[Perf] Linux/x64: Span.IndexerBench Regression + Related Issues on 2/6/2025 4:29:54 PM +00:00

[performanceautofiler]

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	ViperUbuntu
Baseline	adb2af26bb6bb19312c38cacda2694b981b56c6d
Compare	9c2bfb9ab73961d149ea263c7a78606bfb4bc0b4
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in Span.IndexerBench

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
CoveredIndex3 - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	713.95 ns	845.70 ns	1.18	0.03	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 'Span.IndexerBench*'

Span.IndexerBench.CoveredIndex3(length: 1024)

ETL Files

Histogram

JIT Disasms

Docs

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

[LoopedBard3]

Likely caused by #112197 in commit range: 666bb9d...16782a4. FYI @amanasifkhalid

Related Regressions:

• [Perf] Linux/x64: 5 Regressions on 2/6/2025 4:29:54 PM +00:00 perf-autofiling-issues#49898

[dotnet-policy-service]

Tagging subscribers to this area: @JulieLeeMSFT, @jakobbotsch
See info in area-owners.md if you want to be subscribed.

[amanasifkhalid]

The Span.IndexerBench regression improved, and then later regressed again (probably due to #113896). This should be tracked in a newer issue.

Some of the Perf_128 regressions in dotnet/perf-autofiling-issues#49898 improved from #111915, while others regressed further. Since those regressions are on an Intel config with the JCC erratum, I'm not weighting them as heavily. Similarly, the remaining regressions should be tracked in a newer issue.