Generate vpblendd instead of vpblendw for V4SI under AVX2.

gcc/ChangeLog:

	* config/i386/i386-expand.cc (expand_vec_perm_blend): Generate
	vpblendd instead of vpblendw for V4SI under avx2.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/pr88828-0.c: Adjust testcase.
This commit is contained in:
liuhongt 2023-03-21 13:37:59 +08:00
parent 0090888656
commit 3588c8cbc1
2 changed files with 15 additions and 5 deletions

View file

@ -19069,10 +19069,20 @@ expand_vec_perm_blend (struct expand_vec_perm_d *d)
goto do_subreg;
case E_V4SImode:
for (i = 0; i < 4; ++i)
mask |= (d->perm[i] >= 4 ? 3 : 0) << (i * 2);
vmode = V8HImode;
goto do_subreg;
if (TARGET_AVX2)
{
/* Use vpblendd instead of vpblendw. */
for (i = 0; i < nelt; ++i)
mask |= ((unsigned HOST_WIDE_INT) (d->perm[i] >= nelt)) << i;
break;
}
else
{
for (i = 0; i < 4; ++i)
mask |= (d->perm[i] >= 4 ? 3 : 0) << (i * 2);
vmode = V8HImode;
goto do_subreg;
}
case E_V16QImode:
/* See if bytes move in pairs so we can use pblendw with

View file

@ -1,5 +1,5 @@
/* { dg-do compile } */
/* { dg-options "-O2 -msse4.2" } */
/* { dg-options "-O2 -msse4.2 -mno-avx2" } */
typedef int v4si __attribute__((vector_size(16)));
typedef float v4sf __attribute__((vector_size(16)));