i386: add alias for f*mul_*ch intrinsics
gcc/ChangeLog: * config/i386/avx512fp16intrin.h (_mm512_mul_pch): Add alias for _mm512_fmul_pch. (_mm512_mask_mul_pch): Likewise. (_mm512_maskz_mul_pch): Likewise. (_mm512_mul_round_pch): Likewise. (_mm512_mask_mul_round_pch): Likewise. (_mm512_maskz_mul_round_pch): Likewise. (_mm512_cmul_pch): Likewise. (_mm512_mask_cmul_pch): Likewise. (_mm512_maskz_cmul_pch): Likewise. (_mm512_cmul_round_pch): Likewise. (_mm512_mask_cmul_round_pch): Likewise. (_mm512_maskz_cmul_round_pch): Likewise. (_mm_mul_sch): Likewise. (_mm_mask_mul_sch): Likewise. (_mm_maskz_mul_sch): Likewise. (_mm_mul_round_sch): Likewise. (_mm_mask_mul_round_sch): Likewise. (_mm_maskz_mul_round_sch): Likewise. (_mm_cmul_sch): Likewise. (_mm_mask_cmul_sch): Likewise. (_mm_maskz_cmul_sch): Likewise. (_mm_cmul_round_sch): Likewise. (_mm_mask_cmul_round_sch): Likewise. (_mm_maskz_cmul_round_sch): Likewise. * config/i386/avx512fp16vlintrin.h (_mm_mul_pch): Likewise. (_mm_mask_mul_pch): Likewise. (_mm_maskz_mul_pch): Likewise. (_mm256_mul_pch): Likewise. (_mm256_mask_mul_pch): Likewise. (_mm256_maskz_mul_pch): Likewise. (_mm_cmul_pch): Likewise. (_mm_mask_cmul_pch): Likewise. (_mm_maskz_cmul_pch): Likewise. (_mm256_cmul_pch): Likewise. (_mm256_mask_cmul_pch): Likewise. (_mm256_maskz_cmul_pch): Likewise. gcc/testsuite/ChangeLog: * gcc.target/i386/avx512fp16-vfcmulcph-1a.c: Add new test for alias. * gcc.target/i386/avx512fp16-vfcmulcsh-1a.c: Likewise. * gcc.target/i386/avx512fp16-vfmulcph-1a.c: Likewise. * gcc.target/i386/avx512fp16-vfmulcsh-1a.c: Likewise. * gcc.target/i386/avx512fp16vl-vfcmulcph-1a.c: Likewise. * gcc.target/i386/avx512fp16vl-vfmulcph-1a.c: Likewise.
This commit is contained in:
konglin1
liuhongt
parent
280d2838c1
commit
a72b7a455c
8 changed files with 136 additions and 36 deletions
|
|
@ -7162,6 +7162,45 @@ _mm512_set1_pch (_Float16 _Complex __A)
|
|||
return (__m512h) _mm512_set1_ps (u.b);
|
||||
}
|
||||
|
||||
// intrinsics below are alias for f*mul_*ch
|
||||
#define _mm512_mul_pch(A, B) _mm512_fmul_pch ((A), (B))
|
||||
#define _mm512_mask_mul_pch(W, U, A, B) \
|
||||
_mm512_mask_fmul_pch ((W), (U), (A), (B))
|
||||
#define _mm512_maskz_mul_pch(U, A, B) _mm512_maskz_fmul_pch ((U), (A), (B))
|
||||
#define _mm512_mul_round_pch(A, B, R) _mm512_fmul_round_pch ((A), (B), (R))
|
||||
#define _mm512_mask_mul_round_pch(W, U, A, B, R) \
|
||||
_mm512_mask_fmul_round_pch ((W), (U), (A), (B), (R))
|
||||
#define _mm512_maskz_mul_round_pch(U, A, B, R) \
|
||||
_mm512_maskz_fmul_round_pch ((U), (A), (B), (R))
|
||||
|
||||
#define _mm512_cmul_pch(A, B) _mm512_fcmul_pch ((A), (B))
|
||||
#define _mm512_mask_cmul_pch(W, U, A, B) \
|
||||
_mm512_mask_fcmul_pch ((W), (U), (A), (B))
|
||||
#define _mm512_maskz_cmul_pch(U, A, B) _mm512_maskz_fcmul_pch ((U), (A), (B))
|
||||
#define _mm512_cmul_round_pch(A, B, R) _mm512_fcmul_round_pch ((A), (B), (R))
|
||||
#define _mm512_mask_cmul_round_pch(W, U, A, B, R) \
|
||||
_mm512_mask_fcmul_round_pch ((W), (U), (A), (B), (R))
|
||||
#define _mm512_maskz_cmul_round_pch(U, A, B, R) \
|
||||
_mm512_maskz_fcmul_round_pch ((U), (A), (B), (R))
|
||||
|
||||
#define _mm_mul_sch(A, B) _mm_fmul_sch ((A), (B))
|
||||
#define _mm_mask_mul_sch(W, U, A, B) _mm_mask_fmul_sch ((W), (U), (A), (B))
|
||||
#define _mm_maskz_mul_sch(U, A, B) _mm_maskz_fmul_sch ((U), (A), (B))
|
||||
#define _mm_mul_round_sch(A, B, R) _mm_fmul_round_sch ((A), (B), (R))
|
||||
#define _mm_mask_mul_round_sch(W, U, A, B, R) \
|
||||
_mm_mask_fmul_round_sch ((W), (U), (A), (B), (R))
|
||||
#define _mm_maskz_mul_round_sch(U, A, B, R) \
|
||||
_mm_maskz_fmul_round_sch ((U), (A), (B), (R))
|
||||
|
||||
#define _mm_cmul_sch(A, B) _mm_fcmul_sch ((A), (B))
|
||||
#define _mm_mask_cmul_sch(W, U, A, B) _mm_mask_fcmul_sch ((W), (U), (A), (B))
|
||||
#define _mm_maskz_cmul_sch(U, A, B) _mm_maskz_fcmul_sch ((U), (A), (B))
|
||||
#define _mm_cmul_round_sch(A, B, R) _mm_fcmul_round_sch ((A), (B), (R))
|
||||
#define _mm_mask_cmul_round_sch(W, U, A, B, R) \
|
||||
_mm_mask_fcmul_round_sch ((W), (U), (A), (B), (R))
|
||||
#define _mm_maskz_cmul_round_sch(U, A, B, R) \
|
||||
_mm_maskz_fcmul_round_sch ((U), (A), (B), (R))
|
||||
|
||||
#ifdef __DISABLE_AVX512FP16__
|
||||
#undef __DISABLE_AVX512FP16__
|
||||
#pragma GCC pop_options
|
||||
|
|
|
|||
|
|
@ -3337,6 +3337,23 @@ _mm_set1_pch (_Float16 _Complex __A)
|
|||
return (__m128h) _mm_set1_ps (u.b);
|
||||
}
|
||||
|
||||
// intrinsics below are alias for f*mul_*ch
|
||||
#define _mm_mul_pch(A, B) _mm_fmul_pch ((A), (B))
|
||||
#define _mm_mask_mul_pch(W, U, A, B) _mm_mask_fmul_pch ((W), (U), (A), (B))
|
||||
#define _mm_maskz_mul_pch(U, A, B) _mm_maskz_fmul_pch ((U), (A), (B))
|
||||
#define _mm256_mul_pch(A, B) _mm256_fmul_pch ((A), (B))
|
||||
#define _mm256_mask_mul_pch(W, U, A, B) \
|
||||
_mm256_mask_fmul_pch ((W), (U), (A), (B))
|
||||
#define _mm256_maskz_mul_pch(U, A, B) _mm256_maskz_fmul_pch ((U), (A), (B))
|
||||
|
||||
#define _mm_cmul_pch(A, B) _mm_fcmul_pch ((A), (B))
|
||||
#define _mm_mask_cmul_pch(W, U, A, B) _mm_mask_fcmul_pch ((W), (U), (A), (B))
|
||||
#define _mm_maskz_cmul_pch(U, A, B) _mm_maskz_fcmul_pch ((U), (A), (B))
|
||||
#define _mm256_cmul_pch(A, B) _mm256_fcmul_pch ((A), (B))
|
||||
#define _mm256_mask_cmul_pch(W, U, A, B) \
|
||||
_mm256_mask_fcmul_pch ((W), (U), (A), (B))
|
||||
#define _mm256_maskz_cmul_pch(U, A, B) _mm256_maskz_fcmul_pch((U), (A), (B))
|
||||
|
||||
#ifdef __DISABLE_AVX512FP16VL__
|
||||
#undef __DISABLE_AVX512FP16VL__
|
||||
#pragma GCC pop_options
|
||||
|
|
|
|||
|
|
@ -1,11 +1,11 @@
|
|||
/* { dg-do compile } */
|
||||
/* { dg-options "-mavx512fp16 -O2" } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcph\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcph\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcph\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcph\[ \\t\]+\{rn-sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcph\[ \\t\]+\{rn-sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcph\[ \\t\]+\{rz-sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcph\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcph\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcph\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcph\[ \\t\]+\{rn-sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcph\[ \\t\]+\{rn-sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcph\[ \\t\]+\{rz-sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
|
||||
#include <immintrin.h>
|
||||
|
||||
|
|
@ -22,4 +22,11 @@ avx512f_test (void)
|
|||
res = _mm512_fcmul_round_pch (x1, x2, 8);
|
||||
res1 = _mm512_mask_fcmul_round_pch (res1, m16, x1, x2, 8);
|
||||
res2 = _mm512_maskz_fcmul_round_pch (m16, x1, x2, 11);
|
||||
|
||||
res = _mm512_cmul_pch (x1, x2);
|
||||
res1 = _mm512_mask_cmul_pch (res1, m16, x1, x2);
|
||||
res2 = _mm512_maskz_cmul_pch (m16, x1, x2);
|
||||
res = _mm512_cmul_round_pch (x1, x2, 8);
|
||||
res1 = _mm512_mask_cmul_round_pch (res1, m16, x1, x2, 8);
|
||||
res2 = _mm512_maskz_cmul_round_pch (m16, x1, x2, 11);
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,11 +1,11 @@
|
|||
/* { dg-do compile } */
|
||||
/* { dg-options "-mavx512fp16 -O2" } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcsh\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcsh\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcsh\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcsh\[ \\t\]+\{rn-sae\}\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcsh\[ \\t\]+\{rn-sae\}\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcsh\[ \\t\]+\{rz-sae\}\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcsh\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcsh\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcsh\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcsh\[ \\t\]+\{rn-sae\}\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcsh\[ \\t\]+\{rn-sae\}\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcsh\[ \\t\]+\{rz-sae\}\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
|
||||
#include <immintrin.h>
|
||||
|
||||
|
|
@ -22,4 +22,11 @@ avx512f_test (void)
|
|||
res = _mm_fcmul_round_sch (x1, x2, 8);
|
||||
res1 = _mm_mask_fcmul_round_sch (res1, m8, x1, x2, 8);
|
||||
res2 = _mm_maskz_fcmul_round_sch (m8, x1, x2, 11);
|
||||
|
||||
res = _mm_cmul_sch (x1, x2);
|
||||
res1 = _mm_mask_cmul_sch (res1, m8, x1, x2);
|
||||
res2 = _mm_maskz_cmul_sch (m8, x1, x2);
|
||||
res = _mm_cmul_round_sch (x1, x2, 8);
|
||||
res1 = _mm_mask_cmul_round_sch (res1, m8, x1, x2, 8);
|
||||
res2 = _mm_maskz_cmul_round_sch (m8, x1, x2, 11);
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,11 +1,11 @@
|
|||
/* { dg-do compile } */
|
||||
/* { dg-options "-mavx512fp16 -O2" } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcph\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcph\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcph\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcph\[ \\t\]+\{rn-sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcph\[ \\t\]+\{rn-sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcph\[ \\t\]+\{rz-sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcph\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcph\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcph\[ \\t\]+\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcph\[ \\t\]+\{rn-sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcph\[ \\t\]+\{rn-sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcph\[ \\t\]+\{rz-sae\}\[^\{\n\]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\[^\n\r]*%zmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
|
||||
#include <immintrin.h>
|
||||
|
||||
|
|
@ -22,4 +22,11 @@ avx512f_test (void)
|
|||
res = _mm512_fmul_round_pch (x1, x2, 8);
|
||||
res1 = _mm512_mask_fmul_round_pch (res1, m16, x1, x2, 8);
|
||||
res2 = _mm512_maskz_fmul_round_pch (m16, x1, x2, 11);
|
||||
|
||||
res = _mm512_mul_pch (x1, x2);
|
||||
res1 = _mm512_mask_mul_pch (res1, m16, x1, x2);
|
||||
res2 = _mm512_maskz_mul_pch (m16, x1, x2);
|
||||
res = _mm512_mul_round_pch (x1, x2, 8);
|
||||
res1 = _mm512_mask_mul_round_pch (res1, m16, x1, x2, 8);
|
||||
res2 = _mm512_maskz_mul_round_pch (m16, x1, x2, 11);
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,11 +1,11 @@
|
|||
/* { dg-do compile } */
|
||||
/* { dg-options "-mavx512fp16 -O2" } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcsh\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcsh\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcsh\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcsh\[ \\t\]+\{rn-sae\}\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcsh\[ \\t\]+\{rn-sae\}\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcsh\[ \\t\]+\{rz-sae\}\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcsh\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcsh\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\[^\{\n\r]*(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcsh\[ \\t\]+\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcsh\[ \\t\]+\{rn-sae\}\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcsh\[ \\t\]+\{rn-sae\}\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcsh\[ \\t\]+\{rz-sae\}\[^\{\n\]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
|
||||
#include <immintrin.h>
|
||||
|
||||
|
|
@ -22,4 +22,11 @@ avx512f_test (void)
|
|||
res = _mm_fmul_round_sch (x1, x2, 8);
|
||||
res1 = _mm_mask_fmul_round_sch (res1, m8, x1, x2, 8);
|
||||
res2 = _mm_maskz_fmul_round_sch (m8, x1, x2, 11);
|
||||
|
||||
res = _mm_mul_sch (x1, x2);
|
||||
res1 = _mm_mask_mul_sch (res1, m8, x1, x2);
|
||||
res2 = _mm_maskz_mul_sch (m8, x1, x2);
|
||||
res = _mm_mul_round_sch (x1, x2, 8);
|
||||
res1 = _mm_mask_mul_round_sch (res1, m8, x1, x2, 8);
|
||||
res2 = _mm_maskz_mul_round_sch (m8, x1, x2, 11);
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,11 +1,11 @@
|
|||
/* { dg-do compile } */
|
||||
/* { dg-options "-mavx512f -mavx512fp16 -mavx512vl -O2" } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcph\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcph\[ \\t\]+%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcph\[ \\t\]+%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcph\[ \\t\]+%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcph\[ \\t\]+%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcph\[ \\t\]+%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcph\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcph\[ \\t\]+%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcph\[ \\t\]+%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcph\[ \\t\]+%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcph\[ \\t\]+%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfcmulcph\[ \\t\]+%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
|
||||
#include <immintrin.h>
|
||||
|
||||
|
|
@ -25,4 +25,12 @@ avx512f_test (void)
|
|||
res2 = _mm_fcmul_pch (x4, x5);
|
||||
res2 = _mm_mask_fcmul_pch (res2, m8, x4, x5);
|
||||
res2 = _mm_maskz_fcmul_pch (m8, x4, x5);
|
||||
|
||||
res1 = _mm256_cmul_pch (x1, x2);
|
||||
res1 = _mm256_mask_cmul_pch (res1, m8, x1, x2);
|
||||
res1 = _mm256_maskz_cmul_pch (m8, x1, x2);
|
||||
|
||||
res2 = _mm_cmul_pch (x4, x5);
|
||||
res2 = _mm_mask_cmul_pch (res2, m8, x4, x5);
|
||||
res2 = _mm_maskz_cmul_pch (m8, x4, x5);
|
||||
}
|
||||
|
|
|
|||
|
|
@ -1,11 +1,11 @@
|
|||
/* { dg-do compile } */
|
||||
/* { dg-options "-mavx512f -mavx512fp16 -mavx512vl -O2" } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcph\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcph\[ \\t\]+%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcph\[ \\t\]+%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcph\[ \\t\]+%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcph\[ \\t\]+%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcph\[ \\t\]+%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 1 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcph\[ \\t\]+\[^\{\n\]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcph\[ \\t\]+%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcph\[ \\t\]+%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\[^\n\r]*%ymm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcph\[ \\t\]+%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcph\[ \\t\]+%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
/* { dg-final { scan-assembler-times "vfmulcph\[ \\t\]+%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\[^\n\r]*%xmm\[0-9\]+\{%k\[0-9\]\}\{z\}\[^\n\r]*(?:\n|\[ \\t\]+#)" 2 } } */
|
||||
|
||||
#include <immintrin.h>
|
||||
|
||||
|
|
@ -25,4 +25,12 @@ avx512f_test (void)
|
|||
res2 = _mm_fmul_pch (x4, x5);
|
||||
res2 = _mm_mask_fmul_pch (res2, m8, x4, x5);
|
||||
res2 = _mm_maskz_fmul_pch (m8, x4, x5);
|
||||
|
||||
res1 = _mm256_mul_pch (x1, x2);
|
||||
res1 = _mm256_mask_mul_pch (res1, m8, x1, x2);
|
||||
res1 = _mm256_maskz_mul_pch (m8, x1, x2);
|
||||
|
||||
res2 = _mm_mul_pch (x4, x5);
|
||||
res2 = _mm_mask_mul_pch (res2, m8, x4, x5);
|
||||
res2 = _mm_maskz_mul_pch (m8, x4, x5);
|
||||
}
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue