[Perf] Linux/arm64: 1 Regression on 6/25/2026 12:43:10 AM +00:00

### Run Information

Name | Value
-- | --
Architecture | arm64
OS | azurelinux 3.0
Queue | CobaltAzureLinux
Baseline | [9c1fdaea7e4595785db31a5a219f66fb7d2a4ec1](https://github.com/dotnet/runtime/commit/9c1fdaea7e4595785db31a5a219f66fb7d2a4ec1)
Compare | [818cfd5edcda78ac3eb201af392fd301ab9ad46b](https://github.com/dotnet/runtime/commit/818cfd5edcda78ac3eb201af392fd301ab9ad46b)
Diff | [Diff](https://github.com/dotnet/runtime/compare/9c1fdaea7e4595785db31a5a219f66fb7d2a4ec1...818cfd5edcda78ac3eb201af392fd301ab9ad46b)
Configs | CompilationMode:tiered, R2RType:r2r_interpreter, RunKind:micro

### Regressions in PerfLabTests.CastingPerf

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

• [CheckIsInstAnyIsInterfaceNo - 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 'PerfLabTests.CastingPerf*'
```

### PerfLabTests.CastingPerf.CheckIsInstAnyIsInterfaceNo

#### 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 performance/src/benchmarks/micro/runtime/perflab/CastingPerf.cs#L345-L352 and compare the baseline and test commits listed in the report. Run benchmarks_ci.py with the provided CastingPerf filter, then use the linked test report and profiling workflow to investigate the arm64 AzureLinux regression; done means the benchmark no longer regresses and the result is verified.

Written by the indexing model from the issue text.