Evolution of nvbench compare that uses bulk data#386
Open
oleksandr-pavlyk wants to merge 106 commits into
Open
Evolution of nvbench compare that uses bulk data#386oleksandr-pavlyk wants to merge 106 commits into
oleksandr-pavlyk wants to merge 106 commits into
Conversation
oleksandr-pavlyk
force-pushed
the
nvbench-compare-process-bulk-data
branch
from
June 29, 2026 19:59
f18d48d to
f0db899
Compare
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
📝 WalkthroughSummary by CodeRabbit
WalkthroughChangesNVBench comparison tools
Assessment against linked issues
Suggested reviewers: Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
This comment was marked as resolved.
This comment was marked as resolved.
Sorry, something went wrong.
oleksandr-pavlyk
force-pushed
the
nvbench-compare-process-bulk-data
branch
2 times, most recently
from
June 30, 2026 11:41
42927d9 to
a240460
Compare
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as resolved.
This comment was marked as resolved.
Sorry, something went wrong.
Teach nvbench_compare to parse GPU timing summaries into structured values and prefer the robust median/IQR summaries when both compared measurements provide them. Fall back to the existing mean/stdev summaries when robust summaries are not available. Classify comparisons with the larger available relative noise estimate instead of the smaller one, keep unavailable noise distinct from encoded infinite noise, and report improvements separately from regressions. Keep the process exit code as success for completed comparisons; regression counts are reported in the summary instead of being used as the process status. Make plotting tolerate unavailable noise by leaving gaps in confidence bands, sort plotted series by the plotted axis, and avoid reusing pyplot state across plot calls. Add focused Python tests for robust-summary preference, unavailable-noise classification, non-finite timing centers, plot-along handling when the selected axis is absent, and the exit-code contract.
Teach nvbench_compare to keep the order of --benchmark and --axis arguments so
axis filters can apply either globally or to the most recent benchmark. Build a
filter plan from the ordered CLI arguments and apply the same plan to table
output and plotting labels.
Add explicit --reference-devices and --compare-devices filters. The filters
accept all, a single device id, or a comma-separated list of ids; ordered lists
and duplicates are preserved so selected reference and compare devices can be
paired by position. Device-section mismatches remain fatal for unfiltered
all-vs-all comparisons, but become warnings when the user explicitly selects
devices and the selected device counts match.
Match duplicate benchmark states by occurrence within each filtered device
section instead of matching only by state name across the whole benchmark. This
keeps repeated axis values and filtered duplicate states aligned between the
reference and compare inputs, and reports mismatched occurrence counts instead
of silently dropping extra states.
Add Python tests for duplicate-state matching, axis filtering before matching,
device filter parsing and validation, explicit cross-device pairing, and
benchmark-scoped axis filters.
Original commit messages folded into this change:
Tweaks for nvbench_compare
1. When JSON files contain multiple entries with the same name and axis values,
make sure that scripts compares corresponding entries.
Previous logic would extract the first entry from ref data, and would compare
measurements for each state in cmp against the first entry from ref. The
change introduces a counter to know which nth entry we process for a
particular axis value, and retrieve corresponding entry in ref.
Scope occurrence matching by device.
Device pairing in nvbench_compare.py is strictly index-based under
--ignore-devices, reused IDs in a different order no longer pair against the
wrong reference device.
Require devices in ref and cmp to have the same cardinality
Handle mismatch when number of duplicates in ref data is not same as in cmp data
Use pytest monkeypatch fixture to pretend third-party package dependencies are
available during test run for nvbench_compare without introducing test-time
dependency
Added the happy-path test and fixed its direct-call setup by initializing the
device globals that main() normally populates.
Fix to filter-before-matching.
- compare_benches() now pairs devices by selected position instead of taking a
device id.
- For each device pair, compare_benches() now builds:
- ref_device_states: matching reference device and axis filters
- cmp_device_states: matching compare device and axis filters
- State occurrence counts and duplicate occurrence matching now operate only
on those filtered per-device lists.
- Removed the later matches_axis_filters() skip inside the compare-state loop
because filtering now happens before matching.
Added a regression test where ref/cmp have duplicate state names in opposite
order, and --axis keeps only one of them. The test verifies the kept compare
state is matched against the kept reference state, not the first unfiltered
occurrence.
Introduce device filtering in nvbench_compare
- --reference-devices all|ID|ID,ID,...
- --compare-devices all|ID|ID,ID,...
- Integer lists preserve order and duplicates.
- Requested IDs are validated against the file-level device list.
- Filtered reference/compare device counts must match before comparison.
- compare_benches() pairs selected reference and compare devices by position.
- Each benchmark validates that requested device IDs are present in its own
devices list.
Implemented benchmark-scoped --axis handling.
- --axis and --benchmark now share an ordered argparse action, so their
relative CLI order is preserved.
- -a before any -b becomes a global axis filter.
- -a after -b <name> applies to that most recent benchmark only.
- Repeated -b entries are treated as separate filter scopes and combined as
alternatives for that benchmark.
- Device filtering remains global and is applied independently.
Allow non-matching devices for explicit device selection
Now the device-section equality check remains fatal only for unfiltered
all-vs-all comparisons. If either --reference-devices or --compare-devices is
explicit, mismatched selected device metadata is printed as a warning, but
comparison proceeds after the selected device counts have been validated.
Fix for resolve_benchmark_device_ids, add comments
The return value of resolve_benchmark_device_ids now always owns its list.
Use monkeypatch class in set_test_devices helper
Stricted device id validation
Test for device id validation
Introduce GpuTimingData, SummaryComparison, ComparisonStats, and ComparisonRunData to make timing extraction, classification, and run-level state explicit. Load sample-time and SM-frequency bulk data from JSON binary output into GpuTimingData when available, preserving count validation between paired sample and frequency arrays. Move GPU timing comparison logic into compare_gpu_timings(), prefer robust median/IQR data when available, and fall back to mean/stdev summaries otherwise. Keep missing or invalid noise on the unknown path. Replace module-level comparison counters and selected-device globals with per-run data passed into compare_benches(). Update tests to validate timing classification, bulk-data loading, device pairing, filtered duplicate matching, and summary counters through the new structures.
It is not emitted just yet, but the code becomes ready for it when it starts being emitted
Store JSON-bin sample time and frequency metadata in GpuTimingData instead of reading the binary files during summary extraction. Add Float32BinarySource and lazy cached accessors for samples and frequencies. Use np.fromfile by default, but allow tests and alternate callers to inject a float32 reader returning any buffer-compatible object convertable to "<f4" data type. Treat optional bulk-data failures as unavailable evidence instead of aborting comparison: unreadable files, invalid buffers, count mismatches, and mismatched sample/frequency metadata now emit RuntimeWarning and return None. Update nvbench_compare tests to verify lazy loading, cache reuse, injected reader behavior, warning-based degradation, and count mismatch handling.
Its intent is to be cheaply retrievable metric of average SM clock frequence over entire sample
The quantile values are not currently used, but plumbed through
Implemented the clear-gap comparison, with the log-distance-equivalent
algebra and pessimistic SM-clock fallback.
What changed:
- Added TimingInterval and interval construction from summaries:
- robust interval: [min, q3], centered at median
- fallback interval: clipped [mean - stdev, mean + stdev] intersected with [min, max]
- Added CLEAR_GAP_RELATIVE_THRESHOLD = 0.005.
- FAST gap uses:
(ref.lower - cmp.upper) / cmp.upper >= delta
which is equivalent to log(ref.lower / cmp.upper) >= log(1 + delta).
- SLOW gap uses:
(cmp.lower - ref.upper) / ref.upper >= delta
- FAST/SLOW now requires SM clock summaries on both sides and the same clear-gap result after scaling intervals by sm_clock_rate_mean.
- If intervals are missing, overlap, fail the gap threshold, have missing/invalid clock summaries, or time/cycle comparison disagrees, status is UNDECIDED.
- Existing center/noise values are still computed and displayed, but no longer drive FAST/SLOW/SAME classification.
Updated tests to cover:
- center/noise-only comparisons becoming UNDECIDED
- clear FAST/SLOW with matching clock evidence
- missing clock fallback to UNDECIDED
- frequency-shift disagreement becoming UNDECIDED
- regression reporting with robust interval and clock evidence
If SLOW/FAST check returned undecided, we attempt conservative
SAME check based on summary data alone (bulk data are not read)
Reference and compare measurements are considered SAME if
- both centers are positive finite values;
- abs(ref - cmp) / min(ref, cmp) <= 0.5%.
This is equivalent to max(ref, cmp) / min(ref, cmp) <= 1 + delta;
- interval overlap must cover at least 50% of the smaller interval;
- relative dispersion must be finite on both sides and no more than 2%;
- if SM clock summaries are available, the same check must also pass in cycle space.
Otherwise UNDECIDED remains working decision, to be refined by further checks
- Add DecisionReason(code, message) and internal
TimingDecision(status, reason).
- SummaryComparison now carries reason
- ComparisonStats now aggregates undecided reasons.
- Final summary prints a reason breakdown only when
undecided reasons exist, e.g.:
- Undecided (comparison requires more evidence): 3
- Reasons:
- noise_too_high: 2 (relative dispersion is too
high to declare same)
- weak_interval_overlap: 1 (timing intervals do not
overlap strongly enough to declare same)
Add a bulk-data SAME path to nvbench_compare for cases where summary intervals do not provide a clear FAST/SLOW decision. The new path compares sample times and SM-clock-adjusted cycles with symmetric nearest-neighbor coverage over unique values and sample counts. The comparison now requires both sample-weight coverage and unique-support coverage to pass before declaring SAME. If bulk data is available but coverage does not pass, the result remains UNDECIDED instead of falling back to the summary-only SAME rule. Also improve undecided diagnostics by aggregating reason codes while preserving the most severe representative detail, including observed coverage values and thresholds for bulk support mismatches. Add tests for: - bulk data confirming SAME despite changed mode weights; - bulk time mismatch overriding summary-only SAME; - cycle coverage vetoing time-only agreement; - sample-weight and unique-support coverage diagnostics; - aggregation of undecided reason details.
…ice-ids are by design and maybe useful
Mention nvbench-compare-legacy abd nvbench-compare-robust. State that the document is about the robust script from now on.
Instead of hard-coding script name in the exception message, using `sys.argv[0]` to get the name a user used to call the tool.
…exception message
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as outdated.
This comment was marked as resolved.
This comment was marked as resolved.
Sorry, something went wrong.
Since nvbench_compare.py with legacy decision tree and legacy display formatter are preserved, it makes sense to remove `--display legacy`. Instead we introduce `--display simple` as requested during presentation. This display centers, percent interval span, and % center difference.
Device metadata is now validated before the early continue that skips rendering when threshold filtering removes all rows and there is no --plot-along data. This prevents malformed benchmark device references from affecting stats while avoiding validation.
This ensures proper restoration
…no attribute 'get'" text
oleksandr-pavlyk
changed the title
Collaborator
Author
|
@bernhardmgruber @gevtushenko In response to feedback:
Please give it a go. |
Collaborator
Author
|
Per @gevtushenko , restored |
gevtushenko
reviewed
Jul 18, 2026
This fixes Python 3.10 CI failure.
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
2 participants
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 contains only Python changes.
python/scripts/nvbench_compare_robust.pydocs/nvbench_compare_robust.mddocumenting usage ofnvbench_compare_robustand its decision logiccuda-bench[tools].cuda-bench([Skill]: Report and interpret benchmark results #390).python/scripts/nvbench_compare.pyCloses #319
Closes #320
Closes #393
Closes #384