Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Perf] Changes at 3/8/2022 1:43:56 AM #4111

Closed
performanceautofiler bot opened this issue Mar 15, 2022 · 1 comment
Closed

[Perf] Changes at 3/8/2022 1:43:56 AM #4111

performanceautofiler bot opened this issue Mar 15, 2022 · 1 comment
Labels
arch-x64 branch-refs/heads/main kind-micro os-windows perf-improvement PGO Applied if there were any profile guided optimization updates in the observed interval. runtime-coreclr

Comments

@performanceautofiler
Copy link

performanceautofiler bot commented Mar 15, 2022

Run Information

Architecture x64
OS Windows 10.0.19042
Baseline 380a4723ea98067c28d54f30e1a652483a6a257a
Compare 34880aaeb463cc17268b44aecb80dda0914cfa01
Diff Diff

Improvements in System.Numerics.Tests.Perf_VectorOf<UInt64>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
GetHashCodeBenchmark - Duration of single invocation 17.42 ns 11.70 ns 0.67 0.39 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;UInt64&gt;*'

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_VectorOf<UInt64>.GetHashCodeBenchmark


Description of detection logic

IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed:Marked as improvement because 11.698769186174355 < 16.339155838720647.
IsChangePoint: Marked as a change because one of 3/4/2022 6:17:23 AM, 3/7/2022 10:45:01 PM, 3/15/2022 4:36:24 AM falls between 3/6/2022 4:27:35 PM and 3/15/2022 4:36:24 AM.
IsImprovementStdDev: Marked as improvement because 9.329981542780262 (T) = (0 -12.612002274585238) / Math.Sqrt((2.601894295242495 / (200)) + (1.2171930333813394 / (37))) is greater than 1.9701100622679821 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (200) + (37) - 2, .975) and 0.13681619273493748 = (14.611027417839875 - 12.612002274585238) / 14.611027417839875 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

### Run Information
Architecture x64
OS Windows 10.0.19042
Baseline 380a4723ea98067c28d54f30e1a652483a6a257a
Compare 34880aaeb463cc17268b44aecb80dda0914cfa01
Diff Diff

Improvements in System.Text.Tests.Perf_Encoding

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
GetByteCount - Duration of single invocation 26.29 ns 21.49 ns 0.82 0.23 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Text.Tests.Perf_Encoding*'

Payloads

Baseline
Compare

Histogram

System.Text.Tests.Perf_Encoding.GetByteCount(size: 512, encName: "utf-8")


Description of detection logic

IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed:Marked as improvement because 21.489972522810607 < 25.046683117707722.
IsChangePoint: Marked as a change because one of 1/21/2022 2:09:07 PM, 2/2/2022 4:36:37 PM, 2/25/2022 7:19:51 AM, 3/7/2022 10:45:01 PM, 3/15/2022 4:36:24 AM falls between 3/6/2022 4:27:35 PM and 3/15/2022 4:36:24 AM.
IsImprovementStdDev: Marked as improvement because 11.567863196640094 (T) = (0 -22.2294587250423) / Math.Sqrt((5.175498137196498 / (299)) + (0.654565819431264 / (37))) is greater than 1.9670919629190173 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (37) - 2, .975) and 0.08871825176607326 = (24.3936178554253 - 22.2294587250423) / 24.3936178554253 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

@performanceautofiler performanceautofiler bot added CoreClr PGO Applied if there were any profile guided optimization updates in the observed interval. untriaged labels Mar 15, 2022
@EgorBo
Copy link
Member

EgorBo commented Mar 29, 2022

Can be dotnet/runtime#66245

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
arch-x64 branch-refs/heads/main kind-micro os-windows perf-improvement PGO Applied if there were any profile guided optimization updates in the observed interval. runtime-coreclr
Projects
None yet
Development

No branches or pull requests

1 participant