Fix batch norm vectorize path accuracy issue by enforcing shape alignment #1238
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
xytintel
changed the title
ZhiweiYan-96
approved these changes
Jan 2, 2025
fengyuan14
approved these changes
Jan 2, 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Outdated suggestions cannot be applied.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.
When to implement a kernel for all shapes with vectorized LD/ST, we have to handle non-aligned head (base address) and short tail (tail < vector size). Before the commit, there was lack of head handling which leaded to non-vector-size-aligned vectorized ST.
The fixing enforces shapes for vectorize path. The vectorized kernel could be called only in the case in which feature dim could be divided by vector size. There will always be aligned head and exact tail.