[Perf] Linux/arm64: 1 Regression on 6/16/2026 2:04:12 PM +00:00

### Run Information

Name | Value
-- | --
Architecture | arm64
OS | azurelinux 3.0
Queue | CobaltAzureLinux
Baseline | [3d40d73dd958fb9748f8f343c8081f47c2d7191f](https://github.com/dotnet/runtime/commit/3d40d73dd958fb9748f8f343c8081f47c2d7191f)
Compare | [581acb2f5497286af1c2554d68c04312591160ab](https://github.com/dotnet/runtime/commit/581acb2f5497286af1c2554d68c04312591160ab)
Diff | [Diff](https://github.com/dotnet/runtime/compare/3d40d73dd958fb9748f8f343c8081f47c2d7191f...581acb2f5497286af1c2554d68c04312591160ab)
Configs | CompilationMode:tiered, R2RType:r2r_interpreter, RunKind:micro

### Regressions in System.Linq.Tests.Perf_Enumerable

Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio
-- | -- | -- | -- | -- | -- | -- | -- | --
|

• [WhereFirst_LastElementMatches - Duration of single invocation]()
• 📝 - [Benchmark Source]()
• [ADX - Test Multi Config Graph]()

![graph]()
[Test Report]()

### Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md

```cmd
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Linq.Tests.Perf_Enumerable*'
```

### System.Linq.Tests.Perf_Enumerable.WhereFirst_LastElementMatches(input: Array)

#### ETL Files

#### Histogram

#### JIT Disasms

### Docs

[Profiling workflow for dotnet/runtime repository](https://github.com/dotnet/performance/blob/master/docs/profiling-workflow-dotnet-runtime.md)
[Benchmarking workflow for dotnet/runtime repository](https://github.com/dotnet/performance/blob/master/docs/benchmarking-workflow-dotnet-runtime.md)

Start with the linked commit comparison and the System.Linq.Tests.Perf_Enumerable benchmark source at src/benchmarks/micro/libraries/System.Linq/Perf.Enumerable.cs. Reproduce with benchmarks_ci.py using the supplied filter, then investigate the WhereFirst_LastElementMatches regression on arm64. Done means identifying and addressing the regression and confirming the benchmark no longer shows the reported slowdown.

Written by the indexing model from the issue text.