Reduce test parametrization by 65% in top 6 files for 45% CI speedup

[Copilot]

Test Suite Optimization Phase 1: Reduce Parametrization

Completed ✅

• Update test_zeros_like.py: Reduce 8 dtypes × 6 shapes to 4 dtypes × 4 shapes
• Update test_empty.py: Reduce 8 dtypes × 6 shapes to 4 dtypes × 4 shapes
• Update test_full.py: Reduce 9 fill_values × 6 shapes to 4 fill_values × 4 shapes
• Update test_randint.py: Reduce 5 dtypes × 6 shapes to 4 dtypes × 4 shapes
• Update test_ones.py: Reduce 8 dtypes × 6 shapes to 4 dtypes × 4 shapes
• Update test_zeros.py: Reduce 8 dtypes × 6 shapes to 4 dtypes × 4 shapes
• Add edge case tests to maintain coverage
• Run linting validation
• Fix OOM error by increasing heap size in edge case tests
• Wait for CI tests to validate changes

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.

File	Before	After	Reduction
test_zeros_like.py	48	16	66.7%
test_empty.py	48	16	66.7%
test_full.py	54	16	70.4%
test_randint.py	30	16	46.7%
test_ones.py	48	16	66.7%
test_zeros.py	48	16	66.7%

Original prompt

---

This section details on the original issue you should resolve

<issue_title>Test Suite Optimization Phase 1: Reduce Parametrization in Critical Path</issue_title>
<issue_description>Description:

Implement Phase 1 of the parallelism-aware optimization plan to reduce CI wall clock time by 45% (103 min → 56 min).

Background
Current CI performance (after PR #370 parallelization):

Wall clock: 102.6 minutes (1.7 hours)
Parallelization: 3.6× speedup
Critical path bottleneck: 8-rank jobs take 52.9 min (limit overall wall clock time)
Analysis in this PR identified that with parallelization, the critical path (longest-running jobs) determines wall clock time. The top 6 tensor creation test files contain 480K tests with excessive parametrization (8 dtypes × 8 shapes).

Scope: Phase 1 - Critical Path Optimization
Goal: Reduce parametrization in top 6 test files while maintaining multi-rank testing for all tests.

Changes needed:

Reduce parametrization in top 6 files (tests/unittests/):

test_zeros_like.py: 139,216 tests → 27,000 tests (80% reduction)
test_empty.py: 95,872 tests → 19,000 tests (80% reduction)
test_full.py: 76,608 tests → 15,000 tests (80% reduction)
test_randint.py: 59,360 tests → 12,000 tests (80% reduction)
test_ones.py: 59,136 tests → 12,000 tests (80% reduction)
test_zeros.py: 50,176 tests → 10,000 tests (80% reduction)
Parametrization strategy:

Current: 8 dtypes × 8 shapes = 64 base combinations
Target: 4 dtypes × 4 shapes = 16 base combinations (75% reduction)
Representative dtypes: torch.float32, torch.float16, torch.int32, torch.bool
Representative shapes: (1,), (100,), (32, 32), (4, 8, 16)
Add explicit edge case tests:

Large tensors: (1024, 1024) for memory validation
Edge dtypes: torch.int8, torch.float64 for numerical precision
Complex shapes: (2, 3, 4, 5) for multi-dimensional handling
Ensures coverage of removed parametrization combinations
Keep all multi-rank testing:

Unlike PR Reduce CI time 30% via marker-based multi-rank test filtering #356 (closed), this approach does NOT remove multi-rank testing
All tests still run on 1, 2, 4, 8 ranks
Only reduces the number of dtype/shape combinations tested
Expected impact:

Unittests (8-rank): 50 min → 29 min (42% reduction)
Examples (8-rank): 53 min → 35 min (34% reduction)
Wall clock: 103 min → 56 min (45% reduction)
Test count: 530,877 → ~95,000 (82% reduction)
Annual cost savings: $102K
Implementation approach:

Create parametrization constants for representative values
Update @pytest.mark.parametrize decorators in top 6 files
Add explicit edge case test functions
Verify coverage with pytest-cov
Reference: See PARALLELISM_AWARE_OPTIMIZATION_PLAN.md in this PR for complete analysis and implementation details.</issue_description>

Comments on the Issue (you are @copilot in this section)

• Fixes Test Suite Optimization Phase 1: Reduce Parametrization in Critical Path #373

---

💡 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.

[mawad-amd]

@copilot for this and other tests you jeed to increase the Iris symmetry heap size in ctor. I am seeing oom error now

[Copilot]

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).