KEMBAR78
[Perf] Windows/arm64: 5 Regressions on 6/4/2024 6:36:34 PM · Issue #36251 · dotnet/perf-autofiling-issues · GitHub
Skip to content

[Perf] Windows/arm64: 5 Regressions on 6/4/2024 6:36:34 PM #36251

@performanceautofiler

Description

@performanceautofiler

Run Information

Name Value
Architecture arm64
OS Windows 10.0.22621
Queue AmpereWindows
Baseline 59e8bbcf83b664c3de6cfa553d9bbfad76578765
Compare 454d6e929d7caa30618358eae8106e5f4b46ed10
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

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

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
175.47 ns 265.36 ns 1.51 0.71 False
47.97 ns 100.88 ns 2.10 0.76 True
76.39 ns 80.80 ns 1.06 0.78 False
65.71 ns 118.08 ns 1.80 0.73 False

graph
graph
graph
graph
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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Numerics.Tensors.Tests.Perf_NumberTensorPrimitives&lt;Double&gt;*'

System.Numerics.Tensors.Tests.Perf_NumberTensorPrimitives<Double>.MaxMagnitude_Scalar(BufferLength: 128)

ETL Files

Histogram

JIT Disasms

System.Numerics.Tensors.Tests.Perf_NumberTensorPrimitives<Double>.Max_Scalar(BufferLength: 128)

ETL Files

Histogram

JIT Disasms

System.Numerics.Tensors.Tests.Perf_NumberTensorPrimitives<Double>.AddMultiply_ScalarMultiplier(BufferLength: 128)

ETL Files

Histogram

JIT Disasms

System.Numerics.Tensors.Tests.Perf_NumberTensorPrimitives<Double>.Max_Vector(BufferLength: 128)

ETL Files

Histogram

JIT Disasms

Docs

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


Run Information

Name Value
Architecture arm64
OS Windows 10.0.22621
Queue AmpereWindows
Baseline 59e8bbcf83b664c3de6cfa553d9bbfad76578765
Compare 454d6e929d7caa30618358eae8106e5f4b46ed10
Diff Diff
Configs CompilationMode:tiered, 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
71.53 ns 87.81 ns 1.23 0.74 False

graph
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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Numerics.Tensors.Tests.Perf_FloatingPointTensorPrimitives&lt;Double&gt;*'

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

ETL Files

Histogram

JIT Disasms

Docs

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

Metadata

Metadata

Assignees

No one assigned

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions