[Perf] Linux/arm64: 3 Improvements on 6/12/2026 2:03:56 AM +00:00

### Run Information

Name | Value
-- | --
Architecture | arm64
OS | azurelinux 3.0
Queue | CobaltAzureLinux
Baseline | [e563422012f994091f0f1d52deeed8c6273edecb](https://github.com/dotnet/runtime/commit/e563422012f994091f0f1d52deeed8c6273edecb)
Compare | [4c74f6ac0db2db2326798751e773f8c0c2a7aac9](https://github.com/dotnet/runtime/commit/4c74f6ac0db2db2326798751e773f8c0c2a7aac9)
Diff | [Diff](https://github.com/dotnet/runtime/compare/e563422012f994091f0f1d52deeed8c6273edecb...4c74f6ac0db2db2326798751e773f8c0c2a7aac9)
Configs | CompilationMode:tiered, R2RType:r2r_interpreter, RunKind:micro

### Improvements in System.Collections.CopyTo<String>

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

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

| 843.67 ns | 611.02 ns | 0.72 | 0.46 | False | | |
|

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

| 810.05 ns | 641.52 ns | 0.79 | 0.40 | 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.Collections.CopyTo*'
```

### System.Collections.CopyTo<String>.Array(Size: 2048)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Collections.CopyTo<String>.Memory(Size: 2048)

#### 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)

---

### Run Information

Name | Value
-- | --
Architecture | arm64
OS | azurelinux 3.0
Queue | CobaltAzureLinux
Baseline | [e563422012f994091f0f1d52deeed8c6273edecb](https://github.com/dotnet/runtime/commit/e563422012f994091f0f1d52deeed8c6273edecb)
Compare | [4c74f6ac0db2db2326798751e773f8c0c2a7aac9](https://github.com/dotnet/runtime/commit/4c74f6ac0db2db2326798751e773f8c0c2a7aac9)
Diff | [Diff](https://github.com/dotnet/runtime/compare/e563422012f994091f0f1d52deeed8c6273edecb...4c74f6ac0db2db2326798751e773f8c0c2a7aac9)
Configs | CompilationMode:tiered, R2RType:r2r_interpreter, RunKind:micro

### Improvements in Span.IndexerBench

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

• [CoveredIndex1 - Duration of single invocation]()
• 📝 - [Benchmark Source]()
• [ADX - Test Multi Config Graph]()

| 1.34 μs | 1.14 μs | 0.85 | 0.19 | False | | |

![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 'Span.IndexerBench*'
```

### Span.IndexerBench.CoveredIndex1(length: 1024)

#### 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 src/benchmarks/micro/libraries/System.Collections/CopyTo.cs and src/benchmarks/micro/runtime/Span/Indexer.cs, then read the benchmarking workflow linked in the issue. Run the two benchmarks with the provided filters and compare the results with the baseline and test reports. Done means the reported arm64 performance behavior is understood and the necessary runtime or benchmark change is validated by the relevant runs.

Written by the indexing model from the issue text.