[Perf] Linux/arm64: 1 Regression in System.Tests.Perf_Int128

[performanceautofiler]

Run Information

Name	Value
Architecture	arm64
OS	ubuntu 22.04
Queue	AmpereUbuntu
Baseline	9882188fbe16adee3538b65a3926465dfd6052c1
Compare	6c553628dfaec02e665a4ade3deabe3a91281024
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Tests.Perf_Int128

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
TryFormat - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	133.94 ns	150.39 ns	1.12	0.04	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_Int128*'

Details

System.Tests.Perf_Int128.TryFormat(value: 170141183460469231731687303715884105727)

ETL Files

Histogram

JIT Disasms

Docs

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

[LoopedBard3]

Likely caused by #104506.

[LoopedBard3]

@matouskozak @tannergooding FYI

[EgorBo]

I think we should just revert that change then since there were no improvemens from it, only regressions

[stephentoub]

Do we know why it regressed?

[EgorBo]

I bet it has something to do with struct promotion, it's nice to see safe code to be faster than unnecessary unsafe

@EgorBot -arm64 -perf -commit 8d231b4 vs 01dbf51 --disasm

using BenchmarkDotNet.Attributes;

public class Perf_Int128
{
    private char[] _destination = new char[Int128.MinValue.ToString().Length];

    public static IEnumerable<object> StringValues => Values.Select(value => value.ToString()).ToArray();

    public static IEnumerable<object> Values => [Int128.MaxValue];

    [Benchmark]
    [ArgumentsSource(nameof(Values))]
    public bool TryFormat(Int128 value) => value.TryFormat(new Span<char>(_destination), out _);
}