support canonicalizing linalg.generics that transpose#3013
Open
copybara-service[bot] wants to merge 1 commit into
Open
support canonicalizing linalg.generics that transpose#3013copybara-service[bot] wants to merge 1 commit into
copybara-service[bot] wants to merge 1 commit into
Conversation
This is a follow on from #3004. In #3004, a pattern was added to support canonicalizing linalg.generics in which one or more dimensions were dropped from an arg, creating an implicit broadcast. We noticed that transpositions were also possible, and then I found an upstream canonicalization pattern that supports extracting such transpositions into an explicit transpose op. Nb., this is not something I actually saw in any torch-mlir outputs, but having it should increase the robustness of our linalg-canonicalizations from all frontends, and it's rather simple to include. PiperOrigin-RevId: 923530441
Collaborator
|
Note due to copybara this squashed the commit it's rebased over into one. The new part is simply the line: And the new test tests/Transforms/linalg_canonicalizations/transpose_non_unit.mlir |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
support canonicalizing linalg.generics that transpose
This is a follow on from #3004. In #3004, a pattern was added to support canonicalizing linalg.generics in which one or more dimensions were dropped from an arg, creating an implicit broadcast. We noticed that transpositions were also possible, and then I found an upstream canonicalization pattern that supports extracting such transpositions into an explicit transpose op.
Nb., this is not something I actually saw in any torch-mlir outputs, but having it should increase the robustness of our linalg-canonicalizations from all frontends, and it's rather simple to include.