[Perf] Windows/x64: 3 Regressions on 5/28/2026 12:29:59 PM +00:00

### Run Information

Name | Value
-- | --
Architecture | x64
OS | Windows 10.0.22631
Queue | ViperWindows
Baseline | [c2bf1a1c93c92918d8c8f7a9f46e2f6f6d432401](https://github.com/dotnet/sdk/commit/c2bf1a1c93c92918d8c8f7a9f46e2f6f6d432401)
Compare | [1616fce88662817fb8b76911fb188b56650859a0](https://github.com/dotnet/sdk/commit/1616fce88662817fb8b76911fb188b56650859a0)
Diff | [Diff](https://github.com/dotnet/sdk/compare/c2bf1a1c93c92918d8c8f7a9f46e2f6f6d432401...1616fce88662817fb8b76911fb188b56650859a0)
Configs | CompilationMode:tiered, RunKind:bepuphysics

### Regressions in DemoBenchmarks.OneBodyConstraintBenchmarks

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

• [Contact4NonconvexOneBody - Duration of single invocation]()
• 📝 - [Benchmark Source]()
• [ADX - Test Multi Config Graph]()

| 275.25 μs | 423.84 μs | 1.54 | 0.00 | True | | |
|

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

| 37.19 μs | 42.50 μs | 1.14 | 0.00 | True | | |

![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 'DemoBenchmarks.OneBodyConstraintBenchmarks*'
```

### DemoBenchmarks.OneBodyConstraintBenchmarks.Contact4NonconvexOneBody

#### ETL Files

#### Histogram

#### JIT Disasms

### DemoBenchmarks.OneBodyConstraintBenchmarks.OneBodyLinearMotor

#### 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 | [c2bf1a1c93c92918d8c8f7a9f46e2f6f6d432401](https://github.com/dotnet/sdk/commit/c2bf1a1c93c92918d8c8f7a9f46e2f6f6d432401)
Compare | [1616fce88662817fb8b76911fb188b56650859a0](https://github.com/dotnet/sdk/commit/1616fce88662817fb8b76911fb188b56650859a0)
Diff | [Diff](https://github.com/dotnet/sdk/compare/c2bf1a1c93c92918d8c8f7a9f46e2f6f6d432401...1616fce88662817fb8b76911fb188b56650859a0)
Configs | CompilationMode:tiered, RunKind:bepuphysics

### Regressions in DemoBenchmarks.TwoBodyConstraintBenchmarks

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

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

| 47.35 μs | 59.31 μs | 1.25 | 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.TwoBodyConstraintBenchmarks*'
```

### DemoBenchmarks.TwoBodyConstraintBenchmarks.SwingLimit

#### 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/real-world/bepuphysics2/OneBodyConstraintBenchmarks.cs and TwoBodyConstraintBenchmarks.cs, then run the listed benchmarks_ci.py commands. Compare the reported regressions with the baseline and compare commits and the linked test reports. Done means identifying the regression cause and restoring the affected benchmark performance.

Written by the indexing model from the issue text.