Skip to content

[Perf] Linux/arm64: 3 Improvements on 6/2/2023 3:25:13 AM #18608

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
performanceautofiler bot opened this issue Jun 8, 2023 · 1 comment
Closed

[Perf] Linux/arm64: 3 Improvements on 6/2/2023 3:25:13 AM #18608

performanceautofiler bot opened this issue Jun 8, 2023 · 1 comment
Labels
ampere arch-arm64 branch-refs/heads/main kind-micro os-linux perf-improvement PGO Applied if there were any profile guided optimization updates in the observed interval. runtime-coreclr untriaged

Comments

@performanceautofiler
Copy link

performanceautofiler bot commented Jun 8, 2023

Run Information

Name Value
Architecture arm64
OS ubuntu 20.04
Queue AmpereUbuntu
Baseline 3eb4407e441b539c81c6ea8cc797f97536abd01f
Compare 2855dd2d29c64df89498fbcb984653f596c1b976
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

Improvements in System.Buffers.Tests.RentReturnArrayPoolTests<Object>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
MultipleSerial - Duration of single invocation 366.94 ns 339.39 ns 0.92 0.01 False
SingleSerial - Duration of single invocation 46.79 ns 42.23 ns 0.90 0.02 False

graph
graph
Test Report

Repro

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

Payloads

Baseline
Compare

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Buffers.Tests.RentReturnArrayPoolTests&lt;Object&gt;*'

Payloads

Baseline
Compare

Histogram

System.Buffers.Tests.RentReturnArrayPoolTests<Object>.MultipleSerial(RentalSize: 4096, ManipulateArray: False, Async: False, UseSharedPool: False)


Description of detection logic

IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed: Marked as improvement because we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 5/19/2023 4:22:12 AM, 6/1/2023 4:59:33 PM, 6/7/2023 7:43:49 PM falls between 5/29/2023 5:51:10 AM and 6/7/2023 7:43:49 PM.
IsImprovementStdDev: Marked as improvement because 54.904996216500194 (T) = (0 -338.9235520238095) / Math.Sqrt((95.79322816789413 / (299)) + (8.168562595735118 / (11))) is greater than 1.9676960046166507 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (11) - 2, .975) and 0.1431175658111231 = (395.53098359944073 - 338.9235520238095) / 395.53098359944073 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

System.Buffers.Tests.RentReturnArrayPoolTests<Object>.SingleSerial(RentalSize: 4096, ManipulateArray: False, Async: False, UseSharedPool: False)


Description of detection logic

IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed: Marked as improvement because we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 6/1/2023 4:59:33 PM, 6/7/2023 7:43:49 PM falls between 5/29/2023 5:51:10 AM and 6/7/2023 7:43:49 PM.
IsImprovementStdDev: Marked as improvement because 17.04200944667172 (T) = (0 -42.75574673326153) / Math.Sqrt((0.501823567710066 / (299)) + (0.5772122455464197 / (11))) is greater than 1.9676960046166507 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (11) - 2, .975) and 0.08488124395474816 = (46.72152816322267 - 42.75574673326153) / 46.72152816322267 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

Docs

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


Run Information

Name Value
Architecture arm64
OS ubuntu 20.04
Queue AmpereUbuntu
Baseline 3eb4407e441b539c81c6ea8cc797f97536abd01f
Compare 2855dd2d29c64df89498fbcb984653f596c1b976
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

Improvements in System.Threading.Tasks.ValueTaskPerfTest

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
CreateAndAwait_FromCompletedValueTaskSource_ConfigureAwait - Duration of single invocation 29.77 ns 24.69 ns 0.83 0.05 False

graph
Test Report

Repro

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

Payloads

Baseline
Compare

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

Payloads

Baseline
Compare

Histogram

System.Threading.Tasks.ValueTaskPerfTest.CreateAndAwait_FromCompletedValueTaskSource_ConfigureAwait


Description of detection logic

IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed: Marked as improvement because we could not find enough baseline builds for window checking.
IsChangePoint: Marked as a change because one of 3/17/2023 7:47:41 PM, 6/1/2023 4:59:33 PM, 6/7/2023 7:43:49 PM falls between 5/29/2023 5:51:10 AM and 6/7/2023 7:43:49 PM.
IsImprovementStdDev: Marked as improvement because 24.30905183394486 (T) = (0 -24.88171769972312) / Math.Sqrt((0.5086107595707746 / (299)) + (0.49012506063573874 / (11))) is greater than 1.9676960046166507 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (11) - 2, .975) and 0.1736399847888668 = (30.11002134870465 - 24.88171769972312) / 30.11002134870465 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

@performanceautofiler performanceautofiler bot added ampere arch-arm64 branch-refs/heads/main kind-micro os-linux perf-improvement PGO Applied if there were any profile guided optimization updates in the observed interval. runtime-coreclr untriaged labels Jun 8, 2023
@EgorBo
Copy link
Member

EgorBo commented Jun 8, 2023

Likely dotnet/runtime#86809

@EgorBo EgorBo closed this as completed Jun 8, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ampere arch-arm64 branch-refs/heads/main kind-micro os-linux perf-improvement PGO Applied if there were any profile guided optimization updates in the observed interval. runtime-coreclr untriaged
Projects
None yet
Development

No branches or pull requests

1 participant