[Perf] Windows/x64: 2 Improvements on 7/13/2023 3:06:28 AM

[performanceautofiler]

Run Information

Name	Value
Architecture	x64
OS	Windows 10.0.19042
Queue	OwlWindows
Baseline	82bf906968d9bc1ca5b3131c7a7af8f30d5ac2f5
Compare	b9c99648783d0c28afdee394a93516c0bd228165
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Improvements in System.IO.Tests.BinaryWriterTests

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
WriteNonAsciiChar - Duration of single invocation 📝 - Benchmark Source	6.12 ns	5.12 ns	0.84	0.06	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.IO.Tests.BinaryWriterTests*'

Payloads

Baseline
Compare

System.IO.Tests.BinaryWriterTests.WriteNonAsciiChar

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 5.1186960238014105 < 5.83107792112803.
IsChangePoint: Marked as a change because one of 5/10/2023 6:18:38 PM, 5/11/2023 5:02:01 PM, 6/19/2023 6:37:24 PM, 6/30/2023 8:34:57 AM, 7/12/2023 9:48:15 PM, 7/17/2023 10:23:26 PM falls between 7/8/2023 10:33:35 PM and 7/17/2023 10:23:26 PM.
IsImprovementStdDev: Marked as improvement because 5.054942447997451 (T) = (0 -5.4594777382500395) / Math.Sqrt((0.09226394966023761 / (299)) + (0.07945935467281225 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.0908924874631552 = (6.005315832244621 - 5.4594777382500395) / 6.005315832244621 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	x64
OS	Windows 10.0.19042
Queue	OwlWindows
Baseline	82bf906968d9bc1ca5b3131c7a7af8f30d5ac2f5
Compare	b9c99648783d0c28afdee394a93516c0bd228165
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Improvements in System.Memory.Span<Char>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
BinarySearch - Duration of single invocation 📝 - Benchmark Source	8.02 ns	7.01 ns	0.88	0.09	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.Memory.Span<Char>*'

Payloads

Baseline
Compare

System.Memory.Span<Char>.BinarySearch(Size: 33)

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 7.014131280460576 < 7.647359961906466.
IsChangePoint: Marked as a change because one of 5/22/2023 7:40:07 AM, 5/26/2023 6:22:05 AM, 6/13/2023 11:57:38 AM, 6/19/2023 6:37:24 PM, 6/30/2023 8:34:57 AM, 7/12/2023 9:48:15 PM, 7/17/2023 10:23:26 PM falls between 7/8/2023 10:33:35 PM and 7/17/2023 10:23:26 PM.
IsImprovementStdDev: Marked as improvement because 4.52386336534398 (T) = (0 -6.395155357838121) / Math.Sqrt((0.39747320702127026 / (299)) + (0.08448106409394975 / (7))) is greater than 1.9677981407170237 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (7) - 2, .975) and 0.07568332644629143 = (6.918792596535934 - 6.395155357838121) / 6.918792596535934 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]

Could be dotnet/runtime#88993

[BrennanConroy]

How? The PR you linked is from after this benchmark run.

[EgorBo]

How? The PR you linked is from after this benchmark run.

I didn't check the exact time the benchmark was invoked, but that PR is located in this range:

[BrennanConroy]

I see, so the issue title and run information aren't accurate.

I would still like to understand how the Ascii.Equals change affects BinaryWriter.Write(char).