diff options
| author | Nishant Patel <nishant.b.patel@intel.com> | 2025-09-25 10:21:54 -0700 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2025-09-25 10:21:54 -0700 |
| commit | 50a7eb6fc2977d3a5c2d71d91a799d4275f5a595 (patch) | |
| tree | 57d70cbd4da9494ea18cfcf419e91b29f71885b2 /llvm/unittests/Support/CommandLineTest.cpp | |
| parent | a5569b4bd7f8d2696f962e4edaa5179895228e42 (diff) | |
| download | llvm-50a7eb6fc2977d3a5c2d71d91a799d4275f5a595.zip llvm-50a7eb6fc2977d3a5c2d71d91a799d4275f5a595.tar.gz llvm-50a7eb6fc2977d3a5c2d71d91a799d4275f5a595.tar.bz2 | |
[MLIR][XeGPU] Add support for vector.multi_reduction in wg to sg pass [1/N] (#157554)
This PR adds pattern for lowering vector.multi_reduction from workgroup
to subgroup IR. It currently only supports sg local reductions
Diffstat (limited to 'llvm/unittests/Support/CommandLineTest.cpp')
0 files changed, 0 insertions, 0 deletions