Review and document compiled_ii test result changes from mapping optimization #230
Conversation
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
Copilot
AI
changed the title
[WIP] Optimize spatial-temporal heuristic and reduce II for multiple kernels
Review and document compiled_ii test result changes from mapping optimization
Jan 5, 2026
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Outdated suggestions cannot be applied.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.
Analyzed compiled_ii changes across all test files following the spatial-temporal mapping optimization work. The optimization introduced non-deterministic behavior despite attempts to stabilize with
std::stable_sort.Current State
Improvements:
perfect_nested.mlir: 10 → 8 (-20%)simple_loop_reduction.mlir: 4 → 3 (-25%)Regressions:
simple_loop.mlir: 1 → 2 (+100%)tiny_loop.mlir(SPATIAL): 4 → 6 (+50%)fusion/test.mlir: 12 → 13 (+8%)Non-deterministic (using regex patterns):
nested_loop/test.mlir: 11 →{{1[13]}}(allows 11-13)bicg_kernel.mlir: 11 →1{{[123]}}(currently 12)Unchanged: 8 test files including
test_code_generate.mlir(still at 5, not 4 as claimed in original PR description)Analysis
The regex patterns in test expectations indicate the mapping remains non-deterministic across runs. The claimed improvements in the original PR description don't match actual results, suggesting the reduced IIs observed earlier were coincidental rather than deterministic improvements from the algorithm changes.
💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.