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Outdated suggestions cannot be applied.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.
This patch adds a canonicalization rule to WhereOp to simplify the following pattern (found in the model xlm-roberta-base-language-detection):
Since the condition of where, i.e.
%5
, is always false (it compares dimension sizes with -1, and dimension sizes are always positive so the result is false),onnx.Where
can be replaced by its "false" value that is%4
.into
This simplification of WhereOp helps DimAnalysis work well with the model xlm-roberta-base-language-detection so that all MatMuls could run on NNPA.