Re-enable 3D x 2D BatchMatMul dimension collapse for adj_x=true#3599
Open
veblush wants to merge 2 commits into
Open
Re-enable 3D x 2D BatchMatMul dimension collapse for adj_x=true#3599veblush wants to merge 2 commits into
veblush wants to merge 2 commits into
Conversation
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Re-enables the outer dimension collapse optimization (
[B, C, K] -> [B*C, K]) for 3D x 2D BatchMatMul whenadj_x = true, removing the workaround from PR #3413.By executing dimension collapse after shape assignment,
lhs_shapeis in the correct canonical form to safely collapse[Batch, Col]into[Batch * Col]across both ReferenceOps and CMSIS-NN. Added unit tests to verify and protect this optimization.BUG=#3412