[Perf] Linux/x64: 1 Regression on 11/2/2023 10:42:26 AM

[performanceautofiler]

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	7580471ec925bd0d367e0b8c45d7f2b04bb3c25b
Compare	98b754659af74cc34ffd17c5b777f1ba7b307789
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Collections.IndexerSetReverse<Int32>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
IList - Duration of single invocation 📝 - Benchmark Source 📈 - ADX Test Multi Config Graph	5.88 μs	7.77 μs	1.32	0.37	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.Collections.IndexerSetReverse<Int32>*'

Payloads

Baseline
Compare

System.Collections.IndexerSetReverse<Int32>.IList(Size: 512)

ETL Files

Histogram

JIT Disasms

Docs

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

[radekdoulik]

looks like dotnet/runtime#92534. could that be the changes in the src/libraries/System.Collections.NonGeneric/src/System/Collections/SortedList.cs

@eiriktsarpalis could you take a look?

[eiriktsarpalis]

I don't think dotnet/runtime#92534 is related, the benchmark is testing List<T> indexers which weren't changed by that PR.