[Perf] Windows/x64: 1 Regression on 9/1/2026 4:51:38 PM +00:00

### Run Information

Name | Value
-- | --
Architecture | x64
OS | Windows 10.0.22631
Queue | ViperWindows
Baseline | [a1d60271d589de52ba513a8265a9038da9eaba5c](https://github.com/dotnet/sdk/commit/a1d60271d589de52ba513a8265a9038da9eaba5c)
Compare | [f8a811758057986566da27d06d8f03a7e5e226bf](https://github.com/dotnet/sdk/commit/f8a811758057986566da27d06d8f03a7e5e226bf)
Diff | [Diff](https://github.com/dotnet/sdk/compare/a1d60271d589de52ba513a8265a9038da9eaba5c...f8a811758057986566da27d06d8f03a7e5e226bf)
Configs | CompilationMode:tiered, RunKind:scenarios

### Regressions in Startup - Static Console Template - FDD Publish

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

• [Startup - Static Console Template - FDD Publish - Time To Main]()
• [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 'Startup - Static Console Template - FDD Publish*'
```

### Startup - Static Console Template - FDD Publish

#### 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 baseline/compare commits and the Startup - Static Console Template - FDD Publish report, then run the documented benchmarks_ci.py command from the dotnet/performance repository. Compare the 35.62 ms baseline with the 39.05 ms test result and use the linked graph and report to identify the regression. Done means the cause is identified and the startup benchmark no longer regresses.

Written by the indexing model from the issue text.