refactor(rocprofiler-sdk): migrate SPM off the per-queue callback registry#8887
Open
amd-vkale wants to merge 1 commit into
Open
refactor(rocprofiler-sdk): migrate SPM off the per-queue callback registry#8887amd-vkale wants to merge 1 commit into
amd-vkale wants to merge 1 commit into
Conversation
✅ All Policy Checks Passed
📖 Need help? See the Policy FAQ for details on every check and how to fix failures. |
|
🚫 Please fix the failed policies before requesting reviews. The following policy checks failed:
The |
amd-vkale
force-pushed
the
users/vkale/remove-callbacks-spm
branch
4 times, most recently
from
July 20, 2026 23:15
8515be4 to
99b69d8
Compare
…istry Isolates the SPM slice of the callback-removal effort (reference PRs ROCm#8730 / ROCm#8586) into a small, single-service change, per review guidance to land callback removal one service at a time. Independent of kernel replay. SPM no longer registers a queue_callbacks_t with the HSA queue controller. Instead the HSA write interceptor and async signal handler call explicit free functions: - spm::write_hook / signal_completion_hook / is_any_active (new spm/queue_hooks.{hpp,cpp}) iterating active dispatch_spm contexts and calling the existing pre_kernel_call / post_kernel_call - hsa/queue_hooks/client_ids.hpp: stable inst_pkt producer tags The per-queue callback registry is intentionally retained for counters, thread-trace and pc-sampling; those migrate in follow-up PRs. The WriteInterceptor gate and should_batch predicate detect SPM via is_any_active() (it no longer contributes to queue.get_notifiers()). Removes the now-unused queue_id from spm_counter_callback_info and updates spm tests off iterate_callbacks. Co-authored-by: Cursor <cursoragent@cursor.com>
amd-vkale
force-pushed
the
users/vkale/remove-callbacks-spm
branch
from
July 20, 2026 23:18
99b69d8 to
194cdec
Compare
amd-vkale
marked this pull request as ready for review
July 20, 2026 23:18
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
2 participants
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
The purpose of this PR is to Isolate the SPM slice of the callback-removal effort (reference PRs #8730 / #8586) into a small, single-service change, per review guidance to land callback removal one service at a time. This is independent of kernel replay feature in PR #7960 and #8622 but it aids it.
Technical Details
SPM no longer registers a queue_callbacks_t with the HSA queue controller. Instead the HSA write interceptor and async signal handler call explicit free functions:
The per-queue callback registry is intentionally retained for counters, thread-trace and pc-sampling; those migrate in follow-up PRs. The WriteInterceptor gate and should_batch predicate detect SPM via is_any_active() (it no longer contributes to queue.get_notifiers()). Removes the now-unused queue_id from spm_counter_callback_info and updates spm tests off iterate_callbacks.
Issue Tracking
Aids PR #7960 and addresses kernel replay feature in AIPROFSDK-68. This PR also can help for other features requiring the removal of the SPM per-queue callback registry.
Test Plan
Test Result
Submission Checklist