projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 837d1ce) | patch
[mlir][sparse][gpu] end to end test for matmul
authorAart Bik <ajcbik@google.com>
Thu, 25 May 2023 21:30:58 +0000 (14:30 -0700)
committerAart Bik <ajcbik@google.com>
Thu, 25 May 2023 23:10:22 +0000 (16:10 -0700)
commit22caafc9f3eb4f70d6eafe2fa574fcd8841fd37e
tree70e9a3326adc44c07b9c658789422eed27655437tree | snapshot
parent837d1ce0dc8eec5b17255291b3462e6296cb369bcommit | diff
[mlir][sparse][gpu] end to end test for matmul

(1) minor bug fix in copy back [always nice to run stuff ;-)]
(2) run with and without lib (even though some fall back to CPU)

Reviewed By: wrengr

Differential Revision: https://reviews.llvm.org/D151507
mlir/lib/Dialect/SparseTensor/Transforms/SparseGPUCodegen.cpp diff | blob | history
mlir/test/Dialect/SparseTensor/GPU/gpu_matmul_lib.mlir diff | blob | history
mlir/test/Integration/Dialect/SparseTensor/GPU/CUDA/sparse-matmul-lib.mlir [new file with mode: 0644] blob
mlir/test/Integration/Dialect/SparseTensor/GPU/CUDA/sparse-matvec-lib.mlir diff | blob | history
Domain: System / Toolchain;