[Perf] Linux/arm64: 8 Regressions on 7/6/2026 12:45:47 PM +00:00

### Run Information

Name | Value
-- | --
Architecture | arm64
OS | azurelinux 3.0
Queue | CobaltAzureLinux
Baseline | [ff279bafa8ca2fbf920b605868e9b0a2c0497034](https://github.com/dotnet/runtime/commit/ff279bafa8ca2fbf920b605868e9b0a2c0497034)
Compare | [d720474264849c4dafe6e28dc5bd679b4ddbe5fe](https://github.com/dotnet/runtime/commit/d720474264849c4dafe6e28dc5bd679b4ddbe5fe)
Diff | [Diff](https://github.com/dotnet/runtime/compare/ff279bafa8ca2fbf920b605868e9b0a2c0497034...d720474264849c4dafe6e28dc5bd679b4ddbe5fe)
Configs | CompilationMode:tiered, R2RType:r2r_interpreter, RunKind:micro

### Regressions in System.Numerics.Tests.Perf_Matrix4x4

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

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

| 53.91 ns | 2256.44 ns | 41.86 | 0.06 | False | | |
|

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

| 3.50 ns | 15.12 ns | 4.32 | 0.54 | False | | |
|

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

| 3.14 ns | 10.24 ns | 3.26 | 0.54 | False | | |
|

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

| 2.96 ns | 8.62 ns | 2.92 | 0.55 | False | | |
|

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

| 3.18 ns | 7.58 ns | 2.38 | 0.52 | False | | |
|

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

| 25.43 ns | 37.72 ns | 1.48 | 0.43 | False | | |
|

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

| 15.12 ns | 17.40 ns | 1.15 | 0.06 | False | | |

![graph]()
![graph]()
![graph]()
![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.Numerics.Tests.Perf_Matrix4x4*'
```

### System.Numerics.Tests.Perf_Matrix4x4.InvertBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Numerics.Tests.Perf_Matrix4x4.CreateFromQuaternionBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Numerics.Tests.Perf_Matrix4x4.CreatePerspectiveOffCenterBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Numerics.Tests.Perf_Matrix4x4.CreateOrthographicOffCenterBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Numerics.Tests.Perf_Matrix4x4.CreatePerspectiveBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Numerics.Tests.Perf_Matrix4x4.TransformBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Numerics.Tests.Perf_Matrix4x4.CreateBillboardBenchmark

#### 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 | [ff279bafa8ca2fbf920b605868e9b0a2c0497034](https://github.com/dotnet/runtime/commit/ff279bafa8ca2fbf920b605868e9b0a2c0497034)
Compare | [d720474264849c4dafe6e28dc5bd679b4ddbe5fe](https://github.com/dotnet/runtime/commit/d720474264849c4dafe6e28dc5bd679b4ddbe5fe)
Diff | [Diff](https://github.com/dotnet/runtime/compare/ff279bafa8ca2fbf920b605868e9b0a2c0497034...d720474264849c4dafe6e28dc5bd679b4ddbe5fe)
Configs | CompilationMode:tiered, R2RType:r2r_interpreter, RunKind:micro

### Regressions in System.Numerics.Tests.Perf_Plane

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

• [TransformByMatrix4x4Benchmark - Duration of single invocation]()
• 📝 - [Benchmark Source]()
• [ADX - Test Multi Config Graph]()

| 1.02 μs | 3.32 μs | 3.25 | 0.13 | 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 'System.Numerics.Tests.Perf_Plane*'
```

### System.Numerics.Tests.Perf_Plane.TransformByMatrix4x4Benchmark

#### 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.Numerics.Vectors/Perf_Matrix4x4.cs at the listed benchmark methods, then inspect the baseline and comparison commits and their ARM64 AzureLinux report links. Reproduce the Matrix4x4 microbenchmarks with the tiered and r2r_interpreter configuration. Done means the regression is explained and the affected benchmark results are validated against the baseline.

Written by the indexing model from the issue text.