diff options
| author | Durgadoss R <durgadossr@nvidia.com> | 2024-10-26 11:15:50 +0530 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2024-10-26 11:15:50 +0530 |
| commit | 13d6233e77982f2a596922a79365373e1466a968 (patch) | |
| tree | 2246258f1ada07fd18e24868f3dc7ba4e0312bf5 /clang/lib/CodeGen/CodeGenFunction.cpp | |
| parent | bb00f5b1edd0ed77b7e7b0113dad223505564b18 (diff) | |
| download | llvm-13d6233e77982f2a596922a79365373e1466a968.zip llvm-13d6233e77982f2a596922a79365373e1466a968.tar.gz llvm-13d6233e77982f2a596922a79365373e1466a968.tar.bz2 | |
[MLIR][NVGPU] Fix nvgpu_arrive syntax in matmulBuilder.py (#113713)
This patch updates the syntax for nvgpu_arrive Op
in matmulBuilder.py. This fixes the compilation
error for this test.
For the warp-specialized matmul_kernel implementation,
removing the WaitGroupSyncOp (after the mma-main-loop)
fixes the hang observed.
With these two fixes, the test compiles and
executes successfully on an sm90a machine.
Signed-off-by: Durgadoss R <durgadossr@nvidia.com>
Diffstat (limited to 'clang/lib/CodeGen/CodeGenFunction.cpp')
0 files changed, 0 insertions, 0 deletions