dotnet / dotnet/perf-autofiling-issues

[Perf] Linux/arm64: 8 Improvements on 8/10/2026 5:40:28 AM +00:00

Open
#78,253 2 comments 0 reactions 0 assignees View on GitHub
ampere arch-arm64 branch-refs/heads/main compilationmode-tiered kind-micro Look Again os-linux perf-improvement runkind-micro runtime-coreclr untriaged
Dominant language
No language data
Stars
10
Forks
8
PR metrics pending

Description

### Run Information

Name | Value
-- | --
Architecture | arm64
OS | ubuntu 22.04
Queue | AmpereUbuntu
Baseline | [c668fd41fd95a3b52c783bfdc761604712010ba3](https://github.com/dotnet/runtime/commit/c668fd41fd95a3b52c783bfdc761604712010ba3)
Compare | [795badfa03d01074a359ce0b65da2213043ee78c](https://github.com/dotnet/runtime/commit/795badfa03d01074a359ce0b65da2213043ee78c)
Diff | [Diff](https://github.com/dotnet/runtime/compare/c668fd41fd95a3b52c783bfdc761604712010ba3...795badfa03d01074a359ce0b65da2213043ee78c)
Configs | CompilationMode:tiered, RunKind:micro

### Improvements in System.Tests.Perf_Half

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

  • [SingleToHalf - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 4.04 ns | 2.34 ns | 0.58 | 0.16 | False | | |
|
  • [SingleToHalf - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 4.04 ns | 2.34 ns | 0.58 | 0.12 | False | | |
|
  • [SingleToHalf - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 4.04 ns | 2.34 ns | 0.58 | 0.15 | False | | |
|
  • [SingleToHalf - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 4.04 ns | 2.34 ns | 0.58 | 0.10 | False | | |
|
  • [HalfToSingle - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 3.48 ns | 2.23 ns | 0.64 | 0.12 | False | | |
|
  • [HalfToSingle - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 3.48 ns | 2.29 ns | 0.66 | 0.11 | False | | |
|
  • [HalfToSingle - Duration of single invocation]()
  • 📝 - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 3.48 ns | 2.33 ns | 0.67 | 0.13 | False | | |

![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.Tests.Perf_Half*'
```

### System.Tests.Perf_Half.SingleToHalf(value: 6.097555E-05)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Half.SingleToHalf(value: 65520)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Half.SingleToHalf(value: 12345)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Half.SingleToHalf(value: NaN)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Half.HalfToSingle(value: 6.1E-05)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Half.HalfToSingle(value: NaN)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Half.HalfToSingle(value: 12344)

#### 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 | arm64
OS | ubuntu 22.04
Queue | AmpereUbuntu
Baseline | [c668fd41fd95a3b52c783bfdc761604712010ba3](https://github.com/dotnet/runtime/commit/c668fd41fd95a3b52c783bfdc761604712010ba3)
Compare | [795badfa03d01074a359ce0b65da2213043ee78c](https://github.com/dotnet/runtime/commit/795badfa03d01074a359ce0b65da2213043ee78c)
Diff | [Diff](https://github.com/dotnet/runtime/compare/c668fd41fd95a3b52c783bfdc761604712010ba3...795badfa03d01074a359ce0b65da2213043ee78c)
Configs | CompilationMode:tiered, RunKind:micro

### Improvements in System.IO.Tests.BinaryWriterTests

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

  • [WriteHalf - Duration of single invocation]()
  • [ADX - Test Multi Config Graph]()
| 10.27 ns | 4.65 ns | 0.45 | 0.01 | False | | |

![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.IO.Tests.BinaryWriterTests*'
```

### System.IO.Tests.BinaryWriterTests.WriteHalf

#### 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 System.Tests.Perf_Half benchmark source in performance/src/benchmarks/micro/libraries/System.Runtime/Perf.Half.cs at lines 35-41, then run the provided benchmarks_ci.py command using the System.Tests.Perf_Half filter. Compare the ARM64 results with the linked baseline and test commits; done requires identifying and addressing the performance behavior, then validating the benchmark results.

Written by the indexing model from the issue text.

Assessment

Tech stack
csharp, python
Domain
performance
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Active
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.