[Perf] Linux/x64: 3 Regressions on 3/18/2026 11:50:02 AM +00:00

### Run Information

Name | Value
-- | --
Architecture | x64
OS | ubuntu 22.04
Queue | ViperUbuntu
Baseline | [e2415a7d4013188f35cefb68d6c269ba17687b43](https://github.com/dotnet/runtime/commit/e2415a7d4013188f35cefb68d6c269ba17687b43)
Compare | [593e56654f34b3f697cdcc9c0f138471c78e66fe](https://github.com/dotnet/runtime/commit/593e56654f34b3f697cdcc9c0f138471c78e66fe)
Diff | [Diff](https://github.com/dotnet/runtime/compare/e2415a7d4013188f35cefb68d6c269ba17687b43...593e56654f34b3f697cdcc9c0f138471c78e66fe)
Configs | CompilationMode:wasm, RunKind:micro, RuntimeType:coreclr

### Regressions in System.Globalization.Tests.StringSearch

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

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

| 5.66 μs | 6.05 μs | 1.07 | 0.08 | False | | |
|

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

| 5.63 μs | 6.02 μs | 1.07 | 0.14 | 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
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Globalization.Tests.StringSearch*'
```

### System.Globalization.Tests.StringSearch.IsSuffix_SecondHalf(Options: (, None, True))

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Globalization.Tests.StringSearch.IsSuffix_SecondHalf(Options: (en-US, IgnoreCase, True))

#### 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 | x64
OS | ubuntu 22.04
Queue | ViperUbuntu
Baseline | [e2415a7d4013188f35cefb68d6c269ba17687b43](https://github.com/dotnet/runtime/commit/e2415a7d4013188f35cefb68d6c269ba17687b43)
Compare | [593e56654f34b3f697cdcc9c0f138471c78e66fe](https://github.com/dotnet/runtime/commit/593e56654f34b3f697cdcc9c0f138471c78e66fe)
Diff | [Diff](https://github.com/dotnet/runtime/compare/e2415a7d4013188f35cefb68d6c269ba17687b43...593e56654f34b3f697cdcc9c0f138471c78e66fe)
Configs | CompilationMode:wasm, RunKind:micro, RuntimeType:coreclr

### Regressions in System.Numerics.Tests.Perf_Vector3

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

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

| 880.01 ns | 930.13 ns | 1.06 | 0.23 | 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
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Numerics.Tests.Perf_Vector3*'
```

### System.Numerics.Tests.Perf_Vector3.UnitZBenchmark

#### 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 at src/benchmarks/micro/libraries/System.Globalization/StringSearch.cs#L94-L96 and src/benchmarks/micro/libraries/System.Numerics.Vectors/Perf_Vector3.cs#L32-L34. Run the listed benchmarks with benchmarks_ci.py and compare the baseline and regression commits, then use the linked test reports and profiling workflow to identify the cause. Done means the reported regressions are explained and a validated change or follow-up is recorded.

Written by the indexing model from the issue text.