diff options
author | liuhongt <hongtao.liu@intel.com> | 2023-03-21 13:37:59 +0800 |
---|---|---|
committer | liuhongt <hongtao.liu@intel.com> | 2023-03-30 09:20:12 +0800 |
commit | 3588c8cbc1003d004c3ce5ff96af67aa95c073e9 (patch) | |
tree | 0a32cbc119b45dae6136ce79d2ad56af4684dbba /gcc | |
parent | 009088865692bb3999805873933be155592d484b (diff) | |
download | gcc-3588c8cbc1003d004c3ce5ff96af67aa95c073e9.zip gcc-3588c8cbc1003d004c3ce5ff96af67aa95c073e9.tar.gz gcc-3588c8cbc1003d004c3ce5ff96af67aa95c073e9.tar.bz2 |
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.
Diffstat (limited to 'gcc')
-rw-r--r-- | gcc/config/i386/i386-expand.cc | 18 | ||||
-rw-r--r-- | gcc/testsuite/gcc.target/i386/pr88828-0.c | 2 |
2 files changed, 15 insertions, 5 deletions
diff --git a/gcc/config/i386/i386-expand.cc b/gcc/config/i386/i386-expand.cc index 1e3ce4b..76dbb3b 100644 --- a/gcc/config/i386/i386-expand.cc +++ b/gcc/config/i386/i386-expand.cc @@ -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 diff --git a/gcc/testsuite/gcc.target/i386/pr88828-0.c b/gcc/testsuite/gcc.target/i386/pr88828-0.c index 3ddb2d1..441c441 100644 --- a/gcc/testsuite/gcc.target/i386/pr88828-0.c +++ b/gcc/testsuite/gcc.target/i386/pr88828-0.c @@ -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))); |