fix(hipsparse): expand SpSM regression testing - #10246
Open
jsandham wants to merge 7 commits into
Open
Conversation
… expand_spsm_testing
… expand_spsm_testing
✅ All Checks Passed — Ready for Review
📖 Need help? See the Policy FAQ for details on every check and how to fix failures. |
|
🎉 All checks passed! This PR is ready for review. |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Expands SpSM testing similar to #8565 in order to detect regressions when reusing the sparse matrix descriptor.
Technical Details
A new test, testing_spsm_csr_reuse_descr, exercises the descriptor-reuse paths. For a single CSR sparse-matrix descriptor it sweeps over a set of operations (NON_TRANSPOSE, TRANSPOSE), fill mode (LOWER, UPPER), diag type (UNIT, NON_UNIT) and SpSM algorithms (DEFAULT), validating every result against a host reference. Two call patterns are covered are:
call_spsm — runs the full bufferSize → preprocess → SpSM flow repeatedly across configurations, so each unique (op, fill_mode, diag_type, alg) must compute the correct result despite reusing the sparse matrix descriptor.
call_spsm_shared_buffer — runs multiple configurations against a single user-provided externalBuffer sized to the maximum required across all configurations, verifying that one shared user buffer remains valid when reusing the sparse matrix descriptor.
JIRA ID: AISPARSE-646