diff options
| author | Aart Bik <ajcbik@google.com> | 2023-05-16 10:00:36 -0700 |
|---|---|---|
| committer | Aart Bik <ajcbik@google.com> | 2023-05-16 10:50:22 -0700 |
| commit | 195621aacb96a4e2f49f5d888e2fc7af20e6e797 (patch) | |
| tree | 76812d1efb04ea18639e59b6ba6838f65b045bae /mlir | |
| parent | dcd4c3c3fd0995912944f3dd7f89ab700d763032 (diff) | |
| download | llvm-195621aacb96a4e2f49f5d888e2fc7af20e6e797.tar.gz | |
[mlir][sparse][gpu] set cubin flag when building for cuda
Reviewed By: Peiming
Differential Revision: https://reviews.llvm.org/D150692
Diffstat (limited to 'mlir')
| -rw-r--r-- | mlir/lib/Dialect/SparseTensor/Pipelines/CMakeLists.txt | 8 |
1 files changed, 8 insertions, 0 deletions
diff --git a/mlir/lib/Dialect/SparseTensor/Pipelines/CMakeLists.txt b/mlir/lib/Dialect/SparseTensor/Pipelines/CMakeLists.txt index 234a0d82babe..939d7481f1a2 100644 --- a/mlir/lib/Dialect/SparseTensor/Pipelines/CMakeLists.txt +++ b/mlir/lib/Dialect/SparseTensor/Pipelines/CMakeLists.txt @@ -27,3 +27,11 @@ add_mlir_dialect_library(MLIRSparseTensorPipelines MLIRVectorToLLVM MLIRVectorTransforms ) + +if(MLIR_ENABLE_CUDA_RUNNER) + # Enable gpu-to-cubin pass. + target_compile_definitions(obj.MLIRSparseTensorPipelines + PRIVATE + MLIR_GPU_TO_CUBIN_PASS_ENABLE=1 + ) +endif() |