[XLA][host offloading] Correctly handle queueing tasks on stream. #97353
+186
−106
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
fe5a0dd to
82f25f8
Compare
Previous implementation was queuing H2D and D2H mem copies onto the compute stream. This implementation queues copies to the correct streams, and also queues host execution to the D2H stream to free up the compute stream for device. PiperOrigin-RevId: 786758068
82f25f8 to
35a5a74
Compare
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Outdated suggestions cannot be applied.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.
[XLA][host offloading] Correctly handle queueing tasks on stream.
Previous implementation was queuing H2D and D2H mem copies onto the compute stream.
This implementation queues copies to the correct streams, and also queues host execution to the D2H stream to free up the compute stream for device.