Use linalg.index to lower aten.reflection_pad2d #4105
Merged
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
Signed-off-by: Praveen G <[email protected]>
|
Enables successful compilation of ~10 onnx zoo models which were failing due to this. |
praveen-g-ctt
requested review from
vivekkhandelwal1,
frederik-h,
zjgarvey,
AmosLewis and
jinchen62
vivekkhandelwal1
approved these changes
Mar 27, 2025
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Outdated suggestions cannot be applied.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.
"aten.reflection_pad2d" was lowered to linalg using affine maps of the form {indexing_maps = [affine_map<(d0, d1) -> (d0, -d1 + 1)>, affine_map<(d0, d1) -> (d0, d1)>]}.
This causes lowering issues in downstream passes such as ""BinaryOpExpr(AffineBinaryOpExpr): Assertion `cast(expr.getRHS()).getValue() > 0 && "nonpositive multiplying coefficient"' failed."
Using linalg.index with tensor.extract op instead of the above affine map helps in successful compilation of the same.