[Perf] Windows/x86: 1 Regression on 8/10/2026 9:35:23 AM +00:00

### Run Information

Name | Value
-- | --
Architecture | x86
OS | Windows 10.0.22631
Queue | ViperWindows
Baseline | [14b601ec5edfeecbc70368890e8676fe5c29da83](https://github.com/dotnet/runtime/commit/14b601ec5edfeecbc70368890e8676fe5c29da83)
Compare | [1e4f4bc96e9a45eeba82a5d358d1779795bfbcb1](https://github.com/dotnet/runtime/commit/1e4f4bc96e9a45eeba82a5d358d1779795bfbcb1)
Diff | [Diff](https://github.com/dotnet/runtime/compare/14b601ec5edfeecbc70368890e8676fe5c29da83...1e4f4bc96e9a45eeba82a5d358d1779795bfbcb1)
Configs | CompilationMode:tiered, RunKind:micro

### Regressions in System.Collections.CopyTo<Int32>

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

• [ImmutableArray - 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.Collections.CopyTo*'
```

### System.Collections.CopyTo<Int32>.ImmutableArray(Size: 2048)

#### 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 benchmark source at src/benchmarks/micro/libraries/System.Collections/CopyTo.cs#L69-L70 and reproduce System.Collections.CopyTo using the provided benchmarks_ci.py command. Compare the baseline and test commits, then follow the profiling and benchmarking workflow docs to investigate the x86 Windows slowdown. Done means the regression is explained and addressed, with the benchmark confirming the result.

Written by the indexing model from the issue text.