diff options
Diffstat (limited to 'gcc-4.9/gcc/config/arm')
-rw-r--r-- | gcc-4.9/gcc/config/arm/aout.h | 9 | ||||
-rw-r--r-- | gcc-4.9/gcc/config/arm/arm-cores.def | 9 | ||||
-rw-r--r-- | gcc-4.9/gcc/config/arm/arm-opts.h | 9 | ||||
-rw-r--r-- | gcc-4.9/gcc/config/arm/arm.c | 13 | ||||
-rw-r--r-- | gcc-4.9/gcc/config/arm/arm.h | 9 | ||||
-rw-r--r-- | gcc-4.9/gcc/config/arm/arm.md | 13 | ||||
-rw-r--r-- | gcc-4.9/gcc/config/arm/arm_neon.h | 608 | ||||
-rw-r--r-- | gcc-4.9/gcc/config/arm/bpabi.h | 9 | ||||
-rw-r--r-- | gcc-4.9/gcc/config/arm/elf.h | 9 | ||||
-rw-r--r-- | gcc-4.9/gcc/config/arm/linux-eabi.h | 5 | ||||
-rw-r--r-- | gcc-4.9/gcc/config/arm/linux-elf.h | 11 | ||||
-rw-r--r-- | gcc-4.9/gcc/config/arm/linux-gas.h | 9 | ||||
-rw-r--r-- | gcc-4.9/gcc/config/arm/linux-grte.h | 27 | ||||
-rw-r--r-- | gcc-4.9/gcc/config/arm/neon-docgen.ml | 424 | ||||
-rw-r--r-- | gcc-4.9/gcc/config/arm/neon-gen.ml | 520 | ||||
-rw-r--r-- | gcc-4.9/gcc/config/arm/netbsd-elf.h | 9 | ||||
-rw-r--r-- | gcc-4.9/gcc/config/arm/uclinux-eabi.h | 9 | ||||
-rw-r--r-- | gcc-4.9/gcc/config/arm/uclinux-elf.h | 9 | ||||
-rw-r--r-- | gcc-4.9/gcc/config/arm/unspecs.md | 9 | ||||
-rw-r--r-- | gcc-4.9/gcc/config/arm/vxworks.h | 9 |
20 files changed, 638 insertions, 1091 deletions
diff --git a/gcc-4.9/gcc/config/arm/aout.h b/gcc-4.9/gcc/config/arm/aout.h index 51d32a9d4..c8f4e45c6 100644 --- a/gcc-4.9/gcc/config/arm/aout.h +++ b/gcc-4.9/gcc/config/arm/aout.h @@ -14,8 +14,13 @@ or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. - You should have received a copy of the GNU General Public License - along with GCC; see the file COPYING3. If not see + Under Section 7 of GPL version 3, you are granted additional + permissions described in the GCC Runtime Library Exception, version + 3.1, as published by the Free Software Foundation. + + You should have received a copy of the GNU General Public License and + a copy of the GCC Runtime Library Exception along with this program; + see the files COPYING3 and COPYING.RUNTIME respectively. If not, see <http://www.gnu.org/licenses/>. */ #ifndef ASM_APP_ON diff --git a/gcc-4.9/gcc/config/arm/arm-cores.def b/gcc-4.9/gcc/config/arm/arm-cores.def index 42f00b463..56041ec8b 100644 --- a/gcc-4.9/gcc/config/arm/arm-cores.def +++ b/gcc-4.9/gcc/config/arm/arm-cores.def @@ -14,8 +14,13 @@ MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. - You should have received a copy of the GNU General Public License - along with GCC; see the file COPYING3. If not see + Under Section 7 of GPL version 3, you are granted additional + permissions described in the GCC Runtime Library Exception, version + 3.1, as published by the Free Software Foundation. + + You should have received a copy of the GNU General Public License and + a copy of the GCC Runtime Library Exception along with this program; + see the files COPYING3 and COPYING.RUNTIME respectively. If not, see <http://www.gnu.org/licenses/>. */ /* Before using #include to read this file, define a macro: diff --git a/gcc-4.9/gcc/config/arm/arm-opts.h b/gcc-4.9/gcc/config/arm/arm-opts.h index a8393975a..21902940e 100644 --- a/gcc-4.9/gcc/config/arm/arm-opts.h +++ b/gcc-4.9/gcc/config/arm/arm-opts.h @@ -13,8 +13,13 @@ or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. - You should have received a copy of the GNU General Public License - along with GCC; see the file COPYING3. If not see + Under Section 7 of GPL version 3, you are granted additional + permissions described in the GCC Runtime Library Exception, version + 3.1, as published by the Free Software Foundation. + + You should have received a copy of the GNU General Public License and + a copy of the GCC Runtime Library Exception along with this program; + see the files COPYING3 and COPYING.RUNTIME respectively. If not, see <http://www.gnu.org/licenses/>. */ #ifndef ARM_OPTS_H diff --git a/gcc-4.9/gcc/config/arm/arm.c b/gcc-4.9/gcc/config/arm/arm.c index 83763555c..3c237cb6d 100644 --- a/gcc-4.9/gcc/config/arm/arm.c +++ b/gcc-4.9/gcc/config/arm/arm.c @@ -16739,11 +16739,12 @@ thumb1_reorg (void) rtx prev, insn = BB_END (bb); bool insn_clobbered = false; - while (insn != BB_HEAD (bb) && DEBUG_INSN_P (insn)) + while (insn != BB_HEAD (bb) && !NONDEBUG_INSN_P (insn)) insn = PREV_INSN (insn); /* Find the last cbranchsi4_insn in basic block BB. */ - if (INSN_CODE (insn) != CODE_FOR_cbranchsi4_insn) + if (insn == BB_HEAD (bb) + || INSN_CODE (insn) != CODE_FOR_cbranchsi4_insn) continue; /* Get the register with which we are comparing. */ @@ -28210,9 +28211,13 @@ arm_output_mi_thunk (FILE *file, tree thunk ATTRIBUTE_UNUSED, fputs (":\n", file); if (flag_pic) { - /* Output ".word .LTHUNKn-7-.LTHUNKPCn". */ + /* Output ".word .LTHUNKn-[3,7]-.LTHUNKPCn". */ rtx tem = XEXP (DECL_RTL (function), 0); - tem = plus_constant (GET_MODE (tem), tem, -7); + /* For TARGET_THUMB1_ONLY the thunk is in Thumb mode, so the PC + pipeline offset is four rather than eight. Adjust the offset + accordingly. */ + tem = plus_constant (GET_MODE (tem), tem, + TARGET_THUMB1_ONLY ? -3 : -7); tem = gen_rtx_MINUS (GET_MODE (tem), tem, gen_rtx_SYMBOL_REF (Pmode, diff --git a/gcc-4.9/gcc/config/arm/arm.h b/gcc-4.9/gcc/config/arm/arm.h index 4d9121436..ab5167a8b 100644 --- a/gcc-4.9/gcc/config/arm/arm.h +++ b/gcc-4.9/gcc/config/arm/arm.h @@ -17,8 +17,13 @@ or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. - You should have received a copy of the GNU General Public License - along with GCC; see the file COPYING3. If not see + Under Section 7 of GPL version 3, you are granted additional + permissions described in the GCC Runtime Library Exception, version + 3.1, as published by the Free Software Foundation. + + You should have received a copy of the GNU General Public License and + a copy of the GCC Runtime Library Exception along with this program; + see the files COPYING3 and COPYING.RUNTIME respectively. If not, see <http://www.gnu.org/licenses/>. */ #ifndef GCC_ARM_H diff --git a/gcc-4.9/gcc/config/arm/arm.md b/gcc-4.9/gcc/config/arm/arm.md index 662465f2a..467f9ce4e 100644 --- a/gcc-4.9/gcc/config/arm/arm.md +++ b/gcc-4.9/gcc/config/arm/arm.md @@ -75,6 +75,8 @@ ] ) +;; UNSPEC_VOLATILE Usage: + ;;--------------------------------------------------------------------------- ;; Attributes @@ -8349,8 +8351,8 @@ (define_insn_and_split "*arm_cmpdi_unsigned" [(set (reg:CC_CZ CC_REGNUM) - (compare:CC_CZ (match_operand:DI 0 "s_register_operand" "l,r,r") - (match_operand:DI 1 "arm_di_operand" "Py,r,rDi")))] + (compare:CC_CZ (match_operand:DI 0 "s_register_operand" "l,r,r,r") + (match_operand:DI 1 "arm_di_operand" "Py,r,Di,rDi")))] "TARGET_32BIT" "#" ; "cmp\\t%R0, %R1\;it eq\;cmpeq\\t%Q0, %Q1" @@ -8370,9 +8372,9 @@ operands[1] = gen_lowpart (SImode, operands[1]); } [(set_attr "conds" "set") - (set_attr "enabled_for_depr_it" "yes,yes,no") - (set_attr "arch" "t2,t2,*") - (set_attr "length" "6,6,8") + (set_attr "enabled_for_depr_it" "yes,yes,no,*") + (set_attr "arch" "t2,t2,t2,a") + (set_attr "length" "6,6,10,8") (set_attr "type" "multiple")] ) @@ -9860,6 +9862,7 @@ "TARGET_32BIT" "%i1%?\\t%0, %2, %4%S3" [(set_attr "predicable" "yes") + (set_attr "predicable_short_it" "no") (set_attr "shift" "4") (set_attr "arch" "a,t2,t2,a") ;; Thumb2 doesn't allow the stack pointer to be used for diff --git a/gcc-4.9/gcc/config/arm/arm_neon.h b/gcc-4.9/gcc/config/arm/arm_neon.h index 37a6e611b..95735433d 100644 --- a/gcc-4.9/gcc/config/arm/arm_neon.h +++ b/gcc-4.9/gcc/config/arm/arm_neon.h @@ -1,5 +1,4 @@ -/* ARM NEON intrinsics include file. This file is generated automatically - using neon-gen.ml. Please do not edit manually. +/* ARM NEON intrinsics include file. Copyright (C) 2006-2014 Free Software Foundation, Inc. Contributed by CodeSourcery. @@ -7707,12 +7706,32 @@ vbslq_p16 (uint16x8_t __a, poly16x8_t __b, poly16x8_t __c) return (poly16x8_t)__builtin_neon_vbslv8hi ((int16x8_t) __a, (int16x8_t) __b, (int16x8_t) __c); } +/* For big-endian, the shuffle masks for ZIP, UZP and TRN must be changed as + follows. (nelt = the number of elements within a vector.) + + Firstly, a value of N within a mask, becomes (N ^ (nelt - 1)), as gcc vector + extension's indexing scheme is reversed *within each vector* (relative to the + neon intrinsics view), but without changing which of the two vectors. + + Secondly, the elements within each mask are reversed, as the mask is itself a + vector, and will itself be loaded in reverse order (again, relative to the + neon intrinsics view, i.e. that would result from a "vld1" instruction). */ + __extension__ static __inline int8x8x2_t __attribute__ ((__always_inline__)) vtrn_s8 (int8x8_t __a, int8x8_t __b) { int8x8x2_t __rv; - __rv.val[0] = (int8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 8, 2, 10, 4, 12, 6, 14 }); - __rv.val[1] = (int8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 1, 9, 3, 11, 5, 13, 7, 15 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 9, 1, 11, 3, 13, 5, 15, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 8, 0, 10, 2, 12, 4, 14, 6 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 0, 8, 2, 10, 4, 12, 6, 14 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 1, 9, 3, 11, 5, 13, 7, 15 }); +#endif return __rv; } @@ -7720,8 +7739,13 @@ __extension__ static __inline int16x4x2_t __attribute__ ((__always_inline__)) vtrn_s16 (int16x4_t __a, int16x4_t __b) { int16x4x2_t __rv; - __rv.val[0] = (int16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 2, 6 }); - __rv.val[1] = (int16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 5, 3, 7 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 5, 1, 7, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 0, 6, 2 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 2, 6 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 5, 3, 7 }); +#endif return __rv; } @@ -7729,8 +7753,17 @@ __extension__ static __inline uint8x8x2_t __attribute__ ((__always_inline__)) vtrn_u8 (uint8x8_t __a, uint8x8_t __b) { uint8x8x2_t __rv; - __rv.val[0] = (uint8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 8, 2, 10, 4, 12, 6, 14 }); - __rv.val[1] = (uint8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 1, 9, 3, 11, 5, 13, 7, 15 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 9, 1, 11, 3, 13, 5, 15, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 8, 0, 10, 2, 12, 4, 14, 6 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 0, 8, 2, 10, 4, 12, 6, 14 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 1, 9, 3, 11, 5, 13, 7, 15 }); +#endif return __rv; } @@ -7738,8 +7771,13 @@ __extension__ static __inline uint16x4x2_t __attribute__ ((__always_inline__)) vtrn_u16 (uint16x4_t __a, uint16x4_t __b) { uint16x4x2_t __rv; - __rv.val[0] = (uint16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 2, 6 }); - __rv.val[1] = (uint16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 5, 3, 7 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 5, 1, 7, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 0, 6, 2 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 2, 6 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 5, 3, 7 }); +#endif return __rv; } @@ -7747,8 +7785,17 @@ __extension__ static __inline poly8x8x2_t __attribute__ ((__always_inline__)) vtrn_p8 (poly8x8_t __a, poly8x8_t __b) { poly8x8x2_t __rv; - __rv.val[0] = (poly8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 8, 2, 10, 4, 12, 6, 14 }); - __rv.val[1] = (poly8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 1, 9, 3, 11, 5, 13, 7, 15 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 9, 1, 11, 3, 13, 5, 15, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 8, 0, 10, 2, 12, 4, 14, 6 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 0, 8, 2, 10, 4, 12, 6, 14 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 1, 9, 3, 11, 5, 13, 7, 15 }); +#endif return __rv; } @@ -7756,8 +7803,13 @@ __extension__ static __inline poly16x4x2_t __attribute__ ((__always_inline__)) vtrn_p16 (poly16x4_t __a, poly16x4_t __b) { poly16x4x2_t __rv; - __rv.val[0] = (poly16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 2, 6 }); - __rv.val[1] = (poly16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 5, 3, 7 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 5, 1, 7, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 0, 6, 2 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 2, 6 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 5, 3, 7 }); +#endif return __rv; } @@ -7765,8 +7817,13 @@ __extension__ static __inline int32x2x2_t __attribute__ ((__always_inline__)) vtrn_s32 (int32x2_t __a, int32x2_t __b) { int32x2x2_t __rv; - __rv.val[0] = (int32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); - __rv.val[1] = (int32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#endif return __rv; } @@ -7774,8 +7831,13 @@ __extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__)) vtrn_f32 (float32x2_t __a, float32x2_t __b) { float32x2x2_t __rv; - __rv.val[0] = (float32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); - __rv.val[1] = (float32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#endif return __rv; } @@ -7783,8 +7845,13 @@ __extension__ static __inline uint32x2x2_t __attribute__ ((__always_inline__)) vtrn_u32 (uint32x2_t __a, uint32x2_t __b) { uint32x2x2_t __rv; - __rv.val[0] = (uint32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); - __rv.val[1] = (uint32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#endif return __rv; } @@ -7792,8 +7859,17 @@ __extension__ static __inline int8x16x2_t __attribute__ ((__always_inline__)) vtrnq_s8 (int8x16_t __a, int8x16_t __b) { int8x16x2_t __rv; - __rv.val[0] = (int8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 0, 16, 2, 18, 4, 20, 6, 22, 8, 24, 10, 26, 12, 28, 14, 30 }); - __rv.val[1] = (int8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 17, 1, 19, 3, 21, 5, 23, 7, 25, 9, 27, 11, 29, 13, 31, 15 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 16, 0, 18, 2, 20, 4, 22, 6, 24, 8, 26, 10, 28, 12, 30, 14 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 0, 16, 2, 18, 4, 20, 6, 22, 8, 24, 10, 26, 12, 28, 14, 30 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31 }); +#endif return __rv; } @@ -7801,8 +7877,17 @@ __extension__ static __inline int16x8x2_t __attribute__ ((__always_inline__)) vtrnq_s16 (int16x8_t __a, int16x8_t __b) { int16x8x2_t __rv; - __rv.val[0] = (int16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 8, 2, 10, 4, 12, 6, 14 }); - __rv.val[1] = (int16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 1, 9, 3, 11, 5, 13, 7, 15 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 9, 1, 11, 3, 13, 5, 15, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 8, 0, 10, 2, 12, 4, 14, 6 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 0, 8, 2, 10, 4, 12, 6, 14 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 1, 9, 3, 11, 5, 13, 7, 15 }); +#endif return __rv; } @@ -7810,8 +7895,13 @@ __extension__ static __inline int32x4x2_t __attribute__ ((__always_inline__)) vtrnq_s32 (int32x4_t __a, int32x4_t __b) { int32x4x2_t __rv; - __rv.val[0] = (int32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 2, 6 }); - __rv.val[1] = (int32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 5, 3, 7 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 5, 1, 7, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 0, 6, 2 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 2, 6 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 5, 3, 7 }); +#endif return __rv; } @@ -7819,8 +7909,13 @@ __extension__ static __inline float32x4x2_t __attribute__ ((__always_inline__)) vtrnq_f32 (float32x4_t __a, float32x4_t __b) { float32x4x2_t __rv; - __rv.val[0] = (float32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 2, 6 }); - __rv.val[1] = (float32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 5, 3, 7 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 5, 1, 7, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 0, 6, 2 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 2, 6 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 5, 3, 7 }); +#endif return __rv; } @@ -7828,8 +7923,17 @@ __extension__ static __inline uint8x16x2_t __attribute__ ((__always_inline__)) vtrnq_u8 (uint8x16_t __a, uint8x16_t __b) { uint8x16x2_t __rv; - __rv.val[0] = (uint8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 0, 16, 2, 18, 4, 20, 6, 22, 8, 24, 10, 26, 12, 28, 14, 30 }); - __rv.val[1] = (uint8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 17, 1, 19, 3, 21, 5, 23, 7, 25, 9, 27, 11, 29, 13, 31, 15 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 16, 0, 18, 2, 20, 4, 22, 6, 24, 8, 26, 10, 28, 12, 30, 14 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 0, 16, 2, 18, 4, 20, 6, 22, 8, 24, 10, 26, 12, 28, 14, 30 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31 }); +#endif return __rv; } @@ -7837,8 +7941,17 @@ __extension__ static __inline uint16x8x2_t __attribute__ ((__always_inline__)) vtrnq_u16 (uint16x8_t __a, uint16x8_t __b) { uint16x8x2_t __rv; - __rv.val[0] = (uint16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 8, 2, 10, 4, 12, 6, 14 }); - __rv.val[1] = (uint16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 1, 9, 3, 11, 5, 13, 7, 15 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 9, 1, 11, 3, 13, 5, 15, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 8, 0, 10, 2, 12, 4, 14, 6 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 0, 8, 2, 10, 4, 12, 6, 14 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 1, 9, 3, 11, 5, 13, 7, 15 }); +#endif return __rv; } @@ -7846,8 +7959,13 @@ __extension__ static __inline uint32x4x2_t __attribute__ ((__always_inline__)) vtrnq_u32 (uint32x4_t __a, uint32x4_t __b) { uint32x4x2_t __rv; - __rv.val[0] = (uint32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 2, 6 }); - __rv.val[1] = (uint32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 5, 3, 7 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 5, 1, 7, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 0, 6, 2 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 2, 6 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 5, 3, 7 }); +#endif return __rv; } @@ -7855,8 +7973,17 @@ __extension__ static __inline poly8x16x2_t __attribute__ ((__always_inline__)) vtrnq_p8 (poly8x16_t __a, poly8x16_t __b) { poly8x16x2_t __rv; - __rv.val[0] = (poly8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 0, 16, 2, 18, 4, 20, 6, 22, 8, 24, 10, 26, 12, 28, 14, 30 }); - __rv.val[1] = (poly8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 17, 1, 19, 3, 21, 5, 23, 7, 25, 9, 27, 11, 29, 13, 31, 15 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 16, 0, 18, 2, 20, 4, 22, 6, 24, 8, 26, 10, 28, 12, 30, 14 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 0, 16, 2, 18, 4, 20, 6, 22, 8, 24, 10, 26, 12, 28, 14, 30 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 1, 17, 3, 19, 5, 21, 7, 23, 9, 25, 11, 27, 13, 29, 15, 31 }); +#endif return __rv; } @@ -7864,8 +7991,17 @@ __extension__ static __inline poly16x8x2_t __attribute__ ((__always_inline__)) vtrnq_p16 (poly16x8_t __a, poly16x8_t __b) { poly16x8x2_t __rv; - __rv.val[0] = (poly16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 8, 2, 10, 4, 12, 6, 14 }); - __rv.val[1] = (poly16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 1, 9, 3, 11, 5, 13, 7, 15 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 9, 1, 11, 3, 13, 5, 15, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 8, 0, 10, 2, 12, 4, 14, 6 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 0, 8, 2, 10, 4, 12, 6, 14 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 1, 9, 3, 11, 5, 13, 7, 15 }); +#endif return __rv; } @@ -7873,8 +8009,17 @@ __extension__ static __inline int8x8x2_t __attribute__ ((__always_inline__)) vzip_s8 (int8x8_t __a, int8x8_t __b) { int8x8x2_t __rv; - __rv.val[0] = (int8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 8, 1, 9, 2, 10, 3, 11 }); - __rv.val[1] = (int8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 4, 12, 5, 13, 6, 14, 7, 15 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 12, 4, 13, 5, 14, 6, 15, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 8, 0, 9, 1, 10, 2, 11, 3 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 0, 8, 1, 9, 2, 10, 3, 11 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 4, 12, 5, 13, 6, 14, 7, 15 }); +#endif return __rv; } @@ -7882,8 +8027,13 @@ __extension__ static __inline int16x4x2_t __attribute__ ((__always_inline__)) vzip_s16 (int16x4_t __a, int16x4_t __b) { int16x4x2_t __rv; - __rv.val[0] = (int16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 1, 5 }); - __rv.val[1] = (int16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 2, 6, 3, 7 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 6, 2, 7, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 0, 5, 1 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 1, 5 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 2, 6, 3, 7 }); +#endif return __rv; } @@ -7891,8 +8041,17 @@ __extension__ static __inline uint8x8x2_t __attribute__ ((__always_inline__)) vzip_u8 (uint8x8_t __a, uint8x8_t __b) { uint8x8x2_t __rv; - __rv.val[0] = (uint8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 8, 1, 9, 2, 10, 3, 11 }); - __rv.val[1] = (uint8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 4, 12, 5, 13, 6, 14, 7, 15 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 12, 4, 13, 5, 14, 6, 15, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 8, 0, 9, 1, 10, 2, 11, 3 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 0, 8, 1, 9, 2, 10, 3, 11 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 4, 12, 5, 13, 6, 14, 7, 15 }); +#endif return __rv; } @@ -7900,8 +8059,13 @@ __extension__ static __inline uint16x4x2_t __attribute__ ((__always_inline__)) vzip_u16 (uint16x4_t __a, uint16x4_t __b) { uint16x4x2_t __rv; - __rv.val[0] = (uint16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 1, 5 }); - __rv.val[1] = (uint16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 2, 6, 3, 7 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 6, 2, 7, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 0, 5, 1 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 1, 5 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 2, 6, 3, 7 }); +#endif return __rv; } @@ -7909,8 +8073,17 @@ __extension__ static __inline poly8x8x2_t __attribute__ ((__always_inline__)) vzip_p8 (poly8x8_t __a, poly8x8_t __b) { poly8x8x2_t __rv; - __rv.val[0] = (poly8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 8, 1, 9, 2, 10, 3, 11 }); - __rv.val[1] = (poly8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 4, 12, 5, 13, 6, 14, 7, 15 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 12, 4, 13, 5, 14, 6, 15, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 8, 0, 9, 1, 10, 2, 11, 3 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 0, 8, 1, 9, 2, 10, 3, 11 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 4, 12, 5, 13, 6, 14, 7, 15 }); +#endif return __rv; } @@ -7918,8 +8091,13 @@ __extension__ static __inline poly16x4x2_t __attribute__ ((__always_inline__)) vzip_p16 (poly16x4_t __a, poly16x4_t __b) { poly16x4x2_t __rv; - __rv.val[0] = (poly16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 1, 5 }); - __rv.val[1] = (poly16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 2, 6, 3, 7 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 6, 2, 7, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 0, 5, 1 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 4, 1, 5 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 2, 6, 3, 7 }); +#endif return __rv; } @@ -7927,8 +8105,13 @@ __extension__ static __inline int32x2x2_t __attribute__ ((__always_inline__)) vzip_s32 (int32x2_t __a, int32x2_t __b) { int32x2x2_t __rv; - __rv.val[0] = (int32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); - __rv.val[1] = (int32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#endif return __rv; } @@ -7936,8 +8119,13 @@ __extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__)) vzip_f32 (float32x2_t __a, float32x2_t __b) { float32x2x2_t __rv; - __rv.val[0] = (float32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); - __rv.val[1] = (float32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#endif return __rv; } @@ -7945,8 +8133,13 @@ __extension__ static __inline uint32x2x2_t __attribute__ ((__always_inline__)) vzip_u32 (uint32x2_t __a, uint32x2_t __b) { uint32x2x2_t __rv; - __rv.val[0] = (uint32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); - __rv.val[1] = (uint32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#endif return __rv; } @@ -7954,8 +8147,17 @@ __extension__ static __inline int8x16x2_t __attribute__ ((__always_inline__)) vzipq_s8 (int8x16_t __a, int8x16_t __b) { int8x16x2_t __rv; - __rv.val[0] = (int8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23 }); - __rv.val[1] = (int8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 24, 8, 25, 9, 26, 10, 27, 11, 28, 12, 29, 13, 30, 14, 31, 15 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 16, 0, 17, 1, 18, 2, 19, 3, 20, 4, 21, 5, 22, 6, 23, 7 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31 }); +#endif return __rv; } @@ -7963,8 +8165,17 @@ __extension__ static __inline int16x8x2_t __attribute__ ((__always_inline__)) vzipq_s16 (int16x8_t __a, int16x8_t __b) { int16x8x2_t __rv; - __rv.val[0] = (int16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 8, 1, 9, 2, 10, 3, 11 }); - __rv.val[1] = (int16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 4, 12, 5, 13, 6, 14, 7, 15 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 12, 4, 13, 5, 14, 6, 15, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 8, 0, 9, 1, 10, 2, 11, 3 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 0, 8, 1, 9, 2, 10, 3, 11 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 4, 12, 5, 13, 6, 14, 7, 15 }); +#endif return __rv; } @@ -7972,8 +8183,13 @@ __extension__ static __inline int32x4x2_t __attribute__ ((__always_inline__)) vzipq_s32 (int32x4_t __a, int32x4_t __b) { int32x4x2_t __rv; - __rv.val[0] = (int32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 1, 5 }); - __rv.val[1] = (int32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 2, 6, 3, 7 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 6, 2, 7, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 0, 5, 1 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 1, 5 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 2, 6, 3, 7 }); +#endif return __rv; } @@ -7981,8 +8197,13 @@ __extension__ static __inline float32x4x2_t __attribute__ ((__always_inline__)) vzipq_f32 (float32x4_t __a, float32x4_t __b) { float32x4x2_t __rv; - __rv.val[0] = (float32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 1, 5 }); - __rv.val[1] = (float32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 2, 6, 3, 7 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 6, 2, 7, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 0, 5, 1 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 1, 5 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 2, 6, 3, 7 }); +#endif return __rv; } @@ -7990,8 +8211,17 @@ __extension__ static __inline uint8x16x2_t __attribute__ ((__always_inline__)) vzipq_u8 (uint8x16_t __a, uint8x16_t __b) { uint8x16x2_t __rv; - __rv.val[0] = (uint8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23 }); - __rv.val[1] = (uint8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 24, 8, 25, 9, 26, 10, 27, 11, 28, 12, 29, 13, 30, 14, 31, 15 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 16, 0, 17, 1, 18, 2, 19, 3, 20, 4, 21, 5, 22, 6, 23, 7 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31 }); +#endif return __rv; } @@ -7999,8 +8229,17 @@ __extension__ static __inline uint16x8x2_t __attribute__ ((__always_inline__)) vzipq_u16 (uint16x8_t __a, uint16x8_t __b) { uint16x8x2_t __rv; - __rv.val[0] = (uint16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 8, 1, 9, 2, 10, 3, 11 }); - __rv.val[1] = (uint16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 4, 12, 5, 13, 6, 14, 7, 15 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 12, 4, 13, 5, 14, 6, 15, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 8, 0, 9, 1, 10, 2, 11, 3 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 0, 8, 1, 9, 2, 10, 3, 11 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 4, 12, 5, 13, 6, 14, 7, 15 }); +#endif return __rv; } @@ -8008,8 +8247,13 @@ __extension__ static __inline uint32x4x2_t __attribute__ ((__always_inline__)) vzipq_u32 (uint32x4_t __a, uint32x4_t __b) { uint32x4x2_t __rv; - __rv.val[0] = (uint32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 1, 5 }); - __rv.val[1] = (uint32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 2, 6, 3, 7 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 6, 2, 7, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 0, 5, 1 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 4, 1, 5 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 2, 6, 3, 7 }); +#endif return __rv; } @@ -8017,8 +8261,17 @@ __extension__ static __inline poly8x16x2_t __attribute__ ((__always_inline__)) vzipq_p8 (poly8x16_t __a, poly8x16_t __b) { poly8x16x2_t __rv; - __rv.val[0] = (poly8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23 }); - __rv.val[1] = (poly8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 24, 8, 25, 9, 26, 10, 27, 11, 28, 12, 29, 13, 30, 14, 31, 15 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 16, 0, 17, 1, 18, 2, 19, 3, 20, 4, 21, 5, 22, 6, 23, 7 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 0, 16, 1, 17, 2, 18, 3, 19, 4, 20, 5, 21, 6, 22, 7, 23 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 8, 24, 9, 25, 10, 26, 11, 27, 12, 28, 13, 29, 14, 30, 15, 31 }); +#endif return __rv; } @@ -8026,8 +8279,17 @@ __extension__ static __inline poly16x8x2_t __attribute__ ((__always_inline__)) vzipq_p16 (poly16x8_t __a, poly16x8_t __b) { poly16x8x2_t __rv; - __rv.val[0] = (poly16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 8, 1, 9, 2, 10, 3, 11 }); - __rv.val[1] = (poly16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 4, 12, 5, 13, 6, 14, 7, 15 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 12, 4, 13, 5, 14, 6, 15, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 8, 0, 9, 1, 10, 2, 11, 3 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 0, 8, 1, 9, 2, 10, 3, 11 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 4, 12, 5, 13, 6, 14, 7, 15 }); +#endif return __rv; } @@ -8035,8 +8297,17 @@ __extension__ static __inline int8x8x2_t __attribute__ ((__always_inline__)) vuzp_s8 (int8x8_t __a, int8x8_t __b) { int8x8x2_t __rv; - __rv.val[0] = (int8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 2, 4, 6, 8, 10, 12, 14 }); - __rv.val[1] = (int8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 1, 3, 5, 7, 9, 11, 13, 15 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 9, 11, 13, 15, 1, 3, 5, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 8, 10, 12, 14, 0, 2, 4, 6 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 0, 2, 4, 6, 8, 10, 12, 14 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 1, 3, 5, 7, 9, 11, 13, 15 }); +#endif return __rv; } @@ -8044,8 +8315,13 @@ __extension__ static __inline int16x4x2_t __attribute__ ((__always_inline__)) vuzp_s16 (int16x4_t __a, int16x4_t __b) { int16x4x2_t __rv; - __rv.val[0] = (int16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 2, 4, 6 }); - __rv.val[1] = (int16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 3, 5, 7 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 5, 7, 1, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 6, 0, 2 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 2, 4, 6 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 3, 5, 7 }); +#endif return __rv; } @@ -8053,8 +8329,13 @@ __extension__ static __inline int32x2x2_t __attribute__ ((__always_inline__)) vuzp_s32 (int32x2_t __a, int32x2_t __b) { int32x2x2_t __rv; - __rv.val[0] = (int32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); - __rv.val[1] = (int32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#endif return __rv; } @@ -8062,8 +8343,13 @@ __extension__ static __inline float32x2x2_t __attribute__ ((__always_inline__)) vuzp_f32 (float32x2_t __a, float32x2_t __b) { float32x2x2_t __rv; - __rv.val[0] = (float32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); - __rv.val[1] = (float32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#endif return __rv; } @@ -8071,8 +8357,17 @@ __extension__ static __inline uint8x8x2_t __attribute__ ((__always_inline__)) vuzp_u8 (uint8x8_t __a, uint8x8_t __b) { uint8x8x2_t __rv; - __rv.val[0] = (uint8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 2, 4, 6, 8, 10, 12, 14 }); - __rv.val[1] = (uint8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 1, 3, 5, 7, 9, 11, 13, 15 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 9, 11, 13, 15, 1, 3, 5, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 8, 10, 12, 14, 0, 2, 4, 6 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 0, 2, 4, 6, 8, 10, 12, 14 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 1, 3, 5, 7, 9, 11, 13, 15 }); +#endif return __rv; } @@ -8080,8 +8375,13 @@ __extension__ static __inline uint16x4x2_t __attribute__ ((__always_inline__)) vuzp_u16 (uint16x4_t __a, uint16x4_t __b) { uint16x4x2_t __rv; - __rv.val[0] = (uint16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 2, 4, 6 }); - __rv.val[1] = (uint16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 3, 5, 7 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 5, 7, 1, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 6, 0, 2 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 2, 4, 6 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 3, 5, 7 }); +#endif return __rv; } @@ -8089,8 +8389,13 @@ __extension__ static __inline uint32x2x2_t __attribute__ ((__always_inline__)) vuzp_u32 (uint32x2_t __a, uint32x2_t __b) { uint32x2x2_t __rv; - __rv.val[0] = (uint32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); - __rv.val[1] = (uint32x2_t) __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 3, 1 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 2, 0 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x2_t) { 0, 2 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x2_t) { 1, 3 }); +#endif return __rv; } @@ -8098,8 +8403,17 @@ __extension__ static __inline poly8x8x2_t __attribute__ ((__always_inline__)) vuzp_p8 (poly8x8_t __a, poly8x8_t __b) { poly8x8x2_t __rv; - __rv.val[0] = (poly8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 0, 2, 4, 6, 8, 10, 12, 14 }); - __rv.val[1] = (poly8x8_t) __builtin_shuffle (__a, __b, (uint8x8_t) { 1, 3, 5, 7, 9, 11, 13, 15 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 9, 11, 13, 15, 1, 3, 5, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 8, 10, 12, 14, 0, 2, 4, 6 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 0, 2, 4, 6, 8, 10, 12, 14 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x8_t) + { 1, 3, 5, 7, 9, 11, 13, 15 }); +#endif return __rv; } @@ -8107,8 +8421,13 @@ __extension__ static __inline poly16x4x2_t __attribute__ ((__always_inline__)) vuzp_p16 (poly16x4_t __a, poly16x4_t __b) { poly16x4x2_t __rv; - __rv.val[0] = (poly16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 2, 4, 6 }); - __rv.val[1] = (poly16x4_t) __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 3, 5, 7 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 5, 7, 1, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 4, 6, 0, 2 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x4_t) { 0, 2, 4, 6 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x4_t) { 1, 3, 5, 7 }); +#endif return __rv; } @@ -8116,8 +8435,17 @@ __extension__ static __inline int8x16x2_t __attribute__ ((__always_inline__)) vuzpq_s8 (int8x16_t __a, int8x16_t __b) { int8x16x2_t __rv; - __rv.val[0] = (int8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30 }); - __rv.val[1] = (int8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 17, 19, 21, 23, 25, 27, 29, 31, 1, 3, 5, 7, 9, 11, 13, 15 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 16, 18, 20, 22, 24, 26, 28, 30, 0, 2, 4, 6, 8, 10, 12, 14 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31 }); +#endif return __rv; } @@ -8125,8 +8453,17 @@ __extension__ static __inline int16x8x2_t __attribute__ ((__always_inline__)) vuzpq_s16 (int16x8_t __a, int16x8_t __b) { int16x8x2_t __rv; - __rv.val[0] = (int16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 2, 4, 6, 8, 10, 12, 14 }); - __rv.val[1] = (int16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 1, 3, 5, 7, 9, 11, 13, 15 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 9, 11, 13, 15, 1, 3, 5, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 8, 10, 12, 14, 0, 2, 4, 6 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 0, 2, 4, 6, 8, 10, 12, 14 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 1, 3, 5, 7, 9, 11, 13, 15 }); +#endif return __rv; } @@ -8134,8 +8471,13 @@ __extension__ static __inline int32x4x2_t __attribute__ ((__always_inline__)) vuzpq_s32 (int32x4_t __a, int32x4_t __b) { int32x4x2_t __rv; - __rv.val[0] = (int32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 2, 4, 6 }); - __rv.val[1] = (int32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 3, 5, 7 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 5, 7, 1, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 6, 0, 2 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 2, 4, 6 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 3, 5, 7 }); +#endif return __rv; } @@ -8143,8 +8485,13 @@ __extension__ static __inline float32x4x2_t __attribute__ ((__always_inline__)) vuzpq_f32 (float32x4_t __a, float32x4_t __b) { float32x4x2_t __rv; - __rv.val[0] = (float32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 2, 4, 6 }); - __rv.val[1] = (float32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 3, 5, 7 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 5, 7, 1, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 6, 0, 2 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 2, 4, 6 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 3, 5, 7 }); +#endif return __rv; } @@ -8152,8 +8499,17 @@ __extension__ static __inline uint8x16x2_t __attribute__ ((__always_inline__)) vuzpq_u8 (uint8x16_t __a, uint8x16_t __b) { uint8x16x2_t __rv; - __rv.val[0] = (uint8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30 }); - __rv.val[1] = (uint8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 17, 19, 21, 23, 25, 27, 29, 31, 1, 3, 5, 7, 9, 11, 13, 15 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 16, 18, 20, 22, 24, 26, 28, 30, 0, 2, 4, 6, 8, 10, 12, 14 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31 }); +#endif return __rv; } @@ -8161,8 +8517,17 @@ __extension__ static __inline uint16x8x2_t __attribute__ ((__always_inline__)) vuzpq_u16 (uint16x8_t __a, uint16x8_t __b) { uint16x8x2_t __rv; - __rv.val[0] = (uint16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 2, 4, 6, 8, 10, 12, 14 }); - __rv.val[1] = (uint16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 1, 3, 5, 7, 9, 11, 13, 15 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 9, 11, 13, 15, 1, 3, 5, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 8, 10, 12, 14, 0, 2, 4, 6 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 0, 2, 4, 6, 8, 10, 12, 14 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 1, 3, 5, 7, 9, 11, 13, 15 }); +#endif return __rv; } @@ -8170,8 +8535,13 @@ __extension__ static __inline uint32x4x2_t __attribute__ ((__always_inline__)) vuzpq_u32 (uint32x4_t __a, uint32x4_t __b) { uint32x4x2_t __rv; - __rv.val[0] = (uint32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 2, 4, 6 }); - __rv.val[1] = (uint32x4_t) __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 3, 5, 7 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 5, 7, 1, 3 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 4, 6, 0, 2 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint32x4_t) { 0, 2, 4, 6 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint32x4_t) { 1, 3, 5, 7 }); +#endif return __rv; } @@ -8179,8 +8549,17 @@ __extension__ static __inline poly8x16x2_t __attribute__ ((__always_inline__)) vuzpq_p8 (poly8x16_t __a, poly8x16_t __b) { poly8x16x2_t __rv; - __rv.val[0] = (poly8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30 }); - __rv.val[1] = (poly8x16_t) __builtin_shuffle (__a, __b, (uint8x16_t) { 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 17, 19, 21, 23, 25, 27, 29, 31, 1, 3, 5, 7, 9, 11, 13, 15 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 16, 18, 20, 22, 24, 26, 28, 30, 0, 2, 4, 6, 8, 10, 12, 14 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 0, 2, 4, 6, 8, 10, 12, 14, 16, 18, 20, 22, 24, 26, 28, 30 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint8x16_t) + { 1, 3, 5, 7, 9, 11, 13, 15, 17, 19, 21, 23, 25, 27, 29, 31 }); +#endif return __rv; } @@ -8188,8 +8567,17 @@ __extension__ static __inline poly16x8x2_t __attribute__ ((__always_inline__)) vuzpq_p16 (poly16x8_t __a, poly16x8_t __b) { poly16x8x2_t __rv; - __rv.val[0] = (poly16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 0, 2, 4, 6, 8, 10, 12, 14 }); - __rv.val[1] = (poly16x8_t) __builtin_shuffle (__a, __b, (uint16x8_t) { 1, 3, 5, 7, 9, 11, 13, 15 }); +#ifdef __ARM_BIG_ENDIAN + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 9, 11, 13, 15, 1, 3, 5, 7 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 8, 10, 12, 14, 0, 2, 4, 6 }); +#else + __rv.val[0] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 0, 2, 4, 6, 8, 10, 12, 14 }); + __rv.val[1] = __builtin_shuffle (__a, __b, (uint16x8_t) + { 1, 3, 5, 7, 9, 11, 13, 15 }); +#endif return __rv; } diff --git a/gcc-4.9/gcc/config/arm/bpabi.h b/gcc-4.9/gcc/config/arm/bpabi.h index bc223f8e3..7a576ac46 100644 --- a/gcc-4.9/gcc/config/arm/bpabi.h +++ b/gcc-4.9/gcc/config/arm/bpabi.h @@ -14,8 +14,13 @@ or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. - You should have received a copy of the GNU General Public License - along with GCC; see the file COPYING3. If not see + Under Section 7 of GPL version 3, you are granted additional + permissions described in the GCC Runtime Library Exception, version + 3.1, as published by the Free Software Foundation. + + You should have received a copy of the GNU General Public License and + a copy of the GCC Runtime Library Exception along with this program; + see the files COPYING3 and COPYING.RUNTIME respectively. If not, see <http://www.gnu.org/licenses/>. */ /* Use the AAPCS ABI by default. */ diff --git a/gcc-4.9/gcc/config/arm/elf.h b/gcc-4.9/gcc/config/arm/elf.h index 2edf520de..15a32fb8a 100644 --- a/gcc-4.9/gcc/config/arm/elf.h +++ b/gcc-4.9/gcc/config/arm/elf.h @@ -16,8 +16,13 @@ or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. - You should have received a copy of the GNU General Public License - along with GCC; see the file COPYING3. If not see + Under Section 7 of GPL version 3, you are granted additional + permissions described in the GCC Runtime Library Exception, version + 3.1, as published by the Free Software Foundation. + + You should have received a copy of the GNU General Public License and + a copy of the GCC Runtime Library Exception along with this program; + see the files COPYING3 and COPYING.RUNTIME respectively. If not, see <http://www.gnu.org/licenses/>. */ #ifndef OBJECT_FORMAT_ELF diff --git a/gcc-4.9/gcc/config/arm/linux-eabi.h b/gcc-4.9/gcc/config/arm/linux-eabi.h index 4d42cbfc8..350639f32 100644 --- a/gcc-4.9/gcc/config/arm/linux-eabi.h +++ b/gcc-4.9/gcc/config/arm/linux-eabi.h @@ -68,8 +68,9 @@ GLIBC_DYNAMIC_LINKER_DEFAULT and TARGET_DEFAULT_FLOAT_ABI. */ #undef GLIBC_DYNAMIC_LINKER -#define GLIBC_DYNAMIC_LINKER_SOFT_FLOAT "/lib/ld-linux.so.3" -#define GLIBC_DYNAMIC_LINKER_HARD_FLOAT "/lib/ld-linux-armhf.so.3" + +#define GLIBC_DYNAMIC_LINKER_SOFT_FLOAT RUNTIME_ROOT_PREFIX "/lib/ld-linux.so.3" +#define GLIBC_DYNAMIC_LINKER_HARD_FLOAT RUNTIME_ROOT_PREFIX "/lib/ld-linux-armhf.so.3" #define GLIBC_DYNAMIC_LINKER_DEFAULT GLIBC_DYNAMIC_LINKER_SOFT_FLOAT #define GLIBC_DYNAMIC_LINKER \ diff --git a/gcc-4.9/gcc/config/arm/linux-elf.h b/gcc-4.9/gcc/config/arm/linux-elf.h index 5dc3328e8..e825ae48c 100644 --- a/gcc-4.9/gcc/config/arm/linux-elf.h +++ b/gcc-4.9/gcc/config/arm/linux-elf.h @@ -14,8 +14,13 @@ or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. - You should have received a copy of the GNU General Public License - along with GCC; see the file COPYING3. If not see + Under Section 7 of GPL version 3, you are granted additional + permissions described in the GCC Runtime Library Exception, version + 3.1, as published by the Free Software Foundation. + + You should have received a copy of the GNU General Public License and + a copy of the GCC Runtime Library Exception along with this program; + see the files COPYING3 and COPYING.RUNTIME respectively. If not, see <http://www.gnu.org/licenses/>. */ /* elfos.h should have already been included. Now just override @@ -57,7 +62,7 @@ #define LIBGCC_SPEC "%{mfloat-abi=soft*:-lfloat} -lgcc" -#define GLIBC_DYNAMIC_LINKER "/lib/ld-linux.so.2" +#define GLIBC_DYNAMIC_LINKER RUNTIME_ROOT_PREFIX "/lib/ld-linux.so.2" #define LINUX_TARGET_LINK_SPEC "%{h*} \ %{static:-Bstatic} \ diff --git a/gcc-4.9/gcc/config/arm/linux-gas.h b/gcc-4.9/gcc/config/arm/linux-gas.h index 52a739c26..1dd043782 100644 --- a/gcc-4.9/gcc/config/arm/linux-gas.h +++ b/gcc-4.9/gcc/config/arm/linux-gas.h @@ -15,8 +15,13 @@ or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. - You should have received a copy of the GNU General Public License - along with GCC; see the file COPYING3. If not see + Under Section 7 of GPL version 3, you are granted additional + permissions described in the GCC Runtime Library Exception, version + 3.1, as published by the Free Software Foundation. + + You should have received a copy of the GNU General Public License and + a copy of the GCC Runtime Library Exception along with this program; + see the files COPYING3 and COPYING.RUNTIME respectively. If not, see <http://www.gnu.org/licenses/>. */ /* This is how we tell the assembler that a symbol is weak. diff --git a/gcc-4.9/gcc/config/arm/linux-grte.h b/gcc-4.9/gcc/config/arm/linux-grte.h new file mode 100644 index 000000000..7ee5806b7 --- /dev/null +++ b/gcc-4.9/gcc/config/arm/linux-grte.h @@ -0,0 +1,27 @@ +/* Definitions for ARM Linux-based GRTE (Google RunTime Environment). + Copyright (C) 2011 Free Software Foundation, Inc. + Contributed by Chris Demetriou. + +This file is part of GCC. + +GCC is free software; you can redistribute it and/or modify +it under the terms of the GNU General Public License as published by +the Free Software Foundation; either version 3, or (at your option) +any later version. + +GCC is distributed in the hope that it will be useful, +but WITHOUT ANY WARRANTY; without even the implied warranty of +MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the +GNU General Public License for more details. + +Under Section 7 of GPL version 3, you are granted additional +permissions described in the GCC Runtime Library Exception, version +3.1, as published by the Free Software Foundation. + +You should have received a copy of the GNU General Public License and +a copy of the GCC Runtime Library Exception along with this program; +see the files COPYING3 and COPYING.RUNTIME respectively. If not, see +<http://www.gnu.org/licenses/>. */ + +#undef SUBSUBTARGET_EXTRA_SPECS +#define SUBSUBTARGET_EXTRA_SPECS LINUX_GRTE_EXTRA_SPECS diff --git a/gcc-4.9/gcc/config/arm/neon-docgen.ml b/gcc-4.9/gcc/config/arm/neon-docgen.ml deleted file mode 100644 index 5788a533e..000000000 --- a/gcc-4.9/gcc/config/arm/neon-docgen.ml +++ /dev/null @@ -1,424 +0,0 @@ -(* ARM NEON documentation generator. - - Copyright (C) 2006-2014 Free Software Foundation, Inc. - Contributed by CodeSourcery. - - This file is part of GCC. - - GCC is free software; you can redistribute it and/or modify it under - the terms of the GNU General Public License as published by the Free - Software Foundation; either version 3, or (at your option) any later - version. - - GCC is distributed in the hope that it will be useful, but WITHOUT ANY - WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License - for more details. - - You should have received a copy of the GNU General Public License - along with GCC; see the file COPYING3. If not see - <http://www.gnu.org/licenses/>. - - This is an O'Caml program. The O'Caml compiler is available from: - - http://caml.inria.fr/ - - Or from your favourite OS's friendly packaging system. Tested with version - 3.09.2, though other versions will probably work too. - - Compile with: - ocamlc -c neon.ml - ocamlc -o neon-docgen neon.cmo neon-docgen.ml - - Run with: - /path/to/neon-docgen /path/to/gcc/doc/arm-neon-intrinsics.texi -*) - -open Neon - -(* The combined "ops" and "reinterp" table. *) -let ops_reinterp = reinterp @ ops - -(* Helper functions for extracting things from the "ops" table. *) -let single_opcode desired_opcode () = - List.fold_left (fun got_so_far -> - fun row -> - match row with - (opcode, _, _, _, _, _) -> - if opcode = desired_opcode then row :: got_so_far - else got_so_far - ) [] ops_reinterp - -let multiple_opcodes desired_opcodes () = - List.fold_left (fun got_so_far -> - fun desired_opcode -> - (single_opcode desired_opcode ()) @ got_so_far) - [] desired_opcodes - -let ldx_opcode number () = - List.fold_left (fun got_so_far -> - fun row -> - match row with - (opcode, _, _, _, _, _) -> - match opcode with - Vldx n | Vldx_lane n | Vldx_dup n when n = number -> - row :: got_so_far - | _ -> got_so_far - ) [] ops_reinterp - -let stx_opcode number () = - List.fold_left (fun got_so_far -> - fun row -> - match row with - (opcode, _, _, _, _, _) -> - match opcode with - Vstx n | Vstx_lane n when n = number -> - row :: got_so_far - | _ -> got_so_far - ) [] ops_reinterp - -let tbl_opcode () = - List.fold_left (fun got_so_far -> - fun row -> - match row with - (opcode, _, _, _, _, _) -> - match opcode with - Vtbl _ -> row :: got_so_far - | _ -> got_so_far - ) [] ops_reinterp - -let tbx_opcode () = - List.fold_left (fun got_so_far -> - fun row -> - match row with - (opcode, _, _, _, _, _) -> - match opcode with - Vtbx _ -> row :: got_so_far - | _ -> got_so_far - ) [] ops_reinterp - -(* The groups of intrinsics. *) -let intrinsic_groups = - [ "Addition", single_opcode Vadd; - "Multiplication", single_opcode Vmul; - "Multiply-accumulate", single_opcode Vmla; - "Multiply-subtract", single_opcode Vmls; - "Fused-multiply-accumulate", single_opcode Vfma; - "Fused-multiply-subtract", single_opcode Vfms; - "Round to integral (to nearest, ties to even)", single_opcode Vrintn; - "Round to integral (to nearest, ties away from zero)", single_opcode Vrinta; - "Round to integral (towards +Inf)", single_opcode Vrintp; - "Round to integral (towards -Inf)", single_opcode Vrintm; - "Round to integral (towards 0)", single_opcode Vrintz; - "Subtraction", single_opcode Vsub; - "Comparison (equal-to)", single_opcode Vceq; - "Comparison (greater-than-or-equal-to)", single_opcode Vcge; - "Comparison (less-than-or-equal-to)", single_opcode Vcle; - "Comparison (greater-than)", single_opcode Vcgt; - "Comparison (less-than)", single_opcode Vclt; - "Comparison (absolute greater-than-or-equal-to)", single_opcode Vcage; - "Comparison (absolute less-than-or-equal-to)", single_opcode Vcale; - "Comparison (absolute greater-than)", single_opcode Vcagt; - "Comparison (absolute less-than)", single_opcode Vcalt; - "Test bits", single_opcode Vtst; - "Absolute difference", single_opcode Vabd; - "Absolute difference and accumulate", single_opcode Vaba; - "Maximum", single_opcode Vmax; - "Minimum", single_opcode Vmin; - "Pairwise add", single_opcode Vpadd; - "Pairwise add, single_opcode widen and accumulate", single_opcode Vpada; - "Folding maximum", single_opcode Vpmax; - "Folding minimum", single_opcode Vpmin; - "Reciprocal step", multiple_opcodes [Vrecps; Vrsqrts]; - "Vector shift left", single_opcode Vshl; - "Vector shift left by constant", single_opcode Vshl_n; - "Vector shift right by constant", single_opcode Vshr_n; - "Vector shift right by constant and accumulate", single_opcode Vsra_n; - "Vector shift right and insert", single_opcode Vsri; - "Vector shift left and insert", single_opcode Vsli; - "Absolute value", single_opcode Vabs; - "Negation", single_opcode Vneg; - "Bitwise not", single_opcode Vmvn; - "Count leading sign bits", single_opcode Vcls; - "Count leading zeros", single_opcode Vclz; - "Count number of set bits", single_opcode Vcnt; - "Reciprocal estimate", single_opcode Vrecpe; - "Reciprocal square-root estimate", single_opcode Vrsqrte; - "Get lanes from a vector", single_opcode Vget_lane; - "Set lanes in a vector", single_opcode Vset_lane; - "Create vector from literal bit pattern", single_opcode Vcreate; - "Set all lanes to the same value", - multiple_opcodes [Vdup_n; Vmov_n; Vdup_lane]; - "Combining vectors", single_opcode Vcombine; - "Splitting vectors", multiple_opcodes [Vget_high; Vget_low]; - "Conversions", multiple_opcodes [Vcvt; Vcvt_n]; - "Move, single_opcode narrowing", single_opcode Vmovn; - "Move, single_opcode long", single_opcode Vmovl; - "Table lookup", tbl_opcode; - "Extended table lookup", tbx_opcode; - "Multiply, lane", single_opcode Vmul_lane; - "Long multiply, lane", single_opcode Vmull_lane; - "Saturating doubling long multiply, lane", single_opcode Vqdmull_lane; - "Saturating doubling multiply high, lane", single_opcode Vqdmulh_lane; - "Multiply-accumulate, lane", single_opcode Vmla_lane; - "Multiply-subtract, lane", single_opcode Vmls_lane; - "Vector multiply by scalar", single_opcode Vmul_n; - "Vector long multiply by scalar", single_opcode Vmull_n; - "Vector saturating doubling long multiply by scalar", - single_opcode Vqdmull_n; - "Vector saturating doubling multiply high by scalar", - single_opcode Vqdmulh_n; - "Vector multiply-accumulate by scalar", single_opcode Vmla_n; - "Vector multiply-subtract by scalar", single_opcode Vmls_n; - "Vector extract", single_opcode Vext; - "Reverse elements", multiple_opcodes [Vrev64; Vrev32; Vrev16]; - "Bit selection", single_opcode Vbsl; - "Transpose elements", single_opcode Vtrn; - "Zip elements", single_opcode Vzip; - "Unzip elements", single_opcode Vuzp; - "Element/structure loads, VLD1 variants", ldx_opcode 1; - "Element/structure stores, VST1 variants", stx_opcode 1; - "Element/structure loads, VLD2 variants", ldx_opcode 2; - "Element/structure stores, VST2 variants", stx_opcode 2; - "Element/structure loads, VLD3 variants", ldx_opcode 3; - "Element/structure stores, VST3 variants", stx_opcode 3; - "Element/structure loads, VLD4 variants", ldx_opcode 4; - "Element/structure stores, VST4 variants", stx_opcode 4; - "Logical operations (AND)", single_opcode Vand; - "Logical operations (OR)", single_opcode Vorr; - "Logical operations (exclusive OR)", single_opcode Veor; - "Logical operations (AND-NOT)", single_opcode Vbic; - "Logical operations (OR-NOT)", single_opcode Vorn; - "Reinterpret casts", single_opcode Vreinterp ] - -(* Given an intrinsic shape, produce a string to document the corresponding - operand shapes. *) -let rec analyze_shape shape = - let rec n_things n thing = - match n with - 0 -> [] - | n -> thing :: (n_things (n - 1) thing) - in - let rec analyze_shape_elt reg_no elt = - match elt with - Dreg -> "@var{d" ^ (string_of_int reg_no) ^ "}" - | Qreg -> "@var{q" ^ (string_of_int reg_no) ^ "}" - | Corereg -> "@var{r" ^ (string_of_int reg_no) ^ "}" - | Immed -> "#@var{0}" - | VecArray (1, elt) -> - let elt_regexp = analyze_shape_elt 0 elt in - "@{" ^ elt_regexp ^ "@}" - | VecArray (n, elt) -> - let rec f m = - match m with - 0 -> [] - | m -> (analyze_shape_elt (m - 1) elt) :: (f (m - 1)) - in - let ops = List.rev (f n) in - "@{" ^ (commas (fun x -> x) ops "") ^ "@}" - | (PtrTo elt | CstPtrTo elt) -> - "[" ^ (analyze_shape_elt reg_no elt) ^ "]" - | Element_of_dreg -> (analyze_shape_elt reg_no Dreg) ^ "[@var{0}]" - | Element_of_qreg -> (analyze_shape_elt reg_no Qreg) ^ "[@var{0}]" - | All_elements_of_dreg -> (analyze_shape_elt reg_no Dreg) ^ "[]" - | Alternatives alts -> (analyze_shape_elt reg_no (List.hd alts)) - in - match shape with - All (n, elt) -> commas (analyze_shape_elt 0) (n_things n elt) "" - | Long -> (analyze_shape_elt 0 Qreg) ^ ", " ^ (analyze_shape_elt 0 Dreg) ^ - ", " ^ (analyze_shape_elt 0 Dreg) - | Long_noreg elt -> (analyze_shape_elt 0 elt) ^ ", " ^ - (analyze_shape_elt 0 elt) - | Wide -> (analyze_shape_elt 0 Qreg) ^ ", " ^ (analyze_shape_elt 0 Qreg) ^ - ", " ^ (analyze_shape_elt 0 Dreg) - | Wide_noreg elt -> analyze_shape (Long_noreg elt) - | Narrow -> (analyze_shape_elt 0 Dreg) ^ ", " ^ (analyze_shape_elt 0 Qreg) ^ - ", " ^ (analyze_shape_elt 0 Qreg) - | Use_operands elts -> commas (analyze_shape_elt 0) (Array.to_list elts) "" - | By_scalar Dreg -> - analyze_shape (Use_operands [| Dreg; Dreg; Element_of_dreg |]) - | By_scalar Qreg -> - analyze_shape (Use_operands [| Qreg; Qreg; Element_of_dreg |]) - | By_scalar _ -> assert false - | Wide_lane -> - analyze_shape (Use_operands [| Qreg; Dreg; Element_of_dreg |]) - | Wide_scalar -> - analyze_shape (Use_operands [| Qreg; Dreg; Element_of_dreg |]) - | Pair_result elt -> - let elt_regexp = analyze_shape_elt 0 elt in - let elt_regexp' = analyze_shape_elt 1 elt in - elt_regexp ^ ", " ^ elt_regexp' - | Unary_scalar _ -> "FIXME Unary_scalar" - | Binary_imm elt -> analyze_shape (Use_operands [| elt; elt; Immed |]) - | Narrow_imm -> analyze_shape (Use_operands [| Dreg; Qreg; Immed |]) - | Long_imm -> analyze_shape (Use_operands [| Qreg; Dreg; Immed |]) - -(* Document a single intrinsic. *) -let describe_intrinsic first chan - (elt_ty, (_, features, shape, name, munge, _)) = - let c_arity, new_elt_ty = munge shape elt_ty in - let c_types = strings_of_arity c_arity in - Printf.fprintf chan "@itemize @bullet\n"; - let item_code = if first then "@item" else "@itemx" in - Printf.fprintf chan "%s %s %s_%s (" item_code (List.hd c_types) - (intrinsic_name name) (string_of_elt elt_ty); - Printf.fprintf chan "%s)\n" (commas (fun ty -> ty) (List.tl c_types) ""); - if not (List.exists (fun feature -> feature = No_op) features) then - begin - let print_one_insn name = - Printf.fprintf chan "@code{"; - let no_suffix = (new_elt_ty = NoElts) in - let name_with_suffix = - if no_suffix then name - else name ^ "." ^ (string_of_elt_dots new_elt_ty) - in - let possible_operands = analyze_all_shapes features shape - analyze_shape - in - let rec print_one_possible_operand op = - Printf.fprintf chan "%s %s}" name_with_suffix op - in - (* If the intrinsic expands to multiple instructions, we assume - they are all of the same form. *) - print_one_possible_operand (List.hd possible_operands) - in - let rec print_insns names = - match names with - [] -> () - | [name] -> print_one_insn name - | name::names -> (print_one_insn name; - Printf.fprintf chan " @emph{or} "; - print_insns names) - in - let insn_names = get_insn_names features name in - Printf.fprintf chan "@*@emph{Form of expected instruction(s):} "; - print_insns insn_names; - Printf.fprintf chan "\n" - end; - Printf.fprintf chan "@end itemize\n"; - Printf.fprintf chan "\n\n" - -(* Document a group of intrinsics. *) -let document_group chan (group_title, group_extractor) = - (* Extract the rows in question from the ops table and then turn them - into a list of intrinsics. *) - let intrinsics = - List.fold_left (fun got_so_far -> - fun row -> - match row with - (_, _, _, _, _, elt_tys) -> - List.fold_left (fun got_so_far' -> - fun elt_ty -> - (elt_ty, row) :: got_so_far') - got_so_far elt_tys - ) [] (group_extractor ()) - in - (* Emit the title for this group. *) - Printf.fprintf chan "@subsubsection %s\n\n" group_title; - (* Emit a description of each intrinsic. *) - List.iter (describe_intrinsic true chan) intrinsics; - (* Close this group. *) - Printf.fprintf chan "\n\n" - -let gnu_header chan = - List.iter (fun s -> Printf.fprintf chan "%s\n" s) [ - "@c Copyright (C) 2006-2014 Free Software Foundation, Inc."; - "@c This is part of the GCC manual."; - "@c For copying conditions, see the file gcc.texi."; - ""; - "@c This file is generated automatically using gcc/config/arm/neon-docgen.ml"; - "@c Please do not edit manually."] - -let crypto_doc = -" -@itemize @bullet -@item poly128_t vldrq_p128(poly128_t const *) -@end itemize - -@itemize @bullet -@item void vstrq_p128(poly128_t *, poly128_t) -@end itemize - -@itemize @bullet -@item uint64x1_t vceq_p64 (poly64x1_t, poly64x1_t) -@end itemize - -@itemize @bullet -@item uint64x1_t vtst_p64 (poly64x1_t, poly64x1_t) -@end itemize - -@itemize @bullet -@item uint32_t vsha1h_u32 (uint32_t) -@*@emph{Form of expected instruction(s):} @code{sha1h.32 @var{q0}, @var{q1}} -@end itemize - -@itemize @bullet -@item uint32x4_t vsha1cq_u32 (uint32x4_t, uint32_t, uint32x4_t) -@*@emph{Form of expected instruction(s):} @code{sha1c.32 @var{q0}, @var{q1}, @var{q2}} -@end itemize - -@itemize @bullet -@item uint32x4_t vsha1pq_u32 (uint32x4_t, uint32_t, uint32x4_t) -@*@emph{Form of expected instruction(s):} @code{sha1p.32 @var{q0}, @var{q1}, @var{q2}} -@end itemize - -@itemize @bullet -@item uint32x4_t vsha1mq_u32 (uint32x4_t, uint32_t, uint32x4_t) -@*@emph{Form of expected instruction(s):} @code{sha1m.32 @var{q0}, @var{q1}, @var{q2}} -@end itemize - -@itemize @bullet -@item uint32x4_t vsha1su0q_u32 (uint32x4_t, uint32x4_t, uint32x4_t) -@*@emph{Form of expected instruction(s):} @code{sha1su0.32 @var{q0}, @var{q1}, @var{q2}} -@end itemize - -@itemize @bullet -@item uint32x4_t vsha1su1q_u32 (uint32x4_t, uint32x4_t) -@*@emph{Form of expected instruction(s):} @code{sha1su1.32 @var{q0}, @var{q1}, @var{q2}} -@end itemize - -@itemize @bullet -@item uint32x4_t vsha256hq_u32 (uint32x4_t, uint32x4_t, uint32x4_t) -@*@emph{Form of expected instruction(s):} @code{sha256h.32 @var{q0}, @var{q1}, @var{q2}} -@end itemize - -@itemize @bullet -@item uint32x4_t vsha256h2q_u32 (uint32x4_t, uint32x4_t, uint32x4_t) -@*@emph{Form of expected instruction(s):} @code{sha256h2.32 @var{q0}, @var{q1}, @var{q2}} -@end itemize - -@itemize @bullet -@item uint32x4_t vsha256su0q_u32 (uint32x4_t, uint32x4_t) -@*@emph{Form of expected instruction(s):} @code{sha256su0.32 @var{q0}, @var{q1}} -@end itemize - -@itemize @bullet -@item uint32x4_t vsha256su1q_u32 (uint32x4_t, uint32x4_t, uint32x4_t) -@*@emph{Form of expected instruction(s):} @code{sha256su1.32 @var{q0}, @var{q1}, @var{q2}} -@end itemize - -@itemize @bullet -@item poly128_t vmull_p64 (poly64_t a, poly64_t b) -@*@emph{Form of expected instruction(s):} @code{vmull.p64 @var{q0}, @var{d1}, @var{d2}} -@end itemize - -@itemize @bullet -@item poly128_t vmull_high_p64 (poly64x2_t a, poly64x2_t b) -@*@emph{Form of expected instruction(s):} @code{vmull.p64 @var{q0}, @var{d1}, @var{d2}} -@end itemize -" - -(* Program entry point. *) -let _ = - if Array.length Sys.argv <> 2 then - failwith "Usage: neon-docgen <output filename>" - else - let file = Sys.argv.(1) in - try - let chan = open_out file in - gnu_header chan; - List.iter (document_group chan) intrinsic_groups; - Printf.fprintf chan "%s\n" crypto_doc; - close_out chan - with Sys_error sys -> - failwith ("Could not create output file " ^ file ^ ": " ^ sys) diff --git a/gcc-4.9/gcc/config/arm/neon-gen.ml b/gcc-4.9/gcc/config/arm/neon-gen.ml deleted file mode 100644 index f3dd86b0a..000000000 --- a/gcc-4.9/gcc/config/arm/neon-gen.ml +++ /dev/null @@ -1,520 +0,0 @@ -(* Auto-generate ARM Neon intrinsics header file. - Copyright (C) 2006-2014 Free Software Foundation, Inc. - Contributed by CodeSourcery. - - This file is part of GCC. - - GCC is free software; you can redistribute it and/or modify it under - the terms of the GNU General Public License as published by the Free - Software Foundation; either version 3, or (at your option) any later - version. - - GCC is distributed in the hope that it will be useful, but WITHOUT ANY - WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License - for more details. - - You should have received a copy of the GNU General Public License - along with GCC; see the file COPYING3. If not see - <http://www.gnu.org/licenses/>. - - This is an O'Caml program. The O'Caml compiler is available from: - - http://caml.inria.fr/ - - Or from your favourite OS's friendly packaging system. Tested with version - 3.09.2, though other versions will probably work too. - - Compile with: - ocamlc -c neon.ml - ocamlc -o neon-gen neon.cmo neon-gen.ml - - Run with: - ./neon-gen > arm_neon.h -*) - -open Neon - -(* The format codes used in the following functions are documented at: - http://caml.inria.fr/pub/docs/manual-ocaml/libref/Format.html\ - #6_printflikefunctionsforprettyprinting - (one line, remove the backslash.) -*) - -(* Following functions can be used to approximate GNU indentation style. *) -let start_function () = - Format.printf "@[<v 0>"; - ref 0 - -let end_function nesting = - match !nesting with - 0 -> Format.printf "@;@;@]" - | _ -> failwith ("Bad nesting (ending function at level " - ^ (string_of_int !nesting) ^ ")") - -let open_braceblock nesting = - begin match !nesting with - 0 -> Format.printf "@,@<0>{@[<v 2>@," - | _ -> Format.printf "@,@[<v 2> @<0>{@[<v 2>@," - end; - incr nesting - -let close_braceblock nesting = - decr nesting; - match !nesting with - 0 -> Format.printf "@]@,@<0>}" - | _ -> Format.printf "@]@,@<0>}@]" - -let print_function arity fnname body = - let ffmt = start_function () in - Format.printf "__extension__ static __inline "; - let inl = "__attribute__ ((__always_inline__))" in - begin match arity with - Arity0 ret -> - Format.printf "%s %s@,%s (void)" (string_of_vectype ret) inl fnname - | Arity1 (ret, arg0) -> - Format.printf "%s %s@,%s (%s __a)" (string_of_vectype ret) inl fnname - (string_of_vectype arg0) - | Arity2 (ret, arg0, arg1) -> - Format.printf "%s %s@,%s (%s __a, %s __b)" - (string_of_vectype ret) inl fnname (string_of_vectype arg0) - (string_of_vectype arg1) - | Arity3 (ret, arg0, arg1, arg2) -> - Format.printf "%s %s@,%s (%s __a, %s __b, %s __c)" - (string_of_vectype ret) inl fnname (string_of_vectype arg0) - (string_of_vectype arg1) (string_of_vectype arg2) - | Arity4 (ret, arg0, arg1, arg2, arg3) -> - Format.printf "%s %s@,%s (%s __a, %s __b, %s __c, %s __d)" - (string_of_vectype ret) inl fnname (string_of_vectype arg0) - (string_of_vectype arg1) (string_of_vectype arg2) - (string_of_vectype arg3) - end; - open_braceblock ffmt; - let rec print_lines = function - [] -> () - | "" :: lines -> print_lines lines - | [line] -> Format.printf "%s" line - | line::lines -> Format.printf "%s@," line ; print_lines lines in - print_lines body; - close_braceblock ffmt; - end_function ffmt - -let union_string num elts base = - let itype = inttype_for_array num elts in - let iname = string_of_inttype itype - and sname = string_of_vectype (T_arrayof (num, elts)) in - Printf.sprintf "union { %s __i; %s __o; } %s" sname iname base - -let rec signed_ctype = function - T_uint8x8 | T_poly8x8 -> T_int8x8 - | T_uint8x16 | T_poly8x16 -> T_int8x16 - | T_uint16x4 | T_poly16x4 -> T_int16x4 - | T_uint16x8 | T_poly16x8 -> T_int16x8 - | T_uint32x2 -> T_int32x2 - | T_uint32x4 -> T_int32x4 - | T_uint64x1 -> T_int64x1 - | T_uint64x2 -> T_int64x2 - | T_poly64x2 -> T_int64x2 - (* Cast to types defined by mode in arm.c, not random types pulled in from - the <stdint.h> header in use. This fixes incompatible pointer errors when - compiling with C++. *) - | T_uint8 | T_int8 -> T_intQI - | T_uint16 | T_int16 -> T_intHI - | T_uint32 | T_int32 -> T_intSI - | T_uint64 | T_int64 -> T_intDI - | T_float16 -> T_floatHF - | T_float32 -> T_floatSF - | T_poly8 -> T_intQI - | T_poly16 -> T_intHI - | T_poly64 -> T_intDI - | T_poly128 -> T_intTI - | T_arrayof (n, elt) -> T_arrayof (n, signed_ctype elt) - | T_ptrto elt -> T_ptrto (signed_ctype elt) - | T_const elt -> T_const (signed_ctype elt) - | x -> x - -let add_cast ctype cval = - let stype = signed_ctype ctype in - if ctype <> stype then - Printf.sprintf "(%s) %s" (string_of_vectype stype) cval - else - cval - -let cast_for_return to_ty = "(" ^ (string_of_vectype to_ty) ^ ")" - -(* Return a tuple of a list of declarations to go at the start of the function, - and a list of statements needed to return THING. *) -let return arity thing = - match arity with - Arity0 (ret) | Arity1 (ret, _) | Arity2 (ret, _, _) | Arity3 (ret, _, _, _) - | Arity4 (ret, _, _, _, _) -> - begin match ret with - T_arrayof (num, vec) -> - let uname = union_string num vec "__rv" in - [uname ^ ";"], ["__rv.__o = " ^ thing ^ ";"; "return __rv.__i;"] - | T_void -> - [], [thing ^ ";"] - | _ -> - [], ["return " ^ (cast_for_return ret) ^ thing ^ ";"] - end - -let mask_shape_for_shuffle = function - All (num, reg) -> All (num, reg) - | Pair_result reg -> All (2, reg) - | _ -> failwith "mask_for_shuffle" - -let mask_elems shuffle shape elttype part = - let elem_size = elt_width elttype in - let num_elems = - match regmap shape 0 with - Dreg -> 64 / elem_size - | Qreg -> 128 / elem_size - | _ -> failwith "mask_elems" in - shuffle elem_size num_elems part - -(* Return a tuple of a list of declarations 0and a list of statements needed - to implement an intrinsic using __builtin_shuffle. SHUFFLE is a function - which returns a list of elements suitable for using as a mask. *) - -let shuffle_fn shuffle shape arity elttype = - let mshape = mask_shape_for_shuffle shape in - let masktype = type_for_elt mshape (unsigned_of_elt elttype) 0 in - let masktype_str = string_of_vectype masktype in - let shuffle_res = type_for_elt mshape elttype 0 in - let shuffle_res_str = string_of_vectype shuffle_res in - match arity with - Arity0 (ret) | Arity1 (ret, _) | Arity2 (ret, _, _) | Arity3 (ret, _, _, _) - | Arity4 (ret, _, _, _, _) -> - begin match ret with - T_arrayof (num, vec) -> - let elems1 = mask_elems shuffle mshape elttype `lo - and elems2 = mask_elems shuffle mshape elttype `hi in - let mask1 = (String.concat ", " (List.map string_of_int elems1)) - and mask2 = (String.concat ", " (List.map string_of_int elems2)) in - let shuf1 = Printf.sprintf - "__rv.val[0] = (%s) __builtin_shuffle (__a, __b, (%s) { %s });" - shuffle_res_str masktype_str mask1 - and shuf2 = Printf.sprintf - "__rv.val[1] = (%s) __builtin_shuffle (__a, __b, (%s) { %s });" - shuffle_res_str masktype_str mask2 in - [Printf.sprintf "%s __rv;" (string_of_vectype ret);], - [shuf1; shuf2; "return __rv;"] - | _ -> - let elems = mask_elems shuffle mshape elttype `lo in - let mask = (String.concat ", " (List.map string_of_int elems)) in - let shuf = Printf.sprintf - "return (%s) __builtin_shuffle (__a, (%s) { %s });" shuffle_res_str masktype_str mask in - [""], - [shuf] - end - -let rec element_type ctype = - match ctype with - T_arrayof (_, v) -> element_type v - | _ -> ctype - -let params ps = - let pdecls = ref [] in - let ptype t p = - match t with - T_arrayof (num, elts) -> - let uname = union_string num elts (p ^ "u") in - let decl = Printf.sprintf "%s = { %s };" uname p in - pdecls := decl :: !pdecls; - p ^ "u.__o" - | _ -> add_cast t p in - let plist = match ps with - Arity0 _ -> [] - | Arity1 (_, t1) -> [ptype t1 "__a"] - | Arity2 (_, t1, t2) -> [ptype t1 "__a"; ptype t2 "__b"] - | Arity3 (_, t1, t2, t3) -> [ptype t1 "__a"; ptype t2 "__b"; ptype t3 "__c"] - | Arity4 (_, t1, t2, t3, t4) -> - [ptype t1 "__a"; ptype t2 "__b"; ptype t3 "__c"; ptype t4 "__d"] in - !pdecls, plist - -let modify_params features plist = - let is_flipped = - List.exists (function Flipped _ -> true | _ -> false) features in - if is_flipped then - match plist with - [ a; b ] -> [ b; a ] - | _ -> - failwith ("Don't know how to flip args " ^ (String.concat ", " plist)) - else - plist - -(* !!! Decide whether to add an extra information word based on the shape - form. *) -let extra_word shape features paramlist bits = - let use_word = - match shape with - All _ | Long | Long_noreg _ | Wide | Wide_noreg _ | Narrow - | By_scalar _ | Wide_scalar | Wide_lane | Binary_imm _ | Long_imm - | Narrow_imm -> true - | _ -> List.mem InfoWord features - in - if use_word then - paramlist @ [string_of_int bits] - else - paramlist - -(* Bit 0 represents signed (1) vs unsigned (0), or float (1) vs poly (0). - Bit 1 represents floats & polynomials (1), or ordinary integers (0). - Bit 2 represents rounding (1) vs none (0). *) -let infoword_value elttype features = - let bits01 = - match elt_class elttype with - Signed | ConvClass (Signed, _) | ConvClass (_, Signed) -> 0b001 - | Poly -> 0b010 - | Float -> 0b011 - | _ -> 0b000 - and rounding_bit = if List.mem Rounding features then 0b100 else 0b000 in - bits01 lor rounding_bit - -(* "Cast" type operations will throw an exception in mode_of_elt (actually in - elt_width, called from there). Deal with that here, and generate a suffix - with multiple modes (<to><from>). *) -let rec mode_suffix elttype shape = - try - let mode = mode_of_elt elttype shape in - string_of_mode mode - with MixedMode (dst, src) -> - let dstmode = mode_of_elt ~argpos:0 dst shape - and srcmode = mode_of_elt ~argpos:1 src shape in - string_of_mode dstmode ^ string_of_mode srcmode - -let get_shuffle features = - try - match List.find (function Use_shuffle _ -> true | _ -> false) features with - Use_shuffle fn -> Some fn - | _ -> None - with Not_found -> None - -let print_feature_test_start features = - try - match List.find (fun feature -> - match feature with Requires_feature _ -> true - | Requires_arch _ -> true - | Requires_FP_bit _ -> true - | _ -> false) - features with - Requires_feature feature -> - Format.printf "#ifdef __ARM_FEATURE_%s@\n" feature - | Requires_arch arch -> - Format.printf "#if __ARM_ARCH >= %d@\n" arch - | Requires_FP_bit bit -> - Format.printf "#if ((__ARM_FP & 0x%X) != 0)@\n" - (1 lsl bit) - | _ -> assert false - with Not_found -> assert true - -let print_feature_test_end features = - let feature = - List.exists (function Requires_feature _ -> true - | Requires_arch _ -> true - | Requires_FP_bit _ -> true - | _ -> false) features in - if feature then Format.printf "#endif@\n" - - -let print_variant opcode features shape name (ctype, asmtype, elttype) = - let bits = infoword_value elttype features in - let modesuf = mode_suffix elttype shape in - let pdecls, paramlist = params ctype in - let rdecls, stmts = - match get_shuffle features with - Some shuffle -> shuffle_fn shuffle shape ctype elttype - | None -> - let paramlist' = modify_params features paramlist in - let paramlist'' = extra_word shape features paramlist' bits in - let parstr = String.concat ", " paramlist'' in - let builtin = Printf.sprintf "__builtin_neon_%s%s (%s)" - (builtin_name features name) modesuf parstr in - return ctype builtin in - let body = pdecls @ rdecls @ stmts - and fnname = (intrinsic_name name) ^ "_" ^ (string_of_elt elttype) in - begin - print_feature_test_start features; - print_function ctype fnname body; - print_feature_test_end features; - end - -(* When this function processes the element types in the ops table, it rewrites - them in a list of tuples (a,b,c): - a : C type as an "arity", e.g. Arity1 (T_poly8x8, T_poly8x8) - b : Asm type : a single, processed element type, e.g. P16. This is the - type which should be attached to the asm opcode. - c : Variant type : the unprocessed type for this variant (e.g. in add - instructions which don't care about the sign, b might be i16 and c - might be s16.) -*) - -let print_op (opcode, features, shape, name, munge, types) = - let sorted_types = List.sort compare types in - let munged_types = List.map - (fun elt -> let c, asm = munge shape elt in c, asm, elt) sorted_types in - List.iter - (fun variant -> print_variant opcode features shape name variant) - munged_types - -let print_ops ops = - List.iter print_op ops - -(* Output type definitions. Table entries are: - cbase : "C" name for the type. - abase : "ARM" base name for the type (i.e. int in int8x8_t). - esize : element size. - enum : element count. - alevel: architecture level at which available. -*) - -type fpulevel = CRYPTO | ALL - -let deftypes () = - let typeinfo = [ - (* Doubleword vector types. *) - "__builtin_neon_qi", "int", 8, 8, ALL; - "__builtin_neon_hi", "int", 16, 4, ALL; - "__builtin_neon_si", "int", 32, 2, ALL; - "__builtin_neon_di", "int", 64, 1, ALL; - "__builtin_neon_hf", "float", 16, 4, ALL; - "__builtin_neon_sf", "float", 32, 2, ALL; - "__builtin_neon_poly8", "poly", 8, 8, ALL; - "__builtin_neon_poly16", "poly", 16, 4, ALL; - "__builtin_neon_poly64", "poly", 64, 1, CRYPTO; - "__builtin_neon_uqi", "uint", 8, 8, ALL; - "__builtin_neon_uhi", "uint", 16, 4, ALL; - "__builtin_neon_usi", "uint", 32, 2, ALL; - "__builtin_neon_udi", "uint", 64, 1, ALL; - - (* Quadword vector types. *) - "__builtin_neon_qi", "int", 8, 16, ALL; - "__builtin_neon_hi", "int", 16, 8, ALL; - "__builtin_neon_si", "int", 32, 4, ALL; - "__builtin_neon_di", "int", 64, 2, ALL; - "__builtin_neon_sf", "float", 32, 4, ALL; - "__builtin_neon_poly8", "poly", 8, 16, ALL; - "__builtin_neon_poly16", "poly", 16, 8, ALL; - "__builtin_neon_poly64", "poly", 64, 2, CRYPTO; - "__builtin_neon_uqi", "uint", 8, 16, ALL; - "__builtin_neon_uhi", "uint", 16, 8, ALL; - "__builtin_neon_usi", "uint", 32, 4, ALL; - "__builtin_neon_udi", "uint", 64, 2, ALL - ] in - List.iter - (fun (cbase, abase, esize, enum, fpulevel) -> - let attr = - match enum with - 1 -> "" - | _ -> Printf.sprintf "\t__attribute__ ((__vector_size__ (%d)))" - (esize * enum / 8) in - if fpulevel == CRYPTO then - Format.printf "#ifdef __ARM_FEATURE_CRYPTO\n"; - Format.printf "typedef %s %s%dx%d_t%s;@\n" cbase abase esize enum attr; - if fpulevel == CRYPTO then - Format.printf "#endif\n";) - typeinfo; - Format.print_newline (); - (* Extra types not in <stdint.h>. *) - Format.printf "typedef float float32_t;\n"; - Format.printf "typedef __builtin_neon_poly8 poly8_t;\n"; - Format.printf "typedef __builtin_neon_poly16 poly16_t;\n"; - Format.printf "#ifdef __ARM_FEATURE_CRYPTO\n"; - Format.printf "typedef __builtin_neon_poly64 poly64_t;\n"; - Format.printf "typedef __builtin_neon_poly128 poly128_t;\n"; - Format.printf "#endif\n" - -(* Output structs containing arrays, for load & store instructions etc. - poly128_t is deliberately not included here because it has no array types - defined for it. *) - -let arrtypes () = - let typeinfo = [ - "int", 8, ALL; "int", 16, ALL; - "int", 32, ALL; "int", 64, ALL; - "uint", 8, ALL; "uint", 16, ALL; - "uint", 32, ALL; "uint", 64, ALL; - "float", 32, ALL; "poly", 8, ALL; - "poly", 16, ALL; "poly", 64, CRYPTO - ] in - let writestruct elname elsize regsize arrsize fpulevel = - let elnum = regsize / elsize in - let structname = - Printf.sprintf "%s%dx%dx%d_t" elname elsize elnum arrsize in - let sfmt = start_function () in - Format.printf "%stypedef struct %s" - (if fpulevel == CRYPTO then "#ifdef __ARM_FEATURE_CRYPTO\n" else "") structname; - open_braceblock sfmt; - Format.printf "%s%dx%d_t val[%d];" elname elsize elnum arrsize; - close_braceblock sfmt; - Format.printf " %s;%s" structname (if fpulevel == CRYPTO then "\n#endif\n" else ""); - end_function sfmt; - in - for n = 2 to 4 do - List.iter - (fun (elname, elsize, alevel) -> - writestruct elname elsize 64 n alevel; - writestruct elname elsize 128 n alevel) - typeinfo - done - -let print_lines = List.iter (fun s -> Format.printf "%s@\n" s) - -(* Do it. *) - -let _ = - print_lines [ -"/* ARM NEON intrinsics include file. This file is generated automatically"; -" using neon-gen.ml. Please do not edit manually."; -""; -" Copyright (C) 2006-2014 Free Software Foundation, Inc."; -" Contributed by CodeSourcery."; -""; -" This file is part of GCC."; -""; -" GCC is free software; you can redistribute it and/or modify it"; -" under the terms of the GNU General Public License as published"; -" by the Free Software Foundation; either version 3, or (at your"; -" option) any later version."; -""; -" GCC is distributed in the hope that it will be useful, but WITHOUT"; -" ANY WARRANTY; without even the implied warranty of MERCHANTABILITY"; -" or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public"; -" License for more details."; -""; -" Under Section 7 of GPL version 3, you are granted additional"; -" permissions described in the GCC Runtime Library Exception, version"; -" 3.1, as published by the Free Software Foundation."; -""; -" You should have received a copy of the GNU General Public License and"; -" a copy of the GCC Runtime Library Exception along with this program;"; -" see the files COPYING3 and COPYING.RUNTIME respectively. If not, see"; -" <http://www.gnu.org/licenses/>. */"; -""; -"#ifndef _GCC_ARM_NEON_H"; -"#define _GCC_ARM_NEON_H 1"; -""; -"#ifndef __ARM_NEON__"; -"#error You must enable NEON instructions (e.g. -mfloat-abi=softfp -mfpu=neon) to use arm_neon.h"; -"#else"; -""; -"#ifdef __cplusplus"; -"extern \"C\" {"; -"#endif"; -""; -"#include <stdint.h>"; -""]; - deftypes (); - arrtypes (); - Format.print_newline (); - print_ops ops; - Format.print_newline (); - print_ops reinterp; - print_ops reinterpq; - Format.printf "%s" crypto_intrinsics; - print_lines [ -"#ifdef __cplusplus"; -"}"; -"#endif"; -"#endif"; -"#endif"] diff --git a/gcc-4.9/gcc/config/arm/netbsd-elf.h b/gcc-4.9/gcc/config/arm/netbsd-elf.h index 9deda9679..645551fdf 100644 --- a/gcc-4.9/gcc/config/arm/netbsd-elf.h +++ b/gcc-4.9/gcc/config/arm/netbsd-elf.h @@ -14,8 +14,13 @@ or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. - You should have received a copy of the GNU General Public License - along with GCC; see the file COPYING3. If not see + Under Section 7 of GPL version 3, you are granted additional + permissions described in the GCC Runtime Library Exception, version + 3.1, as published by the Free Software Foundation. + + You should have received a copy of the GNU General Public License and + a copy of the GCC Runtime Library Exception along with this program; + see the files COPYING3 and COPYING.RUNTIME respectively. If not, see <http://www.gnu.org/licenses/>. */ /* Run-time Target Specification. */ diff --git a/gcc-4.9/gcc/config/arm/uclinux-eabi.h b/gcc-4.9/gcc/config/arm/uclinux-eabi.h index b5055ce40..4d57d1388 100644 --- a/gcc-4.9/gcc/config/arm/uclinux-eabi.h +++ b/gcc-4.9/gcc/config/arm/uclinux-eabi.h @@ -14,8 +14,13 @@ or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. - You should have received a copy of the GNU General Public License - along with GCC; see the file COPYING3. If not see + Under Section 7 of GPL version 3, you are granted additional + permissions described in the GCC Runtime Library Exception, version + 3.1, as published by the Free Software Foundation. + + You should have received a copy of the GNU General Public License and + a copy of the GCC Runtime Library Exception along with this program; + see the files COPYING3 and COPYING.RUNTIME respectively. If not, see <http://www.gnu.org/licenses/>. */ /* Override settings that are different to the uclinux-elf or diff --git a/gcc-4.9/gcc/config/arm/uclinux-elf.h b/gcc-4.9/gcc/config/arm/uclinux-elf.h index 5cd4fe527..43edba70c 100644 --- a/gcc-4.9/gcc/config/arm/uclinux-elf.h +++ b/gcc-4.9/gcc/config/arm/uclinux-elf.h @@ -14,8 +14,13 @@ or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. - You should have received a copy of the GNU General Public License - along with GCC; see the file COPYING3. If not see + Under Section 7 of GPL version 3, you are granted additional + permissions described in the GCC Runtime Library Exception, version + 3.1, as published by the Free Software Foundation. + + You should have received a copy of the GNU General Public License and + a copy of the GCC Runtime Library Exception along with this program; + see the files COPYING3 and COPYING.RUNTIME respectively. If not, see <http://www.gnu.org/licenses/>. */ /* We don't want a PLT. */ diff --git a/gcc-4.9/gcc/config/arm/unspecs.md b/gcc-4.9/gcc/config/arm/unspecs.md index 87edf18e2..db3fea5f5 100644 --- a/gcc-4.9/gcc/config/arm/unspecs.md +++ b/gcc-4.9/gcc/config/arm/unspecs.md @@ -58,6 +58,7 @@ ; instruction stream. UNSPEC_PIC_OFFSET ; A symbolic 12-bit OFFSET that has been treated ; correctly for PIC usage. + UNSPEC_GOT_PREL_SYM ; Specify an R_ARM_GOT_PREL relocation of a symbol. UNSPEC_GOTSYM_OFF ; The offset of the start of the GOT from a ; a given symbolic address. UNSPEC_THUMB1_CASESI ; A Thumb1 compressed dispatch-table call. @@ -70,6 +71,11 @@ ; that. UNSPEC_UNALIGNED_STORE ; Same for str/strh. UNSPEC_PIC_UNIFIED ; Create a common pic addressing form. + UNSPEC_PROLOGUE_USE ; As USE insns are not meaningful after reload, + ; this unspec is used to prevent the deletion of + ; instructions setting registers for EH handling + ; and stack frame generation. Operand 0 is the + ; register to "use". UNSPEC_LL ; Represent an unpaired load-register-exclusive. UNSPEC_VRINTZ ; Represent a float to integral float rounding ; towards zero. @@ -83,11 +89,12 @@ ; FPSCR rounding mode and signal inexactness. UNSPEC_VRINTA ; Represent a float to integral float rounding ; towards nearest, ties away from zero. - UNSPEC_GOT_PREL_SYM ; Specify an R_ARM_GOT_PREL relocation of a symbol ]) (define_c_enum "unspec" [ UNSPEC_WADDC ; Used by the intrinsic form of the iWMMXt WADDC instruction. + UNSPEC_WMADDS ; Used by the intrinsic form of the iWMMXt WMADDS instruction. + UNSPEC_WMADDU ; Used by the intrinsic form of the iWMMXt WMADDU instruction. UNSPEC_WABS ; Used by the intrinsic form of the iWMMXt WABS instruction. UNSPEC_WQMULWMR ; Used by the intrinsic form of the iWMMXt WQMULWMR instruction. UNSPEC_WQMULMR ; Used by the intrinsic form of the iWMMXt WQMULMR instruction. diff --git a/gcc-4.9/gcc/config/arm/vxworks.h b/gcc-4.9/gcc/config/arm/vxworks.h index 8bef16bc4..faf84724d 100644 --- a/gcc-4.9/gcc/config/arm/vxworks.h +++ b/gcc-4.9/gcc/config/arm/vxworks.h @@ -17,8 +17,13 @@ but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details. -You should have received a copy of the GNU General Public License -along with GCC; see the file COPYING3. If not see +Under Section 7 of GPL version 3, you are granted additional +permissions described in the GCC Runtime Library Exception, version +3.1, as published by the Free Software Foundation. + +You should have received a copy of the GNU General Public License and +a copy of the GCC Runtime Library Exception along with this program; +see the files COPYING3 and COPYING.RUNTIME respectively. If not, see <http://www.gnu.org/licenses/>. */ |