[Perf] Linux/x64: 11 Improvements on 4/22/2025 7:20:48 PM +00:00

[performanceautofiler]

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	ViperUbuntu
Baseline	aec77dd2f0bb9f57acf94c86077e8fb39583637e
Compare	31289efa35151a4e60dcd2e6471c51f620f78c28
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Improvements in Exceptions.Handling

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
MultipleNestedTryFinally - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	1.89 μs	1.79 μs	0.95	0.03	False
ThrowAndCatchDeep - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	12.39 μs	11.05 μs	0.89	0.03	False
ThrowAndCatchDeep - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	5.02 μs	4.55 μs	0.91	0.11	False
ThrowAndCatchDeep - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	8.91 μs	7.49 μs	0.84	0.06	False
ThrowAndCatch_ManyCatchBlocks - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	1.95 μs	1.84 μs	0.94	0.04	False
ThrowAndCatchDeepRecursive - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	8.82 μs	7.91 μs	0.90	0.03	False
ThrowAndCatch - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	1.69 μs	1.59 μs	0.94	0.04	False
ThrowAndCatchWhen - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	1.75 μs	1.65 μs	0.94	0.03	False
ThrowAndCatchDeepRecursive - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	8.64 μs	7.37 μs	0.85	0.05	False
ThrowAndCatchDeepRecursive - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	12.56 μs	10.90 μs	0.87	0.03	False
ThrowAndCatchDeepRecursive - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	4.98 μs	4.29 μs	0.86	0.13	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 'Exceptions.Handling*'

Exceptions.Handling.MultipleNestedTryFinally(kind: Software)

ETL Files

Histogram

JIT Disasms

Exceptions.Handling.ThrowAndCatchDeep(kind: ReflectionHardware)

ETL Files

Histogram

JIT Disasms

Exceptions.Handling.ThrowAndCatchDeep(kind: Software)

ETL Files

Histogram

JIT Disasms

Exceptions.Handling.ThrowAndCatchDeep(kind: ReflectionSoftware)

ETL Files

Histogram

JIT Disasms

Exceptions.Handling.ThrowAndCatch_ManyCatchBlocks(kind: Software)

ETL Files

Histogram

JIT Disasms

Exceptions.Handling.ThrowAndCatchDeepRecursive(kind: Hardware)

ETL Files

Histogram

JIT Disasms

Exceptions.Handling.ThrowAndCatch(kind: Software)

ETL Files

Histogram

JIT Disasms

Exceptions.Handling.ThrowAndCatchWhen(kind: Software)

ETL Files

Histogram

JIT Disasms

Exceptions.Handling.ThrowAndCatchDeepRecursive(kind: ReflectionSoftware)

ETL Files

Histogram

JIT Disasms

Exceptions.Handling.ThrowAndCatchDeepRecursive(kind: ReflectionHardware)

ETL Files

Histogram

JIT Disasms

Exceptions.Handling.ThrowAndCatchDeepRecursive(kind: Software)

ETL Files

Histogram

JIT Disasms

Docs

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

[AndyAyersMS]

dotnet/runtime#114582