diff options
author | Andrew Hsieh <andrewhsieh@google.com> | 2014-05-27 17:28:09 +0000 |
---|---|---|
committer | Gerrit Code Review <noreply-gerritcodereview@google.com> | 2014-05-27 17:28:09 +0000 |
commit | 8f2898c09773292b6ba523cee7e528a320ff1e02 (patch) | |
tree | 99f5865580b6a3c8243c9cbe896103eb5f948275 /gcc-4.8 | |
parent | 41a51304ab0f3b4580f34718ee4781c3629fb548 (diff) | |
parent | 04ad5b9bb3c8c6505f36f90e227b18266d946d8e (diff) | |
download | toolchain_gcc-8f2898c09773292b6ba523cee7e528a320ff1e02.tar.gz toolchain_gcc-8f2898c09773292b6ba523cee7e528a320ff1e02.tar.bz2 toolchain_gcc-8f2898c09773292b6ba523cee7e528a320ff1e02.zip |
Merge "[4.8, 4.9] Fix aarch64/arm_neon.h vqdmulh_n_s16"
Diffstat (limited to 'gcc-4.8')
-rw-r--r-- | gcc-4.8/gcc/config/aarch64/arm_neon.h | 148 |
1 files changed, 74 insertions, 74 deletions
diff --git a/gcc-4.8/gcc/config/aarch64/arm_neon.h b/gcc-4.8/gcc/config/aarch64/arm_neon.h index 3b0ed0d45..b083eb4e6 100644 --- a/gcc-4.8/gcc/config/aarch64/arm_neon.h +++ b/gcc-4.8/gcc/config/aarch64/arm_neon.h @@ -9283,7 +9283,7 @@ vminvq_u32 (uint32x4_t a) int16x4_t result; \ __asm__ ("mla %0.4h, %2.4h, %3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -9311,7 +9311,7 @@ vminvq_u32 (uint32x4_t a) uint16x4_t result; \ __asm__ ("mla %0.4h, %2.4h, %3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -9339,7 +9339,7 @@ vminvq_u32 (uint32x4_t a) int16x4_t result; \ __asm__ ("mla %0.4h, %2.4h, %3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -9367,7 +9367,7 @@ vminvq_u32 (uint32x4_t a) uint16x4_t result; \ __asm__ ("mla %0.4h, %2.4h, %3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -9404,7 +9404,7 @@ vmla_n_s16 (int16x4_t a, int16x4_t b, int16_t c) int16x4_t result; __asm__ ("mla %0.4h,%2.4h,%3.h[0]" : "=w"(result) - : "0"(a), "w"(b), "w"(c) + : "0"(a), "w"(b), "x"(c) : /* No clobbers */); return result; } @@ -9426,7 +9426,7 @@ vmla_n_u16 (uint16x4_t a, uint16x4_t b, uint16_t c) uint16x4_t result; __asm__ ("mla %0.4h,%2.4h,%3.h[0]" : "=w"(result) - : "0"(a), "w"(b), "w"(c) + : "0"(a), "w"(b), "x"(c) : /* No clobbers */); return result; } @@ -9517,7 +9517,7 @@ vmla_u32 (uint32x2_t a, uint32x2_t b, uint32x2_t c) int32x4_t result; \ __asm__ ("smlal2 %0.4s, %2.8h, %3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -9545,7 +9545,7 @@ vmla_u32 (uint32x2_t a, uint32x2_t b, uint32x2_t c) uint32x4_t result; \ __asm__ ("umlal2 %0.4s, %2.8h, %3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -9573,7 +9573,7 @@ vmla_u32 (uint32x2_t a, uint32x2_t b, uint32x2_t c) int32x4_t result; \ __asm__ ("smlal2 %0.4s, %2.8h, %3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -9601,7 +9601,7 @@ vmla_u32 (uint32x2_t a, uint32x2_t b, uint32x2_t c) uint32x4_t result; \ __asm__ ("umlal2 %0.4s, %2.8h, %3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -9626,7 +9626,7 @@ vmlal_high_n_s16 (int32x4_t a, int16x8_t b, int16_t c) int32x4_t result; __asm__ ("smlal2 %0.4s,%2.8h,%3.h[0]" : "=w"(result) - : "0"(a), "w"(b), "w"(c) + : "0"(a), "w"(b), "x"(c) : /* No clobbers */); return result; } @@ -9648,7 +9648,7 @@ vmlal_high_n_u16 (uint32x4_t a, uint16x8_t b, uint16_t c) uint32x4_t result; __asm__ ("umlal2 %0.4s,%2.8h,%3.h[0]" : "=w"(result) - : "0"(a), "w"(b), "w"(c) + : "0"(a), "w"(b), "x"(c) : /* No clobbers */); return result; } @@ -9739,7 +9739,7 @@ vmlal_high_u32 (uint64x2_t a, uint32x4_t b, uint32x4_t c) int32x4_t result; \ __asm__ ("smlal %0.4s,%2.4h,%3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -9767,7 +9767,7 @@ vmlal_high_u32 (uint64x2_t a, uint32x4_t b, uint32x4_t c) uint32x4_t result; \ __asm__ ("umlal %0.4s,%2.4h,%3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -9795,7 +9795,7 @@ vmlal_high_u32 (uint64x2_t a, uint32x4_t b, uint32x4_t c) int32x4_t result; \ __asm__ ("smlal %0.4s, %2.4h, %3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -9823,7 +9823,7 @@ vmlal_high_u32 (uint64x2_t a, uint32x4_t b, uint32x4_t c) uint32x4_t result; \ __asm__ ("umlal %0.4s, %2.4h, %3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -9848,7 +9848,7 @@ vmlal_n_s16 (int32x4_t a, int16x4_t b, int16_t c) int32x4_t result; __asm__ ("smlal %0.4s,%2.4h,%3.h[0]" : "=w"(result) - : "0"(a), "w"(b), "w"(c) + : "0"(a), "w"(b), "x"(c) : /* No clobbers */); return result; } @@ -9870,7 +9870,7 @@ vmlal_n_u16 (uint32x4_t a, uint16x4_t b, uint16_t c) uint32x4_t result; __asm__ ("umlal %0.4s,%2.4h,%3.h[0]" : "=w"(result) - : "0"(a), "w"(b), "w"(c) + : "0"(a), "w"(b), "x"(c) : /* No clobbers */); return result; } @@ -9976,7 +9976,7 @@ vmlal_u32 (uint64x2_t a, uint32x2_t b, uint32x2_t c) int16x8_t result; \ __asm__ ("mla %0.8h, %2.8h, %3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -10004,7 +10004,7 @@ vmlal_u32 (uint64x2_t a, uint32x2_t b, uint32x2_t c) uint16x8_t result; \ __asm__ ("mla %0.8h, %2.8h, %3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -10032,7 +10032,7 @@ vmlal_u32 (uint64x2_t a, uint32x2_t b, uint32x2_t c) int16x8_t result; \ __asm__ ("mla %0.8h, %2.8h, %3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -10060,7 +10060,7 @@ vmlal_u32 (uint64x2_t a, uint32x2_t b, uint32x2_t c) uint16x8_t result; \ __asm__ ("mla %0.8h, %2.8h, %3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -10109,7 +10109,7 @@ vmlaq_n_s16 (int16x8_t a, int16x8_t b, int16_t c) int16x8_t result; __asm__ ("mla %0.8h,%2.8h,%3.h[0]" : "=w"(result) - : "0"(a), "w"(b), "w"(c) + : "0"(a), "w"(b), "x"(c) : /* No clobbers */); return result; } @@ -10131,7 +10131,7 @@ vmlaq_n_u16 (uint16x8_t a, uint16x8_t b, uint16_t c) uint16x8_t result; __asm__ ("mla %0.8h,%2.8h,%3.h[0]" : "=w"(result) - : "0"(a), "w"(b), "w"(c) + : "0"(a), "w"(b), "x"(c) : /* No clobbers */); return result; } @@ -10237,7 +10237,7 @@ vmlaq_u32 (uint32x4_t a, uint32x4_t b, uint32x4_t c) int16x4_t result; \ __asm__ ("mls %0.4h,%2.4h,%3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -10265,7 +10265,7 @@ vmlaq_u32 (uint32x4_t a, uint32x4_t b, uint32x4_t c) uint16x4_t result; \ __asm__ ("mls %0.4h,%2.4h,%3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -10302,7 +10302,7 @@ vmls_n_s16 (int16x4_t a, int16x4_t b, int16_t c) int16x4_t result; __asm__ ("mls %0.4h, %2.4h, %3.h[0]" : "=w"(result) - : "0"(a), "w"(b), "w"(c) + : "0"(a), "w"(b), "x"(c) : /* No clobbers */); return result; } @@ -10324,7 +10324,7 @@ vmls_n_u16 (uint16x4_t a, uint16x4_t b, uint16_t c) uint16x4_t result; __asm__ ("mls %0.4h, %2.4h, %3.h[0]" : "=w"(result) - : "0"(a), "w"(b), "w"(c) + : "0"(a), "w"(b), "x"(c) : /* No clobbers */); return result; } @@ -10415,7 +10415,7 @@ vmls_u32 (uint32x2_t a, uint32x2_t b, uint32x2_t c) int32x4_t result; \ __asm__ ("smlsl2 %0.4s, %2.8h, %3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -10443,7 +10443,7 @@ vmls_u32 (uint32x2_t a, uint32x2_t b, uint32x2_t c) uint32x4_t result; \ __asm__ ("umlsl2 %0.4s, %2.8h, %3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -10471,7 +10471,7 @@ vmls_u32 (uint32x2_t a, uint32x2_t b, uint32x2_t c) int32x4_t result; \ __asm__ ("smlsl2 %0.4s, %2.8h, %3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -10499,7 +10499,7 @@ vmls_u32 (uint32x2_t a, uint32x2_t b, uint32x2_t c) uint32x4_t result; \ __asm__ ("umlsl2 %0.4s, %2.8h, %3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -10524,7 +10524,7 @@ vmlsl_high_n_s16 (int32x4_t a, int16x8_t b, int16_t c) int32x4_t result; __asm__ ("smlsl2 %0.4s, %2.8h, %3.h[0]" : "=w"(result) - : "0"(a), "w"(b), "w"(c) + : "0"(a), "w"(b), "x"(c) : /* No clobbers */); return result; } @@ -10546,7 +10546,7 @@ vmlsl_high_n_u16 (uint32x4_t a, uint16x8_t b, uint16_t c) uint32x4_t result; __asm__ ("umlsl2 %0.4s, %2.8h, %3.h[0]" : "=w"(result) - : "0"(a), "w"(b), "w"(c) + : "0"(a), "w"(b), "x"(c) : /* No clobbers */); return result; } @@ -10637,7 +10637,7 @@ vmlsl_high_u32 (uint64x2_t a, uint32x4_t b, uint32x4_t c) int32x4_t result; \ __asm__ ("smlsl %0.4s, %2.4h, %3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -10665,7 +10665,7 @@ vmlsl_high_u32 (uint64x2_t a, uint32x4_t b, uint32x4_t c) uint32x4_t result; \ __asm__ ("umlsl %0.4s, %2.4h, %3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -10693,7 +10693,7 @@ vmlsl_high_u32 (uint64x2_t a, uint32x4_t b, uint32x4_t c) int32x4_t result; \ __asm__ ("smlsl %0.4s, %2.4h, %3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -10721,7 +10721,7 @@ vmlsl_high_u32 (uint64x2_t a, uint32x4_t b, uint32x4_t c) uint32x4_t result; \ __asm__ ("umlsl %0.4s, %2.4h, %3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -10746,7 +10746,7 @@ vmlsl_n_s16 (int32x4_t a, int16x4_t b, int16_t c) int32x4_t result; __asm__ ("smlsl %0.4s, %2.4h, %3.h[0]" : "=w"(result) - : "0"(a), "w"(b), "w"(c) + : "0"(a), "w"(b), "x"(c) : /* No clobbers */); return result; } @@ -10768,7 +10768,7 @@ vmlsl_n_u16 (uint32x4_t a, uint16x4_t b, uint16_t c) uint32x4_t result; __asm__ ("umlsl %0.4s, %2.4h, %3.h[0]" : "=w"(result) - : "0"(a), "w"(b), "w"(c) + : "0"(a), "w"(b), "x"(c) : /* No clobbers */); return result; } @@ -10874,7 +10874,7 @@ vmlsl_u32 (uint64x2_t a, uint32x2_t b, uint32x2_t c) int16x8_t result; \ __asm__ ("mls %0.8h,%2.8h,%3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -10902,7 +10902,7 @@ vmlsl_u32 (uint64x2_t a, uint32x2_t b, uint32x2_t c) uint16x8_t result; \ __asm__ ("mls %0.8h,%2.8h,%3.h[%4]" \ : "=w"(result) \ - : "0"(a_), "w"(b_), "w"(c_), "i"(d) \ + : "0"(a_), "w"(b_), "x"(c_), "i"(d) \ : /* No clobbers */); \ result; \ }) @@ -10945,7 +10945,7 @@ vmlsl_u32 (uint64x2_t a, uint32x2_t b, uint32x2_t c) int16x8_t __result; \ __asm__ ("mls %0.8h, %2.8h, %3.h[%4]" \ : "=w"(__result) \ - : "0"(__a_), "w"(__b_), "w"(__c_), "i"(__d) \ + : "0"(__a_), "w"(__b_), "x"(__c_), "i"(__d) \ : /* No clobbers */); \ __result; \ }) @@ -10973,7 +10973,7 @@ vmlsl_u32 (uint64x2_t a, uint32x2_t b, uint32x2_t c) uint16x8_t __result; \ __asm__ ("mls %0.8h, %2.8h, %3.h[%4]" \ : "=w"(__result) \ - : "0"(__a_), "w"(__b_), "w"(__c_), "i"(__d) \ + : "0"(__a_), "w"(__b_), "x"(__c_), "i"(__d) \ : /* No clobbers */); \ __result; \ }) @@ -11022,7 +11022,7 @@ vmlsq_n_s16 (int16x8_t a, int16x8_t b, int16_t c) int16x8_t result; __asm__ ("mls %0.8h, %2.8h, %3.h[0]" : "=w"(result) - : "0"(a), "w"(b), "w"(c) + : "0"(a), "w"(b), "x"(c) : /* No clobbers */); return result; } @@ -11044,7 +11044,7 @@ vmlsq_n_u16 (uint16x8_t a, uint16x8_t b, uint16_t c) uint16x8_t result; __asm__ ("mls %0.8h, %2.8h, %3.h[0]" : "=w"(result) - : "0"(a), "w"(b), "w"(c) + : "0"(a), "w"(b), "x"(c) : /* No clobbers */); return result; } @@ -11659,7 +11659,7 @@ vmovq_n_u64 (uint64_t a) int16x4_t result; \ __asm__ ("mul %0.4h,%1.4h,%2.h[%3]" \ : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ + : "w"(a_), "x"(b_), "i"(c) \ : /* No clobbers */); \ result; \ }) @@ -11685,7 +11685,7 @@ vmovq_n_u64 (uint64_t a) uint16x4_t result; \ __asm__ ("mul %0.4h,%1.4h,%2.h[%3]" \ : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ + : "w"(a_), "x"(b_), "i"(c) \ : /* No clobbers */); \ result; \ }) @@ -11724,7 +11724,7 @@ vmovq_n_u64 (uint64_t a) int16x4_t result; \ __asm__ ("mul %0.4h, %1.4h, %2.h[%3]" \ : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ + : "w"(a_), "x"(b_), "i"(c) \ : /* No clobbers */); \ result; \ }) @@ -11750,7 +11750,7 @@ vmovq_n_u64 (uint64_t a) uint16x4_t result; \ __asm__ ("mul %0.4h, %1.4h, %2.h[%3]" \ : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ + : "w"(a_), "x"(b_), "i"(c) \ : /* No clobbers */); \ result; \ }) @@ -11785,7 +11785,7 @@ vmul_n_s16 (int16x4_t a, int16_t b) int16x4_t result; __asm__ ("mul %0.4h,%1.4h,%2.h[0]" : "=w"(result) - : "w"(a), "w"(b) + : "w"(a), "x"(b) : /* No clobbers */); return result; } @@ -11807,7 +11807,7 @@ vmul_n_u16 (uint16x4_t a, uint16_t b) uint16x4_t result; __asm__ ("mul %0.4h,%1.4h,%2.h[0]" : "=w"(result) - : "w"(a), "w"(b) + : "w"(a), "x"(b) : /* No clobbers */); return result; } @@ -11844,7 +11844,7 @@ vmul_n_u32 (uint32x2_t a, uint32_t b) int32x4_t result; \ __asm__ ("smull2 %0.4s, %1.8h, %2.h[%3]" \ : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ + : "w"(a_), "x"(b_), "i"(c) \ : /* No clobbers */); \ result; \ }) @@ -11870,7 +11870,7 @@ vmul_n_u32 (uint32x2_t a, uint32_t b) uint32x4_t result; \ __asm__ ("umull2 %0.4s, %1.8h, %2.h[%3]" \ : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ + : "w"(a_), "x"(b_), "i"(c) \ : /* No clobbers */); \ result; \ }) @@ -11896,7 +11896,7 @@ vmul_n_u32 (uint32x2_t a, uint32_t b) int32x4_t result; \ __asm__ ("smull2 %0.4s, %1.8h, %2.h[%3]" \ : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ + : "w"(a_), "x"(b_), "i"(c) \ : /* No clobbers */); \ result; \ }) @@ -11922,7 +11922,7 @@ vmul_n_u32 (uint32x2_t a, uint32_t b) uint32x4_t result; \ __asm__ ("umull2 %0.4s, %1.8h, %2.h[%3]" \ : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ + : "w"(a_), "x"(b_), "i"(c) \ : /* No clobbers */); \ result; \ }) @@ -11946,7 +11946,7 @@ vmull_high_n_s16 (int16x8_t a, int16_t b) int32x4_t result; __asm__ ("smull2 %0.4s,%1.8h,%2.h[0]" : "=w"(result) - : "w"(a), "w"(b) + : "w"(a), "x"(b) : /* No clobbers */); return result; } @@ -11968,7 +11968,7 @@ vmull_high_n_u16 (uint16x8_t a, uint16_t b) uint32x4_t result; __asm__ ("umull2 %0.4s,%1.8h,%2.h[0]" : "=w"(result) - : "w"(a), "w"(b) + : "w"(a), "x"(b) : /* No clobbers */); return result; } @@ -12069,7 +12069,7 @@ vmull_high_u32 (uint32x4_t a, uint32x4_t b) int32x4_t result; \ __asm__ ("smull %0.4s,%1.4h,%2.h[%3]" \ : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ + : "w"(a_), "x"(b_), "i"(c) \ : /* No clobbers */); \ result; \ }) @@ -12095,7 +12095,7 @@ vmull_high_u32 (uint32x4_t a, uint32x4_t b) uint32x4_t result; \ __asm__ ("umull %0.4s,%1.4h,%2.h[%3]" \ : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ + : "w"(a_), "x"(b_), "i"(c) \ : /* No clobbers */); \ result; \ }) @@ -12121,7 +12121,7 @@ vmull_high_u32 (uint32x4_t a, uint32x4_t b) int32x4_t result; \ __asm__ ("smull %0.4s, %1.4h, %2.h[%3]" \ : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ + : "w"(a_), "x"(b_), "i"(c) \ : /* No clobbers */); \ result; \ }) @@ -12147,7 +12147,7 @@ vmull_high_u32 (uint32x4_t a, uint32x4_t b) uint32x4_t result; \ __asm__ ("umull %0.4s, %1.4h, %2.h[%3]" \ : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ + : "w"(a_), "x"(b_), "i"(c) \ : /* No clobbers */); \ result; \ }) @@ -12171,7 +12171,7 @@ vmull_n_s16 (int16x4_t a, int16_t b) int32x4_t result; __asm__ ("smull %0.4s,%1.4h,%2.h[0]" : "=w"(result) - : "w"(a), "w"(b) + : "w"(a), "x"(b) : /* No clobbers */); return result; } @@ -12193,7 +12193,7 @@ vmull_n_u16 (uint16x4_t a, uint16_t b) uint32x4_t result; __asm__ ("umull %0.4s,%1.4h,%2.h[0]" : "=w"(result) - : "w"(a), "w"(b) + : "w"(a), "x"(b) : /* No clobbers */); return result; } @@ -12320,7 +12320,7 @@ vmull_u32 (uint32x2_t a, uint32x2_t b) int16x8_t result; \ __asm__ ("mul %0.8h,%1.8h,%2.h[%3]" \ : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ + : "w"(a_), "x"(b_), "i"(c) \ : /* No clobbers */); \ result; \ }) @@ -12346,7 +12346,7 @@ vmull_u32 (uint32x2_t a, uint32x2_t b) uint16x8_t result; \ __asm__ ("mul %0.8h,%1.8h,%2.h[%3]" \ : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ + : "w"(a_), "x"(b_), "i"(c) \ : /* No clobbers */); \ result; \ }) @@ -12398,7 +12398,7 @@ vmull_u32 (uint32x2_t a, uint32x2_t b) int16x8_t result; \ __asm__ ("mul %0.8h, %1.8h, %2.h[%3]" \ : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ + : "w"(a_), "x"(b_), "i"(c) \ : /* No clobbers */); \ result; \ }) @@ -12424,7 +12424,7 @@ vmull_u32 (uint32x2_t a, uint32x2_t b) uint16x8_t result; \ __asm__ ("mul %0.8h, %1.8h, %2.h[%3]" \ : "=w"(result) \ - : "w"(a_), "w"(b_), "i"(c) \ + : "w"(a_), "x"(b_), "i"(c) \ : /* No clobbers */); \ result; \ }) @@ -12470,7 +12470,7 @@ vmulq_n_s16 (int16x8_t a, int16_t b) int16x8_t result; __asm__ ("mul %0.8h,%1.8h,%2.h[0]" : "=w"(result) - : "w"(a), "w"(b) + : "w"(a), "x"(b) : /* No clobbers */); return result; } @@ -12492,7 +12492,7 @@ vmulq_n_u16 (uint16x8_t a, uint16_t b) uint16x8_t result; __asm__ ("mul %0.8h,%1.8h,%2.h[0]" : "=w"(result) - : "w"(a), "w"(b) + : "w"(a), "x"(b) : /* No clobbers */); return result; } @@ -13815,7 +13815,7 @@ vqdmulh_n_s16 (int16x4_t a, int16_t b) int16x4_t result; __asm__ ("sqdmulh %0.4h,%1.4h,%2.h[0]" : "=w"(result) - : "w"(a), "w"(b) + : "w"(a), "x"(b) : /* No clobbers */); return result; } @@ -13837,7 +13837,7 @@ vqdmulhq_n_s16 (int16x8_t a, int16_t b) int16x8_t result; __asm__ ("sqdmulh %0.8h,%1.8h,%2.h[0]" : "=w"(result) - : "w"(a), "w"(b) + : "w"(a), "x"(b) : /* No clobbers */); return result; } @@ -13958,7 +13958,7 @@ vqrdmulh_n_s16 (int16x4_t a, int16_t b) int16x4_t result; __asm__ ("sqrdmulh %0.4h,%1.4h,%2.h[0]" : "=w"(result) - : "w"(a), "w"(b) + : "w"(a), "x"(b) : /* No clobbers */); return result; } @@ -13980,7 +13980,7 @@ vqrdmulhq_n_s16 (int16x8_t a, int16_t b) int16x8_t result; __asm__ ("sqrdmulh %0.8h,%1.8h,%2.h[0]" : "=w"(result) - : "w"(a), "w"(b) + : "w"(a), "x"(b) : /* No clobbers */); return result; } |