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] Linux/x64: 24 Improvements on 1/27/2023 3:53:39 PM #12309

Open
performanceautofiler bot opened this issue Jan 31, 2023 · 2 comments
Open

[Perf] Linux/x64: 24 Improvements on 1/27/2023 3:53:39 PM #12309

performanceautofiler bot opened this issue Jan 31, 2023 · 2 comments

Comments

@performanceautofiler
Copy link

performanceautofiler bot commented Jan 31, 2023

Run Information

Architecture x64
OS ubuntu 18.04
Baseline acc409ef8a94c8148c86edc6a94eb8edf2e5e2e5
Compare ec06321141611cc131c18761808abce15d097db3
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
EqualsBenchmark - Duration of single invocation 81.14 ns 68.09 ns 0.84 0.14 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;Byte&gt;*'

Payloads

Baseline
Compare

Histogram

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


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 68.08543906612266 < 75.42704829997972.
IsChangePoint: Marked as a change because one of 12/9/2022 1:52:32 PM, 1/12/2023 3:42:01 AM, 1/27/2023 11:36:27 AM, 1/30/2023 9:42:46 PM falls between 1/22/2023 2:59:30 AM and 1/30/2023 9:42:46 PM.
IsImprovementStdDev: Marked as improvement because 30.463810803354857 (T) = (0 -68.54867432993251) / Math.Sqrt((31.607028106694663 / (299)) + (2.3005061427274103 / (12))) is greater than 1.9676708853560316 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (12) - 2, .975) and 0.19508316107733756 = (85.16243047130334 - 68.54867432993251) / 85.16243047130334 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 acc409ef8a94c8148c86edc6a94eb8edf2e5e2e5
Compare ddfaf2750e8dcf127a8baf0a3e5a2bd4835f79c7
Diff Diff

Improvements in System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Int64>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
EqualsBenchmark - Duration of single invocation 97.25 ns 80.15 ns 0.82 0.13 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Runtime.Intrinsics.Tests.Perf_Vector128Of&lt;Int64&gt;*'

Payloads

Baseline
Compare

Histogram

System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Int64>.EqualsBenchmark


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 80.14744042069866 < 85.37590531283514.
IsChangePoint: Marked as a change because one of 12/12/2022 1:43:17 AM, 1/27/2023 11:36:27 AM, 1/30/2023 9:42:46 PM falls between 1/22/2023 2:59:30 AM and 1/30/2023 9:42:46 PM.
IsImprovementStdDev: Marked as improvement because 15.10196865735339 (T) = (0 -81.26498947728989) / Math.Sqrt((16.35492991976052 / (299)) + (5.25013488902686 / (13))) is greater than 1.9676459287777595 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (13) - 2, .975) and 0.11177597163318864 = (91.49154591855935 - 81.26498947728989) / 91.49154591855935 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 acc409ef8a94c8148c86edc6a94eb8edf2e5e2e5
Compare ddfaf2750e8dcf127a8baf0a3e5a2bd4835f79c7
Diff Diff

Improvements in System.Numerics.Tests.Perf_VectorOf<Int64>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
EqualsBenchmark - Duration of single invocation 84.58 ns 68.21 ns 0.81 0.08 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;Int64&gt;*'

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_VectorOf<Int64>.EqualsBenchmark


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 68.21498324545092 < 74.49218243404418.
IsChangePoint: Marked as a change because one of 12/9/2022 1:52:32 PM, 1/12/2023 3:42:01 AM, 1/27/2023 11:36:27 AM, 1/30/2023 9:42:46 PM falls between 1/22/2023 2:59:30 AM and 1/30/2023 9:42:46 PM.
IsImprovementStdDev: Marked as improvement because 23.629629305800872 (T) = (0 -66.98456075069937) / Math.Sqrt((30.46840089065395 / (299)) + (6.161789592027861 / (13))) is greater than 1.9676459287777595 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (13) - 2, .975) and 0.21117046396100392 = (84.91639535590103 - 66.98456075069937) / 84.91639535590103 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 acc409ef8a94c8148c86edc6a94eb8edf2e5e2e5
Compare ddfaf2750e8dcf127a8baf0a3e5a2bd4835f79c7
Diff Diff

Improvements in System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Byte>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
EqualsBenchmark - Duration of single invocation 92.04 ns 80.84 ns 0.88 0.11 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Runtime.Intrinsics.Tests.Perf_Vector128Of&lt;Byte&gt;*'

Payloads

Baseline
Compare

Histogram

System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Byte>.EqualsBenchmark


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 80.84397621470404 < 86.07927349873403.
IsChangePoint: Marked as a change because one of 12/8/2022 9:08:34 PM, 1/27/2023 11:36:27 AM, 1/30/2023 9:42:46 PM falls between 1/22/2023 2:59:30 AM and 1/30/2023 9:42:46 PM.
IsImprovementStdDev: Marked as improvement because 23.5688545423843 (T) = (0 -81.80294549556469) / Math.Sqrt((13.515414237000684 / (299)) + (1.4352930516523599 / (12))) is greater than 1.9676708853560316 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (12) - 2, .975) and 0.10471790842767748 = (91.37114018655258 - 81.80294549556469) / 91.37114018655258 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 acc409ef8a94c8148c86edc6a94eb8edf2e5e2e5
Compare ddfaf2750e8dcf127a8baf0a3e5a2bd4835f79c7
Diff Diff

Improvements in System.Numerics.Tests.Perf_Quaternion

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
AddBenchmark - Duration of single invocation 216.15 ns 169.44 ns 0.78 0.08 False
SubtractBenchmark - Duration of single invocation 210.67 ns 171.40 ns 0.81 0.11 False
MultiplyByQuaternionBenchmark - Duration of single invocation 253.85 ns 227.70 ns 0.90 0.06 False
DivideBenchmark - Duration of single invocation 205.68 ns 167.92 ns 0.82 0.10 False

graph
graph
graph
graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Numerics.Tests.Perf_Quaternion*'

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_Quaternion.AddBenchmark


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 169.4412089102544 < 195.7381302016684.
IsChangePoint: Marked as a change because one of 12/9/2022 1:52:32 PM, 1/12/2023 3:42:01 AM, 1/27/2023 11:36:27 AM, 1/30/2023 9:42:46 PM falls between 1/22/2023 2:59:30 AM and 1/30/2023 9:42:46 PM.
IsImprovementStdDev: Marked as improvement because 44.04876247294383 (T) = (0 -169.88840325165924) / Math.Sqrt((457.37209733742225 / (299)) + (3.979339749174926 / (13))) is greater than 1.9676459287777595 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (13) - 2, .975) and 0.2599725995656774 = (229.57042286806086 - 169.88840325165924) / 229.57042286806086 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### System.Numerics.Tests.Perf_Quaternion.SubtractBenchmark

```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 171.39586040956834 < 198.28522909060058.
IsChangePoint: Marked as a change because one of 12/9/2022 1:52:32 PM, 1/12/2023 3:42:01 AM, 1/27/2023 11:36:27 AM, 1/30/2023 9:42:46 PM falls between 1/22/2023 2:59:30 AM and 1/30/2023 9:42:46 PM.
IsImprovementStdDev: Marked as improvement because 43.46208452513088 (T) = (0 -170.21825274942609) / Math.Sqrt((445.36854898400327 / (299)) + (3.6938962687925088 / (13))) is greater than 1.9676459287777595 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (13) - 2, .975) and 0.253758488686632 = (228.10075581274734 - 170.21825274942609) / 228.10075581274734 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### System.Numerics.Tests.Perf_Quaternion.MultiplyByQuaternionBenchmark

```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 227.70095258917488 < 241.81747386879178.
IsChangePoint: Marked as a change because one of 12/9/2022 1:52:32 PM, 1/12/2023 3:42:01 AM, 1/27/2023 11:36:27 AM, 1/30/2023 9:42:46 PM falls between 1/22/2023 2:59:30 AM and 1/30/2023 9:42:46 PM.
IsImprovementStdDev: Marked as improvement because 37.29102812963702 (T) = (0 -221.48359102005165) / Math.Sqrt((169.05343565310022 / (299)) + (13.608669362494716 / (13))) is greater than 1.9676459287777595 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (13) - 2, .975) and 0.17612995972077017 = (268.8331656592166 - 221.48359102005165) / 268.8331656592166 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### System.Numerics.Tests.Perf_Quaternion.DivideBenchmark

```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 167.92458396628817 < 195.19136788339372.
IsChangePoint: Marked as a change because one of 12/9/2022 1:52:32 PM, 1/12/2023 3:42:01 AM, 1/27/2023 11:36:27 AM, 1/30/2023 9:42:46 PM falls between 1/22/2023 2:59:30 AM and 1/30/2023 9:42:46 PM.
IsImprovementStdDev: Marked as improvement because 35.93743552679844 (T) = (0 -170.52217037498488) / Math.Sqrt((451.63889214682445 / (299)) + (13.560422441939833 / (12))) is greater than 1.9676708853560316 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (12) - 2, .975) and 0.25509980777392877 = (228.91948767712597 - 170.52217037498488) / 228.91948767712597 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 acc409ef8a94c8148c86edc6a94eb8edf2e5e2e5
Compare ddfaf2750e8dcf127a8baf0a3e5a2bd4835f79c7
Diff Diff

Improvements in System.Numerics.Tests.Perf_Vector2

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
EqualsBenchmark - Duration of single invocation 78.38 ns 70.65 ns 0.90 0.11 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Numerics.Tests.Perf_Vector2*'

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_Vector2.EqualsBenchmark


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 70.64691464277035 < 74.57690003793137.
IsChangePoint: Marked as a change because one of 12/9/2022 7:57:12 PM, 1/27/2023 11:36:27 AM, 1/30/2023 9:42:46 PM falls between 1/22/2023 2:59:30 AM and 1/30/2023 9:42:46 PM.
IsImprovementStdDev: Marked as improvement because 26.32383559581847 (T) = (0 -69.19119512829691) / Math.Sqrt((10.90592925622536 / (299)) + (1.6951957427444997 / (13))) is greater than 1.9676459287777595 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (13) - 2, .975) and 0.1345101650684222 = (79.94454970550508 - 69.19119512829691) / 79.94454970550508 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 acc409ef8a94c8148c86edc6a94eb8edf2e5e2e5
Compare ddfaf2750e8dcf127a8baf0a3e5a2bd4835f79c7
Diff Diff

Improvements in System.Numerics.Tests.Perf_Plane

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
EqualsBenchmark - Duration of single invocation 190.48 ns 169.97 ns 0.89 0.06 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Numerics.Tests.Perf_Plane*'

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_Plane.EqualsBenchmark


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 169.9678197867776 < 181.2571830873123.
IsChangePoint: Marked as a change because one of 12/9/2022 1:52:32 PM, 1/27/2023 11:36:27 AM, 1/30/2023 9:42:46 PM falls between 1/22/2023 2:59:30 AM and 1/30/2023 9:42:46 PM.
IsImprovementStdDev: Marked as improvement because 40.76823705928075 (T) = (0 -171.916230279938) / Math.Sqrt((46.75732752220852 / (299)) + (2.1141531328522327 / (13))) is greater than 1.9676459287777595 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (13) - 2, .975) and 0.11811775966851346 = (194.94238847050283 - 171.916230279938) / 194.94238847050283 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 acc409ef8a94c8148c86edc6a94eb8edf2e5e2e5
Compare ddfaf2750e8dcf127a8baf0a3e5a2bd4835f79c7
Diff Diff

Improvements in System.Numerics.Tests.Perf_VectorOf<Int16>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
EqualsBenchmark - Duration of single invocation 80.27 ns 70.17 ns 0.87 0.10 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;Int16&gt;*'

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_VectorOf<Int16>.EqualsBenchmark


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 70.17234749114117 < 75.87097365143832.
IsChangePoint: Marked as a change because one of 12/9/2022 1:52:32 PM, 1/12/2023 3:42:01 AM, 1/27/2023 11:36:27 AM, 1/30/2023 9:42:46 PM falls between 1/22/2023 2:59:30 AM and 1/30/2023 9:42:46 PM.
IsImprovementStdDev: Marked as improvement because 39.381330370787424 (T) = (0 -69.3986949134532) / Math.Sqrt((51.54297202540026 / (299)) + (0.6814773723590628 / (13))) is greater than 1.9676459287777595 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (13) - 2, .975) and 0.21201278971172346 = (88.0708392310891 - 69.3986949134532) / 88.0708392310891 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 acc409ef8a94c8148c86edc6a94eb8edf2e5e2e5
Compare ddfaf2750e8dcf127a8baf0a3e5a2bd4835f79c7
Diff Diff

Improvements in System.Runtime.Intrinsics.Tests.Perf_Vector128Of<SByte>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
EqualsBenchmark - Duration of single invocation 90.22 ns 81.07 ns 0.90 0.13 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Runtime.Intrinsics.Tests.Perf_Vector128Of&lt;SByte&gt;*'

Payloads

Baseline
Compare

Histogram

System.Runtime.Intrinsics.Tests.Perf_Vector128Of<SByte>.EqualsBenchmark


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 81.07407715132473 < 86.23890426403277.
IsChangePoint: Marked as a change because one of 12/9/2022 8:25:19 AM, 1/27/2023 11:36:27 AM, 1/30/2023 9:42:46 PM falls between 1/22/2023 2:59:30 AM and 1/30/2023 9:42:46 PM.
IsImprovementStdDev: Marked as improvement because 9.061530494664877 (T) = (0 -83.07449219220962) / Math.Sqrt((20.56949455658792 / (299)) + (9.923200438662688 / (12))) is greater than 1.9676708853560316 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (12) - 2, .975) and 0.0935738076251062 = (91.65058654643376 - 83.07449219220962) / 91.65058654643376 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 acc409ef8a94c8148c86edc6a94eb8edf2e5e2e5
Compare ddfaf2750e8dcf127a8baf0a3e5a2bd4835f79c7
Diff Diff

Improvements in System.Numerics.Tests.Perf_VectorOf<UInt32>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
EqualsBenchmark - Duration of single invocation 78.14 ns 67.49 ns 0.86 0.14 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;UInt32&gt;*'

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_VectorOf<UInt32>.EqualsBenchmark


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 67.49457902023525 < 74.17342666359721.
IsChangePoint: Marked as a change because one of 12/9/2022 1:52:32 PM, 1/12/2023 3:42:01 AM, 1/27/2023 11:36:27 AM, 1/30/2023 9:42:46 PM falls between 1/22/2023 2:59:30 AM and 1/30/2023 9:42:46 PM.
IsImprovementStdDev: Marked as improvement because 27.00853352028762 (T) = (0 -67.95189045078979) / Math.Sqrt((33.016794290767315 / (299)) + (3.563244516613072 / (13))) is greater than 1.9676459287777595 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (13) - 2, .975) and 0.19773248261908935 = (84.69979025528306 - 67.95189045078979) / 84.69979025528306 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 acc409ef8a94c8148c86edc6a94eb8edf2e5e2e5
Compare ddfaf2750e8dcf127a8baf0a3e5a2bd4835f79c7
Diff Diff

Improvements in System.Runtime.Intrinsics.Tests.Perf_Vector128Int

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
EqualsBenchmark - Duration of single invocation 89.59 ns 80.01 ns 0.89 0.13 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Runtime.Intrinsics.Tests.Perf_Vector128Int*'

Payloads

Baseline
Compare

Histogram

System.Runtime.Intrinsics.Tests.Perf_Vector128Int.EqualsBenchmark


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 80.01384656714241 < 85.0623104316183.
IsChangePoint: Marked as a change because one of 12/9/2022 1:52:32 PM, 1/27/2023 11:36:27 AM, 1/30/2023 9:42:46 PM falls between 1/22/2023 2:59:30 AM and 1/30/2023 9:42:46 PM.
IsImprovementStdDev: Marked as improvement because 25.739518588478496 (T) = (0 -80.24977457075042) / Math.Sqrt((17.133624870069205 / (299)) + (1.6871489131589141 / (13))) is greater than 1.9676459287777595 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (13) - 2, .975) and 0.12182975809876502 = (91.38293549666405 - 80.24977457075042) / 91.38293549666405 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 acc409ef8a94c8148c86edc6a94eb8edf2e5e2e5
Compare ddfaf2750e8dcf127a8baf0a3e5a2bd4835f79c7
Diff Diff

Improvements in System.Numerics.Tests.Perf_Vector4

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
EqualsBenchmark - Duration of single invocation 60.06 ns 51.87 ns 0.86 0.07 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Numerics.Tests.Perf_Vector4*'

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_Vector4.EqualsBenchmark


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 51.870466638802206 < 57.117916593298204.
IsChangePoint: Marked as a change because one of 12/5/2022 8:20:45 AM, 1/12/2023 3:42:01 AM, 1/27/2023 11:36:27 AM, 1/30/2023 9:42:46 PM falls between 1/22/2023 2:59:30 AM and 1/30/2023 9:42:46 PM.
IsImprovementStdDev: Marked as improvement because 43.9799113709258 (T) = (0 -51.22278683128123) / Math.Sqrt((9.27657337894222 / (299)) + (0.7410293146373528 / (13))) is greater than 1.9676459287777595 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (13) - 2, .975) and 0.20302340436135227 = (64.27138150805352 - 51.22278683128123) / 64.27138150805352 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 acc409ef8a94c8148c86edc6a94eb8edf2e5e2e5
Compare ddfaf2750e8dcf127a8baf0a3e5a2bd4835f79c7
Diff Diff

Improvements in System.Numerics.Tests.Perf_VectorOf<Int32>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
EqualsBenchmark - Duration of single invocation 78.14 ns 67.12 ns 0.86 0.16 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;Int32&gt;*'

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_VectorOf<Int32>.EqualsBenchmark


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 67.1224270266829 < 75.46524504172909.
IsChangePoint: Marked as a change because one of 12/9/2022 1:52:32 PM, 1/12/2023 3:42:01 AM, 1/27/2023 11:36:27 AM, 1/30/2023 9:42:46 PM falls between 1/22/2023 2:59:30 AM and 1/30/2023 9:42:46 PM.
IsImprovementStdDev: Marked as improvement because 25.75302049533593 (T) = (0 -67.69774269816412) / Math.Sqrt((30.402783467550133 / (299)) + (4.296089132342644 / (13))) is greater than 1.9676459287777595 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (13) - 2, .975) and 0.20004834314884293 = (84.62729230994054 - 67.69774269816412) / 84.62729230994054 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
Copy link
Author

performanceautofiler bot commented Jan 31, 2023

Run Information

Architecture x64
OS ubuntu 18.04
Baseline acc409ef8a94c8148c86edc6a94eb8edf2e5e2e5
Compare ddfaf2750e8dcf127a8baf0a3e5a2bd4835f79c7
Diff Diff

Improvements in System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Int32>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
EqualsBenchmark - Duration of single invocation 89.51 ns 84.57 ns 0.94 0.13 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Runtime.Intrinsics.Tests.Perf_Vector128Of&lt;Int32&gt;*'

Payloads

Baseline
Compare

Histogram

System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Int32>.EqualsBenchmark


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 84.57303534662137 < 85.55099131852761.
IsChangePoint: Marked as a change because one of 12/9/2022 1:52:32 PM, 1/27/2023 11:36:27 AM, 1/30/2023 9:42:46 PM falls between 1/22/2023 2:59:30 AM and 1/30/2023 9:42:46 PM.
IsImprovementStdDev: Marked as improvement because 23.524357948223745 (T) = (0 -80.5268218487794) / Math.Sqrt((14.402207665355702 / (299)) + (1.9288448966161285 / (13))) is greater than 1.9676459287777595 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (13) - 2, .975) and 0.11466035312961378 = (90.95585195290428 - 80.5268218487794) / 90.95585195290428 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 acc409ef8a94c8148c86edc6a94eb8edf2e5e2e5
Compare ddfaf2750e8dcf127a8baf0a3e5a2bd4835f79c7
Diff Diff

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

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
EqualsBenchmark - Duration of single invocation 109.42 ns 99.82 ns 0.91 0.09 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;Double&gt;*'

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_VectorOf<Double>.EqualsBenchmark


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 99.819906696785 < 102.07886251275879.
IsChangePoint: Marked as a change because one of 1/14/2023 6:09:05 AM, 1/27/2023 11:36:27 AM, 1/30/2023 9:42:46 PM falls between 1/22/2023 2:59:30 AM and 1/30/2023 9:42:46 PM.
IsImprovementStdDev: Marked as improvement because 34.294370246992244 (T) = (0 -96.86956095565043) / Math.Sqrt((28.110401756621144 / (299)) + (1.7198250497198881 / (13))) is greater than 1.9676459287777595 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (13) - 2, .975) and 0.14414130191692717 = (113.18405850476957 - 96.86956095565043) / 113.18405850476957 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 acc409ef8a94c8148c86edc6a94eb8edf2e5e2e5
Compare ddfaf2750e8dcf127a8baf0a3e5a2bd4835f79c7
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
EqualsBenchmark - Duration of single invocation 78.03 ns 68.26 ns 0.87 0.08 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;UInt64&gt;*'

Payloads

Baseline
Compare

Histogram

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


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 68.25682548727853 < 75.05533081670013.
IsChangePoint: Marked as a change because one of 12/9/2022 1:52:32 PM, 1/12/2023 10:41:19 PM, 1/27/2023 11:36:27 AM, 1/30/2023 9:42:46 PM falls between 1/22/2023 2:59:30 AM and 1/30/2023 9:42:46 PM.
IsImprovementStdDev: Marked as improvement because 30.179295925067358 (T) = (0 -67.70467639681803) / Math.Sqrt((32.58127067728039 / (299)) + (2.8284225338043645 / (13))) is greater than 1.9676459287777595 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (13) - 2, .975) and 0.20300740129388398 = (84.95019465266519 - 67.70467639681803) / 84.95019465266519 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 acc409ef8a94c8148c86edc6a94eb8edf2e5e2e5
Compare ddfaf2750e8dcf127a8baf0a3e5a2bd4835f79c7
Diff Diff

Improvements in System.Runtime.Intrinsics.Tests.Perf_Vector128Of<UInt32>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
EqualsBenchmark - Duration of single invocation 90.35 ns 81.02 ns 0.90 0.08 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Runtime.Intrinsics.Tests.Perf_Vector128Of&lt;UInt32&gt;*'

Payloads

Baseline
Compare

Histogram

System.Runtime.Intrinsics.Tests.Perf_Vector128Of<UInt32>.EqualsBenchmark


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 81.02198994443985 < 85.62451779399056.
IsChangePoint: Marked as a change because one of 12/9/2022 1:52:32 PM, 1/27/2023 11:36:27 AM, 1/30/2023 9:42:46 PM falls between 1/22/2023 2:59:30 AM and 1/30/2023 9:42:46 PM.
IsImprovementStdDev: Marked as improvement because 8.323016616307813 (T) = (0 -82.33547103583327) / Math.Sqrt((12.046029158105362 / (299)) + (13.136874276015893 / (13))) is greater than 1.9676459287777595 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (13) - 2, .975) and 0.09389368598180749 = (90.86734057807278 - 82.33547103583327) / 90.86734057807278 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 acc409ef8a94c8148c86edc6a94eb8edf2e5e2e5
Compare ddfaf2750e8dcf127a8baf0a3e5a2bd4835f79c7
Diff Diff

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

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
EqualsBenchmark - Duration of single invocation 110.54 ns 98.00 ns 0.89 0.15 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;Single&gt;*'

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_VectorOf<Single>.EqualsBenchmark


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 97.99620572627167 < 102.97108783852488.
IsChangePoint: Marked as a change because one of 1/12/2023 3:42:01 AM, 1/27/2023 11:36:27 AM, 1/30/2023 9:42:46 PM falls between 1/22/2023 2:59:30 AM and 1/30/2023 9:42:46 PM.
IsImprovementStdDev: Marked as improvement because 20.895923109679046 (T) = (0 -99.29053264022842) / Math.Sqrt((30.40318534700818 / (299)) + (4.602890224405132 / (13))) is greater than 1.9676459287777595 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (13) - 2, .975) and 0.12440077410426101 = (113.397236662303 - 99.29053264022842) / 113.397236662303 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 acc409ef8a94c8148c86edc6a94eb8edf2e5e2e5
Compare ddfaf2750e8dcf127a8baf0a3e5a2bd4835f79c7
Diff Diff

Improvements in System.Runtime.Intrinsics.Tests.Perf_Vector128Of<UInt64>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
EqualsBenchmark - Duration of single invocation 89.69 ns 79.22 ns 0.88 0.13 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Runtime.Intrinsics.Tests.Perf_Vector128Of&lt;UInt64&gt;*'

Payloads

Baseline
Compare

Histogram

System.Runtime.Intrinsics.Tests.Perf_Vector128Of<UInt64>.EqualsBenchmark


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 79.22140833356767 < 85.43540445008277.
IsChangePoint: Marked as a change because one of 12/9/2022 5:51:37 PM, 1/27/2023 11:36:27 AM, 1/30/2023 9:42:46 PM falls between 1/22/2023 2:59:30 AM and 1/30/2023 9:42:46 PM.
IsImprovementStdDev: Marked as improvement because 25.17750124325588 (T) = (0 -80.28584411214845) / Math.Sqrt((15.525521523709354 / (299)) + (1.8567085966330723 / (13))) is greater than 1.9676459287777595 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (13) - 2, .975) and 0.12156791426389348 = (91.39675726310783 - 80.28584411214845) / 91.39675726310783 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 acc409ef8a94c8148c86edc6a94eb8edf2e5e2e5
Compare ddfaf2750e8dcf127a8baf0a3e5a2bd4835f79c7
Diff Diff

Improvements in System.Numerics.Tests.Perf_Vector3

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
EqualsBenchmark - Duration of single invocation 59.05 ns 50.48 ns 0.85 0.08 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Numerics.Tests.Perf_Vector3*'

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_Vector3.EqualsBenchmark


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 50.48269358707184 < 56.72250896737144.
IsChangePoint: Marked as a change because one of 12/9/2022 1:52:32 PM, 1/12/2023 3:42:01 AM, 1/27/2023 11:36:27 AM, 1/30/2023 9:42:46 PM falls between 1/22/2023 2:59:30 AM and 1/30/2023 9:42:46 PM.
IsImprovementStdDev: Marked as improvement because 29.95331484141473 (T) = (0 -50.68724272484867) / Math.Sqrt((10.69718024602953 / (299)) + (1.8365291270600645 / (13))) is greater than 1.9676459287777595 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (13) - 2, .975) and 0.19913626510522073 = (63.29072040140283 - 50.68724272484867) / 63.29072040140283 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 acc409ef8a94c8148c86edc6a94eb8edf2e5e2e5
Compare ddfaf2750e8dcf127a8baf0a3e5a2bd4835f79c7
Diff Diff

Improvements in System.Runtime.Intrinsics.Tests.Perf_Vector128Of<UInt16>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
EqualsBenchmark - Duration of single invocation 98.05 ns 82.67 ns 0.84 0.08 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Runtime.Intrinsics.Tests.Perf_Vector128Of&lt;UInt16&gt;*'

Payloads

Baseline
Compare

Histogram

System.Runtime.Intrinsics.Tests.Perf_Vector128Of<UInt16>.EqualsBenchmark


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 82.67267031735398 < 87.17097855193825.
IsChangePoint: Marked as a change because one of 12/7/2022 12:36:41 PM, 12/8/2022 3:49:24 AM, 1/27/2023 11:36:27 AM, 1/30/2023 9:42:46 PM falls between 1/22/2023 2:59:30 AM and 1/30/2023 9:42:46 PM.
IsImprovementStdDev: Marked as improvement because 37.256538193449366 (T) = (0 -81.75706016585416) / Math.Sqrt((18.39196104468752 / (299)) + (0.7517148444519374 / (13))) is greater than 1.9676459287777595 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (13) - 2, .975) and 0.13601012748344185 = (94.62733622990159 - 81.75706016585416) / 94.62733622990159 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

@lewing
Copy link
Member

lewing commented Jan 31, 2023

dotnet/runtime@084998c...1b22d37 probably dotnet/runtime#79905 ? or the other interp change cc @BrzVlad @SamMonoRT

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