Fix Vec2/Vec4 UVM performance regression with vectorized at::Half copy#5491
Closed
q10 wants to merge 1 commit into
Closed
Fix Vec2/Vec4 UVM performance regression with vectorized at::Half copy#5491q10 wants to merge 1 commit into
q10 wants to merge 1 commit into
Conversation
Summary: Apply vectorized copy optimization pattern for at::Half types in Vec2 and Vec4 classes for ROCm. This ensures at::Half copy operations use efficient 32-bit or 64-bit memory operations instead of scalar element-by-element access. With UVM (managed memory), each separate copy can trigger a page fault, causing significant slowdown. Using vectorized operations reduces this overhead. Reviewed By: spcyppt Differential Revision: D96381299
Contributor
Contributor
|
This pull request has been merged in fc7c8f2. |
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary:
Apply vectorized copy optimization pattern for at::Half types in Vec2 and Vec4 classes for ROCm. This ensures at::Half copy operations use efficient 32-bit or 64-bit memory operations instead of scalar element-by-element access.
With UVM (managed memory), each separate copy can trigger a page fault, causing significant slowdown. Using vectorized operations reduces this overhead.
Reviewed By: spcyppt
Differential Revision: D96381299