diff options
| author | Alan Li <me@alanli.org> | 2025-07-23 08:22:41 -0700 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-07-23 11:22:41 -0400 |
| commit | dbc63f1e3724b6f2348c431dc1216537d9c042e8 (patch) | |
| tree | 656ce38b0262230a60e3523fb97335c96b141c42 /llvm/lib/FileCheck/FileCheck.cpp | |
| parent | 05f0dd2e917e90579ac49f94b29d12099d489efd (diff) | |
| download | llvm-dbc63f1e3724b6f2348c431dc1216537d9c042e8.zip llvm-dbc63f1e3724b6f2348c431dc1216537d9c042e8.tar.gz llvm-dbc63f1e3724b6f2348c431dc1216537d9c042e8.tar.bz2 | |
[AMDGPU] fold `memref.subview/expand_shape/collapse_shape` into `amdgpu.gather_to_lds` (#149851)
This PR adds a new optimization pass to fold
`memref.subview/expand_shape/collapse_shape` ops into consumer
`amdgpu.gather_to_lds` operations.
* Implements a new pass `AmdgpuFoldMemRefOpsPass` with pattern
`FoldMemRefOpsIntoGatherToLDSOp`
* Adds corresponding folding tests
---------
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Diffstat (limited to 'llvm/lib/FileCheck/FileCheck.cpp')
0 files changed, 0 insertions, 0 deletions