[Perf] Linux/arm64: 6 Improvements on 8/28/2026 6:27:02 PM +00:00

### Run Information

Name | Value
-- | --
Architecture | arm64
OS | azurelinux 3.0
Queue | CobaltAzureLinux
Baseline | [57c9c3fdcbc94ad98f0a4b8abedb7c6eadfb264b](https://github.com/dotnet/runtime/commit/57c9c3fdcbc94ad98f0a4b8abedb7c6eadfb264b)
Compare | [d2ea726dd3d8faad797755c9fbb1ff15226e25f0](https://github.com/dotnet/runtime/commit/d2ea726dd3d8faad797755c9fbb1ff15226e25f0)
Diff | [Diff](https://github.com/dotnet/runtime/compare/57c9c3fdcbc94ad98f0a4b8abedb7c6eadfb264b...d2ea726dd3d8faad797755c9fbb1ff15226e25f0)
Configs | CompilationMode:tiered, R2RType:r2r_interpreter, RunKind:micro

### Improvements in System.IO.Tests.Perf_RandomAccess

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

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

| 4.89 ms | 2.02 ms | 0.41 | 0.63 | False | | |
|

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

| 92.86 ms | 53.26 ms | 0.57 | 0.74 | False | | |
|

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

| 3.11 ms | 2.01 ms | 0.65 | 0.62 | False | | |
|

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

| 102.79 ms | 66.95 ms | 0.65 | 0.68 | False | | |

![graph]()
![graph]()
![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.IO.Tests.Perf_RandomAccess*'
```

### System.IO.Tests.Perf_RandomAccess.ReadAsync(fileSize: 1048576, bufferSize: 4096, options: None)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_RandomAccess.ReadAsync(fileSize: 104857600, bufferSize: 16384, options: None)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_RandomAccess.ReadAsync(fileSize: 1048576, bufferSize: 4096, options: Asynchronous)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.IO.Tests.Perf_RandomAccess.ReadAsync(fileSize: 104857600, bufferSize: 16384, options: Asynchronous)

#### 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 | [57c9c3fdcbc94ad98f0a4b8abedb7c6eadfb264b](https://github.com/dotnet/runtime/commit/57c9c3fdcbc94ad98f0a4b8abedb7c6eadfb264b)
Compare | [d2ea726dd3d8faad797755c9fbb1ff15226e25f0](https://github.com/dotnet/runtime/commit/d2ea726dd3d8faad797755c9fbb1ff15226e25f0)
Diff | [Diff](https://github.com/dotnet/runtime/compare/57c9c3fdcbc94ad98f0a4b8abedb7c6eadfb264b...d2ea726dd3d8faad797755c9fbb1ff15226e25f0)
Configs | CompilationMode:tiered, R2RType:r2r_interpreter, RunKind:micro

### Improvements in PerfLabTests.CastingPerf

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

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

| 399.63 μs | 337.86 μs | 0.85 | 0.11 | 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 'PerfLabTests.CastingPerf*'
```

### PerfLabTests.CastingPerf.ObjInt

#### 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 | [57c9c3fdcbc94ad98f0a4b8abedb7c6eadfb264b](https://github.com/dotnet/runtime/commit/57c9c3fdcbc94ad98f0a4b8abedb7c6eadfb264b)
Compare | [d2ea726dd3d8faad797755c9fbb1ff15226e25f0](https://github.com/dotnet/runtime/commit/d2ea726dd3d8faad797755c9fbb1ff15226e25f0)
Diff | [Diff](https://github.com/dotnet/runtime/compare/57c9c3fdcbc94ad98f0a4b8abedb7c6eadfb264b...d2ea726dd3d8faad797755c9fbb1ff15226e25f0)
Configs | CompilationMode:tiered, R2RType:r2r_interpreter, RunKind:micro

### Improvements in PerfLabTests.LowLevelPerf

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

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

| 238.62 μs | 190.88 μs | 0.80 | 0.14 | 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 'PerfLabTests.LowLevelPerf*'
```

### PerfLabTests.LowLevelPerf.GenericClassWithSTringGenericInstanceMethod

#### 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 linked benchmark sources, src/benchmarks/micro/libraries/System.IO.FileSystem/Perf.RandomAccess.cs and src/benchmarks/micro/runtime/perflab/CastingPerf.cs, then read the benchmarking workflow documentation. Run the provided benchmarks and compare the reported ARM64 results with the baseline. Done means determining whether the improvements need runtime follow-up or can be closed as expected performance data.

Written by the indexing model from the issue text.