[Perf] Linux/x64: 9 Improvements on 7/12/2024 11:27:13 PM

[performanceautofiler]

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	b8ac8b2d7f79aec93f9cad722f3cc4ccb931b826
Compare	ac0eeb015a0266adb06696bb58c21e5bfe6d9b56
Diff	Diff
Configs	CompilationMode:wasm, RunKind:micro

Improvements in System.Tests.Perf_Random

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
Next - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	101.69 ns	74.36 ns	0.73	0.32	False
Next_unseeded - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	75.25 ns	55.75 ns	0.74	0.43	False
NextSingle_unseeded - Duration of single invocation ADX - Test Multi Config Graph	74.44 ns	55.93 ns	0.75	0.39	False
NextDouble_unseeded - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	79.83 ns	61.89 ns	0.78	0.40	False
NextSingle - Duration of single invocation ADX - Test Multi Config Graph	107.09 ns	82.69 ns	0.77	0.36	False
NextDouble - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	99.58 ns	77.30 ns	0.78	0.32	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.Tests.Perf_Random*'

System.Tests.Perf_Random.Next

ETL Files

Histogram

JIT Disasms

System.Tests.Perf_Random.Next_unseeded

ETL Files

Histogram

JIT Disasms

System.Tests.Perf_Random.NextSingle_unseeded

ETL Files

Histogram

JIT Disasms

System.Tests.Perf_Random.NextDouble_unseeded

ETL Files

Histogram

JIT Disasms

System.Tests.Perf_Random.NextSingle

ETL Files

Histogram

JIT Disasms

System.Tests.Perf_Random.NextDouble

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	b8ac8b2d7f79aec93f9cad722f3cc4ccb931b826
Compare	ac0eeb015a0266adb06696bb58c21e5bfe6d9b56
Diff	Diff
Configs	CompilationMode:wasm, RunKind:micro

Improvements in PerfLabTests.CastingPerf

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
CheckArrayIsVariantGenericInterfaceReflection - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	452.90 ns	368.81 ns	0.81	0.07	True
CheckListIsVariantGenericInterface - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	175.93 ns	56.83 ns	0.32	0.10	True
AssignArrayElementByVariance - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	178.98 ns	67.11 ns	0.37	0.12	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 'PerfLabTests.CastingPerf*'

PerfLabTests.CastingPerf.CheckArrayIsVariantGenericInterfaceReflection

ETL Files

Histogram

JIT Disasms

PerfLabTests.CastingPerf.CheckListIsVariantGenericInterface

ETL Files

Histogram

JIT Disasms

PerfLabTests.CastingPerf.AssignArrayElementByVariance

ETL Files

Histogram

JIT Disasms

Docs

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

[lewing]

the casting perf improvements are from dotnet/runtime#103757 the others appear to be noise