[Perf] Linux/arm64: 4 Regressions on 7/14/2026 2:58:00 AM +00:00

### Run Information

Name | Value
-- | --
Architecture | arm64
OS | azurelinux 3.0
Queue | CobaltAzureLinux
Baseline | [8a5301832157c4740b8c85ee25086762b29af531](https://github.com/dotnet/runtime/commit/8a5301832157c4740b8c85ee25086762b29af531)
Compare | [1baa904ac12c971494469fc724fb3b9f7126716d](https://github.com/dotnet/runtime/commit/1baa904ac12c971494469fc724fb3b9f7126716d)
Diff | [Diff](https://github.com/dotnet/runtime/compare/8a5301832157c4740b8c85ee25086762b29af531...1baa904ac12c971494469fc724fb3b9f7126716d)
Configs | CompilationMode:tiered, R2RType:r2r_interpreter, RunKind:micro

### Regressions in System.Buffers.Tests.RentReturnArrayPoolTests<Object>

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

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

| 3.12 μs | 7.46 μs | 2.39 | 0.57 | False | | |
|

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

| 3.20 μs | 5.19 μs | 1.62 | 0.63 | False | | |
|

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

| 1.81 μs | 2.42 μs | 1.34 | 0.24 | False | | |
|

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

| 2.59 μs | 2.96 μs | 1.14 | 0.24 | 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.Buffers.Tests.RentReturnArrayPoolTests*'
```

### System.Buffers.Tests.RentReturnArrayPoolTests<Object>.ProducerConsumer(RentalSize: 4096, ManipulateArray: True, Async: True, UseSharedPool: True)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Buffers.Tests.RentReturnArrayPoolTests<Object>.MultipleSerial(RentalSize: 4096, ManipulateArray: False, Async: True, UseSharedPool: True)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Buffers.Tests.RentReturnArrayPoolTests<Object>.MultipleSerial(RentalSize: 4096, ManipulateArray: False, Async: True, UseSharedPool: False)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Buffers.Tests.RentReturnArrayPoolTests<Object>.ProducerConsumer(RentalSize: 4096, ManipulateArray: True, Async: True, UseSharedPool: False)

#### 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.Buffers.Tests.RentReturnArrayPoolTests benchmarks in dotnet/performance/src/benchmarks/micro/libraries/System.Buffers/ArrayPoolTests.cs, especially the cited MultipleSerial and ProducerConsumer ranges. Run the provided benchmarks_ci.py command on Linux/arm64 and compare the baseline and test commits; done means identifying and addressing the cause of the four reported regressions, with the benchmark results no longer regressed.

Written by the indexing model from the issue text.