Fix branch predictor performance counter reporting - #1917
Open
davidharrishmc wants to merge 1 commit into
Open
davidharrishmc wants to merge 1 commit into
davidharrishmc wants to merge 1 commit into
Conversation
…1379) The testbench logger read the hpmcounters, which count only events that software enables in mhpmevent. Embench never enables them, so every counter above minstret reported 0 and parseHPMC.py divided by zero. The logger now counts the csrc counter events directly. parseHPMC.py fixes: - Keep the speed- and size-optimized builds of each benchmark separate. They were filed under one name, so per-benchmark tables and bar graphs mixed results from different predictors. - Exclude zero values from the geometric mean's count as well as its product. - Fix swapped entries/size columns in --table output. - Label the summary graph's y axis by the metric shown. - Regenerate the sim_bp reference data from the current embench build. Co-Authored-By: Claude Opus 5.5 (1M context) <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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes #1379.
The testbench logger read the hpmcounters, which count only events that software enables in
mhpmevent. Embench never enables them, so every counter aboveminstretreported 0 andparseHPMC.pydivided by zero. The logger now counts the csrc counter events directly.parseHPMC.pyfixes:--tableoutput.sim_bpreference data from the current embench build.With these changes, the per-benchmark branch counts match the
BPRED_LOGGERtrace exactly. Wally's twobit and gshare mean misprediction rates tracksim_bpat 64, 1K, and 64K entries (e.g. gshare 12.06/6.64/2.81% vs. 11.76/6.30/1.98%). The parsing script was at fault; the branch predictor was not.🤖 Generated with Claude Code