[CPU] Improve vector size selection in vectorization pass #14403
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
This PR should be mostly RFC for existing working cases. It simplifies the retrieval of the vector sizes by removing the `getCanonicalVectorShape` and only looking at the lowering config of the operation to be vectorized and no longer looking at the lowering config of another (root) operation. It also gives priority to the lowering config found in the operation to be vectorize and fall back to retrieving it from the IR when the lowering config is not found.
hanhanW
added
benchmarks:x86_64
|
Closing stale PR. |
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Outdated suggestions cannot be applied.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.
This PR should mostly be mostly NFC for existing working cases. It simplifies the retrieval of the vector sizes by removing the
getCanonicalVectorShapeand only looking at the lowering config of the operation to be vectorized and no longer looking at the lowering config of another (root) operation. It also gives priority to the lowering config found in the operation to be vectorize and fall back to retrieving it from the IR when the lowering config is not found.