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 6/20/2022 5:51:41 PM #6234

Closed
performanceautofiler bot opened this issue Jun 21, 2022 · 1 comment
Closed

[Perf] Changes at 6/20/2022 5:51:41 PM #6234

performanceautofiler bot opened this issue Jun 21, 2022 · 1 comment

Comments

@performanceautofiler
Copy link

performanceautofiler bot commented Jun 21, 2022

Run Information

Architecture x64
OS ubuntu 18.04
Baseline b9f899e8978fc9e6101823fc630cfc17ab45a7ae
Compare 1070187000bead58fe6687f01ac3d8fbdc01ae4c
Diff Diff

Improvements in System.Linq.Tests.Perf_Enumerable

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
WhereFirst_LastElementMatches - Duration of single invocation 212.22 ns 189.16 ns 0.89 0.04 False
WhereAny_LastElementMatches - Duration of single invocation 209.93 ns 189.26 ns 0.90 0.03 False
SelectToArray - Duration of single invocation 219.04 ns 199.13 ns 0.91 0.04 False

graph
graph
graph
Test Report

Repro

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

Payloads

Baseline
Compare

Histogram

System.Linq.Tests.Perf_Enumerable.WhereFirst_LastElementMatches(input: Array)


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 189.16366766528944 < 201.55220371447874.
IsChangePoint: Marked as a change because one of 4/25/2022 11:05:49 AM, 5/9/2022 11:56:12 AM, 5/20/2022 10:18:01 PM, 5/25/2022 1:42:32 AM, 5/31/2022 6:06:22 PM, 6/6/2022 10:12:27 PM, 6/20/2022 2:50:37 PM, 6/21/2022 6:07:15 AM falls between 6/12/2022 5:56:07 PM and 6/21/2022 6:07:15 AM.
IsImprovementStdDev: Marked as improvement because 21.625199933352974 (T) = (0 -189.80983582372784) / Math.Sqrt((107.84974097752533 / (299)) + (0.4569019100724338 / (4))) is greater than 1.9678765312856872 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (4) - 2, .975) and 0.07279951349780936 = (204.71283027446879 - 189.80983582372784) / 204.71283027446879 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### System.Linq.Tests.Perf_Enumerable.WhereAny_LastElementMatches(input: Array)

```log

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 189.2587731838298 < 199.27213785704615.
IsChangePoint: Marked as a change because one of 5/20/2022 10:18:01 PM, 5/25/2022 1:42:32 AM, 5/31/2022 6:06:22 PM, 6/6/2022 10:12:27 PM, 6/20/2022 2:50:37 PM, 6/21/2022 6:07:15 AM falls between 6/12/2022 5:56:07 PM and 6/21/2022 6:07:15 AM.
IsImprovementStdDev: Marked as improvement because 19.654139800581817 (T) = (0 -188.5132482414027) / Math.Sqrt((122.68839919891658 / (271)) + (1.0873033405043768 / (4))) is greater than 1.9686916197951025 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (271) + (4) - 2, .975) and 0.08151173251960853 = (205.2429572764545 - 188.5132482414027) / 205.2429572764545 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### System.Linq.Tests.Perf_Enumerable.SelectToArray(input: Range)

```log

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 199.13020573075715 < 209.91312819814644.
IsChangePoint: Marked as a change because one of 4/25/2022 11:05:49 AM, 5/9/2022 11:56:12 AM, 5/11/2022 11:37:12 AM, 5/20/2022 10:18:01 PM, 5/25/2022 1:42:32 AM, 5/31/2022 6:06:22 PM, 6/6/2022 10:12:27 PM, 6/20/2022 2:50:37 PM, 6/21/2022 6:07:15 AM falls between 6/12/2022 5:56:07 PM and 6/21/2022 6:07:15 AM.
IsImprovementStdDev: Marked as improvement because 19.405022994744854 (T) = (0 -197.88543018319922) / Math.Sqrt((96.28940383527738 / (299)) + (1.6364652772058734 / (4))) is greater than 1.9678765312856872 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (4) - 2, .975) and 0.0773634064815076 = (214.4781938775692 - 197.88543018319922) / 214.4781938775692 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 ubuntu 18.04
Baseline b9f899e8978fc9e6101823fc630cfc17ab45a7ae
Compare 1070187000bead58fe6687f01ac3d8fbdc01ae4c
Diff Diff

Improvements in System.Collections.ContainsFalse<String>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
LinkedList - Duration of single invocation 1.07 ms 986.43 μs 0.92 0.04 False
ImmutableArray - Duration of single invocation 774.40 μs 692.65 μs 0.89 0.04 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.Collections.ContainsFalse&lt;String&gt;*'

Payloads

Baseline
Compare

Histogram

System.Collections.ContainsFalse<String>.LinkedList(Size: 512)


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 986.4290554298642 < 1.0166534794930553.
IsChangePoint: Marked as a change because one of 5/11/2022 11:37:12 AM, 5/15/2022 3:27:46 PM, 5/20/2022 10:18:01 PM, 5/25/2022 1:42:32 AM, 5/31/2022 6:06:22 PM, 6/6/2022 10:12:27 PM, 6/20/2022 2:50:37 PM, 6/21/2022 6:07:15 AM falls between 6/12/2022 5:56:07 PM and 6/21/2022 6:07:15 AM.
IsImprovementStdDev: Marked as improvement because 10.791187089249725 (T) = (0 -983486.6374999369) / Math.Sqrt((1733799276.1948192 / (299)) + (115770184.15450804 / (4))) is greater than 1.9678765312856872 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (4) - 2, .975) and 0.0607444983930263 = (1047091.6974319427 - 983486.6374999369) / 1047091.6974319427 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### System.Collections.ContainsFalse&lt;String&gt;.ImmutableArray(Size: 512)

```log

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 692.6500087344721 < 736.3705811061508.
IsChangePoint: Marked as a change because one of 4/22/2022 6:17:37 AM, 4/25/2022 11:05:49 AM, 5/25/2022 1:42:32 AM, 6/6/2022 10:12:27 PM, 6/17/2022 3:57:37 AM, 6/21/2022 6:07:15 AM falls between 6/12/2022 5:56:07 PM and 6/21/2022 6:07:15 AM.
IsImprovementStdDev: Marked as improvement because 25.658192732311377 (T) = (0 -687918.3815971393) / Math.Sqrt((1381705435.0395648 / (299)) + (2936131.995630279 / (24))) is greater than 1.967381707010986 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (24) - 2, .975) and 0.07513041187754078 = (743800.4129789313 - 687918.3815971393) / 743800.4129789313 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 ubuntu 18.04
Baseline b9f899e8978fc9e6101823fc630cfc17ab45a7ae
Compare 1070187000bead58fe6687f01ac3d8fbdc01ae4c
Diff Diff

Improvements in System.Collections.IterateFor<String>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
ImmutableSortedSet - Duration of single invocation 11.72 μs 10.35 μs 0.88 0.03 False

graph
Test Report

Repro

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

Payloads

Baseline
Compare

Histogram

System.Collections.IterateFor<String>.ImmutableSortedSet(Size: 512)


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 10.352100226870295 < 11.139823212676962.
IsChangePoint: Marked as a change because one of 5/9/2022 11:56:12 AM, 5/15/2022 3:27:46 PM, 6/20/2022 2:50:37 PM, 6/21/2022 6:07:15 AM falls between 6/12/2022 5:56:07 PM and 6/21/2022 6:07:15 AM.
IsImprovementStdDev: Marked as improvement because 39.473969466855415 (T) = (0 -10360.756116955434) / Math.Sqrt((313209.2246656296 / (299)) + (79.39906315805214 / (4))) is greater than 1.9678765312856872 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (4) - 2, .975) and 0.11069500782545857 = (11650.396892095661 - 10360.756116955434) / 11650.396892095661 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 ubuntu 18.04
Baseline b9f899e8978fc9e6101823fc630cfc17ab45a7ae
Compare 1070187000bead58fe6687f01ac3d8fbdc01ae4c
Diff Diff

Improvements in Benchstone.MDBenchF.MDInvMt

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
Test - Duration of single invocation 5.99 ms 5.52 ms 0.92 0.14 False

graph
Test Report

Repro

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

Payloads

Baseline
Compare

Histogram

Benchstone.MDBenchF.MDInvMt.Test


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 5.518099479166666 < 5.673694829886485.
IsChangePoint: Marked as a change because one of 5/21/2022 9:00:51 AM, 5/25/2022 1:42:32 AM, 5/31/2022 6:06:22 PM, 6/6/2022 10:12:27 PM, 6/20/2022 2:50:37 PM, 6/21/2022 6:07:15 AM falls between 6/12/2022 5:56:07 PM and 6/21/2022 6:07:15 AM.
IsImprovementStdDev: Marked as improvement because 24.92963207536796 (T) = (0 -5521331.221006945) / Math.Sqrt((43297888644.019 / (299)) + (72454717.17422187 / (4))) is greater than 1.9678765312856872 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (4) - 2, .975) and 0.05449144112934909 = (5839535.950474969 - 5521331.221006945) / 5839535.950474969 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 ubuntu 18.04
Baseline b9f899e8978fc9e6101823fc630cfc17ab45a7ae
Compare 1070187000bead58fe6687f01ac3d8fbdc01ae4c
Diff Diff

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

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
DotBenchmark - Duration of single invocation 81.73 ns 72.48 ns 0.89 0.08 False
GetHashCodeBenchmark - Duration of single invocation 82.49 ns 73.51 ns 0.89 0.03 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.Numerics.Tests.Perf_VectorOf&lt;Byte&gt;*'

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_VectorOf<Byte>.DotBenchmark


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 72.47975072939349 < 77.79480865368242.
IsChangePoint: Marked as a change because one of 4/25/2022 11:05:49 AM, 5/9/2022 11:56:12 AM, 5/11/2022 11:37:12 AM, 5/20/2022 10:18:01 PM, 5/25/2022 1:42:32 AM, 5/31/2022 6:06:22 PM, 6/2/2022 5:58:32 PM, 6/6/2022 10:12:27 PM, 6/8/2022 9:59:38 PM, 6/20/2022 2:50:37 PM, 6/21/2022 6:07:15 AM falls between 6/12/2022 5:56:07 PM and 6/21/2022 6:07:15 AM.
IsImprovementStdDev: Marked as improvement because 32.77713124528809 (T) = (0 -72.34335329968607) / Math.Sqrt((16.13605135050373 / (299)) + (0.008368457170520977 / (4))) is greater than 1.9678765312856872 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (4) - 2, .975) and 0.09688114685542869 = (80.10391217921496 - 72.34335329968607) / 80.10391217921496 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### System.Numerics.Tests.Perf_VectorOf&lt;Byte&gt;.GetHashCodeBenchmark

```log

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 73.50721256811127 < 78.37848436294641.
IsChangePoint: Marked as a change because one of 4/20/2022 2:49:46 PM, 4/25/2022 11:05:49 AM, 5/9/2022 11:56:12 AM, 5/11/2022 11:37:12 AM, 5/20/2022 10:18:01 PM, 5/25/2022 1:42:32 AM, 6/6/2022 10:12:27 PM, 6/20/2022 2:50:37 PM, 6/21/2022 6:07:15 AM falls between 6/12/2022 5:56:07 PM and 6/21/2022 6:07:15 AM.
IsImprovementStdDev: Marked as improvement because 16.545960187192904 (T) = (0 -73.4972510767237) / Math.Sqrt((18.910816474062926 / (299)) + (0.0034972013977159606 / (4))) is greater than 1.9678765312856872 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (4) - 2, .975) and 0.05393170076664674 = (77.68704557195524 - 73.4972510767237) / 77.68704557195524 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 ubuntu 18.04
Baseline b9f899e8978fc9e6101823fc630cfc17ab45a7ae
Compare 1070187000bead58fe6687f01ac3d8fbdc01ae4c
Diff Diff

Improvements in System.Numerics.Tests.Perf_VectorOf<UInt16>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
GetHashCodeBenchmark - Duration of single invocation 39.13 ns 35.41 ns 0.90 0.02 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;UInt16&gt;*'

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_VectorOf<UInt16>.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 35.40831994246297 < 37.22440327834237.
IsChangePoint: Marked as a change because one of 5/11/2022 9:09:01 PM, 5/20/2022 10:18:01 PM, 5/25/2022 1:42:32 AM, 5/31/2022 6:06:22 PM, 6/2/2022 5:58:32 PM, 6/6/2022 10:12:27 PM, 6/20/2022 2:50:37 PM, 6/21/2022 6:07:15 AM falls between 6/12/2022 5:56:07 PM and 6/21/2022 6:07:15 AM.
IsImprovementStdDev: Marked as improvement because 19.647854682730625 (T) = (0 -35.40509271130672) / Math.Sqrt((3.027298715508896 / (299)) + (0.00022942932956425521 / (4))) is greater than 1.9678765312856872 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (4) - 2, .975) and 0.05302800205222459 = (37.38768705730967 - 35.40509271130672) / 37.38768705730967 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 ubuntu 18.04
Baseline b9f899e8978fc9e6101823fc630cfc17ab45a7ae
Compare 1070187000bead58fe6687f01ac3d8fbdc01ae4c
Diff Diff

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

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
GetHashCodeBenchmark - Duration of single invocation 82.53 ns 73.40 ns 0.89 0.03 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;SByte&gt;*'

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_VectorOf<SByte>.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 73.40004375432399 < 78.3734577001778.
IsChangePoint: Marked as a change because one of 5/20/2022 10:18:01 PM, 5/25/2022 1:42:32 AM, 5/31/2022 6:06:22 PM, 6/2/2022 5:58:32 PM, 6/6/2022 10:12:27 PM, 6/20/2022 2:50:37 PM, 6/21/2022 6:07:15 AM falls between 6/12/2022 5:56:07 PM and 6/21/2022 6:07:15 AM.
IsImprovementStdDev: Marked as improvement because 15.666345146602398 (T) = (0 -73.46610692420283) / Math.Sqrt((20.132286087314032 / (271)) + (0.002256461770732378 / (4))) is greater than 1.9686916197951025 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (271) + (4) - 2, .975) and 0.05512632019446913 = (77.75230540798137 - 73.46610692420283) / 77.75230540798137 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 ubuntu 18.04
Baseline b9f899e8978fc9e6101823fc630cfc17ab45a7ae
Compare 1070187000bead58fe6687f01ac3d8fbdc01ae4c
Diff Diff

Improvements in Benchstone.MDBenchF.MDSqMtx

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
Test - Duration of single invocation 931.93 ms 823.47 ms 0.88 0.03 False

graph
Test Report

Repro

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

Payloads

Baseline
Compare

Histogram

Benchstone.MDBenchF.MDSqMtx.Test


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 823.4660683999999 < 885.2679747.
IsChangePoint: Marked as a change because one of 4/22/2022 6:17:37 AM, 4/25/2022 11:05:49 AM, 5/9/2022 11:56:12 AM, 5/20/2022 10:18:01 PM, 5/25/2022 1:42:32 AM, 5/31/2022 6:06:22 PM, 6/2/2022 5:58:32 PM, 6/6/2022 10:12:27 PM, 6/20/2022 2:50:37 PM, 6/21/2022 6:07:15 AM falls between 6/12/2022 5:56:07 PM and 6/21/2022 6:07:15 AM.
IsImprovementStdDev: Marked as improvement because 24.826297593573678 (T) = (0 -823922390.7817308) / Math.Sqrt((2104245331708927.5 / (299)) + (1439157123977.154 / (4))) is greater than 1.9678765312856872 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (4) - 2, .975) and 0.07574548602526443 = (891445352.2531053 - 823922390.7817308) / 891445352.2531053 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 ubuntu 18.04
Baseline b9f899e8978fc9e6101823fc630cfc17ab45a7ae
Compare 1070187000bead58fe6687f01ac3d8fbdc01ae4c
Diff Diff

Improvements in PerfLabTests.LowLevelPerf

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
InterfaceInterfaceMethod - Duration of single invocation 2.50 ms 2.28 ms 0.91 0.03 False
InterfaceInterfaceMethodLongHierarchy - Duration of single invocation 260.82 μs 239.29 μs 0.92 0.02 False

graph
graph
Test Report

Repro

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

Payloads

Baseline
Compare

Histogram

PerfLabTests.LowLevelPerf.InterfaceInterfaceMethod


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 2.2845838625 < 2.3574241769965276.
IsChangePoint: Marked as a change because one of 4/20/2022 2:49:46 PM, 4/25/2022 11:05:49 AM, 5/9/2022 11:56:12 AM, 5/11/2022 11:37:12 AM, 5/20/2022 10:18:01 PM, 5/25/2022 1:42:32 AM, 5/31/2022 6:06:22 PM, 6/6/2022 10:12:27 PM, 6/20/2022 2:50:37 PM, 6/21/2022 6:07:15 AM falls between 6/12/2022 5:56:07 PM and 6/21/2022 6:07:15 AM.
IsImprovementStdDev: Marked as improvement because 27.39881838854242 (T) = (0 -2284373.117196085) / Math.Sqrt((8765538891.385807 / (299)) + (1011410.1246835754 / (4))) is greater than 1.9678765312856872 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (4) - 2, .975) and 0.06122713060633958 = (2433360.8177998667 - 2284373.117196085) / 2433360.8177998667 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### PerfLabTests.LowLevelPerf.InterfaceInterfaceMethodLongHierarchy

```log

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 239.28821628787884 < 247.90109792217547.
IsChangePoint: Marked as a change because one of 4/22/2022 6:17:37 AM, 4/22/2022 1:40:09 PM, 6/13/2022 2:27:15 PM, 6/21/2022 6:07:15 AM falls between 6/12/2022 5:56:07 PM and 6/21/2022 6:07:15 AM.
IsImprovementStdDev: Marked as improvement because 77.65972262974172 (T) = (0 -239311.23894491312) / Math.Sqrt((42172734.15410024 / (299)) + (27756.07303728091 / (45))) is greater than 1.9669246454804268 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (45) - 2, .975) and 0.10884618727271268 = (268540.89106405206 - 239311.23894491312) / 268540.89106405206 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 ubuntu 18.04
Baseline b9f899e8978fc9e6101823fc630cfc17ab45a7ae
Compare 1070187000bead58fe6687f01ac3d8fbdc01ae4c
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
GetChars - Duration of single invocation 20.12 ns 18.60 ns 0.92 0.05 False

graph
Test Report

Repro

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

Payloads

Baseline
Compare

Histogram

System.Text.Tests.Perf_Encoding.GetChars(size: 16, encName: "ascii")


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 18.601244807890364 < 19.111594654771697.
IsChangePoint: Marked as a change because one of 5/24/2022 7:55:26 PM, 5/31/2022 6:06:22 PM, 6/7/2022 9:00:42 AM, 6/20/2022 2:50:37 PM, 6/21/2022 6:07:15 AM falls between 6/12/2022 5:56:07 PM and 6/21/2022 6:07:15 AM.
IsImprovementStdDev: Marked as improvement because 9.260952063435917 (T) = (0 -18.76774322328784) / Math.Sqrt((0.3237206945200681 / (271)) + (0.050429269191136404 / (4))) is greater than 1.9686916197951025 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (271) + (4) - 2, .975) and 0.054794695819592024 = (19.855732019575832 - 18.76774322328784) / 19.855732019575832 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 ubuntu 18.04
Baseline b9f899e8978fc9e6101823fc630cfc17ab45a7ae
Compare 1070187000bead58fe6687f01ac3d8fbdc01ae4c
Diff Diff

Improvements in System.Collections.ContainsTrueComparer<Int32>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
HashSet - Duration of single invocation 5.20 μs 4.08 μs 0.78 0.23 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Collections.ContainsTrueComparer&lt;Int32&gt;*'

Payloads

Baseline
Compare

Histogram

System.Collections.ContainsTrueComparer<Int32>.HashSet(Size: 512)


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 4.075893285661964 < 4.905406835119271.
IsChangePoint: Marked as a change because one of 4/29/2022 5:18:09 PM, 5/23/2022 7:50:08 PM, 5/24/2022 7:55:26 PM, 6/9/2022 8:09:33 PM, 6/20/2022 2:50:37 PM, 6/21/2022 6:07:15 AM falls between 6/12/2022 5:56:07 PM and 6/21/2022 6:07:15 AM.
IsImprovementStdDev: Marked as improvement because 18.80991476759611 (T) = (0 -4103.033993300732) / Math.Sqrt((100160.04027523316 / (299)) + (681.7711869351147 / (4))) is greater than 1.9678765312856872 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (4) - 2, .975) and 0.0934349902660856 = (4525.912592308203 - 4103.033993300732) / 4525.912592308203 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 ubuntu 18.04
Baseline b9f899e8978fc9e6101823fc630cfc17ab45a7ae
Compare 1070187000bead58fe6687f01ac3d8fbdc01ae4c
Diff Diff

Improvements in System.Collections.ContainsKeyFalse<Int32, Int32>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
ImmutableDictionary - Duration of single invocation 17.03 μs 15.74 μs 0.92 0.05 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'System.Collections.ContainsKeyFalse&lt;Int32, Int32&gt;*'

Payloads

Baseline
Compare

Histogram

System.Collections.ContainsKeyFalse<Int32, Int32>.ImmutableDictionary(Size: 512)


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 15.736565621734588 < 16.15902570753297.
IsChangePoint: Marked as a change because one of 4/22/2022 6:17:37 AM, 4/25/2022 11:05:49 AM, 5/9/2022 11:56:12 AM, 6/8/2022 12:55:36 PM, 6/20/2022 2:50:37 PM, 6/21/2022 6:07:15 AM falls between 6/12/2022 5:56:07 PM and 6/21/2022 6:07:15 AM.
IsImprovementStdDev: Marked as improvement because 23.634857672772586 (T) = (0 -15723.554730495818) / Math.Sqrt((278119.61573448277 / (299)) + (1813.6414525672255 / (4))) is greater than 1.9678765312856872 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (4) - 2, .975) and 0.05295124197056448 = (16602.687662261957 - 15723.554730495818) / 16602.687662261957 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

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

No branches or pull requests

1 participant