[Perf] Linux/arm64: 1 Improvement on 8/2/2026 11:04:49 PM +00:00

### Run Information

Name | Value
-- | --
Architecture | arm64
OS | azurelinux 3.0
Queue | CobaltAzureLinux
Baseline | [a2f953fe266dc72602436e77614a9e10f60a7128](https://github.com/dotnet/runtime/commit/a2f953fe266dc72602436e77614a9e10f60a7128)
Compare | [abcd6eb3137ac133ef7f73eae95e7928160386c9](https://github.com/dotnet/runtime/commit/abcd6eb3137ac133ef7f73eae95e7928160386c9)
Diff | [Diff](https://github.com/dotnet/runtime/compare/a2f953fe266dc72602436e77614a9e10f60a7128...abcd6eb3137ac133ef7f73eae95e7928160386c9)
Configs | CompilationMode:tiered, RunKind:micro

### Improvements in System.Tests.Perf_Random

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

• [NextSingle - Duration of single invocation]()
• [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.Tests.Perf_Random*'
```

### System.Tests.Perf_Random.NextSingle

#### 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 System.Tests.Perf_Random.NextSingle benchmark and the linked performance report, then follow the benchmarking workflow in docs/benchmarking-workflow-dotnet-runtime.md. Run the provided benchmarks_ci.py command for System.Tests.Perf_Random and compare the arm64 Azure Linux result; completion would require identifying and implementing a justified performance improvement, then confirming it with the benchmark.

Written by the indexing model from the issue text.