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 3/30/2022 8:03:41 PM #4424

Closed
performanceautofiler bot opened this issue Apr 7, 2022 · 0 comments
Closed

[Perf] Changes at 3/30/2022 8:03:41 PM #4424

performanceautofiler bot opened this issue Apr 7, 2022 · 0 comments
Labels
arch-arm64 branch-refs/heads/main kind-micro os-linux perf-regression PGO Applied if there were any profile guided optimization updates in the observed interval. runtime-coreclr

Comments

@performanceautofiler
Copy link

performanceautofiler bot commented Apr 7, 2022

Run Information

Architecture arm64
OS ubuntu 18.04
Baseline 2f21e533978677667d698f86064bf96932bed4e4
Compare c0db07b3f3f093b5f4cd27e1f5e8aa54adad049d
Diff Diff

Regressions in System.Net.Security.Tests.SslStreamTests

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
HandshakeECDSA512CertAsync - Duration of single invocation 25.84 ms 31.21 ms 1.21 0.39 False
HandshakeECDSA512CertAsync - Duration of single invocation 25.13 ms 29.19 ms 1.16 0.43 False

graph
graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Net.Security.Tests.SslStreamTests*'

Payloads

Baseline
Compare

Histogram

System.Net.Security.Tests.SslStreamTests.HandshakeECDSA512CertAsync(protocol: Tls12)


Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 3/22/2022 12:26:23 PM, 4/4/2022 9:46:30 AM falls between 3/22/2022 12:26:23 PM and 4/4/2022 9:46:30 AM.
IsRegressionStdDev: Marked as regression because -5.8932024753062935 (T) = (0 -30347361.57729926) / Math.Sqrt((795196950257.3137 / (2)) + (579626775720.0012 / (17))) is less than -2.109815577813699 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (2) + (17) - 2, .025) and -0.14625076739620207 = (26475324.98166667 - 30347361.57729926) / 26475324.98166667 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### System.Net.Security.Tests.SslStreamTests.HandshakeECDSA512CertAsync(protocol: Tls13)

```log

Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 3/22/2022 12:26:23 PM, 4/4/2022 9:46:30 AM falls between 3/22/2022 12:26:23 PM and 4/4/2022 9:46:30 AM.
IsRegressionStdDev: Marked as regression because -8.374998680396441 (T) = (0 -28398312.30331734) / Math.Sqrt((325519628766.6072 / (2)) + (479354713144.30145 / (16))) is less than -2.1199052992212764 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (2) + (16) - 2, .025) and -0.14871993475218157 = (24721702.34378655 - 28398312.30331734) / 24721702.34378655 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
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 arm64
OS ubuntu 18.04
Baseline 2f21e533978677667d698f86064bf96932bed4e4
Compare c0db07b3f3f093b5f4cd27e1f5e8aa54adad049d
Diff Diff

Regressions in Benchstone.BenchF.Simpsn

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
Test - Duration of single invocation 497.73 ms 540.43 ms 1.09 0.01 True

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'Benchstone.BenchF.Simpsn*'

Payloads

Baseline
Compare

Histogram

Benchstone.BenchF.Simpsn.Test


Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 3/22/2022 12:26:23 PM, 4/4/2022 9:46:30 AM falls between 3/22/2022 12:26:23 PM and 4/4/2022 9:46:30 AM.
IsRegressionStdDev: Marked as regression because -26.64550919545056 (T) = (0 -541544199.8401207) / Math.Sqrt((2356915331020.8457 / (2)) + (28242057126123.527 / (17))) is less than -2.109815577813699 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (2) + (17) - 2, .025) and -0.09041088964840711 = (496642325.3666667 - 541544199.8401207) / 496642325.3666667 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsChangeEdgeDetector: Marked as regression because Edge Detector said so.

Docs

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

Run Information

Architecture arm64
OS ubuntu 18.04
Baseline 2f21e533978677667d698f86064bf96932bed4e4
Compare c0db07b3f3f093b5f4cd27e1f5e8aa54adad049d
Diff Diff

Regressions in System.Memory.Slice<String>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
ReadOnlyMemorySpanStart - Duration of single invocation 21.20 ns 22.42 ns 1.06 0.28 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Memory.Slice&lt;String&gt;*'

Payloads

Baseline
Compare

Histogram

System.Memory.Slice<String>.ReadOnlyMemorySpanStart


Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 3/22/2022 12:26:23 PM, 4/4/2022 9:46:30 AM falls between 3/22/2022 12:26:23 PM and 4/4/2022 9:46:30 AM.
IsRegressionStdDev: Marked as regression because -6.99330087065396 (T) = (0 -23.208086904012728) / Math.Sqrt((3.771442922104985E-05 / (2)) + (1.4126594863576727 / (17))) is less than -2.109815577813699 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (2) + (17) - 2, .025) and -0.09513830184170863 = (21.19192330775335 - 23.208086904012728) / 21.19192330775335 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
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 arm64
OS ubuntu 18.04
Baseline 2f21e533978677667d698f86064bf96932bed4e4
Compare c0db07b3f3f093b5f4cd27e1f5e8aa54adad049d
Diff Diff

Regressions in LinqBenchmarks

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
Where01ForX - Duration of single invocation 336.07 ms 506.48 ms 1.51 0.08 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'LinqBenchmarks*'

Payloads

Baseline
Compare

Histogram

LinqBenchmarks.Where01ForX


Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 3/9/2022 10:55:02 PM, 3/22/2022 12:26:23 PM, 4/4/2022 9:46:30 AM falls between 3/22/2022 12:26:23 PM and 4/4/2022 9:46:30 AM.
IsRegressionStdDev: Marked as regression because -7.794211500576467 (T) = (0 -452267557.28587586) / Math.Sqrt((181394972590738.5 / (2)) + (1642276390809481.5 / (17))) is less than -2.109815577813699 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (2) + (17) - 2, .025) and -0.3086548021538158 = (345597293.1452381 - 452267557.28587586) / 345597293.1452381 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
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 arm64
OS ubuntu 18.04
Baseline 2f21e533978677667d698f86064bf96932bed4e4
Compare c0db07b3f3f093b5f4cd27e1f5e8aa54adad049d
Diff Diff

Regressions in Benchstone.BenchF.NewtR

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
Test - Duration of single invocation 171.92 ms 215.75 ms 1.25 0.00 True

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'Benchstone.BenchF.NewtR*'

Payloads

Baseline
Compare

Histogram

Benchstone.BenchF.NewtR.Test


Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 3/22/2022 12:26:23 PM, 4/4/2022 9:46:30 AM falls between 3/22/2022 12:26:23 PM and 4/4/2022 9:46:30 AM.
IsRegressionStdDev: Marked as regression because -97.7285862150521 (T) = (0 -215725886.97530708) / Math.Sqrt((393715657197.3479 / (2)) + (265999363.28675532 / (17))) is less than -2.109815577813699 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (2) + (17) - 2, .025) and -0.25157670758625783 = (172363296.36666667 - 215725886.97530708) / 172363296.36666667 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsChangeEdgeDetector: Marked as regression because Edge Detector said so.

Docs

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

Run Information

Architecture arm64
OS ubuntu 18.04
Baseline 2f21e533978677667d698f86064bf96932bed4e4
Compare c0db07b3f3f093b5f4cd27e1f5e8aa54adad049d
Diff Diff

Regressions in Benchstone.BenchF.Trap

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
Test - Duration of single invocation 483.33 ms 598.28 ms 1.24 0.00 True

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'Benchstone.BenchF.Trap*'

Payloads

Baseline
Compare

Histogram

Benchstone.BenchF.Trap.Test


Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 3/22/2022 12:26:23 PM, 4/4/2022 9:46:30 AM falls between 3/22/2022 12:26:23 PM and 4/4/2022 9:46:30 AM.
IsRegressionStdDev: Marked as regression because -131.7607792764048 (T) = (0 -594190038.4023916) / Math.Sqrt((641809188652.3247 / (2)) + (6701680315206.672 / (17))) is less than -2.109815577813699 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (2) + (17) - 2, .025) and -0.2308014798028553 = (482766756.5833334 - 594190038.4023916) / 482766756.5833334 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsChangeEdgeDetector: Marked as regression because Edge Detector said so.

Docs

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

Run Information

Architecture arm64
OS ubuntu 18.04
Baseline 2f21e533978677667d698f86064bf96932bed4e4
Compare c0db07b3f3f093b5f4cd27e1f5e8aa54adad049d
Diff Diff

Regressions in Span.IndexerBench

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
Ref - Duration of single invocation 785.03 ns 979.48 ns 1.25 0.00 True

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'Span.IndexerBench*'

Payloads

Baseline
Compare

Histogram

Span.IndexerBench.Ref(length: 1024)


Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 3/22/2022 12:26:23 PM, 4/4/2022 9:46:30 AM falls between 3/22/2022 12:26:23 PM and 4/4/2022 9:46:30 AM.
IsRegressionStdDev: Marked as regression because -69.9070508348881 (T) = (0 -976.3391146184076) / Math.Sqrt((9.05797872493691 / (2)) + (47.50325771203067 / (17))) is less than -2.109815577813699 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (2) + (17) - 2, .025) and -0.24033200864316684 = (787.159492631696 - 976.3391146184076) / 787.159492631696 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsChangeEdgeDetector: Marked as regression because Edge Detector said so.

Docs

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

Run Information

Architecture arm64
OS ubuntu 18.04
Baseline 2f21e533978677667d698f86064bf96932bed4e4
Compare c0db07b3f3f093b5f4cd27e1f5e8aa54adad049d
Diff Diff

Regressions in System.Threading.Tests.Perf_Timer

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
LongScheduleAndDispose - Duration of single invocation 791.27 ns 841.51 ns 1.06 0.37 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Threading.Tests.Perf_Timer*'

Payloads

Baseline
Compare

Histogram

System.Threading.Tests.Perf_Timer.LongScheduleAndDispose


Description of detection logic

IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 2/5/2022 9:44:06 AM, 3/22/2022 12:26:23 PM, 4/4/2022 9:46:30 AM falls between 3/22/2022 12:26:23 PM and 4/4/2022 9:46:30 AM.
IsRegressionStdDev: Marked as regression because -2.4525820511051286 (T) = (0 -876.3313901702076) / Math.Sqrt((1164.0801766827617 / (2)) + (598.3507278415084 / (17))) is less than -2.109815577813699 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (2) + (17) - 2, .025) and -0.07472733882128796 = (815.3988072280063 - 876.3313901702076) / 815.3988072280063 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

Docs

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

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
arch-arm64 branch-refs/heads/main kind-micro os-linux perf-regression 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