[Perf] Linux/x64: 7 Regressions on 5/20/2024 11:59:52 PM

[performanceautofiler]

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	5f067ce8b50087e032d13a1b97ae5ec39fc54739
Compare	cbe4d849731509800204c52ab3d8dab560a69e74
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Numerics.Tensors.Tests.Perf_FloatingPointTensorPrimitives<Double>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
CosineSimilarity - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	1.39 μs	6.95 μs	4.99	0.02	True
CosineSimilarity - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	77.16 ns	278.59 ns	3.61	0.19	True
Sin - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	256.95 μs	282.21 μs	1.10	0.16	False

Test Report

Repro

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

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Numerics.Tensors.Tests.Perf_FloatingPointTensorPrimitives<Double>*'

System.Numerics.Tensors.Tests.Perf_FloatingPointTensorPrimitives<Double>.CosineSimilarity(BufferLength: 3079)

ETL Files

Histogram

JIT Disasms

System.Numerics.Tensors.Tests.Perf_FloatingPointTensorPrimitives<Double>.CosineSimilarity(BufferLength: 128)

ETL Files

Histogram

JIT Disasms

System.Numerics.Tensors.Tests.Perf_FloatingPointTensorPrimitives<Double>.Sin(BufferLength: 3079)

ETL Files

Histogram

JIT Disasms

Docs

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

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	5f067ce8b50087e032d13a1b97ae5ec39fc54739
Compare	cbe4d849731509800204c52ab3d8dab560a69e74
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Numerics.Tensors.Tests.Perf_FloatingPointTensorPrimitives<Single>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
FusedMultiplyAdd_ScalarMultiplier - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	13.08 μs	16.32 μs	1.25	0.14	False
FusedMultiplyAdd_ScalarAddend - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	13.54 μs	15.26 μs	1.13	0.18	False
Sin - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	126.92 μs	141.95 μs	1.12	0.19	False
CosineSimilarity - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	45.56 ns	259.29 ns	5.69	0.39	True

Test Report

Repro

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

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Numerics.Tensors.Tests.Perf_FloatingPointTensorPrimitives<Single>*'

System.Numerics.Tensors.Tests.Perf_FloatingPointTensorPrimitives<Single>.FusedMultiplyAdd_ScalarMultiplier(BufferLength: 3079)

ETL Files

Histogram

JIT Disasms

System.Numerics.Tensors.Tests.Perf_FloatingPointTensorPrimitives<Single>.FusedMultiplyAdd_ScalarAddend(BufferLength: 3079)

ETL Files

Histogram

JIT Disasms

System.Numerics.Tensors.Tests.Perf_FloatingPointTensorPrimitives<Single>.Sin(BufferLength: 3079)

ETL Files

Histogram

JIT Disasms

System.Numerics.Tensors.Tests.Perf_FloatingPointTensorPrimitives<Single>.CosineSimilarity(BufferLength: 128)

ETL Files

Histogram

JIT Disasms

Docs

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

[radekdoulik]

looks like dotnet/runtime#102188