fix(hipblaslt): skip gfx1250 subtile codegen tests on other archs#8893
Merged
Conversation
Use pytestmark skipif + a module-scoped fixture to pin rocisa to gfx1250, matching the pattern in test_emitMfmaInstruction.py. On machines with an older amdclang++ that does not know gfx1250, the entire module is skipped instead of failing with wrong encodings.
github-actions
Bot
added
project: hipblaslt
project: hipsparselt
ci:hipsparselt-fast
labels
WorldofKerry
changed the title
✅ All Policy Checks Passed
📖 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. |
Codecov Report✅ All modified and coverable lines are covered by tests. ❌ Your project status has failed because the head coverage (76.92%) is below the target coverage (80.00%). You can increase the head coverage or adjust the target coverage. Additional details and impacted files@@ Coverage Diff @@
## develop #8893 +/- ##
========================================
Coverage 71.34% 71.34%
========================================
Files 2613 2613
Lines 409004 409004
Branches 61116 61116
========================================
Hits 291781 291781
Misses 95820 95820
Partials 21403 21403
*This pull request uses carry forward flags. Click here to find out more. 🚀 New features to boost your workflow:
|
WorldofKerry
changed the title
WorldofKerry
changed the title
b-shi
approved these changes
Jun 30, 2026
JP-Fernando
pushed a commit
that referenced
this pull request
Jul 1, 2026
) ISSUE ID : AIHPBLAS-3658 ## Motivation Address test failures on gfx950 ``` FAILED Tensile/Tests/unit/test_subtile_gfx1250_codegen.py::TestGfx1250SubtileCodegen::test_gr_ptr_updates_tdm[A] - AssertionError: assert 's_add_u64' in '/* TDM addr update: A += 128 */\ns_add_u32 s[sgprAddressA], s[sgprAddressA], 128\n\ns_addc_u32 s[sgprAddressA+1], s[sgprAddressA+1], 128\ns_mov_b64 s[sgprtdmAGroup0+2:sgprtdmAGroup0+2+1], s[sgprAddressA:sgprAddressA+1] // sync ... FAILED Tensile/Tests/unit/test_subtile_gfx1250_codegen.py::TestGfx1250SubtileCodegen::test_gr_ptr_updates_tdm[B] - AssertionError: assert 's_add_u64' in '/* TDM addr update: B += 128 */\ns_add_u32 s[sgprAddressB], s[sgprAddressB], 128\n\ns_addc_u32 s[sgprAddressB+1], s[sgprAddressB+1], 128\ns_mov_b64 s[sgprtdmBGroup0+2:sgprtdmBGroup0+2+1], s[sgprAddressB:sgprAddressB+1] // sync ... ``` ## Technical Details Rocisa emits two u32 instructions on gfx950 and a single u64 on gfx1250. Use pytestmark skipif + a module-scoped fixture to pin rocisa to gfx1250, matching the pattern in test_emitMfmaInstruction.py. On machines with an older amdclang++ that does not know gfx1250, the entire module is skipped instead of failing with wrong encodings. ## Test Expect CI to pass.
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
3 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.
ISSUE ID : AIHPBLAS-3658
Motivation
Address test failures on gfx950
Technical Details
Rocisa emits two u32 instructions on gfx950 and a single u64 on gfx1250.
Use pytestmark skipif + a module-scoped fixture to pin rocisa to gfx1250, matching the pattern in test_emitMfmaInstruction.py. On machines with an older amdclang++ that does not know gfx1250, the entire module is skipped instead of failing with wrong encodings.
Test
Expect CI to pass.