Fix non-memcpy benchmark path saving raw timestamps instead of cycle counts - #73
Open
ycmath wants to merge 1 commit into
Open
Fix non-memcpy benchmark path saving raw timestamps instead of cycle counts#73ycmath wants to merge 1 commit into
ycmath wants to merge 1 commit into
Conversation
…counts The non-memcpy benchmark path called copy_back_benchmark_data, which returns a (cycle_start, cycle_stop) tuple of absolute timestamps, and bound it to cycle_counts. As a result perf_cycles.npy stored the two stacked timestamp arrays rather than elapsed cycles, and the printed "Cycle count" was computed from absolute timestamps. Call copy_back_benchmark_cycles, which returns the stop-start difference, matching the memcpy path. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
In the non-memcpy benchmark path,
Program.runcallscopy_back_benchmark_data, which returns a(cycle_start, cycle_stop)tuple of absolute timestamps, and binds the tuple tocycle_counts. Consequently:perf_cycles.npystores the two stacked timestamp arrays instead of elapsed cycle counts, andThe memcpy path already computes the difference correctly. This changes the call to
copy_back_benchmark_cycles, which returnscycle_stop - cycle_start, making both paths consistent.🤖 Generated with Claude Code