Skip to content

[Perf] Windows/x64: 4 Regressions on 5/12/2023 4:02:48 AM #17846

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.

Sign up for GitHub

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

Jump to bottom
Closed
performanceautofiler bot opened this issue May 16, 2023 · 1 comment
Closed

[Perf] Windows/x64: 4 Regressions on 5/12/2023 4:02:48 AM #17846

performanceautofiler bot opened this issue May 16, 2023 · 1 comment
Assignees
@DrewScoggins
Labels
arch-x64 branch-refs/heads/main kind-micro os-windows perf-regression PGO Applied if there were any profile guided optimization updates in the observed interval. runtime-coreclr

Comments

@performanceautofiler
Copy link

performanceautofiler bot commented May 16, 2023 •
edited
Loading

Run Information

Name Value
Architecture x64
OS Windows 10.0.19042
Queue OwlWindows
Baseline 3a91c9dc96bdfd8164825eec94660691b661f676
Compare f1819bd78f0e7506b8c3c7f90b47aa41b0e22c6f
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

Regressions in PerfLabTests.LowLevelPerf

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
ObjectStringIsString - Duration of single invocation 69.62 μs 83.54 μs 1.20 0.04 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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'PerfLabTests.LowLevelPerf*'

Payloads

Baseline
Compare

Histogram

PerfLabTests.LowLevelPerf.ObjectStringIsString

Description of detection logic

IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because 83.53528147163118 > 73.10650520833335.
IsChangePoint: Marked as a change because one of 3/6/2023 11:14:52 AM, 3/14/2023 8:42:09 PM, 3/25/2023 12:18:49 AM, 4/9/2023 11:04:55 PM, 4/19/2023 8:38:27 PM, 5/11/2023 9:15:05 PM, 5/16/2023 7:34:13 AM falls between 5/7/2023 5:11:33 AM and 5/16/2023 7:34:13 AM.
IsRegressionStdDev: Marked as regression because -25.813478022801444 (T) = (0 -83555.84121959867) / Math.Sqrt((9923708.209022328 / (38)) + (650.9364091968152 / (13))) is less than -2.0095752371279447 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (38) + (13) - 2, .025) and -0.18749429902466938 = (70363.15145952786 - 83555.84121959867) / 70363.15145952786 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
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 3a91c9dc96bdfd8164825eec94660691b661f676
Compare f1819bd78f0e7506b8c3c7f90b47aa41b0e22c6f
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

Regressions in System.Net.Primitives.Tests.CredentialCacheTests

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
ForEach - Duration of single invocation 333.26 ns 365.90 ns 1.10 0.16 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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Net.Primitives.Tests.CredentialCacheTests*'

Payloads

Baseline
Compare

Histogram

System.Net.Primitives.Tests.CredentialCacheTests.ForEach(uriCount: 10, hostPortCount: 10)

Description of detection logic

IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because 365.89922930123316 > 350.88450737798996.
IsChangePoint: Marked as a change because one of 3/20/2023 8:31:51 AM, 4/6/2023 1:55:21 PM, 4/19/2023 8:38:27 PM, 4/22/2023 6:52:03 AM, 5/11/2023 9:15:05 PM, 5/16/2023 7:34:13 AM falls between 5/7/2023 5:11:33 AM and 5/16/2023 7:34:13 AM.
IsRegressionStdDev: Marked as regression because -9.976775381941204 (T) = (0 -386.22096836117237) / Math.Sqrt((168.40367299428272 / (38)) + (167.79939770773777 / (13))) is less than -2.0095752371279447 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (38) + (13) - 2, .025) and -0.1205296046405196 = (344.67716583452255 - 386.22096836117237) / 344.67716583452255 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
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 3a91c9dc96bdfd8164825eec94660691b661f676
Compare f1819bd78f0e7506b8c3c7f90b47aa41b0e22c6f
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

Regressions in System.Collections.CtorFromCollection<Int32>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
Queue - Duration of single invocation 106.58 ns 113.26 ns 1.06 0.09 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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Collections.CtorFromCollection&lt;Int32&gt;*'

Payloads

Baseline
Compare

Histogram

System.Collections.CtorFromCollection<Int32>.Queue(Size: 512)

Description of detection logic

IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because 113.26197212990337 > 112.05046152894155.
IsChangePoint: Marked as a change because one of 2/28/2023 10:21:25 PM, 4/25/2023 6:46:56 PM, 5/11/2023 9:15:05 PM, 5/16/2023 7:34:13 AM falls between 5/7/2023 5:11:33 AM and 5/16/2023 7:34:13 AM.
IsRegressionStdDev: Marked as regression because -12.660625305012173 (T) = (0 -113.67343676353076) / Math.Sqrt((6.064952885004328 / (38)) + (1.1581208156319598 / (13))) is less than -2.0095752371279447 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (38) + (13) - 2, .025) and -0.05880890903980384 = (107.3597282692088 - 113.67343676353076) / 107.3597282692088 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
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 3a91c9dc96bdfd8164825eec94660691b661f676
Compare f1819bd78f0e7506b8c3c7f90b47aa41b0e22c6f
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

Regressions 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
ProducerConsumer - Duration of single invocation 187.55 ns 286.66 ns 1.53 0.36 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
py .\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>.ProducerConsumer(RentalSize: 4096, ManipulateArray: False, Async: True, UseSharedPool: True)

Description of detection logic

IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
IsRegressionBase: Marked as regression because the compare was 5% greater than the baseline, and the value was not too small.
IsRegressionChecked: Marked as regression because the three check build points were 0.05 greater than the baseline.
IsRegressionWindowed: Marked as regression because 286.6569611111111 > 202.88795037828947.
IsChangePoint: Marked as a change because one of 3/22/2023 7:51:01 PM, 5/11/2023 9:15:05 PM, 5/16/2023 7:34:13 AM falls between 5/7/2023 5:11:33 AM and 5/16/2023 7:34:13 AM.
IsRegressionStdDev: Marked as regression because -10.642289918461623 (T) = (0 -268.44406271929824) / Math.Sqrt((34.05184165582092 / (38)) + (595.4919765055974 / (13))) is less than -2.0095752371279447 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (38) + (13) - 2, .025) and -0.3716073499319395 = (195.7149491307543 - 268.44406271929824) / 195.7149491307543 is less than -0.05.
IsImprovementBase: Marked as not an improvement because the compare was not 5% less than the baseline, or the value was too small.
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 arch-x64 branch-refs/heads/main kind-micro os-windows perf-regression PGO Applied if there were any profile guided optimization updates in the observed interval. runtime-coreclr untriaged labels May 16, 2023
@EgorBo
Copy link
Member

EgorBo commented May 16, 2023

The last one is the same as dotnet/runtime#87180

@EgorBo EgorBo closed this as completed May 16, 2023
@EgorBo EgorBo removed the untriaged label May 16, 2023
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@DrewScoggins DrewScoggins

Labels
arch-x64 branch-refs/heads/main kind-micro os-windows perf-regression PGO Applied if there were any profile guided optimization updates in the observed interval. runtime-coreclr
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@EgorBo @DrewScoggins