diff options
| author | Aart Bik <ajcbik@google.com> | 2023-05-11 13:56:34 -0700 |
|---|---|---|
| committer | Aart Bik <ajcbik@google.com> | 2023-05-12 10:44:36 -0700 |
| commit | b700a90cc0aa08252d764b1f7da67bd300469a76 (patch) | |
| tree | ed31487f0e75ac76da26b2ad6f9b8ddd43231a2f /utils | |
| parent | 52761cb99164acd4ea76f91fc16a3e40ec94b898 (diff) | |
| download | llvm-b700a90cc0aa08252d764b1f7da67bd300469a76.tar.gz | |
[mlir][gpu][sparse] add gpu ops for sparse matrix computations
This revision extends the GPU dialect with ops that can be lowered to
host-oriented sparse matrix library calls (in this case cuSparse focused
although the ops could be generalized to support more GPUs in principle).
This will allow the "sparse compiler pipeline" to accelerate sparse operations
(see follow up revisions with examples of this).
For some background;
https://discourse.llvm.org/t/sparse-compiler-and-gpu-code-generation/69786/2
Reviewed By: ThomasRaoux
Differential Revision: https://reviews.llvm.org/D150152
Diffstat (limited to 'utils')
| -rw-r--r-- | utils/bazel/llvm-project-overlay/mlir/BUILD.bazel | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/utils/bazel/llvm-project-overlay/mlir/BUILD.bazel b/utils/bazel/llvm-project-overlay/mlir/BUILD.bazel index 7036cd5f3013..c661dd4decab 100644 --- a/utils/bazel/llvm-project-overlay/mlir/BUILD.bazel +++ b/utils/bazel/llvm-project-overlay/mlir/BUILD.bazel @@ -7758,6 +7758,7 @@ cc_library( ":LLVMSupportHeaders", ":mlir_c_runner_utils", "@cuda//:cuda_headers", + "@cuda//:cusparse_static", "@cuda//:libcuda", ], ) |