diff options
| author | Simon Pilgrim <llvm-dev@redking.me.uk> | 2025-06-20 15:51:04 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-06-20 15:51:04 +0100 |
| commit | 95c6c11c747dee61133cff56f1a7ea7445c7ae79 (patch) | |
| tree | 9c872c7f1b014bbbe00001ab2ee2de8901684b46 /clang/lib/AST/ByteCode/Program.cpp | |
| parent | 20d57e77f6709ef32791391bc064d3ed5663272a (diff) | |
| download | llvm-95c6c11c747dee61133cff56f1a7ea7445c7ae79.zip llvm-95c6c11c747dee61133cff56f1a7ea7445c7ae79.tar.gz llvm-95c6c11c747dee61133cff56f1a7ea7445c7ae79.tar.bz2 | |
[X86] combineConcatVectorOps - only always concat logic ops on AVX512 targets (#145036)
We should only concat logic ops if at least one operand will freely
concatenate. We've now addressed the remaining regressions on AVX2
targets, but still have a number on AVX512 targets which can
aggressively use VPTERNLOG in many cases.
Diffstat (limited to 'clang/lib/AST/ByteCode/Program.cpp')
0 files changed, 0 insertions, 0 deletions