This is an archive of the discontinued LLVM Phabricator instance.

[mlir][sparse] implement lowering rules for sparse_tensor::unpack
ClosedPublic

Authored by Peiming on Feb 9 2023, 12:32 PM.

Diff Detail

Event Timeline

Peiming created this revision.Feb 9 2023, 12:32 PM
Herald added a project: Restricted Project. · View Herald Transcript
Peiming requested review of this revision.Feb 9 2023, 12:32 PM
aartbik added inline comments.Feb 10 2023, 4:39 PM
mlir/include/mlir/Dialect/SparseTensor/IR/SparseTensorOps.td
102 ↗(On Diff #496626)

some rebasing here

mlir/lib/Dialect/SparseTensor/Transforms/BufferizableOpInterfaceImpl.cpp
157

Even though I know what you mean, this comment is not very clear "does not count".
How about rephrasing this a bit?

mlir/lib/Dialect/SparseTensor/Transforms/SparseTensorCodegen.cpp
1193

Say in words, Converts Memref back to Tensor.

Peiming updated this revision to Diff 496636.Feb 10 2023, 4:48 PM
Peiming marked 2 inline comments as done.

address comments.

Peiming marked an inline comment as done.Feb 10 2023, 4:48 PM
aartbik accepted this revision.Feb 10 2023, 4:51 PM
aartbik added inline comments.
mlir/lib/Dialect/SparseTensor/Transforms/BufferizableOpInterfaceImpl.cpp
158

memroy -> memory

This revision is now accepted and ready to land.Feb 10 2023, 4:51 PM
Peiming marked an inline comment as done.Feb 10 2023, 5:02 PM
This revision was landed with ongoing or failed builds.Feb 10 2023, 5:05 PM
This revision was automatically updated to reflect the committed changes.