[torch] Fix unsqueezed output shape in canonicalization of AtenUnflattenIntOp #3730
Conversation
This file contains 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
zjgarvey
approved these changes
Sep 24, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Fixes iree-org/iree#18562.
During canonicalization pass on
AtenUnflattenIntOp, if the second dim was statically equal to one, we would create anAtenAddIntOpto add one to the dimension obtained fromop.getDim(). This, when passed intoTorch::unsqueezeTensor(), would make it get interpreted as non-constant, which would lead to MLIR failing an assertion whenUnsqueezeOpwould later get lowered intoExpandShapeOp, as the output of theUnsqueezeOpwould consist of only dynamic dims.This patch fixes this behavior, by extracting the integer value from the dim if it was constant, and then emitting a
ConstantIntOpfrom (dim+1). This creates an output with static shape.