dotnet / dotnet/perf-autofiling-issues

[Perf] Windows/x86: 1284 Regressions on 2/27/2026 3:09:53 PM +00:00

Open
#69,518 40 comments 0 reactions 0 assignees View on GitHub
arch-x86 branch-refs/heads/main kind-micro os-windows perf-regression runtime-coreclr untriaged
Dominant language
No language data
Stars
10
Forks
8
PR metrics pending

Description

### Run Information

Name | Value
-- | --
Architecture | x86
OS | Windows 10.0.22631
Queue | ViperWindows
Baseline | [7a5e8fc86df2058a2bc5d5e25cb7309f456befa6](https://github.com/dotnet/runtime/commit/7a5e8fc86df2058a2bc5d5e25cb7309f456befa6)
Compare | [b41bbeab8b775a5058bad74e73a84476bfd8d9a7](https://github.com/dotnet/runtime/commit/b41bbeab8b775a5058bad74e73a84476bfd8d9a7)
Diff | [Diff](https://github.com/dotnet/runtime/compare/7a5e8fc86df2058a2bc5d5e25cb7309f456befa6...b41bbeab8b775a5058bad74e73a84476bfd8d9a7)
Configs | CompilationMode:tiered, RunKind:micro

### Regressions in System.Runtime.Intrinsics.Tests.Perf_Vector128Int

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

  • [GreaterThanAllBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.02 ns | 1.12 ns | 71.01 | 0.81 | False | | |
|
  • [SubtractionOperatorBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.00 ns | 1.15 ns | 6353.58 | 0.88 | False | | |
|
  • [XorBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.02 ns | 1.17 ns | 75.08 | 0.65 | False | | |
|
  • [GreaterThanOrEqualBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.02 ns | 1.17 ns | 68.71 | 0.83 | False | | |
|
  • [SquareRootBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 8.82 ns | 9.99 ns | 1.13 | 0.25 | False | | |
|
  • [OnesComplementOperatorBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.00 ns | 1.15 ns | 10245.30 | 0.67 | False | | |
|
  • [EqualsAnyBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.00 ns | 1.13 ns | 2178.18 | 0.92 | False | | |
|
  • [SubtractBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.00 ns | 1.17 ns | 4209.28 | 0.69 | False | | |
|
  • [LessThanOrEqualAnyBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.01 ns | 1.14 ns | 118.21 | 0.89 | False | | |
|
  • [GreaterThanBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.00 ns | 1.14 ns | 10685.34 | 0.85 | False | | |
|
  • [LessThanOrEqualAllBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.00 ns | 1.15 ns | ∞ | 0.90 | False | | |
|
  • [GreaterThanOrEqualAnyBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.00 ns | 1.13 ns | ∞ | 0.85 | False | | |
|
  • [MaxBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.00 ns | 1.14 ns | 6009.31 | 0.87 | False | | |
|
  • [LessThanBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.05 ns | 1.14 ns | 22.66 | 0.80 | False | | |
|
  • [BitwiseOrOperatorBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.00 ns | 1.15 ns | 5881.05 | 0.85 | False | | |
|
  • [EqualityOperatorBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.00 ns | 1.13 ns | 14490.55 | 0.89 | False | | |
|
  • [LessThanAllBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.00 ns | 1.15 ns | ∞ | 0.90 | False | | |
|
  • [BitwiseOrBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.03 ns | 1.17 ns | 34.22 | 0.70 | False | | |
|
  • [AllBitsSetBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.02 ns | 1.17 ns | 67.78 | 0.83 | False | | |
|
  • [EqualsAllBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.02 ns | 1.13 ns | 72.52 | 0.83 | False | | |
|
  • [UnaryNegateOperatorBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.00 ns | 1.14 ns | 2409.77 | 0.65 | False | | |
|
  • [SumBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.01 ns | 1.41 ns | 123.54 | 0.34 | False | | |
|
  • [GetHashCodeBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 7.01 ns | 8.04 ns | 1.15 | 0.30 | False | | |
|
  • [NegateBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.03 ns | 1.13 ns | 33.29 | 0.68 | False | | |
|
  • [CountBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.00 ns | 1.13 ns | 5460.31 | 0.87 | False | | |
|
  • [BitwiseAndOperatorBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.00 ns | 1.15 ns | 14956.03 | 0.75 | False | | |
|
  • [EqualsStaticBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.03 ns | 1.13 ns | 35.61 | 0.78 | False | | |
|
  • [BitwiseAndBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.00 ns | 1.17 ns | 16483.11 | 0.68 | False | | |
|
  • [DotBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.53 ns | 1.68 ns | 3.19 | 0.03 | False | | |
|
  • [AddBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.00 ns | 1.17 ns | 11631.73 | 0.61 | False | | |
|
  • [EqualsBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.01 ns | 1.13 ns | 85.96 | 0.87 | False | | |
|
  • [DivideBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.53 ns | 1.66 ns | 3.16 | 0.18 | False | | |
|
  • [LessThanAnyBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.02 ns | 1.13 ns | 71.43 | 0.90 | False | | |
|
  • [DivisionOperatorBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.51 ns | 1.66 ns | 3.27 | 0.30 | False | | |
|
  • [GreaterThanAnyBenchmark - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 0.00 ns | 1.13 ns | 23164.87 | 0.83 | False | | |

[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.Runtime.Intrinsics.Tests.Perf_Vector128Int*'
```

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.GreaterThanAllBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.SubtractionOperatorBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.XorBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.GreaterThanOrEqualBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.SquareRootBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.OnesComplementOperatorBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.EqualsAnyBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.SubtractBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.LessThanOrEqualAnyBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.GreaterThanBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.LessThanOrEqualAllBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.GreaterThanOrEqualAnyBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.MaxBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.LessThanBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.BitwiseOrOperatorBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.EqualityOperatorBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.LessThanAllBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.BitwiseOrBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.AllBitsSetBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.EqualsAllBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.UnaryNegateOperatorBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.SumBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.GetHashCodeBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.NegateBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.CountBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.BitwiseAndOperatorBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.EqualsStaticBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.BitwiseAndBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.DotBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.AddBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.EqualsBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.DivideBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.LessThanAnyBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.DivisionOperatorBenchmark

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Runtime.Intrinsics.Tests.Perf_Vector128Int.GreaterThanAnyBenchmark

#### 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)

Contributor guide

No contributing guide indexed for this repository

Research direction

Start with the listed Perf_Vector128.cs benchmark lines and the linked regression reports for the x86 Windows run. Compare the baseline commit 7a5e8fc86df2058a2bc5d5e25cb7309f456befa6 with b41bbeab8b775a5058bad74e73a84476bfd8d9a7, then run the affected microbenchmarks to confirm the regression. Done means identifying and resolving the regression so results return to the expected baseline.

Written by the indexing model from the issue text.

Assessment

Tech stack
csharp
Domain
performance
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.