[Perf] Linux/arm64: 1 Regression on 6/25/2024 5:29:23 PM

[performanceautofiler]

Run Information

Name	Value
Architecture	arm64
OS	ubuntu 22.04
Queue	AmpereUbuntu
Baseline	a54d9e9b991c9059f85150f2e69b6507f103b322
Compare	b8b3bf2ff50c5b63cc27db0b250ac29d5a40c5ad
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Net.Primitives.Tests.CredentialCacheTests

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
GetCredential_Uri - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	334.76 ns	405.38 ns	1.21	0.02	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.Net.Primitives.Tests.CredentialCacheTests*'

System.Net.Primitives.Tests.CredentialCacheTests.GetCredential_Uri(uriString: "http://notfound", uriCount: 10)

ETL Files

Histogram

JIT Disasms

Docs

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

[DrewScoggins]

The change to fix the previous regression seems to have caused a new one here. Also the second test in this issue did not seem to fully come back from this fix, #102281.

Change - #103714

[stephentoub]

cc: @rzikm

[matouskozak]

Related Mono arm64 AOT-llvm regression: #104302
CoreCLR Windows x64 - dotnet/perf-autofiling-issues#37375, dotnet/perf-autofiling-issues#37366
CoreCLR Linux x64 - dotnet/perf-autofiling-issues#37352