Fixing GFX Executor missing threadfence_system from v1.67#327
Merged
Conversation
nileshnegi
approved these changes
Jun 28, 2026
nileshnegi
reviewed
Jun 28, 2026
Contributor
There was a problem hiding this comment.
Pull request overview
Restores a missing system-scope thread fence before collecting stop timestamps in GFX kernels (addressing inflated timing due to undrained writes), and bumps the project version/release notes to v1.68.
Changes:
- Add
__threadfence_system()before synchronization + timestamp collection in GFX device kernels. - Adjust CPU-side timing start placement in
RunGpuExecutorand filter per-transfer cycle aggregation for small/empty sub-executors. - Bump version to
1.68and add a v1.68.00 changelog entry.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 3 comments.
| File | Description |
|---|---|
| src/header/TransferBench.hpp | Adds system-scope fences before timing, adjusts GPU executor CPU timing start point, and filters per-transfer cycle aggregation. |
| CHANGELOG.md | Adds v1.68.00 release notes describing the timing fixes. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
gilbertlee-amd
added a commit
that referenced
this pull request
Jun 29, 2026
* Fixing GFX Executor missing threadfence_system from v1.67 (#327)
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The threadfence_system prior to timestamp collection in v1.67 was accidentally removed which could cause artificially inflated Transfer times because stop timestamp could be collected prior to all writes being drained. This should not have impacted GFX Executor times.