[Perf] Linux/x64: 8 Regressions on 5/4/2024 5:29:12 AM

[performanceautofiler]

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	7ac5ef959579da0202e6ad618924dfc8fe129e89
Compare	deb7c1707c00dd14bd9cd179c976ccfc1e70544d
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Regressions in System.Memory.Span<Int32>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
StartsWith - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	1.72 ns	3.22 ns	1.88	0.25	False
SequenceEqual - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	0.93 ns	3.29 ns	3.53	0.20	False
StartsWith - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	1.14 ns	2.31 ns	2.02	0.14	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.Memory.Span<Int32>*'

System.Memory.Span<Int32>.StartsWith(Size: 33)

ETL Files

Histogram

JIT Disasms

System.Memory.Span<Int32>.SequenceEqual(Size: 4)

ETL Files

Histogram

JIT Disasms

System.Memory.Span<Int32>.StartsWith(Size: 4)

ETL Files

Histogram

JIT Disasms

Docs

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

[DrewScoggins]

Looks like #101834

[DrewScoggins]

Improvements: dotnet/perf-autofiling-issues#33897

[AndyAyersMS]

Will revisit once we enable the new layout. Also curious to see the ARM64 results.

[dotnet-policy-service]

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

[AndyAyersMS]

These have all since improved, though it's not clear which commit(s) are responsible. Implicated range is 1be664e...29cb8a6