diff options
| author | Tim Gymnich <tim@gymni.ch> | 2024-06-14 22:53:30 +0200 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-06-14 22:53:30 +0200 |
| commit | 7091dd277a1e2349f33390be9f3ccf21bff39003 (patch) | |
| tree | bb1de7b3edf9fc71278b86f7b7064ecdde3e977b /llvm/lib/CodeGen/TargetLoweringBase.cpp | |
| parent | 2146d12eb9401d488ad916fc9227b5f24bcfa5c4 (diff) | |
| download | llvm-7091dd277a1e2349f33390be9f3ccf21bff39003.zip llvm-7091dd277a1e2349f33390be9f3ccf21bff39003.tar.gz llvm-7091dd277a1e2349f33390be9f3ccf21bff39003.tar.bz2 | |
[AMDGPU] Fix lowering of abs for i16 vectors with more than 2 elements (#95413)
fixes #94606
Expansion of `ABS` for `i16` vectors with more than 2 elements is
currently falling back to scalarization of the vector.
This PR adds a custom lowering for `ABS` on `i16` vectors that splits
the vector into multiple `<2 x i 16>` vectors.
Diffstat (limited to 'llvm/lib/CodeGen/TargetLoweringBase.cpp')
0 files changed, 0 insertions, 0 deletions