mirror of git://gcc.gnu.org/git/gcc.git
i386: Enable AVX512 memory broadcast for FP add
Many AVX512 vector operations can broadcast from a scalar memory source. This patch enables memory broadcast for FP add operations. gcc/ PR target/72782 * config/i386/sse.md (*<plusminus_insn><mode>3<mask_name>_bcst_1): New. (*add<mode>3<mask_name>_bcst_2): Likewise. gcc/testsuite/ PR target/72782 * gcc.target/i386/avx512-binop-1.h: New file. * gcc.target/i386/avx512-binop-2.h: Likewise. * gcc.target/i386/avx512-binop-3.h: Likewise. * gcc.target/i386/avx512-binop-4.h: Likewise. * gcc.target/i386/avx512-binop-5.h: Likewise. * gcc.target/i386/avx512-binop-6.h: Likewise. * gcc.target/i386/avx512f-add-df-zmm-1.c: Likewise. * gcc.target/i386/avx512f-add-sf-zmm-1.c: Likewise. * gcc.target/i386/avx512f-add-sf-zmm-2.c: Likewise. * gcc.target/i386/avx512f-add-sf-zmm-3.c: Likewise. * gcc.target/i386/avx512f-add-sf-zmm-4.c: Likewise. * gcc.target/i386/avx512f-add-sf-zmm-5.c: Likewise. * gcc.target/i386/avx512f-add-sf-zmm-6.c: Likewise. * gcc.target/i386/avx512f-sub-df-zmm-1.c: Likewise. * gcc.target/i386/avx512f-sub-sf-zmm-1.c: Likewise. * gcc.target/i386/avx512f-sub-sf-zmm-2.c: Likewise. * gcc.target/i386/avx512f-sub-sf-zmm-3.c: Likewise. * gcc.target/i386/avx512f-sub-sf-zmm-4.c: Likewise. * gcc.target/i386/avx512f-sub-sf-zmm-5.c: Likewise. * gcc.target/i386/avx512vl-add-sf-xmm-1.c: Likewise. * gcc.target/i386/avx512vl-add-sf-ymm-1.c: Likewise. * gcc.target/i386/avx512vl-sub-sf-xmm-1.c: Likewise. * gcc.target/i386/avx512vl-sub-sf-ymm-1.c: Likewise. From-SVN: r265311
This commit is contained in:
H.J. Lu
H.J. Lu
parent
3b1778b7c3
commit
13e29c3648
|
|
@ -1,3 +1,10 @@
|
||||||
|
2018-10-19 H.J. Lu <hongjiu.lu@intel.com>
|
||||||
|
|
||||||
|
PR target/72782
|
||||||
|
* config/i386/sse.md
|
||||||
|
(*<plusminus_insn><mode>3<mask_name>_bcst_1): New.
|
||||||
|
(*add<mode>3<mask_name>_bcst_2): Likewise.
|
||||||
|
|
||||||
2018-10-19 H.J. Lu <hongjiu.lu@intel.com>
|
2018-10-19 H.J. Lu <hongjiu.lu@intel.com>
|
||||||
|
|
||||||
* config/i386/sse.md
|
* config/i386/sse.md
|
||||||
|
|
|
||||||
|
|
@ -1684,6 +1684,34 @@
|
||||||
(set_attr "prefix" "<mask_prefix3>")
|
(set_attr "prefix" "<mask_prefix3>")
|
||||||
(set_attr "mode" "<MODE>")])
|
(set_attr "mode" "<MODE>")])
|
||||||
|
|
||||||
|
(define_insn "*<plusminus_insn><mode>3<mask_name>_bcst_1"
|
||||||
|
[(set (match_operand:VF_AVX512 0 "register_operand" "=v")
|
||||||
|
(plusminus:VF_AVX512
|
||||||
|
(match_operand:VF_AVX512 1 "register_operand" "v")
|
||||||
|
(vec_duplicate:VF_AVX512
|
||||||
|
(match_operand:<ssescalarmode> 2 "memory_operand" "m"))))]
|
||||||
|
"TARGET_AVX512F
|
||||||
|
&& ix86_binary_operator_ok (<CODE>, <MODE>mode, operands)
|
||||||
|
&& <mask_mode512bit_condition>"
|
||||||
|
"v<plusminus_mnemonic><ssemodesuffix>\t{%2<avx512bcst>, %1, %0<mask_operand3>|%0<mask_operand3>, %1, %2<avx512bcst>}"
|
||||||
|
[(set_attr "prefix" "evex")
|
||||||
|
(set_attr "type" "sseadd")
|
||||||
|
(set_attr "mode" "<MODE>")])
|
||||||
|
|
||||||
|
(define_insn "*add<mode>3<mask_name>_bcst_2"
|
||||||
|
[(set (match_operand:VF_AVX512 0 "register_operand" "=v")
|
||||||
|
(plus:VF_AVX512
|
||||||
|
(vec_duplicate:VF_AVX512
|
||||||
|
(match_operand:<ssescalarmode> 1 "memory_operand" "m"))
|
||||||
|
(match_operand:VF_AVX512 2 "register_operand" "v")))]
|
||||||
|
"TARGET_AVX512F
|
||||||
|
&& ix86_binary_operator_ok (PLUS, <MODE>mode, operands)
|
||||||
|
&& <mask_mode512bit_condition>"
|
||||||
|
"vadd<ssemodesuffix>\t{%1<avx512bcst>, %2, %0<mask_operand3>|%0<mask_operand3>, %2, %1<avx512bcst>}"
|
||||||
|
[(set_attr "prefix" "evex")
|
||||||
|
(set_attr "type" "sseadd")
|
||||||
|
(set_attr "mode" "<MODE>")])
|
||||||
|
|
||||||
(define_insn "<sse>_vm<plusminus_insn><mode>3<mask_scalar_name><round_scalar_name>"
|
(define_insn "<sse>_vm<plusminus_insn><mode>3<mask_scalar_name><round_scalar_name>"
|
||||||
[(set (match_operand:VF_128 0 "register_operand" "=x,v")
|
[(set (match_operand:VF_128 0 "register_operand" "=x,v")
|
||||||
(vec_merge:VF_128
|
(vec_merge:VF_128
|
||||||
|
|
|
||||||
|
|
@ -1,3 +1,30 @@
|
||||||
|
2018-10-19 H.J. Lu <hongjiu.lu@intel.com>
|
||||||
|
|
||||||
|
PR target/72782
|
||||||
|
* gcc.target/i386/avx512-binop-1.h: New file.
|
||||||
|
* gcc.target/i386/avx512-binop-2.h: Likewise.
|
||||||
|
* gcc.target/i386/avx512-binop-3.h: Likewise.
|
||||||
|
* gcc.target/i386/avx512-binop-4.h: Likewise.
|
||||||
|
* gcc.target/i386/avx512-binop-5.h: Likewise.
|
||||||
|
* gcc.target/i386/avx512-binop-6.h: Likewise.
|
||||||
|
* gcc.target/i386/avx512f-add-df-zmm-1.c: Likewise.
|
||||||
|
* gcc.target/i386/avx512f-add-sf-zmm-1.c: Likewise.
|
||||||
|
* gcc.target/i386/avx512f-add-sf-zmm-2.c: Likewise.
|
||||||
|
* gcc.target/i386/avx512f-add-sf-zmm-3.c: Likewise.
|
||||||
|
* gcc.target/i386/avx512f-add-sf-zmm-4.c: Likewise.
|
||||||
|
* gcc.target/i386/avx512f-add-sf-zmm-5.c: Likewise.
|
||||||
|
* gcc.target/i386/avx512f-add-sf-zmm-6.c: Likewise.
|
||||||
|
* gcc.target/i386/avx512f-sub-df-zmm-1.c: Likewise.
|
||||||
|
* gcc.target/i386/avx512f-sub-sf-zmm-1.c: Likewise.
|
||||||
|
* gcc.target/i386/avx512f-sub-sf-zmm-2.c: Likewise.
|
||||||
|
* gcc.target/i386/avx512f-sub-sf-zmm-3.c: Likewise.
|
||||||
|
* gcc.target/i386/avx512f-sub-sf-zmm-4.c: Likewise.
|
||||||
|
* gcc.target/i386/avx512f-sub-sf-zmm-5.c: Likewise.
|
||||||
|
* gcc.target/i386/avx512vl-add-sf-xmm-1.c: Likewise.
|
||||||
|
* gcc.target/i386/avx512vl-add-sf-ymm-1.c: Likewise.
|
||||||
|
* gcc.target/i386/avx512vl-sub-sf-xmm-1.c: Likewise.
|
||||||
|
* gcc.target/i386/avx512vl-sub-sf-ymm-1.c: Likewise.
|
||||||
|
|
||||||
2018-10-19 Ilya Leoshkevich <iii@linux.ibm.com>
|
2018-10-19 Ilya Leoshkevich <iii@linux.ibm.com>
|
||||||
|
|
||||||
PR rtl-optimization/87596
|
PR rtl-optimization/87596
|
||||||
|
|
|
||||||
|
|
@ -0,0 +1,12 @@
|
||||||
|
#include <immintrin.h>
|
||||||
|
|
||||||
|
#define PASTER2(x,y) x##y
|
||||||
|
#define PASTER3(x,y,z) _mm##x##_##y##_##z
|
||||||
|
#define OP(vec, op, suffix) PASTER3 (vec, op, suffix)
|
||||||
|
#define DUP(vec, suffix, val) PASTER3 (vec, set1, suffix) (val)
|
||||||
|
|
||||||
|
type
|
||||||
|
foo (type x, SCALAR *f)
|
||||||
|
{
|
||||||
|
return OP (vec, op, suffix) (x , DUP (vec, suffix, *f));
|
||||||
|
}
|
||||||
|
|
@ -0,0 +1,12 @@
|
||||||
|
#include <immintrin.h>
|
||||||
|
|
||||||
|
#define PASTER2(x,y) x##y
|
||||||
|
#define PASTER3(x,y,z) _mm##x##_##y##_##z
|
||||||
|
#define OP(vec, op, suffix) PASTER3 (vec, op, suffix)
|
||||||
|
#define DUP(vec, suffix, val) PASTER3 (vec, set1, suffix) (val)
|
||||||
|
|
||||||
|
type
|
||||||
|
foo (type x, SCALAR *f)
|
||||||
|
{
|
||||||
|
return OP (vec, op, suffix) (DUP (vec, suffix, *f), x);
|
||||||
|
}
|
||||||
|
|
@ -0,0 +1,15 @@
|
||||||
|
#include <immintrin.h>
|
||||||
|
|
||||||
|
#define PASTER2(x,y) x##y
|
||||||
|
#define PASTER3(x,y,z) _mm##x##_##y##_##z
|
||||||
|
#define OP(vec, op, suffix) PASTER3 (vec, op, suffix)
|
||||||
|
#define DUP(vec, suffix, val) PASTER3 (vec, set1, suffix) (val)
|
||||||
|
|
||||||
|
extern SCALAR bar (void);
|
||||||
|
|
||||||
|
type
|
||||||
|
foo (type x)
|
||||||
|
{
|
||||||
|
SCALAR f = bar ();
|
||||||
|
return OP (vec, op, suffix) (DUP (vec, suffix, f), x);
|
||||||
|
}
|
||||||
|
|
@ -0,0 +1,12 @@
|
||||||
|
#include <immintrin.h>
|
||||||
|
|
||||||
|
#define PASTER2(x,y) x##y
|
||||||
|
#define PASTER3(x,y,z) _mm##x##_##y##_##z
|
||||||
|
#define OP(vec, op, suffix) PASTER3 (vec, op, suffix)
|
||||||
|
#define DUP(vec, suffix, val) PASTER3 (vec, set1, suffix) (val)
|
||||||
|
|
||||||
|
type
|
||||||
|
foo (type x, SCALAR f)
|
||||||
|
{
|
||||||
|
return OP (vec, op, suffix) (DUP (vec, suffix, f), x);
|
||||||
|
}
|
||||||
|
|
@ -0,0 +1,14 @@
|
||||||
|
#include <immintrin.h>
|
||||||
|
|
||||||
|
#define PASTER2(x,y) x##y
|
||||||
|
#define PASTER3(x,y,z) _mm##x##_##y##_##z
|
||||||
|
#define OP(vec, op, suffix) PASTER3 (vec, op, suffix)
|
||||||
|
#define DUP(vec, suffix, val) PASTER3 (vec, set1, suffix) (val)
|
||||||
|
|
||||||
|
extern SCALAR f;
|
||||||
|
|
||||||
|
type
|
||||||
|
foo (type x)
|
||||||
|
{
|
||||||
|
return OP (vec, op, suffix) (x , DUP (vec, suffix, f));
|
||||||
|
}
|
||||||
|
|
@ -0,0 +1,14 @@
|
||||||
|
#include <immintrin.h>
|
||||||
|
|
||||||
|
#define PASTER2(x,y) x##y
|
||||||
|
#define PASTER3(x,y,z) _mm##x##_##y##_##z
|
||||||
|
#define OP(vec, op, suffix) PASTER3 (vec, op, suffix)
|
||||||
|
#define DUP(vec, suffix, val) PASTER3 (vec, set1, suffix) (val)
|
||||||
|
|
||||||
|
extern SCALAR f;
|
||||||
|
|
||||||
|
type
|
||||||
|
foo (type x)
|
||||||
|
{
|
||||||
|
return OP (vec, op, suffix) (DUP (vec, suffix, f), x);
|
||||||
|
}
|
||||||
|
|
@ -0,0 +1,12 @@
|
||||||
|
/* { dg-do compile } */
|
||||||
|
/* { dg-options "-mavx512f -O2" } */
|
||||||
|
/* { dg-final { scan-assembler-times "vaddpd\[ \\t\]+\\(%(?:eax|rdi|edi)\\)\\\{1to\[1-8\]+\\\}, %zmm\[0-9\]+, %zmm0" 1 } } */
|
||||||
|
/* { dg-final { scan-assembler-not "vbroadcastsd\[^\n\]*%zmm\[0-9\]+" } } */
|
||||||
|
|
||||||
|
#define type __m512d
|
||||||
|
#define vec 512
|
||||||
|
#define op add
|
||||||
|
#define suffix pd
|
||||||
|
#define SCALAR double
|
||||||
|
|
||||||
|
#include "avx512-binop-1.h"
|
||||||
|
|
@ -0,0 +1,12 @@
|
||||||
|
/* { dg-do compile } */
|
||||||
|
/* { dg-options "-mavx512f -O2" } */
|
||||||
|
/* { dg-final { scan-assembler-times "vaddps\[ \\t\]+\\(%(?:eax|rdi|edi)\\)\\\{1to\[1-8\]+\\\}, %zmm\[0-9\]+, %zmm0" 1 } } */
|
||||||
|
/* { dg-final { scan-assembler-not "vbroadcastss\[^\n\]*%zmm\[0-9\]+" } } */
|
||||||
|
|
||||||
|
#define type __m512
|
||||||
|
#define vec 512
|
||||||
|
#define op add
|
||||||
|
#define suffix ps
|
||||||
|
#define SCALAR float
|
||||||
|
|
||||||
|
#include "avx512-binop-1.h"
|
||||||
|
|
@ -0,0 +1,12 @@
|
||||||
|
/* { dg-do compile } */
|
||||||
|
/* { dg-options "-mavx512f -O2" } */
|
||||||
|
/* { dg-final { scan-assembler-times "vaddps\[ \\t\]+\\(%(?:eax|rdi|edi)\\)\\\{1to\[1-8\]+\\\}, %zmm\[0-9\]+, %zmm0" 1 } } */
|
||||||
|
/* { dg-final { scan-assembler-not "vbroadcastss\[^\n\]*%zmm\[0-9\]+" } } */
|
||||||
|
|
||||||
|
#define type __m512
|
||||||
|
#define vec 512
|
||||||
|
#define op add
|
||||||
|
#define suffix ps
|
||||||
|
#define SCALAR float
|
||||||
|
|
||||||
|
#include "avx512-binop-2.h"
|
||||||
|
|
@ -0,0 +1,12 @@
|
||||||
|
/* { dg-do compile } */
|
||||||
|
/* { dg-options "-mavx512f -O2" } */
|
||||||
|
/* { dg-final { scan-assembler-times "vbroadcastss\[^\n\]*%zmm\[0-9\]+" 1 } } */
|
||||||
|
/* { dg-final { scan-assembler-times "vaddps\[^\n\]*%zmm\[0-9\]+" 1 } } */
|
||||||
|
|
||||||
|
#define type __m512
|
||||||
|
#define vec 512
|
||||||
|
#define op add
|
||||||
|
#define suffix ps
|
||||||
|
#define SCALAR float
|
||||||
|
|
||||||
|
#include "avx512-binop-3.h"
|
||||||
|
|
@ -0,0 +1,12 @@
|
||||||
|
/* { dg-do compile { target { ! ia32 } } } */
|
||||||
|
/* { dg-options "-mavx512f -O2" } */
|
||||||
|
/* { dg-final { scan-assembler-times "vbroadcastss\[^\n\]*%zmm\[0-9\]+" 1 } } */
|
||||||
|
/* { dg-final { scan-assembler-times "vaddps\[ \\t\]+%zmm\[0-9\]+, %zmm\[0-9\]+, %zmm0" 1 } } */
|
||||||
|
|
||||||
|
#define type __m512
|
||||||
|
#define vec 512
|
||||||
|
#define op add
|
||||||
|
#define suffix ps
|
||||||
|
#define SCALAR float
|
||||||
|
|
||||||
|
#include "avx512-binop-4.h"
|
||||||
|
|
@ -0,0 +1,12 @@
|
||||||
|
/* { dg-do compile } */
|
||||||
|
/* { dg-options "-mavx512f -O2" } */
|
||||||
|
/* { dg-final { scan-assembler-times "vaddps\[ \\t\]+\[^\n\]*\\\{1to\[1-8\]+\\\}, %zmm\[0-9\]+, %zmm0" 1 } } */
|
||||||
|
/* { dg-final { scan-assembler-not "vbroadcastss\[^\n\]*%zmm\[0-9\]+" } } */
|
||||||
|
|
||||||
|
#define type __m512
|
||||||
|
#define vec 512
|
||||||
|
#define op add
|
||||||
|
#define suffix ps
|
||||||
|
#define SCALAR float
|
||||||
|
|
||||||
|
#include "avx512-binop-5.h"
|
||||||
|
|
@ -0,0 +1,12 @@
|
||||||
|
/* { dg-do compile } */
|
||||||
|
/* { dg-options "-mavx512f -O2" } */
|
||||||
|
/* { dg-final { scan-assembler-times "vaddps\[ \\t\]+\[^\n\]*\\\{1to\[1-8\]+\\\}, %zmm\[0-9\]+, %zmm0" 1 } } */
|
||||||
|
/* { dg-final { scan-assembler-not "vbroadcastss\[^\n\]*%zmm\[0-9\]+" } } */
|
||||||
|
|
||||||
|
#define type __m512
|
||||||
|
#define vec 512
|
||||||
|
#define op add
|
||||||
|
#define suffix ps
|
||||||
|
#define SCALAR float
|
||||||
|
|
||||||
|
#include "avx512-binop-6.h"
|
||||||
|
|
@ -0,0 +1,12 @@
|
||||||
|
/* { dg-do compile } */
|
||||||
|
/* { dg-options "-mavx512f -O2" } */
|
||||||
|
/* { dg-final { scan-assembler-times "vsubpd\[ \\t\]+\\(%(?:eax|rdi|edi)\\)\\\{1to\[1-8\]+\\\}, %zmm\[0-9\]+, %zmm0" 1 } } */
|
||||||
|
/* { dg-final { scan-assembler-not "vbroadcastsd\[^\n\]*%zmm\[0-9\]+" } } */
|
||||||
|
|
||||||
|
#define type __m512d
|
||||||
|
#define vec 512
|
||||||
|
#define op sub
|
||||||
|
#define suffix pd
|
||||||
|
#define SCALAR double
|
||||||
|
|
||||||
|
#include "avx512-binop-1.h"
|
||||||
|
|
@ -0,0 +1,12 @@
|
||||||
|
/* { dg-do compile } */
|
||||||
|
/* { dg-options "-mavx512f -O2" } */
|
||||||
|
/* { dg-final { scan-assembler-times "vsubps\[ \\t\]+\\(%(?:eax|rdi|edi)\\)\\\{1to\[1-8\]+\\\}, %zmm\[0-9\]+, %zmm0" 1 } } */
|
||||||
|
/* { dg-final { scan-assembler-not "vbroadcastss\[^\n\]*%zmm\[0-9\]+" } } */
|
||||||
|
|
||||||
|
#define type __m512
|
||||||
|
#define vec 512
|
||||||
|
#define op sub
|
||||||
|
#define suffix ps
|
||||||
|
#define SCALAR float
|
||||||
|
|
||||||
|
#include "avx512-binop-1.h"
|
||||||
|
|
@ -0,0 +1,12 @@
|
||||||
|
/* { dg-do compile } */
|
||||||
|
/* { dg-options "-mavx512f -O2" } */
|
||||||
|
/* { dg-final { scan-assembler-times "vbroadcastss\[^\n\]*%zmm\[0-9\]+" 1 } } */
|
||||||
|
/* { dg-final { scan-assembler-times "vsubps\[^\n\]*%zmm\[0-9\]+" 1 } } */
|
||||||
|
|
||||||
|
#define type __m512
|
||||||
|
#define vec 512
|
||||||
|
#define op sub
|
||||||
|
#define suffix ps
|
||||||
|
#define SCALAR float
|
||||||
|
|
||||||
|
#include "avx512-binop-2.h"
|
||||||
|
|
@ -0,0 +1,12 @@
|
||||||
|
/* { dg-do compile } */
|
||||||
|
/* { dg-options "-mavx512f -O2" } */
|
||||||
|
/* { dg-final { scan-assembler-times "vbroadcastss\[^\n\]*%zmm\[0-9\]+" 1 } } */
|
||||||
|
/* { dg-final { scan-assembler-times "vsubps\[^\n\]*%zmm\[0-9\]+" 1 } } */
|
||||||
|
|
||||||
|
#define type __m512
|
||||||
|
#define vec 512
|
||||||
|
#define op sub
|
||||||
|
#define suffix ps
|
||||||
|
#define SCALAR float
|
||||||
|
|
||||||
|
#include "avx512-binop-3.h"
|
||||||
|
|
@ -0,0 +1,12 @@
|
||||||
|
/* { dg-do compile { target { ! ia32 } } } */
|
||||||
|
/* { dg-options "-mavx512f -O2" } */
|
||||||
|
/* { dg-final { scan-assembler-times "vbroadcastss\[^\n\]*%zmm\[0-9\]+" 1 } } */
|
||||||
|
/* { dg-final { scan-assembler-times "vsubps\[ \\t\]+%zmm\[0-9\]+, %zmm\[0-9\]+, %zmm0" 1 } } */
|
||||||
|
|
||||||
|
#define type __m512
|
||||||
|
#define vec 512
|
||||||
|
#define op sub
|
||||||
|
#define suffix ps
|
||||||
|
#define SCALAR float
|
||||||
|
|
||||||
|
#include "avx512-binop-4.h"
|
||||||
|
|
@ -0,0 +1,12 @@
|
||||||
|
/* { dg-do compile } */
|
||||||
|
/* { dg-options "-mavx512f -O2" } */
|
||||||
|
/* { dg-final { scan-assembler-times "vbroadcastss\[^\n\]*%zmm\[0-9\]+" 1 } } */
|
||||||
|
/* { dg-final { scan-assembler-times "vsubps\[^\n\]*%zmm\[0-9\]+" 1 } } */
|
||||||
|
|
||||||
|
#define type __m512
|
||||||
|
#define vec 512
|
||||||
|
#define op sub
|
||||||
|
#define suffix ps
|
||||||
|
#define SCALAR float
|
||||||
|
|
||||||
|
#include "avx512-binop-6.h"
|
||||||
|
|
@ -0,0 +1,12 @@
|
||||||
|
/* { dg-do compile } */
|
||||||
|
/* { dg-options "-mfma -mavx512vl -O2" } */
|
||||||
|
/* { dg-final { scan-assembler-times "vaddps\[ \\t\]+\\(%(?:eax|rdi|edi)\\)\\\{1to\[1-8\]+\\\}, %xmm\[0-9\]+, %xmm0" 1 } } */
|
||||||
|
/* { dg-final { scan-assembler-not "vbroadcastss\[^\n\]*%xmm\[0-9\]+" } } */
|
||||||
|
|
||||||
|
#define type __m128
|
||||||
|
#define vec
|
||||||
|
#define op add
|
||||||
|
#define suffix ps
|
||||||
|
#define SCALAR float
|
||||||
|
|
||||||
|
#include "avx512-binop-1.h"
|
||||||
|
|
@ -0,0 +1,12 @@
|
||||||
|
/* { dg-do compile } */
|
||||||
|
/* { dg-options "-mfma -mavx512vl -O2" } */
|
||||||
|
/* { dg-final { scan-assembler-times "vaddps\[ \\t\]+\\(%(?:eax|rdi|edi)\\)\\\{1to\[1-8\]+\\\}, %ymm\[0-9\]+, %ymm0" 1 } } */
|
||||||
|
/* { dg-final { scan-assembler-not "vbroadcastss\[^\n\]*%ymm\[0-9\]+" } } */
|
||||||
|
|
||||||
|
#define type __m256
|
||||||
|
#define vec 256
|
||||||
|
#define op add
|
||||||
|
#define suffix ps
|
||||||
|
#define SCALAR float
|
||||||
|
|
||||||
|
#include "avx512-binop-1.h"
|
||||||
|
|
@ -0,0 +1,12 @@
|
||||||
|
/* { dg-do compile } */
|
||||||
|
/* { dg-options "-mfma -mavx512vl -O2" } */
|
||||||
|
/* { dg-final { scan-assembler-times "vsubps\[ \\t\]+\\(%(?:eax|rdi|edi)\\)\\\{1to\[1-8\]+\\\}, %xmm\[0-9\]+, %xmm0" 1 } } */
|
||||||
|
/* { dg-final { scan-assembler-not "vbroadcastss\[^\n\]*%xmm\[0-9\]+" } } */
|
||||||
|
|
||||||
|
#define type __m128
|
||||||
|
#define vec
|
||||||
|
#define op sub
|
||||||
|
#define suffix ps
|
||||||
|
#define SCALAR float
|
||||||
|
|
||||||
|
#include "avx512-binop-1.h"
|
||||||
|
|
@ -0,0 +1,12 @@
|
||||||
|
/* { dg-do compile } */
|
||||||
|
/* { dg-options "-mfma -mavx512vl -O2" } */
|
||||||
|
/* { dg-final { scan-assembler-times "vsubps\[ \\t\]+\\(%(?:eax|rdi|edi)\\)\\\{1to\[1-8\]+\\\}, %ymm\[0-9\]+, %ymm0" 1 } } */
|
||||||
|
/* { dg-final { scan-assembler-not "vbroadcastss\[^\n\]*%ymm\[0-9\]+" } } */
|
||||||
|
|
||||||
|
#define type __m256
|
||||||
|
#define vec 256
|
||||||
|
#define op sub
|
||||||
|
#define suffix ps
|
||||||
|
#define SCALAR float
|
||||||
|
|
||||||
|
#include "avx512-binop-1.h"
|
||||||
Loading…
Reference in New Issue