[Perf] Linux/arm64: 2 Regressions on 8/26/2026 3:50:07 PM +00:00

### Run Information

Name | Value
-- | --
Architecture | arm64
OS | azurelinux 3.0
Queue | CobaltAzureLinux
Baseline | [9f18a550aaa91ecd032ac024b67e03559df9e766](https://github.com/dotnet/runtime/commit/9f18a550aaa91ecd032ac024b67e03559df9e766)
Compare | [7c217acdb9e9fd656a8eba55eb99e52b00300fd3](https://github.com/dotnet/runtime/commit/7c217acdb9e9fd656a8eba55eb99e52b00300fd3)
Diff | [Diff](https://github.com/dotnet/runtime/compare/9f18a550aaa91ecd032ac024b67e03559df9e766...7c217acdb9e9fd656a8eba55eb99e52b00300fd3)
Configs | CompilationMode:tiered, RunKind:micro

### Regressions in System.Tests.Perf_Version

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

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

| 42.37 ns | 75.85 ns | 1.79 | 0.21 | False | | |
|

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

| 46.86 ns | 55.50 ns | 1.18 | 0.21 | False | | |

![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_Version*'
```

### System.Tests.Perf_Version.ToStringL

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Version.TryFormatL

#### 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 in src/benchmarks/micro/libraries/System.Runtime/Perf.Version.cs at lines 60-61 and 75-76, then run the documented benchmarks_ci.py command for System.Tests.Perf_Version. Compare the ARM64 AzureLinux results with the linked baseline and report to determine the cause of the ToStringL and TryFormatL regressions. Done means the regression is explained and addressed or clearly triaged.

Written by the indexing model from the issue text.