dotnet / dotnet/perf-autofiling-issues

[Perf] Linux/x64: 16 Improvements on 6/24/2026 2:33:49 AM +00:00

Open
#75,796 1 comment 0 reactions 0 assignees View on GitHub
arch-wasm arch-x64 branch-refs/heads/main compilationmode-wasm kind-micro Look Again os-linux perf-improvement runkind-micro untriaged
Dominant language
No language data
Stars
10
Forks
8
PR metrics pending

Description

### Run Information

Name | Value
-- | --
Architecture | x64
OS | ubuntu 22.04
Queue | ViperUbuntu
Baseline | [f4430a4ba762ef82841ff7a8c340ed8854b2bca9](https://github.com/dotnet/runtime/commit/f4430a4ba762ef82841ff7a8c340ed8854b2bca9)
Compare | [46b72c7c81592b429e062bacebe8d39f17362333](https://github.com/dotnet/runtime/commit/46b72c7c81592b429e062bacebe8d39f17362333)
Diff | [Diff](https://github.com/dotnet/runtime/compare/f4430a4ba762ef82841ff7a8c340ed8854b2bca9...46b72c7c81592b429e062bacebe8d39f17362333)
Configs | CompilationMode:wasm, RunKind:micro

### Improvements in System.MathBenchmarks.Single

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

  • [ScaleB - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 85.80 μs | 24.97 μs | 0.29 | 0.57 | False | | |
|
  • [Log - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 80.60 μs | 40.42 μs | 0.50 | 0.02 | False | | |
|
  • [Log2 - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 79.33 μs | 40.67 μs | 0.51 | 0.07 | False | | |
|
  • [Round - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 79.56 μs | 48.61 μs | 0.61 | 0.02 | False | | |
|
  • [Exp2M1 - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 103.51 μs | 63.73 μs | 0.62 | 0.02 | False | | |
|
  • [Exp10M1 - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 102.91 μs | 63.77 μs | 0.62 | 0.16 | False | | |
|
  • [Exp2 - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 86.81 μs | 55.38 μs | 0.64 | 0.05 | False | | |
|
  • [Exp10 - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 84.81 μs | 55.24 μs | 0.65 | 0.03 | False | | |
|
  • [CopySign - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 59.67 μs | 39.95 μs | 0.67 | 0.00 | False | | |
|
  • [Log2P1 - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 97.31 μs | 65.29 μs | 0.67 | 0.04 | False | | |
|
  • [Pow - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 82.69 μs | 65.05 μs | 0.79 | 0.09 | False | | |

![graph]()
![graph]()
![graph]()
![graph]()
![graph]()
![graph]()
![graph]()
![graph]()
![graph]()
![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 'System.MathBenchmarks.Single*'
```

### System.MathBenchmarks.Single.ScaleB

#### ETL Files

#### Histogram

#### JIT Disasms

### System.MathBenchmarks.Single.Log

#### ETL Files

#### Histogram

#### JIT Disasms

### System.MathBenchmarks.Single.Log2

#### ETL Files

#### Histogram

#### JIT Disasms

### System.MathBenchmarks.Single.Round

#### ETL Files

#### Histogram

#### JIT Disasms

### System.MathBenchmarks.Single.Exp2M1

#### ETL Files

#### Histogram

#### JIT Disasms

### System.MathBenchmarks.Single.Exp10M1

#### ETL Files

#### Histogram

#### JIT Disasms

### System.MathBenchmarks.Single.Exp2

#### ETL Files

#### Histogram

#### JIT Disasms

### System.MathBenchmarks.Single.Exp10

#### ETL Files

#### Histogram

#### JIT Disasms

### System.MathBenchmarks.Single.CopySign

#### ETL Files

#### Histogram

#### JIT Disasms

### System.MathBenchmarks.Single.Log2P1

#### ETL Files

#### Histogram

#### JIT Disasms

### System.MathBenchmarks.Single.Pow

#### 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 | ubuntu 22.04
Queue | ViperUbuntu
Baseline | [f4430a4ba762ef82841ff7a8c340ed8854b2bca9](https://github.com/dotnet/runtime/commit/f4430a4ba762ef82841ff7a8c340ed8854b2bca9)
Compare | [46b72c7c81592b429e062bacebe8d39f17362333](https://github.com/dotnet/runtime/commit/46b72c7c81592b429e062bacebe8d39f17362333)
Diff | [Diff](https://github.com/dotnet/runtime/compare/f4430a4ba762ef82841ff7a8c340ed8854b2bca9...46b72c7c81592b429e062bacebe8d39f17362333)
Configs | CompilationMode:wasm, RunKind:micro

### Improvements in System.MathBenchmarks.Double

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

  • [ScaleB - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 85.77 μs | 25.24 μs | 0.29 | 0.56 | False | | |
|
  • [Atanh - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 137.94 μs | 79.48 μs | 0.58 | 0.23 | False | | |
|
  • [Asinh - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 138.50 μs | 82.75 μs | 0.60 | 0.06 | False | | |
|
  • [Round - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 77.40 μs | 49.62 μs | 0.64 | 0.06 | False | | |
|
  • [CopySign - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 59.67 μs | 39.41 μs | 0.66 | 0.00 | False | | |

![graph]()
![graph]()
![graph]()
![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 'System.MathBenchmarks.Double*'
```

### System.MathBenchmarks.Double.ScaleB

#### ETL Files

#### Histogram

#### JIT Disasms

### System.MathBenchmarks.Double.Atanh

#### ETL Files

#### Histogram

#### JIT Disasms

### System.MathBenchmarks.Double.Asinh

#### ETL Files

#### Histogram

#### JIT Disasms

### System.MathBenchmarks.Double.Round

#### ETL Files

#### Histogram

#### JIT Disasms

### System.MathBenchmarks.Double.CopySign

#### 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 linked performance report for System.MathBenchmarks.Single.ScaleB and the benchmark source at src/benchmarks/micro/runtime/Math/Functions/Single/ScaleB.cs. Compare the baseline and test results for the wasm microbenchmark configuration, then review the other linked benchmark reports to determine whether the reported improvements indicate a problem. Done means identifying and documenting an actionable performance issue or confirming that no change is needed.

Written by the indexing model from the issue text.

Assessment

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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.