrarily */
+  TEST_VMUL_N(, int, s, 16, 4, 0x11);
+  TEST_VMUL_N(, int, s, 32, 2, 0x22);
+  TEST_VMUL_N(, uint, u, 16, 4, 0x33);
+  TEST_VMUL_N(, uint, u, 32, 2, 0x44);
+  TEST_VMUL_N(, float, f, 32, 2, 22.3f);
+  TEST_VMUL_N(q, int, s, 16, 8, 0x55);
+  TEST_VMUL_N(q, int, s, 32, 4, 0x66);
+  TEST_VMUL_N(q, uint, u, 16, 8, 0x77);
+  TEST_VMUL_N(q, uint, u, 32, 4, 0x88);
+  TEST_VMUL_N(q, float, f, 32, 4, 88.9f);
+
+  /* FIXME: only a subset of the result buffers are used, but we
+     output all of them */
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vmull.c b/ref_vmull.c
new file mode 100644
index 0000000..6fc5be6
--- /dev/null
+++ b/ref_vmull.c
@@ -0,0 +1,81 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VMULL"
+void exec_vmull (void)
+{
+  /* Basic test: y=vmull(x,x), then store the result.  */
+#define TEST_VMULL(T1, T2, W, W2, N)					\
+  VECT_VAR(vector_res, T1, W2, N) =					\
+    vmull_##T2##W(VECT_VAR(vector, T1, W, N),				\
+		  VECT_VAR(vector, T1, W, N));				\
+  vst1q_##T2##W2(VECT_VAR(result, T1, W2, N), VECT_VAR(vector_res, T1, W2, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE(vector, int, 8, 8);
+  DECL_VARIABLE(vector, int, 16, 4);
+  DECL_VARIABLE(vector, int, 32, 2);
+  DECL_VARIABLE(vector, uint, 8, 8);
+  DECL_VARIABLE(vector, uint, 16, 4);
+  DECL_VARIABLE(vector, uint, 32, 2);
+  DECL_VARIABLE(vector, poly, 8, 8);
+  DECL_VARIABLE(vector_res, int, 16, 8);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+  DECL_VARIABLE(vector_res, int, 64, 2);
+  DECL_VARIABLE(vector_res, uint, 16, 8);
+  DECL_VARIABLE(vector_res, uint, 32, 4);
+  DECL_VARIABLE(vector_res, uint, 64, 2);
+  DECL_VARIABLE(vector_res, poly, 16, 8);
+
+  clean_results ();
+
+  VLOAD(vector, buffer, , int, s, 8, 8);
+  VLOAD(vector, buffer, , int, s, 16, 4);
+  VLOAD(vector, buffer, , int, s, 32, 2);
+  VLOAD(vector, buffer, , uint, u, 8, 8);
+  VLOAD(vector, buffer, , uint, u, 16, 4);
+  VLOAD(vector, buffer, , uint, u, 32, 2);
+  VLOAD(vector, buffer, , poly, p, 8, 8);
+
+  TEST_VMULL(int, s, 8, 16, 8);
+  TEST_VMULL(int, s, 16, 32, 4);
+  TEST_VMULL(int, s, 32, 64, 2);
+  TEST_VMULL(uint, u, 8, 16, 8);
+  TEST_VMULL(uint, u, 16, 32, 4);
+  TEST_VMULL(uint, u, 32, 64, 2);
+  TEST_VMULL(poly, p, 8, 16, 8);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vmull_lane.c b/ref_vmull_lane.c
new file mode 100644
index 0000000..769abc6
--- /dev/null
+++ b/ref_vmull_lane.c
@@ -0,0 +1,84 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VMULL_LANE"
+void exec_vmull_lane (void)
+{
+  /* vector_res = vmull_lane(vector,vector2,lane), then store the result.  */
+#define TEST_VMULL_LANE(T1, T2, W, W2, N, L)				\
+  VECT_VAR(vector_res, T1, W2, N) =					\
+    vmull##_lane_##T2##W(VECT_VAR(vector, T1, W, N),			\
+			 VECT_VAR(vector2, T1, W, N),			\
+			 L);						\
+  vst1q_##T2##W2(VECT_VAR(result, T1, W2, N), VECT_VAR(vector_res, T1, W2, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE(vector, int, 16, 4);
+  DECL_VARIABLE(vector, int, 32, 2);
+  DECL_VARIABLE(vector, uint, 16, 4);
+  DECL_VARIABLE(vector, uint, 32, 2);
+  DECL_VARIABLE(vector2, int, 16, 4);
+  DECL_VARIABLE(vector2, int, 32, 2);
+  DECL_VARIABLE(vector2, uint, 16, 4);
+  DECL_VARIABLE(vector2, uint, 32, 2);
+
+  DECL_VARIABLE(vector_res, int, 32, 4);
+  DECL_VARIABLE(vector_res, int, 64, 2);
+  DECL_VARIABLE(vector_res, uint, 32, 4);
+  DECL_VARIABLE(vector_res, uint, 64, 2);
+
+  clean_results ();
+
+  /* Initialize vector */
+  VDUP(vector, , int, s, 16, 4, 0x1000);
+  VDUP(vector, , int, s, 32, 2, 0x1000);
+  VDUP(vector, , uint, u, 16, 4, 0x1000);
+  VDUP(vector, , uint, u, 32, 2, 0x1000);
+
+  /* Initialize vector2 */
+  VDUP(vector2, , int, s, 16, 4, 0x4);
+  VDUP(vector2, , int, s, 32, 2, 0x2);
+  VDUP(vector2, , uint, u, 16, 4, 0x4);
+  VDUP(vector2, , uint, u, 32, 2, 0x2);
+
+  /* Choose lane arbitrarily */
+  TEST_VMULL_LANE(int, s, 16, 32, 4, 2);
+  TEST_VMULL_LANE(int, s, 32, 64, 2, 1);
+  TEST_VMULL_LANE(uint, u, 16, 32, 4, 2);
+  TEST_VMULL_LANE(uint, u, 32, 64, 2, 1);
+
+  /* FIXME: only a subset of the result buffers are used, but we
+     output all of them */
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vmull_n.c b/ref_vmull_n.c
new file mode 100644
index 0000000..200280e
--- /dev/null
+++ b/ref_vmull_n.c
@@ -0,0 +1,82 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN_NAME vmull
+#define TEST_MSG "VMULL_N"
+void exec_vmull_n (void)
+{
+  int i;
+
+  /* vector_res = vmull_n(vector,val), then store the result.  */
+#define TEST_VMULL_N1(INSN, T1, T2, W, W2, N, L)			\
+  VECT_VAR(vector_res, T1, W2, N) =					\
+    INSN##_n_##T2##W(VECT_VAR(vector, T1, W, N),			\
+		     L);						\
+  vst1q_##T2##W2(VECT_VAR(result, T1, W2, N), VECT_VAR(vector_res, T1, W2, N))
+
+#define TEST_VMULL_N(INSN, T1, T2, W, W2, N, L)	\
+  TEST_VMULL_N1(INSN, T1, T2, W, W2, N, L)
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE(vector, int, 16, 4);
+  DECL_VARIABLE(vector, int, 32, 2);
+  DECL_VARIABLE(vector, uint, 16, 4);
+  DECL_VARIABLE(vector, uint, 32, 2);
+
+  DECL_VARIABLE(vector_res, int, 32, 4);
+  DECL_VARIABLE(vector_res, int, 64, 2);
+  DECL_VARIABLE(vector_res, uint, 32, 4);
+  DECL_VARIABLE(vector_res, uint, 64, 2);
+
+  clean_results ();
+
+  /* Initialize vector */
+  VDUP(vector, , int, s, 16, 4, 0x1000);
+  VDUP(vector, , int, s, 32, 2, 0x1000);
+  VDUP(vector, , uint, u, 16, 4, 0x1000);
+  VDUP(vector, , uint, u, 32, 2, 0x1000);
+
+  /* Choose multiplier arbitrarily */
+  TEST_VMULL_N(INSN_NAME, int, s, 16, 32, 4, 0x11);
+  TEST_VMULL_N(INSN_NAME, int, s, 32, 64, 2, 0x22);
+  TEST_VMULL_N(INSN_NAME, uint, u, 16, 32, 4, 0x33);
+  TEST_VMULL_N(INSN_NAME, uint, u, 32, 64, 2, 0x44);
+
+  fprintf(ref_file, "\n%s output:\n", TEST_MSG);
+  fprintf(gcc_tests_file, "\n%s output:\n", TEST_MSG);
+  DUMP(TEST_MSG, int, 32, 4, PRIx32);
+  DUMP(TEST_MSG, int, 64, 2, PRIx64);
+  DUMP(TEST_MSG, uint, 32, 4, PRIx32);
+  DUMP(TEST_MSG, uint, 64, 2, PRIx64);
+}
diff --git a/ref_vmvn.c b/ref_vmvn.c
new file mode 100644
index 0000000..5ea6a33
--- /dev/null
+++ b/ref_vmvn.c
@@ -0,0 +1,120 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN_NAME vmvn
+#define TEST_MSG "VMVN/VMVNQ"
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* Basic test: y=OP(x), then store the result.  */
+#define TEST_UNARY_OP1(INSN, Q, T1, T2, W, N)				\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    INSN##Q##_##T2##W(VECT_VAR(vector, T1, W, N));			\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+#define TEST_UNARY_OP(INSN, Q, T1, T2, W, N)				\
+  TEST_UNARY_OP1(INSN, Q, T1, T2, W, N)					\
+
+    /* With ARM RVCT, we need to declare variables before any executable
+       statement  */
+
+  /* No need for 64 bits variants */
+  DECL_VARIABLE(vector, int, 8, 8);
+  DECL_VARIABLE(vector, int, 16, 4);
+  DECL_VARIABLE(vector, int, 32, 2);
+  DECL_VARIABLE(vector, uint, 8, 8);
+  DECL_VARIABLE(vector, uint, 16, 4);
+  DECL_VARIABLE(vector, uint, 32, 2);
+  DECL_VARIABLE(vector, poly, 8, 8);
+  DECL_VARIABLE(vector, int, 8, 16);
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+  DECL_VARIABLE(vector, uint, 8, 16);
+  DECL_VARIABLE(vector, uint, 16, 8);
+  DECL_VARIABLE(vector, uint, 32, 4);
+  DECL_VARIABLE(vector, poly, 8, 16);
+
+  DECL_VARIABLE(vector_res, int, 8, 8);
+  DECL_VARIABLE(vector_res, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 2);
+  DECL_VARIABLE(vector_res, uint, 8, 8);
+  DECL_VARIABLE(vector_res, uint, 16, 4);
+  DECL_VARIABLE(vector_res, uint, 32, 2);
+  DECL_VARIABLE(vector_res, poly, 8, 8);
+  DECL_VARIABLE(vector_res, int, 8, 16);
+  DECL_VARIABLE(vector_res, int, 16, 8);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+  DECL_VARIABLE(vector_res, uint, 8, 16);
+  DECL_VARIABLE(vector_res, uint, 16, 8);
+  DECL_VARIABLE(vector_res, uint, 32, 4);
+  DECL_VARIABLE(vector_res, poly, 8, 16);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  VLOAD(vector, buffer, , int, s, 8, 8);
+  VLOAD(vector, buffer, , int, s, 16, 4);
+  VLOAD(vector, buffer, , int, s, 32, 2);
+  VLOAD(vector, buffer, , uint, u, 8, 8);
+  VLOAD(vector, buffer, , uint, u, 16, 4);
+  VLOAD(vector, buffer, , uint, u, 32, 2);
+  VLOAD(vector, buffer, , poly, p, 8, 8);
+  VLOAD(vector, buffer, q, int, s, 8, 16);
+  VLOAD(vector, buffer, q, int, s, 16, 8);
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+  VLOAD(vector, buffer, q, uint, u, 8, 16);
+  VLOAD(vector, buffer, q, uint, u, 16, 8);
+  VLOAD(vector, buffer, q, uint, u, 32, 4);
+  VLOAD(vector, buffer, q, poly, p, 8, 16);
+
+  /* Apply a unary operator named INSN_NAME  */
+  TEST_UNARY_OP(INSN_NAME, , int, s, 8, 8);
+  TEST_UNARY_OP(INSN_NAME, , int, s, 16, 4);
+  TEST_UNARY_OP(INSN_NAME, , int, s, 32, 2);
+  TEST_UNARY_OP(INSN_NAME, , uint, u, 8, 8);
+  TEST_UNARY_OP(INSN_NAME, , uint, u, 16, 4);
+  TEST_UNARY_OP(INSN_NAME, , uint, u, 32, 2);
+  TEST_UNARY_OP(INSN_NAME, , poly, p, 8, 8);
+  TEST_UNARY_OP(INSN_NAME, q, int, s, 8, 16);
+  TEST_UNARY_OP(INSN_NAME, q, int, s, 16, 8);
+  TEST_UNARY_OP(INSN_NAME, q, int, s, 32, 4);
+  TEST_UNARY_OP(INSN_NAME, q, uint, u, 8, 16);
+  TEST_UNARY_OP(INSN_NAME, q, uint, u, 16, 8);
+  TEST_UNARY_OP(INSN_NAME, q, uint, u, 32, 4);
+  TEST_UNARY_OP(INSN_NAME, q, poly, p, 8, 16);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vneg.c b/ref_vneg.c
new file mode 100644
index 0000000..1eabe20
--- /dev/null
+++ b/ref_vneg.c
@@ -0,0 +1,54 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vneg
+#define TEST_MSG "VNEG/VNEGQ"
+
+/* Extra tests for functions requiring floating-point types */
+void exec_vneg_f32(void);
+#define EXTRA_TESTS exec_vneg_f32
+
+#include "ref_v_unary_op.c"
+
+void exec_vneg_f32(void)
+{
+  int i;
+
+  DECL_VARIABLE(vector, float, 32, 2);
+  DECL_VARIABLE(vector, float, 32, 4);
+
+  DECL_VARIABLE(vector_res, float, 32, 2);
+  DECL_VARIABLE(vector_res, float, 32, 4);
+
+  VDUP(vector, , float, f, 32, 2, 2.3f);
+  VDUP(vector, q, float, f, 32, 4, 3.4f);
+
+  TEST_UNARY_OP(INSN_NAME, , float, f, 32, 2);
+  TEST_UNARY_OP(INSN_NAME, q, float, f, 32, 4);
+
+  fprintf(ref_file, "\nfloat32:\n");
+  DUMP_FP(TEST_MSG, float, 32, 2, PRIx32);
+  DUMP_FP(TEST_MSG, float, 32, 4, PRIx32);
+}
diff --git a/ref_vorn.c b/ref_vorn.c
new file mode 100644
index 0000000..df9823e
--- /dev/null
+++ b/ref_vorn.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vorn
+#define TEST_MSG "VORN/VORNQ"
+
+#include "ref_v_binary_op.c"
diff --git a/ref_vorr.c b/ref_vorr.c
new file mode 100644
index 0000000..0762e10
--- /dev/null
+++ b/ref_vorr.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vorr
+#define TEST_MSG "VORR/VORRQ"
+
+#include "ref_v_binary_op.c"
diff --git a/ref_vpadal.c b/ref_vpadal.c
new file mode 100644
index 0000000..fab5f05
--- /dev/null
+++ b/ref_vpadal.c
@@ -0,0 +1,140 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN_NAME vpadal
+#define TEST_MSG "VPADAL/VPADALQ"
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* Basic test: y=OP(x), then store the result.  */
+#define TEST_VPADAL1(INSN, Q, T1, T2, W, N, W2, N2)			\
+  VECT_VAR(vector_res, T1, W2, N2) =					\
+    INSN##Q##_##T2##W(VECT_VAR(vector, T1, W2, N2), VECT_VAR(vector2, T1, W, N)); \
+  vst1##Q##_##T2##W2(VECT_VAR(result, T1, W2, N2),			\
+		     VECT_VAR(vector_res, T1, W2, N2))
+
+#define TEST_VPADAL(INSN, Q, T1, T2, W, N, W2, N2)	\
+  TEST_VPADAL1(INSN, Q, T1, T2, W, N, W2, N2)
+
+    /* With ARM RVCT, we need to declare variables before any executable
+       statement  */
+
+  /* No need for 64 bits variants */
+  DECL_VARIABLE(vector, int, 16, 4);
+  DECL_VARIABLE(vector, int, 32, 2);
+  DECL_VARIABLE(vector, int, 64, 1);
+  DECL_VARIABLE(vector, uint, 16, 4);
+  DECL_VARIABLE(vector, uint, 32, 2);
+  DECL_VARIABLE(vector, uint, 64, 1);
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+  DECL_VARIABLE(vector, int, 64, 2);
+  DECL_VARIABLE(vector, uint, 16, 8);
+  DECL_VARIABLE(vector, uint, 32, 4);
+  DECL_VARIABLE(vector, uint, 64, 2);
+
+  DECL_VARIABLE(vector2, int, 8, 8);
+  DECL_VARIABLE(vector2, int, 16, 4);
+  DECL_VARIABLE(vector2, int, 32, 2);
+  DECL_VARIABLE(vector2, uint, 8, 8);
+  DECL_VARIABLE(vector2, uint, 16, 4);
+  DECL_VARIABLE(vector2, uint, 32, 2);
+  DECL_VARIABLE(vector2, int, 8, 16);
+  DECL_VARIABLE(vector2, int, 16, 8);
+  DECL_VARIABLE(vector2, int, 32, 4);
+  DECL_VARIABLE(vector2, uint, 8, 16);
+  DECL_VARIABLE(vector2, uint, 16, 8);
+  DECL_VARIABLE(vector2, uint, 32, 4);
+
+  DECL_VARIABLE(vector_res, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 2);
+  DECL_VARIABLE(vector_res, int, 64, 1);
+  DECL_VARIABLE(vector_res, uint, 16, 4);
+  DECL_VARIABLE(vector_res, uint, 32, 2);
+  DECL_VARIABLE(vector_res, uint, 64, 1);
+  DECL_VARIABLE(vector_res, int, 16, 8);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+  DECL_VARIABLE(vector_res, int, 64, 2);
+  DECL_VARIABLE(vector_res, uint, 16, 8);
+  DECL_VARIABLE(vector_res, uint, 32, 4);
+  DECL_VARIABLE(vector_res, uint, 64, 2);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  VLOAD(vector, buffer, , int, s, 16, 4);
+  VLOAD(vector, buffer, , int, s, 32, 2);
+  VLOAD(vector, buffer, , int, s, 64, 1);
+  VLOAD(vector, buffer, , uint, u, 16, 4);
+  VLOAD(vector, buffer, , uint, u, 32, 2);
+  VLOAD(vector, buffer, , uint, u, 64, 1);
+  VLOAD(vector, buffer, q, int, s, 16, 8);
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+  VLOAD(vector, buffer, q, int, s, 64, 2);
+  VLOAD(vector, buffer, q, uint, u, 16, 8);
+  VLOAD(vector, buffer, q, uint, u, 32, 4);
+  VLOAD(vector, buffer, q, uint, u, 64, 2);
+
+  /* Initialize input "vector2" from "buffer"  */
+  VLOAD(vector2, buffer, , int, s, 8, 8);
+  VLOAD(vector2, buffer, , int, s, 16, 4);
+  VLOAD(vector2, buffer, , int, s, 32, 2);
+  VLOAD(vector2, buffer, , uint, u, 8, 8);
+  VLOAD(vector2, buffer, , uint, u, 16, 4);
+  VLOAD(vector2, buffer, , uint, u, 32, 2);
+  VLOAD(vector2, buffer, q, int, s, 8, 16);
+  VLOAD(vector2, buffer, q, int, s, 16, 8);
+  VLOAD(vector2, buffer, q, int, s, 32, 4);
+  VLOAD(vector2, buffer, q, uint, u, 8, 16);
+  VLOAD(vector2, buffer, q, uint, u, 16, 8);
+  VLOAD(vector2, buffer, q, uint, u, 32, 4);
+
+  /* Apply a unary operator named INSN_NAME  */
+  TEST_VPADAL(INSN_NAME, , int, s, 8, 8, 16, 4);
+  TEST_VPADAL(INSN_NAME, , int, s, 16, 4, 32, 2);
+  TEST_VPADAL(INSN_NAME, , int, s, 32, 2, 64 ,1);
+  TEST_VPADAL(INSN_NAME, , uint, u, 8, 8, 16, 4);
+  TEST_VPADAL(INSN_NAME, , uint, u, 16, 4, 32, 2);
+  TEST_VPADAL(INSN_NAME, , uint, u, 32, 2, 64, 1);
+  TEST_VPADAL(INSN_NAME, q, int, s, 8, 16, 16, 8);
+  TEST_VPADAL(INSN_NAME, q, int, s, 16, 8, 32, 4);
+  TEST_VPADAL(INSN_NAME, q, int, s, 32, 4, 64 ,2);
+  TEST_VPADAL(INSN_NAME, q, uint, u, 8, 16, 16, 8);
+  TEST_VPADAL(INSN_NAME, q, uint, u, 16, 8, 32, 4);
+  TEST_VPADAL(INSN_NAME, q, uint, u, 32, 4, 64, 2);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vpadd.c b/ref_vpadd.c
new file mode 100644
index 0000000..09f8f5c
--- /dev/null
+++ b/ref_vpadd.c
@@ -0,0 +1,96 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#ifndef INSN_NAME
+#define INSN_NAME vpadd
+#define TEST_MSG "VPADD"
+#endif
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* Basic test: y=OP(x), then store the result.  */
+#define TEST_VPADD1(INSN, T1, T2, W, N)					\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    INSN##_##T2##W(VECT_VAR(vector, T1, W, N),				\
+		   VECT_VAR(vector, T1, W, N));				\
+  vst1##_##T2##W(VECT_VAR(result, T1, W, N),				\
+		 VECT_VAR(vector_res, T1, W, N))
+
+#define TEST_VPADD(INSN, T1, T2, W, N)		\
+  TEST_VPADD1(INSN, T1, T2, W, N)		\
+
+    /* With ARM RVCT, we need to declare variables before any executable
+       statement  */
+
+  /* No need for 64 bits variants */
+  DECL_VARIABLE(vector, int, 8, 8);
+  DECL_VARIABLE(vector, int, 16, 4);
+  DECL_VARIABLE(vector, int, 32, 2);
+  DECL_VARIABLE(vector, uint, 8, 8);
+  DECL_VARIABLE(vector, uint, 16, 4);
+  DECL_VARIABLE(vector, uint, 32, 2);
+  DECL_VARIABLE(vector, float, 32, 2);
+
+  DECL_VARIABLE(vector_res, int, 8, 8);
+  DECL_VARIABLE(vector_res, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 2);
+  DECL_VARIABLE(vector_res, uint, 8, 8);
+  DECL_VARIABLE(vector_res, uint, 16, 4);
+  DECL_VARIABLE(vector_res, uint, 32, 2);
+  DECL_VARIABLE(vector_res, float, 32, 2);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  VLOAD(vector, buffer, , int, s, 8, 8);
+  VLOAD(vector, buffer, , int, s, 16, 4);
+  VLOAD(vector, buffer, , int, s, 32, 2);
+  VLOAD(vector, buffer, , uint, u, 8, 8);
+  VLOAD(vector, buffer, , uint, u, 16, 4);
+  VLOAD(vector, buffer, , uint, u, 32, 2);
+  VLOAD(vector, buffer, , float, f, 32, 2);
+
+  /* Apply a binary operator named INSN_NAME  */
+  TEST_VPADD(INSN_NAME, int, s, 8, 8);
+  TEST_VPADD(INSN_NAME, int, s, 16, 4);
+  TEST_VPADD(INSN_NAME, int, s, 32, 2);
+  TEST_VPADD(INSN_NAME, uint, u, 8, 8);
+  TEST_VPADD(INSN_NAME, uint, u, 16, 4);
+  TEST_VPADD(INSN_NAME, uint, u, 32, 2);
+  TEST_VPADD(INSN_NAME, float, f, 32, 2);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vpaddl.c b/ref_vpaddl.c
new file mode 100644
index 0000000..e3a4c5b
--- /dev/null
+++ b/ref_vpaddl.c
@@ -0,0 +1,113 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN_NAME vpaddl
+#define TEST_MSG "VPADDL/VPADDLQ"
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* Basic test: y=OP(x), then store the result.  */
+#define TEST_VPADDL1(INSN, Q, T1, T2, W, N, W2, N2)	\
+  VECT_VAR(vector_res, T1, W2, N2) =			\
+    INSN##Q##_##T2##W(VECT_VAR(vector, T1, W, N));	\
+  vst1##Q##_##T2##W2(VECT_VAR(result, T1, W2, N2),	\
+		    VECT_VAR(vector_res, T1, W2, N2))
+
+#define TEST_VPADDL(INSN, Q, T1, T2, W, N, W2, N2)	\
+  TEST_VPADDL1(INSN, Q, T1, T2, W, N, W2, N2)
+
+    /* With ARM RVCT, we need to declare variables before any executable
+       statement  */
+
+  /* No need for 64 bits variants */
+  DECL_VARIABLE(vector, int, 8, 8);
+  DECL_VARIABLE(vector, int, 16, 4);
+  DECL_VARIABLE(vector, int, 32, 2);
+  DECL_VARIABLE(vector, uint, 8, 8);
+  DECL_VARIABLE(vector, uint, 16, 4);
+  DECL_VARIABLE(vector, uint, 32, 2);
+  DECL_VARIABLE(vector, int, 8, 16);
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+  DECL_VARIABLE(vector, uint, 8, 16);
+  DECL_VARIABLE(vector, uint, 16, 8);
+  DECL_VARIABLE(vector, uint, 32, 4);
+
+  DECL_VARIABLE(vector_res, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 2);
+  DECL_VARIABLE(vector_res, int, 64, 1);
+  DECL_VARIABLE(vector_res, uint, 16, 4);
+  DECL_VARIABLE(vector_res, uint, 32, 2);
+  DECL_VARIABLE(vector_res, uint, 64, 1);
+  DECL_VARIABLE(vector_res, int, 16, 8);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+  DECL_VARIABLE(vector_res, int, 64, 2);
+  DECL_VARIABLE(vector_res, uint, 16, 8);
+  DECL_VARIABLE(vector_res, uint, 32, 4);
+  DECL_VARIABLE(vector_res, uint, 64, 2);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  VLOAD(vector, buffer, , int, s, 8, 8);
+  VLOAD(vector, buffer, , int, s, 16, 4);
+  VLOAD(vector, buffer, , int, s, 32, 2);
+  VLOAD(vector, buffer, , uint, u, 8, 8);
+  VLOAD(vector, buffer, , uint, u, 16, 4);
+  VLOAD(vector, buffer, , uint, u, 32, 2);
+  VLOAD(vector, buffer, q, int, s, 8, 16);
+  VLOAD(vector, buffer, q, int, s, 16, 8);
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+  VLOAD(vector, buffer, q, uint, u, 8, 16);
+  VLOAD(vector, buffer, q, uint, u, 16, 8);
+  VLOAD(vector, buffer, q, uint, u, 32, 4);
+
+  /* Apply a unary operator named INSN_NAME  */
+  TEST_VPADDL(INSN_NAME, , int, s, 8, 8, 16, 4);
+  TEST_VPADDL(INSN_NAME, , int, s, 16, 4, 32, 2);
+  TEST_VPADDL(INSN_NAME, , int, s, 32, 2, 64, 1);
+  TEST_VPADDL(INSN_NAME, , uint, u, 8, 8, 16, 4);
+  TEST_VPADDL(INSN_NAME, , uint, u, 16, 4, 32, 2);
+  TEST_VPADDL(INSN_NAME, , uint, u, 32, 2, 64, 1);
+  TEST_VPADDL(INSN_NAME, q, int, s, 8, 16, 16, 8);
+  TEST_VPADDL(INSN_NAME, q, int, s, 16, 8, 32, 4);
+  TEST_VPADDL(INSN_NAME, q, int, s, 32, 4, 64, 2);
+  TEST_VPADDL(INSN_NAME, q, uint, u, 8, 16, 16, 8);
+  TEST_VPADDL(INSN_NAME, q, uint, u, 16, 8, 32, 4);
+  TEST_VPADDL(INSN_NAME, q, uint, u, 32, 4, 64, 2);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vpmax.c b/ref_vpmax.c
new file mode 100644
index 0000000..bac8d20
--- /dev/null
+++ b/ref_vpmax.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vpmax
+#define TEST_MSG "VPMAX"
+
+#include "ref_vpadd.c"
diff --git a/ref_vpmin.c b/ref_vpmin.c
new file mode 100644
index 0000000..cf0a044
--- /dev/null
+++ b/ref_vpmin.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vpmin
+#define TEST_MSG "VPMIN"
+
+#include "ref_vpadd.c"
diff --git a/ref_vqabs.c b/ref_vqabs.c
new file mode 100644
index 0000000..e0ef53f
--- /dev/null
+++ b/ref_vqabs.c
@@ -0,0 +1,73 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vqabs
+#define TEST_MSG "VQABS/VQABSQ"
+
+/* Extra tests for functions requiring corner cases tests */
+void vqabs_extra(void);
+#define EXTRA_TESTS vqabs_extra
+
+#include "ref_v_unary_sat_op.c"
+
+void vqabs_extra()
+{
+  /* No need for 64 bits variants */
+  DECL_VARIABLE(vector, int, 8, 8);
+  DECL_VARIABLE(vector, int, 16, 4);
+  DECL_VARIABLE(vector, int, 32, 2);
+  DECL_VARIABLE(vector, int, 8, 16);
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+
+  DECL_VARIABLE(vector_res, int, 8, 8);
+  DECL_VARIABLE(vector_res, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 2);
+  DECL_VARIABLE(vector_res, int, 8, 16);
+  DECL_VARIABLE(vector_res, int, 16, 8);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+
+  clean_results ();
+
+  /* Initialize input "vector" with max negative values to check
+     saturation  */
+  VDUP(vector, , int, s, 8, 8, 0x80);
+  VDUP(vector, , int, s, 16, 4, 0x8000);
+  VDUP(vector, , int, s, 32, 2, 0x80000000);
+  VDUP(vector, q, int, s, 8, 16, 0x80);
+  VDUP(vector, q, int, s, 16, 8, 0x8000);
+  VDUP(vector, q, int, s, 32, 4, 0x80000000);
+
+  /* Apply a unary operator named INSN_NAME  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_UNARY_SAT_OP(INSN_NAME, , int, s, 8, 8);
+  TEST_UNARY_SAT_OP(INSN_NAME, , int, s, 16, 4);
+  TEST_UNARY_SAT_OP(INSN_NAME, , int, s, 32, 2);
+  TEST_UNARY_SAT_OP(INSN_NAME, q, int, s, 8, 16);
+  TEST_UNARY_SAT_OP(INSN_NAME, q, int, s, 16, 8);
+  TEST_UNARY_SAT_OP(INSN_NAME, q, int, s, 32, 4);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vqadd.c b/ref_vqadd.c
new file mode 100644
index 0000000..6bf70bd
--- /dev/null
+++ b/ref_vqadd.c
@@ -0,0 +1,157 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vqadd
+#define TEST_MSG "VQADD/VQADDQ"
+
+/* Extra tests for functions requiring types larger than 64 bits to
+   compute saturation */
+void vqadd_64(void);
+#define EXTRA_TESTS vqadd_64
+
+#include "ref_v_binary_sat_op.c"
+
+void vqadd_64(void)
+{
+  int i;
+
+  DECL_VARIABLE_ALL_VARIANTS(vector1);
+  DECL_VARIABLE_ALL_VARIANTS(vector2);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+  /* Initialize input "vector1" from "buffer"  */
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector1, buffer);
+
+  VDUP(vector2, , int, s, 64, 1, 0x0);
+  VDUP(vector2, , uint, u, 64, 1, 0x0);
+  VDUP(vector2, q, int, s, 64, 2, 0x0);
+  VDUP(vector2, q, uint, u, 64, 2, 0x0);
+
+  fprintf(ref_file,
+	  "\n%s 64 bits saturation cumulative saturation output:\n", TEST_MSG);
+  TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 64, 1);
+  TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 64, 1);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 64, 2);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 64, 2);
+
+  fprintf(ref_file, "\n64 bits saturation:\n");
+  DUMP(TEST_MSG, int, 64, 1, PRIx64);
+  DUMP(TEST_MSG, uint, 64, 1, PRIx64);
+  DUMP(TEST_MSG, int, 64, 2, PRIx64);
+  DUMP(TEST_MSG, uint, 64, 2, PRIx64);
+
+  /* Another set of tests */
+  VDUP(vector2, , int, s, 64, 1, 0x44);
+  VDUP(vector2, , uint, u, 64, 1, 0x88);
+  VDUP(vector2, q, int, s, 64, 2, 0x44);
+  VDUP(vector2, q, uint, u, 64, 2, 0x88);
+
+  fprintf(ref_file,
+	  "\n%s 64 bits saturation cumulative saturation output:\n", TEST_MSG);
+  TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 64, 1);
+  TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 64, 1);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 64, 2);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 64, 2);
+
+  DUMP(TEST_MSG, int, 64, 1, PRIx64);
+  DUMP(TEST_MSG, uint, 64, 1, PRIx64);
+  DUMP(TEST_MSG, int, 64, 2, PRIx64);
+  DUMP(TEST_MSG, uint, 64, 2, PRIx64);
+
+  /* Another set of tests */
+  VDUP(vector2, , int, s, 64, 1, 0x8000000000000003LL);
+  VDUP(vector2, , uint, u, 64, 1, 0x88);
+
+  VDUP(vector1, q, int, s, 64, 2, 0x4000000000000000LL);
+  VDUP(vector2, q, int, s, 64, 2, 0x4000000000000000LL);
+
+  VDUP(vector2, q, uint, u, 64, 2, 0x22);
+
+  fprintf(ref_file,
+	  "\n%s 64 bits saturation cumulative saturation output:\n", TEST_MSG);
+  TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 64, 1);
+  TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 64, 1);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 64, 2);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 64, 2);
+
+  DUMP(TEST_MSG, int, 64, 1, PRIx64);
+  DUMP(TEST_MSG, uint, 64, 1, PRIx64);
+  DUMP(TEST_MSG, int, 64, 2, PRIx64);
+  DUMP(TEST_MSG, uint, 64, 2, PRIx64);
+
+  /* To improve coverage, check saturation with less than 64 bits too */
+  VDUP(vector2, , int, s, 8, 8, 0x81);
+  VDUP(vector2, , int, s, 16, 4, 0x8001);
+  VDUP(vector2, , int, s, 32, 2, 0x80000001);
+  VDUP(vector2, q, int, s, 8, 16, 0x81);
+  VDUP(vector2, q, int, s, 16, 8, 0x8001);
+  VDUP(vector2, q, int, s, 32, 4, 0x80000001);
+
+  fprintf(ref_file, "\nless than 64 bits saturation:\n");
+  TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 8, 8);
+  TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 16, 4);
+  TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 32, 2);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 8, 16);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 16, 8);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 32, 4);
+
+  DUMP(TEST_MSG, int, 8, 8, PRIx8);
+  DUMP(TEST_MSG, int, 16, 4, PRIx16);
+  DUMP(TEST_MSG, int, 32, 2, PRIx32);
+  DUMP(TEST_MSG, int, 8, 16, PRIx8);
+  DUMP(TEST_MSG, int, 16, 8, PRIx16);
+  DUMP(TEST_MSG, int, 32, 4, PRIx32);
+
+  VDUP(vector1, , uint, u, 8, 8, 0xF0);
+  VDUP(vector1, , uint, u, 16, 4, 0xFFF0);
+  VDUP(vector1, , uint, u, 32, 2, 0xFFFFFFF0);
+  VDUP(vector1, q, uint, u, 8, 16, 0xF0);
+  VDUP(vector1, q, uint, u, 16, 8, 0xFFF0);
+  VDUP(vector1, q, uint, u, 32, 4, 0xFFFFFFF0);
+
+  VDUP(vector2, , uint, u, 8, 8, 0x20);
+  VDUP(vector2, , uint, u, 16, 4, 0x20);
+  VDUP(vector2, , uint, u, 32, 2, 0x20);
+  VDUP(vector2, q, uint, u, 8, 16, 0x20);
+  VDUP(vector2, q, uint, u, 16, 8, 0x20);
+  VDUP(vector2, q, uint, u, 32, 4, 0x20);
+
+  fprintf(ref_file,
+	  "\n%s less than 64 bits saturation cumulative saturation output:\n",
+	  TEST_MSG);
+  TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 8, 8);
+  TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 16, 4);
+  TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 32, 2);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 8, 16);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 16, 8);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 32, 4);
+
+  DUMP(TEST_MSG, uint, 8, 8, PRIx8);
+  DUMP(TEST_MSG, uint, 16, 4, PRIx16);
+  DUMP(TEST_MSG, uint, 32, 2, PRIx32);
+  DUMP(TEST_MSG, uint, 8, 16, PRIx8);
+  DUMP(TEST_MSG, uint, 16, 8, PRIx16);
+  DUMP(TEST_MSG, uint, 32, 4, PRIx32);
+}
diff --git a/ref_vqdmlal.c b/ref_vqdmlal.c
new file mode 100644
index 0000000..59c3672
--- /dev/null
+++ b/ref_vqdmlal.c
@@ -0,0 +1,98 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2012 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#ifndef INSN_NAME
+#define INSN_NAME vqdmlal
+#define TEST_MSG "VQDMLAL"
+#endif
+
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* vector_res = OP(vector, vector3, vector4),
+     then store the result.  */
+#define TEST_VQDMLXL1(INSN, T1, T2, W, W2, N)			\
+  Set_Neon_Cumulative_Sat(0, VECT_VAR(vector_res, T1, W, N));	\
+  VECT_VAR(vector_res, T1, W, N) =				\
+    INSN##_##T2##W2(VECT_VAR(vector, T1, W, N),			\
+		    VECT_VAR(vector3, T1, W2, N),		\
+		    VECT_VAR(vector4, T1, W2, N));		\
+  vst1q_##T2##W(VECT_VAR(result, T1, W, N),			\
+		VECT_VAR(vector_res, T1, W, N));		\
+  dump_neon_cumulative_sat(TEST_MSG, xSTR(INSN##_##T2##W2),	\
+			   xSTR(T1), W, N)
+
+#define TEST_VQDMLXL(INSN, T1, T2, W, W2, N)	\
+  TEST_VQDMLXL1(INSN, T1, T2, W, W2, N)
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE(vector, int, 32, 4);
+  DECL_VARIABLE(vector3, int, 16, 4);
+  DECL_VARIABLE(vector4, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+  DECL_VARIABLE(vector, int, 64, 2);
+  DECL_VARIABLE(vector3, int, 32, 2);
+  DECL_VARIABLE(vector4, int, 32, 2);
+  DECL_VARIABLE(vector_res, int, 64, 2);
+
+  clean_results ();
+
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+  VLOAD(vector, buffer, q, int, s, 64, 2);
+
+  VDUP(vector3, , int, s, 16, 4, 0x55);
+  VDUP(vector4, , int, s, 16, 4, 0xBB);
+  VDUP(vector3, , int, s, 32, 2, 0x55);
+  VDUP(vector4, , int, s, 32, 2, 0xBB);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_VQDMLXL(INSN_NAME, int, s, 32, 16, 4);
+  TEST_VQDMLXL(INSN_NAME, int, s, 64, 32, 2);
+  dump_results_hex (TEST_MSG);
+
+
+  VDUP(vector3, , int, s, 16, 4, 0x8000);
+  VDUP(vector4, , int, s, 16, 4, 0x8000);
+  VDUP(vector3, , int, s, 32, 2, 0x80000000);
+  VDUP(vector4, , int, s, 32, 2, 0x80000000);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check mul cumulative saturation)");
+  TEST_VQDMLXL(INSN_NAME, int, s, 32, 16, 4);
+  TEST_VQDMLXL(INSN_NAME, int, s, 64, 32, 2);
+  dump_results_hex2 (TEST_MSG, " (check mul cumulative saturation)");
+}
diff --git a/ref_vqdmlal_lane.c b/ref_vqdmlal_lane.c
new file mode 100644
index 0000000..e7d42f7
--- /dev/null
+++ b/ref_vqdmlal_lane.c
@@ -0,0 +1,105 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2012 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#ifndef INSN_NAME
+#define INSN_NAME vqdmlal_lane
+#define TEST_MSG "VQDMLAL_LANE"
+#endif
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* vector_res = vqdmlxl_lane(vector, vector3, vector4, lane),
+     then store the result.  */
+#define TEST_VQDMLXL_LANE1(INSN, T1, T2, W, W2, N, V)		\
+  Set_Neon_Cumulative_Sat(0, VECT_VAR(vector_res, T1, W, N));	\
+  VECT_VAR(vector_res, T1, W, N) =				\
+    INSN##_##T2##W2(VECT_VAR(vector, T1, W, N),			\
+		    VECT_VAR(vector3, T1, W2, N),		\
+		    VECT_VAR(vector4, T1, W2, N),		\
+		    V);						\
+  vst1q_##T2##W(VECT_VAR(result, T1, W, N),			\
+		VECT_VAR(vector_res, T1, W, N));		\
+  dump_neon_cumulative_sat(TEST_MSG, xSTR(INSN##_##T2##W2),	\
+			   xSTR(T1), W, N)
+
+#define TEST_VQDMLXL_LANE(INSN, T1, T2, W, W2, N, V)	\
+  TEST_VQDMLXL_LANE1(INSN, T1, T2, W, W2, N, V)
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE(vector, int, 32, 4);
+  DECL_VARIABLE(vector3, int, 16, 4);
+  DECL_VARIABLE(vector4, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+
+  DECL_VARIABLE(vector, int, 64, 2);
+  DECL_VARIABLE(vector3, int, 32, 2);
+  DECL_VARIABLE(vector4, int, 32, 2);
+  DECL_VARIABLE(vector_res, int, 64, 2);
+
+  clean_results ();
+
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+  VLOAD(vector, buffer, q, int, s, 64, 2);
+
+  VDUP(vector3, , int, s, 16, 4, 0x55);
+  VDUP(vector4, , int, s, 16, 4, 0xBB);
+  VDUP(vector3, , int, s, 32, 2, 0x55);
+  VDUP(vector4, , int, s, 32, 2, 0xBB);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_VQDMLXL_LANE(INSN_NAME, int, s, 32, 16, 4, 0);
+  TEST_VQDMLXL_LANE(INSN_NAME, int, s, 64, 32, 2, 0);
+  dump_results_hex (TEST_MSG);
+
+  VDUP(vector3, , int, s, 16, 4, 0);
+  VDUP(vector3, , int, s, 32, 2, 0);
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (mul with input=0)");
+  TEST_VQDMLXL_LANE(INSN_NAME, int, s, 32, 16, 4, 0);
+  TEST_VQDMLXL_LANE(INSN_NAME, int, s, 64, 32, 2, 0);
+  dump_results_hex2 (TEST_MSG, " (mul with input=0)");
+
+  VDUP(vector3, , int, s, 16, 4, 0x8000);
+  VDUP(vector3, , int, s, 32, 2, 0x80000000);
+  VDUP(vector4, , int, s, 16, 4, 0x8000);
+  VDUP(vector4, , int, s, 32, 2, 0x80000000);
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check mul cumulative saturation)");
+  TEST_VQDMLXL_LANE(INSN_NAME, int, s, 32, 16, 4, 0);
+  TEST_VQDMLXL_LANE(INSN_NAME, int, s, 64, 32, 2, 0);
+  dump_results_hex2 (TEST_MSG, " (check mul cumulative saturation)");
+}
diff --git a/ref_vqdmlal_n.c b/ref_vqdmlal_n.c
new file mode 100644
index 0000000..86f1e30
--- /dev/null
+++ b/ref_vqdmlal_n.c
@@ -0,0 +1,92 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2012 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#ifndef INSN_NAME
+#define INSN_NAME vqdmlal_n
+#define TEST_MSG "VQDMLAL_N"
+#endif
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* vector_res = vqdmlxl_n(vector, vector3, val),
+     then store the result.  */
+#define TEST_VQDMLXL_N1(INSN, T1, T2, W, W2, N, V)		\
+  Set_Neon_Cumulative_Sat(0, VECT_VAR(vector_res, T1, W, N));	\
+  VECT_VAR(vector_res, T1, W, N) =				\
+    INSN##_##T2##W2(VECT_VAR(vector, T1, W, N),			\
+		    VECT_VAR(vector3, T1, W2, N),		\
+		    V);						\
+  vst1q_##T2##W(VECT_VAR(result, T1, W, N),			\
+		VECT_VAR(vector_res, T1, W, N));		\
+  dump_neon_cumulative_sat(TEST_MSG, xSTR(INSN##_##T2##W2),	\
+			   xSTR(T1), W, N)
+
+#define TEST_VQDMLXL_N(INSN, T1, T2, W, W2, N, V)	\
+  TEST_VQDMLXL_N1(INSN, T1, T2, W, W2, N, V)
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE(vector, int, 32, 4);
+  DECL_VARIABLE(vector3, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+
+  DECL_VARIABLE(vector, int, 64, 2);
+  DECL_VARIABLE(vector3, int, 32, 2);
+  DECL_VARIABLE(vector_res, int, 64, 2);
+
+  clean_results ();
+
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+  VLOAD(vector, buffer, q, int, s, 64, 2);
+
+  VDUP(vector3, , int, s, 16, 4, 0x55);
+  VDUP(vector3, , int, s, 32, 2, 0x55);
+
+  /* Choose val arbitrarily */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_VQDMLXL_N(INSN_NAME, int, s, 32, 16, 4, 0x22);
+  TEST_VQDMLXL_N(INSN_NAME, int, s, 64, 32, 2, 0x33);
+
+  dump_results_hex (TEST_MSG);
+
+  VDUP(vector3, , int, s, 16, 4, 0x8000);
+  VDUP(vector3, , int, s, 32, 2, 0x80000000);
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check mul cumulative saturation)");
+  TEST_VQDMLXL_N(INSN_NAME, int, s, 32, 16, 4, 0x8000);
+  TEST_VQDMLXL_N(INSN_NAME, int, s, 64, 32, 2, 0x80000000);
+  dump_results_hex2 (TEST_MSG, " (check mul cumulative saturation)");
+}
diff --git a/ref_vqdmlsl.c b/ref_vqdmlsl.c
new file mode 100644
index 0000000..ceb0b6b
--- /dev/null
+++ b/ref_vqdmlsl.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vqdmlsl
+#define TEST_MSG "VQDMLSL"
+
+#include "ref_vqdmlal.c"
diff --git a/ref_vqdmlsl_lane.c b/ref_vqdmlsl_lane.c
new file mode 100644
index 0000000..7724d98
--- /dev/null
+++ b/ref_vqdmlsl_lane.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vqdmlsl_lane
+#define TEST_MSG "VQDMLSL_LANE"
+
+#include "ref_vqdmlal_lane.c"
diff --git a/ref_vqdmlsl_n.c b/ref_vqdmlsl_n.c
new file mode 100644
index 0000000..c6f8818
--- /dev/null
+++ b/ref_vqdmlsl_n.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vqdmlsl_n
+#define TEST_MSG "VQDMLSL_N"
+
+#include "ref_vqdmlal_n.c"
diff --git a/ref_vqdmulh.c b/ref_vqdmulh.c
new file mode 100644
index 0000000..59ff820
--- /dev/null
+++ b/ref_vqdmulh.c
@@ -0,0 +1,115 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2012 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN vqdmulh
+#define TEST_MSG "VQDMULH"
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN)
+{
+  /* vector_res = vqdmulh(vector,vector2,lane), then store the result.  */
+#define TEST_VQDMULH2(INSN, Q, T1, T2, W, N)			\
+  Set_Neon_Cumulative_Sat(0, VECT_VAR(vector_res, T1, W, N));	\
+  VECT_VAR(vector_res, T1, W, N) =				\
+    INSN##Q##_##T2##W(VECT_VAR(vector, T1, W, N),		\
+		      VECT_VAR(vector2, T1, W, N));		\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),			\
+		    VECT_VAR(vector_res, T1, W, N));		\
+  dump_neon_cumulative_sat(TEST_MSG, xSTR(INSN##Q##_##T2##W),	\
+			   xSTR(T1), W, N)
+
+  /* Two auxliary macros are necessary to expand INSN */
+#define TEST_VQDMULH1(INSN, Q, T1, T2, W, N)	\
+  TEST_VQDMULH2(INSN, Q, T1, T2, W, N)
+
+#define TEST_VQDMULH(Q, T1, T2, W, N)		\
+  TEST_VQDMULH1(INSN, Q, T1, T2, W, N)
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE(vector, int, 16, 4);
+  DECL_VARIABLE(vector, int, 32, 2);
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+
+  DECL_VARIABLE(vector_res, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 2);
+  DECL_VARIABLE(vector_res, int, 16, 8);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+
+  DECL_VARIABLE(vector2, int, 16, 4);
+  DECL_VARIABLE(vector2, int, 32, 2);
+  DECL_VARIABLE(vector2, int, 16, 8);
+  DECL_VARIABLE(vector2, int, 32, 4);
+
+  clean_results ();
+
+  VLOAD(vector, buffer, , int, s, 16, 4);
+  VLOAD(vector, buffer, , int, s, 32, 2);
+  VLOAD(vector, buffer, q, int, s, 16, 8);
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+
+  /* Initialize vector2 */
+  VDUP(vector2, , int, s, 16, 4, 0x55);
+  VDUP(vector2, , int, s, 32, 2, 0xBB);
+  VDUP(vector2, q, int, s, 16, 8, 0x33);
+  VDUP(vector2, q, int, s, 32, 4, 0x22);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_VQDMULH(, int, s, 16, 4);
+  TEST_VQDMULH(, int, s, 32, 2);
+  TEST_VQDMULH(q, int, s, 16, 8);
+  TEST_VQDMULH(q, int, s, 32, 4);
+
+  /* FIXME: only a subset of the result buffers are used, but we
+     output all of them */
+  dump_results_hex (TEST_MSG);
+
+  VDUP(vector, , int, s, 16, 4, 0x8000);
+  VDUP(vector2, , int, s, 16, 4, 0x8000);
+  VDUP(vector, , int, s, 32, 2, 0x80000000);
+  VDUP(vector2, , int, s, 32, 2, 0x80000000);
+  VDUP(vector, q, int, s, 16, 8, 0x8000);
+  VDUP(vector2, q, int, s, 16, 8, 0x8000);
+  VDUP(vector, q, int, s, 32, 4, 0x80000000);
+  VDUP(vector2, q, int, s, 32, 4, 0x80000000);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_VQDMULH(, int, s, 16, 4);
+  TEST_VQDMULH(, int, s, 32, 2);
+  TEST_VQDMULH(q, int, s, 16, 8);
+  TEST_VQDMULH(q, int, s, 32, 4);
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vqdmulh_lane.c b/ref_vqdmulh_lane.c
new file mode 100644
index 0000000..ae52667
--- /dev/null
+++ b/ref_vqdmulh_lane.c
@@ -0,0 +1,116 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2012 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN vqdmulh
+#define TEST_MSG "VQDMULH_LANE"
+#define FNNAME1(NAME) void exec_ ## NAME ## _lane (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN)
+{
+  /* vector_res = vqdmulh_lane(vector,vector2,lane), then store the result.  */
+#define TEST_VQDMULH_LANE2(INSN, Q, T1, T2, W, N, N2, L)		\
+  Set_Neon_Cumulative_Sat(0, VECT_VAR(vector_res, T1, W, N));		\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    INSN##Q##_lane_##T2##W(VECT_VAR(vector, T1, W, N),			\
+			   VECT_VAR(vector2, T1, W, N2),		\
+			   L);						\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),				\
+		    VECT_VAR(vector_res, T1, W, N));			\
+  dump_neon_cumulative_sat(TEST_MSG, xSTR(INSN##Q##_lane_##T2##W),	\
+			   xSTR(T1), W, N)
+
+  /* Two auxliary macros are necessary to expand INSN */
+#define TEST_VQDMULH_LANE1(INSN, Q, T1, T2, W, N, N2, L)	\
+  TEST_VQDMULH_LANE2(INSN, Q, T1, T2, W, N, N2, L)
+
+#define TEST_VQDMULH_LANE(Q, T1, T2, W, N, N2, L)	\
+  TEST_VQDMULH_LANE1(INSN, Q, T1, T2, W, N, N2, L)
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE(vector, int, 16, 4);
+  DECL_VARIABLE(vector, int, 32, 2);
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+
+  DECL_VARIABLE(vector_res, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 2);
+  DECL_VARIABLE(vector_res, int, 16, 8);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+
+  /* vector2: vqdmulh_lane and vqdmulhq_lane have a 2nd argument with
+     the same number of elements, so we need only one variable of each
+     type.  */
+  DECL_VARIABLE(vector2, int, 16, 4);
+  DECL_VARIABLE(vector2, int, 32, 2);
+
+  clean_results ();
+
+  VLOAD(vector, buffer, , int, s, 16, 4);
+  VLOAD(vector, buffer, , int, s, 32, 2);
+
+  VLOAD(vector, buffer, q, int, s, 16, 8);
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+
+  /* Initialize vector2 */
+  VDUP(vector2, , int, s, 16, 4, 0x55);
+  VDUP(vector2, , int, s, 32, 2, 0xBB);
+
+  /* Choose lane arbitrarily */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_VQDMULH_LANE(, int, s, 16, 4, 4, 2);
+  TEST_VQDMULH_LANE(, int, s, 32, 2, 2, 1);
+  TEST_VQDMULH_LANE(q, int, s, 16, 8, 4, 3);
+  TEST_VQDMULH_LANE(q, int, s, 32, 4, 2, 0);
+
+  /* FIXME: only a subset of the result buffers are used, but we
+     output all of them */
+  dump_results_hex (TEST_MSG);
+
+
+  VDUP(vector, , int, s, 16, 4, 0x8000);
+  VDUP(vector, , int, s, 32, 2, 0x80000000);
+  VDUP(vector, q, int, s, 16, 8, 0x8000);
+  VDUP(vector, q, int, s, 32, 4, 0x80000000);
+  VDUP(vector2, , int, s, 16, 4, 0x8000);
+  VDUP(vector2, , int, s, 32, 2, 0x80000000);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check mul cumulative saturation)");
+  TEST_VQDMULH_LANE(, int, s, 16, 4, 4, 3);
+  TEST_VQDMULH_LANE(, int, s, 32, 2, 2, 1);
+  TEST_VQDMULH_LANE(q, int, s, 16, 8, 4, 2);
+  TEST_VQDMULH_LANE(q, int, s, 32, 4, 2, 1);
+  dump_results_hex2 (TEST_MSG, " (check mul cumulative saturation)");
+}
diff --git a/ref_vqdmulh_n.c b/ref_vqdmulh_n.c
new file mode 100644
index 0000000..376259e
--- /dev/null
+++ b/ref_vqdmulh_n.c
@@ -0,0 +1,110 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2012 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN vqdmulh
+#define TEST_MSG "VQDMULH_N"
+#define FNNAME1(NAME) void exec_ ## NAME ## _n (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN)
+{
+  int i;
+
+  /* vector_res = vqdmulh_n(vector,val), then store the result.  */
+#define TEST_VQDMULH_N2(INSN, Q, T1, T2, W, N, L)		\
+  Set_Neon_Cumulative_Sat(0, VECT_VAR(vector_res, T1, W, N));	\
+  VECT_VAR(vector_res, T1, W, N) =				\
+    INSN##Q##_n_##T2##W(VECT_VAR(vector, T1, W, N),		\
+			L);					\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),			\
+		    VECT_VAR(vector_res, T1, W, N));		\
+  dump_neon_cumulative_sat(TEST_MSG, xSTR(INSN##Q##_n_##T2##W),	\
+			   xSTR(T1), W, N)
+
+  /* Two auxliary macros are necessary to expand INSN */
+#define TEST_VQDMULH_N1(INSN, Q, T1, T2, W, N, L)	\
+  TEST_VQDMULH_N2(INSN, Q, T1, T2, W, N, L)
+
+#define TEST_VQDMULH_N(Q, T1, T2, W, N, L)	\
+  TEST_VQDMULH_N1(INSN, Q, T1, T2, W, N, L)
+
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE(vector, int, 16, 4);
+  DECL_VARIABLE(vector, int, 32, 2);
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+
+  DECL_VARIABLE(vector_res, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 2);
+  DECL_VARIABLE(vector_res, int, 16, 8);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+
+  clean_results ();
+
+
+  /* Initialize vector */
+  VDUP(vector, , int, s, 16, 4, 0x1000);
+  VDUP(vector, , int, s, 32, 2, 0x100023);
+  VDUP(vector, q, int, s, 16, 8, 0x1000);
+  VDUP(vector, q, int, s, 32, 4, 0x100045);
+
+  /* Choose multiplier arbitrarily */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_VQDMULH_N(, int, s, 16, 4, 0xCF);
+  TEST_VQDMULH_N(, int, s, 32, 2, 0x2344);
+  TEST_VQDMULH_N(q, int, s, 16, 8, 0x80);
+  TEST_VQDMULH_N(q, int, s, 32, 4, 0x5422);
+
+  fprintf(ref_file, "\n%s output:\n", TEST_MSG);
+  fprintf(gcc_tests_file, "\n%s output:\n", TEST_MSG);
+  DUMP(TEST_MSG, int, 16, 4, PRIx16);
+  DUMP(TEST_MSG, int, 32, 2, PRIx32);
+  DUMP(TEST_MSG, int, 16, 8, PRIx16);
+  DUMP(TEST_MSG, int, 32, 4, PRIx32);
+
+
+
+  VDUP(vector, , int, s, 16, 4, 0x8000);
+  VDUP(vector, , int, s, 32, 2, 0x80000000);
+  VDUP(vector, q, int, s, 16, 8, 0x8000);
+  VDUP(vector, q, int, s, 32, 4, 0x80000000);
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check mul cumulative saturation)");
+  TEST_VQDMULH_N(, int, s, 16, 4, 0x8000);
+  TEST_VQDMULH_N(, int, s, 32, 2, 0x80000000);
+  TEST_VQDMULH_N(q, int, s, 16, 8, 0x8000);
+  TEST_VQDMULH_N(q, int, s, 32, 4, 0x80000000);
+  dump_results_hex2 (TEST_MSG, " (check mul cumulative saturation)");
+}
diff --git a/ref_vqdmull.c b/ref_vqdmull.c
new file mode 100644
index 0000000..478181d
--- /dev/null
+++ b/ref_vqdmull.c
@@ -0,0 +1,93 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2012 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN vqdmull
+#define TEST_MSG "VQDMULL"
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN)
+{
+  /* Basic test: y=vqdmull(x,x), then store the result.  */
+#define TEST_VQDMULL2(INSN, T1, T2, W, W2, N)			\
+  Set_Neon_Cumulative_Sat(0, VECT_VAR(vector_res, T1, W2, N));	\
+  VECT_VAR(vector_res, T1, W2, N) =				\
+    INSN##_##T2##W(VECT_VAR(vector, T1, W, N),			\
+		   VECT_VAR(vector2, T1, W, N));		\
+  vst1q_##T2##W2(VECT_VAR(result, T1, W2, N),			\
+		 VECT_VAR(vector_res, T1, W2, N));		\
+  dump_neon_cumulative_sat(TEST_MSG, xSTR(INSN##_##T2##W),	\
+			   xSTR(T1), W, N)
+
+  /* Two auxliary macros are necessary to expand INSN */
+#define TEST_VQDMULL1(INSN, T1, T2, W, W2, N)	\
+  TEST_VQDMULL2(INSN, T1, T2, W, W2, N)
+
+#define TEST_VQDMULL(T1, T2, W, W2, N)		\
+  TEST_VQDMULL1(INSN, T1, T2, W, W2, N)
+
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE(vector, int, 16, 4);
+  DECL_VARIABLE(vector, int, 32, 2);
+  DECL_VARIABLE(vector2, int, 16, 4);
+  DECL_VARIABLE(vector2, int, 32, 2);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+  DECL_VARIABLE(vector_res, int, 64, 2);
+
+  clean_results ();
+
+  VLOAD(vector, buffer, , int, s, 16, 4);
+  VLOAD(vector, buffer, , int, s, 32, 2);
+  VLOAD(vector2, buffer, , int, s, 16, 4);
+  VLOAD(vector2, buffer, , int, s, 32, 2);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_VQDMULL(int, s, 16, 32, 4);
+  TEST_VQDMULL(int, s, 32, 64, 2);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex (TEST_MSG);
+
+
+  VDUP(vector, , int, s, 16, 4, 0x8000);
+  VDUP(vector2, , int, s, 16, 4, 0x8000);
+  VDUP(vector, , int, s, 32, 2, 0x80000000);
+  VDUP(vector2, , int, s, 32, 2, 0x80000000);
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check mul cumulative saturation)");
+  TEST_VQDMULL(int, s, 16, 32, 4);
+  TEST_VQDMULL(int, s, 32, 64, 2);
+  dump_results_hex2 (TEST_MSG, " (check mul cumulative saturation)");
+}
diff --git a/ref_vqdmull_lane.c b/ref_vqdmull_lane.c
new file mode 100644
index 0000000..bf92c6b
--- /dev/null
+++ b/ref_vqdmull_lane.c
@@ -0,0 +1,109 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2012 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN vqdmull
+#define TEST_MSG "VQDMULL_LANE"
+#define FNNAME1(NAME) void exec_ ## NAME ## _lane (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN)
+{
+  int i;
+
+  /* vector_res = vqdmull_lane(vector,vector2,lane), then store the result.  */
+#define TEST_VQDMULL_LANE2(INSN, T1, T2, W, W2, N, L)		\
+  Set_Neon_Cumulative_Sat(0, VECT_VAR(vector_res, T1, W2, N));	\
+  VECT_VAR(vector_res, T1, W2, N) =				\
+    INSN##_lane_##T2##W(VECT_VAR(vector, T1, W, N),		\
+			VECT_VAR(vector2, T1, W, N),		\
+			L);					\
+  vst1q_##T2##W2(VECT_VAR(result, T1, W2, N),			\
+		 VECT_VAR(vector_res, T1, W2, N));		\
+  dump_neon_cumulative_sat(TEST_MSG, xSTR(INSN##_lane_##T2##W),	\
+			   xSTR(T1), W, N)
+
+  /* Two auxliary macros are necessary to expand INSN */
+#define TEST_VQDMULL_LANE1(INSN, T1, T2, W, W2, N, L)	\
+  TEST_VQDMULL_LANE2(INSN, T1, T2, W, W2, N, L)
+
+#define TEST_VQDMULL_LANE(T1, T2, W, W2, N, L)	\
+  TEST_VQDMULL_LANE1(INSN, T1, T2, W, W2, N, L)
+
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE(vector, int, 16, 4);
+  DECL_VARIABLE(vector, int, 32, 2);
+  DECL_VARIABLE(vector2, int, 16, 4);
+  DECL_VARIABLE(vector2, int, 32, 2);
+
+  DECL_VARIABLE(vector_res, int, 32, 4);
+  DECL_VARIABLE(vector_res, int, 64, 2);
+
+  clean_results ();
+
+  /* Initialize vector */
+  VDUP(vector, , int, s, 16, 4, 0x1000);
+  VDUP(vector, , int, s, 32, 2, 0x1000);
+
+  /* Initialize vector2 */
+  VDUP(vector2, , int, s, 16, 4, 0x4);
+  VDUP(vector2, , int, s, 32, 2, 0x2);
+
+  /* Choose lane arbitrarily */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_VQDMULL_LANE(int, s, 16, 32, 4, 2);
+  TEST_VQDMULL_LANE(int, s, 32, 64, 2, 1);
+
+
+  fprintf(ref_file, "\n%s output:\n", TEST_MSG);
+  fprintf(gcc_tests_file, "\n%s output:\n", TEST_MSG);
+  DUMP(TEST_MSG, int, 32, 4, PRIx32);
+  DUMP(TEST_MSG, int, 64, 2, PRIx64);
+
+
+
+  VDUP(vector, , int, s, 16, 4, 0x8000);
+  VDUP(vector2, , int, s, 16, 4, 0x8000);
+  VDUP(vector, , int, s, 32, 2, 0x80000000);
+  VDUP(vector2, , int, s, 32, 2, 0x80000000);
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check mul cumulative saturation)");
+  TEST_VQDMULL_LANE(int, s, 16, 32, 4, 2);
+  TEST_VQDMULL_LANE(int, s, 32, 64, 2, 1);
+
+  fprintf (ref_file, "\n%s output:\n",
+	   TEST_MSG " (check mul cumulative saturation)");
+  DUMP(TEST_MSG, int, 32, 4, PRIx32);
+  DUMP(TEST_MSG, int, 64, 2, PRIx64);
+}
diff --git a/ref_vqdmull_n.c b/ref_vqdmull_n.c
new file mode 100644
index 0000000..7a482b2
--- /dev/null
+++ b/ref_vqdmull_n.c
@@ -0,0 +1,104 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2012 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN vqdmull
+#define TEST_MSG "VQDMULL_N"
+#define FNNAME1(NAME) void exec_ ## NAME ## _n (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN)
+{
+  int i;
+
+  /* vector_res = vqdmull_n(vector,val), then store the result.  */
+#define TEST_VQDMULL_N2(INSN, T1, T2, W, W2, N, L)		\
+  Set_Neon_Cumulative_Sat(0, VECT_VAR(vector_res, T1, W2, N));	\
+  VECT_VAR(vector_res, T1, W2, N) =				\
+    INSN##_n_##T2##W(VECT_VAR(vector, T1, W, N),		\
+		     L);					\
+  vst1q_##T2##W2(VECT_VAR(result, T1, W2, N),			\
+		 VECT_VAR(vector_res, T1, W2, N));		\
+  dump_neon_cumulative_sat(TEST_MSG, xSTR(INSN##_n_##T2##W),	\
+			   xSTR(T1), W, N)
+
+  /* Two auxliary macros are necessary to expand INSN */
+#define TEST_VQDMULL_N1(INSN, T1, T2, W, W2, N, L)	\
+  TEST_VQDMULL_N2(INSN, T1, T2, W, W2, N, L)
+
+#define TEST_VQDMULL_N(T1, T2, W, W2, N, L)	\
+  TEST_VQDMULL_N1(INSN, T1, T2, W, W2, N, L)
+
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE(vector, int, 16, 4);
+  DECL_VARIABLE(vector, int, 32, 2);
+  DECL_VARIABLE(vector2, int, 16, 4);
+  DECL_VARIABLE(vector2, int, 32, 2);
+
+  DECL_VARIABLE(vector_res, int, 32, 4);
+  DECL_VARIABLE(vector_res, int, 64, 2);
+
+  clean_results ();
+
+  /* Initialize vector */
+  VDUP(vector, , int, s, 16, 4, 0x1000);
+  VDUP(vector, , int, s, 32, 2, 0x1000);
+
+  /* Initialize vector2 */
+  VDUP(vector2, , int, s, 16, 4, 0x4);
+  VDUP(vector2, , int, s, 32, 2, 0x2);
+
+  /* Choose multiplier arbitrarily */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_VQDMULL_N(int, s, 16, 32, 4, 0x22);
+  TEST_VQDMULL_N(int, s, 32, 64, 2, 0x55);
+
+  fprintf(ref_file, "\n%s output:\n", TEST_MSG);
+  fprintf(gcc_tests_file, "\n%s output:\n", TEST_MSG);
+  DUMP(TEST_MSG, int, 32, 4, PRIx32);
+  DUMP(TEST_MSG, int, 64, 2, PRIx64);
+
+
+  VDUP(vector, , int, s, 16, 4, 0x8000);
+  VDUP(vector, , int, s, 32, 2, 0x80000000);
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check mul cumulative saturation)");
+  TEST_VQDMULL_N(int, s, 16, 32, 4, 0x8000);
+  TEST_VQDMULL_N(int, s, 32, 64, 2, 0x80000000);
+
+  fprintf(ref_file, "\n%s output:\n",
+	  TEST_MSG " (check mul cumulative saturation)");
+  DUMP(TEST_MSG, int, 32, 4, PRIx32);
+  DUMP(TEST_MSG, int, 64, 2, PRIx64);
+}
diff --git a/ref_vqmovn.c b/ref_vqmovn.c
new file mode 100644
index 0000000..0f7c933
--- /dev/null
+++ b/ref_vqmovn.c
@@ -0,0 +1,114 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2012 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN_NAME vqmovn
+#define TEST_MSG "VQMOVN"
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* Basic test: y=OP(x), then store the result.  */
+#define TEST_UNARY_OP1(INSN, T1, T2, W, W2, N)			\
+  Set_Neon_Cumulative_Sat(0, VECT_VAR(vector_res, T1, W, N));	\
+  VECT_VAR(vector_res, T1, W, N) =				\
+    INSN##_##T2##W2(VECT_VAR(vector, T1, W2, N));		\
+  vst1##_##T2##W(VECT_VAR(result, T1, W, N),			\
+		 VECT_VAR(vector_res, T1, W, N));		\
+  dump_neon_cumulative_sat(TEST_MSG, xSTR(INSN##_##T2##W2),	\
+			   xSTR(T1), W, N)
+
+#define TEST_UNARY_OP(INSN, T1, T2, W, W2, N)				\
+  TEST_UNARY_OP1(INSN, T1, T2, W, W2, N)				\
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement  */
+
+  /* No need for 64 bits variants */
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+  DECL_VARIABLE(vector, int, 64, 2);
+  DECL_VARIABLE(vector, uint, 16, 8);
+  DECL_VARIABLE(vector, uint, 32, 4);
+  DECL_VARIABLE(vector, uint, 64, 2);
+
+  DECL_VARIABLE(vector_res, int, 8, 8);
+  DECL_VARIABLE(vector_res, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 2);
+  DECL_VARIABLE(vector_res, uint, 8, 8);
+  DECL_VARIABLE(vector_res, uint, 16, 4);
+  DECL_VARIABLE(vector_res, uint, 32, 2);
+
+  clean_results ();
+
+  /* Fill input vector with arbitrary values */
+  VDUP(vector, q, int, s, 16, 8, 0x12);
+  VDUP(vector, q, int, s, 32, 4, 0x1278);
+  VDUP(vector, q, int, s, 64, 2, 0x12345678);
+  VDUP(vector, q, uint, u, 16, 8, 0x82);
+  VDUP(vector, q, uint, u, 32, 4, 0x8765);
+  VDUP(vector, q, uint, u, 64, 2, 0x87654321);
+
+  /* Apply a unary operator named INSN_NAME  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_UNARY_OP(INSN_NAME, int, s, 8, 16, 8);
+  TEST_UNARY_OP(INSN_NAME, int, s, 16, 32, 4);
+  TEST_UNARY_OP(INSN_NAME, int, s, 32, 64, 2);
+  TEST_UNARY_OP(INSN_NAME, uint, u, 8, 16, 8);
+  TEST_UNARY_OP(INSN_NAME, uint, u, 16, 32, 4);
+  TEST_UNARY_OP(INSN_NAME, uint, u, 32, 64, 2);
+
+  dump_results_hex (TEST_MSG);
+
+
+  /* Fill input vector with arbitrary values which cause an cumulative
+     saturation.  */
+  VDUP(vector, q, int, s, 16, 8, 0x1234);
+  VDUP(vector, q, int, s, 32, 4, 0x12345678);
+  VDUP(vector, q, int, s, 64, 2, 0x1234567890ABLL);
+  VDUP(vector, q, uint, u, 16, 8, 0x8234);
+  VDUP(vector, q, uint, u, 32, 4, 0x87654321);
+  VDUP(vector, q, uint, u, 64, 2, 0x8765432187654321ULL);
+
+  /* Apply a unary operator named INSN_NAME  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_UNARY_OP(INSN_NAME, int, s, 8, 16, 8);
+  TEST_UNARY_OP(INSN_NAME, int, s, 16, 32, 4);
+  TEST_UNARY_OP(INSN_NAME, int, s, 32, 64, 2);
+  TEST_UNARY_OP(INSN_NAME, uint, u, 8, 16, 8);
+  TEST_UNARY_OP(INSN_NAME, uint, u, 16, 32, 4);
+  TEST_UNARY_OP(INSN_NAME, uint, u, 32, 64, 2);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vqmovun.c b/ref_vqmovun.c
new file mode 100644
index 0000000..5582cea
--- /dev/null
+++ b/ref_vqmovun.c
@@ -0,0 +1,95 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2012 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN_NAME vqmovun
+#define TEST_MSG "VQMOVUN"
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* Basic test: y=OP(x), then store the result.  */
+#define TEST_UNARY_OP1(INSN, T1, T2, W, W2, N)			\
+  Set_Neon_Cumulative_Sat(0, VECT_VAR(vector_res, T1, W, N));	\
+  VECT_VAR(vector_res, T1, W, N) =				\
+    INSN##_s##W2(VECT_VAR(vector, int, W2, N));			\
+  vst1##_##T2##W(VECT_VAR(result, T1, W, N),			\
+		 VECT_VAR(vector_res, T1, W, N));		\
+  dump_neon_cumulative_sat(TEST_MSG, xSTR(INSN##_s##W2),	\
+			   xSTR(T1), W, N)
+
+#define TEST_UNARY_OP(INSN, T1, T2, W, W2, N)	\
+  TEST_UNARY_OP1(INSN, T1, T2, W, W2, N)	\
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement  */
+
+  /* No need for 64 bits variants */
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+  DECL_VARIABLE(vector, int, 64, 2);
+
+  DECL_VARIABLE(vector_res, uint, 8, 8);
+  DECL_VARIABLE(vector_res, uint, 16, 4);
+  DECL_VARIABLE(vector_res, uint, 32, 2);
+
+  clean_results ();
+
+  /* Fill input vector with arbitrary values */
+  VDUP(vector, q, int, s, 16, 8, 0x34);
+  VDUP(vector, q, int, s, 32, 4, 0x5678);
+  VDUP(vector, q, int, s, 64, 2, 0x12345678);
+
+  /* Apply a unary operator named INSN_NAME  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_UNARY_OP(INSN_NAME, uint, u, 8, 16, 8);
+  TEST_UNARY_OP(INSN_NAME, uint, u, 16, 32, 4);
+  TEST_UNARY_OP(INSN_NAME, uint, u, 32, 64, 2);
+
+  dump_results_hex (TEST_MSG);
+
+  /* Fill input vector with negative values */
+  VDUP(vector, q, int, s, 16, 8, 0x8234);
+  VDUP(vector, q, int, s, 32, 4, 0x87654321);
+  VDUP(vector, q, int, s, 64, 2, 0x8765432187654321LL);
+
+  /* Apply a unary operator named INSN_NAME  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (negative input)");
+  TEST_UNARY_OP(INSN_NAME, uint, u, 8, 16, 8);
+  TEST_UNARY_OP(INSN_NAME, uint, u, 16, 32, 4);
+  TEST_UNARY_OP(INSN_NAME, uint, u, 32, 64, 2);
+
+  dump_results_hex2 (TEST_MSG, " (negative input)");
+}
diff --git a/ref_vqneg.c b/ref_vqneg.c
new file mode 100644
index 0000000..49a685b
--- /dev/null
+++ b/ref_vqneg.c
@@ -0,0 +1,73 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vqneg
+#define TEST_MSG "VQNEG/VQNEGQ"
+
+/* Extra tests for functions requiring corner cases tests */
+void vqneg_extra(void);
+#define EXTRA_TESTS vqneg_extra
+
+#include "ref_v_unary_sat_op.c"
+
+void vqneg_extra()
+{
+  /* No need for 64 bits variants */
+  DECL_VARIABLE(vector, int, 8, 8);
+  DECL_VARIABLE(vector, int, 16, 4);
+  DECL_VARIABLE(vector, int, 32, 2);
+  DECL_VARIABLE(vector, int, 8, 16);
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+
+  DECL_VARIABLE(vector_res, int, 8, 8);
+  DECL_VARIABLE(vector_res, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 2);
+  DECL_VARIABLE(vector_res, int, 8, 16);
+  DECL_VARIABLE(vector_res, int, 16, 8);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+
+  clean_results ();
+
+  /* Initialize input "vector" with max negative values to check
+     saturation  */
+  VDUP(vector, , int, s, 8, 8, 0x80);
+  VDUP(vector, , int, s, 16, 4, 0x8000);
+  VDUP(vector, , int, s, 32, 2, 0x80000000);
+  VDUP(vector, q, int, s, 8, 16, 0x80);
+  VDUP(vector, q, int, s, 16, 8, 0x8000);
+  VDUP(vector, q, int, s, 32, 4, 0x80000000);
+
+  /* Apply a unary operator named INSN_NAME  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_UNARY_SAT_OP(INSN_NAME, , int, s, 8, 8);
+  TEST_UNARY_SAT_OP(INSN_NAME, , int, s, 16, 4);
+  TEST_UNARY_SAT_OP(INSN_NAME, , int, s, 32, 2);
+  TEST_UNARY_SAT_OP(INSN_NAME, q, int, s, 8, 16);
+  TEST_UNARY_SAT_OP(INSN_NAME, q, int, s, 16, 8);
+  TEST_UNARY_SAT_OP(INSN_NAME, q, int, s, 32, 4);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vqrdmulh.c b/ref_vqrdmulh.c
new file mode 100644
index 0000000..f499b47
--- /dev/null
+++ b/ref_vqrdmulh.c
@@ -0,0 +1,135 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2012 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN vqrdmulh
+#define TEST_MSG "VQRDMULH"
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN)
+{
+  /* vector_res = vqrdmulh(vector,vector2), then store the result.  */
+#define TEST_VQRDMULH2(INSN, Q, T1, T2, W, N)				\
+  Set_Neon_Cumulative_Sat(0, VECT_VAR(vector_res, T1, W, N));		\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    INSN##Q##_##T2##W(VECT_VAR(vector, T1, W, N),			\
+		      VECT_VAR(vector2, T1, W, N));			\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),				\
+		    VECT_VAR(vector_res, T1, W, N));			\
+  dump_neon_cumulative_sat(TEST_MSG, xSTR(INSN##Q##_##T2##W),		\
+			   xSTR(T1), W, N)
+
+  /* Two auxliary macros are necessary to expand INSN */
+#define TEST_VQRDMULH1(INSN, Q, T1, T2, W, N)	\
+  TEST_VQRDMULH2(INSN, Q, T1, T2, W, N)
+
+#define TEST_VQRDMULH(Q, T1, T2, W, N)		\
+  TEST_VQRDMULH1(INSN, Q, T1, T2, W, N)
+
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE(vector, int, 16, 4);
+  DECL_VARIABLE(vector, int, 32, 2);
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+
+  DECL_VARIABLE(vector_res, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 2);
+  DECL_VARIABLE(vector_res, int, 16, 8);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+
+  DECL_VARIABLE(vector2, int, 16, 4);
+  DECL_VARIABLE(vector2, int, 32, 2);
+  DECL_VARIABLE(vector2, int, 16, 8);
+  DECL_VARIABLE(vector2, int, 32, 4);
+
+  clean_results ();
+
+  VLOAD(vector, buffer, , int, s, 16, 4);
+  VLOAD(vector, buffer, , int, s, 32, 2);
+  VLOAD(vector, buffer, q, int, s, 16, 8);
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+
+  /* Initialize vector2 */
+  VDUP(vector2, , int, s, 16, 4, 0x5555);
+  VDUP(vector2, , int, s, 32, 2, 0xBB);
+  VDUP(vector2, q, int, s, 16, 8, 0x33);
+  VDUP(vector2, q, int, s, 32, 4, 0x22);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_VQRDMULH(, int, s, 16, 4);
+  TEST_VQRDMULH(, int, s, 32, 2);
+  TEST_VQRDMULH(q, int, s, 16, 8);
+  TEST_VQRDMULH(q, int, s, 32, 4);
+
+  /* FIXME: only a subset of the result buffers are used, but we
+     output all of them */
+  dump_results_hex (TEST_MSG);
+
+  VDUP(vector, , int, s, 16, 4, 0x8000);
+  VDUP(vector, , int, s, 32, 2, 0x80000000);
+  VDUP(vector, q, int, s, 16, 8, 0x8000);
+  VDUP(vector, q, int, s, 32, 4, 0x80000000);
+  VDUP(vector2, , int, s, 16, 4, 0x8000);
+  VDUP(vector2, , int, s, 32, 2, 0x80000000);
+  VDUP(vector2, q, int, s, 16, 8, 0x8000);
+  VDUP(vector2, q, int, s, 32, 4, 0x80000000);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check mul cumulative saturation)");
+  TEST_VQRDMULH(, int, s, 16, 4);
+  TEST_VQRDMULH(, int, s, 32, 2);
+  TEST_VQRDMULH(q, int, s, 16, 8);
+  TEST_VQRDMULH(q, int, s, 32, 4);
+  dump_results_hex2 (TEST_MSG, " (check mul cumulative saturation)");
+
+
+  VDUP(vector, , int, s, 16, 4, 0x8000);
+  VDUP(vector, , int, s, 32, 2, 0x80000000);
+  VDUP(vector, q, int, s, 16, 8, 0x8000);
+  VDUP(vector, q, int, s, 32, 4, 0x80000000);
+  VDUP(vector2, , int, s, 16, 4, 0x8001);
+  VDUP(vector2, , int, s, 32, 2, 0x80000001);
+  VDUP(vector2, q, int, s, 16, 8, 0x8001);
+  VDUP(vector2, q, int, s, 32, 4, 0x80000001);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check rounding cumulative saturation)");
+  TEST_VQRDMULH(, int, s, 16, 4);
+  TEST_VQRDMULH(, int, s, 32, 2);
+  TEST_VQRDMULH(q, int, s, 16, 8);
+  TEST_VQRDMULH(q, int, s, 32, 4);
+  dump_results_hex2 (TEST_MSG, " (check rounding cumulative saturation)");
+}
diff --git a/ref_vqrdmulh_lane.c b/ref_vqrdmulh_lane.c
new file mode 100644
index 0000000..b2c37db
--- /dev/null
+++ b/ref_vqrdmulh_lane.c
@@ -0,0 +1,134 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2012 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN vqrdmulh
+#define TEST_MSG "VQRDMULH_LANE"
+
+#define FNNAME1(NAME) void exec_ ## NAME ## _lane (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN)
+{
+  /* vector_res = vqrdmulh_lane(vector,vector2,lane), then store the result.  */
+#define TEST_VQRDMULH_LANE2(INSN, Q, T1, T2, W, N, N2, L)		\
+  Set_Neon_Cumulative_Sat(0, VECT_VAR(vector_res, T1, W, N));		\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    INSN##Q##_lane_##T2##W(VECT_VAR(vector, T1, W, N),			\
+			   VECT_VAR(vector2, T1, W, N2),		\
+			   L);						\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),				\
+		    VECT_VAR(vector_res, T1, W, N));			\
+  dump_neon_cumulative_sat(TEST_MSG, xSTR(INSN##Q##_lane_##T2##W),	\
+			   xSTR(T1), W, N)
+
+  /* Two auxliary macros are necessary to expand INSN */
+#define TEST_VQRDMULH_LANE1(INSN, Q, T1, T2, W, N, N2, L)	\
+  TEST_VQRDMULH_LANE2(INSN, Q, T1, T2, W, N, N2, L)
+
+#define TEST_VQRDMULH_LANE(Q, T1, T2, W, N, N2, L)	\
+  TEST_VQRDMULH_LANE1(INSN, Q, T1, T2, W, N, N2, L)
+
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE(vector, int, 16, 4);
+  DECL_VARIABLE(vector, int, 32, 2);
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+
+  DECL_VARIABLE(vector_res, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 2);
+  DECL_VARIABLE(vector_res, int, 16, 8);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+
+  /* vector2: vqrdmulh_lane and vqrdmulhq_lane have a 2nd argument with
+     the same number of elements, so we need only one variable of each
+     type.  */
+  DECL_VARIABLE(vector2, int, 16, 4);
+  DECL_VARIABLE(vector2, int, 32, 2);
+
+  clean_results ();
+
+  VLOAD(vector, buffer, , int, s, 16, 4);
+  VLOAD(vector, buffer, , int, s, 32, 2);
+
+  VLOAD(vector, buffer, q, int, s, 16, 8);
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+
+  /* Initialize vector2 */
+  VDUP(vector2, , int, s, 16, 4, 0x55);
+  VDUP(vector2, , int, s, 32, 2, 0xBB);
+
+  /* Choose lane arbitrarily */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_VQRDMULH_LANE(, int, s, 16, 4, 4, 2);
+  TEST_VQRDMULH_LANE(, int, s, 32, 2, 2, 1);
+  TEST_VQRDMULH_LANE(q, int, s, 16, 8, 4, 3);
+  TEST_VQRDMULH_LANE(q, int, s, 32, 4, 2, 0);
+
+  /* FIXME: only a subset of the result buffers are used, but we
+     output all of them */
+  dump_results_hex (TEST_MSG);
+
+
+  VDUP(vector, , int, s, 16, 4, 0x8000);
+  VDUP(vector, , int, s, 32, 2, 0x80000000);
+  VDUP(vector, q, int, s, 16, 8, 0x8000);
+  VDUP(vector, q, int, s, 32, 4, 0x80000000);
+  VDUP(vector2, , int, s, 16, 4, 0x8000);
+  VDUP(vector2, , int, s, 32, 2, 0x80000000);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check mul cumulative saturation)");
+  TEST_VQRDMULH_LANE(, int, s, 16, 4, 4, 2);
+  TEST_VQRDMULH_LANE(, int, s, 32, 2, 2, 1);
+  TEST_VQRDMULH_LANE(q, int, s, 16, 8, 4, 3);
+  TEST_VQRDMULH_LANE(q, int, s, 32, 4, 2, 0);
+  dump_results_hex2 (TEST_MSG, " (check mul cumulative saturation)");
+
+
+  VDUP(vector, , int, s, 16, 4, 0x8000);
+  VDUP(vector, , int, s, 32, 2, 0x80000000);
+  VDUP(vector, q, int, s, 16, 8, 0x8000);
+  VDUP(vector, q, int, s, 32, 4, 0x80000000);
+  VDUP(vector2, , int, s, 16, 4, 0x8001);
+  VDUP(vector2, , int, s, 32, 2, 0x80000001);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check rounding cumulative saturation)");
+  TEST_VQRDMULH_LANE(, int, s, 16, 4, 4, 2);
+  TEST_VQRDMULH_LANE(, int, s, 32, 2, 2, 1);
+  TEST_VQRDMULH_LANE(q, int, s, 16, 8, 4, 3);
+  TEST_VQRDMULH_LANE(q, int, s, 32, 4, 2, 0);
+  dump_results_hex2 (TEST_MSG, " (check rounding cumulative saturation)");
+}
diff --git a/ref_vqrdmulh_n.c b/ref_vqrdmulh_n.c
new file mode 100644
index 0000000..01f0e0b
--- /dev/null
+++ b/ref_vqrdmulh_n.c
@@ -0,0 +1,124 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2012 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN vqrdmulh
+#define TEST_MSG "VQRDMULH_N"
+
+#define FNNAME1(NAME) void exec_ ## NAME ## _n (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN)
+{
+  int i;
+
+  /* vector_res = vqrdmulh_n(vector,val), then store the result.  */
+#define TEST_VQRDMULH_N2(INSN, Q, T1, T2, W, N, L)			\
+  Set_Neon_Cumulative_Sat(0, VECT_VAR(vector_res, T1, W, N));		\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    INSN##Q##_n_##T2##W(VECT_VAR(vector, T1, W, N),			\
+			L);						\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),				\
+		    VECT_VAR(vector_res, T1, W, N));			\
+  dump_neon_cumulative_sat(TEST_MSG, xSTR(INSN##Q##_n_##T2##W),		\
+			   xSTR(T1), W, N)
+
+  /* Two auxliary macros are necessary to expand INSN */
+#define TEST_VQRDMULH_N1(INSN, Q, T1, T2, W, N, L)	\
+  TEST_VQRDMULH_N2(INSN, Q, T1, T2, W, N, L)
+
+#define TEST_VQRDMULH_N(Q, T1, T2, W, N, L)	\
+  TEST_VQRDMULH_N1(INSN, Q, T1, T2, W, N, L)
+
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE(vector, int, 16, 4);
+  DECL_VARIABLE(vector, int, 32, 2);
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+
+  DECL_VARIABLE(vector_res, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 2);
+  DECL_VARIABLE(vector_res, int, 16, 8);
+  DECL_VARIABLE(vector_res, int, 32, 4);
+
+  clean_results ();
+
+  VLOAD(vector, buffer, , int, s, 16, 4);
+  VLOAD(vector, buffer, , int, s, 32, 2);
+
+  VLOAD(vector, buffer, q, int, s, 16, 8);
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+
+  /* Choose multiplier arbitrarily */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_VQRDMULH_N(, int, s, 16, 4, 0x2233);
+  TEST_VQRDMULH_N(, int, s, 32, 2, 0x12345678);
+  TEST_VQRDMULH_N(q, int, s, 16, 8, 0xCD12);
+  TEST_VQRDMULH_N(q, int, s, 32, 4, 0xFA23456);
+
+  fprintf(ref_file, "\n%s output:\n", TEST_MSG);
+  fprintf(gcc_tests_file, "\n%s output:\n", TEST_MSG);
+  DUMP(TEST_MSG, int, 16, 4, PRIx16);
+  DUMP(TEST_MSG, int, 32, 2, PRIx32);
+  DUMP(TEST_MSG, int, 16, 8, PRIx16);
+  DUMP(TEST_MSG, int, 32, 4, PRIx32);
+
+
+  VDUP(vector, , int, s, 16, 4, 0x8000);
+  VDUP(vector, , int, s, 32, 2, 0x80000000);
+  VDUP(vector, q, int, s, 16, 8, 0x8000);
+  VDUP(vector, q, int, s, 32, 4, 0x80000000);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check mul cumulative saturation)");
+  TEST_VQRDMULH_N(, int, s, 16, 4, 0x8000);
+  TEST_VQRDMULH_N(, int, s, 32, 2, 0x80000000);
+  TEST_VQRDMULH_N(q, int, s, 16, 8, 0x8000);
+  TEST_VQRDMULH_N(q, int, s, 32, 4, 0x80000000);
+  dump_results_hex2 (TEST_MSG, " (check mul cumulative saturation)");
+
+
+  VDUP(vector, , int, s, 16, 4, 0x8000);
+  VDUP(vector, , int, s, 32, 2, 0x80000000);
+  VDUP(vector, q, int, s, 16, 8, 0x8000);
+  VDUP(vector, q, int, s, 32, 4, 0x80000000);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check rounding cumulative saturation)");
+  TEST_VQRDMULH_N(, int, s, 16, 4, 0x8001);
+  TEST_VQRDMULH_N(, int, s, 32, 2, 0x80000001);
+  TEST_VQRDMULH_N(q, int, s, 16, 8, 0x8001);
+  TEST_VQRDMULH_N(q, int, s, 32, 4, 0x80000001);
+  dump_results_hex2 (TEST_MSG, " (check rounding cumulative saturation)");
+}
diff --git a/ref_vqrshl.c b/ref_vqrshl.c
new file mode 100644
index 0000000..e4a33e5
--- /dev/null
+++ b/ref_vqrshl.c
@@ -0,0 +1,303 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2012 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN vqrshl
+#define TEST_MSG "VQRSHL/VQRSHLQ"
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN)
+{
+  /* Basic test: v3=vqrshl(v1,v2), then store the result.  */
+#define TEST_VQRSHL2(INSN, T3, Q, T1, T2, W, N)			\
+  Set_Neon_Cumulative_Sat(0, VECT_VAR(vector_res, T1, W, N));	\
+  VECT_VAR(vector_res, T1, W, N) =				\
+    INSN##Q##_##T2##W(VECT_VAR(vector, T1, W, N),		\
+		      VECT_VAR(vector_shift, T3, W, N));	\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),			\
+		    VECT_VAR(vector_res, T1, W, N));		\
+  dump_neon_cumulative_sat(TEST_MSG, xSTR(INSN##Q##_##T2##W),	\
+			   xSTR(T1), W, N)
+
+  /* Two auxliary macros are necessary to expand INSN */
+#define TEST_VQRSHL1(INSN, T3, Q, T1, T2, W, N)	\
+  TEST_VQRSHL2(INSN, T3, Q, T1, T2, W, N)
+
+#define TEST_VQRSHL(T3, Q, T1, T2, W, N)	\
+  TEST_VQRSHL1(INSN, T3, Q, T1, T2, W, N)
+
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+  DECL_VARIABLE_SIGNED_VARIANTS(vector_shift);
+
+  clean_results ();
+
+  /* Fill input vector with 0, to check saturation on limits */
+  VDUP(vector, , int, s, 8, 8, 0);
+  VDUP(vector, , int, s, 16, 4, 0);
+  VDUP(vector, , int, s, 32, 2, 0);
+  VDUP(vector, , int, s, 64, 1, 0);
+  VDUP(vector, , uint, u, 8, 8, 0);
+  VDUP(vector, , uint, u, 16, 4, 0);
+  VDUP(vector, , uint, u, 32, 2, 0);
+  VDUP(vector, , uint, u, 64, 1, 0);
+  VDUP(vector, q, int, s, 8, 16, 0);
+  VDUP(vector, q, int, s, 16, 8, 0);
+  VDUP(vector, q, int, s, 32, 4, 0);
+  VDUP(vector, q, int, s, 64, 2, 0);
+  VDUP(vector, q, uint, u, 8, 16, 0);
+  VDUP(vector, q, uint, u, 16, 8, 0);
+  VDUP(vector, q, uint, u, 32, 4, 0);
+  VDUP(vector, q, uint, u, 64, 2, 0);
+
+  /* Choose init value arbitrarily, will be used as shift amount */
+  /* Use values equal or one-less-than the type width to check
+     behaviour on limits */
+  VDUP(vector_shift, , int, s, 8, 8, 7);
+  VDUP(vector_shift, , int, s, 16, 4, 15);
+  VDUP(vector_shift, , int, s, 32, 2, 31);
+  VDUP(vector_shift, , int, s, 64, 1, 63);
+  VDUP(vector_shift, q, int, s, 8, 16, 8);
+  VDUP(vector_shift, q, int, s, 16, 8, 16);
+  VDUP(vector_shift, q, int, s, 32, 4, 32);
+  VDUP(vector_shift, q, int, s, 64, 2, 64);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (with input = 0)");
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VQRSHL, int);
+  dump_results_hex2 (TEST_MSG, " (with input = 0)");
+
+  /* Use negative shift amounts */
+  VDUP(vector_shift, , int, s, 8, 8, -1);
+  VDUP(vector_shift, , int, s, 16, 4, -2);
+  VDUP(vector_shift, , int, s, 32, 2, -3);
+  VDUP(vector_shift, , int, s, 64, 1, -4);
+  VDUP(vector_shift, q, int, s, 8, 16, -7);
+  VDUP(vector_shift, q, int, s, 16, 8, -11);
+  VDUP(vector_shift, q, int, s, 32, 4, -13);
+  VDUP(vector_shift, q, int, s, 64, 2, -20);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (input 0 and negative shift amount)");
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VQRSHL, int);
+  dump_results_hex2 (TEST_MSG, " (input 0 and negative shift amount)");
+
+  /* Test again, with predefined input values */
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+
+  /* Choose init value arbitrarily, will be used as shift amount */
+  VDUP(vector_shift, , int, s, 8, 8, 1);
+  VDUP(vector_shift, , int, s, 16, 4, 3);
+  VDUP(vector_shift, , int, s, 32, 2, 8);
+  VDUP(vector_shift, , int, s, 64, 1, 3);
+  VDUP(vector_shift, q, int, s, 8, 16, 10);
+  VDUP(vector_shift, q, int, s, 16, 8, 12);
+  VDUP(vector_shift, q, int, s, 32, 4, 31);
+  VDUP(vector_shift, q, int, s, 64, 2, 63);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VQRSHL, int);
+  dump_results_hex (TEST_MSG);
+
+  /* Use negative shift amounts */
+  VDUP(vector_shift, , int, s, 8, 8, -2);
+  VDUP(vector_shift, , int, s, 16, 4, -2);
+  VDUP(vector_shift, , int, s, 32, 2, -3);
+  VDUP(vector_shift, , int, s, 64, 1, -4);
+  VDUP(vector_shift, q, int, s, 8, 16, -7);
+  VDUP(vector_shift, q, int, s, 16, 8, -11);
+  VDUP(vector_shift, q, int, s, 32, 4, -13);
+  VDUP(vector_shift, q, int, s, 64, 2, -20);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (negative shift amount)");
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VQRSHL, int);
+  dump_results_hex2 (TEST_MSG, " (negative shift amount)");
+
+
+  /* Fill input vector with max value, to check saturation on limits */
+  VDUP(vector, , int, s, 8, 8, 0x7F);
+  VDUP(vector, , int, s, 16, 4, 0x7FFF);
+  VDUP(vector, , int, s, 32, 2, 0x7FFFFFFF);
+  VDUP(vector, , int, s, 64, 1, 0x7FFFFFFFFFFFFFFFLL);
+  VDUP(vector, , uint, u, 8, 8, 0xFF);
+  VDUP(vector, , uint, u, 16, 4, 0xFFFF);
+  VDUP(vector, , uint, u, 32, 2, 0xFFFFFFFF);
+  VDUP(vector, , uint, u, 64, 1, 0xFFFFFFFFFFFFFFFFULL);
+  VDUP(vector, q, int, s, 8, 16, 0x7F);
+  VDUP(vector, q, int, s, 16, 8, 0x7FFF);
+  VDUP(vector, q, int, s, 32, 4, 0x7FFFFFFF);
+  VDUP(vector, q, int, s, 64, 2, 0x7FFFFFFFFFFFFFFFLL);
+  VDUP(vector, q, uint, u, 8, 16, 0xFF);
+  VDUP(vector, q, uint, u, 16, 8, 0xFFFF);
+  VDUP(vector, q, uint, u, 32, 4, 0xFFFFFFFF);
+  VDUP(vector, q, uint, u, 64, 2, 0xFFFFFFFFFFFFFFFFULL);
+
+  /* Use -1 shift amount to check cumulative saturation with round_const */
+  VDUP(vector_shift, , int, s, 8, 8, -1);
+  VDUP(vector_shift, , int, s, 16, 4, -1);
+  VDUP(vector_shift, , int, s, 32, 2, -1);
+  VDUP(vector_shift, , int, s, 64, 1, -1);
+  VDUP(vector_shift, q, int, s, 8, 16, -1);
+  VDUP(vector_shift, q, int, s, 16, 8, -1);
+  VDUP(vector_shift, q, int, s, 32, 4, -1);
+  VDUP(vector_shift, q, int, s, 64, 2, -1);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (checking cumulative saturation: shift by -1)");
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VQRSHL, int);
+  dump_results_hex2 (TEST_MSG,
+		     " (checking cumulative saturation: shift by -1)");
+
+
+  /* Use -3 shift amount to check cumulative saturation with round_const */
+  VDUP(vector_shift, , int, s, 8, 8, -3);
+  VDUP(vector_shift, , int, s, 16, 4, -3);
+  VDUP(vector_shift, , int, s, 32, 2, -3);
+  VDUP(vector_shift, , int, s, 64, 1, -3);
+  VDUP(vector_shift, q, int, s, 8, 16, -3);
+  VDUP(vector_shift, q, int, s, 16, 8, -3);
+  VDUP(vector_shift, q, int, s, 32, 4, -3);
+  VDUP(vector_shift, q, int, s, 64, 2, -3);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (checking cumulative saturation: shift by -3)");
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VQRSHL, int);
+  dump_results_hex2 (TEST_MSG,
+		     " (checking cumulative saturation: shift by -3)");
+
+
+  /* Use large shift amount  */
+  VDUP(vector_shift, , int, s, 8, 8, 10);
+  VDUP(vector_shift, , int, s, 16, 4, 20);
+  VDUP(vector_shift, , int, s, 32, 2, 40);
+  VDUP(vector_shift, , int, s, 64, 1, 70);
+  VDUP(vector_shift, q, int, s, 8, 16, 10);
+  VDUP(vector_shift, q, int, s, 16, 8, 20);
+  VDUP(vector_shift, q, int, s, 32, 4, 40);
+  VDUP(vector_shift, q, int, s, 64, 2, 70);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (checking cumulative saturation: large shift amount)");
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VQRSHL, int);
+  dump_results_hex2 (TEST_MSG,
+		     " (checking cumulative saturation: large shift amount)");
+
+
+  /* Fill input vector with negative values, to check saturation on limits */
+  VDUP(vector, , int, s, 8, 8, 0x80);
+  VDUP(vector, , int, s, 16, 4, 0x8000);
+  VDUP(vector, , int, s, 32, 2, 0x80000000);
+  VDUP(vector, , int, s, 64, 1, 0x8000000000000000LL);
+  VDUP(vector, q, int, s, 8, 16, 0x80);
+  VDUP(vector, q, int, s, 16, 8, 0x8000);
+  VDUP(vector, q, int, s, 32, 4, 0x80000000);
+  VDUP(vector, q, int, s, 64, 2, 0x8000000000000000LL);
+
+  /* Use large shift amount  */
+  VDUP(vector_shift, , int, s, 8, 8, 10);
+  VDUP(vector_shift, , int, s, 16, 4, 20);
+  VDUP(vector_shift, , int, s, 32, 2, 40);
+  VDUP(vector_shift, , int, s, 64, 1, 70);
+  VDUP(vector_shift, q, int, s, 8, 16, 10);
+  VDUP(vector_shift, q, int, s, 16, 8, 20);
+  VDUP(vector_shift, q, int, s, 32, 4, 40);
+  VDUP(vector_shift, q, int, s, 64, 2, 70);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (checking cumulative saturation: large shift amount with negative input)");
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VQRSHL, int);
+  dump_results_hex2 (TEST_MSG,
+		     " (checking cumulative saturation: large shift amount with negative input)");
+
+
+  /* Fill input vector with negative and positive values, to check
+   * saturation on limits */
+  VDUP(vector, , int, s, 8, 8, 0x7F);
+  VDUP(vector, , int, s, 16, 4, 0x7FFF);
+  VDUP(vector, , int, s, 32, 2, 0x7FFFFFFF);
+  VDUP(vector, , int, s, 64, 1, 0x7FFFFFFFFFFFFFFFLL);
+  VDUP(vector, q, int, s, 8, 16, 0x80);
+  VDUP(vector, q, int, s, 16, 8, 0x8000);
+  VDUP(vector, q, int, s, 32, 4, 0x80000000);
+  VDUP(vector, q, int, s, 64, 2, 0x8000000000000000LL);
+
+  /* Use large negative shift amount  */
+  VDUP(vector_shift, , int, s, 8, 8, -10);
+  VDUP(vector_shift, , int, s, 16, 4, -20);
+  VDUP(vector_shift, , int, s, 32, 2, -40);
+  VDUP(vector_shift, , int, s, 64, 1, -70);
+  VDUP(vector_shift, q, int, s, 8, 16, -10);
+  VDUP(vector_shift, q, int, s, 16, 8, -20);
+  VDUP(vector_shift, q, int, s, 32, 4, -40);
+  VDUP(vector_shift, q, int, s, 64, 2, -70);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (checking cumulative saturation: large negative shift amount)");
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VQRSHL, int);
+  dump_results_hex2 (TEST_MSG,
+		     " (checking cumulative saturation: large negative shift amount)");
+
+
+  /* Fill input vector with 0, to check saturation in case of large
+   * shift amount */
+  VDUP(vector, , int, s, 8, 8, 0);
+  VDUP(vector, , int, s, 16, 4, 0);
+  VDUP(vector, , int, s, 32, 2, 0);
+  VDUP(vector, , int, s, 64, 1, 0);
+  VDUP(vector, q, int, s, 8, 16, 0);
+  VDUP(vector, q, int, s, 16, 8, 0);
+  VDUP(vector, q, int, s, 32, 4, 0);
+  VDUP(vector, q, int, s, 64, 2, 0);
+
+  /* Use large shift amount  */
+  VDUP(vector_shift, , int, s, 8, 8, -10);
+  VDUP(vector_shift, , int, s, 16, 4, -20);
+  VDUP(vector_shift, , int, s, 32, 2, -40);
+  VDUP(vector_shift, , int, s, 64, 1, -70);
+  VDUP(vector_shift, q, int, s, 8, 16, -10);
+  VDUP(vector_shift, q, int, s, 16, 8, -20);
+  VDUP(vector_shift, q, int, s, 32, 4, -40);
+  VDUP(vector_shift, q, int, s, 64, 2, -70);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (checking cumulative saturation: large shift amount with 0 input)");
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VQRSHL, int);
+  dump_results_hex2 (TEST_MSG,
+		     " (checking cumulative saturation: large shift amount with 0 input)");
+}
diff --git a/ref_vqrshrn_n.c b/ref_vqrshrn_n.c
new file mode 100644
index 0000000..34bf082
--- /dev/null
+++ b/ref_vqrshrn_n.c
@@ -0,0 +1,134 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN vqrshrn_n
+#define TEST_MSG "VQRSHRN_N"
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN)
+{
+  /* Basic test: y=vqrshrn_n(x,v), then store the result.  */
+#define TEST_VQRSHRN_N2(INSN, T1, T2, W, W2, N, V)		\
+  Set_Neon_Cumulative_Sat(0, VECT_VAR(vector_res, T1, W2, N));	\
+  VECT_VAR(vector_res, T1, W2, N) =				\
+    INSN##_##T2##W(VECT_VAR(vector, T1, W, N),			\
+		   V);						\
+  vst1_##T2##W2(VECT_VAR(result, T1, W2, N),			\
+		VECT_VAR(vector_res, T1, W2, N));		\
+  dump_neon_cumulative_sat(TEST_MSG, xSTR(INSN##_##T2##W),	\
+			   xSTR(T1), W, N)
+
+  /* Two auxliary macros are necessary to expand INSN */
+#define TEST_VQRSHRN_N1(INSN, T1, T2, W, W2, N, V)	\
+  TEST_VQRSHRN_N2(INSN, T1, T2, W, W2, N, V)
+
+#define TEST_VQRSHRN_N(T1, T2, W, W2, N, V)	\
+  TEST_VQRSHRN_N1(INSN, T1, T2, W, W2, N, V)
+
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+
+  /* vector is twice as large as vector_res */
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+  DECL_VARIABLE(vector, int, 64, 2);
+  DECL_VARIABLE(vector, uint, 16, 8);
+  DECL_VARIABLE(vector, uint, 32, 4);
+  DECL_VARIABLE(vector, uint, 64, 2);
+
+  DECL_VARIABLE(vector_res, int, 8, 8);
+  DECL_VARIABLE(vector_res, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 2);
+  DECL_VARIABLE(vector_res, uint, 8, 8);
+  DECL_VARIABLE(vector_res, uint, 16, 4);
+  DECL_VARIABLE(vector_res, uint, 32, 2);
+
+  clean_results ();
+
+  VLOAD(vector, buffer, q, int, s, 16, 8);
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+  VLOAD(vector, buffer, q, int, s, 64, 2);
+  VLOAD(vector, buffer, q, uint, u, 16, 8);
+  VLOAD(vector, buffer, q, uint, u, 32, 4);
+  VLOAD(vector, buffer, q, uint, u, 64, 2);
+
+  /* Choose shift amount arbitrarily  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_VQRSHRN_N(int, s, 16, 8, 8, 1);
+  TEST_VQRSHRN_N(int, s, 32, 16, 4, 1);
+  TEST_VQRSHRN_N(int, s, 64, 32, 2, 2);
+  TEST_VQRSHRN_N(uint, u, 16, 8, 8, 2);
+  TEST_VQRSHRN_N(uint, u, 32, 16, 4, 3);
+  TEST_VQRSHRN_N(uint, u, 64, 32, 2, 3);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex (TEST_MSG);
+
+  /* Another set of tests */
+  VDUP(vector, q, int, s, 16, 8, 0x7FFF);
+  VDUP(vector, q, int, s, 32, 4, 0x7FFFFFFF);
+  VDUP(vector, q, int, s, 64, 2, 0x7FFFFFFFFFFFFFFFLL);
+  VDUP(vector, q, uint, u, 16, 8, 0xFFFF);
+  VDUP(vector, q, uint, u, 32, 4, 0xFFFFFFFF);
+  VDUP(vector, q, uint, u, 64, 2, 0xFFFFFFFFFFFFFFFFULL);
+
+  /* shift by 3 to exercise saturation code in the lib  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check saturation: shift by 3)");
+  TEST_VQRSHRN_N(int, s, 16, 8, 8, 3);
+  TEST_VQRSHRN_N(int, s, 32, 16, 4, 3);
+  TEST_VQRSHRN_N(int, s, 64, 32, 2, 3);
+  TEST_VQRSHRN_N(uint, u, 16, 8, 8, 3);
+  TEST_VQRSHRN_N(uint, u, 32, 16, 4, 3);
+  TEST_VQRSHRN_N(uint, u, 64, 32, 2, 3);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex2 (TEST_MSG, " (check saturation: shift by 3)");
+
+
+  /* shift by max to exercise saturation code in the lib  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check saturation: shift by max)");
+  TEST_VQRSHRN_N(int, s, 16, 8, 8, 8);
+  TEST_VQRSHRN_N(int, s, 32, 16, 4, 16);
+  TEST_VQRSHRN_N(int, s, 64, 32, 2, 32);
+  TEST_VQRSHRN_N(uint, u, 16, 8, 8, 8);
+  TEST_VQRSHRN_N(uint, u, 32, 16, 4, 16);
+  TEST_VQRSHRN_N(uint, u, 64, 32, 2, 32);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex2 (TEST_MSG, " (check saturation: shift by max)");
+}
diff --git a/ref_vqrshrun_n.c b/ref_vqrshrun_n.c
new file mode 100644
index 0000000..53d11f5
--- /dev/null
+++ b/ref_vqrshrun_n.c
@@ -0,0 +1,142 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN vqrshrun_n
+#define TEST_MSG "VQRSHRUN_N"
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN)
+{
+  /* Basic test: y=vqrshrun_n(x,v), then store the result.  */
+#define TEST_VQRSHRUN_N2(INSN, T1, T2, W, W2, N, V)			\
+  Set_Neon_Cumulative_Sat(0, VECT_VAR(vector_res, uint, W2, N));	\
+  VECT_VAR(vector_res, uint, W2, N) =					\
+    INSN##_##T2##W(VECT_VAR(vector, T1, W, N),				\
+		   V);							\
+  vst1_u##W2(VECT_VAR(result, uint, W2, N),				\
+	     VECT_VAR(vector_res, uint, W2, N));			\
+  dump_neon_cumulative_sat(TEST_MSG, xSTR(INSN##_##T2##W),		\
+			   xSTR(T1), W, N)
+
+  /* Two auxliary macros are necessary to expand INSN */
+#define TEST_VQRSHRUN_N1(INSN, T1, T2, W, W2, N, V)	\
+  TEST_VQRSHRUN_N2(INSN, T1, T2, W, W2, N, V)
+
+#define TEST_VQRSHRUN_N(T1, T2, W, W2, N, V)	\
+  TEST_VQRSHRUN_N1(INSN, T1, T2, W, W2, N, V)
+
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+
+  /* vector is twice as large as vector_res */
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+  DECL_VARIABLE(vector, int, 64, 2);
+
+  DECL_VARIABLE(vector_res, uint, 8, 8);
+  DECL_VARIABLE(vector_res, uint, 16, 4);
+  DECL_VARIABLE(vector_res, uint, 32, 2);
+
+  clean_results ();
+
+  /* Fill input vector with negative values, to check saturation on limits */
+  VDUP(vector, q, int, s, 16, 8, -2);
+  VDUP(vector, q, int, s, 32, 4, -3);
+  VDUP(vector, q, int, s, 64, 2, -4);
+
+  /* Choose shift amount arbitrarily  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (negative input)");
+  TEST_VQRSHRUN_N(int, s, 16, 8, 8, 3);
+  TEST_VQRSHRUN_N(int, s, 32, 16, 4, 4);
+  TEST_VQRSHRUN_N(int, s, 64, 32, 2, 2);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex2 (TEST_MSG, " (negative input)");
+
+  /* Fill input vector with max value, to check saturation on limits */
+  VDUP(vector, q, int, s, 16, 8, 0x7FFF);
+  VDUP(vector, q, int, s, 32, 4, 0x7FFFFFFF);
+  VDUP(vector, q, int, s, 64, 2, 0x7FFFFFFFFFFFFFFFLL);
+
+  /* shift by 1  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check cumulative saturation: shift by 1)");
+  TEST_VQRSHRUN_N(int, s, 16, 8, 8, 1);
+  TEST_VQRSHRUN_N(int, s, 32, 16, 4, 1);
+  TEST_VQRSHRUN_N(int, s, 64, 32, 2, 1);
+
+  dump_results_hex2 (TEST_MSG, " (check cumulative saturation: shift by 1)");
+
+  /* shift by max  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check cumulative saturation: shift by max, positive input)");
+  TEST_VQRSHRUN_N(int, s, 16, 8, 8, 8);
+  TEST_VQRSHRUN_N(int, s, 32, 16, 4, 16);
+  TEST_VQRSHRUN_N(int, s, 64, 32, 2, 32);
+
+  dump_results_hex2 (TEST_MSG,
+		     " (check cumulative saturation: shift by max, positive input)");
+
+
+  /* Fill input vector with min value, to check saturation on limits */
+  VDUP(vector, q, int, s, 16, 8, 0x8000);
+  VDUP(vector, q, int, s, 32, 4, 0x80000000);
+  VDUP(vector, q, int, s, 64, 2, 0x8000000000000000LL);
+
+  /* shift by max  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check cumulative saturation: shift by max, negative input)");
+  TEST_VQRSHRUN_N(int, s, 16, 8, 8, 8);
+  TEST_VQRSHRUN_N(int, s, 32, 16, 4, 16);
+  TEST_VQRSHRUN_N(int, s, 64, 32, 2, 32);
+
+  dump_results_hex2 (TEST_MSG,
+		     " (check cumulative saturation: shift by max, negative input)");
+
+  /* Fill input vector with positive values, to check normal case */
+  VDUP(vector, q, int, s, 16, 8, 0x1234);
+  VDUP(vector, q, int, s, 32, 4, 0x87654321);
+  VDUP(vector, q, int, s, 64, 2, 0xDEADBEEF);
+
+  /* shift arbitrary amount  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_VQRSHRUN_N(int, s, 16, 8, 8, 6);
+  TEST_VQRSHRUN_N(int, s, 32, 16, 4, 7);
+  TEST_VQRSHRUN_N(int, s, 64, 32, 2, 8);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vqshl.c b/ref_vqshl.c
new file mode 100644
index 0000000..a9d29d7
--- /dev/null
+++ b/ref_vqshl.c
@@ -0,0 +1,241 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN vqshl
+#define TEST_MSG "VQSHL/VQSHLQ"
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN)
+{
+  /* Basic test: v3=vqshl(v1,v2), then store the result.  */
+#define TEST_VQSHL2(INSN, T3, Q, T1, T2, W, N)				\
+  Set_Neon_Cumulative_Sat(0, VECT_VAR(vector_res, T1, W, N));		\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    INSN##Q##_##T2##W(VECT_VAR(vector, T1, W, N),			\
+		      VECT_VAR(vector_shift, T3, W, N));		\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),				\
+		      VECT_VAR(vector_res, T1, W, N));			\
+  dump_neon_cumulative_sat(TEST_MSG, xSTR(INSN##Q##_##T2##W),		\
+			       xSTR(T1), W, N)
+
+  /* Two auxliary macros are necessary to expand INSN */
+#define TEST_VQSHL1(INSN, T3, Q, T1, T2, W, N)	\
+  TEST_VQSHL2(INSN, T3, Q, T1, T2, W, N)
+
+#define TEST_VQSHL(T3, Q, T1, T2, W, N)		\
+  TEST_VQSHL1(INSN, T3, Q, T1, T2, W, N)
+
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+  DECL_VARIABLE_SIGNED_VARIANTS(vector_shift);
+
+  clean_results ();
+
+  /* Fill input vector with 0, to check saturation on limits */
+  VDUP(vector, , int, s, 8, 8, 0);
+  VDUP(vector, , int, s, 16, 4, 0);
+  VDUP(vector, , int, s, 32, 2, 0);
+  VDUP(vector, , int, s, 64, 1, 0);
+  VDUP(vector, , uint, u, 8, 8, 0);
+  VDUP(vector, , uint, u, 16, 4, 0);
+  VDUP(vector, , uint, u, 32, 2, 0);
+  VDUP(vector, , uint, u, 64, 1, 0);
+  VDUP(vector, q, int, s, 8, 16, 0);
+  VDUP(vector, q, int, s, 16, 8, 0);
+  VDUP(vector, q, int, s, 32, 4, 0);
+  VDUP(vector, q, int, s, 64, 2, 0);
+  VDUP(vector, q, uint, u, 8, 16, 0);
+  VDUP(vector, q, uint, u, 16, 8, 0);
+  VDUP(vector, q, uint, u, 32, 4, 0);
+  VDUP(vector, q, uint, u, 64, 2, 0);
+
+  /* Choose init value arbitrarily, will be used as shift amount */
+  /* Use values equal or one-less-than the type width to check
+     behaviour on limits */
+  /* Shift all lanes by 7 ... */
+  VDUP(vector_shift, , int, s, 8, 8, 7);
+  /* except: lane 0 (by 6), lane 1 (by 8) and lane 2 (by 9) */
+  TEST_VSET_LANE(vector_shift, , int, s, 8, 8, 0, 6);
+  TEST_VSET_LANE(vector_shift, , int, s, 8, 8, 1, 8);
+  TEST_VSET_LANE(vector_shift, , int, s, 8, 8, 2, 9);
+
+  VDUP(vector_shift, , int, s, 16, 4, 15);
+  TEST_VSET_LANE(vector_shift, , int, s, 16, 4, 0, 14);
+  TEST_VSET_LANE(vector_shift, , int, s, 16, 4, 1, 16);
+  TEST_VSET_LANE(vector_shift, , int, s, 16, 4, 2, 17);
+
+  VDUP(vector_shift, , int, s, 32, 2, 31);
+  TEST_VSET_LANE(vector_shift, , int, s, 32, 2, 1, 30);
+
+  VDUP(vector_shift, , int, s, 64, 1, 63);
+
+  VDUP(vector_shift, q, int, s, 8, 16, 8);
+  VDUP(vector_shift, q, int, s, 16, 8, 16);
+  VDUP(vector_shift, q, int, s, 32, 4, 32);
+  TEST_VSET_LANE(vector_shift, q, int, s, 32, 4, 1, 33);
+
+  VDUP(vector_shift, q, int, s, 64, 2, 64);
+  TEST_VSET_LANE(vector_shift, q, int, s, 64, 2, 1, 62);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (with input = 0)");
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VQSHL, int);
+  dump_results_hex2 (TEST_MSG, " (with input = 0)");
+
+
+  /* Use negative shift amounts */
+  VDUP(vector_shift, , int, s, 8, 8, -1);
+  VDUP(vector_shift, , int, s, 16, 4, -2);
+  VDUP(vector_shift, , int, s, 32, 2, -3);
+  VDUP(vector_shift, , int, s, 64, 1, -4);
+  VDUP(vector_shift, q, int, s, 8, 16, -7);
+  VDUP(vector_shift, q, int, s, 16, 8, -11);
+  VDUP(vector_shift, q, int, s, 32, 4, -13);
+  VDUP(vector_shift, q, int, s, 64, 2, -20);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (input 0 and negative shift amount)");
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VQSHL, int);
+  dump_results_hex2 (TEST_MSG, " (input 0 and negative shift amount)");
+
+  /* Test again, with predefined input values */
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+
+  /* Choose init value arbitrarily, will be used as shift amount */
+  VDUP(vector_shift, , int, s, 8, 8, 1);
+  VDUP(vector_shift, , int, s, 16, 4, 3);
+  VDUP(vector_shift, , int, s, 32, 2, 8);
+  VDUP(vector_shift, , int, s, 64, 1, -3);
+  VDUP(vector_shift, q, int, s, 8, 16, 10);
+  VDUP(vector_shift, q, int, s, 16, 8, 12);
+  VDUP(vector_shift, q, int, s, 32, 4, 32);
+  VDUP(vector_shift, q, int, s, 64, 2, 63);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VQSHL, int);
+  dump_results_hex (TEST_MSG);
+
+  /* Use negative shift amounts */
+  VDUP(vector_shift, , int, s, 8, 8, -1);
+  VDUP(vector_shift, , int, s, 16, 4, -2);
+  VDUP(vector_shift, , int, s, 32, 2, -3);
+  VDUP(vector_shift, , int, s, 64, 1, -4);
+  VDUP(vector_shift, q, int, s, 8, 16, -7);
+  VDUP(vector_shift, q, int, s, 16, 8, -11);
+  VDUP(vector_shift, q, int, s, 32, 4, -13);
+  VDUP(vector_shift, q, int, s, 64, 2, -20);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (negative shift amount)");
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VQSHL, int);
+  dump_results_hex2 (TEST_MSG, " (negative shift amount)");
+
+  /* Use large shift amounts */
+  VDUP(vector_shift, , int, s, 8, 8, 8);
+  VDUP(vector_shift, , int, s, 16, 4, 16);
+  VDUP(vector_shift, , int, s, 32, 2, 32);
+  VDUP(vector_shift, , int, s, 64, 1, 64);
+  VDUP(vector_shift, q, int, s, 8, 16, 8);
+  VDUP(vector_shift, q, int, s, 16, 8, 16);
+  VDUP(vector_shift, q, int, s, 32, 4, 32);
+  VDUP(vector_shift, q, int, s, 64, 2, 64);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (large shift amount, negative input)");
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VQSHL, int);
+  dump_results_hex2 (TEST_MSG, " (large shift amount, negative input)");
+
+  /* Fill input vector with max value, to check saturation on limits */
+  VDUP(vector, , int, s, 8, 8, 0x7F);
+  VDUP(vector, , int, s, 16, 4, 0x7FFF);
+  VDUP(vector, , int, s, 32, 2, 0x7FFFFFFF);
+  VDUP(vector, , int, s, 64, 1, 0x7FFFFFFFFFFFFFFFLL);
+  VDUP(vector, , uint, u, 8, 8, 0xFF);
+  VDUP(vector, , uint, u, 16, 4, 0xFFFF);
+  VDUP(vector, , uint, u, 32, 2, 0xFFFFFFFF);
+  VDUP(vector, , uint, u, 64, 1, 0xFFFFFFFFFFFFFFFFULL);
+  VDUP(vector, q, int, s, 8, 16, 0x7F);
+  VDUP(vector, q, int, s, 16, 8, 0x7FFF);
+  VDUP(vector, q, int, s, 32, 4, 0x7FFFFFFF);
+  VDUP(vector, q, int, s, 64, 2, 0x7FFFFFFFFFFFFFFFLL);
+  VDUP(vector, q, uint, u, 8, 16, 0xFF);
+  VDUP(vector, q, uint, u, 16, 8, 0xFFFF);
+  VDUP(vector, q, uint, u, 32, 4, 0xFFFFFFFF);
+  VDUP(vector, q, uint, u, 64, 2, 0xFFFFFFFFFFFFFFFFULL);
+
+  /* Shift by -1 */
+  VDUP(vector_shift, , int, s, 8, 8, -1);
+  VDUP(vector_shift, , int, s, 16, 4, -1);
+  VDUP(vector_shift, , int, s, 32, 2, -1);
+  VDUP(vector_shift, , int, s, 64, 1, -1);
+  VDUP(vector_shift, q, int, s, 8, 16, -1);
+  VDUP(vector_shift, q, int, s, 16, 8, -1);
+  VDUP(vector_shift, q, int, s, 32, 4, -1);
+  VDUP(vector_shift, q, int, s, 64, 2, -1);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check cumulative saturation)");
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VQSHL, int);
+  dump_results_hex2 (TEST_MSG, " (check cumulative saturation)");
+
+  /* Use large shift amounts */
+  VDUP(vector_shift, , int, s, 8, 8, 8);
+  VDUP(vector_shift, , int, s, 16, 4, 16);
+  VDUP(vector_shift, , int, s, 32, 2, 32);
+  VDUP(vector_shift, , int, s, 64, 1, 64);
+  VDUP(vector_shift, q, int, s, 8, 16, 8);
+  VDUP(vector_shift, q, int, s, 16, 8, 16);
+  VDUP(vector_shift, q, int, s, 32, 4, 32);
+  VDUP(vector_shift, q, int, s, 64, 2, 64);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (large shift amount, positive input)");
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VQSHL, int);
+  dump_results_hex2 (TEST_MSG, " (large shift amount, positive input)");
+
+  /* Check 64 bits saturation */
+  VDUP(vector, , int, s, 64, 1, -10);
+  VDUP(vector_shift, , int, s, 64, 1, 64);
+  VDUP(vector, q, int, s, 64, 2, 10);
+  VDUP(vector_shift, q, int, s, 64, 2, 64);
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check saturation on 64 bits)");
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VQSHL, int);
+  dump_results_hex2 (TEST_MSG, " (check saturation on 64 bits)");
+}
diff --git a/ref_vqshl_n.c b/ref_vqshl_n.c
new file mode 100644
index 0000000..3ee26b5
--- /dev/null
+++ b/ref_vqshl_n.c
@@ -0,0 +1,132 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2012 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN vqshl
+#define TEST_MSG "VQSHL_N/VQSHLQ_N"
+
+#define FNNAME1(NAME) void exec_ ## NAME ##_n (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN)
+{
+  /* Basic test: v2=vqshl_n(v1,v), then store the result.  */
+#define TEST_VQSHL_N2(INSN, Q, T1, T2, W, N, V)			\
+  Set_Neon_Cumulative_Sat(0, VECT_VAR(vector_res, T1, W, N));	\
+  VECT_VAR(vector_res, T1, W, N) =				\
+    INSN##Q##_n_##T2##W(VECT_VAR(vector, T1, W, N),		\
+			V);					\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),			\
+		    VECT_VAR(vector_res, T1, W, N));		\
+  dump_neon_cumulative_sat(TEST_MSG, xSTR(INSN##Q##_n_##T2##W),	\
+			   xSTR(T1), W, N)
+
+  /* Two auxliary macros are necessary to expand INSN */
+#define TEST_VQSHL_N1(INSN, T3, Q, T1, T2, W, N)	\
+  TEST_VQSHL_N2(INSN, T3, Q, T1, T2, W, N)
+
+#define TEST_VQSHL_N(T3, Q, T1, T2, W, N)	\
+  TEST_VQSHL_N1(INSN, T3, Q, T1, T2, W, N)
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+  clean_results ();
+
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+
+  /* Choose shift amount arbitrarily  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_VQSHL_N(, int, s, 8, 8, 2);
+  TEST_VQSHL_N(, int, s, 16, 4, 1);
+  TEST_VQSHL_N(, int, s, 32, 2, 1);
+  TEST_VQSHL_N(, int, s, 64, 1, 2);
+  TEST_VQSHL_N(, uint, u, 8, 8, 3);
+  TEST_VQSHL_N(, uint, u, 16, 4, 2);
+  TEST_VQSHL_N(, uint, u, 32, 2, 3);
+  TEST_VQSHL_N(, uint, u, 64, 1, 3);
+
+  TEST_VQSHL_N(q, int, s, 8, 16, 2);
+  TEST_VQSHL_N(q, int, s, 16, 8, 1);
+  TEST_VQSHL_N(q, int, s, 32, 4, 1);
+  TEST_VQSHL_N(q, int, s, 64, 2, 2);
+  TEST_VQSHL_N(q, uint, u, 8, 16, 3);
+  TEST_VQSHL_N(q, uint, u, 16, 8, 2);
+  TEST_VQSHL_N(q, uint, u, 32, 4, 3);
+  TEST_VQSHL_N(q, uint, u, 64, 2, 3);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex (TEST_MSG);
+
+
+  /* Fill input vector with max value, to check saturation on limits */
+  VDUP(vector, , int, s, 8, 8, 0x7F);
+  VDUP(vector, , int, s, 16, 4, 0x7FFF);
+  VDUP(vector, , int, s, 32, 2, 0x7FFFFFFF);
+  VDUP(vector, , int, s, 64, 1, 0x7FFFFFFFFFFFFFFFLL);
+  VDUP(vector, , uint, u, 8, 8, 0xFF);
+  VDUP(vector, , uint, u, 16, 4, 0xFFFF);
+  VDUP(vector, , uint, u, 32, 2, 0xFFFFFFFF);
+  VDUP(vector, , uint, u, 64, 1, 0xFFFFFFFFFFFFFFFFULL);
+  VDUP(vector, q, int, s, 8, 16, 0x7F);
+  VDUP(vector, q, int, s, 16, 8, 0x7FFF);
+  VDUP(vector, q, int, s, 32, 4, 0x7FFFFFFF);
+  VDUP(vector, q, int, s, 64, 2, 0x7FFFFFFFFFFFFFFFLL);
+  VDUP(vector, q, uint, u, 8, 16, 0xFF);
+  VDUP(vector, q, uint, u, 16, 8, 0xFFFF);
+  VDUP(vector, q, uint, u, 32, 4, 0xFFFFFFFF);
+  VDUP(vector, q, uint, u, 64, 2, 0xFFFFFFFFFFFFFFFFULL);
+
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check saturation with large positive input)");
+  TEST_VQSHL_N(, int, s, 8, 8, 2);
+  TEST_VQSHL_N(, int, s, 16, 4, 1);
+  TEST_VQSHL_N(, int, s, 32, 2, 1);
+  TEST_VQSHL_N(, int, s, 64, 1, 2);
+  TEST_VQSHL_N(, uint, u, 8, 8, 3);
+  TEST_VQSHL_N(, uint, u, 16, 4, 2);
+  TEST_VQSHL_N(, uint, u, 32, 2, 3);
+  TEST_VQSHL_N(, uint, u, 64, 1, 3);
+
+  TEST_VQSHL_N(q, int, s, 8, 16, 2);
+  TEST_VQSHL_N(q, int, s, 16, 8, 1);
+  TEST_VQSHL_N(q, int, s, 32, 4, 1);
+  TEST_VQSHL_N(q, int, s, 64, 2, 2);
+  TEST_VQSHL_N(q, uint, u, 8, 16, 3);
+  TEST_VQSHL_N(q, uint, u, 16, 8, 2);
+  TEST_VQSHL_N(q, uint, u, 32, 4, 3);
+  TEST_VQSHL_N(q, uint, u, 64, 2, 3);
+
+  dump_results_hex2 (TEST_MSG, " (check saturation with large positive input)");
+}
diff --git a/ref_vqshlu_n.c b/ref_vqshlu_n.c
new file mode 100644
index 0000000..27d53de
--- /dev/null
+++ b/ref_vqshlu_n.c
@@ -0,0 +1,157 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2012 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN vqshlu
+#define TEST_MSG "VQSHLU_N/VQSHLUQ_N"
+
+#define FNNAME1(NAME) void exec_ ## NAME ## _n(void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN)
+{
+  /* Basic test: v2=vqshlu_n(v1,v), then store the result.  */
+#define TEST_VQSHLU_N2(INSN, Q, T1, T2, T3, T4, W, N, V)		\
+  Set_Neon_Cumulative_Sat(0, VECT_VAR(vector_res, T3, W, N));		\
+  VECT_VAR(vector_res, T3, W, N) =					\
+    INSN##Q##_n_##T2##W(VECT_VAR(vector, T1, W, N),			\
+			V);						\
+    vst1##Q##_##T4##W(VECT_VAR(result, T3, W, N),			\
+		      VECT_VAR(vector_res, T3, W, N));			\
+    dump_neon_cumulative_sat(TEST_MSG, xSTR(INSN##Q##_n_##T2##W),	\
+			       xSTR(T1), W, N)
+
+  /* Two auxliary macros are necessary to expand INSN */
+#define TEST_VQSHLU_N1(INSN, Q, T1, T2, T3, T4, W, N, V)	\
+  TEST_VQSHLU_N2(INSN, Q, T1, T2, T3, T4, W, N, V)
+
+#define TEST_VQSHLU_N(Q, T1, T2, T3, T4, W, N, V)		\
+  TEST_VQSHLU_N1(INSN, Q, T1, T2, T3, T4, W, N, V)
+
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+  clean_results ();
+
+  /* Fill input vector with negative values, to check saturation on limits */
+  VDUP(vector, , int, s, 8, 8, -1);
+  VDUP(vector, , int, s, 16, 4, -2);
+  VDUP(vector, , int, s, 32, 2, -3);
+  VDUP(vector, , int, s, 64, 1, -4);
+  VDUP(vector, q, int, s, 8, 16, -1);
+  VDUP(vector, q, int, s, 16, 8, -2);
+  VDUP(vector, q, int, s, 32, 4, -3);
+  VDUP(vector, q, int, s, 64, 2, -4);
+
+  /* Choose shift amount arbitrarily  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (negative input)");
+  TEST_VQSHLU_N(, int, s, uint, u, 8, 8, 2);
+  TEST_VQSHLU_N(, int, s, uint, u, 16, 4, 1);
+  TEST_VQSHLU_N(, int, s, uint, u, 32, 2, 1);
+  TEST_VQSHLU_N(, int, s, uint, u, 64, 1, 2);
+
+  TEST_VQSHLU_N(q, int, s, uint, u, 8, 16, 2);
+  TEST_VQSHLU_N(q, int, s, uint, u, 16, 8, 1);
+  TEST_VQSHLU_N(q, int, s, uint, u, 32, 4, 1);
+  TEST_VQSHLU_N(q, int, s, uint, u, 64, 2, 2);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex2 (TEST_MSG, " (negative input)");
+
+  /* Fill input vector with max value, to check saturation on limits */
+  VDUP(vector, , int, s, 8, 8, 0x7F);
+  VDUP(vector, , int, s, 16, 4, 0x7FFF);
+  VDUP(vector, , int, s, 32, 2, 0x7FFFFFFF);
+  VDUP(vector, , int, s, 64, 1, 0x7FFFFFFFFFFFFFFFLL);
+  VDUP(vector, q, int, s, 8, 16, 0x7F);
+  VDUP(vector, q, int, s, 16, 8, 0x7FFF);
+  VDUP(vector, q, int, s, 32, 4, 0x7FFFFFFF);
+  VDUP(vector, q, int, s, 64, 2, 0x7FFFFFFFFFFFFFFFULL);
+
+  /* shift by 1  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check cumulative saturation: shift by 1)");
+  TEST_VQSHLU_N(, int, s, uint, u, 8, 8, 1);
+  TEST_VQSHLU_N(, int, s, uint, u, 16, 4, 1);
+  TEST_VQSHLU_N(, int, s, uint, u, 32, 2, 1);
+  TEST_VQSHLU_N(, int, s, uint, u, 64, 1, 1);
+
+  TEST_VQSHLU_N(q, int, s, uint, u, 8, 16, 1);
+  TEST_VQSHLU_N(q, int, s, uint, u, 16, 8, 1);
+  TEST_VQSHLU_N(q, int, s, uint, u, 32, 4, 1);
+  TEST_VQSHLU_N(q, int, s, uint, u, 64, 2, 1);
+
+  dump_results_hex2 (TEST_MSG, " (check cumulative saturation: shift by 1)");
+
+  /* shift by 2 to force saturation  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check cumulative saturation: shift by 2)");
+  TEST_VQSHLU_N(, int, s, uint, u, 8, 8, 2);
+  TEST_VQSHLU_N(, int, s, uint, u, 16, 4, 2);
+  TEST_VQSHLU_N(, int, s, uint, u, 32, 2, 2);
+  TEST_VQSHLU_N(, int, s, uint, u, 64, 1, 2);
+
+  TEST_VQSHLU_N(q, int, s, uint, u, 8, 16, 2);
+  TEST_VQSHLU_N(q, int, s, uint, u, 16, 8, 2);
+  TEST_VQSHLU_N(q, int, s, uint, u, 32, 4, 2);
+  TEST_VQSHLU_N(q, int, s, uint, u, 64, 2, 2);
+
+  dump_results_hex2 (TEST_MSG, " (check cumulative saturation: shift by 2)");
+
+  /* Fill input vector with positive values, to check normal case */
+  VDUP(vector, , int, s, 8, 8, 1);
+  VDUP(vector, , int, s, 16, 4, 2);
+  VDUP(vector, , int, s, 32, 2, 3);
+  VDUP(vector, , int, s, 64, 1, 4);
+  VDUP(vector, q, int, s, 8, 16, 5);
+  VDUP(vector, q, int, s, 16, 8, 6);
+  VDUP(vector, q, int, s, 32, 4, 7);
+  VDUP(vector, q, int, s, 64, 2, 8);
+
+  /* shift arbitrary amount  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_VQSHLU_N(, int, s, uint, u, 8, 8, 1);
+  TEST_VQSHLU_N(, int, s, uint, u, 16, 4, 2);
+  TEST_VQSHLU_N(, int, s, uint, u, 32, 2, 3);
+  TEST_VQSHLU_N(, int, s, uint, u, 64, 1, 4);
+
+  TEST_VQSHLU_N(q, int, s, uint, u, 8, 16, 5);
+  TEST_VQSHLU_N(q, int, s, uint, u, 16, 8, 6);
+  TEST_VQSHLU_N(q, int, s, uint, u, 32, 4, 7);
+  TEST_VQSHLU_N(q, int, s, uint, u, 64, 2, 8);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vqshrn_n.c b/ref_vqshrn_n.c
new file mode 100644
index 0000000..96b8d61
--- /dev/null
+++ b/ref_vqshrn_n.c
@@ -0,0 +1,135 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2012 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN vqshrn_n
+#define TEST_MSG "VQSHRN_N"
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN)
+{
+  /* Basic test: y=vqshrn_n(x,v), then store the result.  */
+#define TEST_VQSHRN_N2(INSN, T1, T2, W, W2, N, V)		\
+  Set_Neon_Cumulative_Sat(0, VECT_VAR(vector_res, T1, W2, N));	\
+  VECT_VAR(vector_res, T1, W2, N) =				\
+    INSN##_##T2##W(VECT_VAR(vector, T1, W, N),			\
+		   V);						\
+  vst1_##T2##W2(VECT_VAR(result, T1, W2, N),			\
+		VECT_VAR(vector_res, T1, W2, N));		\
+  dump_neon_cumulative_sat(TEST_MSG, xSTR(INSN##_##T2##W),	\
+			   xSTR(T1), W, N)
+
+  /* Two auxliary macros are necessary to expand INSN */
+#define TEST_VQSHRN_N1(INSN, T1, T2, W, W2, N, V)	\
+  TEST_VQSHRN_N2(INSN, T1, T2, W, W2, N, V)
+
+#define TEST_VQSHRN_N(T1, T2, W, W2, N, V)	\
+  TEST_VQSHRN_N1(INSN, T1, T2, W, W2, N, V)
+
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+
+  /* vector is twice as large as vector_res */
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+  DECL_VARIABLE(vector, int, 64, 2);
+  DECL_VARIABLE(vector, uint, 16, 8);
+  DECL_VARIABLE(vector, uint, 32, 4);
+  DECL_VARIABLE(vector, uint, 64, 2);
+
+  DECL_VARIABLE(vector_res, int, 8, 8);
+  DECL_VARIABLE(vector_res, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 2);
+  DECL_VARIABLE(vector_res, uint, 8, 8);
+  DECL_VARIABLE(vector_res, uint, 16, 4);
+  DECL_VARIABLE(vector_res, uint, 32, 2);
+
+  clean_results ();
+
+  VLOAD(vector, buffer, q, int, s, 16, 8);
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+  VLOAD(vector, buffer, q, int, s, 64, 2);
+  VLOAD(vector, buffer, q, uint, u, 16, 8);
+  VLOAD(vector, buffer, q, uint, u, 32, 4);
+  VLOAD(vector, buffer, q, uint, u, 64, 2);
+
+  /* Choose shift amount arbitrarily  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_VQSHRN_N(int, s, 16, 8, 8, 1);
+  TEST_VQSHRN_N(int, s, 32, 16, 4, 1);
+  TEST_VQSHRN_N(int, s, 64, 32, 2, 2);
+  TEST_VQSHRN_N(uint, u, 16, 8, 8, 2);
+  TEST_VQSHRN_N(uint, u, 32, 16, 4, 3);
+  TEST_VQSHRN_N(uint, u, 64, 32, 2, 3);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex (TEST_MSG);
+
+
+  /* Another set of tests */
+  VDUP(vector, q, int, s, 16, 8, 0x7FFF);
+  VDUP(vector, q, int, s, 32, 4, 0x7FFFFFFF);
+  VDUP(vector, q, int, s, 64, 2, 0x7FFFFFFFFFFFFFFFLL);
+  VDUP(vector, q, uint, u, 16, 8, 0xFFFF);
+  VDUP(vector, q, uint, u, 32, 4, 0xFFFFFFFF);
+  VDUP(vector, q, uint, u, 64, 2, 0xFFFFFFFFFFFFFFFFULL);
+
+  /* shift by 3 to exercise saturation code in the lib  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check saturation: shift by 3)");
+  TEST_VQSHRN_N(int, s, 16, 8, 8, 3);
+  TEST_VQSHRN_N(int, s, 32, 16, 4, 3);
+  TEST_VQSHRN_N(int, s, 64, 32, 2, 3);
+  TEST_VQSHRN_N(uint, u, 16, 8, 8, 3);
+  TEST_VQSHRN_N(uint, u, 32, 16, 4, 3);
+  TEST_VQSHRN_N(uint, u, 64, 32, 2, 3);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex2 (TEST_MSG, " (check saturation: shift by 3)");
+
+
+  /* shift by max to exercise saturation code in the lib  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check saturation: shift by max)");
+  TEST_VQSHRN_N(int, s, 16, 8, 8, 8);
+  TEST_VQSHRN_N(int, s, 32, 16, 4, 16);
+  TEST_VQSHRN_N(int, s, 64, 32, 2, 32);
+  TEST_VQSHRN_N(uint, u, 16, 8, 8, 8);
+  TEST_VQSHRN_N(uint, u, 32, 16, 4, 16);
+  TEST_VQSHRN_N(uint, u, 64, 32, 2, 32);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex2 (TEST_MSG, " (check saturation: shift by max)");
+}
diff --git a/ref_vqshrun_n.c b/ref_vqshrun_n.c
new file mode 100644
index 0000000..871da96
--- /dev/null
+++ b/ref_vqshrun_n.c
@@ -0,0 +1,116 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2012 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define INSN vqshrun_n
+#define TEST_MSG "VQSHRUN_N"
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN)
+{
+  /* Basic test: y=vqshrun_n(x,v), then store the result.  */
+#define TEST_VQSHRUN_N2(INSN, T1, T2, W, W2, N, V)			\
+  Set_Neon_Cumulative_Sat(0, VECT_VAR(vector_res, uint, W2, N));	\
+  VECT_VAR(vector_res, uint, W2, N) =					\
+    INSN##_##T2##W(VECT_VAR(vector, T1, W, N),				\
+		   V);							\
+    vst1_u##W2(VECT_VAR(result, uint, W2, N),				\
+	       VECT_VAR(vector_res, uint, W2, N));			\
+      dump_neon_cumulative_sat(TEST_MSG, xSTR(INSN##_##T2##W),		\
+			       xSTR(T1), W, N)
+
+  /* Two auxliary macros are necessary to expand INSN */
+#define TEST_VQSHRUN_N1(INSN, T1, T2, W, W2, N, V)	\
+  TEST_VQSHRUN_N2(INSN, T1, T2, W, W2, N, V)
+
+#define TEST_VQSHRUN_N(T1, T2, W, W2, N, V)	\
+  TEST_VQSHRUN_N1(INSN, T1, T2, W, W2, N, V)
+
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+
+  /* vector is twice as large as vector_res */
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+  DECL_VARIABLE(vector, int, 64, 2);
+
+  DECL_VARIABLE(vector_res, uint, 8, 8);
+  DECL_VARIABLE(vector_res, uint, 16, 4);
+  DECL_VARIABLE(vector_res, uint, 32, 2);
+
+  clean_results ();
+
+  /* Fill input vector with negative values, to check saturation on limits */
+  VDUP(vector, q, int, s, 16, 8, -2);
+  VDUP(vector, q, int, s, 32, 4, -3);
+  VDUP(vector, q, int, s, 64, 2, -4);
+
+  /* Choose shift amount arbitrarily  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (negative input)");
+  TEST_VQSHRUN_N(int, s, 16, 8, 8, 3);
+  TEST_VQSHRUN_N(int, s, 32, 16, 4, 4);
+  TEST_VQSHRUN_N(int, s, 64, 32, 2, 2);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex2 (TEST_MSG, " (negative input)");
+
+  /* Fill input vector with max value, to check saturation on limits */
+  VDUP(vector, q, int, s, 16, 8, 0x7FFF);
+  VDUP(vector, q, int, s, 32, 4, 0x7FFFFFFF);
+  VDUP(vector, q, int, s, 64, 2, 0x7FFFFFFFFFFFFFFFLL);
+
+  /* shift by 1  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n",
+	  TEST_MSG " (check cumulative saturation)");
+  TEST_VQSHRUN_N(int, s, 16, 8, 8, 1);
+  TEST_VQSHRUN_N(int, s, 32, 16, 4, 1);
+  TEST_VQSHRUN_N(int, s, 64, 32, 2, 1);
+
+  dump_results_hex2 (TEST_MSG, " (check cumulative saturation)");
+
+  /* Fill input vector with positive values, to check normal case */
+  VDUP(vector, q, int, s, 16, 8, 0x1234);
+  VDUP(vector, q, int, s, 32, 4, 0x87654321);
+  VDUP(vector, q, int, s, 64, 2, 0xDEADBEEF);
+
+  /* shift arbitrary amount  */
+  fprintf(ref_file, "\n%s cumulative saturation output:\n", TEST_MSG);
+  TEST_VQSHRUN_N(int, s, 16, 8, 8, 6);
+  TEST_VQSHRUN_N(int, s, 32, 16, 4, 7);
+  TEST_VQSHRUN_N(int, s, 64, 32, 2, 8);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vqsub.c b/ref_vqsub.c
new file mode 100644
index 0000000..dc44505
--- /dev/null
+++ b/ref_vqsub.c
@@ -0,0 +1,163 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vqsub
+#define TEST_MSG "VQSUB/VQSUBQ"
+
+/* Extra tests for functions requiring types larger than 64 bits to
+   compute saturation */
+void vqsub_64(void);
+#define EXTRA_TESTS vqsub_64
+
+#include "ref_v_binary_sat_op.c"
+
+void vqsub_64(void)
+{
+  int i;
+
+  DECL_VARIABLE_ALL_VARIANTS(vector1);
+  DECL_VARIABLE_ALL_VARIANTS(vector2);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+  /* Initialize input "vector1" from "buffer"  */
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector1, buffer);
+
+  VDUP(vector2, , int, s, 64, 1, 0x0);
+  VDUP(vector2, , uint, u, 64, 1, 0x0);
+  VDUP(vector2, q, int, s, 64, 2, 0x0);
+  VDUP(vector2, q, uint, u, 64, 2, 0x0);
+
+  fprintf(ref_file,
+	  "\n%s 64 bits saturation cumulative saturation output:\n",
+	  TEST_MSG);
+  TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 64, 1);
+  TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 64, 1);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 64, 2);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 64, 2);
+
+  fprintf(ref_file, "\n64 bits saturation:\n");
+  DUMP(TEST_MSG, int, 64, 1, PRIx64);
+  DUMP(TEST_MSG, uint, 64, 1, PRIx64);
+  DUMP(TEST_MSG, int, 64, 2, PRIx64);
+  DUMP(TEST_MSG, uint, 64, 2, PRIx64);
+
+  /* Another set of tests */
+  VDUP(vector2, , int, s, 64, 1, 0x44);
+  VDUP(vector2, , uint, u, 64, 1, 0x88);
+  VDUP(vector2, q, int, s, 64, 2, 0x44);
+  VDUP(vector2, q, uint, u, 64, 2, 0x88);
+
+  fprintf(ref_file,
+	  "\n%s 64 bits saturation cumulative saturation output:\n",
+	  TEST_MSG);
+  TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 64, 1);
+  TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 64, 1);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 64, 2);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 64, 2);
+
+  DUMP(TEST_MSG, int, 64, 1, PRIx64);
+  DUMP(TEST_MSG, uint, 64, 1, PRIx64);
+  DUMP(TEST_MSG, int, 64, 2, PRIx64);
+  DUMP(TEST_MSG, uint, 64, 2, PRIx64);
+
+  /* Another set of tests */
+  VDUP(vector2, , int, s, 64, 1, 0x7fffffffffffffffLL);
+  VDUP(vector2, , uint, u, 64, 1, 0xffffffffffffffffULL);
+
+  /* To check positive saturation, we need to write a positive value
+     in vector1 */
+  VDUP(vector1, q, int, s, 64, 2, 0x3fffffffffffffffLL);
+  VDUP(vector2, q, int, s, 64, 2, 0x8000000000000000LL);
+
+  VDUP(vector2, q, uint, u, 64, 2, 0xffffffffffffffffULL);
+
+  fprintf(ref_file,
+	  "\n%s 64 bits saturation cumulative saturation output:\n",
+	  TEST_MSG);
+  TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 64, 1);
+  TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 64, 1);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 64, 2);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 64, 2);
+
+  DUMP(TEST_MSG, int, 64, 1, PRIx64);
+  DUMP(TEST_MSG, uint, 64, 1, PRIx64);
+  DUMP(TEST_MSG, int, 64, 2, PRIx64);
+  DUMP(TEST_MSG, uint, 64, 2, PRIx64);
+
+  /* To improve coverage, check saturation with less than 64 bits too */
+  fprintf(ref_file, "\nless than 64 bits saturation:\n");
+  VDUP(vector2, , int, s, 8, 8, 0x7F);
+  VDUP(vector2, , int, s, 16, 4, 0x7FFF);
+  VDUP(vector2, , int, s, 32, 2, 0x7FFFFFFF);
+  VDUP(vector2, q, int, s, 8, 16, 0x7F);
+  VDUP(vector2, q, int, s, 16, 8, 0x7FFF);
+  VDUP(vector2, q, int, s, 32, 4, 0x7FFFFFFF);
+
+  TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 8, 8);
+  TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 16, 4);
+  TEST_BINARY_SAT_OP(INSN_NAME, , int, s, 32, 2);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 8, 16);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 16, 8);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, int, s, 32, 4);
+
+  DUMP(TEST_MSG, int, 8, 8, PRIx8);
+  DUMP(TEST_MSG, int, 16, 4, PRIx16);
+  DUMP(TEST_MSG, int, 32, 2, PRIx32);
+  DUMP(TEST_MSG, int, 8, 16, PRIx8);
+  DUMP(TEST_MSG, int, 16, 8, PRIx16);
+  DUMP(TEST_MSG, int, 32, 4, PRIx32);
+
+
+  VDUP(vector1, , uint, u, 8, 8, 0x10);
+  VDUP(vector1, , uint, u, 16, 4, 0x10);
+  VDUP(vector1, , uint, u, 32, 2, 0x10);
+  VDUP(vector1, q, uint, u, 8, 16, 0x10);
+  VDUP(vector1, q, uint, u, 16, 8, 0x10);
+  VDUP(vector1, q, uint, u, 32, 4, 0x10);
+
+  VDUP(vector2, , uint, u, 8, 8, 0x20);
+  VDUP(vector2, , uint, u, 16, 4, 0x20);
+  VDUP(vector2, , uint, u, 32, 2, 0x20);
+  VDUP(vector2, q, uint, u, 8, 16, 0x20);
+  VDUP(vector2, q, uint, u, 16, 8, 0x20);
+  VDUP(vector2, q, uint, u, 32, 4, 0x20);
+
+  fprintf(ref_file,
+	  "\n%s less than 64 bits saturation cumulative saturation output:\n",
+	  TEST_MSG);
+  TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 8, 8);
+  TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 16, 4);
+  TEST_BINARY_SAT_OP(INSN_NAME, , uint, u, 32, 2);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 8, 16);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 16, 8);
+  TEST_BINARY_SAT_OP(INSN_NAME, q, uint, u, 32, 4);
+
+  DUMP(TEST_MSG, uint, 8, 8, PRIx8);
+  DUMP(TEST_MSG, uint, 16, 4, PRIx16);
+  DUMP(TEST_MSG, uint, 32, 2, PRIx32);
+  DUMP(TEST_MSG, uint, 8, 16, PRIx8);
+  DUMP(TEST_MSG, uint, 16, 8, PRIx16);
+  DUMP(TEST_MSG, uint, 32, 4, PRIx32);
+}
diff --git a/ref_vraddhn.c b/ref_vraddhn.c
new file mode 100644
index 0000000..c6aac33
--- /dev/null
+++ b/ref_vraddhn.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vraddhn
+#define TEST_MSG "VRADDHN"
+
+#include "ref_vaddhn.c"
diff --git a/ref_vrecpe.c b/ref_vrecpe.c
new file mode 100644
index 0000000..5bbbf7c
--- /dev/null
+++ b/ref_vrecpe.c
@@ -0,0 +1,143 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+#include <math.h>
+
+#define TEST_MSG "VRECPE/VRECPEQ"
+void exec_vrecpe(void)
+{
+  int i;
+
+  /* Basic test: y=vrecpe(x), then store the result.  */
+#define TEST_VRECPE(Q, T1, T2, W, N)					\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vrecpe##Q##_##T2##W(VECT_VAR(vector, T1, W, N));			\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),				\
+		    VECT_VAR(vector_res, T1, W, N))
+
+    /* With ARM RVCT, we need to declare variables before any executable
+       statement  */
+
+  /* No need for 64 bits variants */
+  DECL_VARIABLE(vector, uint, 32, 2);
+  DECL_VARIABLE(vector, uint, 32, 4);
+  DECL_VARIABLE(vector, float, 32, 2);
+  DECL_VARIABLE(vector, float, 32, 4);
+
+  DECL_VARIABLE(vector_res, uint, 32, 2);
+  DECL_VARIABLE(vector_res, uint, 32, 4);
+  DECL_VARIABLE(vector_res, float, 32, 2);
+  DECL_VARIABLE(vector_res, float, 32, 4);
+
+  clean_results ();
+
+  /* Choose init value arbitrarily */
+  VDUP(vector, , uint, u, 32, 2, 0x12345678);
+  VDUP(vector, , float, f, 32, 2, 1.9f);
+  VDUP(vector, q, uint, u, 32, 4, 0xABCDEF10);
+  VDUP(vector, q, float, f, 32, 4, 125.0f);
+
+  /* Apply the operator */
+  TEST_VRECPE(, uint, u, 32, 2);
+  TEST_VRECPE(, float, f, 32, 2);
+  TEST_VRECPE(q, uint, u, 32, 4);
+  TEST_VRECPE(q, float, f, 32, 4);
+
+  fprintf (ref_file, "\n%s %s output:\n", TEST_MSG, " (positive input)");
+  DUMP(TEST_MSG, uint, 32, 2, PRIx32);
+  DUMP(TEST_MSG, uint, 32, 4, PRIx32);
+  DUMP_FP(TEST_MSG, float, 32, 2, PRIx32);
+  DUMP_FP(TEST_MSG, float, 32, 4, PRIx32);
+
+  /* Choose init value arbitrarily */
+  VDUP(vector, , uint, u, 32, 2, 0xFFFFFFFF);
+  VDUP(vector, , float, f, 32, 2, -10.0f);
+  VDUP(vector, q, uint, u, 32, 4, 0x89081234);
+  VDUP(vector, q, float, f, 32, 4, -125.0f);
+
+  /* Apply the operator */
+  TEST_VRECPE(, uint, u, 32, 2);
+  TEST_VRECPE(, float, f, 32, 2);
+  TEST_VRECPE(q, uint, u, 32, 4);
+  TEST_VRECPE(q, float, f, 32, 4);
+
+  fprintf (ref_file, "\n%s %s output:\n", TEST_MSG, " (negative input)");
+  DUMP(TEST_MSG, uint, 32, 2, PRIx32);
+  DUMP(TEST_MSG, uint, 32, 4, PRIx32);
+  DUMP_FP(TEST_MSG, float, 32, 2, PRIx32);
+  DUMP_FP(TEST_MSG, float, 32, 4, PRIx32);
+
+  /* Test FP variants with special input values (NaN, infinity) */
+  VDUP(vector, , float, f, 32, 2, NAN);
+  VDUP(vector, q, float, f, 32, 4, HUGE_VALF);
+
+  /* Apply the operator */
+  TEST_VRECPE(, float, f, 32, 2);
+  TEST_VRECPE(q, float, f, 32, 4);
+
+  fprintf (ref_file, "\n%s %s output:\n", TEST_MSG, " FP special (NaN, infinity)");
+  DUMP_FP(TEST_MSG, float, 32, 2, PRIx32);
+  DUMP_FP(TEST_MSG, float, 32, 4, PRIx32);
+
+  /* Test FP variants with special input values (zero, large value) */
+  VDUP(vector, , float, f, 32, 2, 0.0f);
+  VDUP(vector, q, float, f, 32, 4, 9.0e37f);
+
+  /* Apply the operator */
+  TEST_VRECPE(, float, f, 32, 2);
+  TEST_VRECPE(q, float, f, 32, 4);
+
+  fprintf (ref_file, "\n%s %s output:\n", TEST_MSG, " FP special (zero, large value)");
+  DUMP_FP(TEST_MSG, float, 32, 2, PRIx32);
+  DUMP_FP(TEST_MSG, float, 32, 4, PRIx32);
+
+  /* Test FP variants with special input values (-0, -infinity) */
+  VDUP(vector, , float, f, 32, 2, -0.0f);
+  VDUP(vector, q, float, f, 32, 4, -HUGE_VALF);
+
+  /* Apply the operator */
+  TEST_VRECPE(, float, f, 32, 2);
+  TEST_VRECPE(q, float, f, 32, 4);
+
+  fprintf (ref_file, "\n%s %s output:\n", TEST_MSG, " FP special (-0, -infinity)");
+  DUMP_FP(TEST_MSG, float, 32, 2, PRIx32);
+  DUMP_FP(TEST_MSG, float, 32, 4, PRIx32);
+
+  /* Test FP variants with special input values (large negative value) */
+  VDUP(vector, , float, f, 32, 2, -9.0e37f);
+
+  /* Apply the operator */
+  TEST_VRECPE(, float, f, 32, 2);
+
+  fprintf (ref_file, "\n%s %s output:\n", TEST_MSG, " FP special (large negative value)");
+  DUMP_FP(TEST_MSG, float, 32, 2, PRIx32);
+}
diff --git a/ref_vrecps.c b/ref_vrecps.c
new file mode 100644
index 0000000..15f841e
--- /dev/null
+++ b/ref_vrecps.c
@@ -0,0 +1,120 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+#include <math.h>
+
+#define TEST_MSG "VRECPS/VRECPSQ"
+void exec_vrecps(void)
+{
+  int i;
+
+  /* Basic test: y=vrecps(x), then store the result.  */
+#define TEST_VRECPS(Q, T1, T2, W, N)					\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vrecps##Q##_##T2##W(VECT_VAR(vector, T1, W, N),			\
+			VECT_VAR(vector2, T1, W, N));			\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),				\
+		    VECT_VAR(vector_res, T1, W, N))
+
+    /* With ARM RVCT, we need to declare variables before any executable
+       statement  */
+
+  /* No need for integer variants */
+  DECL_VARIABLE(vector, float, 32, 2);
+  DECL_VARIABLE(vector, float, 32, 4);
+
+  DECL_VARIABLE(vector2, float, 32, 2);
+  DECL_VARIABLE(vector2, float, 32, 4);
+
+  DECL_VARIABLE(vector_res, float, 32, 2);
+  DECL_VARIABLE(vector_res, float, 32, 4);
+
+  clean_results ();
+
+  /* Choose init value arbitrarily */
+  VDUP(vector, , float, f, 32, 2, 12.9f);
+  VDUP(vector, q, float, f, 32, 4, 9.2f);
+
+  VDUP(vector2, , float, f, 32, 2, 8.9f);
+  VDUP(vector2, q, float, f, 32, 4, 3.2f);
+
+  /* Apply the operator */
+  TEST_VRECPS(, float, f, 32, 2);
+  TEST_VRECPS(q, float, f, 32, 4);
+
+  fprintf (ref_file, "\n%s output:\n", TEST_MSG);
+  fprintf (gcc_tests_file, "\n%s output:\n", TEST_MSG);
+  DUMP_FP(TEST_MSG, float, 32, 2, PRIx32);
+  DUMP_FP(TEST_MSG, float, 32, 4, PRIx32);
+
+
+  /* Test FP variants with special input values (NaN) */
+  VDUP(vector, , float, f, 32, 2, NAN);
+  VDUP(vector2, q, float, f, 32, 4, NAN);
+
+  /* Apply the operator */
+  TEST_VRECPS(, float, f, 32, 2);
+  TEST_VRECPS(q, float, f, 32, 4);
+
+  fprintf (ref_file, "\n%s output:\n", TEST_MSG " FP special (NAN) and normal values");
+  DUMP_FP(TEST_MSG, float, 32, 2, PRIx32);
+  DUMP_FP(TEST_MSG, float, 32, 4, PRIx32);
+
+
+  /* Test FP variants with special input values (infinity, 0) */
+  VDUP(vector, , float, f, 32, 2, HUGE_VALF);
+  VDUP(vector, q, float, f, 32, 4, 0.0f);
+  VDUP(vector2, q, float, f, 32, 4, 3.2f); /* Restore a normal value */
+
+  /* Apply the operator */
+  TEST_VRECPS(, float, f, 32, 2);
+  TEST_VRECPS(q, float, f, 32, 4);
+
+  fprintf (ref_file, "\n%s output:\n", TEST_MSG " FP special (infinity, 0) and normal values");
+  DUMP_FP(TEST_MSG, float, 32, 2, PRIx32);
+  DUMP_FP(TEST_MSG, float, 32, 4, PRIx32);
+
+
+  /* Test FP variants with only special input values (infinity, 0) */
+  VDUP(vector, , float, f, 32, 2, HUGE_VALF);
+  VDUP(vector, q, float, f, 32, 4, 0.0f);
+  VDUP(vector2, , float, f, 32, 2, 0.0f);
+  VDUP(vector2, q, float, f, 32, 4, HUGE_VALF);
+
+  /* Apply the operator */
+  TEST_VRECPS(, float, f, 32, 2);
+  TEST_VRECPS(q, float, f, 32, 4);
+
+  fprintf (ref_file, "\n%s output:\n", TEST_MSG " FP special (infinity, 0)");
+  DUMP_FP(TEST_MSG, float, 32, 2, PRIx32);
+  DUMP_FP(TEST_MSG, float, 32, 4, PRIx32);
+}
diff --git a/ref_vreinterpret.c b/ref_vreinterpret.c
new file mode 100644
index 0000000..1b3241c
--- /dev/null
+++ b/ref_vreinterpret.c
@@ -0,0 +1,398 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VREINTERPRET/VREINTERPRETQ"
+
+void exec_vreinterpret (void)
+{
+  int i;
+
+  /* Basic test: y=vreinterpret(x), then store the result.  */
+#define TEST_VREINTERPRET(Q, T1, T2, W, N, TS1, TS2, WS, NS)		\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vreinterpret##Q##_##T2##W##_##TS2##WS(VECT_VAR(vector, TS1, WS, NS)); \
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),				\
+		    VECT_VAR(vector_res, T1, W, N));			\
+  DUMP(TEST_MSG, T1, W, N, PRIx##W);
+
+#define TEST_VREINTERPRET_POLY(Q, T1, T2, W, N, TS1, TS2, WS, NS)	\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vreinterpret##Q##_##T2##W##_##TS2##WS(VECT_VAR(vector, TS1, WS, NS)); \
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),				\
+		    VECT_VAR(vector_res, T1, W, N));			\
+  DUMP_POLY(TEST_MSG, T1, W, N, PRIx##W);
+
+#define TEST_VREINTERPRET_FP(Q, T1, T2, W, N, TS1, TS2, WS, NS)		\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vreinterpret##Q##_##T2##W##_##TS2##WS(VECT_VAR(vector, TS1, WS, NS)); \
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),				\
+		    VECT_VAR(vector_res, T1, W, N));			\
+  DUMP_FP(TEST_MSG, T1, W, N, PRIx##W);
+
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#define TEST_VREINTERPRET_FP16(Q, T1, T2, W, N, TS1, TS2, WS, NS)	\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vreinterpret##Q##_##T2##W##_##TS2##WS(VECT_VAR(vector, TS1, WS, NS)); \
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),				\
+		    VECT_VAR(vector_res, T1, W, N));			\
+  DUMP_FP16(TEST_MSG, T1, W, N, PRIx##W);
+#endif
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  DECL_VARIABLE(vector, float, 16, 4);
+  DECL_VARIABLE(vector_res, float, 16, 4);
+  DECL_VARIABLE(vector, float, 16, 8);
+  DECL_VARIABLE(vector_res, float, 16, 8);
+#endif
+
+  clean_results ();
+
+
+  /* Initialize input "vector" from "buffer"  */
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+  VLOAD(vector, buffer, , float, f, 32, 2);
+  VLOAD(vector, buffer, q, float, f, 32, 4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  VLOAD(vector, buffer, , float, f, 16, 4);
+  VLOAD(vector, buffer, q, float, f, 16, 8);
+#endif
+
+  /* The same result buffers are used multiple times, so output them
+     before overwriting them  */
+  fprintf(ref_file, "\n%s output:\n", TEST_MSG);
+  fprintf(gcc_tests_file, "\n%s output:\n", TEST_MSG);
+
+  /* vreinterpret_s8_xx */
+  TEST_VREINTERPRET(, int, s, 8, 8, int, s, 16, 4);
+  TEST_VREINTERPRET(, int, s, 8, 8, int, s, 32, 2);
+  TEST_VREINTERPRET(, int, s, 8, 8, int, s, 64, 1);
+  TEST_VREINTERPRET(, int, s, 8, 8, uint, u, 8, 8);
+  TEST_VREINTERPRET(, int, s, 8, 8, uint, u, 16, 4);
+  TEST_VREINTERPRET(, int, s, 8, 8, uint, u, 32, 2);
+  TEST_VREINTERPRET(, int, s, 8, 8, uint, u, 64, 1);
+  TEST_VREINTERPRET(, int, s, 8, 8, poly, p, 8, 8);
+  TEST_VREINTERPRET(, int, s, 8, 8, poly, p, 16, 4);
+
+  /* vreinterpret_s16_xx */
+  TEST_VREINTERPRET(, int, s, 16, 4, int, s, 8, 8);
+  TEST_VREINTERPRET(, int, s, 16, 4, int, s, 32, 2);
+  TEST_VREINTERPRET(, int, s, 16, 4, int, s, 64, 1);
+  TEST_VREINTERPRET(, int, s, 16, 4, uint, u, 8, 8);
+  TEST_VREINTERPRET(, int, s, 16, 4, uint, u, 16, 4);
+  TEST_VREINTERPRET(, int, s, 16, 4, uint, u, 32, 2);
+  TEST_VREINTERPRET(, int, s, 16, 4, uint, u, 64, 1);
+  TEST_VREINTERPRET(, int, s, 16, 4, poly, p, 8, 8);
+  TEST_VREINTERPRET(, int, s, 16, 4, poly, p, 16, 4);
+
+  /* vreinterpret_s32_xx */
+  TEST_VREINTERPRET(, int, s, 32, 2, int, s, 8, 8);
+  TEST_VREINTERPRET(, int, s, 32, 2, int, s, 16, 4);
+  TEST_VREINTERPRET(, int, s, 32, 2, int, s, 64, 1);
+  TEST_VREINTERPRET(, int, s, 32, 2, uint, u, 8, 8);
+  TEST_VREINTERPRET(, int, s, 32, 2, uint, u, 16, 4);
+  TEST_VREINTERPRET(, int, s, 32, 2, uint, u, 32, 2);
+  TEST_VREINTERPRET(, int, s, 32, 2, uint, u, 64, 1);
+  TEST_VREINTERPRET(, int, s, 32, 2, poly, p, 8, 8);
+  TEST_VREINTERPRET(, int, s, 32, 2, poly, p, 16, 4);
+
+  /* vreinterpret_s64_xx */
+  TEST_VREINTERPRET(, int, s, 64, 1, int, s, 8, 8);
+  TEST_VREINTERPRET(, int, s, 64, 1, int, s, 16, 4);
+  TEST_VREINTERPRET(, int, s, 64, 1, int, s, 32, 2);
+  TEST_VREINTERPRET(, int, s, 64, 1, uint, u, 8, 8);
+  TEST_VREINTERPRET(, int, s, 64, 1, uint, u, 16, 4);
+  TEST_VREINTERPRET(, int, s, 64, 1, uint, u, 32, 2);
+  TEST_VREINTERPRET(, int, s, 64, 1, uint, u, 64, 1);
+  TEST_VREINTERPRET(, int, s, 64, 1, poly, p, 8, 8);
+  TEST_VREINTERPRET(, int, s, 64, 1, poly, p, 16, 4);
+
+  /* vreinterpret_u8_xx */
+  TEST_VREINTERPRET(, uint, u, 8, 8, int, s, 8, 8);
+  TEST_VREINTERPRET(, uint, u, 8, 8, int, s, 16, 4);
+  TEST_VREINTERPRET(, uint, u, 8, 8, int, s, 32, 2);
+  TEST_VREINTERPRET(, uint, u, 8, 8, int, s, 64, 1);
+  TEST_VREINTERPRET(, uint, u, 8, 8, uint, u, 16, 4);
+  TEST_VREINTERPRET(, uint, u, 8, 8, uint, u, 32, 2);
+  TEST_VREINTERPRET(, uint, u, 8, 8, uint, u, 64, 1);
+  TEST_VREINTERPRET(, uint, u, 8, 8, poly, p, 8, 8);
+  TEST_VREINTERPRET(, uint, u, 8, 8, poly, p, 16, 4);
+
+  /* vreinterpret_u16_xx */
+  TEST_VREINTERPRET(, uint, u, 16, 4, int, s, 8, 8);
+  TEST_VREINTERPRET(, uint, u, 16, 4, int, s, 16, 4);
+  TEST_VREINTERPRET(, uint, u, 16, 4, int, s, 32, 2);
+  TEST_VREINTERPRET(, uint, u, 16, 4, int, s, 64, 1);
+  TEST_VREINTERPRET(, uint, u, 16, 4, uint, u, 8, 8);
+  TEST_VREINTERPRET(, uint, u, 16, 4, uint, u, 32, 2);
+  TEST_VREINTERPRET(, uint, u, 16, 4, uint, u, 64, 1);
+  TEST_VREINTERPRET(, uint, u, 16, 4, poly, p, 8, 8);
+  TEST_VREINTERPRET(, uint, u, 16, 4, poly, p, 16, 4);
+
+  /* vreinterpret_u32_xx */
+  TEST_VREINTERPRET(, uint, u, 32, 2, int, s, 8, 8);
+  TEST_VREINTERPRET(, uint, u, 32, 2, int, s, 16, 4);
+  TEST_VREINTERPRET(, uint, u, 32, 2, int, s, 32, 2);
+  TEST_VREINTERPRET(, uint, u, 32, 2, int, s, 64, 1);
+  TEST_VREINTERPRET(, uint, u, 32, 2, uint, u, 8, 8);
+  TEST_VREINTERPRET(, uint, u, 32, 2, uint, u, 16, 4);
+  TEST_VREINTERPRET(, uint, u, 32, 2, uint, u, 64, 1);
+  TEST_VREINTERPRET(, uint, u, 32, 2, poly, p, 8, 8);
+  TEST_VREINTERPRET(, uint, u, 32, 2, poly, p, 16, 4);
+
+  /* vreinterpret_u64_xx */
+  TEST_VREINTERPRET(, uint, u, 64, 1, int, s, 8, 8);
+  TEST_VREINTERPRET(, uint, u, 64, 1, int, s, 16, 4);
+  TEST_VREINTERPRET(, uint, u, 64, 1, int, s, 32, 2);
+  TEST_VREINTERPRET(, uint, u, 64, 1, int, s, 64, 1);
+  TEST_VREINTERPRET(, uint, u, 64, 1, uint, u, 8, 8);
+  TEST_VREINTERPRET(, uint, u, 64, 1, uint, u, 16, 4);
+  TEST_VREINTERPRET(, uint, u, 64, 1, uint, u, 32, 2);
+  TEST_VREINTERPRET(, uint, u, 64, 1, poly, p, 8, 8);
+  TEST_VREINTERPRET(, uint, u, 64, 1, poly, p, 16, 4);
+
+  /* vreinterpret_p8_xx */
+  TEST_VREINTERPRET_POLY(, poly, p, 8, 8, int, s, 8, 8);
+  TEST_VREINTERPRET_POLY(, poly, p, 8, 8, int, s, 16, 4);
+  TEST_VREINTERPRET_POLY(, poly, p, 8, 8, int, s, 32, 2);
+  TEST_VREINTERPRET_POLY(, poly, p, 8, 8, int, s, 64, 1);
+  TEST_VREINTERPRET_POLY(, poly, p, 8, 8, uint, u, 8, 8);
+  TEST_VREINTERPRET_POLY(, poly, p, 8, 8, uint, u, 16, 4);
+  TEST_VREINTERPRET_POLY(, poly, p, 8, 8, uint, u, 32, 2);
+  TEST_VREINTERPRET_POLY(, poly, p, 8, 8, uint, u, 64, 1);
+  TEST_VREINTERPRET_POLY(, poly, p, 8, 8, poly, p, 16, 4);
+
+  /* vreinterpret_p16_xx */
+  TEST_VREINTERPRET_POLY(, poly, p, 16, 4, int, s, 8, 8);
+  TEST_VREINTERPRET_POLY(, poly, p, 16, 4, int, s, 16, 4);
+  TEST_VREINTERPRET_POLY(, poly, p, 16, 4, int, s, 32, 2);
+  TEST_VREINTERPRET_POLY(, poly, p, 16, 4, int, s, 64, 1);
+  TEST_VREINTERPRET_POLY(, poly, p, 16, 4, uint, u, 8, 8);
+  TEST_VREINTERPRET_POLY(, poly, p, 16, 4, uint, u, 16, 4);
+  TEST_VREINTERPRET_POLY(, poly, p, 16, 4, uint, u, 32, 2);
+  TEST_VREINTERPRET_POLY(, poly, p, 16, 4, uint, u, 64, 1);
+  TEST_VREINTERPRET_POLY(, poly, p, 16, 4, poly, p, 8, 8);
+
+  /* vreinterpretq_s8_xx */
+  TEST_VREINTERPRET(q, int, s, 8, 16, int, s, 16, 8);
+  TEST_VREINTERPRET(q, int, s, 8, 16, int, s, 32, 4);
+  TEST_VREINTERPRET(q, int, s, 8, 16, int, s, 64, 2);
+  TEST_VREINTERPRET(q, int, s, 8, 16, uint, u, 8, 16);
+  TEST_VREINTERPRET(q, int, s, 8, 16, uint, u, 16, 8);
+  TEST_VREINTERPRET(q, int, s, 8, 16, uint, u, 32, 4);
+  TEST_VREINTERPRET(q, int, s, 8, 16, uint, u, 64, 2);
+  TEST_VREINTERPRET(q, int, s, 8, 16, poly, p, 8, 16);
+  TEST_VREINTERPRET(q, int, s, 8, 16, poly, p, 16, 8);
+
+  /* vreinterpretq_s16_xx */
+  TEST_VREINTERPRET(q, int, s, 16, 8, int, s, 8, 16);
+  TEST_VREINTERPRET(q, int, s, 16, 8, int, s, 32, 4);
+  TEST_VREINTERPRET(q, int, s, 16, 8, int, s, 64, 2);
+  TEST_VREINTERPRET(q, int, s, 16, 8, uint, u, 8, 16);
+  TEST_VREINTERPRET(q, int, s, 16, 8, uint, u, 16, 8);
+  TEST_VREINTERPRET(q, int, s, 16, 8, uint, u, 32, 4);
+  TEST_VREINTERPRET(q, int, s, 16, 8, uint, u, 64, 2);
+  TEST_VREINTERPRET(q, int, s, 16, 8, poly, p, 8, 16);
+  TEST_VREINTERPRET(q, int, s, 16, 8, poly, p, 16, 8);
+
+  /* vreinterpretq_s32_xx */
+  TEST_VREINTERPRET(q, int, s, 32, 4, int, s, 8, 16);
+  TEST_VREINTERPRET(q, int, s, 32, 4, int, s, 16, 8);
+  TEST_VREINTERPRET(q, int, s, 32, 4, int, s, 64, 2);
+  TEST_VREINTERPRET(q, int, s, 32, 4, uint, u, 8, 16);
+  TEST_VREINTERPRET(q, int, s, 32, 4, uint, u, 16, 8);
+  TEST_VREINTERPRET(q, int, s, 32, 4, uint, u, 32, 4);
+  TEST_VREINTERPRET(q, int, s, 32, 4, uint, u, 64, 2);
+  TEST_VREINTERPRET(q, int, s, 32, 4, poly, p, 8, 16);
+  TEST_VREINTERPRET(q, int, s, 32, 4, poly, p, 16, 8);
+
+  /* vreinterpretq_s64_xx */
+  TEST_VREINTERPRET(q, int, s, 64, 2, int, s, 8, 16);
+  TEST_VREINTERPRET(q, int, s, 64, 2, int, s, 16, 8);
+  TEST_VREINTERPRET(q, int, s, 64, 2, int, s, 32, 4);
+  TEST_VREINTERPRET(q, int, s, 64, 2, uint, u, 8, 16);
+  TEST_VREINTERPRET(q, int, s, 64, 2, uint, u, 16, 8);
+  TEST_VREINTERPRET(q, int, s, 64, 2, uint, u, 32, 4);
+  TEST_VREINTERPRET(q, int, s, 64, 2, uint, u, 64, 2);
+  TEST_VREINTERPRET(q, int, s, 64, 2, poly, p, 8, 16);
+  TEST_VREINTERPRET(q, int, s, 64, 2, poly, p, 16, 8);
+
+  /* vreinterpretq_u16_xx */
+  TEST_VREINTERPRET(q, uint, u, 16, 8, int, s, 8, 16);
+  TEST_VREINTERPRET(q, uint, u, 16, 8, int, s, 16, 8);
+  TEST_VREINTERPRET(q, uint, u, 16, 8, int, s, 32, 4);
+  TEST_VREINTERPRET(q, uint, u, 16, 8, int, s, 64, 2);
+  TEST_VREINTERPRET(q, uint, u, 16, 8, uint, u, 8, 16);
+  TEST_VREINTERPRET(q, uint, u, 16, 8, uint, u, 32, 4);
+  TEST_VREINTERPRET(q, uint, u, 16, 8, uint, u, 64, 2);
+  TEST_VREINTERPRET(q, uint, u, 16, 8, poly, p, 8, 16);
+  TEST_VREINTERPRET(q, uint, u, 16, 8, poly, p, 16, 8);
+
+  /* vreinterpretq_u32_xx */
+  TEST_VREINTERPRET(q, uint, u, 32, 4, int, s, 8, 16);
+  TEST_VREINTERPRET(q, uint, u, 32, 4, int, s, 16, 8);
+  TEST_VREINTERPRET(q, uint, u, 32, 4, int, s, 32, 4);
+  TEST_VREINTERPRET(q, uint, u, 32, 4, int, s, 64, 2);
+  TEST_VREINTERPRET(q, uint, u, 32, 4, uint, u, 8, 16);
+  TEST_VREINTERPRET(q, uint, u, 32, 4, uint, u, 16, 8);
+  TEST_VREINTERPRET(q, uint, u, 32, 4, uint, u, 64, 2);
+  TEST_VREINTERPRET(q, uint, u, 32, 4, poly, p, 8, 16);
+  TEST_VREINTERPRET(q, uint, u, 32, 4, poly, p, 16, 8);
+
+  /* vreinterpretq_u64_xx */
+  TEST_VREINTERPRET(q, uint, u, 64, 2, int, s, 8, 16);
+  TEST_VREINTERPRET(q, uint, u, 64, 2, int, s, 16, 8);
+  TEST_VREINTERPRET(q, uint, u, 64, 2, int, s, 32, 4);
+  TEST_VREINTERPRET(q, uint, u, 64, 2, int, s, 64, 2);
+  TEST_VREINTERPRET(q, uint, u, 64, 2, uint, u, 8, 16);
+  TEST_VREINTERPRET(q, uint, u, 64, 2, uint, u, 16, 8);
+  TEST_VREINTERPRET(q, uint, u, 64, 2, uint, u, 32, 4);
+  TEST_VREINTERPRET(q, uint, u, 64, 2, poly, p, 8, 16);
+  TEST_VREINTERPRET(q, uint, u, 64, 2, poly, p, 16, 8);
+
+  /* vreinterpretq_u8_xx */
+  TEST_VREINTERPRET(q, uint, u, 8, 16, int, s, 8, 16);
+  TEST_VREINTERPRET(q, uint, u, 8, 16, int, s, 16, 8);
+  TEST_VREINTERPRET(q, uint, u, 8, 16, int, s, 32, 4);
+  TEST_VREINTERPRET(q, uint, u, 8, 16, int, s, 64, 2);
+  TEST_VREINTERPRET(q, uint, u, 8, 16, uint, u, 16, 8);
+  TEST_VREINTERPRET(q, uint, u, 8, 16, uint, u, 32, 4);
+  TEST_VREINTERPRET(q, uint, u, 8, 16, uint, u, 64, 2);
+  TEST_VREINTERPRET(q, uint, u, 8, 16, poly, p, 8, 16);
+  TEST_VREINTERPRET(q, uint, u, 8, 16, poly, p, 16, 8);
+
+  /* vreinterpret_f32_xx */
+  TEST_VREINTERPRET_FP(, float, f, 32, 2, int, s, 8, 8);
+  TEST_VREINTERPRET_FP(, float, f, 32, 2, int, s, 16, 4);
+  TEST_VREINTERPRET_FP(, float, f, 32, 2, int, s, 32, 2);
+  TEST_VREINTERPRET_FP(, float, f, 32, 2, int, s, 64, 1);
+  TEST_VREINTERPRET_FP(, float, f, 32, 2, uint, u, 8, 8);
+  TEST_VREINTERPRET_FP(, float, f, 32, 2, uint, u, 16, 4);
+  TEST_VREINTERPRET_FP(, float, f, 32, 2, uint, u, 32, 2);
+  TEST_VREINTERPRET_FP(, float, f, 32, 2, uint, u, 64, 1);
+  TEST_VREINTERPRET_FP(, float, f, 32, 2, poly, p, 8, 8);
+  TEST_VREINTERPRET_FP(, float, f, 32, 2, poly, p, 16, 4);
+
+  /* vreinterpretq_f32_xx */
+  TEST_VREINTERPRET_FP(q, float, f, 32, 4, int, s, 8, 16);
+  TEST_VREINTERPRET_FP(q, float, f, 32, 4, int, s, 16, 8);
+  TEST_VREINTERPRET_FP(q, float, f, 32, 4, int, s, 32, 4);
+  TEST_VREINTERPRET_FP(q, float, f, 32, 4, int, s, 64, 2);
+  TEST_VREINTERPRET_FP(q, float, f, 32, 4, uint, u, 8, 16);
+  TEST_VREINTERPRET_FP(q, float, f, 32, 4, uint, u, 16, 8);
+  TEST_VREINTERPRET_FP(q, float, f, 32, 4, uint, u, 32, 4);
+  TEST_VREINTERPRET_FP(q, float, f, 32, 4, uint, u, 64, 2);
+  TEST_VREINTERPRET_FP(q, float, f, 32, 4, poly, p, 8, 16);
+  TEST_VREINTERPRET_FP(q, float, f, 32, 4, poly, p, 16, 8);
+
+  /* vreinterpret_xx_f32 */
+  TEST_VREINTERPRET(, int, s, 8, 8, float, f, 32, 2);
+  TEST_VREINTERPRET(, int, s, 16, 4, float, f, 32, 2);
+  TEST_VREINTERPRET(, int, s, 32, 2, float, f, 32, 2);
+  TEST_VREINTERPRET(, int, s, 64, 1, float, f, 32, 2);
+  TEST_VREINTERPRET(, uint, u, 8, 8, float, f, 32, 2);
+  TEST_VREINTERPRET(, uint, u, 16, 4, float, f, 32, 2);
+  TEST_VREINTERPRET(, uint, u, 32, 2, float, f, 32, 2);
+  TEST_VREINTERPRET(, uint, u, 64, 1, float, f, 32, 2);
+  TEST_VREINTERPRET_POLY(, poly, p, 8, 8, float, f, 32, 2);
+  TEST_VREINTERPRET_POLY(, poly, p, 16, 4, float, f, 32, 2);
+
+  /* vreinterpretq_xx_f32 */
+  TEST_VREINTERPRET(q, int, s, 8, 16, float, f, 32, 4);
+  TEST_VREINTERPRET(q, int, s, 16, 8, float, f, 32, 4);
+  TEST_VREINTERPRET(q, int, s, 32, 4, float, f, 32, 4);
+  TEST_VREINTERPRET(q, int, s, 64, 2, float, f, 32, 4);
+  TEST_VREINTERPRET(q, uint, u, 8, 16, float, f, 32, 4);
+  TEST_VREINTERPRET(q, uint, u, 16, 8, float, f, 32, 4);
+  TEST_VREINTERPRET(q, uint, u, 32, 4, float, f, 32, 4);
+  TEST_VREINTERPRET(q, uint, u, 64, 2, float, f, 32, 4);
+  TEST_VREINTERPRET_POLY(q, poly, p, 8, 16, float, f, 32, 4);
+  TEST_VREINTERPRET_POLY(q, poly, p, 16, 8, float, f, 32, 4);
+
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  /* vreinterpret_f16_xx */
+  TEST_VREINTERPRET_FP16(, float, f, 16, 4, int, s, 8, 8);
+  TEST_VREINTERPRET_FP16(, float, f, 16, 4, int, s, 16, 4);
+  TEST_VREINTERPRET_FP16(, float, f, 16, 4, int, s, 32, 2);
+  TEST_VREINTERPRET_FP16(, float, f, 16, 4, int, s, 64, 1);
+  TEST_VREINTERPRET_FP16(, float, f, 16, 4, uint, u, 8, 8);
+  TEST_VREINTERPRET_FP16(, float, f, 16, 4, uint, u, 16, 4);
+  TEST_VREINTERPRET_FP16(, float, f, 16, 4, uint, u, 32, 2);
+  TEST_VREINTERPRET_FP16(, float, f, 16, 4, uint, u, 64, 1);
+  TEST_VREINTERPRET_FP16(, float, f, 16, 4, poly, p, 8, 8);
+  TEST_VREINTERPRET_FP16(, float, f, 16, 4, poly, p, 16, 4);
+  TEST_VREINTERPRET_FP16(, float, f, 16, 4, float, f, 32, 2);
+
+  /* vreinterpretq_f16_xx */
+  TEST_VREINTERPRET_FP16(q, float, f, 16, 8, int, s, 8, 16);
+  TEST_VREINTERPRET_FP16(q, float, f, 16, 8, int, s, 16, 8);
+  TEST_VREINTERPRET_FP16(q, float, f, 16, 8, int, s, 32, 4);
+  TEST_VREINTERPRET_FP16(q, float, f, 16, 8, int, s, 64, 2);
+  TEST_VREINTERPRET_FP16(q, float, f, 16, 8, uint, u, 8, 16);
+  TEST_VREINTERPRET_FP16(q, float, f, 16, 8, uint, u, 16, 8);
+  TEST_VREINTERPRET_FP16(q, float, f, 16, 8, uint, u, 32, 4);
+  TEST_VREINTERPRET_FP16(q, float, f, 16, 8, uint, u, 64, 2);
+  TEST_VREINTERPRET_FP16(q, float, f, 16, 8, poly, p, 8, 16);
+  TEST_VREINTERPRET_FP16(q, float, f, 16, 8, poly, p, 16, 8);
+  TEST_VREINTERPRET_FP16(q, float, f, 16, 8, float, f, 32, 4);
+
+  /* vreinterpret_xx_f16 */
+  TEST_VREINTERPRET(, int, s, 8, 8, float, f, 16, 4);
+  TEST_VREINTERPRET(, int, s, 16, 4, float, f, 16, 4);
+  TEST_VREINTERPRET(, int, s, 32, 2, float, f, 16, 4);
+  TEST_VREINTERPRET(, int, s, 64, 1, float, f, 16, 4);
+  TEST_VREINTERPRET(, uint, u, 8, 8, float, f, 16, 4);
+  TEST_VREINTERPRET(, uint, u, 16, 4, float, f, 16, 4);
+  TEST_VREINTERPRET(, uint, u, 32, 2, float, f, 16, 4);
+  TEST_VREINTERPRET(, uint, u, 64, 1, float, f, 16, 4);
+  TEST_VREINTERPRET_POLY(, poly, p, 8, 8, float, f, 16, 4);
+  TEST_VREINTERPRET_POLY(, poly, p, 16, 4, float, f, 16, 4);
+  TEST_VREINTERPRET_FP(, float, f, 32, 2, float, f, 16, 4);
+
+  /* vreinterpretq_xx_f16 */
+  TEST_VREINTERPRET(q, int, s, 8, 16, float, f, 16, 8);
+  TEST_VREINTERPRET(q, int, s, 16, 8, float, f, 16, 8);
+  TEST_VREINTERPRET(q, int, s, 32, 4, float, f, 16, 8);
+  TEST_VREINTERPRET(q, int, s, 64, 2, float, f, 16, 8);
+  TEST_VREINTERPRET(q, uint, u, 8, 16, float, f, 16, 8);
+  TEST_VREINTERPRET(q, uint, u, 16, 8, float, f, 16, 8);
+  TEST_VREINTERPRET(q, uint, u, 32, 4, float, f, 16, 8);
+  TEST_VREINTERPRET(q, uint, u, 64, 2, float, f, 16, 8);
+  TEST_VREINTERPRET_POLY(q, poly, p, 8, 16, float, f, 16, 8);
+  TEST_VREINTERPRET_POLY(q, poly, p, 16, 8, float, f, 16, 8);
+  TEST_VREINTERPRET_FP(q, float, f, 32, 4, float, f, 16, 8);
+#endif
+}
diff --git a/ref_vrev.c b/ref_vrev.c
new file mode 100644
index 0000000..f639182
--- /dev/null
+++ b/ref_vrev.c
@@ -0,0 +1,106 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+/* Template file for unary operator validation */
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+void exec_vrev (void)
+{
+  /* Basic test: y=vrev(x), then store the result.  */
+#define TEST_VREV(Q, T1, T2, W, N, W2)					\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vrev##W2##Q##_##T2##W(VECT_VAR(vector, T1, W, N));			\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement  */
+
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+  VLOAD(vector, buffer, , float, f, 32, 2);
+  VLOAD(vector, buffer, q, float, f, 32, 4);
+
+  /* Check vrev in each of the existing combinations  */
+#define TEST_MSG "VREV16"
+  TEST_VREV(, int, s, 8, 8, 16);
+  TEST_VREV(, uint, u, 8, 8, 16);
+  TEST_VREV(, poly, p, 8, 8, 16);
+  TEST_VREV(q, int, s, 8, 16, 16);
+  TEST_VREV(q, uint, u, 8, 16, 16);
+  TEST_VREV(q, poly, p, 8, 16, 16);
+  dump_results_hex (TEST_MSG);
+
+#undef TEST_MSG
+#define TEST_MSG "VREV32"
+  TEST_VREV(, int, s, 8, 8, 32);
+  TEST_VREV(, int, s, 16, 4, 32);
+  TEST_VREV(, uint, u, 8, 8, 32);
+  TEST_VREV(, uint, u, 16, 4, 32);
+  TEST_VREV(, poly, p, 8, 8, 32);
+  TEST_VREV(, poly, p, 16, 4, 32);
+  TEST_VREV(q, int, s, 8, 16, 32);
+  TEST_VREV(q, int, s, 16, 8, 32);
+  TEST_VREV(q, uint, u, 8, 16, 32);
+  TEST_VREV(q, uint, u, 16, 8, 32);
+  TEST_VREV(q, poly, p, 8, 16, 32);
+  TEST_VREV(q, poly, p, 16, 8, 32);
+  dump_results_hex (TEST_MSG);
+
+#undef TEST_MSG
+#define TEST_MSG "VREV64"
+  TEST_VREV(, int, s, 8, 8, 64);
+  TEST_VREV(, int, s, 16, 4, 64);
+  TEST_VREV(, int, s, 32, 2, 64);
+  TEST_VREV(, uint, u, 8, 8, 64);
+  TEST_VREV(, uint, u, 16, 4, 64);
+  TEST_VREV(, uint, u, 32, 2, 64);
+  TEST_VREV(, poly, p, 8, 8, 64);
+  TEST_VREV(, poly, p, 16, 4, 64);
+  TEST_VREV(q, int, s, 8, 16, 64);
+  TEST_VREV(q, int, s, 16, 8, 64);
+  TEST_VREV(q, int, s, 32, 4, 64);
+  TEST_VREV(q, uint, u, 8, 16, 64);
+  TEST_VREV(q, uint, u, 16, 8, 64);
+  TEST_VREV(q, uint, u, 32, 4, 64);
+  TEST_VREV(q, poly, p, 8, 16, 64);
+  TEST_VREV(q, poly, p, 16, 8, 64);
+
+  TEST_VREV(, float, f, 32, 2, 64);
+  TEST_VREV(q, float, f, 32, 4, 64);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vrhadd.c b/ref_vrhadd.c
new file mode 100644
index 0000000..20872a1
--- /dev/null
+++ b/ref_vrhadd.c
@@ -0,0 +1,31 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vrhadd
+#define TEST_MSG "VRHADD/VRHADDQ"
+
+#define NO_FLOAT_VARIANT
+
+#include "ref_vmax.c"
diff --git a/ref_vrshl.c b/ref_vrshl.c
new file mode 100644
index 0000000..8790619
--- /dev/null
+++ b/ref_vrshl.c
@@ -0,0 +1,220 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VRSHL/VRSHLQ"
+void exec_vrshl (void)
+{
+  /* Basic test: v3=vrshl(v1,v2), then store the result.  */
+#define TEST_VRSHL(T3, Q, T1, T2, W, N)					\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vrshl##Q##_##T2##W(VECT_VAR(vector, T1, W, N),			\
+		       VECT_VAR(vector_shift, T3, W, N));		\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+  DECL_VARIABLE_SIGNED_VARIANTS(vector_shift);
+
+  clean_results ();
+
+  /* Fill input vector with 0, to check behavior on limits */
+  VDUP(vector, , int, s, 8, 8, 0);
+  VDUP(vector, , int, s, 16, 4, 0);
+  VDUP(vector, , int, s, 32, 2, 0);
+  VDUP(vector, , int, s, 64, 1, 0);
+  VDUP(vector, , uint, u, 8, 8, 0);
+  VDUP(vector, , uint, u, 16, 4, 0);
+  VDUP(vector, , uint, u, 32, 2, 0);
+  VDUP(vector, , uint, u, 64, 1, 0);
+  VDUP(vector, q, int, s, 8, 16, 0);
+  VDUP(vector, q, int, s, 16, 8, 0);
+  VDUP(vector, q, int, s, 32, 4, 0);
+  VDUP(vector, q, int, s, 64, 2, 0);
+  VDUP(vector, q, uint, u, 8, 16, 0);
+  VDUP(vector, q, uint, u, 16, 8, 0);
+  VDUP(vector, q, uint, u, 32, 4, 0);
+  VDUP(vector, q, uint, u, 64, 2, 0);
+
+  /* Choose init value arbitrarily, will be used as shift amount */
+  /* Use values equal to one-less-than the type width to check
+     behaviour on limits */
+  VDUP(vector_shift, , int, s, 8, 8, 7);
+  VDUP(vector_shift, , int, s, 16, 4, 15);
+  VDUP(vector_shift, , int, s, 32, 2, 31);
+  VDUP(vector_shift, , int, s, 64, 1, 63);
+  VDUP(vector_shift, q, int, s, 8, 16, 7);
+  VDUP(vector_shift, q, int, s, 16, 8, 15);
+  VDUP(vector_shift, q, int, s, 32, 4, 31);
+  VDUP(vector_shift, q, int, s, 64, 2, 63);
+
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VRSHL, int);
+
+  dump_results_hex2 (TEST_MSG, " (with input = 0)");
+
+  /* Use negative shift amounts */
+  VDUP(vector_shift, , int, s, 8, 8, -1);
+  VDUP(vector_shift, , int, s, 16, 4, -2);
+  VDUP(vector_shift, , int, s, 32, 2, -3);
+  VDUP(vector_shift, , int, s, 64, 1, -4);
+  VDUP(vector_shift, q, int, s, 8, 16, -7);
+  VDUP(vector_shift, q, int, s, 16, 8, -11);
+  VDUP(vector_shift, q, int, s, 32, 4, -13);
+  VDUP(vector_shift, q, int, s, 64, 2, -20);
+
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VRSHL, int);
+
+  dump_results_hex2 (TEST_MSG, " (input 0 and negative shift amount)");
+
+  /* Test again, with predefined input values */
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+
+  /* Choose init value arbitrarily, will be used as shift amount */
+  VDUP(vector_shift, , int, s, 8, 8, 1);
+  VDUP(vector_shift, , int, s, 16, 4, 3);
+  VDUP(vector_shift, , int, s, 32, 2, 8);
+  VDUP(vector_shift, , int, s, 64, 1, -3);
+  VDUP(vector_shift, q, int, s, 8, 16, 10);
+  VDUP(vector_shift, q, int, s, 16, 8, 12);
+  VDUP(vector_shift, q, int, s, 32, 4, 32);
+  VDUP(vector_shift, q, int, s, 64, 2, 63);
+
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VRSHL, int);
+
+  dump_results_hex (TEST_MSG);
+
+
+  /* Use negative shift amounts */
+  VDUP(vector_shift, , int, s, 8, 8, -1);
+  VDUP(vector_shift, , int, s, 16, 4, -2);
+  VDUP(vector_shift, , int, s, 32, 2, -3);
+  VDUP(vector_shift, , int, s, 64, 1, -4);
+  VDUP(vector_shift, q, int, s, 8, 16, -7);
+  VDUP(vector_shift, q, int, s, 16, 8, -11);
+  VDUP(vector_shift, q, int, s, 32, 4, -13);
+  VDUP(vector_shift, q, int, s, 64, 2, -20);
+
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VRSHL, int);
+
+  dump_results_hex2 (TEST_MSG, " (negative shift amount)");
+
+  /* Fill input vector with max value, to check behavior on limits */
+  VDUP(vector, , int, s, 8, 8, 0x7F);
+  VDUP(vector, , int, s, 16, 4, 0x7FFF);
+  VDUP(vector, , int, s, 32, 2, 0x7FFFFFFF);
+  VDUP(vector, , int, s, 64, 1, 0x7FFFFFFFFFFFFFFFLL);
+  VDUP(vector, , uint, u, 8, 8, 0xFF);
+  VDUP(vector, , uint, u, 16, 4, 0xFFFF);
+  VDUP(vector, , uint, u, 32, 2, 0xFFFFFFFF);
+  VDUP(vector, , uint, u, 64, 1, 0xFFFFFFFFFFFFFFFFULL);
+  VDUP(vector, q, int, s, 8, 16, 0x7F);
+  VDUP(vector, q, int, s, 16, 8, 0x7FFF);
+  VDUP(vector, q, int, s, 32, 4, 0x7FFFFFFF);
+  VDUP(vector, q, int, s, 64, 2, 0x7FFFFFFFFFFFFFFFLL);
+  VDUP(vector, q, uint, u, 8, 16, 0xFF);
+  VDUP(vector, q, uint, u, 16, 8, 0xFFFF);
+  VDUP(vector, q, uint, u, 32, 4, 0xFFFFFFFF);
+  VDUP(vector, q, uint, u, 64, 2, 0xFFFFFFFFFFFFFFFFULL);
+
+  /* Use -1 shift amount to check overflow with round_const */
+  VDUP(vector_shift, , int, s, 8, 8, -1);
+  VDUP(vector_shift, , int, s, 16, 4, -1);
+  VDUP(vector_shift, , int, s, 32, 2, -1);
+  VDUP(vector_shift, , int, s, 64, 1, -1);
+  VDUP(vector_shift, q, int, s, 8, 16, -1);
+  VDUP(vector_shift, q, int, s, 16, 8, -1);
+  VDUP(vector_shift, q, int, s, 32, 4, -1);
+  VDUP(vector_shift, q, int, s, 64, 2, -1);
+
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VRSHL, int);
+
+  dump_results_hex2 (TEST_MSG, " (checking round_const overflow: shift by -1)");
+
+  /* Use -3 shift amount to check overflow with round_const */
+  VDUP(vector_shift, , int, s, 8, 8, -3);
+  VDUP(vector_shift, , int, s, 16, 4, -3);
+  VDUP(vector_shift, , int, s, 32, 2, -3);
+  VDUP(vector_shift, , int, s, 64, 1, -3);
+  VDUP(vector_shift, q, int, s, 8, 16, -3);
+  VDUP(vector_shift, q, int, s, 16, 8, -3);
+  VDUP(vector_shift, q, int, s, 32, 4, -3);
+  VDUP(vector_shift, q, int, s, 64, 2, -3);
+
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VRSHL, int);
+
+  dump_results_hex2 (TEST_MSG, " (checking round_const overflow: shift by -3)");
+
+  /* Use negative shift amount as large as input vector width */
+  VDUP(vector_shift, , int, s, 8, 8, -8);
+  VDUP(vector_shift, , int, s, 16, 4, -16);
+  VDUP(vector_shift, , int, s, 32, 2, -32);
+  VDUP(vector_shift, , int, s, 64, 1, -64);
+  VDUP(vector_shift, q, int, s, 8, 16, -8);
+  VDUP(vector_shift, q, int, s, 16, 8, -16);
+  VDUP(vector_shift, q, int, s, 32, 4, -32);
+  VDUP(vector_shift, q, int, s, 64, 2, -64);
+
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VRSHL, int);
+
+  dump_results_hex2 (TEST_MSG, " (checking negative shift amount as large as input vector width)");
+
+  /* Test large shift amount */
+  VDUP(vector_shift, , int, s, 8, 8, 10);
+  VDUP(vector_shift, , int, s, 16, 4, 20);
+  VDUP(vector_shift, , int, s, 32, 2, 33);
+  VDUP(vector_shift, , int, s, 64, 1, 65);
+  VDUP(vector_shift, q, int, s, 8, 16, 9);
+  VDUP(vector_shift, q, int, s, 16, 8, 16);
+  VDUP(vector_shift, q, int, s, 32, 4, 32);
+  VDUP(vector_shift, q, int, s, 64, 2, 64);
+
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VRSHL, int);
+
+  dump_results_hex2 (TEST_MSG, " (large shift amount)");
+
+  /* Test large negative shift amount */
+  VDUP(vector_shift, , int, s, 8, 8, -10);
+  VDUP(vector_shift, , int, s, 16, 4, -20);
+  VDUP(vector_shift, , int, s, 32, 2, -33);
+  VDUP(vector_shift, , int, s, 64, 1, -65);
+  VDUP(vector_shift, q, int, s, 8, 16, -9);
+  VDUP(vector_shift, q, int, s, 16, 8, -16);
+  VDUP(vector_shift, q, int, s, 32, 4, -32);
+  VDUP(vector_shift, q, int, s, 64, 2, -64);
+
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VRSHL, int);
+
+  dump_results_hex2 (TEST_MSG, " (large negative shift amount)");
+}
diff --git a/ref_vrshr_n.c b/ref_vrshr_n.c
new file mode 100644
index 0000000..c19c7a4
--- /dev/null
+++ b/ref_vrshr_n.c
@@ -0,0 +1,217 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VRSHR_N"
+void exec_vrshr_n (void)
+{
+  /* Basic test: y=vrshr_n(x,v), then store the result.  */
+#define TEST_VRSHR_N(Q, T1, T2, W, N, V)				\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vrshr##Q##_n_##T2##W(VECT_VAR(vector, T1, W, N),			\
+			 V);						\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+
+  /* Choose shift amount arbitrarily  */
+  TEST_VRSHR_N(, int, s, 8, 8, 1);
+  TEST_VRSHR_N(, int, s, 16, 4, 12);
+  TEST_VRSHR_N(, int, s, 32, 2, 2);
+  TEST_VRSHR_N(, int, s, 64, 1, 32);
+  TEST_VRSHR_N(, uint, u, 8, 8, 2);
+  TEST_VRSHR_N(, uint, u, 16, 4, 3);
+  TEST_VRSHR_N(, uint, u, 32, 2, 5);
+  TEST_VRSHR_N(, uint, u, 64, 1, 33);
+
+  TEST_VRSHR_N(q, int, s, 8, 16, 1);
+  TEST_VRSHR_N(q, int, s, 16, 8, 12);
+  TEST_VRSHR_N(q, int, s, 32, 4, 2);
+  TEST_VRSHR_N(q, int, s, 64, 2, 32);
+  TEST_VRSHR_N(q, uint, u, 8, 16, 2);
+  TEST_VRSHR_N(q, uint, u, 16, 8, 3);
+  TEST_VRSHR_N(q, uint, u, 32, 4, 5);
+  TEST_VRSHR_N(q, uint, u, 64, 2, 33);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex (TEST_MSG);
+
+  /* Another set of tests */
+  VDUP(vector, , int, s, 8, 8, 0x7F);
+  VDUP(vector, , int, s, 16, 4, 0x7FFF);
+  VDUP(vector, , int, s, 32, 2, 0x7FFFFFFF);
+  VDUP(vector, , int, s, 64, 1, 0x7FFFFFFFFFFFFFFFLL);
+  VDUP(vector, , uint, u, 8, 8, 0xFF);
+  VDUP(vector, , uint, u, 16, 4, 0xFFFF);
+  VDUP(vector, , uint, u, 32, 2, 0xFFFFFFFF);
+  VDUP(vector, , uint, u, 64, 1, 0xFFFFFFFFFFFFFFFFULL);
+  VDUP(vector, q, int, s, 8, 16, 0x7F);
+  VDUP(vector, q, int, s, 16, 8, 0x7FFF);
+  VDUP(vector, q, int, s, 32, 4, 0x7FFFFFFF);
+  VDUP(vector, q, int, s, 64, 2, 0x7FFFFFFFFFFFFFFFLL);
+  VDUP(vector, q, uint, u, 8, 16, 0xFF);
+  VDUP(vector, q, uint, u, 16, 8, 0xFFFF);
+  VDUP(vector, q, uint, u, 32, 4, 0xFFFFFFFF);
+  VDUP(vector, q, uint, u, 64, 2, 0xFFFFFFFFFFFFFFFFULL);
+
+  /* Use max shift amount, to exercise saturation code in the lib */
+  TEST_VRSHR_N(, int, s, 8, 8, 8);
+  TEST_VRSHR_N(, int, s, 16, 4, 16);
+  TEST_VRSHR_N(, int, s, 32, 2, 32);
+  TEST_VRSHR_N(, int, s, 64, 1, 64);
+  TEST_VRSHR_N(, uint, u, 8, 8, 8);
+  TEST_VRSHR_N(, uint, u, 16, 4, 16);
+  TEST_VRSHR_N(, uint, u, 32, 2, 32);
+  TEST_VRSHR_N(, uint, u, 64, 1, 64);
+  TEST_VRSHR_N(q, int, s, 8, 16, 8);
+  TEST_VRSHR_N(q, int, s, 16, 8, 16);
+  TEST_VRSHR_N(q, int, s, 32, 4, 32);
+  TEST_VRSHR_N(q, int, s, 64, 2, 64);
+  TEST_VRSHR_N(q, uint, u, 8, 16, 8);
+  TEST_VRSHR_N(q, uint, u, 16, 8, 16);
+  TEST_VRSHR_N(q, uint, u, 32, 4, 32);
+  TEST_VRSHR_N(q, uint, u, 64, 2, 64);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex2 (TEST_MSG, " (overflow test: max shift amount, positive input)");
+
+  /* Use 1 as shift amount, to exercise saturation code in the lib */
+  TEST_VRSHR_N(, int, s, 8, 8, 1);
+  TEST_VRSHR_N(, int, s, 16, 4, 1);
+  TEST_VRSHR_N(, int, s, 32, 2, 1);
+  TEST_VRSHR_N(, int, s, 64, 1, 1);
+  TEST_VRSHR_N(, uint, u, 8, 8, 1);
+  TEST_VRSHR_N(, uint, u, 16, 4, 1);
+  TEST_VRSHR_N(, uint, u, 32, 2, 1);
+  TEST_VRSHR_N(, uint, u, 64, 1, 1);
+  TEST_VRSHR_N(q, int, s, 8, 16, 1);
+  TEST_VRSHR_N(q, int, s, 16, 8, 1);
+  TEST_VRSHR_N(q, int, s, 32, 4, 1);
+  TEST_VRSHR_N(q, int, s, 64, 2, 1);
+  TEST_VRSHR_N(q, uint, u, 8, 16, 1);
+  TEST_VRSHR_N(q, uint, u, 16, 8, 1);
+  TEST_VRSHR_N(q, uint, u, 32, 4, 1);
+  TEST_VRSHR_N(q, uint, u, 64, 2, 1);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex2 (TEST_MSG, " (overflow test: shift by 1, with negative input)");
+
+  /* Use 3 as shift amount, to exercise saturation code in the lib */
+  TEST_VRSHR_N(, int, s, 8, 8, 3);
+  TEST_VRSHR_N(, int, s, 16, 4, 3);
+  TEST_VRSHR_N(, int, s, 32, 2, 3);
+  TEST_VRSHR_N(, int, s, 64, 1, 3);
+  TEST_VRSHR_N(, uint, u, 8, 8, 3);
+  TEST_VRSHR_N(, uint, u, 16, 4, 3);
+  TEST_VRSHR_N(, uint, u, 32, 2, 3);
+  TEST_VRSHR_N(, uint, u, 64, 1, 3);
+  TEST_VRSHR_N(q, int, s, 8, 16, 3);
+  TEST_VRSHR_N(q, int, s, 16, 8, 3);
+  TEST_VRSHR_N(q, int, s, 32, 4, 3);
+  TEST_VRSHR_N(q, int, s, 64, 2, 3);
+  TEST_VRSHR_N(q, uint, u, 8, 16, 3);
+  TEST_VRSHR_N(q, uint, u, 16, 8, 3);
+  TEST_VRSHR_N(q, uint, u, 32, 4, 3);
+  TEST_VRSHR_N(q, uint, u, 64, 2, 3);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex2 (TEST_MSG, " (overflow test: shift by 3, positive input)");
+
+  VDUP(vector, , int, s, 8, 8, 0x80);
+  VDUP(vector, , int, s, 16, 4, 0x8000);
+  VDUP(vector, , int, s, 32, 2, 0x80000000);
+  VDUP(vector, , int, s, 64, 1, 0x8000000000000000LL);
+  VDUP(vector, , uint, u, 8, 8, 0xFF);
+  VDUP(vector, , uint, u, 16, 4, 0xFFFF);
+  VDUP(vector, , uint, u, 32, 2, 0xFFFFFFFF);
+  VDUP(vector, , uint, u, 64, 1, 0xFFFFFFFFFFFFFFFFULL);
+  VDUP(vector, q, int, s, 8, 16, 0x80);
+  VDUP(vector, q, int, s, 16, 8, 0x8000);
+  VDUP(vector, q, int, s, 32, 4, 0x80000000);
+  VDUP(vector, q, int, s, 64, 2, 0x8000000000000000LL);
+  VDUP(vector, q, uint, u, 8, 16, 0xFF);
+  VDUP(vector, q, uint, u, 16, 8, 0xFFFF);
+  VDUP(vector, q, uint, u, 32, 4, 0xFFFFFFFF);
+  VDUP(vector, q, uint, u, 64, 2, 0xFFFFFFFFFFFFFFFFULL);
+
+
+  /* Use 1 as shift amount, to exercise saturation code in the lib */
+  TEST_VRSHR_N(, int, s, 8, 8, 1);
+  TEST_VRSHR_N(, int, s, 16, 4, 1);
+  TEST_VRSHR_N(, int, s, 32, 2, 1);
+  TEST_VRSHR_N(, int, s, 64, 1, 1);
+  TEST_VRSHR_N(, uint, u, 8, 8, 1);
+  TEST_VRSHR_N(, uint, u, 16, 4, 1);
+  TEST_VRSHR_N(, uint, u, 32, 2, 1);
+  TEST_VRSHR_N(, uint, u, 64, 1, 1);
+  TEST_VRSHR_N(q, int, s, 8, 16, 1);
+  TEST_VRSHR_N(q, int, s, 16, 8, 1);
+  TEST_VRSHR_N(q, int, s, 32, 4, 1);
+  TEST_VRSHR_N(q, int, s, 64, 2, 1);
+  TEST_VRSHR_N(q, uint, u, 8, 16, 1);
+  TEST_VRSHR_N(q, uint, u, 16, 8, 1);
+  TEST_VRSHR_N(q, uint, u, 32, 4, 1);
+  TEST_VRSHR_N(q, uint, u, 64, 2, 1);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex2 (TEST_MSG, " (overflow test: shift by 1, with negative input)");
+
+  /* Use 3 as shift amount, to exercise saturation code in the lib */
+  TEST_VRSHR_N(, int, s, 8, 8, 3);
+  TEST_VRSHR_N(, int, s, 16, 4, 3);
+  TEST_VRSHR_N(, int, s, 32, 2, 3);
+  TEST_VRSHR_N(, int, s, 64, 1, 3);
+  TEST_VRSHR_N(, uint, u, 8, 8, 3);
+  TEST_VRSHR_N(, uint, u, 16, 4, 3);
+  TEST_VRSHR_N(, uint, u, 32, 2, 3);
+  TEST_VRSHR_N(, uint, u, 64, 1, 3);
+  TEST_VRSHR_N(q, int, s, 8, 16, 3);
+  TEST_VRSHR_N(q, int, s, 16, 8, 3);
+  TEST_VRSHR_N(q, int, s, 32, 4, 3);
+  TEST_VRSHR_N(q, int, s, 64, 2, 3);
+  TEST_VRSHR_N(q, uint, u, 8, 16, 3);
+  TEST_VRSHR_N(q, uint, u, 16, 8, 3);
+  TEST_VRSHR_N(q, uint, u, 32, 4, 3);
+  TEST_VRSHR_N(q, uint, u, 64, 2, 3);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex2 (TEST_MSG, " (overflow test: shift by 3, with negative input)");
+}
diff --git a/ref_vrshrn_n.c b/ref_vrshrn_n.c
new file mode 100644
index 0000000..94f42b0
--- /dev/null
+++ b/ref_vrshrn_n.c
@@ -0,0 +1,119 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VRSHRN_N"
+void exec_vrshrn_n (void)
+{
+  /* Basic test: v2=vrshrn_n(v1,v), then store the result.  */
+#define TEST_VRSHRN_N(T1, T2, W, N, W2, V)				\
+  VECT_VAR(vector_res, T1, W2, N) =					\
+    vrshrn_n_##T2##W(VECT_VAR(vector, T1, W, N),			\
+		     V);						\
+  vst1_##T2##W2(VECT_VAR(result, T1, W2, N), VECT_VAR(vector_res, T1, W2, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+
+  /* vector is twice as large as vector_res */
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+  DECL_VARIABLE(vector, int, 64, 2);
+  DECL_VARIABLE(vector, uint, 16, 8);
+  DECL_VARIABLE(vector, uint, 32, 4);
+  DECL_VARIABLE(vector, uint, 64, 2);
+
+  DECL_VARIABLE(vector_res, int, 8, 8);
+  DECL_VARIABLE(vector_res, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 2);
+  DECL_VARIABLE(vector_res, uint, 8, 8);
+  DECL_VARIABLE(vector_res, uint, 16, 4);
+  DECL_VARIABLE(vector_res, uint, 32, 2);
+
+  clean_results ();
+
+  /* Fill input vector with 0, to check behavior on limits */
+  VDUP(vector, q, int, s, 16, 8, 0);
+  VDUP(vector, q, int, s, 32, 4, 0);
+  VDUP(vector, q, int, s, 64, 2, 0);
+  VDUP(vector, q, uint, u, 16, 8, 0);
+  VDUP(vector, q, uint, u, 32, 4, 0);
+  VDUP(vector, q, uint, u, 64, 2, 0);
+
+  /* Choose shift amount arbitrarily  */
+  TEST_VRSHRN_N(int, s, 16, 8, 8, 1);
+  TEST_VRSHRN_N(int, s, 32, 4, 16, 1);
+  TEST_VRSHRN_N(int, s, 64, 2, 32, 2);
+  TEST_VRSHRN_N(uint, u, 16, 8, 8, 2);
+  TEST_VRSHRN_N(uint, u, 32, 4, 16, 3);
+  TEST_VRSHRN_N(uint, u, 64, 2, 32, 3);
+
+  dump_results_hex2 (TEST_MSG, " (with input = 0)");
+
+  /* Test again, with predefined input values */
+  VLOAD(vector, buffer, q, int, s, 16, 8);
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+  VLOAD(vector, buffer, q, int, s, 64, 2);
+  VLOAD(vector, buffer, q, uint, u, 16, 8);
+  VLOAD(vector, buffer, q, uint, u, 32, 4);
+  VLOAD(vector, buffer, q, uint, u, 64, 2);
+
+  /* Choose shift amount arbitrarily  */
+  TEST_VRSHRN_N(int, s, 16, 8, 8, 1);
+  TEST_VRSHRN_N(int, s, 32, 4, 16, 1);
+  TEST_VRSHRN_N(int, s, 64, 2, 32, 2);
+  TEST_VRSHRN_N(uint, u, 16, 8, 8, 2);
+  TEST_VRSHRN_N(uint, u, 32, 4, 16, 3);
+  TEST_VRSHRN_N(uint, u, 64, 2, 32, 3);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex (TEST_MSG);
+
+  /* Fill input arbitrary values */
+  VDUP(vector, q, int, s, 16, 8, 30);
+  VDUP(vector, q, int, s, 32, 4, 0);
+  VDUP(vector, q, int, s, 64, 2, 0);
+  VDUP(vector, q, uint, u, 16, 8, 0xFFF0);
+  VDUP(vector, q, uint, u, 32, 4, 0xFFFFFFF0);
+  VDUP(vector, q, uint, u, 64, 2, 0);
+
+  /* Choose shift amount arbitrarily  */
+  TEST_VRSHRN_N(int, s, 16, 8, 8, 7);
+  TEST_VRSHRN_N(int, s, 32, 4, 16, 14);
+  TEST_VRSHRN_N(int, s, 64, 2, 32, 31);
+  TEST_VRSHRN_N(uint, u, 16, 8, 8, 7);
+  TEST_VRSHRN_N(uint, u, 32, 4, 16, 16);
+  TEST_VRSHRN_N(uint, u, 64, 2, 32, 3);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex2 (TEST_MSG, " (with large shift amount)");
+}
diff --git a/ref_vrsqrte.c b/ref_vrsqrte.c
new file mode 100644
index 0000000..d96f9d2
--- /dev/null
+++ b/ref_vrsqrte.c
@@ -0,0 +1,143 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+#include <math.h>
+
+#define TEST_MSG "VRSQRTE/VRSQRTEQ"
+void exec_vrsqrte(void)
+{
+  int i;
+
+  /* Basic test: y=vrsqrte(x), then store the result.  */
+#define TEST_VRSQRTE(Q, T1, T2, W, N)					\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vrsqrte##Q##_##T2##W(VECT_VAR(vector, T1, W, N));			\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),				\
+		    VECT_VAR(vector_res, T1, W, N))
+
+    /* With ARM RVCT, we need to declare variables before any executable
+       statement  */
+
+  /* No need for 64 bits variants */
+  DECL_VARIABLE(vector, uint, 32, 2);
+  DECL_VARIABLE(vector, float, 32, 2);
+  DECL_VARIABLE(vector, uint, 32, 4);
+  DECL_VARIABLE(vector, float, 32, 4);
+
+  DECL_VARIABLE(vector_res, uint, 32, 2);
+  DECL_VARIABLE(vector_res, float, 32, 2);
+  DECL_VARIABLE(vector_res, uint, 32, 4);
+  DECL_VARIABLE(vector_res, float, 32, 4);
+
+  clean_results ();
+
+  /* Choose init value arbitrarily */
+  VDUP(vector, , uint, u, 32, 2, 0x12345678);
+  VDUP(vector, , float, f, 32, 2, 25.799999f);
+  VDUP(vector, q, uint, u, 32, 4, 0xABCDEF10);
+  VDUP(vector, q, float, f, 32, 4, 18.2f);
+
+  /* Apply the operator */
+  TEST_VRSQRTE(, uint, u, 32, 2);
+  TEST_VRSQRTE(, float, f, 32, 2);
+  TEST_VRSQRTE(q, uint, u, 32, 4);
+  TEST_VRSQRTE(q, float, f, 32, 4);
+
+  fprintf (ref_file, "\n%s output:\n", TEST_MSG);
+  fprintf (gcc_tests_file, "\n%s output:\n", TEST_MSG);
+  DUMP(TEST_MSG, uint, 32, 2, PRIx32);
+  DUMP(TEST_MSG, uint, 32, 4, PRIx32);
+  DUMP_FP(TEST_MSG, float, 32, 2, PRIx32);
+  DUMP_FP(TEST_MSG, float, 32, 4, PRIx32);
+
+  /* Don't test FP variants with negative inputs: the result depends
+     on the platform */
+  /* Choose init value arbitrarily */
+  VDUP(vector, , uint, u, 32, 2, 0xFFFFFFFF);
+  VDUP(vector, q, uint, u, 32, 4, 0x89081234);
+
+  /* Apply the operator */
+  TEST_VRSQRTE(, uint, u, 32, 2);
+  TEST_VRSQRTE(q, uint, u, 32, 4);
+
+  fprintf (ref_file, "\n%s output:\n", TEST_MSG " (2)");
+  DUMP(TEST_MSG, uint, 32, 2, PRIx32);
+  DUMP(TEST_MSG, uint, 32, 4, PRIx32);
+
+  /* Choose init value arbitrarily */
+  VDUP(vector, , uint, u, 32, 2, 0x80000000);
+  VDUP(vector, q, uint, u, 32, 4, 0x4ABCDEF0);
+
+  /* Apply the operator */
+  TEST_VRSQRTE(, uint, u, 32, 2);
+  TEST_VRSQRTE(q, uint, u, 32, 4);
+
+  fprintf (ref_file, "\n%s output:\n", TEST_MSG " (3)");
+  DUMP(TEST_MSG, uint, 32, 2, PRIx32);
+  DUMP(TEST_MSG, uint, 32, 4, PRIx32);
+
+  /* Test FP variants with special input values (NaNs, ...) */
+  VDUP(vector, , float, f, 32, 2, NAN);
+  VDUP(vector, q, float, f, 32, 4, 0.0f);
+
+  /* Apply the operator */
+  TEST_VRSQRTE(, float, f, 32, 2);
+  TEST_VRSQRTE(q, float, f, 32, 4);
+
+  fprintf (ref_file, "\n%s output:\n", TEST_MSG " FP special (NaN, 0)");
+  DUMP_FP(TEST_MSG, float, 32, 2, PRIx32);
+  DUMP_FP(TEST_MSG, float, 32, 4, PRIx32);
+
+  /* Test FP variants with special input values (negative, infinity) */
+  VDUP(vector, , float, f, 32, 2, -1.0f);
+  VDUP(vector, q, float, f, 32, 4, HUGE_VALF);
+
+  /* Apply the operator */
+  TEST_VRSQRTE(, float, f, 32, 2);
+  TEST_VRSQRTE(q, float, f, 32, 4);
+
+  fprintf (ref_file, "\n%s output:\n", TEST_MSG " FP special (negative, infinity)");
+  DUMP_FP(TEST_MSG, float, 32, 2, PRIx32);
+  DUMP_FP(TEST_MSG, float, 32, 4, PRIx32);
+
+  /* Test FP variants with special input values (-0, -infinity) */
+  VDUP(vector, , float, f, 32, 2, -0.0f);
+  VDUP(vector, q, float, f, 32, 4, -HUGE_VALF);
+
+  /* Apply the operator */
+  TEST_VRSQRTE(, float, f, 32, 2);
+  TEST_VRSQRTE(q, float, f, 32, 4);
+
+  fprintf (ref_file, "\n%s output:\n", TEST_MSG " FP special (-0, -infinity)");
+  DUMP_FP(TEST_MSG, float, 32, 2, PRIx32);
+  DUMP_FP(TEST_MSG, float, 32, 4, PRIx32);
+}
diff --git a/ref_vrsqrts.c b/ref_vrsqrts.c
new file mode 100644
index 0000000..4e355b9
--- /dev/null
+++ b/ref_vrsqrts.c
@@ -0,0 +1,120 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+#include <math.h>
+
+#define TEST_MSG "VRSQRTS/VRSQRTSQ"
+void exec_vrsqrts(void)
+{
+  int i;
+
+  /* Basic test: y=vrsqrts(x), then store the result.  */
+#define TEST_VRSQRTS(Q, T1, T2, W, N)					\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vrsqrts##Q##_##T2##W(VECT_VAR(vector, T1, W, N),			\
+			 VECT_VAR(vector2, T1, W, N));			\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N),				\
+		    VECT_VAR(vector_res, T1, W, N))
+
+    /* With ARM RVCT, we need to declare variables before any executable
+       statement  */
+
+  /* No need for integer variants */
+  DECL_VARIABLE(vector, float, 32, 2);
+  DECL_VARIABLE(vector, float, 32, 4);
+
+  DECL_VARIABLE(vector2, float, 32, 2);
+  DECL_VARIABLE(vector2, float, 32, 4);
+
+  DECL_VARIABLE(vector_res, float, 32, 2);
+  DECL_VARIABLE(vector_res, float, 32, 4);
+
+  clean_results ();
+
+  /* Choose init value arbitrarily */
+  VDUP(vector, , float, f, 32, 2, 12.9f);
+  VDUP(vector, q, float, f, 32, 4, 9.1f);
+
+  VDUP(vector2, , float, f, 32, 2, 9.9f);
+  VDUP(vector2, q, float, f, 32, 4, 1.9f);
+
+  /* Apply the operator */
+  TEST_VRSQRTS(, float, f, 32, 2);
+  TEST_VRSQRTS(q, float, f, 32, 4);
+
+  fprintf (ref_file, "\n%s output:\n", TEST_MSG);
+  fprintf (gcc_tests_file, "\n%s output:\n", TEST_MSG);
+  DUMP_FP(TEST_MSG, float, 32, 2, PRIx32);
+  DUMP_FP(TEST_MSG, float, 32, 4, PRIx32);
+
+
+  /* Test FP variants with special input values (NaN) */
+  VDUP(vector, , float, f, 32, 2, NAN);
+  VDUP(vector2, q, float, f, 32, 4, NAN);
+
+  /* Apply the operator */
+  TEST_VRSQRTS(, float, f, 32, 2);
+  TEST_VRSQRTS(q, float, f, 32, 4);
+
+  fprintf (ref_file, "\n%s output:\n", TEST_MSG " FP special (NAN) and normal values");
+  DUMP_FP(TEST_MSG, float, 32, 2, PRIx32);
+  DUMP_FP(TEST_MSG, float, 32, 4, PRIx32);
+
+
+  /* Test FP variants with special input values (infinity, 0) */
+  VDUP(vector, , float, f, 32, 2, HUGE_VALF);
+  VDUP(vector, q, float, f, 32, 4, 0.0f);
+  VDUP(vector2, q, float, f, 32, 4, 3.2f); /* Restore a normal value */
+
+  /* Apply the operator */
+  TEST_VRSQRTS(, float, f, 32, 2);
+  TEST_VRSQRTS(q, float, f, 32, 4);
+
+  fprintf (ref_file, "\n%s output:\n", TEST_MSG " FP special (infinity, 0) and normal values");
+  DUMP_FP(TEST_MSG, float, 32, 2, PRIx32);
+  DUMP_FP(TEST_MSG, float, 32, 4, PRIx32);
+
+
+  /* Test FP variants with only special input values (infinity, 0) */
+  VDUP(vector, , float, f, 32, 2, HUGE_VALF);
+  VDUP(vector, q, float, f, 32, 4, 0.0f);
+  VDUP(vector2, , float, f, 32, 2, -0.0f);
+  VDUP(vector2, q, float, f, 32, 4, HUGE_VALF);
+
+  /* Apply the operator */
+  TEST_VRSQRTS(, float, f, 32, 2);
+  TEST_VRSQRTS(q, float, f, 32, 4);
+
+  fprintf (ref_file, "\n%s output:\n", TEST_MSG " FP special (infinity, 0)");
+  DUMP_FP(TEST_MSG, float, 32, 2, PRIx32);
+  DUMP_FP(TEST_MSG, float, 32, 4, PRIx32);
+}
diff --git a/ref_vrsra_n.c b/ref_vrsra_n.c
new file mode 100644
index 0000000..1546ff2
--- /dev/null
+++ b/ref_vrsra_n.c
@@ -0,0 +1,238 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VRSRA_N"
+void exec_vrsra_n (void)
+{
+  /* Basic test: y=vrsra_n(x,v), then store the result.  */
+#define TEST_VRSRA_N(Q, T1, T2, W, N, V)				\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vrsra##Q##_n_##T2##W(VECT_VAR(vector, T1, W, N),			\
+			 VECT_VAR(vector2, T1, W, N),			\
+			 V);						\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+  DECL_VARIABLE_ALL_VARIANTS(vector2);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+
+  /* Choose arbitrary initialization values */
+  VDUP(vector2, , int, s, 8, 8, 0x11);
+  VDUP(vector2, , int, s, 16, 4, 0x22);
+  VDUP(vector2, , int, s, 32, 2, 0x33);
+  VDUP(vector2, , int, s, 64, 1, 0x44);
+  VDUP(vector2, , uint, u, 8, 8, 0x55);
+  VDUP(vector2, , uint, u, 16, 4, 0x66);
+  VDUP(vector2, , uint, u, 32, 2, 0x77);
+  VDUP(vector2, , uint, u, 64, 1, 0x88);
+
+  VDUP(vector2, q, int, s, 8, 16, 0x11);
+  VDUP(vector2, q, int, s, 16, 8, 0x22);
+  VDUP(vector2, q, int, s, 32, 4, 0x33);
+  VDUP(vector2, q, int, s, 64, 2, 0x44);
+  VDUP(vector2, q, uint, u, 8, 16, 0x55);
+  VDUP(vector2, q, uint, u, 16, 8, 0x66);
+  VDUP(vector2, q, uint, u, 32, 4, 0x77);
+  VDUP(vector2, q, uint, u, 64, 2, 0x88);
+
+  /* Choose shift amount arbitrarily  */
+  TEST_VRSRA_N(, int, s, 8, 8, 1);
+  TEST_VRSRA_N(, int, s, 16, 4, 12);
+  TEST_VRSRA_N(, int, s, 32, 2, 2);
+  TEST_VRSRA_N(, int, s, 64, 1, 32);
+  TEST_VRSRA_N(, uint, u, 8, 8, 2);
+  TEST_VRSRA_N(, uint, u, 16, 4, 3);
+  TEST_VRSRA_N(, uint, u, 32, 2, 5);
+  TEST_VRSRA_N(, uint, u, 64, 1, 33);
+
+  TEST_VRSRA_N(q, int, s, 8, 16, 1);
+  TEST_VRSRA_N(q, int, s, 16, 8, 12);
+  TEST_VRSRA_N(q, int, s, 32, 4, 2);
+  TEST_VRSRA_N(q, int, s, 64, 2, 32);
+  TEST_VRSRA_N(q, uint, u, 8, 16, 2);
+  TEST_VRSRA_N(q, uint, u, 16, 8, 3);
+  TEST_VRSRA_N(q, uint, u, 32, 4, 5);
+  TEST_VRSRA_N(q, uint, u, 64, 2, 33);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex (TEST_MSG);
+
+  /* Initialize the accumulator with 0 */
+  VDUP(vector, , int, s, 8, 8, 0);
+  VDUP(vector, , int, s, 16, 4, 0);
+  VDUP(vector, , int, s, 32, 2, 0);
+  VDUP(vector, , int, s, 64, 1, 0);
+  VDUP(vector, , uint, u, 8, 8, 0);
+  VDUP(vector, , uint, u, 16, 4, 0);
+  VDUP(vector, , uint, u, 32, 2, 0);
+  VDUP(vector, , uint, u, 64, 1, 0);
+  VDUP(vector, q, int, s, 8, 16, 0);
+  VDUP(vector, q, int, s, 16, 8, 0);
+  VDUP(vector, q, int, s, 32, 4, 0);
+  VDUP(vector, q, int, s, 64, 2, 0);
+  VDUP(vector, q, uint, u, 8, 16, 0);
+  VDUP(vector, q, uint, u, 16, 8, 0);
+  VDUP(vector, q, uint, u, 32, 4, 0);
+  VDUP(vector, q, uint, u, 64, 2, 0);
+
+  /* Initialize with max values to check overflow */
+  VDUP(vector2, , int, s, 8, 8, 0x7F);
+  VDUP(vector2, , int, s, 16, 4, 0x7FFF);
+  VDUP(vector2, , int, s, 32, 2, 0x7FFFFFFF);
+  VDUP(vector2, , int, s, 64, 1, 0x7FFFFFFFFFFFFFFFLL);
+  VDUP(vector2, , uint, u, 8, 8, 0xFF);
+  VDUP(vector2, , uint, u, 16, 4, 0xFFFF);
+  VDUP(vector2, , uint, u, 32, 2, 0xFFFFFFFF);
+  VDUP(vector2, , uint, u, 64, 1, 0xFFFFFFFFFFFFFFFFULL);
+  VDUP(vector2, q, int, s, 8, 16, 0x7F);
+  VDUP(vector2, q, int, s, 16, 8, 0x7FFF);
+  VDUP(vector2, q, int, s, 32, 4, 0x7FFFFFFF);
+  VDUP(vector2, q, int, s, 64, 2, 0x7FFFFFFFFFFFFFFFLL);
+  VDUP(vector2, q, uint, u, 8, 16, 0xFF);
+  VDUP(vector2, q, uint, u, 16, 8, 0xFFFF);
+  VDUP(vector2, q, uint, u, 32, 4, 0xFFFFFFFF);
+  VDUP(vector2, q, uint, u, 64, 2, 0xFFFFFFFFFFFFFFFFULL);
+
+  /* Shift by 1 to check overflow with rounding constant  */
+  TEST_VRSRA_N(, int, s, 8, 8, 1);
+  TEST_VRSRA_N(, int, s, 16, 4, 1);
+  TEST_VRSRA_N(, int, s, 32, 2, 1);
+  TEST_VRSRA_N(, int, s, 64, 1, 1);
+  TEST_VRSRA_N(, uint, u, 8, 8, 1);
+  TEST_VRSRA_N(, uint, u, 16, 4, 1);
+  TEST_VRSRA_N(, uint, u, 32, 2, 1);
+  TEST_VRSRA_N(, uint, u, 64, 1, 1);
+  TEST_VRSRA_N(q, int, s, 8, 16, 1);
+  TEST_VRSRA_N(q, int, s, 16, 8, 1);
+  TEST_VRSRA_N(q, int, s, 32, 4, 1);
+  TEST_VRSRA_N(q, int, s, 64, 2, 1);
+  TEST_VRSRA_N(q, uint, u, 8, 16, 1);
+  TEST_VRSRA_N(q, uint, u, 16, 8, 1);
+  TEST_VRSRA_N(q, uint, u, 32, 4, 1);
+  TEST_VRSRA_N(q, uint, u, 64, 2, 1);
+
+  dump_results_hex2 (TEST_MSG, " (checking overflow: shift by 1, positive input)");
+
+  /* Shift by 3 to check overflow with rounding constant  */
+  TEST_VRSRA_N(, int, s, 8, 8, 3);
+  TEST_VRSRA_N(, int, s, 16, 4, 3);
+  TEST_VRSRA_N(, int, s, 32, 2, 3);
+  TEST_VRSRA_N(, int, s, 64, 1, 3);
+  TEST_VRSRA_N(, uint, u, 8, 8, 3);
+  TEST_VRSRA_N(, uint, u, 16, 4, 3);
+  TEST_VRSRA_N(, uint, u, 32, 2, 3);
+  TEST_VRSRA_N(, uint, u, 64, 1, 3);
+  TEST_VRSRA_N(q, int, s, 8, 16, 3);
+  TEST_VRSRA_N(q, int, s, 16, 8, 3);
+  TEST_VRSRA_N(q, int, s, 32, 4, 3);
+  TEST_VRSRA_N(q, int, s, 64, 2, 3);
+  TEST_VRSRA_N(q, uint, u, 8, 16, 3);
+  TEST_VRSRA_N(q, uint, u, 16, 8, 3);
+  TEST_VRSRA_N(q, uint, u, 32, 4, 3);
+  TEST_VRSRA_N(q, uint, u, 64, 2, 3);
+
+  dump_results_hex2 (TEST_MSG, " (checking overflow: shift by 3, positive input)");
+
+  /* Shift by max to check overflow with rounding constant  */
+  TEST_VRSRA_N(, int, s, 8, 8, 8);
+  TEST_VRSRA_N(, int, s, 16, 4, 16);
+  TEST_VRSRA_N(, int, s, 32, 2, 32);
+  TEST_VRSRA_N(, int, s, 64, 1, 64);
+  TEST_VRSRA_N(, uint, u, 8, 8, 8);
+  TEST_VRSRA_N(, uint, u, 16, 4, 16);
+  TEST_VRSRA_N(, uint, u, 32, 2, 32);
+  TEST_VRSRA_N(, uint, u, 64, 1, 64);
+  TEST_VRSRA_N(q, int, s, 8, 16, 8);
+  TEST_VRSRA_N(q, int, s, 16, 8, 16);
+  TEST_VRSRA_N(q, int, s, 32, 4, 32);
+  TEST_VRSRA_N(q, int, s, 64, 2, 64);
+  TEST_VRSRA_N(q, uint, u, 8, 16, 8);
+  TEST_VRSRA_N(q, uint, u, 16, 8, 16);
+  TEST_VRSRA_N(q, uint, u, 32, 4, 32);
+  TEST_VRSRA_N(q, uint, u, 64, 2, 64);
+
+  dump_results_hex2 (TEST_MSG, " (checking overflow: shift by max, positive input)");
+  /* Initialize with min values to check overflow */
+  VDUP(vector2, , int, s, 8, 8, 0x80);
+  VDUP(vector2, , int, s, 16, 4, 0x8000);
+  VDUP(vector2, , int, s, 32, 2, 0x80000000);
+  VDUP(vector2, , int, s, 64, 1, 0x8000000000000000LL);
+  VDUP(vector2, q, int, s, 8, 16, 0x80);
+  VDUP(vector2, q, int, s, 16, 8, 0x8000);
+  VDUP(vector2, q, int, s, 32, 4, 0x80000000);
+  VDUP(vector2, q, int, s, 64, 2, 0x8000000000000000ULL);
+
+  /* Shift by 1 to check overflow with rounding constant  */
+  TEST_VRSRA_N(, int, s, 8, 8, 1);
+  TEST_VRSRA_N(, int, s, 16, 4, 1);
+  TEST_VRSRA_N(, int, s, 32, 2, 1);
+  TEST_VRSRA_N(, int, s, 64, 1, 1);
+  TEST_VRSRA_N(q, int, s, 8, 16, 1);
+  TEST_VRSRA_N(q, int, s, 16, 8, 1);
+  TEST_VRSRA_N(q, int, s, 32, 4, 1);
+  TEST_VRSRA_N(q, int, s, 64, 2, 1);
+
+  dump_results_hex2 (TEST_MSG, " (checking overflow: shift by 1, negative input)");
+
+  /* Shift by 3 to check overflow with rounding constant  */
+  TEST_VRSRA_N(, int, s, 8, 8, 3);
+  TEST_VRSRA_N(, int, s, 16, 4, 3);
+  TEST_VRSRA_N(, int, s, 32, 2, 3);
+  TEST_VRSRA_N(, int, s, 64, 1, 3);
+  TEST_VRSRA_N(q, int, s, 8, 16, 3);
+  TEST_VRSRA_N(q, int, s, 16, 8, 3);
+  TEST_VRSRA_N(q, int, s, 32, 4, 3);
+  TEST_VRSRA_N(q, int, s, 64, 2, 3);
+
+  dump_results_hex2 (TEST_MSG, " (checking overflow: shift by max, negative input)");
+
+  /* Shift by max to check overflow with rounding constant  */
+  TEST_VRSRA_N(, int, s, 8, 8, 8);
+  TEST_VRSRA_N(, int, s, 16, 4, 16);
+  TEST_VRSRA_N(, int, s, 32, 2, 32);
+  TEST_VRSRA_N(, int, s, 64, 1, 64);
+  TEST_VRSRA_N(q, int, s, 8, 16, 8);
+  TEST_VRSRA_N(q, int, s, 16, 8, 16);
+  TEST_VRSRA_N(q, int, s, 32, 4, 32);
+  TEST_VRSRA_N(q, int, s, 64, 2, 64);
+
+  dump_results_hex2 (TEST_MSG, " (checking overflow: shift by max, negative input)");
+}
diff --git a/ref_vrsubhn.c b/ref_vrsubhn.c
new file mode 100644
index 0000000..e972d82
--- /dev/null
+++ b/ref_vrsubhn.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vrsubhn
+#define TEST_MSG "VRSUBHN"
+
+#include "ref_vaddhn.c"
diff --git a/ref_vsXi_n.c b/ref_vsXi_n.c
new file mode 100644
index 0000000..f710a67
--- /dev/null
+++ b/ref_vsXi_n.c
@@ -0,0 +1,116 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#ifndef INSN_NAME
+#define INSN_NAME vsli
+#define TEST_MSG "VSLI_N"
+#endif
+
+#define FNNAME1(NAME) void exec_ ## NAME ##_n (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* vector_res = vsxi_n(vector, vector2, val),
+     then store the result.  */
+#define TEST_VSXI_N1(INSN, Q, T1, T2, W, N, V)				\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    INSN##Q##_n_##T2##W(VECT_VAR(vector, T1, W, N),			\
+			VECT_VAR(vector2, T1, W, N),			\
+			V);						\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+#define TEST_VSXI_N(INSN, Q, T1, T2, W, N, V)	\
+  TEST_VSXI_N1(INSN, Q, T1, T2, W, N, V)
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+  DECL_VARIABLE_ALL_VARIANTS(vector2);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+
+  /* Fill input vector2 with arbitrary values */
+  VDUP(vector2, , int, s, 8, 8, 2);
+  VDUP(vector2, , int, s, 16, 4, -4);
+  VDUP(vector2, , int, s, 32, 2, 3);
+  VDUP(vector2, , int, s, 64, 1, 100);
+  VDUP(vector2, , uint, u, 8, 8, 20);
+  VDUP(vector2, , uint, u, 16, 4, 30);
+  VDUP(vector2, , uint, u, 32, 2, 40);
+  VDUP(vector2, , uint, u, 64, 1, 2);
+  VDUP(vector2, , poly, p, 8, 8, 20);
+  VDUP(vector2, , poly, p, 16, 4, 30);
+  VDUP(vector2, q, int, s, 8, 16, -10);
+  VDUP(vector2, q, int, s, 16, 8, -20);
+  VDUP(vector2, q, int, s, 32, 4, -30);
+  VDUP(vector2, q, int, s, 64, 2, 24);
+  VDUP(vector2, q, uint, u, 8, 16, 12);
+  VDUP(vector2, q, uint, u, 16, 8, 3);
+  VDUP(vector2, q, uint, u, 32, 4, 55);
+  VDUP(vector2, q, uint, u, 64, 2, 3);
+  VDUP(vector2, q, poly, p, 8, 16, 12);
+  VDUP(vector2, q, poly, p, 16, 8, 3);
+
+  /* Choose shift amount arbitrarily */
+  TEST_VSXI_N(INSN_NAME, , int, s, 8, 8, 4);
+  TEST_VSXI_N(INSN_NAME, , int, s, 16, 4, 3);
+  TEST_VSXI_N(INSN_NAME, , int, s, 32, 2, 1);
+  TEST_VSXI_N(INSN_NAME, , int, s, 64, 1, 32);
+  TEST_VSXI_N(INSN_NAME, , uint, u, 8, 8, 2);
+  TEST_VSXI_N(INSN_NAME, , uint, u, 16, 4, 10);
+  TEST_VSXI_N(INSN_NAME, , uint, u, 32, 2, 30);
+  TEST_VSXI_N(INSN_NAME, , uint, u, 64, 1, 3);
+  TEST_VSXI_N(INSN_NAME, , poly, p, 8, 8, 2);
+  TEST_VSXI_N(INSN_NAME, , poly, p, 16, 4, 10);
+  TEST_VSXI_N(INSN_NAME, q, int, s, 8, 16, 5);
+  TEST_VSXI_N(INSN_NAME, q, int, s, 16, 8, 3);
+  TEST_VSXI_N(INSN_NAME, q, int, s, 32, 4, 20);
+  TEST_VSXI_N(INSN_NAME, q, int, s, 64, 2, 16);
+  TEST_VSXI_N(INSN_NAME, q, uint, u, 8, 16, 3);
+  TEST_VSXI_N(INSN_NAME, q, uint, u, 16, 8, 12);
+  TEST_VSXI_N(INSN_NAME, q, uint, u, 32, 4, 23);
+  TEST_VSXI_N(INSN_NAME, q, uint, u, 64, 2, 53);
+  TEST_VSXI_N(INSN_NAME, q, poly, p, 8, 16, 3);
+  TEST_VSXI_N(INSN_NAME, q, poly, p, 16, 8, 12);
+
+  dump_results_hex (TEST_MSG);
+
+#ifdef EXTRA_TESTS
+  EXTRA_TESTS();
+#endif
+}
diff --git a/ref_vset_lane.c b/ref_vset_lane.c
new file mode 100644
index 0000000..cd04bf8
--- /dev/null
+++ b/ref_vset_lane.c
@@ -0,0 +1,82 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VSET_LANE/VSET_LANEQ"
+void exec_vset_lane (void)
+{
+  /* vec=vset_lane(val, vec, lane), then store the result.  */
+#define TEST_VSET_LANE_HERE(Q, T1, T2, W, N, V, L)			\
+  VECT_VAR(vector, T1, W, N) =						\
+    vset##Q##_lane_##T2##W(V,						\
+			   VECT_VAR(vector, T1, W, N),			\
+			   L);						\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector, T1, W, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+  VLOAD(vector, buffer, , float, f, 32, 2);
+  VLOAD(vector, buffer, q, float, f, 32, 4);
+
+  /* Choose value and lane arbitrarily  */
+  TEST_VSET_LANE_HERE(, int, s, 8, 8, 0x11, 7);
+  TEST_VSET_LANE_HERE(, int, s, 16, 4, 0x22, 3);
+  TEST_VSET_LANE_HERE(, int, s, 32, 2, 0x33, 1);
+  TEST_VSET_LANE_HERE(, int, s, 64, 1, 0x44, 0);
+  TEST_VSET_LANE_HERE(, uint, u, 8, 8, 0x55, 6);
+  TEST_VSET_LANE_HERE(, uint, u, 16, 4, 0x66, 2);
+  TEST_VSET_LANE_HERE(, uint, u, 32, 2, 0x77, 1);
+  TEST_VSET_LANE_HERE(, uint, u, 64, 1, 0x88, 0);
+  TEST_VSET_LANE_HERE(, poly, p, 8, 8, 0x55, 6);
+  TEST_VSET_LANE_HERE(, poly, p, 16, 4, 0x66, 2);
+  TEST_VSET_LANE_HERE(, float, f, 32, 2, 33.2f, 1);
+
+  TEST_VSET_LANE_HERE(q, int, s, 8, 16, 0x99, 15);
+  TEST_VSET_LANE_HERE(q, int, s, 16, 8, 0xAA, 5);
+  TEST_VSET_LANE_HERE(q, int, s, 32, 4, 0xBB, 3);
+  TEST_VSET_LANE_HERE(q, int, s, 64, 2, 0xCC, 1);
+  TEST_VSET_LANE_HERE(q, uint, u, 8, 16, 0xDD, 14);
+  TEST_VSET_LANE_HERE(q, uint, u, 16, 8, 0xEE, 6);
+  TEST_VSET_LANE_HERE(q, uint, u, 32, 4, 0xFF, 2);
+  TEST_VSET_LANE_HERE(q, uint, u, 64, 2, 0x11, 1);
+  TEST_VSET_LANE_HERE(q, poly, p, 8, 16, 0xDD, 14);
+  TEST_VSET_LANE_HERE(q, poly, p, 16, 8, 0xEE, 6);
+  TEST_VSET_LANE_HERE(q, float, f, 32, 4, 11.2f, 3);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vshl.c b/ref_vshl.c
new file mode 100644
index 0000000..048fecd
--- /dev/null
+++ b/ref_vshl.c
@@ -0,0 +1,98 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VSHL/VSHLQ"
+void exec_vshl (void)
+{
+  /* Basic test: v3=vshl(v1,v2), then store the result.  */
+#define TEST_VSHL(T3, Q, T1, T2, W, N)					\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vshl##Q##_##T2##W(VECT_VAR(vector, T1, W, N),			\
+		      VECT_VAR(vector_shift, T3, W, N));		\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+  DECL_VARIABLE_SIGNED_VARIANTS(vector_shift);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+
+  /* Choose init value arbitrarily, will be used as shift amount */
+  VDUP(vector_shift, , int, s, 8, 8, 1);
+  VDUP(vector_shift, , int, s, 16, 4, 3);
+  VDUP(vector_shift, , int, s, 32, 2, 8);
+  VDUP(vector_shift, , int, s, 64, 1, 3);
+  VDUP(vector_shift, q, int, s, 8, 16, 5);
+  VDUP(vector_shift, q, int, s, 16, 8, 12);
+  VDUP(vector_shift, q, int, s, 32, 4, 30);
+  VDUP(vector_shift, q, int, s, 64, 2, 63);
+
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VSHL, int);
+
+  dump_results_hex (TEST_MSG);
+
+  /* Test large shift amount */
+  VDUP(vector_shift, , int, s, 8, 8, 8);
+  VDUP(vector_shift, , int, s, 16, 4, 16);
+  VDUP(vector_shift, , int, s, 32, 2, 32);
+  VDUP(vector_shift, , int, s, 64, 1, 64);
+  VDUP(vector_shift, q, int, s, 8, 16, 8);
+  VDUP(vector_shift, q, int, s, 16, 8, 17);
+  VDUP(vector_shift, q, int, s, 32, 4, 33);
+  VDUP(vector_shift, q, int, s, 64, 2, 65);
+
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VSHL, int);
+
+  dump_results_hex2 (TEST_MSG, " (large shift amount)");
+
+
+  /* Test negative shift amount */
+  VDUP(vector_shift, , int, s, 8, 8, -1);
+  VDUP(vector_shift, , int, s, 16, 4, -1);
+  VDUP(vector_shift, , int, s, 32, 2, -2);
+  VDUP(vector_shift, , int, s, 64, 1, -4);
+  VDUP(vector_shift, q, int, s, 8, 16, -2);
+  VDUP(vector_shift, q, int, s, 16, 8, -5);
+  VDUP(vector_shift, q, int, s, 32, 4, -3);
+  VDUP(vector_shift, q, int, s, 64, 2, -5);
+
+  TEST_MACRO_ALL_VARIANTS_1_5(TEST_VSHL, int);
+
+  dump_results_hex2 (TEST_MSG, " (negative shift amount)");
+}
diff --git a/ref_vshl_n.c b/ref_vshl_n.c
new file mode 100644
index 0000000..87c914b
--- /dev/null
+++ b/ref_vshl_n.c
@@ -0,0 +1,75 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VSHL_N"
+void exec_vshl_n (void)
+{
+  /* Basic test: v2=vshl_n(v1,v), then store the result.  */
+#define TEST_VSHL_N(Q, T1, T2, W, N, V)					\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vshl##Q##_n_##T2##W(VECT_VAR(vector, T1, W, N),			\
+			V);						\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+
+  /* Choose shift amount arbitrarily  */
+  TEST_VSHL_N(, int, s, 8, 8, 1);
+  TEST_VSHL_N(, int, s, 16, 4, 1);
+  TEST_VSHL_N(, int, s, 32, 2, 3);
+  TEST_VSHL_N(, int, s, 64, 1, 2);
+  TEST_VSHL_N(, uint, u, 8, 8, 2);
+  TEST_VSHL_N(, uint, u, 16, 4, 4);
+  TEST_VSHL_N(, uint, u, 32, 2, 3);
+  TEST_VSHL_N(, uint, u, 64, 1, 1);
+
+  TEST_VSHL_N(q, int, s, 8, 16, 5);
+  TEST_VSHL_N(q, int, s, 16, 8, 1);
+  TEST_VSHL_N(q, int, s, 32, 4, 2);
+  TEST_VSHL_N(q, int, s, 64, 2, 2);
+  TEST_VSHL_N(q, uint, u, 8, 16, 2);
+  TEST_VSHL_N(q, uint, u, 16, 8, 3);
+  TEST_VSHL_N(q, uint, u, 32, 4, 2);
+  TEST_VSHL_N(q, uint, u, 64, 2, 1);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vshll_n.c b/ref_vshll_n.c
new file mode 100644
index 0000000..341f321
--- /dev/null
+++ b/ref_vshll_n.c
@@ -0,0 +1,64 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VSHLL_N"
+void exec_vshll_n (void)
+{
+  /* Basic test: v2=vshll_n(v1,v), then store the result.  */
+#define TEST_VSHLL_N(T1, T2, W, W2, N, V)				\
+  VECT_VAR(vector_res, T1, W2, N) =					\
+    vshll##_n_##T2##W(VECT_VAR(vector, T1, W, N),			\
+		      V);						\
+  vst1q##_##T2##W2(VECT_VAR(result, T1, W2, N), VECT_VAR(vector_res, T1, W2, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+
+  /* Choose shift amount arbitrarily  */
+  TEST_VSHLL_N(int, s, 8, 16, 8, 1);
+  TEST_VSHLL_N(int, s, 16, 32, 4, 1);
+  TEST_VSHLL_N(int, s, 32, 64, 2, 3);
+  TEST_VSHLL_N(uint, u, 8, 16, 8, 2);
+  TEST_VSHLL_N(uint, u, 16, 32, 4, 4);
+  TEST_VSHLL_N(uint, u, 32, 64, 2, 3);
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vshr_n.c b/ref_vshr_n.c
new file mode 100644
index 0000000..bff0f7b
--- /dev/null
+++ b/ref_vshr_n.c
@@ -0,0 +1,76 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VSHR_N"
+void exec_vshr_n (void)
+{
+  /* Basic test: y=vshr_n(x,v), then store the result.  */
+#define TEST_VSHR_N(Q, T1, T2, W, N, V)					\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vshr##Q##_n_##T2##W(VECT_VAR(vector, T1, W, N),			\
+			V);						\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+
+  /* Choose shift amount arbitrarily  */
+  TEST_VSHR_N(, int, s, 8, 8, 1);
+  TEST_VSHR_N(, int, s, 16, 4, 12);
+  TEST_VSHR_N(, int, s, 32, 2, 2);
+  TEST_VSHR_N(, int, s, 64, 1, 32);
+  TEST_VSHR_N(, uint, u, 8, 8, 2);
+  TEST_VSHR_N(, uint, u, 16, 4, 3);
+  TEST_VSHR_N(, uint, u, 32, 2, 5);
+  TEST_VSHR_N(, uint, u, 64, 1, 33);
+
+  TEST_VSHR_N(q, int, s, 8, 16, 1);
+  TEST_VSHR_N(q, int, s, 16, 8, 12);
+  TEST_VSHR_N(q, int, s, 32, 4, 2);
+  TEST_VSHR_N(q, int, s, 64, 2, 32);
+  TEST_VSHR_N(q, uint, u, 8, 16, 2);
+  TEST_VSHR_N(q, uint, u, 16, 8, 3);
+  TEST_VSHR_N(q, uint, u, 32, 4, 5);
+  TEST_VSHR_N(q, uint, u, 64, 2, 33);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vshrn_n.c b/ref_vshrn_n.c
new file mode 100644
index 0000000..f9b8041
--- /dev/null
+++ b/ref_vshrn_n.c
@@ -0,0 +1,81 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VSHRN_N"
+void exec_vshrn_n (void)
+{
+  /* Basic test: y=vshrn_n(x,v), then store the result.  */
+#define TEST_VSHRN_N(T1, T2, W, W2, N, V)				\
+  VECT_VAR(vector_res, T1, W2, N) =					\
+    vshrn_n_##T2##W(VECT_VAR(vector, T1, W, N),				\
+		    V);							\
+  vst1_##T2##W2(VECT_VAR(result, T1, W2, N), VECT_VAR(vector_res, T1, W2, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+
+  /* vector is twice as large as vector_res */
+  DECL_VARIABLE(vector, int, 16, 8);
+  DECL_VARIABLE(vector, int, 32, 4);
+  DECL_VARIABLE(vector, int, 64, 2);
+  DECL_VARIABLE(vector, uint, 16, 8);
+  DECL_VARIABLE(vector, uint, 32, 4);
+  DECL_VARIABLE(vector, uint, 64, 2);
+
+  DECL_VARIABLE(vector_res, int, 8, 8);
+  DECL_VARIABLE(vector_res, int, 16, 4);
+  DECL_VARIABLE(vector_res, int, 32, 2);
+  DECL_VARIABLE(vector_res, uint, 8, 8);
+  DECL_VARIABLE(vector_res, uint, 16, 4);
+  DECL_VARIABLE(vector_res, uint, 32, 2);
+
+  clean_results ();
+
+  VLOAD(vector, buffer, q, int, s, 16, 8);
+  VLOAD(vector, buffer, q, int, s, 32, 4);
+  VLOAD(vector, buffer, q, int, s, 64, 2);
+  VLOAD(vector, buffer, q, uint, u, 16, 8);
+  VLOAD(vector, buffer, q, uint, u, 32, 4);
+  VLOAD(vector, buffer, q, uint, u, 64, 2);
+
+  /* Choose shift amount arbitrarily  */
+  TEST_VSHRN_N(int, s, 16, 8, 8, 1);
+  TEST_VSHRN_N(int, s, 32, 16, 4, 1);
+  TEST_VSHRN_N(int, s, 64, 32, 2, 2);
+  TEST_VSHRN_N(uint, u, 16, 8, 8, 2);
+  TEST_VSHRN_N(uint, u, 32, 16, 4, 3);
+  TEST_VSHRN_N(uint, u, 64, 32, 2, 3);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vsli_n.c b/ref_vsli_n.c
new file mode 100644
index 0000000..2616d10
--- /dev/null
+++ b/ref_vsli_n.c
@@ -0,0 +1,96 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vsli
+#define TEST_MSG "VSLI_N"
+
+/* Extra tests for functions requiring corner cases tests */
+void vsli_extra(void);
+#define EXTRA_TESTS vsli_extra
+
+#include "ref_vsXi_n.c"
+
+void vsli_extra(void)
+{
+    /* Test cases with maximum shift amount (this amount is different
+       from vsri).  */
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+  DECL_VARIABLE_ALL_VARIANTS(vector2);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+
+  /* Fill input vector2 with arbitrary values */
+  VDUP(vector2, , int, s, 8, 8, 2);
+  VDUP(vector2, , int, s, 16, 4, -4);
+  VDUP(vector2, , int, s, 32, 2, 3);
+  VDUP(vector2, , int, s, 64, 1, 100);
+  VDUP(vector2, , uint, u, 8, 8, 20);
+  VDUP(vector2, , uint, u, 16, 4, 30);
+  VDUP(vector2, , uint, u, 32, 2, 40);
+  VDUP(vector2, , uint, u, 64, 1, 2);
+  VDUP(vector2, , poly, p, 8, 8, 20);
+  VDUP(vector2, , poly, p, 16, 4, 30);
+  VDUP(vector2, q, int, s, 8, 16, -10);
+  VDUP(vector2, q, int, s, 16, 8, -20);
+  VDUP(vector2, q, int, s, 32, 4, -30);
+  VDUP(vector2, q, int, s, 64, 2, 24);
+  VDUP(vector2, q, uint, u, 8, 16, 12);
+  VDUP(vector2, q, uint, u, 16, 8, 3);
+  VDUP(vector2, q, uint, u, 32, 4, 55);
+  VDUP(vector2, q, uint, u, 64, 2, 3);
+  VDUP(vector2, q, poly, p, 8, 16, 12);
+  VDUP(vector2, q, poly, p, 16, 8, 3);
+
+  /* Use maximum allowed shift amount */
+  TEST_VSXI_N(INSN_NAME, , int, s, 8, 8, 7);
+  TEST_VSXI_N(INSN_NAME, , int, s, 16, 4, 15);
+  TEST_VSXI_N(INSN_NAME, , int, s, 32, 2, 31);
+  TEST_VSXI_N(INSN_NAME, , int, s, 64, 1, 63);
+  TEST_VSXI_N(INSN_NAME, , uint, u, 8, 8, 7);
+  TEST_VSXI_N(INSN_NAME, , uint, u, 16, 4, 15);
+  TEST_VSXI_N(INSN_NAME, , uint, u, 32, 2, 31);
+  TEST_VSXI_N(INSN_NAME, , uint, u, 64, 1, 63);
+  TEST_VSXI_N(INSN_NAME, , poly, p, 8, 8, 7);
+  TEST_VSXI_N(INSN_NAME, , poly, p, 16, 4, 15);
+  TEST_VSXI_N(INSN_NAME, q, int, s, 8, 16, 7);
+  TEST_VSXI_N(INSN_NAME, q, int, s, 16, 8, 15);
+  TEST_VSXI_N(INSN_NAME, q, int, s, 32, 4, 31);
+  TEST_VSXI_N(INSN_NAME, q, int, s, 64, 2, 63);
+  TEST_VSXI_N(INSN_NAME, q, uint, u, 8, 16, 7);
+  TEST_VSXI_N(INSN_NAME, q, uint, u, 16, 8, 15);
+  TEST_VSXI_N(INSN_NAME, q, uint, u, 32, 4, 31);
+  TEST_VSXI_N(INSN_NAME, q, uint, u, 64, 2, 63);
+  TEST_VSXI_N(INSN_NAME, q, poly, p, 8, 16, 7);
+  TEST_VSXI_N(INSN_NAME, q, poly, p, 16, 8, 15);
+
+  dump_results_hex2 (TEST_MSG, "max shift amount");
+}
diff --git a/ref_vsra_n.c b/ref_vsra_n.c
new file mode 100644
index 0000000..bbbed14
--- /dev/null
+++ b/ref_vsra_n.c
@@ -0,0 +1,97 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VSRA_N"
+void exec_vsra_n (void)
+{
+  /* Basic test: y=vsra_n(x,v), then store the result.  */
+#define TEST_VSRA_N(Q, T1, T2, W, N, V)					\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vsra##Q##_n_##T2##W(VECT_VAR(vector, T1, W, N),			\
+			VECT_VAR(vector2, T1, W, N),			\
+			V);						\
+  vst1##Q##_##T2##W(VECT_VAR(result, T1, W, N), VECT_VAR(vector_res, T1, W, N))
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+  DECL_VARIABLE_ALL_VARIANTS(vector2);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+
+  /* Choose arbitrary initialization values */
+  VDUP(vector2, , int, s, 8, 8, 0x11);
+  VDUP(vector2, , int, s, 16, 4, 0x22);
+  VDUP(vector2, , int, s, 32, 2, 0x33);
+  VDUP(vector2, , int, s, 64, 1, 0x44);
+  VDUP(vector2, , uint, u, 8, 8, 0x55);
+  VDUP(vector2, , uint, u, 16, 4, 0x66);
+  VDUP(vector2, , uint, u, 32, 2, 0x77);
+  VDUP(vector2, , uint, u, 64, 1, 0x88);
+
+  VDUP(vector2, q, int, s, 8, 16, 0x11);
+  VDUP(vector2, q, int, s, 16, 8, 0x22);
+  VDUP(vector2, q, int, s, 32, 4, 0x33);
+  VDUP(vector2, q, int, s, 64, 2, 0x44);
+  VDUP(vector2, q, uint, u, 8, 16, 0x55);
+  VDUP(vector2, q, uint, u, 16, 8, 0x66);
+  VDUP(vector2, q, uint, u, 32, 4, 0x77);
+  VDUP(vector2, q, uint, u, 64, 2, 0x88);
+
+  /* Choose shift amount arbitrarily  */
+  TEST_VSRA_N(, int, s, 8, 8, 1);
+  TEST_VSRA_N(, int, s, 16, 4, 12);
+  TEST_VSRA_N(, int, s, 32, 2, 2);
+  TEST_VSRA_N(, int, s, 64, 1, 32);
+  TEST_VSRA_N(, uint, u, 8, 8, 2);
+  TEST_VSRA_N(, uint, u, 16, 4, 3);
+  TEST_VSRA_N(, uint, u, 32, 2, 5);
+  TEST_VSRA_N(, uint, u, 64, 1, 33);
+
+  TEST_VSRA_N(q, int, s, 8, 16, 1);
+  TEST_VSRA_N(q, int, s, 16, 8, 12);
+  TEST_VSRA_N(q, int, s, 32, 4, 2);
+  TEST_VSRA_N(q, int, s, 64, 2, 32);
+  TEST_VSRA_N(q, uint, u, 8, 16, 2);
+  TEST_VSRA_N(q, uint, u, 16, 8, 3);
+  TEST_VSRA_N(q, uint, u, 32, 4, 5);
+  TEST_VSRA_N(q, uint, u, 64, 2, 33);
+
+  /* FIXME: only a few result buffers are used, but we output all of them */
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vsri_n.c b/ref_vsri_n.c
new file mode 100644
index 0000000..7414b56
--- /dev/null
+++ b/ref_vsri_n.c
@@ -0,0 +1,96 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vsri
+#define TEST_MSG "VSRI_N"
+
+/* Extra tests for functions requiring corner cases tests */
+void vsri_extra(void);
+#define EXTRA_TESTS vsri_extra
+
+#include "ref_vsXi_n.c"
+
+void vsri_extra(void)
+{
+    /* Test cases with maximum shift amount (this amount is different
+       from vsli).  */
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+  DECL_VARIABLE_ALL_VARIANTS(vector2);
+  DECL_VARIABLE_ALL_VARIANTS(vector_res);
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+
+  /* Fill input vector2 with arbitrary values */
+  VDUP(vector2, , int, s, 8, 8, 2);
+  VDUP(vector2, , int, s, 16, 4, -4);
+  VDUP(vector2, , int, s, 32, 2, 3);
+  VDUP(vector2, , int, s, 64, 1, 100);
+  VDUP(vector2, , uint, u, 8, 8, 20);
+  VDUP(vector2, , uint, u, 16, 4, 30);
+  VDUP(vector2, , uint, u, 32, 2, 40);
+  VDUP(vector2, , uint, u, 64, 1, 2);
+  VDUP(vector2, , poly, p, 8, 8, 20);
+  VDUP(vector2, , poly, p, 16, 4, 30);
+  VDUP(vector2, q, int, s, 8, 16, -10);
+  VDUP(vector2, q, int, s, 16, 8, -20);
+  VDUP(vector2, q, int, s, 32, 4, -30);
+  VDUP(vector2, q, int, s, 64, 2, 24);
+  VDUP(vector2, q, uint, u, 8, 16, 12);
+  VDUP(vector2, q, uint, u, 16, 8, 3);
+  VDUP(vector2, q, uint, u, 32, 4, 55);
+  VDUP(vector2, q, uint, u, 64, 2, 3);
+  VDUP(vector2, q, poly, p, 8, 16, 12);
+  VDUP(vector2, q, poly, p, 16, 8, 3);
+
+  /* Use maximum allowed shift amount */
+  TEST_VSXI_N(INSN_NAME, , int, s, 8, 8, 8);
+  TEST_VSXI_N(INSN_NAME, , int, s, 16, 4, 16);
+  TEST_VSXI_N(INSN_NAME, , int, s, 32, 2, 32);
+  TEST_VSXI_N(INSN_NAME, , int, s, 64, 1, 64);
+  TEST_VSXI_N(INSN_NAME, , uint, u, 8, 8, 8);
+  TEST_VSXI_N(INSN_NAME, , uint, u, 16, 4, 16);
+  TEST_VSXI_N(INSN_NAME, , uint, u, 32, 2, 32);
+  TEST_VSXI_N(INSN_NAME, , uint, u, 64, 1, 64);
+  TEST_VSXI_N(INSN_NAME, , poly, p, 8, 8, 8);
+  TEST_VSXI_N(INSN_NAME, , poly, p, 16, 4, 16);
+  TEST_VSXI_N(INSN_NAME, q, int, s, 8, 16, 8);
+  TEST_VSXI_N(INSN_NAME, q, int, s, 16, 8, 16);
+  TEST_VSXI_N(INSN_NAME, q, int, s, 32, 4, 32);
+  TEST_VSXI_N(INSN_NAME, q, int, s, 64, 2, 64);
+  TEST_VSXI_N(INSN_NAME, q, uint, u, 8, 16, 8);
+  TEST_VSXI_N(INSN_NAME, q, uint, u, 16, 8, 16);
+  TEST_VSXI_N(INSN_NAME, q, uint, u, 32, 4, 32);
+  TEST_VSXI_N(INSN_NAME, q, uint, u, 64, 2, 64);
+  TEST_VSXI_N(INSN_NAME, q, poly, p, 8, 16, 8);
+  TEST_VSXI_N(INSN_NAME, q, poly, p, 16, 8, 16);
+
+  dump_results_hex2 (TEST_MSG, " max shift amount");
+}
diff --git a/ref_vst1_lane.c b/ref_vst1_lane.c
new file mode 100644
index 0000000..2225749
--- /dev/null
+++ b/ref_vst1_lane.c
@@ -0,0 +1,85 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#define TEST_MSG "VST1_LANE/VST1_LANEQ"
+void exec_vst1_lane (void)
+{
+#define TEST_VST1_LANE(Q, T1, T2, W, N, L)				\
+  VECT_VAR(vector, T1, W, N) =						\
+    vld1##Q##_##T2##W(VECT_VAR(buffer, T1, W, N));			\
+  vst1##Q##_lane_##T2##W(VECT_VAR(result, T1, W, N),			\
+			 VECT_VAR(vector, T1, W, N), L)
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  DECL_VARIABLE(vector, float, 16, 4);
+  DECL_VARIABLE(vector, float, 16, 8);
+#endif
+
+  clean_results ();
+
+  /* Choose lane arbitrarily  */
+  TEST_VST1_LANE(, int, s, 8, 8, 7);
+  TEST_VST1_LANE(, int, s, 16, 4, 3);
+  TEST_VST1_LANE(, int, s, 32, 2, 1);
+  TEST_VST1_LANE(, int, s, 64, 1, 0);
+  TEST_VST1_LANE(, uint, u, 8, 8, 6);
+  TEST_VST1_LANE(, uint, u, 16, 4, 2);
+  TEST_VST1_LANE(, uint, u, 32, 2, 0);
+  TEST_VST1_LANE(, uint, u, 64, 1, 0);
+  TEST_VST1_LANE(, poly, p, 8, 8, 6);
+  TEST_VST1_LANE(, poly, p, 16, 4, 2);
+  TEST_VST1_LANE(, float, f, 32, 2, 1);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_VST1_LANE(, float, f, 16, 4, 2);
+#endif
+
+  TEST_VST1_LANE(q, int, s, 8, 16, 15);
+  TEST_VST1_LANE(q, int, s, 16, 8, 5);
+  TEST_VST1_LANE(q, int, s, 32, 4, 1);
+  TEST_VST1_LANE(q, int, s, 64, 2, 1);
+  TEST_VST1_LANE(q, uint, u, 8, 16, 10);
+  TEST_VST1_LANE(q, uint, u, 16, 8, 4);
+  TEST_VST1_LANE(q, uint, u, 32, 4, 3);
+  TEST_VST1_LANE(q, uint, u, 64, 2, 0);
+  TEST_VST1_LANE(q, poly, p, 8, 16, 10);
+  TEST_VST1_LANE(q, poly, p, 16, 8, 4);
+  TEST_VST1_LANE(q, float, f, 32, 4, 1);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_VST1_LANE(q, float, f, 16, 8, 5);
+#endif
+
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vstX_lane.c b/ref_vstX_lane.c
new file mode 100644
index 0000000..50dd045
--- /dev/null
+++ b/ref_vstX_lane.c
@@ -0,0 +1,243 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+void exec_vstX_lane (void)
+{
+  /* In this case, input variables are arrays of vectors */
+#define DECL_VSTX_LANE(T1, W, N, X)					\
+  VECT_ARRAY_TYPE(T1, W, N, X) VECT_ARRAY_VAR(vector, T1, W, N, X);	\
+  VECT_ARRAY_TYPE(T1, W, N, X) VECT_ARRAY_VAR(vector_src, T1, W, N, X);	\
+  VECT_VAR_DECL(result_bis_##X, T1, W, N)[X * N]
+
+  /* We need to use a temporary result buffer (result_bis), because
+     the one used for other tests is not large enough. A subset of the
+     result data is moved from result_bis to result, and it is this
+     subset which is used to check the actual behaviour. The next
+     macro enables to move another chunk of data from result_bis to
+     result.  */
+#define TEST_VSTX_LANE(Q, T1, T2, W, N, X, L)				\
+  memset (VECT_VAR(buffer_src, T1, W, N), 0xAA,				\
+	  sizeof(VECT_VAR(buffer_src, T1, W, N)));			\
+  memset (VECT_VAR(result_bis_##X, T1, W, N), 0,			\
+	  sizeof(VECT_VAR(result_bis_##X, T1, W, N)));			\
+									\
+  VECT_ARRAY_VAR(vector_src, T1, W, N, X) =				\
+    vld##X##Q##_##T2##W(VECT_VAR(buffer_src, T1, W, N));		\
+									\
+  VECT_ARRAY_VAR(vector, T1, W, N, X) =					\
+    /* Use dedicated init buffer, of size X */				\
+    vld##X##Q##_lane_##T2##W(VECT_VAR(buffer_vld##X##_lane, T1, W, X),	\
+			     VECT_ARRAY_VAR(vector_src, T1, W, N, X),	\
+			     L);					\
+  vst##X##Q##_lane_##T2##W(VECT_VAR(result_bis_##X, T1, W, N),		\
+			   VECT_ARRAY_VAR(vector, T1, W, N, X),		\
+			   L);						\
+  memcpy(VECT_VAR(result, T1, W, N), VECT_VAR(result_bis_##X, T1, W, N), \
+	 sizeof(VECT_VAR(result, T1, W, N)));
+
+  /* Overwrite "result" with the contents of "result_bis"[Y] */
+#define TEST_EXTRA_CHUNK(T1, W, N, X, Y)		\
+  memcpy(VECT_VAR(result, T1, W, N),			\
+	 &(VECT_VAR(result_bis_##X, T1, W, N)[Y*N]),	\
+	 sizeof(VECT_VAR(result, T1, W, N)));
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+
+  /* We need all variants in 64 bits, but there is no 64x2 variant */
+#define DECL_ALL_VSTX_LANE(X)			\
+  DECL_VSTX_LANE(int, 8, 8, X);			\
+  DECL_VSTX_LANE(int, 16, 4, X);		\
+  DECL_VSTX_LANE(int, 32, 2, X);		\
+  DECL_VSTX_LANE(uint, 8, 8, X);		\
+  DECL_VSTX_LANE(uint, 16, 4, X);		\
+  DECL_VSTX_LANE(uint, 32, 2, X);		\
+  DECL_VSTX_LANE(poly, 8, 8, X);		\
+  DECL_VSTX_LANE(poly, 16, 4, X);		\
+  DECL_VSTX_LANE(float, 32, 2, X);		\
+  DECL_VSTX_LANE(int, 16, 8, X);		\
+  DECL_VSTX_LANE(int, 32, 4, X);		\
+  DECL_VSTX_LANE(uint, 16, 8, X);		\
+  DECL_VSTX_LANE(uint, 32, 4, X);		\
+  DECL_VSTX_LANE(poly, 16, 8, X);		\
+  DECL_VSTX_LANE(float, 32, 4, X)
+
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#define DECL_ALL_VSTX_LANE_FP16(X)		\
+  DECL_VSTX_LANE(float, 16, 4, X);		\
+  DECL_VSTX_LANE(float, 16, 8, X)
+#endif
+
+#define DUMMY_ARRAY(V, T, W, N, L) VECT_VAR_DECL(V,T,W,N)[N*L]
+
+  /* Use the same lanes regardless of the size of the array (X), for
+     simplicity */
+#define TEST_ALL_VSTX_LANE(X)			\
+  TEST_VSTX_LANE(, int, s, 8, 8, X, 7);		\
+  TEST_VSTX_LANE(, int, s, 16, 4, X, 2);	\
+  TEST_VSTX_LANE(, int, s, 32, 2, X, 0);	\
+  TEST_VSTX_LANE(, float, f, 32, 2, X, 0);	\
+  TEST_VSTX_LANE(, uint, u, 8, 8, X, 4);	\
+  TEST_VSTX_LANE(, uint, u, 16, 4, X, 3);	\
+  TEST_VSTX_LANE(, uint, u, 32, 2, X, 1);	\
+  TEST_VSTX_LANE(, poly, p, 8, 8, X, 4);	\
+  TEST_VSTX_LANE(, poly, p, 16, 4, X, 3);	\
+  TEST_VSTX_LANE(q, int, s, 16, 8, X, 6);	\
+  TEST_VSTX_LANE(q, int, s, 32, 4, X, 2);	\
+  TEST_VSTX_LANE(q, uint, u, 16, 8, X, 5);	\
+  TEST_VSTX_LANE(q, uint, u, 32, 4, X, 0);	\
+  TEST_VSTX_LANE(q, poly, p, 16, 8, X, 5);	\
+  TEST_VSTX_LANE(q, float, f, 32, 4, X, 2)
+
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#define TEST_ALL_VSTX_LANE_FP16(X)		\
+  TEST_VSTX_LANE(, float, f, 16, 4, X, 3);	\
+  TEST_VSTX_LANE(q, float, f, 16, 8, X, 6)
+#endif
+
+#define TEST_ALL_EXTRA_CHUNKS(X, Y)		\
+  TEST_EXTRA_CHUNK(int, 8, 8, X, Y);		\
+  TEST_EXTRA_CHUNK(int, 16, 4, X, Y);		\
+  TEST_EXTRA_CHUNK(int, 32, 2, X, Y);		\
+  TEST_EXTRA_CHUNK(uint, 8, 8, X, Y);		\
+  TEST_EXTRA_CHUNK(uint, 16, 4, X, Y);		\
+  TEST_EXTRA_CHUNK(uint, 32, 2, X, Y);		\
+  TEST_EXTRA_CHUNK(poly, 8, 8, X, Y);		\
+  TEST_EXTRA_CHUNK(poly, 16, 4, X, Y);		\
+  TEST_EXTRA_CHUNK(float, 32, 2, X, Y);		\
+  TEST_EXTRA_CHUNK(int, 16, 8, X, Y);		\
+  TEST_EXTRA_CHUNK(int, 32, 4, X, Y);		\
+  TEST_EXTRA_CHUNK(uint, 16, 8, X, Y);		\
+  TEST_EXTRA_CHUNK(uint, 32, 4, X, Y);		\
+  TEST_EXTRA_CHUNK(poly, 16, 8, X, Y);		\
+  TEST_EXTRA_CHUNK(float, 32, 4, X, Y)
+
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#define TEST_ALL_EXTRA_CHUNKS_FP16(X, Y)	\
+  TEST_EXTRA_CHUNK(float, 16, 4, X, Y);		\
+  TEST_EXTRA_CHUNK(float, 16, 8, X, Y)
+#endif
+
+  /* Declare the temporary buffers / variables */
+  DECL_ALL_VSTX_LANE(2);
+  DECL_ALL_VSTX_LANE(3);
+  DECL_ALL_VSTX_LANE(4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  DECL_ALL_VSTX_LANE_FP16(2);
+  DECL_ALL_VSTX_LANE_FP16(3);
+  DECL_ALL_VSTX_LANE_FP16(4);
+#endif
+
+  /* Define dummy input arrays, large enough for x4 vectors */
+  DUMMY_ARRAY(buffer_src, int, 8, 8, 4);
+  DUMMY_ARRAY(buffer_src, int, 16, 4, 4);
+  DUMMY_ARRAY(buffer_src, int, 32, 2, 4);
+  DUMMY_ARRAY(buffer_src, uint, 8, 8, 4);
+  DUMMY_ARRAY(buffer_src, uint, 16, 4, 4);
+  DUMMY_ARRAY(buffer_src, uint, 32, 2, 4);
+  DUMMY_ARRAY(buffer_src, poly, 8, 8, 4);
+  DUMMY_ARRAY(buffer_src, poly, 16, 4, 4);
+  DUMMY_ARRAY(buffer_src, float, 32, 2, 4);
+  DUMMY_ARRAY(buffer_src, int, 16, 8, 4);
+  DUMMY_ARRAY(buffer_src, int, 32, 4, 4);
+  DUMMY_ARRAY(buffer_src, uint, 16, 8, 4);
+  DUMMY_ARRAY(buffer_src, uint, 32, 4, 4);
+  DUMMY_ARRAY(buffer_src, poly, 16, 8, 4);
+  DUMMY_ARRAY(buffer_src, float, 32, 4, 4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  DUMMY_ARRAY(buffer_src, float, 16, 4, 4);
+  DUMMY_ARRAY(buffer_src, float, 16, 8, 4);
+#endif
+
+  /* Check vst2_lane/vst2q_lane */
+  clean_results ();
+#define TEST_MSG "VST2_LANE/VST2Q_LANE"
+  TEST_ALL_VSTX_LANE(2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_VSTX_LANE_FP16(2);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 0");
+
+  TEST_ALL_EXTRA_CHUNKS(2, 1);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_EXTRA_CHUNKS_FP16(2, 1);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 1");
+
+  /* Check vst3_lane/vst3q_lane */
+  clean_results ();
+#undef TEST_MSG
+#define TEST_MSG "VST3_LANE/VST3Q_LANE"
+  TEST_ALL_VSTX_LANE(3);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_VSTX_LANE_FP16(3);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 0");
+
+  TEST_ALL_EXTRA_CHUNKS(3, 1);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_EXTRA_CHUNKS_FP16(3, 1);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 1");
+  TEST_ALL_EXTRA_CHUNKS(3, 2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_EXTRA_CHUNKS_FP16(3, 2);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 2");
+
+  /* Check vst4_lane/vst4q_lane */
+  clean_results ();
+#undef TEST_MSG
+#define TEST_MSG "VST4_LANE/VST4Q_LANE"
+  TEST_ALL_VSTX_LANE(4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_VSTX_LANE_FP16(4);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 0");
+
+  TEST_ALL_EXTRA_CHUNKS(4, 1);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_EXTRA_CHUNKS_FP16(4, 1);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 1");
+  TEST_ALL_EXTRA_CHUNKS(4, 2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_EXTRA_CHUNKS_FP16(4, 2);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 2");
+  TEST_ALL_EXTRA_CHUNKS(4, 3);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  TEST_ALL_EXTRA_CHUNKS_FP16(4, 3);
+#endif
+  dump_results_hex2 (TEST_MSG, " chunk 3");
+}
diff --git a/ref_vsub.c b/ref_vsub.c
new file mode 100644
index 0000000..b83c8c6
--- /dev/null
+++ b/ref_vsub.c
@@ -0,0 +1,60 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vsub
+#define TEST_MSG "VSUB/VSUBQ"
+
+/* Extra tests for functions requiring floating-point types */
+void exec_vsub_f32(void);
+#define EXTRA_TESTS exec_vsub_f32
+
+#include "ref_v_binary_op.c"
+
+void exec_vsub_f32(void)
+{
+  int i;
+
+  DECL_VARIABLE(vector, float, 32, 2);
+  DECL_VARIABLE(vector, float, 32, 4);
+
+  DECL_VARIABLE(vector2, float, 32, 2);
+  DECL_VARIABLE(vector2, float, 32, 4);
+
+  DECL_VARIABLE(vector_res, float, 32, 2);
+  DECL_VARIABLE(vector_res, float, 32, 4);
+
+  VDUP(vector, , float, f, 32, 2, 2.3f);
+  VDUP(vector, q, float, f, 32, 4, 3.4f);
+
+  VDUP(vector2, , float, f, 32, 2, 4.5f);
+  VDUP(vector2, q, float, f, 32, 4, 5.6f);
+
+  TEST_BINARY_OP(INSN_NAME, , float, f, 32, 2);
+  TEST_BINARY_OP(INSN_NAME, q, float, f, 32, 4);
+
+  fprintf(ref_file, "\nfloat32:\n");
+  DUMP_FP(TEST_MSG, float, 32, 2, PRIx32);
+  DUMP_FP(TEST_MSG, float, 32, 4, PRIx32);
+}
diff --git a/ref_vsubhn.c b/ref_vsubhn.c
new file mode 100644
index 0000000..ef68d60
--- /dev/null
+++ b/ref_vsubhn.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vsubhn
+#define TEST_MSG "VSUBHN"
+
+#include "ref_vaddhn.c"
diff --git a/ref_vsubl.c b/ref_vsubl.c
new file mode 100644
index 0000000..093ab53
--- /dev/null
+++ b/ref_vsubl.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vsubl
+#define TEST_MSG "VSUBL"
+
+#include "ref_vaddl.c"
diff --git a/ref_vsubw.c b/ref_vsubw.c
new file mode 100644
index 0000000..1df07d1
--- /dev/null
+++ b/ref_vsubw.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vsubw
+#define TEST_MSG "VSUBW"
+
+#include "ref_vaddw.c"
diff --git a/ref_vtbX.c b/ref_vtbX.c
new file mode 100644
index 0000000..6f87d1a
--- /dev/null
+++ b/ref_vtbX.c
@@ -0,0 +1,227 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+void exec_vtbX (void)
+{
+  int i;
+
+  /* In this case, input variables are arrays of vectors */
+#define DECL_VTBX(T1, W, N, X)						\
+  VECT_ARRAY_TYPE(T1, W, N, X) VECT_ARRAY_VAR(table_vector, T1, W, N, X)
+
+  /* The vtbl1 variant is different from vtbl{2,3,4} because it takes a
+     vector as 1st param, instead of an array of vectors */
+#define TEST_VTBL1(T1, T2, T3, W, N)			\
+  VECT_VAR(table_vector, T1, W, N) =			\
+    vld1##_##T2##W((T1##W##_t *)lookup_table);		\
+							\
+  VECT_VAR(vector_res, T1, W, N) =			\
+    vtbl1_##T2##W(VECT_VAR(table_vector, T1, W, N),	\
+		  VECT_VAR(vector, T3, W, N));		\
+  vst1_##T2##W(VECT_VAR(result, T1, W, N),		\
+	       VECT_VAR(vector_res, T1, W, N));
+
+#define TEST_VTBLX(T1, T2, T3, W, N, X)					\
+  VECT_ARRAY_VAR(table_vector, T1, W, N, X) =				\
+    vld##X##_##T2##W((T1##W##_t *)lookup_table);			\
+									\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vtbl##X##_##T2##W(VECT_ARRAY_VAR(table_vector, T1, W, N, X),	\
+		      VECT_VAR(vector, T3, W, N));			\
+  vst1_##T2##W(VECT_VAR(result, T1, W, N),				\
+	       VECT_VAR(vector_res, T1, W, N));
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+
+  /* We need to define a lookup table */
+  uint8_t lookup_table[32];
+
+  DECL_VARIABLE(vector, int, 8, 8);
+  DECL_VARIABLE(vector, uint, 8, 8);
+  DECL_VARIABLE(vector, poly, 8, 8);
+  DECL_VARIABLE(vector_res, int, 8, 8);
+  DECL_VARIABLE(vector_res, uint, 8, 8);
+  DECL_VARIABLE(vector_res, poly, 8, 8);
+
+  /* For vtbl1 */
+  DECL_VARIABLE(table_vector, int, 8, 8);
+  DECL_VARIABLE(table_vector, uint, 8, 8);
+  DECL_VARIABLE(table_vector, poly, 8, 8);
+
+  /* For vtbx* */
+  DECL_VARIABLE(default_vector, int, 8, 8);
+  DECL_VARIABLE(default_vector, uint, 8, 8);
+  DECL_VARIABLE(default_vector, poly, 8, 8);
+
+  /* We need only 8 bits variants */
+#define DECL_ALL_VTBLX(X)			\
+  DECL_VTBX(int, 8, 8, X);			\
+  DECL_VTBX(uint, 8, 8, X);			\
+  DECL_VTBX(poly, 8, 8, X)
+
+#define TEST_ALL_VTBL1()			\
+  TEST_VTBL1(int, s, int, 8, 8);		\
+  TEST_VTBL1(uint, u, uint, 8, 8);		\
+  TEST_VTBL1(poly, p, uint, 8, 8)
+
+#define TEST_ALL_VTBLX(X)			\
+  TEST_VTBLX(int, s, int, 8, 8, X);		\
+  TEST_VTBLX(uint, u, uint, 8, 8, X);		\
+  TEST_VTBLX(poly, p, uint, 8, 8, X)
+
+  /* Declare the temporary buffers / variables */
+  DECL_ALL_VTBLX(2);
+  DECL_ALL_VTBLX(3);
+  DECL_ALL_VTBLX(4);
+
+  /* Fill the lookup table */
+  for (i=0; i<32; i++) {
+    lookup_table[i] = i-15;
+  }
+
+  /* Choose init value arbitrarily, will be used as table index */
+  VDUP(vector, , int, s, 8, 8, 1);
+  VDUP(vector, , uint, u, 8, 8, 2);
+  VDUP(vector, , poly, p, 8, 8, 2);
+
+  /* To ensure code coverage of lib, add some indexes larger than 8,16 and 32 */
+  /* except: lane 0 (by 6), lane 1 (by 8) and lane 2 (by 9) */
+  TEST_VSET_LANE(vector, , int, s, 8, 8, 0, 10);
+  TEST_VSET_LANE(vector, , int, s, 8, 8, 4, 20);
+  TEST_VSET_LANE(vector, , int, s, 8, 8, 5, 40);
+  TEST_VSET_LANE(vector, , uint, u, 8, 8, 0, 10);
+  TEST_VSET_LANE(vector, , uint, u, 8, 8, 4, 20);
+  TEST_VSET_LANE(vector, , uint, u, 8, 8, 5, 40);
+  TEST_VSET_LANE(vector, , poly, p, 8, 8, 0, 10);
+  TEST_VSET_LANE(vector, , poly, p, 8, 8, 4, 20);
+  TEST_VSET_LANE(vector, , poly, p, 8, 8, 5, 40);
+
+
+  /* Check vtbl1 */
+  clean_results ();
+#define TEST_MSG "VTBL1"
+  TEST_ALL_VTBL1();
+  dump_results_hex (TEST_MSG);
+
+  /* Check vtbl2 */
+  clean_results ();
+#undef TEST_MSG
+#define TEST_MSG "VTBL2"
+  TEST_ALL_VTBLX(2);
+  dump_results_hex (TEST_MSG);
+
+  /* Check vtbl3 */
+  clean_results ();
+#undef TEST_MSG
+#define TEST_MSG "VTBL3"
+  TEST_ALL_VTBLX(3);
+  dump_results_hex (TEST_MSG);
+
+  /* Check vtbl4 */
+  clean_results ();
+#undef TEST_MSG
+#define TEST_MSG "VTBL4"
+  TEST_ALL_VTBLX(4);
+  dump_results_hex (TEST_MSG);
+
+
+  /* Now test VTBX */
+
+  /* The vtbx1 variant is different from vtbx{2,3,4} because it takes a
+     vector as 1st param, instead of an array of vectors */
+#define TEST_VTBX1(T1, T2, T3, W, N)			\
+  VECT_VAR(table_vector, T1, W, N) =			\
+    vld1##_##T2##W((T1##W##_t *)lookup_table);		\
+							\
+  VECT_VAR(vector_res, T1, W, N) =			\
+    vtbx1_##T2##W(VECT_VAR(default_vector, T1, W, N),	\
+		  VECT_VAR(table_vector, T1, W, N),	\
+		  VECT_VAR(vector, T3, W, N));		\
+  vst1_##T2##W(VECT_VAR(result, T1, W, N),		\
+	       VECT_VAR(vector_res, T1, W, N));
+
+#define TEST_VTBXX(T1, T2, T3, W, N, X)					\
+  VECT_ARRAY_VAR(table_vector, T1, W, N, X) =				\
+    vld##X##_##T2##W((T1##W##_t *)lookup_table);			\
+									\
+  VECT_VAR(vector_res, T1, W, N) =					\
+    vtbx##X##_##T2##W(VECT_VAR(default_vector, T1, W, N),		\
+		      VECT_ARRAY_VAR(table_vector, T1, W, N, X),	\
+		      VECT_VAR(vector, T3, W, N));			\
+  vst1_##T2##W(VECT_VAR(result, T1, W, N),				\
+	       VECT_VAR(vector_res, T1, W, N));
+
+#define TEST_ALL_VTBX1()			\
+  TEST_VTBX1(int, s, int, 8, 8);		\
+  TEST_VTBX1(uint, u, uint, 8, 8);		\
+  TEST_VTBX1(poly, p, uint, 8, 8)
+
+#define TEST_ALL_VTBXX(X)			\
+  TEST_VTBXX(int, s, int, 8, 8, X);		\
+  TEST_VTBXX(uint, u, uint, 8, 8, X);		\
+  TEST_VTBXX(poly, p, uint, 8, 8, X)
+
+  /* Choose init value arbitrarily, will be used as default value */
+  VDUP(default_vector, , int, s, 8, 8, 0x33);
+  VDUP(default_vector, , uint, u, 8, 8, 0xCC);
+  VDUP(default_vector, , poly, p, 8, 8, 0xCC);
+
+  /* Check vtbx1 */
+  clean_results ();
+#undef TEST_MSG
+#define TEST_MSG "VTBX1"
+  TEST_ALL_VTBX1();
+  dump_results_hex (TEST_MSG);
+
+  /* Check vtbx2 */
+  clean_results ();
+#undef TEST_MSG
+#define TEST_MSG "VTBX2"
+  TEST_ALL_VTBXX(2);
+  dump_results_hex (TEST_MSG);
+
+  /* Check vtbx3 */
+  clean_results ();
+#undef TEST_MSG
+#define TEST_MSG "VTBX3"
+  TEST_ALL_VTBXX(3);
+  dump_results_hex (TEST_MSG);
+
+  /* Check vtbx4 */
+  clean_results ();
+#undef TEST_MSG
+#define TEST_MSG "VTBX4"
+  TEST_ALL_VTBXX(4);
+  dump_results_hex (TEST_MSG);
+}
diff --git a/ref_vtrn.c b/ref_vtrn.c
new file mode 100644
index 0000000..4ac3e84
--- /dev/null
+++ b/ref_vtrn.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vtrn
+#define TEST_MSG "VTRN/VTRNQ"
+
+#include "ref_vuzp.c"
diff --git a/ref_vtst.c b/ref_vtst.c
new file mode 100644
index 0000000..a273a3a
--- /dev/null
+++ b/ref_vtst.c
@@ -0,0 +1,99 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#ifndef INSN_NAME
+#define INSN_NAME vtst
+#define TEST_MSG "VTST/VTSTQ"
+#endif
+
+/* Can't use the standard ref_v_binary_op.c template because vtst has
+   no 64 bits variant, and outputs are always of uint type */
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* Basic test: y=OP(x,x), then store the result.  */
+#define TEST_BINARY_OP1(INSN, Q, T1, T2, W, N)				\
+  VECT_VAR(vector_res, uint, W, N) =					\
+    INSN##Q##_##T2##W(VECT_VAR(vector, T1, W, N),			\
+		      VECT_VAR(vector2, T1, W, N));			\
+  vst1##Q##_u##W(VECT_VAR(result, uint, W, N),				\
+		 VECT_VAR(vector_res, uint, W, N))
+
+#define TEST_BINARY_OP(INSN, Q, T1, T2, W, N)				\
+  TEST_BINARY_OP1(INSN, Q, T1, T2, W, N)				\
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement  */
+  DECL_VARIABLE_ALL_VARIANTS(vector);
+  DECL_VARIABLE_ALL_VARIANTS(vector2);
+  DECL_VARIABLE_UNSIGNED_VARIANTS(vector_res);
+
+
+  clean_results ();
+
+  /* Initialize input "vector" from "buffer"  */
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector, buffer);
+
+  /* Choose init value arbitrarily, will be used as comparison value */
+  VDUP(vector2, , int, s, 8, 8, 15);
+  VDUP(vector2, , int, s, 16, 4, 5);
+  VDUP(vector2, , int, s, 32, 2, 1);
+  VDUP(vector2, , uint, u, 8, 8, 15);
+  VDUP(vector2, , uint, u, 16, 4, 5);
+  VDUP(vector2, , uint, u, 32, 2, 1);
+  VDUP(vector2, q, int, s, 8, 16, 15);
+  VDUP(vector2, q, int, s, 16, 8, 5);
+  VDUP(vector2, q, int, s, 32, 4, 1);
+  VDUP(vector2, q, uint, u, 8, 16, 15);
+  VDUP(vector2, q, uint, u, 16, 8, 5);
+  VDUP(vector2, q, uint, u, 32, 4, 1);
+
+#define TEST_MACRO_NO64BIT_VARIANT_1_5(MACRO, VAR, T1, T2)	\
+  MACRO(VAR, , T1, T2, 8, 8);				\
+  MACRO(VAR, , T1, T2, 16, 4);				\
+  MACRO(VAR, , T1, T2, 32, 2);				\
+  MACRO(VAR, q, T1, T2, 8, 16);				\
+  MACRO(VAR, q, T1, T2, 16, 8);				\
+  MACRO(VAR, q, T1, T2, 32, 4)
+
+  /* Split the test, as both signed and unsigned variants output their
+     result in an unsigned form (thus the same output variable is used
+     in these tests) */
+  TEST_MACRO_NO64BIT_VARIANT_1_5(TEST_BINARY_OP, INSN_NAME, int, s);
+  dump_results_hex2 (TEST_MSG, " (signed input)");
+
+  TEST_MACRO_NO64BIT_VARIANT_1_5(TEST_BINARY_OP, INSN_NAME, uint, u);
+  dump_results_hex2 (TEST_MSG, " (unsigned input)");
+}
diff --git a/ref_vuzp.c b/ref_vuzp.c
new file mode 100644
index 0000000..0e6f1d8
--- /dev/null
+++ b/ref_vuzp.c
@@ -0,0 +1,171 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#if defined(__arm__) || defined(__aarch64__)
+#include <arm_neon.h>
+#else
+#include "stm-arm-neon.h"
+#endif
+
+#include "stm-arm-neon-ref.h"
+
+#ifndef INSN_NAME
+#define INSN_NAME vuzp
+#define TEST_MSG "VUZP/VUZPQ"
+#endif
+
+#define FNNAME1(NAME) void exec_ ## NAME (void)
+#define FNNAME(NAME) FNNAME1(NAME)
+
+FNNAME (INSN_NAME)
+{
+  /* In this case, output variables are arrays of vectors */
+#define DECL_VUZP(T1, W, N)						\
+  VECT_ARRAY_TYPE(T1, W, N, 2) VECT_ARRAY_VAR(result_vec, T1, W, N, 2);	\
+  VECT_VAR_DECL(result_bis, T1, W, N)[2 * N]
+
+  /* We need to use a temporary result buffer (result_bis), because
+     the one used for other tests is not large enough. A subset of the
+     result data is moved from result_bis to result, and it is this
+     subset which is used to check the actual behaviour. The next
+     macro enables to move another chunk of data from result_bis to
+     result.  */
+#define TEST_VUZP(INSN, Q, T1, T2, W, N)				\
+  VECT_ARRAY_VAR(result_vec, T1, W, N, 2) =				\
+    INSN##Q##_##T2##W(VECT_VAR(vector1, T1, W, N),			\
+		      VECT_VAR(vector2, T1, W, N));			\
+  vst2##Q##_##T2##W(VECT_VAR(result_bis, T1, W, N),			\
+		    VECT_ARRAY_VAR(result_vec, T1, W, N, 2));		\
+  memcpy(VECT_VAR(result, T1, W, N), VECT_VAR(result_bis, T1, W, N),	\
+	 sizeof(VECT_VAR(result, T1, W, N)));
+
+  /* Overwrite "result" with the contents of "result_bis"[X] */
+#define TEST_EXTRA_CHUNK(T1, W, N, X)					\
+  memcpy(VECT_VAR(result, T1, W, N), &(VECT_VAR(result_bis, T1, W, N)[X*N]), \
+	 sizeof(VECT_VAR(result, T1, W, N)));
+
+  /* With ARM RVCT, we need to declare variables before any executable
+     statement */
+  DECL_VARIABLE_ALL_VARIANTS(vector1);
+  DECL_VARIABLE_ALL_VARIANTS(vector2);
+
+  /* We don't need 64 bits variants */
+#define DECL_ALL_VUZP()				\
+  DECL_VUZP(int, 8, 8);				\
+  DECL_VUZP(int, 16, 4);			\
+  DECL_VUZP(int, 32, 2);			\
+  DECL_VUZP(uint, 8, 8);			\
+  DECL_VUZP(uint, 16, 4);			\
+  DECL_VUZP(uint, 32, 2);			\
+  DECL_VUZP(poly, 8, 8);			\
+  DECL_VUZP(poly, 16, 4);			\
+  DECL_VUZP(float, 32, 2);			\
+  DECL_VUZP(int, 8, 16);			\
+  DECL_VUZP(int, 16, 8);			\
+  DECL_VUZP(int, 32, 4);			\
+  DECL_VUZP(uint, 8, 16);			\
+  DECL_VUZP(uint, 16, 8);			\
+  DECL_VUZP(uint, 32, 4);			\
+  DECL_VUZP(poly, 8, 16);			\
+  DECL_VUZP(poly, 16, 8);			\
+  DECL_VUZP(float, 32, 4)
+
+  DECL_ALL_VUZP();
+
+  /* Initialize input "vector" from "buffer"  */
+  TEST_MACRO_ALL_VARIANTS_2_5(VLOAD, vector1, buffer);
+  VLOAD(vector1, buffer, , float, f, 32, 2);
+  VLOAD(vector1, buffer, q, float, f, 32, 4);
+
+  /* Choose arbitrary initialization values */
+  VDUP(vector2, , int, s, 8, 8, 0x11);
+  VDUP(vector2, , int, s, 16, 4, 0x22);
+  VDUP(vector2, , int, s, 32, 2, 0x33);
+  VDUP(vector2, , uint, u, 8, 8, 0x55);
+  VDUP(vector2, , uint, u, 16, 4, 0x66);
+  VDUP(vector2, , uint, u, 32, 2, 0x77);
+  VDUP(vector2, , poly, p, 8, 8, 0x55);
+  VDUP(vector2, , poly, p, 16, 4, 0x66);
+  VDUP(vector2, , float, f, 32, 2, 33.6f);
+
+  VDUP(vector2, q, int, s, 8, 16, 0x11);
+  VDUP(vector2, q, int, s, 16, 8, 0x22);
+  VDUP(vector2, q, int, s, 32, 4, 0x33);
+  VDUP(vector2, q, uint, u, 8, 16, 0x55);
+  VDUP(vector2, q, uint, u, 16, 8, 0x66);
+  VDUP(vector2, q, uint, u, 32, 4, 0x77);
+  VDUP(vector2, q, poly, p, 8, 16, 0x55);
+  VDUP(vector2, q, poly, p, 16, 8, 0x66);
+  VDUP(vector2, q, float, f, 32, 4, 33.8f);
+
+#define TEST_ALL_VUZP(INSN)			\
+  TEST_VUZP(INSN, , int, s, 8, 8);		\
+  TEST_VUZP(INSN, , int, s, 16, 4);		\
+  TEST_VUZP(INSN, , int, s, 32, 2);		\
+  TEST_VUZP(INSN, , uint, u, 8, 8);		\
+  TEST_VUZP(INSN, , uint, u, 16, 4);		\
+  TEST_VUZP(INSN, , uint, u, 32, 2);		\
+  TEST_VUZP(INSN, , poly, p, 8, 8);		\
+  TEST_VUZP(INSN, , poly, p, 16, 4);		\
+  TEST_VUZP(INSN, , float, f, 32, 2);		\
+  TEST_VUZP(INSN, q, int, s, 8, 16);		\
+  TEST_VUZP(INSN, q, int, s, 16, 8);		\
+  TEST_VUZP(INSN, q, int, s, 32, 4);		\
+  TEST_VUZP(INSN, q, uint, u, 8, 16);		\
+  TEST_VUZP(INSN, q, uint, u, 16, 8);		\
+  TEST_VUZP(INSN, q, uint, u, 32, 4);		\
+  TEST_VUZP(INSN, q, poly, p, 8, 16);		\
+  TEST_VUZP(INSN, q, poly, p, 16, 8);		\
+  TEST_VUZP(INSN, q, float, f, 32, 4)
+
+#define TEST_ALL_EXTRA_CHUNKS()			\
+  TEST_EXTRA_CHUNK(int, 8, 8, 1);		\
+  TEST_EXTRA_CHUNK(int, 16, 4, 1);		\
+  TEST_EXTRA_CHUNK(int, 32, 2, 1);		\
+  TEST_EXTRA_CHUNK(uint, 8, 8, 1);		\
+  TEST_EXTRA_CHUNK(uint, 16, 4, 1);		\
+  TEST_EXTRA_CHUNK(uint, 32, 2, 1);		\
+  TEST_EXTRA_CHUNK(poly, 8, 8, 1);		\
+  TEST_EXTRA_CHUNK(poly, 16, 4, 1);		\
+  TEST_EXTRA_CHUNK(float, 32, 2, 1);		\
+  TEST_EXTRA_CHUNK(int, 8, 16, 1);		\
+  TEST_EXTRA_CHUNK(int, 16, 8, 1);		\
+  TEST_EXTRA_CHUNK(int, 32, 4, 1);		\
+  TEST_EXTRA_CHUNK(uint, 8, 16, 1);		\
+  TEST_EXTRA_CHUNK(uint, 16, 8, 1);		\
+  TEST_EXTRA_CHUNK(uint, 32, 4, 1);		\
+  TEST_EXTRA_CHUNK(poly, 8, 16, 1);		\
+  TEST_EXTRA_CHUNK(poly, 16, 8, 1);		\
+  TEST_EXTRA_CHUNK(float, 32, 4, 1)
+
+  /* Check vuzp/vuzpq */
+  clean_results ();
+  TEST_ALL_VUZP(INSN_NAME);
+
+  dump_results_hex2 (TEST_MSG, " chunk 0");
+
+  TEST_ALL_EXTRA_CHUNKS();
+  dump_results_hex2 (TEST_MSG, " chunk 1");
+}
diff --git a/ref_vzip.c b/ref_vzip.c
new file mode 100644
index 0000000..8c0b363
--- /dev/null
+++ b/ref_vzip.c
@@ -0,0 +1,29 @@
+/*
+
+Copyright (c) 2009, 2010, 2011 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#define INSN_NAME vzip
+#define TEST_MSG "VZIP/VZIPQ"
+
+#include "ref_vuzp.c"
diff --git a/retarget.c b/retarget.c
new file mode 100644
index 0000000..3f01076
--- /dev/null
+++ b/retarget.c
@@ -0,0 +1,46 @@
+/*
+** Copyright (C) ARM Limited, 2005. All rights reserved.
+*/
+
+#if defined(__cplusplus)
+#include <cstdio>
+#else
+#include <stdio.h>
+#endif
+#include <rt_misc.h>
+
+// Heap base from scatter file
+extern int Image$$HEAP$$ZI$$Base;
+//#pragma import(__use_two_region_memory)
+
+extern void core_init(void);
+
+/*
+The functions below are patched onto main.
+*/
+
+extern void $Super$$main(void);
+
+void $Sub$$main(void)
+{
+  core_init();                    // does some extra setup work
+
+  $Super$$main();                 // calls the original function
+}
+
+
+/*
+This function re-implements the C Library semihosted function. The stack pointer
+has aready been set and is passed back to the function, The base of the heap is
+set from the scatter file
+*/
+__value_in_regs struct __initial_stackheap __user_initial_stackheap(
+        unsigned R0, unsigned SP, unsigned R2, unsigned SL)
+{
+    struct __initial_stackheap config;
+
+    config.heap_base = (unsigned int)&Image$$HEAP$$ZI$$Base; // placed by scatterfile
+    config.stack_base = SP;   // inherit SP from the execution environment
+
+    return config;
+}
diff --git a/scatter.scat b/scatter.scat
new file mode 100644
index 0000000..c6c8b46
--- /dev/null
+++ b/scatter.scat
@@ -0,0 +1,29 @@
+;;  Copyright ARM Ltd 2005. All rights reserved.
+
+ROM_LOAD 0x2000
+{
+
+    ROM_EXEC 0x2000
+    {
+        init.o (CortexA8, +First)     ; Create Translation Table
+        * (InRoot$$Sections)          ; this section must be in a root region
+    }
+
+    I-TCM 0x30000 FIXED ; 0x1E000     ; built at 0x100 to avoid vector space
+    {                                 ; assumes 32K I-TCM
+
+        * (+RO)                       ; any remaining code inc C lib.
+    }
+
+    D-TCM 0x230000 FIXED ; 0x40000            ; 8 Kb of D-TCM used for RW/ZI
+    {
+        * (+RW,+ZI)
+    }
+
+    HEAP 0x4E0000 EMPTY 0x100000 {}   ; 8Kb Heap follows direcly after RW/ZI
+
+    STACK 0x300000 EMPTY -0x8000 {}   ; 32KB Stack, starts after DTCM block.
+
+    TTB 0x20000 EMPTY 0x4000 {}       ; place translation table at 0x28000, 16Kb required
+
+}
diff --git a/stm-arm-neon-ref.h b/stm-arm-neon-ref.h
new file mode 100644
index 0000000..2f2d255
--- /dev/null
+++ b/stm-arm-neon-ref.h
@@ -0,0 +1,815 @@
+/*
+
+Copyright (c) 2009, 2010, 2011, 2012, 2013 STMicroelectronics
+Written by Christophe Lyon
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in
+all copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
+THE SOFTWARE.
+
+*/
+
+#ifndef _STM_ARM_NEON_REF_H_
+#define _STM_ARM_NEON_REF_H_
+
+#if defined(__cplusplus)
+#include <cstdio>
+#include <cinttypes>
+#include <cstring>
+#else
+#include <stdio.h>
+#if defined(_MSC_VER)
+#include "msinttypes.h"
+#include <float.h> /* for isnan() ... */
+static int32_t _ptrNan[]={0x7fc00000L};
+#define NAN (*(float*)_ptrNan)
+static int32_t _ptrInf[]={0x7f800000L};
+#define INFINITY (*(float*)_ptrInf)
+#define HUGE_VALF INFINITY
+#else
+#include <inttypes.h>
+#endif
+#include <string.h>
+#endif
+
+#define xSTR(X) #X
+#define STR(X) xSTR(X)
+
+#define xNAME1(V,T) V ## _ ##  T
+#define xNAME(V,T) xNAME1(V,T)
+
+#define VAR(V,T,W) xNAME(V,T##W)
+#define VAR_DECL(V, T, W) T##W##_t VAR(V,T,W)
+
+#define VECT_NAME(T, W, N) T##W##x##N
+#define VECT_ARRAY_NAME(T, W, N, L) T##W##x##N##x##L
+#define VECT_TYPE(T, W, N) xNAME(VECT_NAME(T,W,N),t)
+#define VECT_ARRAY_TYPE(T, W, N, L) xNAME(VECT_ARRAY_NAME(T,W,N,L),t)
+
+#define VECT_VAR(V,T,W,N) xNAME(V,VECT_NAME(T,W,N))
+#define VECT_VAR_DECL(V, T, W, N) T##W##_t VECT_VAR(V,T,W,N)
+
+/* This one is used for padding between input buffers.  */
+#define PAD(V, T, W, N) char VECT_VAR(V,T,W,N)=42;
+
+/* Array declarations.  */
+#define ARRAY(V, T, W, N) VECT_VAR_DECL(V,T,W,N)[N]
+#define ARRAY4(V, T, W, N) VECT_VAR_DECL(V,T,W,N)[4]
+
+/* Arrays of vectors.  */
+#define VECT_ARRAY_VAR(V,T,W,N,L) xNAME(V,VECT_ARRAY_NAME(T,W,N,L))
+#define VECT_ARRAY(V, T, W, N, L) T##W##_t VECT_ARRAY_VAR(V,T,W,N,L)[N*L]
+
+static int result_idx = 0;
+#define DUMP(MSG,T,W,N,FMT)						\
+  fprintf(ref_file, "%s:%d:%s [] = { ", MSG, result_idx++,		\
+	  STR(VECT_VAR(result, T, W, N)));				\
+  for(i=0; i<N ; i++)							\
+    {									\
+      fprintf(ref_file, "%" FMT ", ", VECT_VAR(result, T, W, N)[i]);	\
+    }									\
+  fprintf(ref_file, " }\n");						\
+  DUMP4GCC(MSG,T,W,N,FMT);
+
+/* Use casts for remove sign bits */
+#define DUMP_POLY(MSG,T,W,N,FMT)					\
+  fprintf(ref_file, "%s:%d:%s [] = { ", MSG, result_idx++,		\
+	  STR(VECT_VAR(result, T, W, N)));				\
+  for(i=0; i<N ; i++)							\
+    {									\
+      fprintf(ref_file, "%" FMT ", ",					\
+	      (uint##W##_t)VECT_VAR(result, T, W, N)[i]);		\
+    }									\
+  fprintf(ref_file, " }\n");						\
+  DUMP4GCC(MSG,T,W,N,FMT);
+
+#define DUMP_FP(MSG,T,W,N,FMT)						\
+  fprintf(ref_file, "%s:%d:%s [] = { ", MSG, result_idx++,		\
+	  STR(VECT_VAR(result, T, W, N)));				\
+  for(i=0; i<N ; i++)							\
+    {									\
+      union fp_operand {						\
+	uint##W##_t i;							\
+	float##W##_t f;							\
+      } tmp;								\
+      tmp.f = VECT_VAR(result, T, W, N)[i];				\
+      fprintf(ref_file, "%" FMT ", ", tmp.i);				\
+    }									\
+  fprintf(ref_file, " }\n");						\
+  DUMP4GCC_FP(MSG,T,W,N,FMT);
+
+#define DUMP4GCC(MSG,T,W,N,FMT)						\
+  fprintf(gcc_tests_file, "VECT_VAR_DECL(expected,%s,%d,%d) [] = { ",	\
+	  STR(T), W, N);						\
+  for(i=0; i<(N-1) ; i++)						\
+    {									\
+      if (W < 32) {							\
+	uint32_t tmp = (uint##W##_t) VECT_VAR(result, T, W, N)[i];	\
+	fprintf(gcc_tests_file, "0x%" FMT ", ", tmp);			\
+      } else {								\
+	fprintf(gcc_tests_file, "0x%" FMT ", ", VECT_VAR(result, T, W, N)[i]); \
+      }									\
+    }									\
+  if (W < 32) {								\
+    uint32_t tmp = (uint##W##_t) VECT_VAR(result, T, W, N)[i];		\
+    fprintf(gcc_tests_file, "0x%" FMT, tmp);				\
+  } else {								\
+    fprintf(gcc_tests_file, "0x%" FMT, VECT_VAR(result, T, W, N)[i]);	\
+  }									\
+  fprintf(gcc_tests_file, " };\n");
+
+#define DUMP4GCC_FP(MSG,T,W,N,FMT)					\
+  {									\
+    union fp_operand {							\
+      uint##W##_t i;							\
+      float##W##_t f;							\
+    } tmp;								\
+    fprintf(gcc_tests_file, "VECT_VAR_DECL(expected,%s,%d,%d) [] = { ",	\
+	    "hfloat", W, N);						\
+    for(i=0; i<(N-1) ; i++)						\
+      {									\
+	tmp.f = VECT_VAR(result, T, W, N)[i];				\
+	fprintf(gcc_tests_file, "0x%" FMT ", ", tmp.i);			\
+      }									\
+    tmp.f = VECT_VAR(result, T, W, N)[i];				\
+    fprintf(gcc_tests_file, "0x%" FMT, tmp.i);				\
+    fprintf(gcc_tests_file, " };\n");					\
+  }
+
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+#define float16_t __fp16
+
+#define DUMP_FP16(MSG,T,W,N,FMT)					\
+  fprintf(ref_file, "%s:%d:%s [] = { ", MSG, result_idx++,		\
+	  STR(VECT_VAR(result, T, W, N)));				\
+  for(i=0; i<N ; i++)							\
+    {									\
+      uint##W##_t tmp;							\
+	tmp = (uint##W##_t)VECT_VAR(result, T, W, N)[i];		\
+	fprintf(ref_file, "%" FMT ", ", tmp);				\
+    }									\
+  fprintf(ref_file, " }\n");						\
+  DUMP4GCC_FP16(MSG,T,W,N,FMT);
+
+#define DUMP4GCC_FP16(MSG,T,W,N,FMT)					\
+  {									\
+    uint##W##_t tmp;							\
+    fprintf(gcc_tests_file, "VECT_VAR_DECL(expected,%s,%d,%d) [] = { ", \
+	    "hfloat", W, N);						\
+    for(i=0; i<(N-1) ; i++)						\
+      {									\
+	tmp = (uint##W##_t)VECT_VAR(result, T, W, N)[i];		\
+	fprintf(gcc_tests_file, "0x%" FMT ", ", tmp);			\
+      }									\
+    tmp = (uint##W##_t)VECT_VAR(result, T, W, N)[i];			\
+    fprintf(gcc_tests_file, "0x%" FMT, tmp);				\
+    fprintf(gcc_tests_file, " };\n");					\
+  }
+#endif
+
+#define CLEAN_PATTERN_8  0x33
+#define CLEAN_PATTERN_16 0x3333
+#define CLEAN_PATTERN_32 0x33333333
+#define CLEAN_PATTERN_64 0x3333333333333333
+
+#define CLEAN(VAR,T,W,N)						\
+  memset(VECT_VAR(VAR, T, W, N),					\
+	 CLEAN_PATTERN_8,						\
+	 sizeof(VECT_VAR(VAR, T, W, N)));
+
+#define CHECK_INIT(VAR,Q,T1,T2,W,N)					\
+  {									\
+    ARRAY(check_result, T1, W, N);					\
+    int i;								\
+									\
+    vst1##Q##_##T2##W(VECT_VAR(check_result, T1, W, N),			\
+		      VECT_VAR(VAR, T1, W, N));				\
+    for(i=0; i<N ; i++)							\
+      {									\
+	/*if (VECT_VAR(check_result, T1, W, N)[i] == CLEAN_PATTERN_##W)*/ { \
+	  fprintf(stdout, "%s:%d: %s[%d] unintialized! %#x\n",		\
+		  __FUNCTION__,	__LINE__,				\
+		  STR(VECT_VAR(VAR, T1, W, N)), i,			\
+		  VECT_VAR(check_result, T1, W, N)[i]);			\
+	}								\
+      }									\
+  }
+
+/* Generic declarations: */
+extern FILE* log_file;
+extern FILE* ref_file;
+extern FILE* gcc_tests_file;
+
+/* Input buffers, one of each size */
+extern ARRAY(buffer, int, 8, 8);
+extern ARRAY(buffer, int, 16, 4);
+extern ARRAY(buffer, int, 32, 2);
+extern ARRAY(buffer, int, 64, 1);
+extern ARRAY(buffer, uint, 8, 8);
+extern ARRAY(buffer, uint, 16, 4);
+extern ARRAY(buffer, uint, 32, 2);
+extern ARRAY(buffer, uint, 64, 1);
+extern ARRAY(buffer, poly, 8, 8);
+extern ARRAY(buffer, poly, 16, 4);
+extern ARRAY(buffer, float, 32, 2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+extern ARRAY(buffer, float, 16, 4);
+#endif
+extern ARRAY(buffer, int, 8, 16);
+extern ARRAY(buffer, int, 16, 8);
+extern ARRAY(buffer, int, 32, 4);
+extern ARRAY(buffer, int, 64, 2);
+extern ARRAY(buffer, uint, 8, 16);
+extern ARRAY(buffer, uint, 16, 8);
+extern ARRAY(buffer, uint, 32, 4);
+extern ARRAY(buffer, uint, 64, 2);
+extern ARRAY(buffer, poly, 8, 16);
+extern ARRAY(buffer, poly, 16, 8);
+extern ARRAY(buffer, float, 32, 4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+extern ARRAY(buffer, float, 16, 8);
+#endif
+
+/* The tests for vld1_dup and vdup expect at least 4 entries in the
+   input buffer, so force 1- and 2-elements initializers to have 4
+   entries.  */
+extern ARRAY(buffer_dup, int, 8, 8);
+extern ARRAY(buffer_dup, int, 16, 4);
+extern ARRAY4(buffer_dup, int, 32, 2);
+extern ARRAY4(buffer_dup, int, 64, 1);
+extern ARRAY(buffer_dup, uint, 8, 8);
+extern ARRAY(buffer_dup, uint, 16, 4);
+extern ARRAY4(buffer_dup, uint, 32, 2);
+extern ARRAY4(buffer_dup, uint, 64, 1);
+extern ARRAY(buffer_dup, poly, 8, 8);
+extern ARRAY(buffer_dup, poly, 16, 4);
+extern ARRAY4(buffer_dup, float, 32, 2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+extern ARRAY4(buffer_dup, float, 16, 4);
+#endif
+extern ARRAY(buffer_dup, int, 8, 16);
+extern ARRAY(buffer_dup, int, 16, 8);
+extern ARRAY(buffer_dup, int, 32, 4);
+extern ARRAY4(buffer_dup, int, 64, 2);
+extern ARRAY(buffer_dup, uint, 8, 16);
+extern ARRAY(buffer_dup, uint, 16, 8);
+extern ARRAY(buffer_dup, uint, 32, 4);
+extern ARRAY4(buffer_dup, uint, 64, 2);
+extern ARRAY(buffer_dup, poly, 8, 16);
+extern ARRAY(buffer_dup, poly, 16, 8);
+extern ARRAY(buffer_dup, float, 32, 4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+extern ARRAY(buffer_dup, float, 16, 8);
+#endif
+
+/* Input buffers for vld2, one of each size */
+extern VECT_ARRAY(buffer_vld2, int, 8, 8, 2);
+extern VECT_ARRAY(buffer_vld2, int, 16, 4, 2);
+extern VECT_ARRAY(buffer_vld2, int, 32, 2, 2);
+extern VECT_ARRAY(buffer_vld2, int, 64, 1, 2);
+extern VECT_ARRAY(buffer_vld2, uint, 8, 8, 2);
+extern VECT_ARRAY(buffer_vld2, uint, 16, 4, 2);
+extern VECT_ARRAY(buffer_vld2, uint, 32, 2, 2);
+extern VECT_ARRAY(buffer_vld2, uint, 64, 1, 2);
+extern VECT_ARRAY(buffer_vld2, poly, 8, 8, 2);
+extern VECT_ARRAY(buffer_vld2, poly, 16, 4, 2);
+extern VECT_ARRAY(buffer_vld2, float, 32, 2, 2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+extern VECT_ARRAY(buffer_vld2, float, 16, 4, 2);
+#endif
+extern VECT_ARRAY(buffer_vld2, int, 8, 16, 2);
+extern VECT_ARRAY(buffer_vld2, int, 16, 8, 2);
+extern VECT_ARRAY(buffer_vld2, int, 32, 4, 2);
+extern VECT_ARRAY(buffer_vld2, int, 64, 2, 2);
+extern VECT_ARRAY(buffer_vld2, uint, 8, 16, 2);
+extern VECT_ARRAY(buffer_vld2, uint, 16, 8, 2);
+extern VECT_ARRAY(buffer_vld2, uint, 32, 4, 2);
+extern VECT_ARRAY(buffer_vld2, uint, 64, 2, 2);
+extern VECT_ARRAY(buffer_vld2, poly, 8, 16, 2);
+extern VECT_ARRAY(buffer_vld2, poly, 16, 8, 2);
+extern VECT_ARRAY(buffer_vld2, float, 32, 4, 2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+extern VECT_ARRAY(buffer_vld2, float, 16, 8, 2);
+#endif
+
+/* Input buffers for vld3, one of each size */
+extern VECT_ARRAY(buffer_vld3, int, 8, 8, 3);
+extern VECT_ARRAY(buffer_vld3, int, 16, 4, 3);
+extern VECT_ARRAY(buffer_vld3, int, 32, 2, 3);
+extern VECT_ARRAY(buffer_vld3, int, 64, 1, 3);
+extern VECT_ARRAY(buffer_vld3, uint, 8, 8, 3);
+extern VECT_ARRAY(buffer_vld3, uint, 16, 4, 3);
+extern VECT_ARRAY(buffer_vld3, uint, 32, 2, 3);
+extern VECT_ARRAY(buffer_vld3, uint, 64, 1, 3);
+extern VECT_ARRAY(buffer_vld3, poly, 8, 8, 3);
+extern VECT_ARRAY(buffer_vld3, poly, 16, 4, 3);
+extern VECT_ARRAY(buffer_vld3, float, 32, 2, 3);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+extern VECT_ARRAY(buffer_vld3, float, 16, 4, 3);
+#endif
+extern VECT_ARRAY(buffer_vld3, int, 8, 16, 3);
+extern VECT_ARRAY(buffer_vld3, int, 16, 8, 3);
+extern VECT_ARRAY(buffer_vld3, int, 32, 4, 3);
+extern VECT_ARRAY(buffer_vld3, int, 64, 2, 3);
+extern VECT_ARRAY(buffer_vld3, uint, 8, 16, 3);
+extern VECT_ARRAY(buffer_vld3, uint, 16, 8, 3);
+extern VECT_ARRAY(buffer_vld3, uint, 32, 4, 3);
+extern VECT_ARRAY(buffer_vld3, uint, 64, 2, 3);
+extern VECT_ARRAY(buffer_vld3, poly, 8, 16, 3);
+extern VECT_ARRAY(buffer_vld3, poly, 16, 8, 3);
+extern VECT_ARRAY(buffer_vld3, float, 32, 4, 3);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+extern VECT_ARRAY(buffer_vld3, float, 16, 8, 3);
+#endif
+
+/* Input buffers for vld4, one of each size */
+extern VECT_ARRAY(buffer_vld4, int, 8, 8, 4);
+extern VECT_ARRAY(buffer_vld4, int, 16, 4, 4);
+extern VECT_ARRAY(buffer_vld4, int, 32, 2, 4);
+extern VECT_ARRAY(buffer_vld4, int, 64, 1, 4);
+extern VECT_ARRAY(buffer_vld4, uint, 8, 8, 4);
+extern VECT_ARRAY(buffer_vld4, uint, 16, 4, 4);
+extern VECT_ARRAY(buffer_vld4, uint, 32, 2, 4);
+extern VECT_ARRAY(buffer_vld4, uint, 64, 1, 4);
+extern VECT_ARRAY(buffer_vld4, poly, 8, 8, 4);
+extern VECT_ARRAY(buffer_vld4, poly, 16, 4, 4);
+extern VECT_ARRAY(buffer_vld4, float, 32, 2, 4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+extern VECT_ARRAY(buffer_vld4, float, 16, 4, 4);
+#endif
+extern VECT_ARRAY(buffer_vld4, int, 8, 16, 4);
+extern VECT_ARRAY(buffer_vld4, int, 16, 8, 4);
+extern VECT_ARRAY(buffer_vld4, int, 32, 4, 4);
+extern VECT_ARRAY(buffer_vld4, int, 64, 2, 4);
+extern VECT_ARRAY(buffer_vld4, uint, 8, 16, 4);
+extern VECT_ARRAY(buffer_vld4, uint, 16, 8, 4);
+extern VECT_ARRAY(buffer_vld4, uint, 32, 4, 4);
+extern VECT_ARRAY(buffer_vld4, uint, 64, 2, 4);
+extern VECT_ARRAY(buffer_vld4, poly, 8, 16, 4);
+extern VECT_ARRAY(buffer_vld4, poly, 16, 8, 4);
+extern VECT_ARRAY(buffer_vld4, float, 32, 4, 4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+extern VECT_ARRAY(buffer_vld4, float, 16, 8, 4);
+#endif
+
+/* Input buffers for vld2_lane */
+extern VECT_VAR_DECL(buffer_vld2_lane, int, 8, 2)[2];
+extern VECT_VAR_DECL(buffer_vld2_lane, int, 16, 2)[2];
+extern VECT_VAR_DECL(buffer_vld2_lane, int, 32, 2)[2];
+extern VECT_VAR_DECL(buffer_vld2_lane, int, 64, 2)[2];
+extern VECT_VAR_DECL(buffer_vld2_lane, uint, 8, 2)[2];
+extern VECT_VAR_DECL(buffer_vld2_lane, uint, 16, 2)[2];
+extern VECT_VAR_DECL(buffer_vld2_lane, uint, 32, 2)[2];
+extern VECT_VAR_DECL(buffer_vld2_lane, uint, 64, 2)[2];
+extern VECT_VAR_DECL(buffer_vld2_lane, poly, 8, 2)[2];
+extern VECT_VAR_DECL(buffer_vld2_lane, poly, 16, 2)[2];
+extern VECT_VAR_DECL(buffer_vld2_lane, float, 32, 2)[2];
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+extern VECT_VAR_DECL(buffer_vld2_lane, float, 16, 2)[2];
+#endif
+
+/* Input buffers for vld3_lane */
+extern VECT_VAR_DECL(buffer_vld3_lane, int, 8, 3)[3];
+extern VECT_VAR_DECL(buffer_vld3_lane, int, 16, 3)[3];
+extern VECT_VAR_DECL(buffer_vld3_lane, int, 32, 3)[3];
+extern VECT_VAR_DECL(buffer_vld3_lane, int, 64, 3)[3];
+extern VECT_VAR_DECL(buffer_vld3_lane, uint, 8, 3)[3];
+extern VECT_VAR_DECL(buffer_vld3_lane, uint, 16, 3)[3];
+extern VECT_VAR_DECL(buffer_vld3_lane, uint, 32, 3)[3];
+extern VECT_VAR_DECL(buffer_vld3_lane, uint, 64, 3)[3];
+extern VECT_VAR_DECL(buffer_vld3_lane, poly, 8, 3)[3];
+extern VECT_VAR_DECL(buffer_vld3_lane, poly, 16, 3)[3];
+extern VECT_VAR_DECL(buffer_vld3_lane, float, 32, 3)[3];
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+extern VECT_VAR_DECL(buffer_vld3_lane, float, 16, 3)[3];
+#endif
+
+/* Input buffers for vld4_lane */
+extern VECT_VAR_DECL(buffer_vld4_lane, int, 8, 4)[4];
+extern VECT_VAR_DECL(buffer_vld4_lane, int, 16, 4)[4];
+extern VECT_VAR_DECL(buffer_vld4_lane, int, 32, 4)[4];
+extern VECT_VAR_DECL(buffer_vld4_lane, int, 64, 4)[4];
+extern VECT_VAR_DECL(buffer_vld4_lane, uint, 8, 4)[4];
+extern VECT_VAR_DECL(buffer_vld4_lane, uint, 16, 4)[4];
+extern VECT_VAR_DECL(buffer_vld4_lane, uint, 32, 4)[4];
+extern VECT_VAR_DECL(buffer_vld4_lane, uint, 64, 4)[4];
+extern VECT_VAR_DECL(buffer_vld4_lane, poly, 8, 4)[4];
+extern VECT_VAR_DECL(buffer_vld4_lane, poly, 16, 4)[4];
+extern VECT_VAR_DECL(buffer_vld4_lane, float, 32, 4)[4];
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+extern VECT_VAR_DECL(buffer_vld4_lane, float, 16, 4)[4];
+#endif
+
+/* Output buffers, one of each size */
+static ARRAY(result, int, 8, 8);
+static ARRAY(result, int, 16, 4);
+static ARRAY(result, int, 32, 2);
+static ARRAY(result, int, 64, 1);
+static ARRAY(result, uint, 8, 8);
+static ARRAY(result, uint, 16, 4);
+static ARRAY(result, uint, 32, 2);
+static ARRAY(result, uint, 64, 1);
+static ARRAY(result, poly, 8, 8);
+static ARRAY(result, poly, 16, 4);
+static ARRAY(result, float, 32, 2);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+static ARRAY(result, float, 16, 4);
+#endif
+static ARRAY(result, int, 8, 16);
+static ARRAY(result, int, 16, 8);
+static ARRAY(result, int, 32, 4);
+static ARRAY(result, int, 64, 2);
+static ARRAY(result, uint, 8, 16);
+static ARRAY(result, uint, 16, 8);
+static ARRAY(result, uint, 32, 4);
+static ARRAY(result, uint, 64, 2);
+static ARRAY(result, poly, 8, 16);
+static ARRAY(result, poly, 16, 8);
+static ARRAY(result, float, 32, 4);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+static ARRAY(result, float, 16, 8);
+#endif
+
+/* Dump results (generic function) */
+static void dump_results (char *test_name)
+{
+  int i;
+
+  fprintf(ref_file, "\n%s output:\n", test_name);
+  fprintf(gcc_tests_file, "\n%s output:\n", test_name);
+
+  DUMP(test_name, int, 8, 8, PRId8);
+  DUMP(test_name, int, 16, 4, PRId16);
+  DUMP(test_name, int, 32, 2, PRId32);
+  DUMP(test_name, int, 64, 1, PRId64);
+  DUMP(test_name, uint, 8, 8, PRIu8);
+  DUMP(test_name, uint, 16, 4, PRIu16);
+  DUMP(test_name, uint, 32, 2, PRIu32);
+  DUMP(test_name, uint, 64, 1, PRIu64);
+  DUMP_POLY(test_name, poly, 8, 8, PRIu8);
+  DUMP_POLY(test_name, poly, 16, 4, PRIu16);
+  DUMP_FP(test_name, float, 32, 2, PRIx32);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  DUMP_FP16(test_name, float, 16, 4, PRIu16);
+#endif
+
+  DUMP(test_name, int, 8, 16, PRId8);
+  DUMP(test_name, int, 16, 8, PRId16);
+  DUMP(test_name, int, 32, 4, PRId32);
+  DUMP(test_name, int, 64, 2, PRId64);
+  DUMP(test_name, uint, 8, 16, PRIu8);
+  DUMP(test_name, uint, 16, 8, PRIu16);
+  DUMP(test_name, uint, 32, 4, PRIu32);
+  DUMP(test_name, uint, 64, 2, PRIu64);
+  DUMP_POLY(test_name, poly, 8, 16, PRIu8);
+  DUMP_POLY(test_name, poly, 16, 8, PRIu16);
+  DUMP_FP(test_name, float, 32, 4, PRIx32);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  DUMP_FP16(test_name, float, 16, 8, PRIu16);
+#endif
+}
+
+/* Dump results in hex (generic function) */
+static void dump_results_hex2 (const char *test_name, const char* comment)
+{
+  int i;
+
+  fprintf(ref_file, "\n%s%s output:\n", test_name, comment);
+  fprintf(gcc_tests_file, "\n%s%s output:\n", test_name, comment);
+
+  DUMP(test_name, int, 8, 8, PRIx8);
+  DUMP(test_name, int, 16, 4, PRIx16);
+  DUMP(test_name, int, 32, 2, PRIx32);
+  DUMP(test_name, int, 64, 1, PRIx64);
+  DUMP(test_name, uint, 8, 8, PRIx8);
+  DUMP(test_name, uint, 16, 4, PRIx16);
+  DUMP(test_name, uint, 32, 2, PRIx32);
+  DUMP(test_name, uint, 64, 1, PRIx64);
+  DUMP_POLY(test_name, poly, 8, 8, PRIx8);
+  DUMP_POLY(test_name, poly, 16, 4, PRIx16);
+  DUMP_FP(test_name, float, 32, 2, PRIx32);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  DUMP_FP16(test_name, float, 16, 4, PRIx16);
+#endif
+
+  DUMP(test_name, int, 8, 16, PRIx8);
+  DUMP(test_name, int, 16, 8, PRIx16);
+  DUMP(test_name, int, 32, 4, PRIx32);
+  DUMP(test_name, int, 64, 2, PRIx64);
+  DUMP(test_name, uint, 8, 16, PRIx8);
+  DUMP(test_name, uint, 16, 8, PRIx16);
+  DUMP(test_name, uint, 32, 4, PRIx32);
+  DUMP(test_name, uint, 64, 2, PRIx64);
+  DUMP_POLY(test_name, poly, 8, 16, PRIx8);
+  DUMP_POLY(test_name, poly, 16, 8, PRIx16);
+  DUMP_FP(test_name, float, 32, 4, PRIx32);
+#if defined(__ARM_FP16_FORMAT_IEEE) && ( ((__ARM_FP & 0x2) != 0) || ((__ARM_NEON_FP16_INTRINSICS & 1) != 0) )
+  DUMP_FP16(test_name, float, 16, 8, PRIx16);
+#endif
+}
+
+static void dump_results_hex (const char *test_name)
+{
+  dump_results_hex2(test_name, "");
+}
+
+#ifndef STM_ARM_NEON_MODELS
+
+/* This hack is to cope with various compilers/libc which may not
+   provide endian.h or cross-compilers such as llvm which includes the
+   host's endian.h.  */
+#ifndef __arm__
+#include <endian.h>
+#define THIS_ENDIAN __BYTE_ORDER
+#else /* __arm__ */
+#ifdef __ARMEL__
+#define THIS_ENDIAN __LITTLE_ENDIAN
+#else /* __ARMEL__ */
+#define THIS_ENDIAN __BIG_ENDIAN
+#endif
+#endif /* __arm__ */
+
+#if THIS_ENDIAN == __LITTLE_ENDIAN
+
+typedef union {
+  struct {
+    int _xxx:27;
+    unsigned int QC:1;
+    int V:1;
+    int C:1;
+    int Z:1;
+    int N:1;
+  } b;
+  unsigned int word;
+} _ARM_FPSCR;
+
+#else /* __BIG_ENDIAN */
+
+typedef union {
+  struct {
+    int N:1;
+    int Z:1;
+    int C:1;
+    int V:1;
+    unsigned int QC:1;
+    int _dnm:27;
+  } b;
+  unsigned int word;
+} _ARM_FPSCR;
+
+#endif /* __BIG_ENDIAN */
+
+#ifdef __ARMCC_VERSION
+register _ARM_FPSCR _afpscr_for_qc __asm("fpscr");
+# define Neon_Cumulative_Sat _afpscr_for_qc.b.QC
+# define Set_Neon_Cumulative_Sat(x, depend)  {Neon_Cumulative_Sat = (x);}
+#else
+/* GCC/ARM does not know this register */
+# define Neon_Cumulative_Sat  __read_neon_cumulative_sat()
+/* We need a fake dependency to ensure correct ordering of asm
+   statements to preset the QC flag value, and Neon operators writing
+   to QC. */
+#define Set_Neon_Cumulative_Sat(x, depend)	\
+  __set_neon_cumulative_sat((x), (depend))
+
+# if defined(__aarch64__)
+static volatile int __read_neon_cumulative_sat (void) {
+    _ARM_FPSCR _afpscr_for_qc;
+    asm volatile ("mrs %0,fpsr" : "=r" (_afpscr_for_qc));
+    return _afpscr_for_qc.b.QC;
+}
+
+#define __set_neon_cumulative_sat(x, depend) {				\
+    _ARM_FPSCR _afpscr_for_qc;						\
+    asm volatile ("mrs %0,fpsr" : "=r" (_afpscr_for_qc));		\
+    _afpscr_for_qc.b.QC = x;						\
+    asm volatile ("msr fpsr,%1" : "=X" (depend) : "r" (_afpscr_for_qc)); \
+  }
+
+# else
+static volatile int __read_neon_cumulative_sat (void) {
+    _ARM_FPSCR _afpscr_for_qc;
+    asm volatile ("vmrs %0,fpscr" : "=r" (_afpscr_for_qc));
+    return _afpscr_for_qc.b.QC;
+}
+
+#define __set_neon_cumulative_sat(x, depend) {				\
+    _ARM_FPSCR _afpscr_for_qc;						\
+    asm volatile ("vmrs %0,fpscr" : "=r" (_afpscr_for_qc));		\
+    _afpscr_for_qc.b.QC = x;						\
+    asm volatile ("vmsr fpscr,%1" : "=X" (depend) : "r" (_afpscr_for_qc)); \
+  }
+
+# endif
+#endif
+
+#endif /* STM_ARM_NEON_MODELS */
+
+static void dump_neon_cumulative_sat(const char* msg, const char *name,
+				     const char* t1, int w, int n)
+{
+  fprintf(ref_file, "%s:%d:%s Neon cumulative saturation %d\n", msg, result_idx++,
+	  name, Neon_Cumulative_Sat);
+  fprintf(gcc_tests_file,
+	  "int VECT_VAR(expected_cumulative_sat,%s,%d,%d) = %d;\n",
+	  t1, w, n, Neon_Cumulative_Sat);
+}
+
+/* Clean output buffers before execution */
+static void clean_results (void)
+{
+  result_idx = 0;
+  CLEAN(result, int, 8, 8);
+  CLEAN(result, int, 16, 4);
+  CLEAN(result, int, 32, 2);
+  CLEAN(result, int, 64, 1);
+  CLEAN(result, uint, 8, 8);
+  CLEAN(result, uint, 16, 4);
+  CLEAN(result, uint, 32, 2);
+  CLEAN(result, uint, 64, 1);
+  CLEAN(result, poly, 8, 8);
+  CLEAN(result, poly, 16, 4);
+  CLEAN(result, float, 32, 2);
+
+  CLEAN(result, int, 8, 16);
+  CLEAN(result, int, 16, 8);
+  CLEAN(result, int, 32, 4);
+  CLEAN(result, int, 64, 2);
+  CLEAN(result, uint, 8, 16);
+  CLEAN(result, uint, 16, 8);
+  CLEAN(result, uint, 32, 4);
+  CLEAN(result, uint, 64, 2);
+  CLEAN(result, poly, 8, 16);
+  CLEAN(result, poly, 16, 8);
+  CLEAN(result, float, 32, 4);
+}
+
+
+/* Helpers to declare variables of various types  */
+#define DECL_VARIABLE(VAR, T1, W, N)		\
+  VECT_TYPE(T1, W, N) VECT_VAR(VAR, T1, W, N)
+
+#define DECL_VARIABLE_64BITS_SIGNED_VARIANTS(VAR)	\
+  DECL_VARIABLE(VAR, int, 8, 8);			\
+  DECL_VARIABLE(VAR, int, 16, 4);			\
+  DECL_VARIABLE(VAR, int, 32, 2);			\
+  DECL_VARIABLE(VAR, int, 64, 1)
+
+#define DECL_VARIABLE_64BITS_UNSIGNED_VARIANTS(VAR)	\
+  DECL_VARIABLE(VAR, uint, 8, 8);			\
+  DECL_VARIABLE(VAR, uint, 16, 4);			\
+  DECL_VARIABLE(VAR, uint, 32, 2);			\
+  DECL_VARIABLE(VAR, uint, 64, 1)
+
+#define DECL_VARIABLE_128BITS_SIGNED_VARIANTS(VAR)	\
+  DECL_VARIABLE(VAR, int, 8, 16);			\
+  DECL_VARIABLE(VAR, int, 16, 8);			\
+  DECL_VARIABLE(VAR, int, 32, 4);			\
+  DECL_VARIABLE(VAR, int, 64, 2)
+
+#define DECL_VARIABLE_128BITS_UNSIGNED_VARIANTS(VAR)	\
+  DECL_VARIABLE(VAR, uint, 8, 16);			\
+  DECL_VARIABLE(VAR, uint, 16, 8);			\
+  DECL_VARIABLE(VAR, uint, 32, 4);			\
+  DECL_VARIABLE(VAR, uint, 64, 2)
+
+#define DECL_VARIABLE_64BITS_VARIANTS(VAR)	\
+  DECL_VARIABLE_64BITS_SIGNED_VARIANTS(VAR);	\
+  DECL_VARIABLE_64BITS_UNSIGNED_VARIANTS(VAR);	\
+  DECL_VARIABLE(VAR, poly, 8, 8);		\
+  DECL_VARIABLE(VAR, poly, 16, 4);		\
+  DECL_VARIABLE(VAR, float, 32, 2)
+
+#define DECL_VARIABLE_128BITS_VARIANTS(VAR)	\
+  DECL_VARIABLE_128BITS_SIGNED_VARIANTS(VAR);	\
+  DECL_VARIABLE_128BITS_UNSIGNED_VARIANTS(VAR);	\
+  DECL_VARIABLE(VAR, poly, 8, 16);		\
+  DECL_VARIABLE(VAR, poly, 16, 8);		\
+  DECL_VARIABLE(VAR, float, 32, 4)
+
+#define DECL_VARIABLE_ALL_VARIANTS(VAR)		\
+  DECL_VARIABLE_64BITS_VARIANTS(VAR);		\
+  DECL_VARIABLE_128BITS_VARIANTS(VAR)
+
+#define DECL_VARIABLE_SIGNED_VARIANTS(VAR)	\
+  DECL_VARIABLE_64BITS_SIGNED_VARIANTS(VAR);	\
+  DECL_VARIABLE_128BITS_SIGNED_VARIANTS(VAR)
+
+#define DECL_VARIABLE_UNSIGNED_VARIANTS(VAR)	\
+  DECL_VARIABLE_64BITS_UNSIGNED_VARIANTS(VAR);	\
+  DECL_VARIABLE_128BITS_UNSIGNED_VARIANTS(VAR)
+
+/* Helpers to initialize vectors */
+#define VDUP(VAR, Q, T1, T2, W, N, V)		\
+  VECT_VAR(VAR, T1, W, N) = vdup##Q##_n_##T2##W(V)
+
+#define TEST_VSET_LANE(VAR, Q, T1, T2, W, N, L, V)			\
+  VECT_VAR(VAR, T1, W, N) = vset##Q##_lane_##T2##W(V,			\
+						   VECT_VAR(VAR, T1, W, N), \
+						   L)
+
+/* We need to load initial values first, so rely on VLD1 */
+#define VLOAD(VAR, BUF, Q, T1, T2, W, N)				\
+  VECT_VAR(VAR, T1, W, N) = vld1##Q##_##T2##W(VECT_VAR(BUF, T1, W, N))
+
+/* Helpers for macros with 1 constant and 5 variable arguments */
+#define TEST_MACRO_64BITS_SIGNED_VARIANTS_1_5(MACRO, VAR)	\
+  MACRO(VAR, , int, s, 8, 8);					\
+  MACRO(VAR, , int, s, 16, 4);					\
+  MACRO(VAR, , int, s, 32, 2);					\
+  MACRO(VAR, , int, s, 64, 1)
+
+#define TEST_MACRO_64BITS_UNSIGNED_VARIANTS_1_5(MACRO, VAR)	\
+  MACRO(VAR, , uint, u, 8, 8);					\
+  MACRO(VAR, , uint, u, 16, 4);					\
+  MACRO(VAR, , uint, u, 32, 2);					\
+  MACRO(VAR, , uint, u, 64, 1)
+
+#define TEST_MACRO_128BITS_SIGNED_VARIANTS_1_5(MACRO, VAR)	\
+  MACRO(VAR, q, int, s, 8, 16);					\
+  MACRO(VAR, q, int, s, 16, 8);					\
+  MACRO(VAR, q, int, s, 32, 4);					\
+  MACRO(VAR, q, int, s, 64, 2)
+
+#define TEST_MACRO_128BITS_UNSIGNED_VARIANTS_1_5(MACRO,VAR)	\
+  MACRO(VAR, q, uint, u, 8, 16);				\
+  MACRO(VAR, q, uint, u, 16, 8);				\
+  MACRO(VAR, q, uint, u, 32, 4);				\
+  MACRO(VAR, q, uint, u, 64, 2)
+
+#define TEST_MACRO_64BITS_VARIANTS_1_5(MACRO, VAR)	\
+  TEST_MACRO_64BITS_SIGNED_VARIANTS_1_5(MACRO, VAR);	\
+  TEST_MACRO_64BITS_UNSIGNED_VARIANTS_1_5(MACRO, VAR)
+
+#define TEST_MACRO_128BITS_VARIANTS_1_5(MACRO, VAR)	\
+  TEST_MACRO_128BITS_SIGNED_VARIANTS_1_5(MACRO, VAR);	\
+  TEST_MACRO_128BITS_UNSIGNED_VARIANTS_1_5(MACRO, VAR)
+
+#define TEST_MACRO_ALL_VARIANTS_1_5(MACRO, VAR)	\
+  TEST_MACRO_64BITS_VARIANTS_1_5(MACRO, VAR);	\
+  TEST_MACRO_128BITS_VARIANTS_1_5(MACRO, VAR)
+
+#define TEST_MACRO_SIGNED_VARIANTS_1_5(MACRO, VAR)	\
+  TEST_MACRO_64BITS_SIGNED_VARIANTS_1_5(MACRO, VAR);	\
+  TEST_MACRO_128BITS_SIGNED_VARIANTS_1_5(MACRO, VAR)
+
+/* Helpers for macros with 2 constant and 5 variable arguments */
+#define TEST_MACRO_64BITS_SIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2)	\
+  MACRO(VAR1, VAR2, , int, s, 8, 8);					\
+  MACRO(VAR1, VAR2, , int, s, 16, 4);					\
+  MACRO(VAR1, VAR2, , int, s, 32, 2);					\
+  MACRO(VAR1, VAR2 , , int, s, 64, 1)
+
+#define TEST_MACRO_64BITS_UNSIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2)	\
+  MACRO(VAR1, VAR2, , uint, u, 8, 8);					\
+  MACRO(VAR1, VAR2, , uint, u, 16, 4);					\
+  MACRO(VAR1, VAR2, , uint, u, 32, 2);					\
+  MACRO(VAR1, VAR2, , uint, u, 64, 1)
+
+#define TEST_MACRO_128BITS_SIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2)	\
+  MACRO(VAR1, VAR2, q, int, s, 8, 16);					\
+  MACRO(VAR1, VAR2, q, int, s, 16, 8);					\
+  MACRO(VAR1, VAR2, q, int, s, 32, 4);					\
+  MACRO(VAR1, VAR2, q, int, s, 64, 2)
+
+#define TEST_MACRO_128BITS_UNSIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2)	\
+  MACRO(VAR1, VAR2, q, uint, u, 8, 16);					\
+  MACRO(VAR1, VAR2, q, uint, u, 16, 8);					\
+  MACRO(VAR1, VAR2, q, uint, u, 32, 4);					\
+  MACRO(VAR1, VAR2, q, uint, u, 64, 2)
+
+#define TEST_MACRO_64BITS_VARIANTS_2_5(MACRO, VAR1, VAR2)	\
+  TEST_MACRO_64BITS_SIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2);	\
+  TEST_MACRO_64BITS_UNSIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2);	\
+  MACRO(VAR1, VAR2, , poly, p, 8, 8);				\
+  MACRO(VAR1, VAR2, , poly, p, 16, 4)
+
+#define TEST_MACRO_128BITS_VARIANTS_2_5(MACRO, VAR1, VAR2)	\
+  TEST_MACRO_128BITS_SIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2);	\
+  TEST_MACRO_128BITS_UNSIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2);	\
+  MACRO(VAR1, VAR2, q, poly, p, 8, 16);				\
+  MACRO(VAR1, VAR2, q, poly, p, 16, 8)
+
+#define TEST_MACRO_ALL_VARIANTS_2_5(MACRO, VAR1, VAR2)	\
+  TEST_MACRO_64BITS_VARIANTS_2_5(MACRO, VAR1, VAR2);	\
+  TEST_MACRO_128BITS_VARIANTS_2_5(MACRO, VAR1, VAR2)
+
+#define TEST_MACRO_SIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2)	\
+  TEST_MACRO_64BITS_SIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2);	\
+  TEST_MACRO_128BITS_SIGNED_VARIANTS_2_5(MACRO, VAR1, VAR2)
+
+#endif /* _STM_ARM_NEON_REF_H_ */