[Perf] Windows/x64: 35 Improvements on 3/6/2023 11:36:59 AM

[performanceautofiler]

Run Information

Architecture	x64
OS	Windows 10.0.19042
Baseline	6123cb00bbec8ae3500c970890f5b0efcf7950e8
Compare	ffbcb8336ac67496b0565112f663f74fda6cac34
Diff	Diff

Improvements in System.Memory.Slice<String>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio	Baseline ETL	Compare ETL
SpanStart - Duration of single invocation	5.57 ns	3.90 ns	0.70	0.05	False

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Memory.Slice<String>*'

Details

Payloads

Baseline
Compare

Histogram

System.Memory.Slice<String>.SpanStart

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 3.9007252161249397 < 5.155807808307661.
IsChangePoint: Marked as a change because one of 2/24/2023 9:01:57 AM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 25.433819065971342 (T) = (0 -3.9838343342607083) / Math.Sqrt((0.15252405386437687 / (299)) + (0.002390744954941845 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.15705136345301762 = (4.726070084862954 - 3.9838343342607083) / 4.726070084862954 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	Windows 10.0.19042
Baseline	6123cb00bbec8ae3500c970890f5b0efcf7950e8
Compare	ffbcb8336ac67496b0565112f663f74fda6cac34
Diff	Diff

Improvements in System.Text.Json.Serialization.Tests.WriteJson<ArrayList>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio	Baseline ETL	Compare ETL
SerializeToStream - Duration of single invocation	8.19 μs	7.20 μs	0.88	0.29	False

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Text.Json.Serialization.Tests.WriteJson<ArrayList>*'

Details

Payloads

Baseline
Compare

Histogram

System.Text.Json.Serialization.Tests.WriteJson<ArrayList>.SerializeToStream(Mode: Reflection)

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 7.198746939087847 < 7.830227525484188.
IsChangePoint: Marked as a change because one of 1/17/2023 12:02:27 AM, 2/9/2023 4:27:10 AM, 2/20/2023 10:31:48 AM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 6.410266586154394 (T) = (0 -7293.488926754658) / Math.Sqrt((182003.8599730799 / (299)) + (78642.03082110213 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.08729828442009509 = (7991.098079749506 - 7293.488926754658) / 7991.098079749506 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	Windows 10.0.19042
Baseline	6123cb00bbec8ae3500c970890f5b0efcf7950e8
Compare	ffbcb8336ac67496b0565112f663f74fda6cac34
Diff	Diff

Improvements in System.IO.Tests.Perf_Path

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio	Baseline ETL	Compare ETL
GetPathRoot - Duration of single invocation	32.87 ns	26.28 ns	0.80	0.17	False

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.IO.Tests.Perf_Path*'

Details

Payloads

Baseline
Compare

Histogram

System.IO.Tests.Perf_Path.GetPathRoot

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 26.28423792793575 < 30.646531382006756.
IsChangePoint: Marked as a change because one of 2/24/2023 9:01:57 AM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 19.977448080575545 (T) = (0 -26.237918486261922) / Math.Sqrt((4.37561815225924 / (299)) + (0.019296391494217306 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.09124656037992705 = (28.872428254281314 - 26.237918486261922) / 28.872428254281314 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	Windows 10.0.19042
Baseline	6123cb00bbec8ae3500c970890f5b0efcf7950e8
Compare	ffbcb8336ac67496b0565112f663f74fda6cac34
Diff	Diff

Improvements in PerfLabTests.CastingPerf

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio	Baseline ETL	Compare ETL
ScalarValueTypeObj - Duration of single invocation	306.69 μs	278.44 μs	0.91	0.04	False
CheckArrayIsInterfaceNo - Duration of single invocation	55.70 μs	27.86 μs	0.50	0.03	False
IntObj - Duration of single invocation	306.57 μs	278.64 μs	0.91	0.04	False
CheckArrayIsInterfaceYes - Duration of single invocation	55.73 μs	27.86 μs	0.50	0.03	False
ObjrefValueTypeObj - Duration of single invocation	306.25 μs	278.55 μs	0.91	0.05	False

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'PerfLabTests.CastingPerf*'

Details

Payloads

Baseline
Compare

Histogram

PerfLabTests.CastingPerf.ScalarValueTypeObj

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 278.4376201923077 < 291.1302566964286.
IsChangePoint: Marked as a change because one of 12/28/2022 5:13:50 PM, 1/3/2023 6:29:42 AM, 1/18/2023 3:20:52 PM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 34.72640911615837 (T) = (0 -278538.25302116043) / Math.Sqrt((123601300.26199426 / (299)) + (11332.457451012315 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.07434453897968876 = (300909.20947426744 - 278538.25302116043) / 300909.20947426744 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### PerfLabTests.CastingPerf.CheckArrayIsInterfaceNo

```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 27.856097211611917 < 52.9243270057715.
IsChangePoint: Marked as a change because one of 1/3/2023 6:29:42 AM, 1/18/2023 3:20:52 PM, 1/27/2023 7:12:54 PM, 2/20/2023 10:31:48 AM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 16.533078941690537 (T) = (0 -27858.220795466732) / Math.Sqrt((194165767.0091151 / (299)) + (90.6871120437611 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.3235246663795351 = (41181.4288133328 - 27858.220795466732) / 41181.4288133328 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### PerfLabTests.CastingPerf.IntObj

```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 278.63593750000007 < 291.1252633625565.
IsChangePoint: Marked as a change because one of 12/28/2022 5:13:50 PM, 1/3/2023 6:29:42 AM, 1/18/2023 3:20:52 PM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 34.38491973959086 (T) = (0 -278543.83244663) / Math.Sqrt((127421726.91058835 / (299)) + (7420.111834147746 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.07466213520582715 = (301018.5177157835 - 278543.83244663) / 301018.5177157835 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### PerfLabTests.CastingPerf.CheckArrayIsInterfaceYes

```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 27.861825184619306 < 52.93342139309016.
IsChangePoint: Marked as a change because one of 1/3/2023 6:29:42 AM, 1/18/2023 3:20:52 PM, 1/27/2023 7:12:54 PM, 2/20/2023 10:31:48 AM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 16.63511992266672 (T) = (0 -27864.459760011236) / Math.Sqrt((194295399.72401035 / (299)) + (108.89667501191882 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.324897256933762 = (41274.39866923678 - 27864.459760011236) / 41274.39866923678 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### PerfLabTests.CastingPerf.ObjrefValueTypeObj

```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 278.5521538220551 < 291.00532787754526.
IsChangePoint: Marked as a change because one of 1/18/2023 3:20:52 PM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 33.230731976612134 (T) = (0 -278491.28345417115) / Math.Sqrt((141001851.27498916 / (299)) + (16847.08159665961 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.07591416708659109 = (301369.4978702991 - 278491.28345417115) / 301369.4978702991 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	Windows 10.0.19042
Baseline	6123cb00bbec8ae3500c970890f5b0efcf7950e8
Compare	ffbcb8336ac67496b0565112f663f74fda6cac34
Diff	Diff

Improvements in System.MathBenchmarks.Single

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio	Baseline ETL	Compare ETL
Exp - Duration of single invocation	20.91 μs	19.49 μs	0.93	0.04	False

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.MathBenchmarks.Single*'

Details

Payloads

Baseline
Compare

Histogram

System.MathBenchmarks.Single.Exp

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 19.494944929343305 < 19.856181414327093.
IsChangePoint: Marked as a change because one of 12/20/2022 1:34:12 PM, 12/28/2022 5:13:50 PM, 1/3/2023 6:29:42 AM, 1/13/2023 4:37:08 PM, 1/18/2023 3:20:52 PM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 42.170238389204826 (T) = (0 -19502.17104120686) / Math.Sqrt((255833.86050067152 / (299)) + (86.83581606079412 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.059892140722969556 = (20744.610151652792 - 19502.17104120686) / 20744.610151652792 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	Windows 10.0.19042
Baseline	6123cb00bbec8ae3500c970890f5b0efcf7950e8
Compare	ffbcb8336ac67496b0565112f663f74fda6cac34
Diff	Diff

Improvements in System.Collections.AddGivenSize<Int32>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio	Baseline ETL	Compare ETL
ICollection - Duration of single invocation	1.64 μs	1.36 μs	0.83	0.14	False

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Collections.AddGivenSize<Int32>*'

Details

Payloads

Baseline
Compare

Histogram

System.Collections.AddGivenSize<Int32>.ICollection(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 1.3629254837166687 < 1.5605909987818485.
IsChangePoint: Marked as a change because one of 1/3/2023 6:29:42 AM, 1/13/2023 4:37:08 PM, 1/18/2023 3:20:52 PM, 1/27/2023 7:12:54 PM, 2/20/2023 10:31:48 AM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 16.15510820295686 (T) = (0 -1359.80667262659) / Math.Sqrt((19353.16859415086 / (299)) + (19.294360982393027 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.0889173583365465 = (1492.5173748715667 - 1359.80667262659) / 1492.5173748715667 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	Windows 10.0.19042
Baseline	6123cb00bbec8ae3500c970890f5b0efcf7950e8
Compare	ffbcb8336ac67496b0565112f663f74fda6cac34
Diff	Diff

Improvements in System.Text.Json.Tests.Perf_Reader

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio	Baseline ETL	Compare ETL
ReadSingleSpanSequenceEmptyLoop - Duration of single invocation	1.03 μs	929.99 ns	0.90	0.06	False

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Text.Json.Tests.Perf_Reader*'

Details

Payloads

Baseline
Compare

Histogram

System.Text.Json.Tests.Perf_Reader.ReadSingleSpanSequenceEmptyLoop(IsDataCompact: False, TestCase: Json400B)

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 929.9895170329452 < 0.9779463403841516.
IsChangePoint: Marked as a change because one of 1/21/2023 1:51:00 AM, 2/8/2023 6:12:15 AM, 2/24/2023 9:01:57 AM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 36.86598679912925 (T) = (0 -932.9259215782813) / Math.Sqrt((801.2684726399103 / (299)) + (15.132824981615949 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.07999553947479725 = (1014.044998266315 - 932.9259215782813) / 1014.044998266315 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	Windows 10.0.19042
Baseline	6123cb00bbec8ae3500c970890f5b0efcf7950e8
Compare	ffbcb8336ac67496b0565112f663f74fda6cac34
Diff	Diff

Improvements in System.Tests.Perf_Char

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio	Baseline ETL	Compare ETL
Char_IsLower - Duration of single invocation	28.06 ns	21.11 ns	0.75	0.05	False
Char_IsUpper - Duration of single invocation	24.69 ns	16.17 ns	0.65	0.09	False

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Tests.Perf_Char*'

Details

Payloads

Baseline
Compare

Histogram

System.Tests.Perf_Char.Char_IsLower(input: "Good afternoon, Constable!")

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 21.113578730004775 < 26.67735401262778.
IsChangePoint: Marked as a change because one of 1/13/2023 4:37:08 PM, 1/18/2023 3:20:52 PM, 2/24/2023 9:01:57 AM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 9.892340271670706 (T) = (0 -20.80863466428544) / Math.Sqrt((12.756273461551197 / (299)) + (0.15753385042690304 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.10822504786403433 = (23.33395282570442 - 20.80863466428544) / 23.33395282570442 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### System.Tests.Perf_Char.Char_IsUpper(input: "Good afternoon, Constable!")

```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 16.173010730547475 < 23.461912180332355.
IsChangePoint: Marked as a change because one of 1/13/2023 4:37:08 PM, 1/18/2023 3:20:52 PM, 2/24/2023 9:01:57 AM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 12.417502800919852 (T) = (0 -16.169064981572138) / Math.Sqrt((15.038741704223721 / (299)) + (0.00020193698222624947 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.14696412207447251 = (18.95473027569861 - 16.169064981572138) / 18.95473027569861 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	Windows 10.0.19042
Baseline	6123cb00bbec8ae3500c970890f5b0efcf7950e8
Compare	ffbcb8336ac67496b0565112f663f74fda6cac34
Diff	Diff

Improvements in System.Globalization.Tests.Perf_DateTimeCultureInfo

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio	Baseline ETL	Compare ETL
ToString - Duration of single invocation	200.91 ns	168.65 ns	0.84	0.02	False
ToString - Duration of single invocation	200.56 ns	171.34 ns	0.85	0.04	False
ToString - Duration of single invocation	204.21 ns	165.03 ns	0.81	0.05	False

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Globalization.Tests.Perf_DateTimeCultureInfo*'

Details

Payloads

Baseline
Compare

Histogram

System.Globalization.Tests.Perf_DateTimeCultureInfo.ToString(culturestring: )

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 168.6501218225524 < 191.04058834717713.
IsChangePoint: Marked as a change because one of 1/13/2023 4:18:46 AM, 2/16/2023 9:36:08 AM, 2/20/2023 10:31:48 AM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 30.9387604358628 (T) = (0 -169.17618152402494) / Math.Sqrt((60.433985104960705 / (299)) + (3.0665890431646132 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.1276482049367835 = (193.93114392773765 - 169.17618152402494) / 193.93114392773765 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### System.Globalization.Tests.Perf_DateTimeCultureInfo.ToString(culturestring: fr)

```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 171.33900555487799 < 190.55185249718602.
IsChangePoint: Marked as a change because one of 1/13/2023 4:37:08 PM, 1/18/2023 3:20:52 PM, 2/17/2023 5:12:50 PM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 29.352092942633284 (T) = (0 -170.42431167186416) / Math.Sqrt((128.29526125808704 / (299)) + (0.4186546067308641 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.10748064753655036 = (190.94746931982448 - 170.42431167186416) / 190.94746931982448 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### System.Globalization.Tests.Perf_DateTimeCultureInfo.ToString(culturestring: ja)

```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 165.03208146087448 < 193.80284461701766.
IsChangePoint: Marked as a change because one of 1/13/2023 4:18:46 AM, 1/18/2023 3:20:52 PM, 2/21/2023 5:46:41 AM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 7.426983506339689 (T) = (0 -168.44119461432305) / Math.Sqrt((264.68784715144415 / (299)) + (70.6714890406268 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.12748558406339697 = (193.05262072204204 - 168.44119461432305) / 193.05262072204204 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	Windows 10.0.19042
Baseline	6123cb00bbec8ae3500c970890f5b0efcf7950e8
Compare	ffbcb8336ac67496b0565112f663f74fda6cac34
Diff	Diff

Improvements in System.Numerics.Tests.Perf_BigInteger

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio	Baseline ETL	Compare ETL
Add - Duration of single invocation	57.43 ns	51.29 ns	0.89	0.04	False

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Numerics.Tests.Perf_BigInteger*'

Details

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_BigInteger.Add(arguments: 1024,1024 bits)

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 51.28718740601939 < 54.24616274821989.
IsChangePoint: Marked as a change because one of 1/18/2023 3:20:52 PM, 2/1/2023 8:39:12 AM, 2/6/2023 2:52:08 AM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 23.749008319092805 (T) = (0 -51.3048271825691) / Math.Sqrt((8.217102781409919 / (299)) + (0.009133191947309327 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.07281945627158597 = (55.33423617396042 - 51.3048271825691) / 55.33423617396042 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]

Run Information

Architecture	x64
OS	Windows 10.0.19042
Baseline	6123cb00bbec8ae3500c970890f5b0efcf7950e8
Compare	ffbcb8336ac67496b0565112f663f74fda6cac34
Diff	Diff

Improvements in Span.IndexerBench

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio	Baseline ETL	Compare ETL
Ref - Duration of single invocation	639.14 ns	577.41 ns	0.90	0.03	False

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'Span.IndexerBench*'

Details

Payloads

Baseline
Compare

Histogram

Span.IndexerBench.Ref(length: 1024)

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 577.4147140010151 < 606.756393551805.
IsChangePoint: Marked as a change because one of 12/21/2022 9:23:17 AM, 1/13/2023 4:37:08 PM, 1/18/2023 3:20:52 PM, 1/27/2023 7:12:54 PM, 2/9/2023 12:40:40 PM, 2/24/2023 9:01:57 AM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 18.848600417633413 (T) = (0 -577.2594203741361) / Math.Sqrt((925.55842096737 / (299)) + (0.04642343186228887 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.05438196243742184 = (610.4572855463692 - 577.2594203741361) / 610.4572855463692 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	Windows 10.0.19042
Baseline	6123cb00bbec8ae3500c970890f5b0efcf7950e8
Compare	ffbcb8336ac67496b0565112f663f74fda6cac34
Diff	Diff

Improvements in System.Collections.IterateFor<String>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio	Baseline ETL	Compare ETL
ImmutableList - Duration of single invocation	6.25 μs	5.47 μs	0.88	0.03	False

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Collections.IterateFor<String>*'

Details

Payloads

Baseline
Compare

Histogram

System.Collections.IterateFor<String>.ImmutableList(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 5.473740935672515 < 5.987314676060642.
IsChangePoint: Marked as a change because one of 12/20/2022 1:34:12 PM, 1/3/2023 6:29:42 AM, 1/13/2023 4:37:08 PM, 1/18/2023 3:20:52 PM, 1/27/2023 7:12:54 PM, 2/13/2023 6:54:14 PM, 2/24/2023 12:59:32 PM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 14.815793908573415 (T) = (0 -5659.232289314066) / Math.Sqrt((60708.23957506061 / (299)) + (10847.127280532282 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.09877466672274221 = (6279.486472860866 - 5659.232289314066) / 6279.486472860866 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	Windows 10.0.19042
Baseline	6123cb00bbec8ae3500c970890f5b0efcf7950e8
Compare	ffbcb8336ac67496b0565112f663f74fda6cac34
Diff	Diff

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
Date_IsMatch - Duration of single invocation	73.91 ns	64.77 ns	0.88	0.09	False
OneNodeBacktracking - Duration of single invocation	74.75 ns	68.31 ns	0.91	0.05	False

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Text.RegularExpressions.Tests.Perf_Regex_Common*'

Details

Payloads

Baseline
Compare

Histogram

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

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 64.7717289042502 < 70.13816486624742.
IsChangePoint: Marked as a change because one of 1/3/2023 6:29:42 AM, 2/14/2023 5:47:38 PM, 2/20/2023 10:31:48 AM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 16.830640611237687 (T) = (0 -64.64078296278532) / Math.Sqrt((17.777806758494947 / (299)) + (1.4763541556506181 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.11924123734120447 = (73.39215424624399 - 64.64078296278532) / 73.39215424624399 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### System.Text.RegularExpressions.Tests.Perf_Regex_Common.OneNodeBacktracking(Options: IgnoreCase, Compiled)

```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 68.30757671371563 < 70.91482148008575.
IsChangePoint: Marked as a change because one of 1/5/2023 3:38:13 PM, 1/13/2023 4:37:08 PM, 1/27/2023 7:12:54 PM, 2/13/2023 6:54:14 PM, 2/20/2023 10:31:48 AM, 3/3/2023 4:59:02 PM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 13.891315188368624 (T) = (0 -67.05185030176845) / Math.Sqrt((8.94922233062816 / (299)) + (2.8494035116339362 / (24))) is greater than 1.967381707010986 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (24) - 2, .975) and 0.07396885729691496 = (72.40777033269539 - 67.05185030176845) / 72.40777033269539 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	Windows 10.0.19042
Baseline	6123cb00bbec8ae3500c970890f5b0efcf7950e8
Compare	ffbcb8336ac67496b0565112f663f74fda6cac34
Diff	Diff

Improvements in System.Collections.IterateForEach<String>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio	Baseline ETL	Compare ETL
List - Duration of single invocation	2.02 μs	1.74 μs	0.86	0.05	False

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Collections.IterateForEach<String>*'

Details

Payloads

Baseline
Compare

Histogram

System.Collections.IterateForEach<String>.List(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 1.7352829996292176 < 1.9183811132681214.
IsChangePoint: Marked as a change because one of 12/20/2022 1:34:12 PM, 12/28/2022 5:13:50 PM, 1/3/2023 6:29:42 AM, 1/13/2023 4:37:08 PM, 1/18/2023 3:20:52 PM, 2/20/2023 10:31:48 AM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 22.09927869938335 (T) = (0 -1734.3196450051068) / Math.Sqrt((13824.900001947059 / (299)) + (0.7047423252617788 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.07981623421384197 = (1884.7535780240512 - 1734.3196450051068) / 1884.7535780240512 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	Windows 10.0.19042
Baseline	6123cb00bbec8ae3500c970890f5b0efcf7950e8
Compare	ffbcb8336ac67496b0565112f663f74fda6cac34
Diff	Diff

Improvements in System.Collections.AddGivenSize<String>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio	Baseline ETL	Compare ETL
List - Duration of single invocation	1.86 μs	1.73 μs	0.93	0.03	False

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Collections.AddGivenSize<String>*'

Details

Payloads

Baseline
Compare

Histogram

System.Collections.AddGivenSize<String>.List(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 1.732181243047831 < 1.773496862073026.
IsChangePoint: Marked as a change because one of 12/20/2022 1:34:12 PM, 1/3/2023 6:29:42 AM, 1/18/2023 3:20:52 PM, 1/27/2023 7:12:54 PM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 27.757570256063794 (T) = (0 -1732.6288624217013) / Math.Sqrt((3849.6783914812277 / (299)) + (0.915317665932691 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.05462017372894191 = (1832.733060589897 - 1732.6288624217013) / 1832.733060589897 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	Windows 10.0.19042
Baseline	6123cb00bbec8ae3500c970890f5b0efcf7950e8
Compare	ffbcb8336ac67496b0565112f663f74fda6cac34
Diff	Diff

Improvements in System.Text.Tests.Perf_Encoding

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio	Baseline ETL	Compare ETL
GetByteCount - Duration of single invocation	25.66 ns	21.19 ns	0.83	0.09	False

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Text.Tests.Perf_Encoding*'

Details

Payloads

Baseline
Compare

Histogram

System.Text.Tests.Perf_Encoding.GetByteCount(size: 512, encName: "utf-8")

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 21.19391616821691 < 24.298507814940802.
IsChangePoint: Marked as a change because one of 1/3/2023 6:29:42 AM, 1/27/2023 7:12:54 PM, 2/20/2023 10:31:48 AM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 16.83839600119808 (T) = (0 -20.825807000529412) / Math.Sqrt((6.782387341752597 / (299)) + (0.06362166723587111 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.12596567988385984 = (23.827218818778324 - 20.825807000529412) / 23.827218818778324 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	Windows 10.0.19042
Baseline	6123cb00bbec8ae3500c970890f5b0efcf7950e8
Compare	ffbcb8336ac67496b0565112f663f74fda6cac34
Diff	Diff

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
LastIndexOfAnyValues - Duration of single invocation	12.91 ns	11.26 ns	0.87	0.05	False

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Memory.Span<Char>*'

Details

Payloads

Baseline
Compare

Histogram

System.Memory.Span<Char>.LastIndexOfAnyValues(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 11.25560517249666 < 12.26224707625238.
IsChangePoint: Marked as a change because one of 12/21/2022 9:23:17 AM, 1/3/2023 6:29:42 AM, 1/18/2023 3:20:52 PM, 1/27/2023 7:12:54 PM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 21.697542291256582 (T) = (0 -11.21962329358327) / Math.Sqrt((0.5828297718754004 / (299)) + (0.012947381663367124 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.10650121435819572 = (12.556954160294872 - 11.21962329358327) / 12.556954160294872 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	Windows 10.0.19042
Baseline	6123cb00bbec8ae3500c970890f5b0efcf7950e8
Compare	ffbcb8336ac67496b0565112f663f74fda6cac34
Diff	Diff

Improvements in System.Linq.Tests.Perf_Enumerable

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio	Baseline ETL	Compare ETL
Repeat - Duration of single invocation	410.93 ns	382.88 ns	0.93	0.06	False
SelectToList - Duration of single invocation	915.34 ns	833.42 ns	0.91	0.23	False

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Linq.Tests.Perf_Enumerable*'

Details

Payloads

Baseline
Compare

Histogram

System.Linq.Tests.Perf_Enumerable.Repeat

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 382.8782006003885 < 390.1653140730006.
IsChangePoint: Marked as a change because one of 1/18/2023 3:20:52 PM, 2/4/2023 10:21:07 PM, 2/6/2023 6:07:54 PM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 30.52668461808432 (T) = (0 -382.69412947816653) / Math.Sqrt((202.1905996671404 / (299)) + (0.12771853409163478 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.06233093268129168 = (408.1334692766302 - 382.69412947816653) / 408.1334692766302 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### System.Linq.Tests.Perf_Enumerable.SelectToList(input: IEnumerable)

```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 833.4222688727854 < 876.7307792535944.
IsChangePoint: Marked as a change because one of 2/9/2023 12:40:40 PM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 29.946690620621684 (T) = (0 -832.8954123662899) / Math.Sqrt((1165.3817044214543 / (299)) + (1.9549460312735836 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.06845247521073324 = (894.0986801019155 - 832.8954123662899) / 894.0986801019155 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	Windows 10.0.19042
Baseline	6123cb00bbec8ae3500c970890f5b0efcf7950e8
Compare	ffbcb8336ac67496b0565112f663f74fda6cac34
Diff	Diff

Improvements in System.Text.Encodings.Web.Tests.Perf_Encoders

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio	Baseline ETL	Compare ETL
EncodeUtf8 - Duration of single invocation	54.44 ns	44.74 ns	0.82	0.04	False
EncodeUtf8 - Duration of single invocation	54.41 ns	44.63 ns	0.82	0.05	False

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Text.Encodings.Web.Tests.Perf_Encoders*'

Details

Payloads

Baseline
Compare

Histogram

System.Text.Encodings.Web.Tests.Perf_Encoders.EncodeUtf8(arguments: UnsafeRelaxed,no <escaping /> required,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 44.74304788050847 < 51.7026891852384.
IsChangePoint: Marked as a change because one of 1/18/2023 3:20:52 PM, 2/20/2023 10:31:48 AM, 2/24/2023 9:01:57 AM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 35.96741016006922 (T) = (0 -44.6720072533041) / Math.Sqrt((13.182062497856121 / (299)) + (0.007328831927233273 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.14606642015565147 = (52.31321066147408 - 44.6720072533041) / 52.31321066147408 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### System.Text.Encodings.Web.Tests.Perf_Encoders.EncodeUtf8(arguments: JavaScript,no escaping required,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 44.62947413988555 < 51.6752747773878.
IsChangePoint: Marked as a change because one of 1/11/2023 2:37:52 AM, 1/18/2023 3:20:52 PM, 2/20/2023 10:31:48 AM, 2/24/2023 9:01:57 AM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 24.659430935128196 (T) = (0 -44.437446008492394) / Math.Sqrt((13.137363002858413 / (299)) + (0.4086565717409789 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.15074601264940898 = (52.325272145172306 - 44.437446008492394) / 52.325272145172306 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	Windows 10.0.19042
Baseline	6123cb00bbec8ae3500c970890f5b0efcf7950e8
Compare	ffbcb8336ac67496b0565112f663f74fda6cac34
Diff	Diff

Improvements in System.Tests.Perf_UInt16

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio	Baseline ETL	Compare ETL
ToString - Duration of single invocation	10.59 ns	8.85 ns	0.84	0.28	False
ToString - Duration of single invocation	10.58 ns	8.90 ns	0.84	0.22	False

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Tests.Perf_UInt16*'

Details

Payloads

Baseline
Compare

Histogram

System.Tests.Perf_UInt16.ToString(value: 65535)

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 8.854897608890152 < 10.055642596393255.
IsChangePoint: Marked as a change because one of 1/3/2023 6:29:42 AM, 1/5/2023 12:24:13 PM, 2/24/2023 9:01:57 AM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 8.497669649808936 (T) = (0 -9.019054466577373) / Math.Sqrt((0.6969412205653179 / (299)) + (0.05522836462652323 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.08696893376138531 = (9.878146319525454 - 9.019054466577373) / 9.878146319525454 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

```#### System.Tests.Perf_UInt16.ToString(value: 12345)

```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 8.902095219089603 < 10.036178127575717.
IsChangePoint: Marked as a change because one of 1/3/2023 6:29:42 AM, 1/5/2023 12:24:13 PM, 2/24/2023 9:01:57 AM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 7.227053188274105 (T) = (0 -9.114119611440172) / Math.Sqrt((0.4933954617493893 / (299)) + (0.05704249850522223 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.0727815425539286 = (9.829527807873976 - 9.114119611440172) / 9.829527807873976 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	Windows 10.0.19042
Baseline	6123cb00bbec8ae3500c970890f5b0efcf7950e8
Compare	ffbcb8336ac67496b0565112f663f74fda6cac34
Diff	Diff

Improvements in PerfLabTests.CastingPerf2.CastingPerf

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio	Baseline ETL	Compare ETL
FooObjIsFoo - Duration of single invocation	612.60 μs	556.83 μs	0.91	0.04	False

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'PerfLabTests.CastingPerf2.CastingPerf*'

Details

Payloads

Baseline
Compare

Histogram

PerfLabTests.CastingPerf2.CastingPerf.FooObjIsFoo

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 556.8280563186813 < 582.0290993303571.
IsChangePoint: Marked as a change because one of 12/21/2022 9:23:17 AM, 12/28/2022 5:13:50 PM, 1/13/2023 4:37:08 PM, 1/18/2023 3:20:52 PM, 2/9/2023 12:40:40 PM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 18.29599112552289 (T) = (0 -556988.3810540013) / Math.Sqrt((786806232.259267 / (299)) + (19802.755627185918 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.0506155035759344 = (586683.6704748641 - 556988.3810540013) / 586683.6704748641 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]

Run Information

Architecture	x64
OS	Windows 10.0.19042
Baseline	6123cb00bbec8ae3500c970890f5b0efcf7950e8
Compare	ffbcb8336ac67496b0565112f663f74fda6cac34
Diff	Diff

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
Parse - Duration of single invocation	114.15 ns	100.94 ns	0.88	0.08	False

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Tests.Perf_Single*'

Details

Payloads

Baseline
Compare

Histogram

System.Tests.Perf_Single.Parse(value: "3.4028235E+38")

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 100.94147616108829 < 108.34504678310023.
IsChangePoint: Marked as a change because one of 2/1/2023 8:39:12 AM, 2/9/2023 4:27:10 AM, 2/14/2023 11:21:41 AM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 11.41530648668651 (T) = (0 -101.22333995408052) / Math.Sqrt((43.30616493250636 / (299)) + (5.969581542274567 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.10123667731981877 = (112.625134337063 - 101.22333995408052) / 112.625134337063 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	Windows 10.0.19042
Baseline	6123cb00bbec8ae3500c970890f5b0efcf7950e8
Compare	ffbcb8336ac67496b0565112f663f74fda6cac34
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
SequenceEqual - Duration of single invocation	40.12 ns	30.69 ns	0.76	0.07	False

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Memory.Span<Int32>*'

Details

Payloads

Baseline
Compare

Histogram

System.Memory.Span<Int32>.SequenceEqual(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 30.692666368568275 < 37.52864458834882.
IsChangePoint: Marked as a change because one of 12/21/2022 9:23:17 AM, 1/13/2023 4:37:08 PM, 1/18/2023 3:20:52 PM, 1/27/2023 7:12:54 PM, 2/9/2023 12:40:40 PM, 2/24/2023 9:01:57 AM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 13.852206267706384 (T) = (0 -30.904547052953692) / Math.Sqrt((15.48162138647201 / (299)) + (0.16741671239936237 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.10978075180172331 = (34.71565809827377 - 30.904547052953692) / 34.71565809827377 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	Windows 10.0.19042
Baseline	6123cb00bbec8ae3500c970890f5b0efcf7950e8
Compare	ffbcb8336ac67496b0565112f663f74fda6cac34
Diff	Diff

Improvements in System.Diagnostics.Perf_Activity

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio	Baseline ETL	Compare ETL
EnumerateActivityTagsSmall - Duration of single invocation	54.12 ns	46.16 ns	0.85	0.19	False

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Diagnostics.Perf_Activity*'

Details

Payloads

Baseline
Compare

Histogram

System.Diagnostics.Perf_Activity.EnumerateActivityTagsSmall

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 46.160307460065624 < 50.11223412054392.
IsChangePoint: Marked as a change because one of 1/18/2023 3:20:52 PM, 2/13/2023 6:54:14 PM, 2/23/2023 8:54:44 PM, 3/6/2023 11:14:52 AM, 3/7/2023 7:56:26 PM falls between 2/26/2023 10:10:21 PM and 3/7/2023 7:56:26 PM.
IsImprovementStdDev: Marked as improvement because 9.624342327038427 (T) = (0 -46.02983733838489) / Math.Sqrt((8.931614836490885 / (299)) + (0.9786018243156506 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.07929689267234834 = (49.994223949115224 - 46.02983733838489) / 49.994223949115224 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

[AndyAyersMS]

dotnet/runtime#83002