[Perf] Linux/x64: 1 Regression on 9/2/2026 5:37:42 AM +00:00

### Run Information

Name | Value
-- | --
Architecture | x64
OS | ubuntu 22.04
Queue | ViperUbuntu
Baseline | [f00a5ba2dde9f648bcd9ac77411d1a8596449303](https://github.com/dotnet/runtime/commit/f00a5ba2dde9f648bcd9ac77411d1a8596449303)
Compare | [696fda84063459254633ad07bf8ce1e6977c9ad5](https://github.com/dotnet/runtime/commit/696fda84063459254633ad07bf8ce1e6977c9ad5)
Diff | [Diff](https://github.com/dotnet/runtime/compare/f00a5ba2dde9f648bcd9ac77411d1a8596449303...696fda84063459254633ad07bf8ce1e6977c9ad5)
Configs | CompilationMode:wasm, RunKind:micro

### Regressions in System.Memory.MemoryMarshal<Int32>

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

• [CastToByte - 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
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Memory.MemoryMarshal*'
```

### System.Memory.MemoryMarshal<Int32>.CastToByte

#### 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 by running the documented benchmarks_ci.py command with the System.Memory.MemoryMarshal filter from the dotnet/performance repository. Inspect the benchmark source at src/benchmarks/micro/libraries/System.Memory/MemoryMarshal.cs#L35-L36 and compare the listed baseline and test commits. Done means the CastToByte regression is explained and the reported performance issue is resolved or documented.

Written by the indexing model from the issue text.