[Perf] Windows/arm64: 3 Improvements on 7/6/2023 2:30:01 AM

[performanceautofiler]

Run Information

Name	Value
Architecture	arm64
OS	Windows 10.0.19041
Queue	SurfaceWindows
Baseline	84fd85932fd3b371cad69cc2412404ea50158c63
Compare	2f14594e1902355cfd84df13c67a0c9367ee4d73
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Improvements in Devirtualization.EqualityComparer

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
ValueTupleCompareNoOpt - Duration of single invocation	15.46 ns	11.69 ns	0.76	0.19	False

Test Report

Repro

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

git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'Devirtualization.EqualityComparer*'

Payloads

Baseline
Compare

Devirtualization.EqualityComparer.ValueTupleCompareNoOpt

ETL Files

Histogram

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 11.689950205565108 < 14.717001011103203.
IsChangePoint: Marked as a change because one of 5/3/2023 1:18:01 AM, 7/5/2023 5:05:14 PM, 7/12/2023 7:14:29 PM falls between 7/3/2023 9:53:34 PM and 7/12/2023 7:14:29 PM.
IsImprovementStdDev: Marked as improvement because 7.08785751958602 (T) = (0 -11.990378695764356) / Math.Sqrt((6.015352578436201 / (299)) + (0.032484472775587137 / (13))) is greater than 1.9676459287777595 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (13) - 2, .975) and 0.08164171622468107 = (13.056318985301235 - 11.990378695764356) / 13.056318985301235 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	Windows 10.0.19041
Queue	SurfaceWindows
Baseline	84fd85932fd3b371cad69cc2412404ea50158c63
Compare	2f14594e1902355cfd84df13c67a0c9367ee4d73
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Improvements in Microsoft.Extensions.Primitives.StringSegmentBenchmark

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
LastIndexOf - Duration of single invocation	4.42 ns	3.37 ns	0.76	0.33	False

Test Report

Repro

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

git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'Microsoft.Extensions.Primitives.StringSegmentBenchmark*'

Payloads

Baseline
Compare

Microsoft.Extensions.Primitives.StringSegmentBenchmark.LastIndexOf

ETL Files

Histogram

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 3.3722262417929527 < 4.1672943266672.
IsChangePoint: Marked as a change because one of 3/16/2023 2:30:29 AM, 4/3/2023 6:15:03 PM, 6/16/2023 10:57:50 PM, 7/5/2023 5:05:14 PM, 7/12/2023 7:14:29 PM falls between 7/3/2023 9:53:34 PM and 7/12/2023 7:14:29 PM.
IsImprovementStdDev: Marked as improvement because 9.528740927341163 (T) = (0 -3.29287730820393) / Math.Sqrt((0.39177682799786934 / (299)) + (0.008212156731155268 / (13))) is greater than 1.9676459287777595 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (13) - 2, .975) and 0.11309908690201088 = (3.712790526623482 - 3.29287730820393) / 3.712790526623482 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	Windows 10.0.19041
Queue	SurfaceWindows
Baseline	84fd85932fd3b371cad69cc2412404ea50158c63
Compare	2f14594e1902355cfd84df13c67a0c9367ee4d73
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
EmptyTakeSelectToArray - Duration of single invocation	36.25 ns	7.73 ns	0.21	0.08	False

Test Report

Repro

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

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

Payloads

Baseline
Compare

System.Linq.Tests.Perf_Enumerable.EmptyTakeSelectToArray

ETL Files

Histogram

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 7.731224900705537 < 34.52907691968702.
IsChangePoint: Marked as a change because one of 5/19/2023 4:22:12 AM, 7/1/2023 8:07:46 AM, 7/5/2023 5:05:14 PM, 7/12/2023 7:14:29 PM falls between 7/3/2023 9:53:34 PM and 7/12/2023 7:14:29 PM.
IsImprovementStdDev: Marked as improvement because 54.71273177501623 (T) = (0 -8.765301265056548) / Math.Sqrt((12.908774906075111 / (299)) + (0.12171277808369485 / (13))) is greater than 1.9676459287777595 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (13) - 2, .975) and 0.5885959671706174 = (21.305822416893253 - 8.765301265056548) / 21.305822416893253 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

[EgorBo]

Comparer is likely dotnet/runtime#88006
Improvements in System.Linq.Tests.Perf_Enumerable are from dotnet/runtime#88425