KEMBAR78
[Perf] Windows 10.0.25094/arm64 : Improvement on 8/10/2022 11:28:06 PM · Issue #7405 · dotnet/perf-autofiling-issues · GitHub
Skip to content

[Perf] Windows 10.0.25094/arm64 : Improvement on 8/10/2022 11:28:06 PM #7405

@performanceautofiler

Description

@performanceautofiler

Run Information

Architecture arm64
OS Windows 10.0.25094
Baseline 9fd407ae7a1b6a846a60fc0269b60d984b0e3c0b
Compare 7be37908e5a1cbb83b1062768c1649827eeaceaa
Diff Diff

Improvements in System.Tests.Perf_Array

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
Reverse - Duration of single invocation 105.75 ns 86.83 ns 0.82 0.59 False
IndexOfShort - Duration of single invocation 26.56 ns 16.82 ns 0.63 0.68 False
IndexOfChar - Duration of single invocation 22.27 ns 13.16 ns 0.59 0.72 False

graph
graph
graph
Test Report

Repro

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

Payloads

Baseline
Compare

Histogram

System.Tests.Perf_Array.Reverse


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 we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 6/22/2022 6:55:40 AM, 8/10/2022 5:14:51 PM, 8/18/2022 11:13:04 AM falls between 8/9/2022 9:33:37 PM and 8/18/2022 11:13:04 AM.
IsImprovementStdDev: Marked as improvement because 31.386959615774234 (T) = (0 -68.59596554323386) / Math.Sqrt((1643.6627725194826 / (299)) + (65.56959697639218 / (37))) is greater than 1.9670919629190173 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (37) - 2, .975) and 0.5523060072810145 = (153.22065218393737 - 68.59596554323386) / 153.22065218393737 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### System.Tests.Perf_Array.IndexOfShort

```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 we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 5/31/2022 5:02:26 PM, 6/6/2022 8:15:49 PM, 6/17/2022 2:19:07 PM, 8/17/2022 10:14:53 AM, 8/18/2022 11:13:04 AM falls between 8/9/2022 9:33:37 PM and 8/18/2022 11:13:04 AM.
IsImprovementStdDev: Marked as improvement because 11.941384025455461 (T) = (0 -16.20729493479791) / Math.Sqrt((7.2856275579830045 / (299)) + (1.4515482441687102 / (4))) is greater than 1.9678765312856872 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (4) - 2, .975) and 0.3143653543424668 = (23.638383849834323 - 16.20729493479791) / 23.638383849834323 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### System.Tests.Perf_Array.IndexOfChar

```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 we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 5/31/2022 10:47:41 AM, 6/6/2022 8:15:49 PM, 6/30/2022 10:26:14 PM, 8/11/2022 10:02:44 AM, 8/18/2022 11:13:04 AM falls between 8/9/2022 9:33:37 PM and 8/18/2022 11:13:04 AM.
IsImprovementStdDev: Marked as improvement because 4.888432564741097 (T) = (0 -18.322311755593066) / Math.Sqrt((9.464402570143697 / (299)) + (8.505378133252316 / (34))) is greater than 1.9671567996108528 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (34) - 2, .975) and 0.124062865710557 = (20.917382125209315 - 18.322311755593066) / 20.917382125209315 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 arm64
OS Windows 10.0.25094
Baseline 9fd407ae7a1b6a846a60fc0269b60d984b0e3c0b
Compare 7be37908e5a1cbb83b1062768c1649827eeaceaa
Diff Diff

Improvements in System.Memory.Span<Int32>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
Reverse - Duration of single invocation 235.75 ns 163.58 ns 0.69 0.63 False
LastIndexOfValue - Duration of single invocation 115.81 ns 58.08 ns 0.50 0.66 False

graph
graph
Test Report

Repro

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

Payloads

Baseline
Compare

Histogram

System.Memory.Span<Int32>.Reverse(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 we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 6/22/2022 6:55:40 AM, 8/10/2022 5:14:51 PM, 8/18/2022 11:13:04 AM falls between 8/9/2022 9:33:37 PM and 8/18/2022 11:13:04 AM.
IsImprovementStdDev: Marked as improvement because 29.220096576861827 (T) = (0 -137.68064416364183) / Math.Sqrt((6847.434229540765 / (299)) + (340.75373276634394 / (37))) is greater than 1.9670919629190173 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (37) - 2, .975) and 0.5459981203497988 = (303.260075199957 - 137.68064416364183) / 303.260075199957 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### System.Memory.Span&lt;Int32&gt;.LastIndexOfValue(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 we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 8/17/2022 10:14:53 AM, 8/18/2022 11:13:04 AM falls between 8/9/2022 9:33:37 PM and 8/18/2022 11:13:04 AM.
IsImprovementStdDev: Marked as improvement because 13.875710502574806 (T) = (0 -69.99694582425289) / Math.Sqrt((111.45597203297228 / (299)) + (66.30161479916354 / (4))) is greater than 1.9678765312856872 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (4) - 2, .975) and 0.44936617689685776 = (127.12067963747548 - 69.99694582425289) / 127.12067963747548 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 arm64
OS Windows 10.0.25094
Baseline 9fd407ae7a1b6a846a60fc0269b60d984b0e3c0b
Compare 7be37908e5a1cbb83b1062768c1649827eeaceaa
Diff Diff

Improvements in System.Memory.Span<Byte>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
Reverse - Duration of single invocation 246.23 ns 43.96 ns 0.18 0.68 False

graph
Test Report

Repro

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

Payloads

Baseline
Compare

Histogram

System.Memory.Span<Byte>.Reverse(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 we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 6/22/2022 6:55:40 AM, 8/10/2022 5:14:51 PM, 8/18/2022 11:13:04 AM falls between 8/9/2022 9:33:37 PM and 8/18/2022 11:13:04 AM.
IsImprovementStdDev: Marked as improvement because 82.8473279479604 (T) = (0 -33.996704204738755) / Math.Sqrt((2343.3931044860055 / (299)) + (19.158088121052103 / (37))) is greater than 1.9670919629190173 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (37) - 2, .975) and 0.8756840704307884 = (273.4702167497486 - 33.996704204738755) / 273.4702167497486 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 arm64
OS Windows 10.0.25094
Baseline 9fd407ae7a1b6a846a60fc0269b60d984b0e3c0b
Compare 7be37908e5a1cbb83b1062768c1649827eeaceaa
Diff Diff

Improvements in System.Collections.IterateForEach<Int32>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
ConcurrentDictionary - Duration of single invocation 28.57 μs 23.07 μs 0.81 0.65 False

graph
Test Report

Repro

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

Payloads

Baseline
Compare

Histogram

System.Collections.IterateForEach<Int32>.ConcurrentDictionary(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 we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 8/10/2022 5:14:51 PM, 8/18/2022 11:13:04 AM falls between 8/9/2022 9:33:37 PM and 8/18/2022 11:13:04 AM.
IsImprovementStdDev: Marked as improvement because 18.403811107525176 (T) = (0 -21388.95300485393) / Math.Sqrt((7315062.335286484 / (299)) + (2779745.331549286 / (37))) is greater than 1.9670919629190173 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (37) - 2, .975) and 0.21355190974424765 = (27196.90373702638 - 21388.95300485393) / 27196.90373702638 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 arm64
OS Windows 10.0.25094
Baseline 9fd407ae7a1b6a846a60fc0269b60d984b0e3c0b
Compare 7be37908e5a1cbb83b1062768c1649827eeaceaa
Diff Diff

Improvements in BenchmarksGame.BinaryTrees_2

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
RunBench - Duration of single invocation 302.28 ms 252.44 ms 0.84 0.54 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'BenchmarksGame.BinaryTrees_2*'

Payloads

Baseline
Compare

Histogram

BenchmarksGame.BinaryTrees_2.RunBench


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 we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 6/22/2022 11:10:17 PM, 8/10/2022 5:14:51 PM, 8/18/2022 11:13:04 AM falls between 8/9/2022 9:33:37 PM and 8/18/2022 11:13:04 AM.
IsImprovementStdDev: Marked as improvement because 18.275465793291815 (T) = (0 -247854770.25983882) / Math.Sqrt((689560499765791.8 / (299)) + (147520533866402.12 / (37))) is greater than 1.9670919629190173 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (37) - 2, .975) and 0.1560991589880753 = (293701295.47760046 - 247854770.25983882) / 293701295.47760046 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 arm64
OS Windows 10.0.25094
Baseline 9fd407ae7a1b6a846a60fc0269b60d984b0e3c0b
Compare 7be37908e5a1cbb83b1062768c1649827eeaceaa
Diff Diff

Improvements in BenchmarksGame.FannkuchRedux_9

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
RunBench - Duration of single invocation 128.82 ms 62.10 ms 0.48 0.66 False

graph
Test Report

Repro

git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net6.0 --filter 'BenchmarksGame.FannkuchRedux_9*'

Payloads

Baseline
Compare

Histogram

BenchmarksGame.FannkuchRedux_9.RunBench(n: 11, expectedSum: 556355)


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 we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 8/10/2022 5:14:51 PM, 8/18/2022 11:13:04 AM falls between 8/9/2022 9:33:37 PM and 8/18/2022 11:13:04 AM.
IsImprovementStdDev: Marked as improvement because 9.326437938067002 (T) = (0 -75839386.09669577) / Math.Sqrt((658128230302220.8 / (299)) + (287732473443652.06 / (37))) is greater than 1.9670919629190173 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (37) - 2, .975) and 0.2797724204288068 = (105299197.43124636 - 75839386.09669577) / 105299197.43124636 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

Metadata

Metadata

Assignees

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions