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.

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

[Perf] Linux/x64: 17 Regressions on 6/3/2023 12:54:16 AM #18528

Closed
performanceautofiler bot opened this issue Jun 6, 2023 · 4 comments
Closed

[Perf] Linux/x64: 17 Regressions on 6/3/2023 12:54:16 AM #18528

performanceautofiler bot opened this issue Jun 6, 2023 · 4 comments
Labels
arch-x64 branch-refs/heads/main kind-micro_mono mono-interpreter os-linux perf-regression PGO Applied if there were any profile guided optimization updates in the observed interval. runtime-mono

Comments

@performanceautofiler
Copy link

performanceautofiler bot commented Jun 6, 2023 •
edited
Loading

Run Information

Name Value
Architecture x64
OS ubuntu 18.04
Queue TigerUbuntu
Baseline 0214a047483067a6a813a34be5b6b1f757600961
Compare 2f18320e731cc3b06bc43cdb4d82dffc4f8f81fc
Diff Diff
Configs CompilationMode:tiered, LLVM:false, MonoAOT:false, MonoInterpreter:true, RunKind:micro_mono

Regressions in System.Numerics.Tests.Perf_VectorOf<Double>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
OneBenchmark - Duration of single invocation 23.22 ns 24.45 ns 1.05 0.21 False

graph
Test Report

Repro

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

Payloads

Baseline
Compare

Repro Steps

Prerequisites (Build files either built locally or downloaded from payload above)

  • Libraries build extracted to runtime/artifacts or build instructions: Libraries README args: -subset libs+libs.tests -rc release -configuration Release -arch $RunArch -framework net8.0
  • CoreCLR product build extracted to runtime/artifacts/bin/coreclr/$RunOS.$RunArch.Release, build instructions: CoreCLR README args: -subset clr+libs -rc release -configuration Release -arch $RunArch -framework net8.0
  • Mono Runtime build extracted to runtime/artifacts/bin/mono/$RunOS.$RunArch.Release, build instructions: MONO README args: -arch $RunArch -os $RunOS -s mono+libs+host+packs -c Release
  • Dotnet SDK installed for dotnet commands
  • Running commands from the runtime folder

Linux

# Set $RunDir to the runtime directory
RunDir=`pwd`

# Set the OS, arch, and OSId
RunOS='linux'
RunOSId='linux'
RunArch='x64'

# Create mono dotnet
mkdir -p $RunDir/artifacts/dotnet-mono
$RunDir/build.sh -subset libs.pretest -configuration release -ci -arch $RunArch -testscope innerloop /p:RuntimeArtifactsPath=$RunDir/artifacts/bin/mono/$RunOS.$RunArch.Release /p:RuntimeFlavor=mono
cp $RunDir/artifacts/bin/runtime/net8.0-$RunOS-Release-$RunArch/* $RunDir/artifacts/bin/testhost/net8.0-$RunOS-Release-$RunArch/shared/Microsoft.NETCore.App/8.0.0 -rf
cp $RunDir/artifacts/bin/testhost/net8.0-$RunOS-Release-$RunArch/* $RunDir/artifacts/dotnet-mono -r
cp $RunDir/artifacts/bin/coreclr/$RunOS.$RunArch.Release/corerun $RunDir/artifacts/dotnet-mono/shared/Microsoft.NETCore.App/8.0.0/corerun

# Create Core Root
$RunDir/src/tests/build.sh release $RunArch generatelayoutonly /p:LibrariesConfiguration=Release

# Clone performance 
git clone --branch main --depth 1 --quiet https://github.com/dotnet/performance.git $RunDir/performance

# Use Interpreter
export MONO_ENV_OPTIONS="--interpreter"

# One line run:
python3 $RunDir/performance/scripts/benchmarks_ci.py --csproj $RunDir/performance/src/benchmarks/micro/MicroBenchmarks.csproj --incremental no --architecture $RunArch -f net8.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;Double&gt;*' --bdn-artifacts $RunDir/artifacts/BenchmarkDotNet.Artifacts --bdn-arguments="--anyCategories Libraries Runtime  --category-exclusion-filter NoInterpreter NoMono --logBuildOutput --generateBinLog --corerun $RunDir/artifacts/dotnet-mono/shared/Microsoft.NETCore.App/8.0.0/corerun" 

# Individual Commands:
# Restore 
dotnet restore $RunDir/performance/src/benchmarks/micro/MicroBenchmarks.csproj --packages $RunDir/performance/artifacts/packages /p:UseSharedCompilation=false /p:BuildInParallel=false /m:1

# Build
dotnet build $RunDir/performance/src/benchmarks/micro/MicroBenchmarks.csproj --configuration Release --framework net8.0 --no-restore /p:NuGetPackageRoot=$RunDir/performance/artifacts/packages /p:UseSharedCompilation=false /p:BuildInParallel=false /m:1

# Run
dotnet run --project $RunDir/performance/src/benchmarks/micro/MicroBenchmarks.csproj --configuration Release --framework net8.0 --no-restore --no-build -- --filter 'System.Numerics.Tests.Perf_VectorOf&lt;Double&gt;*' --anyCategories Libraries Runtime " --category-exclusion-filter NoInterpreter NoMono --logBuildOutput --generateBinLog --corerun $RunDir/artifacts/dotnet-mono/shared/Microsoft.NETCore.App/8.0.0/corerun --artifacts $RunDir/artifacts/BenchmarkDotNet.Artifacts --packages $RunDir/performance/artifacts/packages

Windows

# Set $RunDir to the runtime directory
$RunDir="FullPathHere"

# Set the OS, arch, and OSId
RunOS='windows'
RunOSId='win'
RunArch='x64'

# Create mono dotnet
mkdir -p $RunDir/artifacts/dotnet-mono
$RunDir/build.sh -subset libs.pretest -configuration release -ci -arch $RunArch -testscope innerloop /p:RuntimeArtifactsPath=$RunDir\artifacts\bin\mono\$RunOS.$RunArch.Release /p:RuntimeFlavor=mono
xcopy $RunDir\artifacts\bin\runtime\net8.0-$RunOS-Release-$RunArch\ $RunDir\artifacts\bin\testhost\net8.0-$RunOS-Release-$RunArch\shared\Microsoft.NETCore.App\8.0.0\ /e /y
xcopy $RunDir\artifacts\bin\testhost\net8.0-$RunOS-Release-$RunArch\ $RunDir\artifacts\dotnet-mono\ /e /y
xcopy $RunDir\artifacts\bin\coreclr\$RunOS.$RunArch.Release\corerun $RunDir\artifacts\dotnet-mono\shared\Microsoft.NETCore.App\8.0.0\corerun /y

# Create Core Root
$RunDir\src\tests\build.cmd release $RunArch generatelayoutonly /p:LibrariesConfiguration=Release

# Clone performance 
git clone --branch main --depth 1 --quiet https://github.com/dotnet/performance.git $RunDir\performance

# Use Interpreter
export MONO_ENV_OPTIONS="--interpreter"

# One line run:
python3 $RunDir\performance\scripts\benchmarks_ci.py --csproj $RunDir\performance\src\benchmarks\micro\MicroBenchmarks.csproj --incremental no --architecture $RunArch -f net8.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;Double&gt;*' --bdn-artifacts $RunDir\artifacts\BenchmarkDotNet.Artifacts --bdn-arguments="--anyCategories Libraries Runtime  --category-exclusion-filter NoInterpreter NoMono --logBuildOutput --generateBinLog --corerun $RunDir\artifacts\dotnet-mono\shared\Microsoft.NETCore.App\8.0.0\corerun.exe" 

# Individual Commands:
# Restore 
dotnet restore $RunDir\performance\src\benchmarks\micro\MicroBenchmarks.csproj --packages $RunDir\performance\artifacts\packages /p:UseSharedCompilation=false /p:BuildInParallel=false /m:1

# Build
dotnet build $RunDir\performance\src\benchmarks\micro\MicroBenchmarks.csproj --configuration Release --framework net8.0 --no-restore /p:NuGetPackageRoot=$RunDir\performance\artifacts\packages /p:UseSharedCompilation=false /p:BuildInParallel=false /m:1

# Run
dotnet run --project $RunDir\performance\src\benchmarks\micro\MicroBenchmarks.csproj --configuration Release --framework net8.0 --no-restore --no-build -- --filter 'System.Numerics.Tests.Perf_VectorOf&lt;Double&gt;*' --anyCategories Libraries Runtime " --category-exclusion-filter NoInterpreter NoMono --logBuildOutput --generateBinLog --corerun $RunDir\artifacts\dotnet-mono\shared\Microsoft.NETCore.App\8.0.0\corerun.exe --artifacts $RunDir\artifacts\BenchmarkDotNet.Artifacts --packages $RunDir\performance\artifacts\packages

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_VectorOf<Double>.OneBenchmark

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 24.453986246565808 > 22.946906265802472.
IsChangePoint: Marked as a change because one of 4/6/2023 6:23:49 AM, 4/12/2023 4:44:56 PM, 6/2/2023 6:53:36 PM, 6/5/2023 4:27:01 PM falls between 5/27/2023 6:38:16 PM and 6/5/2023 4:27:01 PM.
IsRegressionStdDev: Marked as regression because -12.32597600355939 (T) = (0 -25.063827868305715) / Math.Sqrt((0.525769555894141 / (31)) + (0.4643205455730661 / (8))) is less than -2.026192463026769 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (31) + (8) - 2, .025) and -0.15564289235915835 = (21.688211846429297 - 25.063827868305715) / 21.688211846429297 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 ubuntu 18.04
Queue TigerUbuntu
Baseline 0214a047483067a6a813a34be5b6b1f757600961
Compare 2f18320e731cc3b06bc43cdb4d82dffc4f8f81fc
Diff Diff
Configs CompilationMode:tiered, LLVM:false, MonoAOT:false, MonoInterpreter:true, RunKind:micro_mono

Regressions in System.Numerics.Tests.Perf_VectorOf<Single>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
AbsBenchmark - Duration of single invocation 61.94 ns 65.64 ns 1.06 0.20 False
OneBenchmark - Duration of single invocation 33.84 ns 42.54 ns 1.26 0.20 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

Repro Steps

Prerequisites (Build files either built locally or downloaded from payload above)

  • Libraries build extracted to runtime/artifacts or build instructions: Libraries README args: -subset libs+libs.tests -rc release -configuration Release -arch $RunArch -framework net8.0
  • CoreCLR product build extracted to runtime/artifacts/bin/coreclr/$RunOS.$RunArch.Release, build instructions: CoreCLR README args: -subset clr+libs -rc release -configuration Release -arch $RunArch -framework net8.0
  • Mono Runtime build extracted to runtime/artifacts/bin/mono/$RunOS.$RunArch.Release, build instructions: MONO README args: -arch $RunArch -os $RunOS -s mono+libs+host+packs -c Release
  • Dotnet SDK installed for dotnet commands
  • Running commands from the runtime folder

Linux

# Set $RunDir to the runtime directory
RunDir=`pwd`

# Set the OS, arch, and OSId
RunOS='linux'
RunOSId='linux'
RunArch='x64'

# Create mono dotnet
mkdir -p $RunDir/artifacts/dotnet-mono
$RunDir/build.sh -subset libs.pretest -configuration release -ci -arch $RunArch -testscope innerloop /p:RuntimeArtifactsPath=$RunDir/artifacts/bin/mono/$RunOS.$RunArch.Release /p:RuntimeFlavor=mono
cp $RunDir/artifacts/bin/runtime/net8.0-$RunOS-Release-$RunArch/* $RunDir/artifacts/bin/testhost/net8.0-$RunOS-Release-$RunArch/shared/Microsoft.NETCore.App/8.0.0 -rf
cp $RunDir/artifacts/bin/testhost/net8.0-$RunOS-Release-$RunArch/* $RunDir/artifacts/dotnet-mono -r
cp $RunDir/artifacts/bin/coreclr/$RunOS.$RunArch.Release/corerun $RunDir/artifacts/dotnet-mono/shared/Microsoft.NETCore.App/8.0.0/corerun

# Create Core Root
$RunDir/src/tests/build.sh release $RunArch generatelayoutonly /p:LibrariesConfiguration=Release

# Clone performance 
git clone --branch main --depth 1 --quiet https://github.com/dotnet/performance.git $RunDir/performance

# Use Interpreter
export MONO_ENV_OPTIONS="--interpreter"

# One line run:
python3 $RunDir/performance/scripts/benchmarks_ci.py --csproj $RunDir/performance/src/benchmarks/micro/MicroBenchmarks.csproj --incremental no --architecture $RunArch -f net8.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;Single&gt;*' --bdn-artifacts $RunDir/artifacts/BenchmarkDotNet.Artifacts --bdn-arguments="--anyCategories Libraries Runtime  --category-exclusion-filter NoInterpreter NoMono --logBuildOutput --generateBinLog --corerun $RunDir/artifacts/dotnet-mono/shared/Microsoft.NETCore.App/8.0.0/corerun" 

# Individual Commands:
# Restore 
dotnet restore $RunDir/performance/src/benchmarks/micro/MicroBenchmarks.csproj --packages $RunDir/performance/artifacts/packages /p:UseSharedCompilation=false /p:BuildInParallel=false /m:1

# Build
dotnet build $RunDir/performance/src/benchmarks/micro/MicroBenchmarks.csproj --configuration Release --framework net8.0 --no-restore /p:NuGetPackageRoot=$RunDir/performance/artifacts/packages /p:UseSharedCompilation=false /p:BuildInParallel=false /m:1

# Run
dotnet run --project $RunDir/performance/src/benchmarks/micro/MicroBenchmarks.csproj --configuration Release --framework net8.0 --no-restore --no-build -- --filter 'System.Numerics.Tests.Perf_VectorOf&lt;Single&gt;*' --anyCategories Libraries Runtime " --category-exclusion-filter NoInterpreter NoMono --logBuildOutput --generateBinLog --corerun $RunDir/artifacts/dotnet-mono/shared/Microsoft.NETCore.App/8.0.0/corerun --artifacts $RunDir/artifacts/BenchmarkDotNet.Artifacts --packages $RunDir/performance/artifacts/packages

Windows

# Set $RunDir to the runtime directory
$RunDir="FullPathHere"

# Set the OS, arch, and OSId
RunOS='windows'
RunOSId='win'
RunArch='x64'

# Create mono dotnet
mkdir -p $RunDir/artifacts/dotnet-mono
$RunDir/build.sh -subset libs.pretest -configuration release -ci -arch $RunArch -testscope innerloop /p:RuntimeArtifactsPath=$RunDir\artifacts\bin\mono\$RunOS.$RunArch.Release /p:RuntimeFlavor=mono
xcopy $RunDir\artifacts\bin\runtime\net8.0-$RunOS-Release-$RunArch\ $RunDir\artifacts\bin\testhost\net8.0-$RunOS-Release-$RunArch\shared\Microsoft.NETCore.App\8.0.0\ /e /y
xcopy $RunDir\artifacts\bin\testhost\net8.0-$RunOS-Release-$RunArch\ $RunDir\artifacts\dotnet-mono\ /e /y
xcopy $RunDir\artifacts\bin\coreclr\$RunOS.$RunArch.Release\corerun $RunDir\artifacts\dotnet-mono\shared\Microsoft.NETCore.App\8.0.0\corerun /y

# Create Core Root
$RunDir\src\tests\build.cmd release $RunArch generatelayoutonly /p:LibrariesConfiguration=Release

# Clone performance 
git clone --branch main --depth 1 --quiet https://github.com/dotnet/performance.git $RunDir\performance

# Use Interpreter
export MONO_ENV_OPTIONS="--interpreter"

# One line run:
python3 $RunDir\performance\scripts\benchmarks_ci.py --csproj $RunDir\performance\src\benchmarks\micro\MicroBenchmarks.csproj --incremental no --architecture $RunArch -f net8.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;Single&gt;*' --bdn-artifacts $RunDir\artifacts\BenchmarkDotNet.Artifacts --bdn-arguments="--anyCategories Libraries Runtime  --category-exclusion-filter NoInterpreter NoMono --logBuildOutput --generateBinLog --corerun $RunDir\artifacts\dotnet-mono\shared\Microsoft.NETCore.App\8.0.0\corerun.exe" 

# Individual Commands:
# Restore 
dotnet restore $RunDir\performance\src\benchmarks\micro\MicroBenchmarks.csproj --packages $RunDir\performance\artifacts\packages /p:UseSharedCompilation=false /p:BuildInParallel=false /m:1

# Build
dotnet build $RunDir\performance\src\benchmarks\micro\MicroBenchmarks.csproj --configuration Release --framework net8.0 --no-restore /p:NuGetPackageRoot=$RunDir\performance\artifacts\packages /p:UseSharedCompilation=false /p:BuildInParallel=false /m:1

# Run
dotnet run --project $RunDir\performance\src\benchmarks\micro\MicroBenchmarks.csproj --configuration Release --framework net8.0 --no-restore --no-build -- --filter 'System.Numerics.Tests.Perf_VectorOf&lt;Single&gt;*' --anyCategories Libraries Runtime " --category-exclusion-filter NoInterpreter NoMono --logBuildOutput --generateBinLog --corerun $RunDir\artifacts\dotnet-mono\shared\Microsoft.NETCore.App\8.0.0\corerun.exe --artifacts $RunDir\artifacts\BenchmarkDotNet.Artifacts --packages $RunDir\performance\artifacts\packages

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_VectorOf<Single>.AbsBenchmark

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 65.64331154429536 > 65.41025247229987.
IsChangePoint: Marked as a change because one of 6/2/2023 6:53:36 PM, 6/5/2023 4:27:01 PM falls between 5/27/2023 6:38:16 PM and 6/5/2023 4:27:01 PM.
IsRegressionStdDev: Marked as regression because -5.413384388349239 (T) = (0 -67.98557358794382) / Math.Sqrt((2.163633155752701 / (31)) + (10.429668274894885 / (8))) is less than -2.026192463026769 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (31) + (8) - 2, .025) and -0.10292291826782121 = (61.64127380244988 - 67.98557358794382) / 61.64127380244988 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

System.Numerics.Tests.Perf_VectorOf<Single>.OneBenchmark

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 42.543600752277534 > 35.40286428024142.
IsChangePoint: Marked as a change because one of 4/11/2023 10:53:42 PM, 5/10/2023 2:00:36 PM, 6/2/2023 6:53:36 PM, 6/5/2023 4:27:01 PM falls between 5/27/2023 6:38:16 PM and 6/5/2023 4:27:01 PM.
IsRegressionStdDev: Marked as regression because -9.607115204879223 (T) = (0 -42.25933630947851) / Math.Sqrt((2.214764459732585 / (31)) + (5.872784045345695 / (8))) is less than -2.026192463026769 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (31) + (8) - 2, .025) and -0.2563438811733283 = (33.63675896603369 - 42.25933630947851) / 33.63675896603369 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 ubuntu 18.04
Queue TigerUbuntu
Baseline 0214a047483067a6a813a34be5b6b1f757600961
Compare 2f18320e731cc3b06bc43cdb4d82dffc4f8f81fc
Diff Diff
Configs CompilationMode:tiered, LLVM:false, MonoAOT:false, MonoInterpreter:true, RunKind:micro_mono

Regressions in System.Numerics.Tests.Perf_VectorOf<UInt32>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
MinBenchmark - Duration of single invocation 80.99 ns 95.93 ns 1.18 0.17 False
LessThanOrEqualBenchmark - Duration of single invocation 70.02 ns 77.93 ns 1.11 0.16 False
MaxBenchmark - Duration of single invocation 79.90 ns 84.12 ns 1.05 0.15 False
EqualsStaticBenchmark - Duration of single invocation 68.00 ns 79.37 ns 1.17 0.15 False
LessThanBenchmark - Duration of single invocation 69.86 ns 77.77 ns 1.11 0.15 False

graph
graph
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

Repro Steps

Prerequisites (Build files either built locally or downloaded from payload above)

  • Libraries build extracted to runtime/artifacts or build instructions: Libraries README args: -subset libs+libs.tests -rc release -configuration Release -arch $RunArch -framework net8.0
  • CoreCLR product build extracted to runtime/artifacts/bin/coreclr/$RunOS.$RunArch.Release, build instructions: CoreCLR README args: -subset clr+libs -rc release -configuration Release -arch $RunArch -framework net8.0
  • Mono Runtime build extracted to runtime/artifacts/bin/mono/$RunOS.$RunArch.Release, build instructions: MONO README args: -arch $RunArch -os $RunOS -s mono+libs+host+packs -c Release
  • Dotnet SDK installed for dotnet commands
  • Running commands from the runtime folder

Linux

# Set $RunDir to the runtime directory
RunDir=`pwd`

# Set the OS, arch, and OSId
RunOS='linux'
RunOSId='linux'
RunArch='x64'

# Create mono dotnet
mkdir -p $RunDir/artifacts/dotnet-mono
$RunDir/build.sh -subset libs.pretest -configuration release -ci -arch $RunArch -testscope innerloop /p:RuntimeArtifactsPath=$RunDir/artifacts/bin/mono/$RunOS.$RunArch.Release /p:RuntimeFlavor=mono
cp $RunDir/artifacts/bin/runtime/net8.0-$RunOS-Release-$RunArch/* $RunDir/artifacts/bin/testhost/net8.0-$RunOS-Release-$RunArch/shared/Microsoft.NETCore.App/8.0.0 -rf
cp $RunDir/artifacts/bin/testhost/net8.0-$RunOS-Release-$RunArch/* $RunDir/artifacts/dotnet-mono -r
cp $RunDir/artifacts/bin/coreclr/$RunOS.$RunArch.Release/corerun $RunDir/artifacts/dotnet-mono/shared/Microsoft.NETCore.App/8.0.0/corerun

# Create Core Root
$RunDir/src/tests/build.sh release $RunArch generatelayoutonly /p:LibrariesConfiguration=Release

# Clone performance 
git clone --branch main --depth 1 --quiet https://github.com/dotnet/performance.git $RunDir/performance

# Use Interpreter
export MONO_ENV_OPTIONS="--interpreter"

# One line run:
python3 $RunDir/performance/scripts/benchmarks_ci.py --csproj $RunDir/performance/src/benchmarks/micro/MicroBenchmarks.csproj --incremental no --architecture $RunArch -f net8.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;UInt32&gt;*' --bdn-artifacts $RunDir/artifacts/BenchmarkDotNet.Artifacts --bdn-arguments="--anyCategories Libraries Runtime  --category-exclusion-filter NoInterpreter NoMono --logBuildOutput --generateBinLog --corerun $RunDir/artifacts/dotnet-mono/shared/Microsoft.NETCore.App/8.0.0/corerun" 

# Individual Commands:
# Restore 
dotnet restore $RunDir/performance/src/benchmarks/micro/MicroBenchmarks.csproj --packages $RunDir/performance/artifacts/packages /p:UseSharedCompilation=false /p:BuildInParallel=false /m:1

# Build
dotnet build $RunDir/performance/src/benchmarks/micro/MicroBenchmarks.csproj --configuration Release --framework net8.0 --no-restore /p:NuGetPackageRoot=$RunDir/performance/artifacts/packages /p:UseSharedCompilation=false /p:BuildInParallel=false /m:1

# Run
dotnet run --project $RunDir/performance/src/benchmarks/micro/MicroBenchmarks.csproj --configuration Release --framework net8.0 --no-restore --no-build -- --filter 'System.Numerics.Tests.Perf_VectorOf&lt;UInt32&gt;*' --anyCategories Libraries Runtime " --category-exclusion-filter NoInterpreter NoMono --logBuildOutput --generateBinLog --corerun $RunDir/artifacts/dotnet-mono/shared/Microsoft.NETCore.App/8.0.0/corerun --artifacts $RunDir/artifacts/BenchmarkDotNet.Artifacts --packages $RunDir/performance/artifacts/packages

Windows

# Set $RunDir to the runtime directory
$RunDir="FullPathHere"

# Set the OS, arch, and OSId
RunOS='windows'
RunOSId='win'
RunArch='x64'

# Create mono dotnet
mkdir -p $RunDir/artifacts/dotnet-mono
$RunDir/build.sh -subset libs.pretest -configuration release -ci -arch $RunArch -testscope innerloop /p:RuntimeArtifactsPath=$RunDir\artifacts\bin\mono\$RunOS.$RunArch.Release /p:RuntimeFlavor=mono
xcopy $RunDir\artifacts\bin\runtime\net8.0-$RunOS-Release-$RunArch\ $RunDir\artifacts\bin\testhost\net8.0-$RunOS-Release-$RunArch\shared\Microsoft.NETCore.App\8.0.0\ /e /y
xcopy $RunDir\artifacts\bin\testhost\net8.0-$RunOS-Release-$RunArch\ $RunDir\artifacts\dotnet-mono\ /e /y
xcopy $RunDir\artifacts\bin\coreclr\$RunOS.$RunArch.Release\corerun $RunDir\artifacts\dotnet-mono\shared\Microsoft.NETCore.App\8.0.0\corerun /y

# Create Core Root
$RunDir\src\tests\build.cmd release $RunArch generatelayoutonly /p:LibrariesConfiguration=Release

# Clone performance 
git clone --branch main --depth 1 --quiet https://github.com/dotnet/performance.git $RunDir\performance

# Use Interpreter
export MONO_ENV_OPTIONS="--interpreter"

# One line run:
python3 $RunDir\performance\scripts\benchmarks_ci.py --csproj $RunDir\performance\src\benchmarks\micro\MicroBenchmarks.csproj --incremental no --architecture $RunArch -f net8.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;UInt32&gt;*' --bdn-artifacts $RunDir\artifacts\BenchmarkDotNet.Artifacts --bdn-arguments="--anyCategories Libraries Runtime  --category-exclusion-filter NoInterpreter NoMono --logBuildOutput --generateBinLog --corerun $RunDir\artifacts\dotnet-mono\shared\Microsoft.NETCore.App\8.0.0\corerun.exe" 

# Individual Commands:
# Restore 
dotnet restore $RunDir\performance\src\benchmarks\micro\MicroBenchmarks.csproj --packages $RunDir\performance\artifacts\packages /p:UseSharedCompilation=false /p:BuildInParallel=false /m:1

# Build
dotnet build $RunDir\performance\src\benchmarks\micro\MicroBenchmarks.csproj --configuration Release --framework net8.0 --no-restore /p:NuGetPackageRoot=$RunDir\performance\artifacts\packages /p:UseSharedCompilation=false /p:BuildInParallel=false /m:1

# Run
dotnet run --project $RunDir\performance\src\benchmarks\micro\MicroBenchmarks.csproj --configuration Release --framework net8.0 --no-restore --no-build -- --filter 'System.Numerics.Tests.Perf_VectorOf&lt;UInt32&gt;*' --anyCategories Libraries Runtime " --category-exclusion-filter NoInterpreter NoMono --logBuildOutput --generateBinLog --corerun $RunDir\artifacts\dotnet-mono\shared\Microsoft.NETCore.App\8.0.0\corerun.exe --artifacts $RunDir\artifacts\BenchmarkDotNet.Artifacts --packages $RunDir\performance\artifacts\packages

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_VectorOf<UInt32>.MinBenchmark

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 95.92835843573133 > 84.51734113360612.
IsChangePoint: Marked as a change because one of 4/12/2023 4:44:56 PM, 6/2/2023 6:53:36 PM, 6/5/2023 4:27:01 PM falls between 5/27/2023 6:38:16 PM and 6/5/2023 4:27:01 PM.
IsRegressionStdDev: Marked as regression because -4.457709662718162 (T) = (0 -88.84887587085068) / Math.Sqrt((2.7770090419122657 / (31)) + (24.11520706950679 / (8))) is less than -2.026192463026769 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (31) + (8) - 2, .025) and -0.0969643130554456 = (80.99522911859745 - 88.84887587085068) / 80.99522911859745 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

System.Numerics.Tests.Perf_VectorOf<UInt32>.LessThanOrEqualBenchmark

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 77.93329981056941 > 73.54801624883825.
IsChangePoint: Marked as a change because one of 3/14/2023 5:06:59 PM, 3/16/2023 1:49:47 PM, 5/10/2023 2:00:36 PM, 5/18/2023 1:58:11 PM, 6/2/2023 6:53:36 PM, 6/5/2023 4:27:01 PM falls between 5/27/2023 6:38:16 PM and 6/5/2023 4:27:01 PM.
IsRegressionStdDev: Marked as regression because -13.828528156287858 (T) = (0 -77.73759020516718) / Math.Sqrt((6.420659169864607 / (31)) + (0.14555387515338025 / (8))) is less than -2.026192463026769 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (31) + (8) - 2, .025) and -0.09222517560841406 = (71.173593084287 - 77.73759020516718) / 71.173593084287 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

System.Numerics.Tests.Perf_VectorOf<UInt32>.MaxBenchmark

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 84.11577702929209 > 84.01472413040696.
IsChangePoint: Marked as a change because one of 4/17/2023 1:30:24 AM, 6/3/2023 4:12:47 AM, 6/5/2023 4:27:01 PM falls between 5/27/2023 6:38:16 PM and 6/5/2023 4:27:01 PM.
IsRegressionStdDev: Marked as regression because -2.027066648057749 (T) = (0 -91.15441513397342) / Math.Sqrt((7.2887431423170534 / (33)) + (149.10972276125736 / (6))) is less than -2.026192463026769 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (33) + (6) - 2, .025) and -0.12530204968617994 = (81.0043980275289 - 91.15441513397342) / 81.0043980275289 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

System.Numerics.Tests.Perf_VectorOf<UInt32>.EqualsStaticBenchmark

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 79.3743555865286 > 71.33672549699887.
IsChangePoint: Marked as a change because one of 5/10/2023 2:00:36 PM, 6/2/2023 6:53:36 PM, 6/5/2023 4:27:01 PM falls between 5/27/2023 6:38:16 PM and 6/5/2023 4:27:01 PM.
IsRegressionStdDev: Marked as regression because -9.116631122244293 (T) = (0 -74.56466127538336) / Math.Sqrt((0.8265113561142344 / (31)) + (3.834340637936446 / (8))) is less than -2.026192463026769 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (31) + (8) - 2, .025) and -0.09525125612161693 = (68.07995960618527 - 74.56466127538336) / 68.07995960618527 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

System.Numerics.Tests.Perf_VectorOf<UInt32>.LessThanBenchmark

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 77.76724431839433 > 73.45505274330976.
IsChangePoint: Marked as a change because one of 4/18/2023 4:36:42 PM, 6/2/2023 6:53:36 PM, 6/5/2023 4:27:01 PM falls between 5/27/2023 6:38:16 PM and 6/5/2023 4:27:01 PM.
IsRegressionStdDev: Marked as regression because -20.45617986320619 (T) = (0 -78.01831730513265) / Math.Sqrt((3.7412905264441294 / (31)) + (0.16695389545825168 / (8))) is less than -2.026192463026769 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (31) + (8) - 2, .025) and -0.10944555643760416 = (70.32189804396269 - 78.01831730513265) / 70.32189804396269 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 ubuntu 18.04
Queue TigerUbuntu
Baseline 0214a047483067a6a813a34be5b6b1f757600961
Compare 2f18320e731cc3b06bc43cdb4d82dffc4f8f81fc
Diff Diff
Configs CompilationMode:tiered, LLVM:false, MonoAOT:false, MonoInterpreter:true, RunKind:micro_mono

Regressions in System.Runtime.Intrinsics.Tests.Perf_Vector128

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
ConvertUIntToFloatBenchmark - Duration of single invocation 63.56 ns 68.11 ns 1.07 0.14 False

graph
Test Report

Repro

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

Payloads

Baseline
Compare

Repro Steps

Prerequisites (Build files either built locally or downloaded from payload above)

  • Libraries build extracted to runtime/artifacts or build instructions: Libraries README args: -subset libs+libs.tests -rc release -configuration Release -arch $RunArch -framework net8.0
  • CoreCLR product build extracted to runtime/artifacts/bin/coreclr/$RunOS.$RunArch.Release, build instructions: CoreCLR README args: -subset clr+libs -rc release -configuration Release -arch $RunArch -framework net8.0
  • Mono Runtime build extracted to runtime/artifacts/bin/mono/$RunOS.$RunArch.Release, build instructions: MONO README args: -arch $RunArch -os $RunOS -s mono+libs+host+packs -c Release
  • Dotnet SDK installed for dotnet commands
  • Running commands from the runtime folder

Linux

# Set $RunDir to the runtime directory
RunDir=`pwd`

# Set the OS, arch, and OSId
RunOS='linux'
RunOSId='linux'
RunArch='x64'

# Create mono dotnet
mkdir -p $RunDir/artifacts/dotnet-mono
$RunDir/build.sh -subset libs.pretest -configuration release -ci -arch $RunArch -testscope innerloop /p:RuntimeArtifactsPath=$RunDir/artifacts/bin/mono/$RunOS.$RunArch.Release /p:RuntimeFlavor=mono
cp $RunDir/artifacts/bin/runtime/net8.0-$RunOS-Release-$RunArch/* $RunDir/artifacts/bin/testhost/net8.0-$RunOS-Release-$RunArch/shared/Microsoft.NETCore.App/8.0.0 -rf
cp $RunDir/artifacts/bin/testhost/net8.0-$RunOS-Release-$RunArch/* $RunDir/artifacts/dotnet-mono -r
cp $RunDir/artifacts/bin/coreclr/$RunOS.$RunArch.Release/corerun $RunDir/artifacts/dotnet-mono/shared/Microsoft.NETCore.App/8.0.0/corerun

# Create Core Root
$RunDir/src/tests/build.sh release $RunArch generatelayoutonly /p:LibrariesConfiguration=Release

# Clone performance 
git clone --branch main --depth 1 --quiet https://github.com/dotnet/performance.git $RunDir/performance

# Use Interpreter
export MONO_ENV_OPTIONS="--interpreter"

# One line run:
python3 $RunDir/performance/scripts/benchmarks_ci.py --csproj $RunDir/performance/src/benchmarks/micro/MicroBenchmarks.csproj --incremental no --architecture $RunArch -f net8.0 --filter 'System.Runtime.Intrinsics.Tests.Perf_Vector128*' --bdn-artifacts $RunDir/artifacts/BenchmarkDotNet.Artifacts --bdn-arguments="--anyCategories Libraries Runtime  --category-exclusion-filter NoInterpreter NoMono --logBuildOutput --generateBinLog --corerun $RunDir/artifacts/dotnet-mono/shared/Microsoft.NETCore.App/8.0.0/corerun" 

# Individual Commands:
# Restore 
dotnet restore $RunDir/performance/src/benchmarks/micro/MicroBenchmarks.csproj --packages $RunDir/performance/artifacts/packages /p:UseSharedCompilation=false /p:BuildInParallel=false /m:1

# Build
dotnet build $RunDir/performance/src/benchmarks/micro/MicroBenchmarks.csproj --configuration Release --framework net8.0 --no-restore /p:NuGetPackageRoot=$RunDir/performance/artifacts/packages /p:UseSharedCompilation=false /p:BuildInParallel=false /m:1

# Run
dotnet run --project $RunDir/performance/src/benchmarks/micro/MicroBenchmarks.csproj --configuration Release --framework net8.0 --no-restore --no-build -- --filter 'System.Runtime.Intrinsics.Tests.Perf_Vector128*' --anyCategories Libraries Runtime " --category-exclusion-filter NoInterpreter NoMono --logBuildOutput --generateBinLog --corerun $RunDir/artifacts/dotnet-mono/shared/Microsoft.NETCore.App/8.0.0/corerun --artifacts $RunDir/artifacts/BenchmarkDotNet.Artifacts --packages $RunDir/performance/artifacts/packages

Windows

# Set $RunDir to the runtime directory
$RunDir="FullPathHere"

# Set the OS, arch, and OSId
RunOS='windows'
RunOSId='win'
RunArch='x64'

# Create mono dotnet
mkdir -p $RunDir/artifacts/dotnet-mono
$RunDir/build.sh -subset libs.pretest -configuration release -ci -arch $RunArch -testscope innerloop /p:RuntimeArtifactsPath=$RunDir\artifacts\bin\mono\$RunOS.$RunArch.Release /p:RuntimeFlavor=mono
xcopy $RunDir\artifacts\bin\runtime\net8.0-$RunOS-Release-$RunArch\ $RunDir\artifacts\bin\testhost\net8.0-$RunOS-Release-$RunArch\shared\Microsoft.NETCore.App\8.0.0\ /e /y
xcopy $RunDir\artifacts\bin\testhost\net8.0-$RunOS-Release-$RunArch\ $RunDir\artifacts\dotnet-mono\ /e /y
xcopy $RunDir\artifacts\bin\coreclr\$RunOS.$RunArch.Release\corerun $RunDir\artifacts\dotnet-mono\shared\Microsoft.NETCore.App\8.0.0\corerun /y

# Create Core Root
$RunDir\src\tests\build.cmd release $RunArch generatelayoutonly /p:LibrariesConfiguration=Release

# Clone performance 
git clone --branch main --depth 1 --quiet https://github.com/dotnet/performance.git $RunDir\performance

# Use Interpreter
export MONO_ENV_OPTIONS="--interpreter"

# One line run:
python3 $RunDir\performance\scripts\benchmarks_ci.py --csproj $RunDir\performance\src\benchmarks\micro\MicroBenchmarks.csproj --incremental no --architecture $RunArch -f net8.0 --filter 'System.Runtime.Intrinsics.Tests.Perf_Vector128*' --bdn-artifacts $RunDir\artifacts\BenchmarkDotNet.Artifacts --bdn-arguments="--anyCategories Libraries Runtime  --category-exclusion-filter NoInterpreter NoMono --logBuildOutput --generateBinLog --corerun $RunDir\artifacts\dotnet-mono\shared\Microsoft.NETCore.App\8.0.0\corerun.exe" 

# Individual Commands:
# Restore 
dotnet restore $RunDir\performance\src\benchmarks\micro\MicroBenchmarks.csproj --packages $RunDir\performance\artifacts\packages /p:UseSharedCompilation=false /p:BuildInParallel=false /m:1

# Build
dotnet build $RunDir\performance\src\benchmarks\micro\MicroBenchmarks.csproj --configuration Release --framework net8.0 --no-restore /p:NuGetPackageRoot=$RunDir\performance\artifacts\packages /p:UseSharedCompilation=false /p:BuildInParallel=false /m:1

# Run
dotnet run --project $RunDir\performance\src\benchmarks\micro\MicroBenchmarks.csproj --configuration Release --framework net8.0 --no-restore --no-build -- --filter 'System.Runtime.Intrinsics.Tests.Perf_Vector128*' --anyCategories Libraries Runtime " --category-exclusion-filter NoInterpreter NoMono --logBuildOutput --generateBinLog --corerun $RunDir\artifacts\dotnet-mono\shared\Microsoft.NETCore.App\8.0.0\corerun.exe --artifacts $RunDir\artifacts\BenchmarkDotNet.Artifacts --packages $RunDir\performance\artifacts\packages

Payloads

Baseline
Compare

Histogram

System.Runtime.Intrinsics.Tests.Perf_Vector128.ConvertUIntToFloatBenchmark

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 68.11016558271288 > 66.43330889698382.
IsChangePoint: Marked as a change because one of 4/25/2023 1:57:48 PM, 4/26/2023 6:27:29 AM, 6/2/2023 6:53:36 PM, 6/5/2023 4:27:01 PM falls between 5/27/2023 6:38:16 PM and 6/5/2023 4:27:01 PM.
IsRegressionStdDev: Marked as regression because -13.408614348126468 (T) = (0 -68.46619229829822) / Math.Sqrt((3.658653076455545 / (31)) + (0.2287726159752659 / (8))) is less than -2.026192463026769 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (31) + (8) - 2, .025) and -0.08106888713989988 = (63.33194222195583 - 68.46619229829822) / 63.33194222195583 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
Copy link
Author

performanceautofiler bot commented Jun 6, 2023 •
edited
Loading

Run Information

Name Value
Architecture x64
OS ubuntu 18.04
Queue TigerUbuntu
Baseline 0214a047483067a6a813a34be5b6b1f757600961
Compare 2f18320e731cc3b06bc43cdb4d82dffc4f8f81fc
Diff Diff
Configs CompilationMode:tiered, LLVM:false, MonoAOT:false, MonoInterpreter:true, RunKind:micro_mono

Regressions in System.Numerics.Tests.Perf_VectorOf<Int32>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
DivisionOperatorBenchmark - Duration of single invocation 71.67 ns 76.79 ns 1.07 0.16 False
LessThanBenchmark - Duration of single invocation 70.09 ns 77.80 ns 1.11 0.14 False
GreaterThanOrEqualBenchmark - Duration of single invocation 67.98 ns 72.73 ns 1.07 0.13 False
GreaterThanBenchmark - Duration of single invocation 68.43 ns 73.51 ns 1.07 0.18 False
SquareRootBenchmark - Duration of single invocation 61.93 ns 66.85 ns 1.08 0.13 False
LessThanOrEqualBenchmark - Duration of single invocation 70.18 ns 84.66 ns 1.21 0.18 False
MinBenchmark - Duration of single invocation 80.38 ns 86.21 ns 1.07 0.13 False

graph
graph
graph
graph
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

Repro Steps

Prerequisites (Build files either built locally or downloaded from payload above)

  • Libraries build extracted to runtime/artifacts or build instructions: Libraries README args: -subset libs+libs.tests -rc release -configuration Release -arch $RunArch -framework net8.0
  • CoreCLR product build extracted to runtime/artifacts/bin/coreclr/$RunOS.$RunArch.Release, build instructions: CoreCLR README args: -subset clr+libs -rc release -configuration Release -arch $RunArch -framework net8.0
  • Mono Runtime build extracted to runtime/artifacts/bin/mono/$RunOS.$RunArch.Release, build instructions: MONO README args: -arch $RunArch -os $RunOS -s mono+libs+host+packs -c Release
  • Dotnet SDK installed for dotnet commands
  • Running commands from the runtime folder

Linux

# Set $RunDir to the runtime directory
RunDir=`pwd`

# Set the OS, arch, and OSId
RunOS='linux'
RunOSId='linux'
RunArch='x64'

# Create mono dotnet
mkdir -p $RunDir/artifacts/dotnet-mono
$RunDir/build.sh -subset libs.pretest -configuration release -ci -arch $RunArch -testscope innerloop /p:RuntimeArtifactsPath=$RunDir/artifacts/bin/mono/$RunOS.$RunArch.Release /p:RuntimeFlavor=mono
cp $RunDir/artifacts/bin/runtime/net8.0-$RunOS-Release-$RunArch/* $RunDir/artifacts/bin/testhost/net8.0-$RunOS-Release-$RunArch/shared/Microsoft.NETCore.App/8.0.0 -rf
cp $RunDir/artifacts/bin/testhost/net8.0-$RunOS-Release-$RunArch/* $RunDir/artifacts/dotnet-mono -r
cp $RunDir/artifacts/bin/coreclr/$RunOS.$RunArch.Release/corerun $RunDir/artifacts/dotnet-mono/shared/Microsoft.NETCore.App/8.0.0/corerun

# Create Core Root
$RunDir/src/tests/build.sh release $RunArch generatelayoutonly /p:LibrariesConfiguration=Release

# Clone performance 
git clone --branch main --depth 1 --quiet https://github.com/dotnet/performance.git $RunDir/performance

# Use Interpreter
export MONO_ENV_OPTIONS="--interpreter"

# One line run:
python3 $RunDir/performance/scripts/benchmarks_ci.py --csproj $RunDir/performance/src/benchmarks/micro/MicroBenchmarks.csproj --incremental no --architecture $RunArch -f net8.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;Int32&gt;*' --bdn-artifacts $RunDir/artifacts/BenchmarkDotNet.Artifacts --bdn-arguments="--anyCategories Libraries Runtime  --category-exclusion-filter NoInterpreter NoMono --logBuildOutput --generateBinLog --corerun $RunDir/artifacts/dotnet-mono/shared/Microsoft.NETCore.App/8.0.0/corerun" 

# Individual Commands:
# Restore 
dotnet restore $RunDir/performance/src/benchmarks/micro/MicroBenchmarks.csproj --packages $RunDir/performance/artifacts/packages /p:UseSharedCompilation=false /p:BuildInParallel=false /m:1

# Build
dotnet build $RunDir/performance/src/benchmarks/micro/MicroBenchmarks.csproj --configuration Release --framework net8.0 --no-restore /p:NuGetPackageRoot=$RunDir/performance/artifacts/packages /p:UseSharedCompilation=false /p:BuildInParallel=false /m:1

# Run
dotnet run --project $RunDir/performance/src/benchmarks/micro/MicroBenchmarks.csproj --configuration Release --framework net8.0 --no-restore --no-build -- --filter 'System.Numerics.Tests.Perf_VectorOf&lt;Int32&gt;*' --anyCategories Libraries Runtime " --category-exclusion-filter NoInterpreter NoMono --logBuildOutput --generateBinLog --corerun $RunDir/artifacts/dotnet-mono/shared/Microsoft.NETCore.App/8.0.0/corerun --artifacts $RunDir/artifacts/BenchmarkDotNet.Artifacts --packages $RunDir/performance/artifacts/packages

Windows

# Set $RunDir to the runtime directory
$RunDir="FullPathHere"

# Set the OS, arch, and OSId
RunOS='windows'
RunOSId='win'
RunArch='x64'

# Create mono dotnet
mkdir -p $RunDir/artifacts/dotnet-mono
$RunDir/build.sh -subset libs.pretest -configuration release -ci -arch $RunArch -testscope innerloop /p:RuntimeArtifactsPath=$RunDir\artifacts\bin\mono\$RunOS.$RunArch.Release /p:RuntimeFlavor=mono
xcopy $RunDir\artifacts\bin\runtime\net8.0-$RunOS-Release-$RunArch\ $RunDir\artifacts\bin\testhost\net8.0-$RunOS-Release-$RunArch\shared\Microsoft.NETCore.App\8.0.0\ /e /y
xcopy $RunDir\artifacts\bin\testhost\net8.0-$RunOS-Release-$RunArch\ $RunDir\artifacts\dotnet-mono\ /e /y
xcopy $RunDir\artifacts\bin\coreclr\$RunOS.$RunArch.Release\corerun $RunDir\artifacts\dotnet-mono\shared\Microsoft.NETCore.App\8.0.0\corerun /y

# Create Core Root
$RunDir\src\tests\build.cmd release $RunArch generatelayoutonly /p:LibrariesConfiguration=Release

# Clone performance 
git clone --branch main --depth 1 --quiet https://github.com/dotnet/performance.git $RunDir\performance

# Use Interpreter
export MONO_ENV_OPTIONS="--interpreter"

# One line run:
python3 $RunDir\performance\scripts\benchmarks_ci.py --csproj $RunDir\performance\src\benchmarks\micro\MicroBenchmarks.csproj --incremental no --architecture $RunArch -f net8.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;Int32&gt;*' --bdn-artifacts $RunDir\artifacts\BenchmarkDotNet.Artifacts --bdn-arguments="--anyCategories Libraries Runtime  --category-exclusion-filter NoInterpreter NoMono --logBuildOutput --generateBinLog --corerun $RunDir\artifacts\dotnet-mono\shared\Microsoft.NETCore.App\8.0.0\corerun.exe" 

# Individual Commands:
# Restore 
dotnet restore $RunDir\performance\src\benchmarks\micro\MicroBenchmarks.csproj --packages $RunDir\performance\artifacts\packages /p:UseSharedCompilation=false /p:BuildInParallel=false /m:1

# Build
dotnet build $RunDir\performance\src\benchmarks\micro\MicroBenchmarks.csproj --configuration Release --framework net8.0 --no-restore /p:NuGetPackageRoot=$RunDir\performance\artifacts\packages /p:UseSharedCompilation=false /p:BuildInParallel=false /m:1

# Run
dotnet run --project $RunDir\performance\src\benchmarks\micro\MicroBenchmarks.csproj --configuration Release --framework net8.0 --no-restore --no-build -- --filter 'System.Numerics.Tests.Perf_VectorOf&lt;Int32&gt;*' --anyCategories Libraries Runtime " --category-exclusion-filter NoInterpreter NoMono --logBuildOutput --generateBinLog --corerun $RunDir\artifacts\dotnet-mono\shared\Microsoft.NETCore.App\8.0.0\corerun.exe --artifacts $RunDir\artifacts\BenchmarkDotNet.Artifacts --packages $RunDir\performance\artifacts\packages

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_VectorOf<Int32>.DivisionOperatorBenchmark

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 76.79063694555967 > 75.34329669750544.
IsChangePoint: Marked as a change because one of 3/13/2023 6:11:08 PM, 3/14/2023 10:43:28 AM, 6/2/2023 6:53:36 PM, 6/5/2023 4:27:01 PM falls between 5/27/2023 6:38:16 PM and 6/5/2023 4:27:01 PM.
IsRegressionStdDev: Marked as regression because -4.9904856495849526 (T) = (0 -77.48062041827704) / Math.Sqrt((5.922457925254232 / (31)) + (5.745135570778818 / (8))) is less than -2.026192463026769 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (31) + (8) - 2, .025) and -0.06543398142358646 = (72.72212241133028 - 77.48062041827704) / 72.72212241133028 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

System.Numerics.Tests.Perf_VectorOf<Int32>.LessThanBenchmark

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 77.80409335253924 > 73.51162998700975.
IsChangePoint: Marked as a change because one of 6/2/2023 6:53:36 PM, 6/5/2023 4:27:01 PM falls between 5/27/2023 6:38:16 PM and 6/5/2023 4:27:01 PM.
IsRegressionStdDev: Marked as regression because -13.689914126447869 (T) = (0 -78.03018577932832) / Math.Sqrt((9.336647578388032 / (31)) + (0.20474422668473272 / (8))) is less than -2.026192463026769 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (31) + (8) - 2, .025) and -0.111470678106055 = (70.20444831913306 - 78.03018577932832) / 70.20444831913306 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

System.Numerics.Tests.Perf_VectorOf<Int32>.GreaterThanOrEqualBenchmark

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 72.72720904151637 > 71.419102998906.
IsChangePoint: Marked as a change because one of 5/10/2023 2:00:36 PM, 6/2/2023 1:14:24 PM, 6/5/2023 4:27:01 PM falls between 5/27/2023 6:38:16 PM and 6/5/2023 4:27:01 PM.
IsRegressionStdDev: Marked as regression because -5.202124932148511 (T) = (0 -74.06024374006087) / Math.Sqrt((20.735522408405462 / (30)) + (0.8448784425501253 / (9))) is less than -2.026192463026769 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (30) + (9) - 2, .025) and -0.0663672326144313 = (69.45097474393138 - 74.06024374006087) / 69.45097474393138 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

System.Numerics.Tests.Perf_VectorOf<Int32>.GreaterThanBenchmark

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 73.50948615586698 > 71.37272509744152.
IsChangePoint: Marked as a change because one of 4/21/2023 6:49:58 AM, 5/10/2023 2:00:36 PM, 6/2/2023 6:53:36 PM, 6/5/2023 4:27:01 PM falls between 5/27/2023 6:38:16 PM and 6/5/2023 4:27:01 PM.
IsRegressionStdDev: Marked as regression because -12.599555069943634 (T) = (0 -73.74715083097458) / Math.Sqrt((4.936774015960166 / (31)) + (0.2734284104401215 / (8))) is less than -2.026192463026769 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (31) + (8) - 2, .025) and -0.08124471503945023 = (68.20579079388503 - 73.74715083097458) / 68.20579079388503 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

System.Numerics.Tests.Perf_VectorOf<Int32>.SquareRootBenchmark

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 66.84687218278464 > 65.04773304436945.
IsChangePoint: Marked as a change because one of 6/2/2023 6:53:36 PM, 6/5/2023 4:27:01 PM falls between 5/27/2023 6:38:16 PM and 6/5/2023 4:27:01 PM.
IsRegressionStdDev: Marked as regression because -5.474712950219962 (T) = (0 -68.00553714491095) / Math.Sqrt((2.2699511325018604 / (31)) + (6.624449363711505 / (8))) is less than -2.026192463026769 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (31) + (8) - 2, .025) and -0.08275149188649694 = (62.808075218094324 - 68.00553714491095) / 62.808075218094324 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

System.Numerics.Tests.Perf_VectorOf<Int32>.LessThanOrEqualBenchmark

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 84.65557082192963 > 73.43478862396833.
IsChangePoint: Marked as a change because one of 6/2/2023 6:53:36 PM, 6/5/2023 4:27:01 PM falls between 5/27/2023 6:38:16 PM and 6/5/2023 4:27:01 PM.
IsRegressionStdDev: Marked as regression because -9.102138433108417 (T) = (0 -79.48799542865852) / Math.Sqrt((1.9963002990132022 / (30)) + (7.724656707329765 / (8))) is less than -2.028094000977961 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (30) + (8) - 2, .025) and -0.13164979261096882 = (70.24080766653256 - 79.48799542865852) / 70.24080766653256 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

System.Numerics.Tests.Perf_VectorOf<Int32>.MinBenchmark

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 86.20717986377852 > 84.7839009499437.
IsChangePoint: Marked as a change because one of 3/7/2023 7:00:18 AM, 3/7/2023 10:25:17 PM, 6/2/2023 6:53:36 PM, 6/5/2023 4:27:01 PM falls between 5/27/2023 6:38:16 PM and 6/5/2023 4:27:01 PM.
IsRegressionStdDev: Marked as regression because -21.32022475262961 (T) = (0 -86.18823218830114) / Math.Sqrt((1.8701959766565557 / (31)) + (0.05156299823943734 / (8))) is less than -2.026192463026769 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (31) + (8) - 2, .025) and -0.06828671671818447 = (80.67893276167892 - 86.18823218830114) / 80.67893276167892 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 ubuntu 18.04
Queue TigerUbuntu
Baseline 0214a047483067a6a813a34be5b6b1f757600961
Compare 2f18320e731cc3b06bc43cdb4d82dffc4f8f81fc
Diff Diff
Configs CompilationMode:tiered, LLVM:false, MonoAOT:false, MonoInterpreter:true, RunKind:micro_mono

Regressions in System.Numerics.Tests.Perf_VectorOf<Int64>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
AddBenchmark - Duration of single invocation 38.57 ns 40.85 ns 1.06 0.20 False

graph
Test Report

Repro

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

Payloads

Baseline
Compare

Repro Steps

Prerequisites (Build files either built locally or downloaded from payload above)

  • Libraries build extracted to runtime/artifacts or build instructions: Libraries README args: -subset libs+libs.tests -rc release -configuration Release -arch $RunArch -framework net8.0
  • CoreCLR product build extracted to runtime/artifacts/bin/coreclr/$RunOS.$RunArch.Release, build instructions: CoreCLR README args: -subset clr+libs -rc release -configuration Release -arch $RunArch -framework net8.0
  • Mono Runtime build extracted to runtime/artifacts/bin/mono/$RunOS.$RunArch.Release, build instructions: MONO README args: -arch $RunArch -os $RunOS -s mono+libs+host+packs -c Release
  • Dotnet SDK installed for dotnet commands
  • Running commands from the runtime folder

Linux

# Set $RunDir to the runtime directory
RunDir=`pwd`

# Set the OS, arch, and OSId
RunOS='linux'
RunOSId='linux'
RunArch='x64'

# Create mono dotnet
mkdir -p $RunDir/artifacts/dotnet-mono
$RunDir/build.sh -subset libs.pretest -configuration release -ci -arch $RunArch -testscope innerloop /p:RuntimeArtifactsPath=$RunDir/artifacts/bin/mono/$RunOS.$RunArch.Release /p:RuntimeFlavor=mono
cp $RunDir/artifacts/bin/runtime/net8.0-$RunOS-Release-$RunArch/* $RunDir/artifacts/bin/testhost/net8.0-$RunOS-Release-$RunArch/shared/Microsoft.NETCore.App/8.0.0 -rf
cp $RunDir/artifacts/bin/testhost/net8.0-$RunOS-Release-$RunArch/* $RunDir/artifacts/dotnet-mono -r
cp $RunDir/artifacts/bin/coreclr/$RunOS.$RunArch.Release/corerun $RunDir/artifacts/dotnet-mono/shared/Microsoft.NETCore.App/8.0.0/corerun

# Create Core Root
$RunDir/src/tests/build.sh release $RunArch generatelayoutonly /p:LibrariesConfiguration=Release

# Clone performance 
git clone --branch main --depth 1 --quiet https://github.com/dotnet/performance.git $RunDir/performance

# Use Interpreter
export MONO_ENV_OPTIONS="--interpreter"

# One line run:
python3 $RunDir/performance/scripts/benchmarks_ci.py --csproj $RunDir/performance/src/benchmarks/micro/MicroBenchmarks.csproj --incremental no --architecture $RunArch -f net8.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;Int64&gt;*' --bdn-artifacts $RunDir/artifacts/BenchmarkDotNet.Artifacts --bdn-arguments="--anyCategories Libraries Runtime  --category-exclusion-filter NoInterpreter NoMono --logBuildOutput --generateBinLog --corerun $RunDir/artifacts/dotnet-mono/shared/Microsoft.NETCore.App/8.0.0/corerun" 

# Individual Commands:
# Restore 
dotnet restore $RunDir/performance/src/benchmarks/micro/MicroBenchmarks.csproj --packages $RunDir/performance/artifacts/packages /p:UseSharedCompilation=false /p:BuildInParallel=false /m:1

# Build
dotnet build $RunDir/performance/src/benchmarks/micro/MicroBenchmarks.csproj --configuration Release --framework net8.0 --no-restore /p:NuGetPackageRoot=$RunDir/performance/artifacts/packages /p:UseSharedCompilation=false /p:BuildInParallel=false /m:1

# Run
dotnet run --project $RunDir/performance/src/benchmarks/micro/MicroBenchmarks.csproj --configuration Release --framework net8.0 --no-restore --no-build -- --filter 'System.Numerics.Tests.Perf_VectorOf&lt;Int64&gt;*' --anyCategories Libraries Runtime " --category-exclusion-filter NoInterpreter NoMono --logBuildOutput --generateBinLog --corerun $RunDir/artifacts/dotnet-mono/shared/Microsoft.NETCore.App/8.0.0/corerun --artifacts $RunDir/artifacts/BenchmarkDotNet.Artifacts --packages $RunDir/performance/artifacts/packages

Windows

# Set $RunDir to the runtime directory
$RunDir="FullPathHere"

# Set the OS, arch, and OSId
RunOS='windows'
RunOSId='win'
RunArch='x64'

# Create mono dotnet
mkdir -p $RunDir/artifacts/dotnet-mono
$RunDir/build.sh -subset libs.pretest -configuration release -ci -arch $RunArch -testscope innerloop /p:RuntimeArtifactsPath=$RunDir\artifacts\bin\mono\$RunOS.$RunArch.Release /p:RuntimeFlavor=mono
xcopy $RunDir\artifacts\bin\runtime\net8.0-$RunOS-Release-$RunArch\ $RunDir\artifacts\bin\testhost\net8.0-$RunOS-Release-$RunArch\shared\Microsoft.NETCore.App\8.0.0\ /e /y
xcopy $RunDir\artifacts\bin\testhost\net8.0-$RunOS-Release-$RunArch\ $RunDir\artifacts\dotnet-mono\ /e /y
xcopy $RunDir\artifacts\bin\coreclr\$RunOS.$RunArch.Release\corerun $RunDir\artifacts\dotnet-mono\shared\Microsoft.NETCore.App\8.0.0\corerun /y

# Create Core Root
$RunDir\src\tests\build.cmd release $RunArch generatelayoutonly /p:LibrariesConfiguration=Release

# Clone performance 
git clone --branch main --depth 1 --quiet https://github.com/dotnet/performance.git $RunDir\performance

# Use Interpreter
export MONO_ENV_OPTIONS="--interpreter"

# One line run:
python3 $RunDir\performance\scripts\benchmarks_ci.py --csproj $RunDir\performance\src\benchmarks\micro\MicroBenchmarks.csproj --incremental no --architecture $RunArch -f net8.0 --filter 'System.Numerics.Tests.Perf_VectorOf&lt;Int64&gt;*' --bdn-artifacts $RunDir\artifacts\BenchmarkDotNet.Artifacts --bdn-arguments="--anyCategories Libraries Runtime  --category-exclusion-filter NoInterpreter NoMono --logBuildOutput --generateBinLog --corerun $RunDir\artifacts\dotnet-mono\shared\Microsoft.NETCore.App\8.0.0\corerun.exe" 

# Individual Commands:
# Restore 
dotnet restore $RunDir\performance\src\benchmarks\micro\MicroBenchmarks.csproj --packages $RunDir\performance\artifacts\packages /p:UseSharedCompilation=false /p:BuildInParallel=false /m:1

# Build
dotnet build $RunDir\performance\src\benchmarks\micro\MicroBenchmarks.csproj --configuration Release --framework net8.0 --no-restore /p:NuGetPackageRoot=$RunDir\performance\artifacts\packages /p:UseSharedCompilation=false /p:BuildInParallel=false /m:1

# Run
dotnet run --project $RunDir\performance\src\benchmarks\micro\MicroBenchmarks.csproj --configuration Release --framework net8.0 --no-restore --no-build -- --filter 'System.Numerics.Tests.Perf_VectorOf&lt;Int64&gt;*' --anyCategories Libraries Runtime " --category-exclusion-filter NoInterpreter NoMono --logBuildOutput --generateBinLog --corerun $RunDir\artifacts\dotnet-mono\shared\Microsoft.NETCore.App\8.0.0\corerun.exe --artifacts $RunDir\artifacts\BenchmarkDotNet.Artifacts --packages $RunDir\performance\artifacts\packages

Payloads

Baseline
Compare

Histogram

System.Numerics.Tests.Perf_VectorOf<Int64>.AddBenchmark

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 40.85050538974211 > 40.43809357308549.
IsChangePoint: Marked as a change because one of 5/12/2023 4:02:48 AM, 6/2/2023 6:53:36 PM, 6/5/2023 4:27:01 PM falls between 5/27/2023 6:38:16 PM and 6/5/2023 4:27:01 PM.
IsRegressionStdDev: Marked as regression because -5.327498956387599 (T) = (0 -41.2363325448851) / Math.Sqrt((2.1600287759482724 / (31)) + (0.7924955310684484 / (8))) is less than -2.026192463026769 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (31) + (8) - 2, .025) and -0.05604476634563909 = (39.04790200095421 - 41.2363325448851) / 39.04790200095421 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

@kotlarmilos
Copy link
Member

@kg is there any chance dotnet/runtime#87077 have caused the regressions?

@kotlarmilos kotlarmilos mentioned this issue Jun 7, 2023
Closed
@kg
Copy link

kg commented Jun 7, 2023

@kg is there any chance dotnet/runtime#87077 have caused the regressions?

I am fairly certain it's not possible. But I don't see anything in the diff range that looks responsible.

@kotlarmilos
Copy link
Member

Noise in the measurement according to the historical data.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
arch-x64 branch-refs/heads/main kind-micro_mono mono-interpreter os-linux perf-regression PGO Applied if there were any profile guided optimization updates in the observed interval. runtime-mono
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@kg @kotlarmilos