FreeChainXenon/gcc
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

i386: Disable ix86_expand_vecop_qihi2 when !TARGET_AVX512BW

Browse source 
Since vpermq is really slow, we should avoid using it for permutation
when vpmovwb is not available (needs AVX512BW) for ix86_expand_vecop_qihi2
and fall back to ix86_expand_vecop_qihi.

gcc/ChangeLog:

	PR target/115069
	* config/i386/i386-expand.cc (ix86_expand_vecop_qihi2):
	Do not enable the optimization when AVX512BW is not enabled.

gcc/testsuite/ChangeLog:

	PR target/115069
	* gcc.target/i386/pr115069.c: New.
This commit is contained in:
Haochen Jiang 2024-05-21 14:10:43 +08:00
parent d2f4279516
commit 1ad5c9d524
2 changed files with 16 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

7
gcc/config/i386/i386-expand.cc
View file

@ -23963,6 +23963,13 @@ ix86_expand_vecop_qihi2 (enum rtx_code code, rtx dest, rtx op1, rtx op2)
bool op2vec = GET_MODE_CLASS (GET_MODE (op2)) == MODE_VECTOR_INT;
bool uns_p = code != ASHIFTRT;
/* Without VPMOVWB (provided by AVX512BW ISA), the expansion uses the
generic permutation to merge the data back into the right place. This
permutation results in VPERMQ, which is slow, so better fall back to
ix86_expand_vecop_qihi. */
if (!TARGET_AVX512BW)
return false;
if ((qimode == V16QImode && !TARGET_AVX2)
|| (qimode == V32QImode && (!TARGET_AVX512BW || !TARGET_EVEX512))
/* There are no V64HImode instructions. */

9
gcc/testsuite/gcc.target/i386/pr115069.c Normal file
View file

@ -0,0 +1,9 @@
/* { dg-do compile } */
/* { dg-options "-O2 -mavx2" } */
/* { dg-final { scan-assembler-not "vpermq" } } */
typedef char v16qi __attribute__((vector_size(16)));
v16qi foo (v16qi a, v16qi b) {
return a * b;
}