Open
Conversation
Contributor
There was a problem hiding this comment.
Pull request overview
Note
Copilot was unable to run its full agentic suite in this review.
This PR improves GPU topology discovery performance by centralizing vendor-library initialization/shutdown into outer scopes, and makes Triton HIP utilities import-safe on non-AMD systems.
Changes:
- Move NVML/AMDSMI lifecycle management out of low-level query helpers and into outer “scope” helpers.
- Add unit tests validating vendor lifecycle behavior and fallbacks when vendor libs are missing.
- Make
iris/device_utils.pyresilient to missingtriton.language.extra.hipsymbols.
Reviewed changes
Copilot reviewed 3 out of 3 changed files in this pull request and generated 3 comments.
| File | Description |
|---|---|
| tests/unittests/test_topology.py | Adds lifecycle-focused unit tests and fake NVML/AMDSMI modules to validate new behavior. |
| iris/topology.py | Introduces outer init/shutdown helpers and removes repeated init/shutdown from query helpers to reduce overhead. |
| iris/device_utils.py | Wraps HIP-only Triton imports and adds compile-time assertions for missing symbols. |
a32781a to
6a53fbc
Compare
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
Technical Details
Currently, every helper function that touches the vendor library performs its own
init()+shutdown()pair inside atry/finallyblock. During a single topology discovery this performs very poorly. Now it's calling these functions once lazily when required.Also improving device_utils.py because unit tests that require no GPU fail when they are running on a machine with no supported AMD GPU as extra.hip package is only available on systems with AMD GPUs.
Test Plan
Test Result
Submission Checklist