This is an archive of the discontinued LLVM Phabricator instance.

Differential D150692

[mlir][sparse][gpu] set cubin flag when building for cuda
ClosedPublic

Authored by aartbik on May 16 2023, 10:03 AM.

Details

Reviewers
Peiming
bixia
wrengr
nicolasvasilache
K-Wu
Commits
rG195621aacb96: [mlir][sparse][gpu] set cubin flag when building for cuda

Diff Detail

Event Timeline

aartbik created this revision.May 16 2023, 10:03 AM
Herald added a project: Restricted Project. · View Herald TranscriptMay 16 2023, 10:03 AM
Herald added subscribers: bviyer, hanchung, jsetoain and 23 others. · View Herald Transcript
aartbik requested review of this revision.May 16 2023, 10:03 AM
Herald added a reviewer: nicolasvasilache. · View Herald TranscriptMay 16 2023, 10:03 AM
Herald added a project: Restricted Project. · View Herald Transcript
Herald added subscribers: stephenneuendorffer, nicolasvasilache. · View Herald Transcript
Peiming accepted this revision.May 16 2023, 10:05 AM
This revision is now accepted and ready to land.May 16 2023, 10:05 AM
aartbik added a reviewer: K-Wu.May 16 2023, 10:05 AM
This revision was landed with ongoing or failed builds.May 16 2023, 10:50 AM
Closed by commit rG195621aacb96: [mlir][sparse][gpu] set cubin flag when building for cuda (authored by aartbik). · Explain Why
This revision was automatically updated to reflect the committed changes.
aartbik added a commit: rG195621aacb96: [mlir][sparse][gpu] set cubin flag when building for cuda.
Harbormaster completed remote builds in B232359: Diff 522681.May 16 2023, 11:24 AM

Revision Contents

PathSize
mlir/
lib/
Dialect/
SparseTensor/
Pipelines/
8 lines

Diff 522707

mlir/lib/Dialect/SparseTensor/Pipelines/CMakeLists.txt

Show All 21 Linesadd_mlir_dialect_library(MLIRSparseTensorPipelines
MLIRReconcileUnrealizedCasts MLIRReconcileUnrealizedCasts
MLIRSCFToControlFlow MLIRSCFToControlFlow
MLIRSparseTensorDialect MLIRSparseTensorDialect
MLIRSparseTensorTransforms MLIRSparseTensorTransforms
MLIRTensorTransforms MLIRTensorTransforms
MLIRVectorToLLVM MLIRVectorToLLVM
MLIRVectorTransforms 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()