doc: point the packed-matrix prototype report at its implementation - #9163
Open
kim-em wants to merge 1 commit into
Open
doc: point the packed-matrix prototype report at its implementation#9163kim-em wants to merge 1 commit into
kim-em wants to merge 1 commit into
Conversation
The prototype report's factors price a benchmark, and the specialization they justified has since landed, so a reader arriving there could take them for the shipped implementation's. Add the forward pointer, and say what the benchmark module's packed variants are for now that the implementation exists.
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR adds a forward pointer from the packed-matrix prototype report to the report that measures the landed implementation, and updates the benchmark module's description of what its packed variants are for now that the implementation exists.
reports/hexbz-packed-fp-matrix.mdprices a benchmark prototype. Its factors were the input to a decision, not a description of shipped code, and the specialization they justified landed in #9158 "perf: pack the Berlekamp fixed-space matrix into UInt32 words". A reader arriving at the prototype page had nothing telling them that, and its17.0xis not the implementation's6.06x.bench/HexBench/BerlekampKernel.leandescribed its packed variants as prototyped "before any production specialization is written". One is written. The variants are still doing two jobs, and the docstring now names them: they remain the entry-for-entry oracleHex.Berlekamp.Packed's output is checked against on every phase-profile run, and they are the floor the implementation's own cost is read against, which is where the measured 2.62x gap oncyclo_phi385comes from.Documentation only. No Lean declaration changes;
check_factor_sweep_freshness.pystill passes, so no re-measurement is implied.🤖 Prepared with Claude Code