[Perf] Linux/x64: 1 Regression on 12/6/2023 10:36:59 AM

[performanceautofiler]

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	c08faf9216976a14f06a11373fbd3aec7671bf7a
Compare	2bfa26cebc917d05a3363078fa277ab5fee2651b
Diff	Diff
Configs	CompilationMode:tiered, LLVM:true, MonoAOT:true, MonoInterpreter:false, RunKind:micro_mono

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

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
AbsBenchmark - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	24.57 ns	27.78 ns	1.13	0.02	True

Test Report

Repro

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

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.Numerics.Tests.Perf_VectorOf<SByte>*' --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.Numerics.Tests.Perf_VectorOf<SByte>* --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.Numerics.Tests.Perf_VectorOf<SByte>*' --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.Numerics.Tests.Perf_VectorOf<SByte>* --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

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

ETL Files

Histogram

JIT Disasms

Docs

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

[kotlarmilos]

Looks related to dotnet/runtime#95597.

/cc: @MichalPetryka

[MichalPetryka]

Looks related to dotnet/runtime#95597.

Even if so, that was correctness fix. And Abs should be intrinsified on AOT builds it seems:
https://github.com/dotnet/runtime/blob/f9529fd9c3fe8a970fb7a68b7fddd15fb686b5dd/src/mono/mono/mini/simd-intrinsics.c#L1478-L1481

[matouskozak]

Reproduced locally with dotnet/runtime#95597.

[fanyang-mono]

As @MichalPetryka mentioned earlier, the intrinsics support for {Vector, Vector128}.Abs for integer types is missing for mini JIT on amd64. Adding that should fix this.

[matouskozak]

As @MichalPetryka mentioned earlier, the intrinsics support for {Vector, Vector128}.Abs for integer types is missing for mini JIT on amd64. Adding that should fix this.

This is AOT-llvm scenario, that should be intrinsified.

[fanyang-mono]

This is a microbenchmark test written with generics. It won't be AOT'ed, but fall back to mini JIT.

[fanyang-mono]

The interesting thing is that the performance of Vector.Abs didn't change for int16, int32, int64, which I would expect similar regression.

[fanyang-mono]

https://www.intel.com/content/www/us/en/docs/intrinsics-guide/index.html#techs=SSE_ALL&text=abs&ig_expand=10,19,37 these intrinsics probably could be used.

[jkurdek]

Regression would be fixed by intrinsifyingSystem.Numerics.Vectorstatic methods on x64. Currently we only have intrinsics support for methods from Vector128 on this platform. We need AVX support on x64 first.

[jkurdek]

I think we can close this as won't fix. @kotlarmilos ?

[matouskozak]

The regression is no longer present. We can close it.