Repository navigation
Measure and validate scalar replay mux allocation savings - #542
Merged
Merged
Conversation
Merging this PR will not alter performance1 warning
Comparing |
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
PR #541 had only synthetic structural evidence. This report compares its exact parent (
49bfc050) with the merged revision (1689438c, freshly fetched main for the campaign), using matching Release builds and the established 13-case public/synthetic corpus. Production code is unchanged and both frontend cleanup calls remain enabled.Direct diagnostic counters show that #541 avoids all 207 targeted scalar replay mux allocations / 207 output bits on Ibex. Cleanup still directly removes 176 muxes / 744 bits from Ibex and 18 / 340 from AES VHDL. The report separates cumulative allocations, live cleanup counts, folded and hierarchy-expanded structure, and independently measured total instances.
The separate uninstrumented campaign retains all 312 balanced paired samples after 26 declared warm-ups. Ibex's median paired loading-time change is -1.64% (exploratory 95% interval -3.44% to -0.86%); no representative RSS improvement is established. Exact environment, revisions, methods, limitations and sanitized CSV evidence are included.
Validation:
MacOSX.sdk/SDKSettings.json; zero Bazel tests executed. Build-path parity remains unvalidated.git diff --checkpassed.Recommendation: keep both cleanup calls. Separately assess eligibility of the 26 remaining five-bit same-case replay pairs before considering another optimization. No vector optimization, broad planner, dead-RHS work or primitive changes are included.