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: 14 Regressions on 4/17/2023 1:30:24 AM #16361

Closed
performanceautofiler bot opened this issue Apr 18, 2023 · 9 comments
Closed

[Perf] Linux/x64: 14 Regressions on 4/17/2023 1:30:24 AM #16361

performanceautofiler bot opened this issue Apr 18, 2023 · 9 comments
Labels
arch-x64 branch-refs/heads/main kind-micro_mono LinkedFromMaster Is this issue linked from the master perf issue mono-aot os-linux perf-regression runtime-mono

Comments

@performanceautofiler
Copy link

performanceautofiler bot commented Apr 18, 2023 •
edited
Loading

Run Information

Name Value
Architecture x64
OS ubuntu 18.04
Queue TigerUbuntu
Baseline e7ed417c2bf4a24a0694a387f33ba843a2318fdc
Compare c1b7a9feb6f3b4d9ca27dc4f74d8260e4edb73e8
Diff Diff
Configs CompilationMode:tiered, LLVM:false, MonoAOT:true, MonoInterpreter:false, RunKind:micro_mono

Regressions in System.Linq.Tests.Perf_Enumerable

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
GroupBy - Duration of single invocation 3.55 μs 3.89 μs 1.10 0.01 False

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 (Files either built locally (with build.(sh/cmd) or downloaded from payload above (if same system setup) (in this order))

  • 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 $RunArch -framework net8.0
  • AOT MONO build extracted to runtime/artifacts/bin/mono/$RunOS.$RunArch.Release, build instructions: MONO README args: -arch $RunArch -os $RunOS -s mono+libs+host+packs -c Release /p:CrossBuild=false /p:MonoLLVMUseCxx11Abi=false
  • 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 aot directory 
mkdir -p $RunDir/artifacts/bin/aot/sgen
mkdir -p $RunDir/artifacts/bin/aot/pack
cp -r $RunDir/artifacts/obj/mono/$RunOS.$RunArch.Release/mono/* $RunDir/artifacts/bin/aot/sgen
cp -r $RunDir/artifacts/bin/microsoft.netcore.app.runtime.$RunOS-$RunArch/Release/* $RunDir/artifacts/bin/aot/pack

# 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

# 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.Linq.Tests.Perf_Enumerable*' --bdn-artifacts $RunDir/artifacts/BenchmarkDotNet.Artifacts --bdn-arguments="--anyCategories Libraries Runtime  --category-exclusion-filter NoAOT NoWASM --runtimes monoaotllvm --aotcompilerpath $RunDir/artifacts/bin/aot/sgen/mini/mono-sgen --customruntimepack $RunDir/artifacts/bin/aot/pack --aotcompilermode llvm --logBuildOutput --generateBinLog"

# 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.Linq.Tests.Perf_Enumerable* --anyCategories Libraries Runtime " --category-exclusion-filter NoAOT NoWASM --runtimes monoaotllvm --aotcompilerpath $RunDir/artifacts/bin/aot/sgen/mini/mono-sgen --customruntimepack $RunDir/artifacts/bin/aot/pack --aotcompilermode llvm --logBuildOutput --generateBinLog " --artifacts $RunDir/artifacts/BenchmarkDotNet.Artifacts --packages $RunDir/performance/artifacts/packages --buildTimeout 1200

Windows

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

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

# Create aot directory
mkdir $RunDir\artifacts\bin\aot\sgen
mkdir $RunDir\artifacts\bin\aot\pack
xcopy $RunDir\artifacts\obj\mono\$RunOS.$RunArch.Release\mono $RunDir\artifacts\bin\aot\sgen\ /e /y
xcopy $RunDir\artifacts\bin\microsoft.netcore.app.runtime.$RunOSId-$RunArch\Release $RunDir\artifacts\bin\aot\pack\ /e /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

# 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.Linq.Tests.Perf_Enumerable*' --bdn-artifacts $RunDir\artifacts\BenchmarkDotNet.Artifacts --bdn-arguments="--anyCategories Libraries Runtime  --category-exclusion-filter NoAOT NoWASM --runtimes monoaotllvm --aotcompilerpath $RunDir\artifacts\bin\aot\sgen\mini\mono-sgen.exe --customruntimepack $RunDir\artifacts\bin\aot\pack --aotcompilermode llvm --logBuildOutput --generateBinLog"

# 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.Linq.Tests.Perf_Enumerable* --anyCategories Libraries Runtime " --category-exclusion-filter NoAOT NoWASM --runtimes monoaotllvm --aotcompilerpath $RunDir\artifacts\bin\aot\sgen\mini\mono-sgen.exe --customruntimepack $RunDir\artifacts\bin\aot\pack -aotcompilermode llvm --logBuildOutput --generateBinLog " --artifacts $RunDir\artifacts\BenchmarkDotNet.Artifacts --packages $RunDir\performance\artifacts\packages --buildTimeout 1200

Payloads

Baseline
Compare

Histogram

System.Linq.Tests.Perf_Enumerable.GroupBy(input: IEnumerable)

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 3.887127089035415 > 3.738592290001163.
IsChangePoint: Marked as a change because one of 2/24/2023 12:21:41 AM, 4/12/2023 4:44:56 PM, 4/17/2023 11:29:15 PM falls between 4/9/2023 11:24:15 AM and 4/17/2023 11:29:15 PM.
IsRegressionStdDev: Marked as regression because -47.57959220880649 (T) = (0 -3894.353387902118) / Math.Sqrt((1244.5694515618377 / (32)) + (39.21943804142913 / (3))) is less than -2.034515297446192 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (32) + (3) - 2, .025) and -0.09657948209865881 = (3551.3644487028114 - 3894.353387902118) / 3551.3644487028114 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.

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 e7ed417c2bf4a24a0694a387f33ba843a2318fdc
Compare c1b7a9feb6f3b4d9ca27dc4f74d8260e4edb73e8
Diff Diff
Configs CompilationMode:tiered, LLVM:false, MonoAOT:true, MonoInterpreter:false, RunKind:micro_mono

Regressions in StoreBlock.LocalAddress

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
InitBlockAllOnes8 - Duration of single invocation 4.44 ns 5.89 ns 1.33 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

Repro Steps

Prerequisites (Files either built locally (with build.(sh/cmd) or downloaded from payload above (if same system setup) (in this order))

  • 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 $RunArch -framework net8.0
  • AOT MONO build extracted to runtime/artifacts/bin/mono/$RunOS.$RunArch.Release, build instructions: MONO README args: -arch $RunArch -os $RunOS -s mono+libs+host+packs -c Release /p:CrossBuild=false /p:MonoLLVMUseCxx11Abi=false
  • 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 aot directory 
mkdir -p $RunDir/artifacts/bin/aot/sgen
mkdir -p $RunDir/artifacts/bin/aot/pack
cp -r $RunDir/artifacts/obj/mono/$RunOS.$RunArch.Release/mono/* $RunDir/artifacts/bin/aot/sgen
cp -r $RunDir/artifacts/bin/microsoft.netcore.app.runtime.$RunOS-$RunArch/Release/* $RunDir/artifacts/bin/aot/pack

# 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

# 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 'StoreBlock.LocalAddress*' --bdn-artifacts $RunDir/artifacts/BenchmarkDotNet.Artifacts --bdn-arguments="--anyCategories Libraries Runtime  --category-exclusion-filter NoAOT NoWASM --runtimes monoaotllvm --aotcompilerpath $RunDir/artifacts/bin/aot/sgen/mini/mono-sgen --customruntimepack $RunDir/artifacts/bin/aot/pack --aotcompilermode llvm --logBuildOutput --generateBinLog"

# 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 StoreBlock.LocalAddress* --anyCategories Libraries Runtime " --category-exclusion-filter NoAOT NoWASM --runtimes monoaotllvm --aotcompilerpath $RunDir/artifacts/bin/aot/sgen/mini/mono-sgen --customruntimepack $RunDir/artifacts/bin/aot/pack --aotcompilermode llvm --logBuildOutput --generateBinLog " --artifacts $RunDir/artifacts/BenchmarkDotNet.Artifacts --packages $RunDir/performance/artifacts/packages --buildTimeout 1200

Windows

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

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

# Create aot directory
mkdir $RunDir\artifacts\bin\aot\sgen
mkdir $RunDir\artifacts\bin\aot\pack
xcopy $RunDir\artifacts\obj\mono\$RunOS.$RunArch.Release\mono $RunDir\artifacts\bin\aot\sgen\ /e /y
xcopy $RunDir\artifacts\bin\microsoft.netcore.app.runtime.$RunOSId-$RunArch\Release $RunDir\artifacts\bin\aot\pack\ /e /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

# 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 'StoreBlock.LocalAddress*' --bdn-artifacts $RunDir\artifacts\BenchmarkDotNet.Artifacts --bdn-arguments="--anyCategories Libraries Runtime  --category-exclusion-filter NoAOT NoWASM --runtimes monoaotllvm --aotcompilerpath $RunDir\artifacts\bin\aot\sgen\mini\mono-sgen.exe --customruntimepack $RunDir\artifacts\bin\aot\pack --aotcompilermode llvm --logBuildOutput --generateBinLog"

# 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 StoreBlock.LocalAddress* --anyCategories Libraries Runtime " --category-exclusion-filter NoAOT NoWASM --runtimes monoaotllvm --aotcompilerpath $RunDir\artifacts\bin\aot\sgen\mini\mono-sgen.exe --customruntimepack $RunDir\artifacts\bin\aot\pack -aotcompilermode llvm --logBuildOutput --generateBinLog " --artifacts $RunDir\artifacts\BenchmarkDotNet.Artifacts --packages $RunDir\performance\artifacts\packages --buildTimeout 1200

Payloads

Baseline
Compare

Histogram

StoreBlock.LocalAddress.InitBlockAllOnes8

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 5.887488395845173 > 4.674741650472123.
IsChangePoint: Marked as a change because one of 2/15/2023 12:21:17 PM, 3/13/2023 12:04:12 PM, 4/5/2023 11:58:06 PM, 4/12/2023 4:44:56 PM, 4/17/2023 11:29:15 PM falls between 4/9/2023 11:24:15 AM and 4/17/2023 11:29:15 PM.
IsRegressionStdDev: Marked as regression because -5.678900310694933 (T) = (0 -5.6858776669697875) / Math.Sqrt((0.03609416526359048 / (31)) + (0.08129377199532836 / (2))) is less than -2.0395134463927462 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (31) + (2) - 2, .025) and -0.2566397436629582 = (4.524668024899577 - 5.6858776669697875) / 4.524668024899577 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.

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 e7ed417c2bf4a24a0694a387f33ba843a2318fdc
Compare c1b7a9feb6f3b4d9ca27dc4f74d8260e4edb73e8
Diff Diff
Configs CompilationMode:tiered, LLVM:false, MonoAOT:true, MonoInterpreter:false, RunKind:micro_mono

Regressions in System.Collections.CopyTo<String>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
Span - Duration of single invocation 1.39 μs 1.83 μs 1.32 0.01 False
List - Duration of single invocation 1.39 μs 1.84 μs 1.32 0.03 False
ImmutableArray - Duration of single invocation 1.47 μs 1.90 μs 1.29 0.05 False
Array - Duration of single invocation 1.46 μs 1.90 μs 1.30 0.07 False
Memory - Duration of single invocation 1.42 μs 1.85 μs 1.31 0.05 False
ReadOnlyMemory - Duration of single invocation 1.41 μs 1.86 μs 1.32 0.02 False
ReadOnlySpan - Duration of single invocation 1.39 μs 1.84 μs 1.32 0.01 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 (Files either built locally (with build.(sh/cmd) or downloaded from payload above (if same system setup) (in this order))

  • 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 $RunArch -framework net8.0
  • AOT MONO build extracted to runtime/artifacts/bin/mono/$RunOS.$RunArch.Release, build instructions: MONO README args: -arch $RunArch -os $RunOS -s mono+libs+host+packs -c Release /p:CrossBuild=false /p:MonoLLVMUseCxx11Abi=false
  • 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 aot directory 
mkdir -p $RunDir/artifacts/bin/aot/sgen
mkdir -p $RunDir/artifacts/bin/aot/pack
cp -r $RunDir/artifacts/obj/mono/$RunOS.$RunArch.Release/mono/* $RunDir/artifacts/bin/aot/sgen
cp -r $RunDir/artifacts/bin/microsoft.netcore.app.runtime.$RunOS-$RunArch/Release/* $RunDir/artifacts/bin/aot/pack

# 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

# 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.Collections.CopyTo&lt;String&gt;*' --bdn-artifacts $RunDir/artifacts/BenchmarkDotNet.Artifacts --bdn-arguments="--anyCategories Libraries Runtime  --category-exclusion-filter NoAOT NoWASM --runtimes monoaotllvm --aotcompilerpath $RunDir/artifacts/bin/aot/sgen/mini/mono-sgen --customruntimepack $RunDir/artifacts/bin/aot/pack --aotcompilermode llvm --logBuildOutput --generateBinLog"

# 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.Collections.CopyTo&lt;String&gt;* --anyCategories Libraries Runtime " --category-exclusion-filter NoAOT NoWASM --runtimes monoaotllvm --aotcompilerpath $RunDir/artifacts/bin/aot/sgen/mini/mono-sgen --customruntimepack $RunDir/artifacts/bin/aot/pack --aotcompilermode llvm --logBuildOutput --generateBinLog " --artifacts $RunDir/artifacts/BenchmarkDotNet.Artifacts --packages $RunDir/performance/artifacts/packages --buildTimeout 1200

Windows

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

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

# Create aot directory
mkdir $RunDir\artifacts\bin\aot\sgen
mkdir $RunDir\artifacts\bin\aot\pack
xcopy $RunDir\artifacts\obj\mono\$RunOS.$RunArch.Release\mono $RunDir\artifacts\bin\aot\sgen\ /e /y
xcopy $RunDir\artifacts\bin\microsoft.netcore.app.runtime.$RunOSId-$RunArch\Release $RunDir\artifacts\bin\aot\pack\ /e /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

# 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.Collections.CopyTo&lt;String&gt;*' --bdn-artifacts $RunDir\artifacts\BenchmarkDotNet.Artifacts --bdn-arguments="--anyCategories Libraries Runtime  --category-exclusion-filter NoAOT NoWASM --runtimes monoaotllvm --aotcompilerpath $RunDir\artifacts\bin\aot\sgen\mini\mono-sgen.exe --customruntimepack $RunDir\artifacts\bin\aot\pack --aotcompilermode llvm --logBuildOutput --generateBinLog"

# 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.Collections.CopyTo&lt;String&gt;* --anyCategories Libraries Runtime " --category-exclusion-filter NoAOT NoWASM --runtimes monoaotllvm --aotcompilerpath $RunDir\artifacts\bin\aot\sgen\mini\mono-sgen.exe --customruntimepack $RunDir\artifacts\bin\aot\pack -aotcompilermode llvm --logBuildOutput --generateBinLog " --artifacts $RunDir\artifacts\BenchmarkDotNet.Artifacts --packages $RunDir\performance\artifacts\packages --buildTimeout 1200

Payloads

Baseline
Compare

Histogram

System.Collections.CopyTo<String>.Span(Size: 2048)

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 1.8311509402611619 > 1.462104405618501.
IsChangePoint: Marked as a change because one of 4/12/2023 4:44:56 PM, 4/17/2023 11:29:15 PM falls between 4/9/2023 11:24:15 AM and 4/17/2023 11:29:15 PM.
IsRegressionStdDev: Marked as regression because -229.57025982852278 (T) = (0 -1832.4984140122845) / Math.Sqrt((59.0363394997998 / (32)) + (5.454864289416478 / (3))) is less than -2.034515297446192 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (32) + (3) - 2, .025) and -0.3153970610083753 = (1393.1142681796039 - 1832.4984140122845) / 1393.1142681796039 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.

System.Collections.CopyTo<String>.List(Size: 2048)

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 1.8362452619510023 > 1.4586348522724484.
IsChangePoint: Marked as a change because one of 4/12/2023 4:44:56 PM, 4/17/2023 11:29:15 PM falls between 4/9/2023 11:24:15 AM and 4/17/2023 11:29:15 PM.
IsRegressionStdDev: Marked as regression because -59.81059786483695 (T) = (0 -1838.143895619105) / Math.Sqrt((107.11889897930276 / (32)) + (157.12362823851248 / (3))) is less than -2.034515297446192 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (32) + (3) - 2, .025) and -0.3208143602070343 = (1391.6746751079997 - 1838.143895619105) / 1391.6746751079997 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.

System.Collections.CopyTo<String>.ImmutableArray(Size: 2048)

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 1.898935151690175 > 1.543165166919089.
IsChangePoint: Marked as a change because one of 4/12/2023 4:44:56 PM, 4/17/2023 11:29:15 PM falls between 4/9/2023 11:24:15 AM and 4/17/2023 11:29:15 PM.
IsRegressionStdDev: Marked as regression because -83.88008271178099 (T) = (0 -1905.243514234953) / Math.Sqrt((494.65674903225806 / (32)) + (32.287161865332884 / (3))) is less than -2.034515297446192 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (32) + (3) - 2, .025) and -0.29105308147753006 = (1475.7282574737517 - 1905.243514234953) / 1475.7282574737517 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.

System.Collections.CopyTo<String>.Array(Size: 2048)

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 1.8960831835664338 > 1.528437795442668.
IsChangePoint: Marked as a change because one of 4/12/2023 4:44:56 PM, 4/17/2023 11:29:15 PM falls between 4/9/2023 11:24:15 AM and 4/17/2023 11:29:15 PM.
IsRegressionStdDev: Marked as regression because -117.88816692854058 (T) = (0 -1895.712806285079) / Math.Sqrt((424.5771124117872 / (32)) + (0.2743586610873221 / (2))) is less than -2.03693334345674 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (32) + (2) - 2, .025) and -0.2948085780336037 = (1464.0873086924207 - 1895.712806285079) / 1464.0873086924207 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.

System.Collections.CopyTo<String>.Memory(Size: 2048)

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 1.8515024691541104 > 1.4837268556349303.
IsChangePoint: Marked as a change because one of 4/12/2023 4:44:56 PM, 4/17/2023 11:29:15 PM falls between 4/9/2023 11:24:15 AM and 4/17/2023 11:29:15 PM.
IsRegressionStdDev: Marked as regression because -160.75723064797933 (T) = (0 -1852.6534860326694) / Math.Sqrt((216.08928553116942 / (32)) + (1.833616548272508 / (3))) is less than -2.034515297446192 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (32) + (3) - 2, .025) and -0.30799082438893105 = (1416.4116838496896 - 1852.6534860326694) / 1416.4116838496896 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.

System.Collections.CopyTo<String>.ReadOnlyMemory(Size: 2048)

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 1.8587302163690587 > 1.4803618270676546.
IsChangePoint: Marked as a change because one of 4/12/2023 4:44:56 PM, 4/17/2023 11:29:15 PM falls between 4/9/2023 11:24:15 AM and 4/17/2023 11:29:15 PM.
IsRegressionStdDev: Marked as regression because -147.78470175282746 (T) = (0 -1853.1245201060601) / Math.Sqrt((33.10763843094257 / (32)) + (23.658379591020093 / (3))) is less than -2.034515297446192 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (32) + (3) - 2, .025) and -0.3126649626121382 = (1411.7269622390425 - 1853.1245201060601) / 1411.7269622390425 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.

System.Collections.CopyTo<String>.ReadOnlySpan(Size: 2048)

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 1.8353331575500247 > 1.4550727582089193.
IsChangePoint: Marked as a change because one of 4/12/2023 4:44:56 PM, 4/17/2023 11:29:15 PM falls between 4/9/2023 11:24:15 AM and 4/17/2023 11:29:15 PM.
IsRegressionStdDev: Marked as regression because -166.1474854271144 (T) = (0 -1830.447001812654) / Math.Sqrt((27.51492151465147 / (32)) + (18.699850717435154 / (3))) is less than -2.034515297446192 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (32) + (3) - 2, .025) and -0.3188155307258884 = (1387.947714571695 - 1830.447001812654) / 1387.947714571695 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.

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 e7ed417c2bf4a24a0694a387f33ba843a2318fdc
Compare c1b7a9feb6f3b4d9ca27dc4f74d8260e4edb73e8
Diff Diff
Configs CompilationMode:tiered, LLVM:false, MonoAOT:true, MonoInterpreter:false, RunKind:micro_mono

Regressions in System.Buffers.Text.Tests.Utf8FormatterTests

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
FormatterInt32 - Duration of single invocation 13.94 ns 33.92 ns 2.43 0.02 False
FormatterDecimal - Duration of single invocation 135.46 ns 170.06 ns 1.26 0.00 False
FormatterUInt32 - Duration of single invocation 14.09 ns 30.94 ns 2.20 0.01 False
FormatterUInt64 - Duration of single invocation 13.97 ns 38.59 ns 2.76 0.01 False

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 (Files either built locally (with build.(sh/cmd) or downloaded from payload above (if same system setup) (in this order))

  • 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 $RunArch -framework net8.0
  • AOT MONO build extracted to runtime/artifacts/bin/mono/$RunOS.$RunArch.Release, build instructions: MONO README args: -arch $RunArch -os $RunOS -s mono+libs+host+packs -c Release /p:CrossBuild=false /p:MonoLLVMUseCxx11Abi=false
  • 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 aot directory 
mkdir -p $RunDir/artifacts/bin/aot/sgen
mkdir -p $RunDir/artifacts/bin/aot/pack
cp -r $RunDir/artifacts/obj/mono/$RunOS.$RunArch.Release/mono/* $RunDir/artifacts/bin/aot/sgen
cp -r $RunDir/artifacts/bin/microsoft.netcore.app.runtime.$RunOS-$RunArch/Release/* $RunDir/artifacts/bin/aot/pack

# 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

# 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.Buffers.Text.Tests.Utf8FormatterTests*' --bdn-artifacts $RunDir/artifacts/BenchmarkDotNet.Artifacts --bdn-arguments="--anyCategories Libraries Runtime  --category-exclusion-filter NoAOT NoWASM --runtimes monoaotllvm --aotcompilerpath $RunDir/artifacts/bin/aot/sgen/mini/mono-sgen --customruntimepack $RunDir/artifacts/bin/aot/pack --aotcompilermode llvm --logBuildOutput --generateBinLog"

# 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.Buffers.Text.Tests.Utf8FormatterTests* --anyCategories Libraries Runtime " --category-exclusion-filter NoAOT NoWASM --runtimes monoaotllvm --aotcompilerpath $RunDir/artifacts/bin/aot/sgen/mini/mono-sgen --customruntimepack $RunDir/artifacts/bin/aot/pack --aotcompilermode llvm --logBuildOutput --generateBinLog " --artifacts $RunDir/artifacts/BenchmarkDotNet.Artifacts --packages $RunDir/performance/artifacts/packages --buildTimeout 1200

Windows

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

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

# Create aot directory
mkdir $RunDir\artifacts\bin\aot\sgen
mkdir $RunDir\artifacts\bin\aot\pack
xcopy $RunDir\artifacts\obj\mono\$RunOS.$RunArch.Release\mono $RunDir\artifacts\bin\aot\sgen\ /e /y
xcopy $RunDir\artifacts\bin\microsoft.netcore.app.runtime.$RunOSId-$RunArch\Release $RunDir\artifacts\bin\aot\pack\ /e /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

# 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.Buffers.Text.Tests.Utf8FormatterTests*' --bdn-artifacts $RunDir\artifacts\BenchmarkDotNet.Artifacts --bdn-arguments="--anyCategories Libraries Runtime  --category-exclusion-filter NoAOT NoWASM --runtimes monoaotllvm --aotcompilerpath $RunDir\artifacts\bin\aot\sgen\mini\mono-sgen.exe --customruntimepack $RunDir\artifacts\bin\aot\pack --aotcompilermode llvm --logBuildOutput --generateBinLog"

# 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.Buffers.Text.Tests.Utf8FormatterTests* --anyCategories Libraries Runtime " --category-exclusion-filter NoAOT NoWASM --runtimes monoaotllvm --aotcompilerpath $RunDir\artifacts\bin\aot\sgen\mini\mono-sgen.exe --customruntimepack $RunDir\artifacts\bin\aot\pack -aotcompilermode llvm --logBuildOutput --generateBinLog " --artifacts $RunDir\artifacts\BenchmarkDotNet.Artifacts --packages $RunDir\performance\artifacts\packages --buildTimeout 1200

Payloads

Baseline
Compare

Histogram

System.Buffers.Text.Tests.Utf8FormatterTests.FormatterInt32(value: 4)

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 33.9151550964328 > 14.64853113726557.
IsChangePoint: Marked as a change because one of 4/12/2023 4:44:56 PM, 4/17/2023 11:29:15 PM falls between 4/9/2023 11:24:15 AM and 4/17/2023 11:29:15 PM.
IsRegressionStdDev: Marked as regression because -102.50384154460747 (T) = (0 -33.53613612101288) / Math.Sqrt((0.014826587180579097 / (33)) + (0.10813282063343416 / (3))) is less than -2.0322445093148245 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (33) + (3) - 2, .025) and -1.4032434622955796 = (13.954531302034269 - 33.53613612101288) / 13.954531302034269 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.

System.Buffers.Text.Tests.Utf8FormatterTests.FormatterDecimal(value: 123456.789)

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 170.05706406350967 > 139.69935050776354.
IsChangePoint: Marked as a change because one of 4/12/2023 4:44:56 PM, 4/17/2023 11:29:15 PM falls between 4/9/2023 11:24:15 AM and 4/17/2023 11:29:15 PM.
IsRegressionStdDev: Marked as regression because -60.954048195380956 (T) = (0 -169.1188925722246) / Math.Sqrt((2.5628494839503606 / (32)) + (0.7200510444293529 / (3))) is less than -2.034515297446192 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (32) + (3) - 2, .025) and -0.2561533482612199 = (134.63236220826118 - 169.1188925722246) / 134.63236220826118 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.

System.Buffers.Text.Tests.Utf8FormatterTests.FormatterUInt32(value: 0)

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 30.941670582290616 > 14.669559669881329.
IsChangePoint: Marked as a change because one of 4/12/2023 4:44:56 PM, 4/17/2023 11:29:15 PM falls between 4/9/2023 11:24:15 AM and 4/17/2023 11:29:15 PM.
IsRegressionStdDev: Marked as regression because -755.1540205774565 (T) = (0 -30.978058161658634) / Math.Sqrt((0.0054413805304492835 / (31)) + (0.0009933312583328142 / (3))) is less than -2.03693334345674 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (31) + (3) - 2, .025) and -1.2157937999390074 = (13.980569023395292 - 30.978058161658634) / 13.980569023395292 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.

System.Buffers.Text.Tests.Utf8FormatterTests.FormatterUInt64(value: 0)

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 38.59458694826479 > 14.646464626494977.
IsChangePoint: Marked as a change because one of 4/12/2023 4:44:56 PM, 4/17/2023 11:29:15 PM falls between 4/9/2023 11:24:15 AM and 4/17/2023 11:29:15 PM.
IsRegressionStdDev: Marked as regression because -615.0060853406278 (T) = (0 -38.65855994495812) / Math.Sqrt((0.001193115286073401 / (31)) + (0.00472363831142205 / (3))) is less than -2.03693334345674 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (31) + (3) - 2, .025) and -1.769570673480579 = (13.958322246521725 - 38.65855994495812) / 13.958322246521725 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.

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository
@performanceautofiler
Copy link
Author

performanceautofiler bot commented Apr 18, 2023 •
edited
Loading

Run Information

Name Value
Architecture x64
OS ubuntu 18.04
Queue TigerUbuntu
Baseline e7ed417c2bf4a24a0694a387f33ba843a2318fdc
Compare c1b7a9feb6f3b4d9ca27dc4f74d8260e4edb73e8
Diff Diff
Configs CompilationMode:tiered, LLVM:false, MonoAOT:true, MonoInterpreter:false, RunKind:micro_mono

Regressions in System.Tests.Perf_Guid

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio Baseline ETL Compare ETL
GuidToString - Duration of single invocation 75.69 ns 85.73 ns 1.13 0.02 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 (Files either built locally (with build.(sh/cmd) or downloaded from payload above (if same system setup) (in this order))

  • 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 $RunArch -framework net8.0
  • AOT MONO build extracted to runtime/artifacts/bin/mono/$RunOS.$RunArch.Release, build instructions: MONO README args: -arch $RunArch -os $RunOS -s mono+libs+host+packs -c Release /p:CrossBuild=false /p:MonoLLVMUseCxx11Abi=false
  • 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 aot directory 
mkdir -p $RunDir/artifacts/bin/aot/sgen
mkdir -p $RunDir/artifacts/bin/aot/pack
cp -r $RunDir/artifacts/obj/mono/$RunOS.$RunArch.Release/mono/* $RunDir/artifacts/bin/aot/sgen
cp -r $RunDir/artifacts/bin/microsoft.netcore.app.runtime.$RunOS-$RunArch/Release/* $RunDir/artifacts/bin/aot/pack

# 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

# 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.Tests.Perf_Guid*' --bdn-artifacts $RunDir/artifacts/BenchmarkDotNet.Artifacts --bdn-arguments="--anyCategories Libraries Runtime  --category-exclusion-filter NoAOT NoWASM --runtimes monoaotllvm --aotcompilerpath $RunDir/artifacts/bin/aot/sgen/mini/mono-sgen --customruntimepack $RunDir/artifacts/bin/aot/pack --aotcompilermode llvm --logBuildOutput --generateBinLog"

# 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.Tests.Perf_Guid* --anyCategories Libraries Runtime " --category-exclusion-filter NoAOT NoWASM --runtimes monoaotllvm --aotcompilerpath $RunDir/artifacts/bin/aot/sgen/mini/mono-sgen --customruntimepack $RunDir/artifacts/bin/aot/pack --aotcompilermode llvm --logBuildOutput --generateBinLog " --artifacts $RunDir/artifacts/BenchmarkDotNet.Artifacts --packages $RunDir/performance/artifacts/packages --buildTimeout 1200

Windows

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

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

# Create aot directory
mkdir $RunDir\artifacts\bin\aot\sgen
mkdir $RunDir\artifacts\bin\aot\pack
xcopy $RunDir\artifacts\obj\mono\$RunOS.$RunArch.Release\mono $RunDir\artifacts\bin\aot\sgen\ /e /y
xcopy $RunDir\artifacts\bin\microsoft.netcore.app.runtime.$RunOSId-$RunArch\Release $RunDir\artifacts\bin\aot\pack\ /e /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

# 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.Tests.Perf_Guid*' --bdn-artifacts $RunDir\artifacts\BenchmarkDotNet.Artifacts --bdn-arguments="--anyCategories Libraries Runtime  --category-exclusion-filter NoAOT NoWASM --runtimes monoaotllvm --aotcompilerpath $RunDir\artifacts\bin\aot\sgen\mini\mono-sgen.exe --customruntimepack $RunDir\artifacts\bin\aot\pack --aotcompilermode llvm --logBuildOutput --generateBinLog"

# 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.Tests.Perf_Guid* --anyCategories Libraries Runtime " --category-exclusion-filter NoAOT NoWASM --runtimes monoaotllvm --aotcompilerpath $RunDir\artifacts\bin\aot\sgen\mini\mono-sgen.exe --customruntimepack $RunDir\artifacts\bin\aot\pack -aotcompilermode llvm --logBuildOutput --generateBinLog " --artifacts $RunDir\artifacts\BenchmarkDotNet.Artifacts --packages $RunDir\performance\artifacts\packages --buildTimeout 1200

Payloads

Baseline
Compare

Histogram

System.Tests.Perf_Guid.GuidToString

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 85.73124911170949 > 80.61474353922618.
IsChangePoint: Marked as a change because one of 4/12/2023 4:44:56 PM, 4/17/2023 11:29:15 PM falls between 4/9/2023 11:24:15 AM and 4/17/2023 11:29:15 PM.
IsRegressionStdDev: Marked as regression because -12.800850343152844 (T) = (0 -87.40128595156021) / Math.Sqrt((0.6002879859077066 / (32)) + (2.1137289877105707 / (3))) is less than -2.034515297446192 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (32) + (3) - 2, .025) and -0.1422873172813559 = (76.51427502458426 - 87.40128595156021) / 76.51427502458426 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.

Docs

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

@kotlarmilos
Copy link
Member

Range too wide, should be investigated further

@kotlarmilos
Copy link
Member

@stephentoub could some of the regressions (i.e. System.Tests.Perf_Guid.GuidToString) be related to dotnet/runtime#84553?

@kotlarmilos kotlarmilos mentioned this issue Apr 20, 2023
Closed
@kotlarmilos kotlarmilos added the LinkedFromMaster Is this issue linked from the master perf issue label Apr 20, 2023
@stephentoub
Copy link
Member

stephentoub commented Apr 24, 2023 •
edited
Loading

could some of the regressions (i.e. System.Tests.Perf_Guid.GuidToString) be related to dotnet/runtime#84553?

Yes. I was expecting @vargaz's and my subsequent changes to bring the number back down, but it doesn't appear to have budged. At this point I don't know what could be done other than improving the generics support in mono. Zoltan?

@vargaz
Copy link

vargaz commented Apr 25, 2023

Marking HexsToChars with AggressiveInlining seems to fix the regression to Guid.ToString ().

@stephentoub
Copy link
Member

stephentoub commented Apr 25, 2023 •
edited
Loading

That means Ssse3 isn't supported? Are any of the intrinsics?

I can mark that helper as AggressiveInlining if you'd like.

@vargaz
Copy link

vargaz commented Apr 25, 2023 •
edited
Loading

This is the aot=true,llvm=false configuration, so simd is not supported yet. Adding AggressiveInlining seems to help on wasm as well.

@stephentoub
Copy link
Member

dotnet/runtime#85322

@kotlarmilos
Copy link
Member

Resolved by dotnet/runtime#85277.

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 LinkedFromMaster Is this issue linked from the master perf issue mono-aot os-linux perf-regression runtime-mono
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@vargaz @stephentoub @kotlarmilos