[Perf] Linux/x64: 1 Regression on 7/3/2026 8:55:02 AM +00:00

### Run Information

Name | Value
-- | --
Architecture | x64
OS | ubuntu 22.04
Queue | ViperUbuntu
Baseline | [4895d1315f4855111e88c88c726c4f2aca4c6adf](https://github.com/dotnet/sdk/commit/4895d1315f4855111e88c88c726c4f2aca4c6adf)
Compare | [bcaa8d44d57494224d443dba7c1dfed381ad5528](https://github.com/dotnet/sdk/commit/bcaa8d44d57494224d443dba7c1dfed381ad5528)
Diff | [Diff](https://github.com/dotnet/sdk/compare/4895d1315f4855111e88c88c726c4f2aca4c6adf...bcaa8d44d57494224d443dba7c1dfed381ad5528)
Configs | CompilationMode:tiered, RunKind:mlnet

### Regressions in Microsoft.ML.Benchmarks.HashBench

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

• [HashVectorKey - Duration of single invocation]()
• 📝 - [Benchmark Source]()
• [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
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'Microsoft.ML.Benchmarks.HashBench*'
```

### Microsoft.ML.Benchmarks.HashBench.HashVectorKey

#### 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 Microsoft.ML.Benchmarks.HashBench.HashVectorKey source at src/benchmarks/real-world/Microsoft.ML.Benchmarks/HashBench.cs:186-187 and compare the listed baseline and comparison commits. Run the documented benchmarks_ci.py command for the HashBench filter, then use the linked report and profiling workflow to investigate the 1.41x regression. Done means identifying and addressing the regression, with benchmark results showing whether the change improves it.

Written by the indexing model from the issue text.