rocr/aie: Throw exception for malformed packets and packet submission errors #2528
+8
−9
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
ypapadop-amd
requested review from
cfreeamd,
dayatsin-amd and
kentrussell
as code owners
Contributor
There was a problem hiding this comment.
Pull request overview
This PR improves error handling in the AIE AQL queue implementation by replacing silent failures with exceptions. The changes ensure that malformed packets and submission errors are properly propagated to the public API instead of being silently swallowed in Release builds, making debugging easier.
Key changes:
- Replaced
assert()calls withthrow hsa_exception()for packet validation and submission errors - Simplified exception throwing by removing redundant
AMD::namespace prefix - Added
#include <cassert>header (though cassert is no longer used after these changes)
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
projects/rocr-runtime/runtime/hsa-runtime/core/runtime/amd_aie_aql_queue.cpp
Show resolved
Hide resolved
ypapadop-amd
force-pushed
the
users/ypapadop-amd/aie-queue-throw-exception
branch
from
1dc903d to
b2eaba1
Compare
dayatsin-amd
approved these changes
Jan 8, 2026
ypapadop-amd
force-pushed
the
users/ypapadop-amd/aie-queue-throw-exception
branch
4 times, most recently
from
830b381 to
44cf2da
Compare
ypapadop-amd
force-pushed
the
users/ypapadop-amd/aie-queue-throw-exception
branch
from
44cf2da to
fc4c43a
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Outdated suggestions cannot be applied.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.
Motivation
When either malformed packets were queued or a submission error happened, the error would be swallowed in Release builds.
Technical Details
Replacing asserts() with exceptions which will propagate to the public API and will cause an
abort()for easier debugging.JIRA ID
NA
Test Plan
Local testing on Phoenix NPU.
Test Result
If the kernel is given an argument to non-NPU memory, the following is reported:
and execution aborts.
Submission Checklist