Skip to content

[Perf] Linux/arm64: 17 Regressions on 5/21/2024 3:15:28 PM #34815

@performanceautofiler

Description

@performanceautofiler

Run Information

Name Value
Architecture arm64
OS ubuntu 22.04
Queue AmpereUbuntu
Baseline 24562bcabefaea5e03c74d01e4df8fc7c112a13a
Compare 7d8d6acb59b23ba0b0b6e5d7213e797b6b514d66
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

Regressions in System.Tests.Perf_String

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
64.33 ns 68.03 ns 1.06 0.00 False
21.42 ns 27.70 ns 1.29 0.22 False
21.08 ns 29.54 ns 1.40 0.19 False
26.64 ns 34.29 ns 1.29 0.19 False
25.58 ns 31.20 ns 1.22 0.21 False
42.21 ns 52.15 ns 1.24 0.04 False
21.56 ns 28.74 ns 1.33 0.28 False
21.13 ns 27.33 ns 1.29 0.20 False
26.44 ns 31.06 ns 1.17 0.17 False
49.03 ns 56.63 ns 1.16 0.02 False
44.00 ns 50.87 ns 1.16 0.01 False
26.90 ns 31.19 ns 1.16 0.14 False
287.11 ns 307.98 ns 1.07 0.09 False

graph
graph
graph
graph
graph
graph
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

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Tests.Perf_String*'
Details

System.Tests.Perf_String.Replace_String(text: "This is a very nice sentence", oldValue: "nice", newValue: "bad")

ETL Files

Histogram

JIT Disasms

System.Tests.Perf_String.ToLowerInvariant(s: "TEST")

ETL Files

Histogram

JIT Disasms

System.Tests.Perf_String.ToLowerInvariant(s: "TeSt")

ETL Files

Histogram

JIT Disasms

System.Tests.Perf_String.ToLower(s: "TEST")

ETL Files

Histogram

JIT Disasms

System.Tests.Perf_String.ToLower(s: "TeSt")

ETL Files

Histogram

JIT Disasms

System.Tests.Perf_String.ToUpperInvariant(s: "This is a much longer piece of text that might benefit more from vectorization.")

ETL Files

Histogram

JIT Disasms

System.Tests.Perf_String.ToUpperInvariant(s: "TeSt")

ETL Files

Histogram

JIT Disasms

System.Tests.Perf_String.ToUpperInvariant(s: "test")

ETL Files

Histogram

JIT Disasms

System.Tests.Perf_String.ToUpper(s: "TeSt")

ETL Files

Histogram

JIT Disasms

System.Tests.Perf_String.ToUpper(s: "This is a much longer piece of text that might benefit more from vectorization.")

ETL Files

Histogram

JIT Disasms

System.Tests.Perf_String.ToLowerInvariant(s: "This is a much longer piece of text that might benefit more from vectorization.")

ETL Files

Histogram

JIT Disasms

System.Tests.Perf_String.ToUpper(s: "test")

ETL Files

Histogram

JIT Disasms

System.Tests.Perf_String.Join_Enumerable

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 ubuntu 22.04
Queue AmpereUbuntu
Baseline 24562bcabefaea5e03c74d01e4df8fc7c112a13a
Compare 7d8d6acb59b23ba0b0b6e5d7213e797b6b514d66
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

Regressions in System.IO.Hashing.Tests.Crc32_AppendPerf

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
515.04 ns 1.59 μs 3.09 0.00 False
21.82 ns 34.17 ns 1.57 0.03 False

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
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.IO.Hashing.Tests.Crc32_AppendPerf*'
Details

System.IO.Hashing.Tests.Crc32_AppendPerf.Append(BufferSize: 10240)

ETL Files

Histogram

JIT Disasms

System.IO.Hashing.Tests.Crc32_AppendPerf.Append(BufferSize: 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 ubuntu 22.04
Queue AmpereUbuntu
Baseline 24562bcabefaea5e03c74d01e4df8fc7c112a13a
Compare 7d8d6acb59b23ba0b0b6e5d7213e797b6b514d66
Diff Diff
Configs CompilationMode:tiered, RunKind:micro

Regressions in System.Linq.Tests.Perf_Enumerable

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
206.19 ns 289.52 ns 1.40 0.16 False
714.21 ns 878.42 ns 1.23 0.01 True

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
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Linq.Tests.Perf_Enumerable*'
Details

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

ETL Files

Histogram

JIT Disasms

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

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