[Perf] Linux/arm64: 1 Improvement on 6/10/2026 9:01:08 AM +00:00

### Run Information

Name | Value
-- | --
Architecture | arm64
OS | azurelinux 3.0
Queue | CobaltAzureLinux
Baseline | [65937ca43416615d941a93c9f33ad4b1acfb7b58](https://github.com/dotnet/runtime/commit/65937ca43416615d941a93c9f33ad4b1acfb7b58)
Compare | [25bd04c79542dfaaab5c5cd42670bcfc20b7d57a](https://github.com/dotnet/runtime/commit/25bd04c79542dfaaab5c5cd42670bcfc20b7d57a)
Diff | [Diff](https://github.com/dotnet/runtime/compare/65937ca43416615d941a93c9f33ad4b1acfb7b58...25bd04c79542dfaaab5c5cd42670bcfc20b7d57a)
Configs | CompilationMode:tiered, RunKind:micro

### Improvements in MicroBenchmarks.Serializers.Json_ToStream<IndexViewModel>

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

• [JsonNet_ - Duration of single invocation]()
• 📝 - [Benchmark Source]()
• [ADX - Test Multi Config 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 'MicroBenchmarks.Serializers.Json_ToStream*'
```

### MicroBenchmarks.Serializers.Json_ToStream<IndexViewModel>.JsonNet_

#### 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 source, src/benchmarks/micro/Serializers/Json_ToStream.cs, and run the provided benchmarks_ci.py command. Read the benchmarking and profiling workflow docs, then compare the baseline, test report, and available history to understand the ARM64 improvement. Done means the result is triaged with its cause and any follow-up action recorded.

Written by the indexing model from the issue text.