diff options
| author | Simon Pilgrim <llvm-dev@redking.me.uk> | 2024-07-03 12:21:31 +0100 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-07-03 12:21:31 +0100 |
| commit | 7de7f50fc9d76ced7a971a66abf59aab6f9e5be6 (patch) | |
| tree | 391d95a73b6fefa28e8ee2158f8d8b94dd4fbbc5 /clang/lib/CodeGen/CodeGenModule.cpp | |
| parent | 298e292a76289d93f7c1a80c26e354830c6080e4 (diff) | |
| download | llvm-7de7f50fc9d76ced7a971a66abf59aab6f9e5be6.zip llvm-7de7f50fc9d76ced7a971a66abf59aab6f9e5be6.tar.gz llvm-7de7f50fc9d76ced7a971a66abf59aab6f9e5be6.tar.bz2 | |
[InstCombine][X86] Fold blendv(x,y,shuffle(bitcast(sext(m)))) -> select(shuffle(m),x,y) (#96882)
We already handle blendv(x,y,bitcast(sext(m))) -> select(m,x,y) cases, but this adds support for peeking through one-use shuffles as well. VectorCombine should already have canonicalized the IR to shuffle(bitcast(...)) for us.
The particular use case is where we have split generic 256/512-bit code to use target-specific blendv intrinsics (e.g. AVX1 spoofing AVX2 256-bit ops).
Fixes #58895
Diffstat (limited to 'clang/lib/CodeGen/CodeGenModule.cpp')
0 files changed, 0 insertions, 0 deletions