Script for benchmark stability assessment #10982
Merged
Conversation
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10982
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit 7b6d907 with merge base 0c9a4f5 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
yangw-dev
reviewed
May 19, 2025
There was a problem hiding this comment.
recommand to add the pip dependencies in requirements.txt next to the analyze_latency_stability.py
maybe it's good it has its own folder
guangy10
changed the title
guangy10
force-pushed
the
benchmark_assessment
branch
2 times, most recently
from
cae229e to
3b8aa35
Compare
guangy10
force-pushed
the
benchmark_assessment
branch
from
3b8aa35 to
dd44b4e
Compare
guangy10
changed the title
guangy10
force-pushed
the
benchmark_assessment
branch
from
dd44b4e to
cd676b8
Compare
|
Fixed linter |
|
As discussed with @yangw-dev offline, to make the stability assessment part of the benchmark infra as suggested in this post, I will merge this script under .ci/scripts together with other scripts used by CI and benchmark infra. @yangw-dev will take over from there and rework on the interface to
|
guangy10
force-pushed
the
benchmark_assessment
branch
from
cd676b8 to
7b6d907
Compare
yangw-dev
approved these changes
Jun 4, 2025
yangw-dev
added a commit
that referenced
this pull request
Jun 23, 2025
# Summary Provide methods and script to fetch all execuTorch benchamrk data from HUD API into two dataset,private and public, the script will: - fetch all data from HUD API from input time range in UTC - clean out records and tables with only FAILURE_REPORT due to job-level failures - get all private table metrics, generate `table_name` and find intersected public table metrics - generate private and public table groups - output data OutputType: - run with excel-sheet export - run with csv export - run with dataframe format print - run with json format print See more guidance in README.md the data is similar to the excel sheet generated manually in #10982 The result should be the same as the hud per model datatable: <img width="1480" alt="image" src="https://github.com/user-attachments/assets/7c6cc12e-50c5-4ce2-ac87-5cac650486e3" /> ## helper methods: common.py provide common.py helper method to convert back csv and excel sheets back to {"groupInfo":{}, "df":df.DataFrame} format. # run with ``` bash python3 .ci/scripts/benchmark_tooling/get_benchmark_analysis_data.py \ --startTime "2025-04-29T09:48:57" \ --endTime "2025-05-13T22:00:00" \ --outputType "excel" \ --models "mv3" python3 .ci/scripts/benchmark_tooling/analyze_benchmark_stability.py \ --primary-file private.xlsx \ --reference-file public.xlsx ``` Generate excel files: [private.xlsx](https://github.com/user-attachments/files/20844977/private.xlsx) [public.xlsx](https://github.com/user-attachments/files/20844978/public.xlsx) For instance you can find result for mv3 xnnq_q8 S22 Ultra android 14: ``` Latency Stability Analysis: table10 (Primary) ================================================================================ Model: mv3(xnnpack_q8) Device: Samsung Galaxy S22 Ultra 5G (private)(Android 14) Dataset Overview: - Number of samples: 88 - Date range: 2025-04-29 09:48:57+00:00 to 2025-05-13 21:08:36+00:00 Central Tendency Metrics: - Mean latency: 2.91 ms - Median latency (P50): 2.54 ms - Mean trimmed latency: 2.41 ms - Median trimmed latency: 2.15 ms Dispersion Metrics: - Standard deviation: 1.14 ms - Coefficient of variation (CV): 39.08% - Interquartile range (IQR): 0.82 ms - Trimmed standard deviation: 0.76 ms - Trimmed coefficient of variation: 31.60% Percentile Metrics: - P50 (median): 2.54 ms - P90: 3.88 ms - P95: 4.60 ms - P99: 5.91 ms Inter-Jitter Metrics (variability between runs): - Max/Min ratio: 5.6103 - P99/P50 ratio: 2.3319 - Mean rolling std (window=5): 0.79 ms Intra-Jitter Metrics (variability within runs): - Mean trimming effect ratio: 15.37% - Max trimming effect ratio: 38.83% Stability Assessment: - Overall stability score: 0.0/100 - Overall stability rating: Poor Interpretation: The benchmark shows poor stability (score: 0.0/100) with significant variation between runs (CV: 39.08%). Performance is unpredictable and may lead to inconsistent user experience. The significant difference between raw and trimmed means suggests considerable intra-run jitter (15.4%) with occasional outliers within benchmark runs. The max/min ratio of 5.61 indicates substantial performance differences between the best and worst runs. The P99/P50 ratio of 2.33 suggests occasional latency spikes that could affect tail latency sensitive applications. ``` --------- Signed-off-by: Yang Wang <[email protected]>
hinriksnaer
pushed a commit
to hinriksnaer/executorch
that referenced
this pull request
Jun 26, 2025
# Summary Provide methods and script to fetch all execuTorch benchamrk data from HUD API into two dataset,private and public, the script will: - fetch all data from HUD API from input time range in UTC - clean out records and tables with only FAILURE_REPORT due to job-level failures - get all private table metrics, generate `table_name` and find intersected public table metrics - generate private and public table groups - output data OutputType: - run with excel-sheet export - run with csv export - run with dataframe format print - run with json format print See more guidance in README.md the data is similar to the excel sheet generated manually in pytorch#10982 The result should be the same as the hud per model datatable: <img width="1480" alt="image" src="https://github.com/user-attachments/assets/7c6cc12e-50c5-4ce2-ac87-5cac650486e3" /> ## helper methods: common.py provide common.py helper method to convert back csv and excel sheets back to {"groupInfo":{}, "df":df.DataFrame} format. # run with ``` bash python3 .ci/scripts/benchmark_tooling/get_benchmark_analysis_data.py \ --startTime "2025-04-29T09:48:57" \ --endTime "2025-05-13T22:00:00" \ --outputType "excel" \ --models "mv3" python3 .ci/scripts/benchmark_tooling/analyze_benchmark_stability.py \ --primary-file private.xlsx \ --reference-file public.xlsx ``` Generate excel files: [private.xlsx](https://github.com/user-attachments/files/20844977/private.xlsx) [public.xlsx](https://github.com/user-attachments/files/20844978/public.xlsx) For instance you can find result for mv3 xnnq_q8 S22 Ultra android 14: ``` Latency Stability Analysis: table10 (Primary) ================================================================================ Model: mv3(xnnpack_q8) Device: Samsung Galaxy S22 Ultra 5G (private)(Android 14) Dataset Overview: - Number of samples: 88 - Date range: 2025-04-29 09:48:57+00:00 to 2025-05-13 21:08:36+00:00 Central Tendency Metrics: - Mean latency: 2.91 ms - Median latency (P50): 2.54 ms - Mean trimmed latency: 2.41 ms - Median trimmed latency: 2.15 ms Dispersion Metrics: - Standard deviation: 1.14 ms - Coefficient of variation (CV): 39.08% - Interquartile range (IQR): 0.82 ms - Trimmed standard deviation: 0.76 ms - Trimmed coefficient of variation: 31.60% Percentile Metrics: - P50 (median): 2.54 ms - P90: 3.88 ms - P95: 4.60 ms - P99: 5.91 ms Inter-Jitter Metrics (variability between runs): - Max/Min ratio: 5.6103 - P99/P50 ratio: 2.3319 - Mean rolling std (window=5): 0.79 ms Intra-Jitter Metrics (variability within runs): - Mean trimming effect ratio: 15.37% - Max trimming effect ratio: 38.83% Stability Assessment: - Overall stability score: 0.0/100 - Overall stability rating: Poor Interpretation: The benchmark shows poor stability (score: 0.0/100) with significant variation between runs (CV: 39.08%). Performance is unpredictable and may lead to inconsistent user experience. The significant difference between raw and trimmed means suggests considerable intra-run jitter (15.4%) with occasional outliers within benchmark runs. The max/min ratio of 5.61 indicates substantial performance differences between the best and worst runs. The P99/P50 ratio of 2.33 suggests occasional latency spikes that could affect tail latency sensitive applications. ``` --------- Signed-off-by: Yang Wang <[email protected]>
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.
Summary
The custom script for ET benchmark stability assessment.
Then
Datasets:
The generated analysis: