[Perf] Windows/x64: 2 Regressions on 8/20/2026 10:44:23 AM +00:00

### Run Information

Name | Value
-- | --
Architecture | x64
OS | Windows 10.0.22631
Queue | ViperWindows
Baseline | [19bc97f3dd3ab67c7810e4ab179125b7c6a60641](https://github.com/dotnet/sdk/commit/19bc97f3dd3ab67c7810e4ab179125b7c6a60641)
Compare | [b8c18a5c2f5d06efdd635120822953728b21678e](https://github.com/dotnet/sdk/commit/b8c18a5c2f5d06efdd635120822953728b21678e)
Diff | [Diff](https://github.com/dotnet/sdk/compare/19bc97f3dd3ab67c7810e4ab179125b7c6a60641...b8c18a5c2f5d06efdd635120822953728b21678e)
Configs | CompilationMode:tiered, RunKind:bepuphysics

### Regressions in DemoBenchmarks.GatherScatterBenchmarks

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

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

| 21.44 μs | 24.11 μs | 1.12 | 0.00 | True | | |

![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 'DemoBenchmarks.GatherScatterBenchmarks*'
```

### DemoBenchmarks.GatherScatterBenchmarks.GatherState

#### 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 | Windows 10.0.22631
Queue | ViperWindows
Baseline | [19bc97f3dd3ab67c7810e4ab179125b7c6a60641](https://github.com/dotnet/sdk/commit/19bc97f3dd3ab67c7810e4ab179125b7c6a60641)
Compare | [b8c18a5c2f5d06efdd635120822953728b21678e](https://github.com/dotnet/sdk/commit/b8c18a5c2f5d06efdd635120822953728b21678e)
Diff | [Diff](https://github.com/dotnet/sdk/compare/19bc97f3dd3ab67c7810e4ab179125b7c6a60641...b8c18a5c2f5d06efdd635120822953728b21678e)
Configs | CompilationMode:tiered, RunKind:bepuphysics

### Regressions in DemoBenchmarks.SweepBenchmarks

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

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

| 2.37 μs | 2.69 μs | 1.13 | 0.00 | True | | |

![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 'DemoBenchmarks.SweepBenchmarks*'
```

### DemoBenchmarks.SweepBenchmarks.CapsuleCapsule

#### 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/real-world/bepuphysics2/GatherScatterBenchmarks.cs and SweepBenchmarks.cs at the linked benchmark lines, then run the provided benchmarks_ci.py command. Compare the Windows/x64 results with the linked baseline and compare commits and inspect the generated reports. Done means the two reported regressions are explained and no longer appear as unexplained performance regressions.

Written by the indexing model from the issue text.