diff options
| author | Zhuoran Yin <zhuoryin@amd.com> | 2025-07-02 13:24:44 -0400 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-07-02 18:24:44 +0100 |
| commit | 6a97b56ce5c5b189223da1a6961912d1de40829e (patch) | |
| tree | ab0e491aa7f2e8a011798887046d74ed148479a3 /clang/lib/Frontend/CompilerInvocation.cpp | |
| parent | dfcef35ff1d30d112362645ec2cd0d5e99952b0f (diff) | |
| download | llvm-6a97b56ce5c5b189223da1a6961912d1de40829e.zip llvm-6a97b56ce5c5b189223da1a6961912d1de40829e.tar.gz llvm-6a97b56ce5c5b189223da1a6961912d1de40829e.tar.bz2 | |
[MLIR][AMDGPU] Redirect transfer read to masked load lowering (#146705)
This PR reworks https://github.com/llvm/llvm-project/pull/131803.
Instead of applying the optimization on transfer_read op, which is too
high level, it redirect the pre-existing pattern onto maskedload op.
This simplified the implementation of the lowering pattern. This also
allows moving the usage of the pass to a target dependent pipeline.
Signed-off-by: jerryyin <zhuoryin@amd.com>
Diffstat (limited to 'clang/lib/Frontend/CompilerInvocation.cpp')
0 files changed, 0 insertions, 0 deletions