Skip to content
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

[Perf] Windows/x64: 6 Improvements on 5/3/2023 1:06:54 PM #17622

Closed
performanceautofiler bot opened this issue May 9, 2023 · 1 comment
Closed

[Perf] Windows/x64: 6 Improvements on 5/3/2023 1:06:54 PM #17622

performanceautofiler bot opened this issue May 9, 2023 · 1 comment
Assignees
Labels
arch-x64 branch-refs/heads/main kind-micro os-windows 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 May 9, 2023

Run Information

Name Value
Architecture x64
OS Windows 10.0.19042
Queue OwlWindows
Baseline 442141d696ee7d4ae54420974559e99738d753e6
Compare d819cc97b954dc64b9120cb42b2ffbbe10d7a3ae
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

Improvements in System.Collections.CtorDefaultSize<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 5.05 ns 3.84 ns 0.76 0.07 False
Stack - Duration of single invocation 5.20 ns 3.35 ns 0.64 0.07 False
List - Duration of single invocation 4.82 ns 3.66 ns 0.76 0.06 False

graph
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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Collections.CtorDefaultSize&lt;Int32&gt;*'

Payloads

Baseline
Compare

Histogram

System.Collections.CtorDefaultSize<Int32>.Queue


Description of detection logic

IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed: Marked as improvement because 3.8363254856224454 < 4.795564420001662.
IsChangePoint: Marked as a change because one of 2/24/2023 9:01:57 AM, 3/6/2023 11:14:52 AM, 4/6/2023 9:09:21 PM, 4/9/2023 11:04:55 PM, 5/3/2023 7:05:50 AM, 5/9/2023 7:24:34 AM falls between 4/30/2023 6:17:41 PM and 5/9/2023 7:24:34 AM.
IsImprovementStdDev: Marked as improvement because 47.34373005044103 (T) = (0 -4.08110925786983) / Math.Sqrt((0.10675673985950929 / (299)) + (0.00991770685927808 / (25))) is greater than 1.9673585853226652 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (25) - 2, .975) and 0.24155803365560857 = (5.38091170975195 - 4.08110925786983) / 5.38091170975195 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

System.Collections.CtorDefaultSize<Int32>.Stack


Description of detection logic

IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed: Marked as improvement because 3.346217166278123 < 4.938573359990268.
IsChangePoint: Marked as a change because one of 2/24/2023 9:01:57 AM, 3/6/2023 11:14:52 AM, 5/3/2023 7:05:50 AM, 5/9/2023 7:24:34 AM falls between 4/30/2023 6:17:41 PM and 5/9/2023 7:24:34 AM.
IsImprovementStdDev: Marked as improvement because 65.84280951999789 (T) = (0 -3.5998245297473686) / Math.Sqrt((0.08950911858186937 / (299)) + (0.006506891265406021 / (26))) is greater than 1.967335607330539 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (26) - 2, .975) and 0.30011494985827203 = (5.143451098174475 - 3.5998245297473686) / 5.143451098174475 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

System.Collections.CtorDefaultSize<Int32>.List


Description of detection logic

IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed: Marked as improvement because 3.6625362325522537 < 4.580349515103915.
IsChangePoint: Marked as a change because one of 2/24/2023 9:01:57 AM, 3/6/2023 11:14:52 AM, 4/6/2023 9:09:21 PM, 4/9/2023 11:04:55 PM, 5/3/2023 7:05:50 AM, 5/9/2023 7:24:34 AM falls between 4/30/2023 6:17:41 PM and 5/9/2023 7:24:34 AM.
IsImprovementStdDev: Marked as improvement because 48.09709648607299 (T) = (0 -3.881463265688048) / Math.Sqrt((0.11029376766664893 / (299)) + (0.008222534682252019 / (26))) is greater than 1.967335607330539 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (26) - 2, .975) and 0.24491045197473366 = (5.140401262127083 - 3.881463265688048) / 5.140401262127083 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 442141d696ee7d4ae54420974559e99738d753e6
Compare c8f43d52f699c1da289a5cb36d371aec15901ab8
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

Improvements in System.Collections.CtorDefaultSizeNonGeneric

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
ArrayList - Duration of single invocation 4.81 ns 3.62 ns 0.75 0.06 False
Queue - Duration of single invocation 18.76 ns 16.82 ns 0.90 0.04 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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Collections.CtorDefaultSizeNonGeneric*'

Payloads

Baseline
Compare

Histogram

System.Collections.CtorDefaultSizeNonGeneric.ArrayList


Description of detection logic

IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed: Marked as improvement because 3.6239049886977925 < 4.579521896372443.
IsChangePoint: Marked as a change because one of 2/24/2023 9:01:57 AM, 3/6/2023 11:14:52 AM, 4/6/2023 9:09:21 PM, 4/9/2023 5:39:24 PM, 5/3/2023 7:05:50 AM, 5/9/2023 7:24:34 AM falls between 4/30/2023 6:17:41 PM and 5/9/2023 7:24:34 AM.
IsImprovementStdDev: Marked as improvement because 52.14781202985259 (T) = (0 -3.870734966760381) / Math.Sqrt((0.10048365109802873 / (299)) + (0.006665983591924521 / (26))) is greater than 1.967335607330539 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (26) - 2, .975) and 0.24694279881247813 = (5.140027823459474 - 3.870734966760381) / 5.140027823459474 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.

JIT Disasms

System.Collections.CtorDefaultSizeNonGeneric.Queue


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 16.823188085226178 < 17.809846475371227.
IsChangePoint: Marked as a change because one of 3/1/2023 5:53:50 PM, 3/14/2023 8:42:09 PM, 4/4/2023 4:23:54 PM, 4/22/2023 6:52:03 AM, 5/2/2023 3:18:41 PM, 5/9/2023 7:24:34 AM falls between 4/30/2023 6:17:41 PM and 5/9/2023 7:24:34 AM.
IsImprovementStdDev: Marked as improvement because 21.436005875239427 (T) = (0 -17.287311534067577) / Math.Sqrt((0.4851512844699258 / (299)) + (0.05195725427462196 / (29))) is greater than 1.9672675222597202 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (29) - 2, .975) and 0.06755894336018824 = (18.53984379062516 - 17.287311534067577) / 18.53984379062516 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 442141d696ee7d4ae54420974559e99738d753e6
Compare c8f43d52f699c1da289a5cb36d371aec15901ab8
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

Improvements in StoreBlock.AnyLocation

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
InitBlockAllZeros128 - Duration of single invocation 2.31 ns 1.03 ns 0.45 0.07 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 'StoreBlock.AnyLocation*'

Payloads

Baseline
Compare

Histogram

StoreBlock.AnyLocation.InitBlockAllZeros128


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 1.0331159499300493 < 2.197056011501806.
IsChangePoint: Marked as a change because one of 3/3/2023 11:43:56 AM, 5/3/2023 7:05:50 AM, 5/9/2023 7:24:34 AM falls between 4/30/2023 6:17:41 PM and 5/9/2023 7:24:34 AM.
IsImprovementStdDev: Marked as improvement because 23.61318979081387 (T) = (0 -1.0866687421861267) / Math.Sqrt((0.04271380623636815 / (299)) + (0.062496307806191094 / (26))) is greater than 1.967335607330539 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (26) - 2, .975) and 0.5230293548425967 = (2.2782717410785716 - 1.0866687421861267) / 2.2782717410785716 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

@kunalspathak
Copy link
Member

dotnet/runtime#85559

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
arch-x64 branch-refs/heads/main kind-micro os-windows 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

2 participants