Skip to content

[Perf] Linux/arm64: 29 Improvements on 4/26/2023 12:55:36 AM #17095

Open
@performanceautofiler

Description

@performanceautofiler

Run Information

Name Value
Architecture arm64
OS ubuntu 20.04
Queue AmpereUbuntu
Baseline 195bf987887ea645a747ff0586440f7920c47b01
Compare 63a7a13190448f1ba5b3b449f1b9628d042d209d
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

Improvements in System.Collections.Sort<Int32>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
List - Duration of single invocation 6.45 μs 5.80 μs 0.90 0.17 False

graph
Test Report

Repro

General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

Payloads

Baseline
Compare

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

Payloads

Baseline
Compare

Histogram

System.Collections.Sort<Int32>.List(Size: 512)


Description of detection logic

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.
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 we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 4/25/2023 6:46:56 PM, 4/27/2023 1:05:59 AM falls between 4/18/2023 7:36:21 AM and 4/27/2023 1:05:59 AM.
IsImprovementStdDev: Marked as improvement because 6.60857280715939 (T) = (0 -5917.036122539682) / Math.Sqrt((31026.933693964485 / (299)) + (15982.93035389738 / (3))) is greater than 1.9679030112610798 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (3) - 2, .975) and 0.07605147266278466 = (6404.0754949762795 - 5917.036122539682) / 6404.0754949762795 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

Docs

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


Run Information

Name Value
Architecture arm64
OS ubuntu 20.04
Queue AmpereUbuntu
Baseline 195bf987887ea645a747ff0586440f7920c47b01
Compare 63a7a13190448f1ba5b3b449f1b9628d042d209d
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

Improvements in System.Globalization.Tests.StringSearch

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
IndexOf_Word_NotFound - Duration of single invocation 630.60 ns 560.37 ns 0.89 0.00 False
IndexOf_Word_NotFound - Duration of single invocation 630.53 ns 560.20 ns 0.89 0.00 False
IndexOf_Word_NotFound - Duration of single invocation 972.86 ns 813.76 ns 0.84 0.00 False
IndexOf_Word_NotFound - Duration of single invocation 630.21 ns 565.25 ns 0.90 0.00 False

graph
graph
graph
graph
Test Report

Repro

General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

Payloads

Baseline
Compare

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

Payloads

Baseline
Compare

Histogram

System.Globalization.Tests.StringSearch.IndexOf_Word_NotFound(Options: (, None, False))


Description of detection logic

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.
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 we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 4/25/2023 6:46:56 PM, 4/27/2023 1:05:59 AM falls between 4/18/2023 7:36:21 AM and 4/27/2023 1:05:59 AM.
IsImprovementStdDev: Marked as improvement because 253.57583013706957 (T) = (0 -560.8285427113) / Math.Sqrt((3.067647567245063 / (299)) + (0.19521845260956933 / (3))) is greater than 1.9679030112610798 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (3) - 2, .975) and 0.11039879301561933 = (630.4269129899537 - 560.8285427113) / 630.4269129899537 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

System.Globalization.Tests.StringSearch.IndexOf_Word_NotFound(Options: (en-US, None, False))


Description of detection logic

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.
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 we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 4/25/2023 6:46:56 PM, 4/27/2023 1:05:59 AM falls between 4/18/2023 7:36:21 AM and 4/27/2023 1:05:59 AM.
IsImprovementStdDev: Marked as improvement because 335.43410173328925 (T) = (0 -560.3666850425417) / Math.Sqrt((2.549714317952406 / (299)) + (0.10779984928880615 / (3))) is greater than 1.9679030112610798 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (3) - 2, .975) and 0.11207290608992006 = (631.0953780843744 - 560.3666850425417) / 631.0953780843744 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

System.Globalization.Tests.StringSearch.IndexOf_Word_NotFound(Options: (en-US, IgnoreCase, False))


Description of detection logic

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.
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 we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 1/21/2023 1:51:00 AM, 4/25/2023 6:46:56 PM, 4/27/2023 1:05:59 AM falls between 4/18/2023 7:36:21 AM and 4/27/2023 1:05:59 AM.
IsImprovementStdDev: Marked as improvement because 195.46215480786444 (T) = (0 -812.9808314600823) / Math.Sqrt((75.14136434811185 / (299)) + (1.5017150872871674 / (3))) is greater than 1.9679030112610798 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (3) - 2, .975) and 0.17251174105812017 = (982.4681168282093 - 812.9808314600823) / 982.4681168282093 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

System.Globalization.Tests.StringSearch.IndexOf_Word_NotFound(Options: (en-US, IgnoreNonSpace, False))


Description of detection logic

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.
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 we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 4/25/2023 6:46:56 PM, 4/27/2023 1:05:59 AM falls between 4/18/2023 7:36:21 AM and 4/27/2023 1:05:59 AM.
IsImprovementStdDev: Marked as improvement because 44.66639370096367 (T) = (0 -562.2130464328677) / Math.Sqrt((3.2880491914222154 / (299)) + (6.953843860861608 / (3))) is greater than 1.9679030112610798 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (3) - 2, .975) and 0.10813331268853882 = (630.3778966424491 - 562.2130464328677) / 630.3778966424491 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

Docs

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


Run Information

Name Value
Architecture arm64
OS ubuntu 20.04
Queue AmpereUbuntu
Baseline 195bf987887ea645a747ff0586440f7920c47b01
Compare 63a7a13190448f1ba5b3b449f1b9628d042d209d
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

Improvements in System.Collections.TryAddDefaultSize<Int32>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
Dictionary - Duration of single invocation 13.56 μs 11.38 μs 0.84 0.00 False

graph
Test Report

Repro

General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

Payloads

Baseline
Compare

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

Payloads

Baseline
Compare

Histogram

System.Collections.TryAddDefaultSize<Int32>.Dictionary(Count: 512)


Description of detection logic

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.
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 we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 4/25/2023 6:46:56 PM, 4/27/2023 1:05:59 AM falls between 4/18/2023 7:36:21 AM and 4/27/2023 1:05:59 AM.
IsImprovementStdDev: Marked as improvement because 125.60612064878433 (T) = (0 -11397.621717303518) / Math.Sqrt((44835.78730678877 / (299)) + (304.13367980100054 / (3))) is greater than 1.9679030112610798 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (3) - 2, .975) and 0.14872644055377252 = (13388.90605825691 - 11397.621717303518) / 13388.90605825691 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

Docs

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


Run Information

Name Value
Architecture arm64
OS ubuntu 20.04
Queue AmpereUbuntu
Baseline 195bf987887ea645a747ff0586440f7920c47b01
Compare 63a7a13190448f1ba5b3b449f1b9628d042d209d
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

Improvements in System.Tests.Perf_Single

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
ToStringWithFormat - Duration of single invocation 216.76 ns 194.40 ns 0.90 0.02 False

graph
Test Report

Repro

General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

Payloads

Baseline
Compare

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

Payloads

Baseline
Compare

Histogram

System.Tests.Perf_Single.ToStringWithFormat(value: 12345, format: "G17")


Description of detection logic

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.
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 we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 4/12/2023 8:39:35 PM, 4/25/2023 6:46:56 PM, 4/27/2023 1:05:59 AM falls between 4/18/2023 7:36:21 AM and 4/27/2023 1:05:59 AM.
IsImprovementStdDev: Marked as improvement because 26.260700155123168 (T) = (0 -195.24170803231854) / Math.Sqrt((6.913693463625097 / (299)) + (1.154983133257625 / (3))) is greater than 1.9679030112610798 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (3) - 2, .975) and 0.07912719077439576 = (212.01810508066197 - 195.24170803231854) / 212.01810508066197 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

Docs

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


Run Information

Name Value
Architecture arm64
OS ubuntu 20.04
Queue AmpereUbuntu
Baseline 195bf987887ea645a747ff0586440f7920c47b01
Compare 63a7a13190448f1ba5b3b449f1b9628d042d209d
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

Improvements in System.Memory.Span<Char>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
SequenceEqual - Duration of single invocation 62.03 ns 53.87 ns 0.87 0.00 False

graph
Test Report

Repro

General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

Payloads

Baseline
Compare

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Memory.Span&lt;Char&gt;*'

Payloads

Baseline
Compare

Histogram

System.Memory.Span<Char>.SequenceEqual(Size: 512)


Description of detection logic

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.
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 we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 4/25/2023 6:46:56 PM, 4/27/2023 1:05:59 AM falls between 4/18/2023 7:36:21 AM and 4/27/2023 1:05:59 AM.
IsImprovementStdDev: Marked as improvement because 31.92117568296261 (T) = (0 -54.334160097541435) / Math.Sqrt((0.4122321390792662 / (299)) + (0.1691065148301776 / (3))) is greater than 1.9679030112610798 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (3) - 2, .975) and 0.12371392331171674 = (62.00504782968205 - 54.334160097541435) / 62.00504782968205 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

Docs

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


Run Information

Name Value
Architecture arm64
OS ubuntu 20.04
Queue AmpereUbuntu
Baseline 195bf987887ea645a747ff0586440f7920c47b01
Compare 63a7a13190448f1ba5b3b449f1b9628d042d209d
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

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
SelectToList - Duration of single invocation 656.79 ns 562.60 ns 0.86 0.46 False
SelectToList - Duration of single invocation 391.46 ns 311.60 ns 0.80 0.41 False

graph
graph
Test Report

Repro

General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

Payloads

Baseline
Compare

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

Payloads

Baseline
Compare

Histogram

System.Linq.Tests.Perf_Enumerable.SelectToList(input: IList)


Description of detection logic

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.
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 we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 4/25/2023 6:46:56 PM, 4/27/2023 1:05:59 AM falls between 4/18/2023 7:36:21 AM and 4/27/2023 1:05:59 AM.
IsImprovementStdDev: Marked as improvement because 3.4432541226982694 (T) = (0 -508.1394543071963) / Math.Sqrt((1425.3683662752633 / (299)) + (2254.7849653006706 / (3))) is greater than 1.9679030112610798 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (3) - 2, .975) and 0.15708503252480843 = (602.8359608196798 - 508.1394543071963) / 602.8359608196798 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

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


Description of detection logic

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.
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 we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 4/26/2023 12:55:36 AM, 4/27/2023 1:05:59 AM falls between 4/18/2023 7:36:21 AM and 4/27/2023 1:05:59 AM.
IsImprovementStdDev: Marked as improvement because 30.035343482453023 (T) = (0 -309.09692971800587) / Math.Sqrt((773.7001823610248 / (299)) + (12.516483492195778 / (2))) is greater than 1.9679296690655894 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (2) - 2, .975) and 0.2242089313878641 = (398.4280590790635 - 309.09692971800587) / 398.4280590790635 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

Docs

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


Run Information

Name Value
Architecture arm64
OS ubuntu 20.04
Queue AmpereUbuntu
Baseline 195bf987887ea645a747ff0586440f7920c47b01
Compare 63a7a13190448f1ba5b3b449f1b9628d042d209d
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

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
GetString - Duration of single invocation 27.13 ns 24.66 ns 0.91 0.27 False

graph
Test Report

Repro

General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

Payloads

Baseline
Compare

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

Payloads

Baseline
Compare

Histogram

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


Description of detection logic

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.
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 we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 1/17/2023 11:08:46 AM, 4/25/2023 6:46:56 PM, 4/27/2023 1:05:59 AM falls between 4/18/2023 7:36:21 AM and 4/27/2023 1:05:59 AM.
IsImprovementStdDev: Marked as improvement because 7.964103968693639 (T) = (0 -24.463333504494102) / Math.Sqrt((0.8513902822252984 / (299)) + (0.6572996502546483 / (3))) is greater than 1.9679030112610798 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (3) - 2, .975) and 0.1329770921599296 = (28.215325435215107 - 24.463333504494102) / 28.215325435215107 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

Docs

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


Run Information

Name Value
Architecture arm64
OS ubuntu 20.04
Queue AmpereUbuntu
Baseline 195bf987887ea645a747ff0586440f7920c47b01
Compare 63a7a13190448f1ba5b3b449f1b9628d042d209d
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

Improvements in System.Collections.TryAddDefaultSize<String>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
Dictionary - Duration of single invocation 27.66 μs 24.96 μs 0.90 0.01 False

graph
Test Report

Repro

General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

Payloads

Baseline
Compare

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Collections.TryAddDefaultSize&lt;String&gt;*'

Payloads

Baseline
Compare

Histogram

System.Collections.TryAddDefaultSize<String>.Dictionary(Count: 512)


Description of detection logic

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.
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 we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 3/16/2023 8:14:39 PM, 4/25/2023 6:46:56 PM, 4/27/2023 1:05:59 AM falls between 4/18/2023 7:36:21 AM and 4/27/2023 1:05:59 AM.
IsImprovementStdDev: Marked as improvement because 63.52772782890929 (T) = (0 -24950.04424143476) / Math.Sqrt((266075.37093546434 / (299)) + (203.37658100858704 / (3))) is greater than 1.9679030112610798 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (3) - 2, .975) and 0.07304025243642087 = (26915.995335302803 - 24950.04424143476) / 26915.995335302803 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

Docs

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


Run Information

Name Value
Architecture arm64
OS ubuntu 20.04
Queue AmpereUbuntu
Baseline 195bf987887ea645a747ff0586440f7920c47b01
Compare 63a7a13190448f1ba5b3b449f1b9628d042d209d
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

Improvements in System.Security.Cryptography.X509Certificates.Tests.X509Certificate2Tests

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
CertProp - Duration of single invocation 62.54 ns 42.39 ns 0.68 0.04 False

graph
Test Report

Repro

General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

Payloads

Baseline
Compare

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Security.Cryptography.X509Certificates.Tests.X509Certificate2Tests*'

Payloads

Baseline
Compare

Histogram

System.Security.Cryptography.X509Certificates.Tests.X509Certificate2Tests.CertProp


Description of detection logic

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.
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 we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 2/18/2023 9:46:56 PM, 4/25/2023 6:46:56 PM, 4/27/2023 1:05:59 AM falls between 4/18/2023 7:36:21 AM and 4/27/2023 1:05:59 AM.
IsImprovementStdDev: Marked as improvement because 50.57319388571694 (T) = (0 -41.9206349759531) / Math.Sqrt((18.307644473564398 / (299)) + (0.1676030597830944 / (3))) is greater than 1.9679030112610798 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (3) - 2, .975) and 0.29219821667969825 = (59.22651788090048 - 41.9206349759531) / 59.22651788090048 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

Docs

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


Run Information

Name Value
Architecture arm64
OS ubuntu 20.04
Queue AmpereUbuntu
Baseline 195bf987887ea645a747ff0586440f7920c47b01
Compare 63a7a13190448f1ba5b3b449f1b9628d042d209d
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

Improvements in System.Text.RegularExpressions.Tests.Perf_Regex_Common

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
CtorInvoke - Duration of single invocation 362.87 μs 280.60 μs 0.77 0.33 False
CtorInvoke - Duration of single invocation 361.08 μs 307.90 μs 0.85 0.24 False

graph
graph
Test Report

Repro

General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

Payloads

Baseline
Compare

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

Payloads

Baseline
Compare

Histogram

System.Text.RegularExpressions.Tests.Perf_Regex_Common.CtorInvoke(Options: Compiled)


Description of detection logic

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.
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 we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 1/21/2023 1:51:00 AM, 4/12/2023 2:59:13 PM, 4/25/2023 6:46:56 PM, 4/27/2023 1:05:59 AM falls between 4/18/2023 7:36:21 AM and 4/27/2023 1:05:59 AM.
IsImprovementStdDev: Marked as improvement because 4.4710811569082205 (T) = (0 -263941.3752885983) / Math.Sqrt((529327065.434973 / (299)) + (208938282.09139478 / (3))) is greater than 1.9679030112610798 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (3) - 2, .975) and 0.1252273796406848 = (301725.6932209237 - 263941.3752885983) / 301725.6932209237 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

System.Text.RegularExpressions.Tests.Perf_Regex_Common.CtorInvoke(Options: IgnoreCase, Compiled)


Description of detection logic

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.
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 we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 1/21/2023 1:51:00 AM, 4/12/2023 2:59:13 PM, 4/25/2023 6:46:56 PM, 4/27/2023 1:05:59 AM falls between 4/18/2023 7:36:21 AM and 4/27/2023 1:05:59 AM.
IsImprovementStdDev: Marked as improvement because 7.664054320382402 (T) = (0 -302577.6700604377) / Math.Sqrt((480900598.0601342 / (299)) + (25139162.813897338 / (3))) is greater than 1.9679030112610798 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (3) - 2, .975) and 0.0741171696904298 = (326799.0939623218 - 302577.6700604377) / 326799.0939623218 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

Docs

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

Metadata

Metadata

Assignees

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions