[Perf] Linux/arm64: 2 Regressions on 7/5/2026 2:44:21 PM +00:00

### Run Information

Name | Value
-- | --
Architecture | arm64
OS | azurelinux 3.0
Queue | CobaltAzureLinux
Baseline | [986fba00d9f89d2dfb8ac440bf37727a18828f64](https://github.com/dotnet/runtime/commit/986fba00d9f89d2dfb8ac440bf37727a18828f64)
Compare | [8f365c934088b8ae21a4dfce8073da0d3eb22a54](https://github.com/dotnet/runtime/commit/8f365c934088b8ae21a4dfce8073da0d3eb22a54)
Diff | [Diff](https://github.com/dotnet/runtime/compare/986fba00d9f89d2dfb8ac440bf37727a18828f64...8f365c934088b8ae21a4dfce8073da0d3eb22a54)
Configs | CompilationMode:tiered, R2RType:r2r_interpreter, RunKind:micro

### Regressions in System.Tests.Perf_String

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

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

| 33.92 ns | 38.75 ns | 1.14 | 0.10 | False | | |
|

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

| 34.07 ns | 38.78 ns | 1.14 | 0.11 | 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_String*'
```

### System.Tests.Perf_String.Split(s: "ABCDEFGHIJKLMNOPQRSTUVWXYZ", arr: [' '], options: None)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_String.Split(s: "ABCDEFGHIJKLMNOPQRSTUVWXYZ", arr: [' '], options: RemoveEmptyEntries)

#### 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.Runtime/Perf.String.cs lines 114-121 and reproduce System.Tests.Perf_String with scripts/benchmarks_ci.py using the documented workflow. Compare the baseline and test commits and inspect the supplied performance report to identify the cause of the ARM64 AzureLinux regression. Done means the regression is explained and a validated resolution restores the affected Split benchmarks.

Written by the indexing model from the issue text.