Fix synchronization between SwapDeviceBuffers and Transport #401
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
|
Can one of the admins verify this patch? |
agheata
approved these changes
Jun 25, 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Outdated suggestions cannot be applied.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.
This PR fixes a subtle but important synchronization that was missing between the swap of the device buffers and the transport.
In rare cases, this could lead to the following scenario:
The hit slot counter statistics were copied from the GPU to the CPU, and reset to 0 on the device. Then the swap was executed.
However, after resetting the slot counter statistics and before the swap was executed, the transport already ran again and wrote some steps (then back to the initial position, as the counter was already reset), so some later steps overwrote some initial steps in the buffer.
This race condition broke reproducibility and could result in wrong results.
So far, no more issues with reproducibility are observed, so the CI test is put back in place.