[Perf] Windows/x64: 2 Regressions on 9/12/2026 2:03:45 AM +00:00

### Run Information

Name | Value
-- | --
Architecture | x64
OS | Windows 10.0.22631
Queue | ViperWindows
Baseline | [b5f06b0847863033c479487e1abe17d30a9a9ab7](https://github.com/dotnet/runtime/commit/b5f06b0847863033c479487e1abe17d30a9a9ab7)
Compare | [ea973e7517a629d0c3c75f4879ce279b07f21365](https://github.com/dotnet/runtime/commit/ea973e7517a629d0c3c75f4879ce279b07f21365)
Diff | [Diff](https://github.com/dotnet/runtime/compare/b5f06b0847863033c479487e1abe17d30a9a9ab7...ea973e7517a629d0c3c75f4879ce279b07f21365)
Configs | CompilationMode:tiered, RunKind:micro

### Regressions in System.Memory.Span<Byte>

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

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

| 4.92 ns | 14.63 ns | 2.97 | 0.21 | False | | |
|

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

| 26.59 ns | 35.22 ns | 1.32 | 0.32 | 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.Memory.Span*'
```

### System.Memory.Span<Byte>.Fill(Size: 512)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Memory.Span<Byte>.Fill(Size: 3000)

#### 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 source at src/benchmarks/micro/libraries/System.Memory/Span.cs#L53-L54 and compare the baseline and compare commits listed in the issue. Run the provided benchmarks_ci.py command, then inspect the linked performance report for the two Fill regressions on Windows/x64. Done means identifying and addressing the regression so the affected benchmark results return to the expected range.

Written by the indexing model from the issue text.