[Perf] Windows/x86: 6 Regressions on 7/3/2026 10:18:16 AM +00:00

### Run Information

Name | Value
-- | --
Architecture | x86
OS | Windows 10.0.22631
Queue | ViperWindows
Baseline | [e1979b72ccb5f916649f1d9949ef663254790c25](https://github.com/dotnet/runtime/commit/e1979b72ccb5f916649f1d9949ef663254790c25)
Compare | [6814be7e81ea875d36976bea750ba5f8325ac58b](https://github.com/dotnet/runtime/commit/6814be7e81ea875d36976bea750ba5f8325ac58b)
Diff | [Diff](https://github.com/dotnet/runtime/compare/e1979b72ccb5f916649f1d9949ef663254790c25...6814be7e81ea875d36976bea750ba5f8325ac58b)
Configs | CompilationMode:tiered, RunKind:micro

### Regressions in System.Formats.Tar.Tests.Perf_TarFile

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

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

| 338.92 μs | 716.16 μs | 2.11 | 0.68 | False | | |
|

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

| 332.91 μs | 634.43 μs | 1.91 | 0.70 | False | | |
|

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

| 335.63 μs | 628.38 μs | 1.87 | 0.72 | False | | |
|

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

| 344.75 μs | 553.79 μs | 1.61 | 0.77 | 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.Formats.Tar.Tests.Perf_TarFile*'
```

### System.Formats.Tar.Tests.Perf_TarFile.ExtractToDirectory_Path_Async

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Formats.Tar.Tests.Perf_TarFile.ExtractToDirectory_Path

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Formats.Tar.Tests.Perf_TarFile.ExtractToDirectory_Stream_Async

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Formats.Tar.Tests.Perf_TarFile.ExtractToDirectory_Stream

#### 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 | x86
OS | Windows 10.0.22631
Queue | ViperWindows
Baseline | [e1979b72ccb5f916649f1d9949ef663254790c25](https://github.com/dotnet/runtime/commit/e1979b72ccb5f916649f1d9949ef663254790c25)
Compare | [6814be7e81ea875d36976bea750ba5f8325ac58b](https://github.com/dotnet/runtime/commit/6814be7e81ea875d36976bea750ba5f8325ac58b)
Diff | [Diff](https://github.com/dotnet/runtime/compare/e1979b72ccb5f916649f1d9949ef663254790c25...6814be7e81ea875d36976bea750ba5f8325ac58b)
Configs | CompilationMode:tiered, RunKind:micro

### Regressions in System.Numerics.Tests.Perf_VectorConvert

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

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

| 432.52 ns | 548.06 ns | 1.27 | 0.09 | False | | |
|

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

| 437.27 ns | 548.22 ns | 1.25 | 0.08 | 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.Numerics.Tests.Perf_VectorConvert*'
```

### System.Numerics.Tests.Perf_VectorConvert.Widen_uint

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Numerics.Tests.Perf_VectorConvert.Widen_sbyte

#### 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 benchmark sources src/benchmarks/micro/libraries/System.Formats.Tar/Perf.TarFile.cs and src/benchmarks/micro/libraries/System.Numerics.Vectors/Perf_VectorConvert.cs, then run the supplied benchmarks_ci.py command for Perf_TarFile. Compare the reported x86 Windows regressions with the linked baseline and compare commits; done means the affected benchmarks are explained and verified against a new benchmark report.

Written by the indexing model from the issue text.