OpenE2K
/
gcc
2
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

Enable avx512 embedde broadcast for vpternlog. 

gcc/ChangeLog:

	PR target/101989
	* config/i386/sse.md (<avx512>_vternlog<mode><sd_maskz_name>):
	Enable avx512 embedded broadcast.
	(*<avx512>_vternlog<mode>_all): Ditto.
	(<avx512>_vternlog<mode>_mask): Ditto.

gcc/testsuite/ChangeLog:

	PR target/101989
	* gcc.target/i386/pr101989-broadcast-1.c: New test.
This commit is contained in:
liuhongt 2021-08-24 18:09:33 +08:00
parent 6ddb30f941
commit 8da9b4f73c
2 changed files with 34 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

6
gcc/config/i386/sse.md
View File

@ -10034,7 +10034,7 @@
(unspec:VI48_AVX512VL
[(match_operand:VI48_AVX512VL 1 "register_operand" "0")
(match_operand:VI48_AVX512VL 2 "register_operand" "v")
(match_operand:VI48_AVX512VL 3 "nonimmediate_operand" "vm")
(match_operand:VI48_AVX512VL 3 "bcst_vector_operand" "vmBr")
(match_operand:SI 4 "const_0_to_255_operand")]
UNSPEC_VTERNLOG))]
"TARGET_AVX512F"
@ -10048,7 +10048,7 @@
(unspec:V
[(match_operand:V 1 "register_operand" "0")
(match_operand:V 2 "register_operand" "v")
(match_operand:V 3 "nonimmediate_operand" "vm")
(match_operand:V 3 "bcst_vector_operand" "vmBr")
(match_operand:SI 4 "const_0_to_255_operand")]
UNSPEC_VTERNLOG))]
"TARGET_AVX512F"
@ -10281,7 +10281,7 @@
(unspec:VI48_AVX512VL
[(match_operand:VI48_AVX512VL 1 "register_operand" "0")
(match_operand:VI48_AVX512VL 2 "register_operand" "v")
(match_operand:VI48_AVX512VL 3 "nonimmediate_operand" "vm")
(match_operand:VI48_AVX512VL 3 "bcst_vector_operand" "vmBr")
(match_operand:SI 4 "const_0_to_255_operand")]
UNSPEC_VTERNLOG)
(match_dup 1)

31
gcc/testsuite/gcc.target/i386/pr101989-broadcast-1.c Normal file
View File

@ -0,0 +1,31 @@
/* { dg-do compile } */
/* { dg-options "-O2 -mavx512vl" } */
/* { dg-final { scan-assembler-times "vpternlog" 4 } } */
/* { dg-final { scan-assembler-times "\\\{1to4\\\}" 4 } } */
#include<immintrin.h>
extern long long C;
__m256d
copysign2_pd(__m256d from, __m256d to) {
__m256i a = _mm256_castpd_si256(from);
__m256d avx_signbit = _mm256_castsi256_pd(_mm256_slli_epi64(_mm256_cmpeq_epi64(a, a), 63));
/* (avx_signbit & from) | (~avx_signbit & to) */
return _mm256_or_pd(_mm256_and_pd(avx_signbit, from), _mm256_andnot_pd(avx_signbit, to));
}
__m256i
mask_pternlog (__m256i A, __m256i B, __mmask8 U)
{
return _mm256_mask_ternarylogic_epi64 (A, U, B, _mm256_set1_epi64x (C) ,202);
}
__m256i
maskz_pternlog (__m256i A, __m256i B, __mmask8 U)
{
return _mm256_maskz_ternarylogic_epi64 (U, A, B, _mm256_set1_epi64x (C) ,202);
}
__m256i
none_pternlog (__m256i A, __m256i B)
{
return _mm256_ternarylogic_epi64 (A, B, _mm256_set1_epi64x (C) ,202);
}