diff options
| author | Jan Beulich <jbeulich@suse.com> | 2023-07-12 12:14:08 +0200 |
|---|---|---|
| committer | Jan Beulich <jbeulich@suse.com> | 2023-07-12 12:14:08 +0200 |
| commit | 28cdba24a9b8405d9f4ec2591c53d23a8bb74051 (patch) | |
| tree | c90e5f5e9a9d2bcaea4877097399bca216a6e708 /gcc/tree-ssa-loop-ch.cc | |
| parent | 96d32c111e63b7cde38410f4e316512771c8ecff (diff) | |
| download | gcc-28cdba24a9b8405d9f4ec2591c53d23a8bb74051.zip gcc-28cdba24a9b8405d9f4ec2591c53d23a8bb74051.tar.gz gcc-28cdba24a9b8405d9f4ec2591c53d23a8bb74051.tar.bz2 | |
x86: make better use of VBROADCASTSS / VPBROADCASTD
... in vec_dupv4sf / *vec_dupv4si. The respective broadcast insns are
never longer (yet sometimes shorter) than the corresponding VSHUFPS /
VPSHUFD, due to the immediate operand of the shuffle insns balancing the
(uniform) need for VEX3 in the broadcast ones. When EVEX encoding is
respective the broadcast insns are always shorter.
Add new alternatives to cover the AVX2 and AVX512 cases as appropriate.
While touching this anyway, switch to consistently using "sseshuf1" in
the "type" attributes for all shuffle forms.
gcc/
* config/i386/sse.md (vec_dupv4sf): Make first alternative use
vbroadcastss for AVX2. New AVX512F alternative.
(*vec_dupv4si): New AVX2 and AVX512F alternatives using
vpbroadcastd. Replace sselog1 by sseshuf1 in "type" attribute.
gcc/testsuite/
* gcc.target/i386/avx2-dupv4sf.c: New test.
* gcc.target/i386/avx2-dupv4si.c: Likewise.
* gcc.target/i386/avx512f-dupv4sf.c: Likewise.
* gcc.target/i386/avx512f-dupv4si.c: Likewise.
Diffstat (limited to 'gcc/tree-ssa-loop-ch.cc')
0 files changed, 0 insertions, 0 deletions