Reduce test parametrization by 65% in top 6 files for 45% CI speedup#374
Draft
Reduce test parametrization by 65% in top 6 files for 45% CI speedup#374
Conversation
- test_zeros_like.py: 8 dtypes × 6 shapes → 4 dtypes × 4 shapes (67% reduction) - test_empty.py: 8 dtypes × 6 shapes → 4 dtypes × 4 shapes (67% reduction) - test_full.py: 9 fill_values × 6 shapes → 4 fill_values × 4 shapes (70% reduction) - test_randint.py: 5 dtypes × 6 shapes → 4 dtypes × 4 shapes (47% reduction) - test_ones.py: 8 dtypes × 6 shapes → 4 dtypes × 4 shapes (67% reduction) - test_zeros.py: 8 dtypes × 6 shapes → 4 dtypes × 4 shapes (67% reduction) Added edge case tests to maintain coverage: - Large tensors (1024, 1024) for memory validation - Edge dtypes (int8, float64) for numerical precision - Complex shapes (2, 3, 4, 5) for multi-dimensional handling Co-authored-by: mawad-amd <[email protected]>
Copilot
AI
changed the title
[WIP] Implement test suite optimization to reduce parametrization
Reduce test parametrization by 65% in top 6 files for 45% CI speedup
Feb 15, 2026
mawad-amd
reviewed
Feb 16, 2026
| large_result = shmem.empty(100, 100) | ||
| assert large_result.shape == (100, 100) | ||
| assert large_result.numel() == 10000 | ||
| # Large tensor for memory validation |
Collaborator
There was a problem hiding this comment.
@copilot for this and other tests you jeed to increase the Iris symmetry heap size in ctor. I am seeing oom error now
Contributor
Author
There was a problem hiding this comment.
Fixed in commit 7b91468. Increased symmetric heap size from 1 MB to 16 MB in all test_*_edge_cases() functions to accommodate large tensor allocations (1024×1024 elements requiring up to 8 MB for float64).
Increase symmetric heap size from 1 MB (1 << 20) to 16 MB (1 << 24) in all test_*_edge_cases() functions to accommodate large tensor allocations (1024 x 1024 elements requiring up to 8 MB for float64). Fixes OOM errors reported in PR review. Co-authored-by: mawad-amd <[email protected]>
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.
Test Suite Optimization Phase 1: Reduce Parametrization
Completed ✅
Recent Fix (addressing PR review)
Fixed OOM error in edge case tests by increasing symmetric heap size from 1 MB to 16 MB in all
test_*_edge_cases()functions. Large tensor tests (1024×1024) require up to 8 MB for float64 dtype.Test Reduction Summary
Successfully reduced parametrized test count by 65.2% (276 → 96 tests) in the main test functions while maintaining comprehensive edge case coverage.
Original prompt
💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.