dotnet / dotnet/perf-autofiling-issues

[Perf] Linux/arm64: 103 Improvements on 8/11/2026 9:14:21 PM +00:00

Open
#77,903 5 comments 0 reactions 0 assignees View on GitHub
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 | azurelinux 3.0
Queue | CobaltAzureLinux
Baseline | [643b8962835e549e8f6c88fd8b19f6f79685fba0](https://github.com/dotnet/runtime/commit/643b8962835e549e8f6c88fd8b19f6f79685fba0)
Compare | [633ab1a41439ad2405ba2eb241295ba1842fcf5a](https://github.com/dotnet/runtime/commit/633ab1a41439ad2405ba2eb241295ba1842fcf5a)
Diff | [Diff](https://github.com/dotnet/runtime/compare/643b8962835e549e8f6c88fd8b19f6f79685fba0...633ab1a41439ad2405ba2eb241295ba1842fcf5a)
Configs | CompilationMode:tiered, RunKind:micro

### Improvements in System.Tests.Perf_Int32

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

  • [ParseHex - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 16.41 ns | 8.25 ns | 0.50 | 0.14 | False | | |
|
  • [TryParseSpan - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 17.00 ns | 9.66 ns | 0.57 | 0.16 | False | | |
|
  • [ParseSpan - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 17.00 ns | 9.79 ns | 0.58 | 0.17 | False | | |
|
  • [TryParse - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 16.97 ns | 10.02 ns | 0.59 | 0.16 | False | | |
|
  • [Parse - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 15.79 ns | 9.59 ns | 0.61 | 0.20 | False | | |
|
  • [ParseSpan - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 21.13 ns | 13.61 ns | 0.64 | 0.20 | False | | |
|
  • [Parse - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 20.25 ns | 13.40 ns | 0.66 | 0.15 | False | | |
|
  • [TryParseSpan - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 20.48 ns | 13.84 ns | 0.68 | 0.17 | False | | |
|
  • [ToString - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 32.84 ns | 22.60 ns | 0.69 | 0.16 | False | | |
|
  • [TryFormat - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 23.69 ns | 16.51 ns | 0.70 | 0.22 | False | | |
|
  • [Parse - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 26.35 ns | 19.16 ns | 0.73 | 0.23 | 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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Tests.Perf_Int32*'
```

### System.Tests.Perf_Int32.ParseHex(value: "4")

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Int32.TryParseSpan(value: "4")

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Int32.ParseSpan(value: "4")

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Int32.TryParse(value: "4")

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Int32.Parse(value: "4")

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Int32.ParseSpan(value: "12345")

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Int32.Parse(value: "12345")

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Int32.TryParseSpan(value: "12345")

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Int32.ToString(value: -2147483648)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Int32.TryFormat(value: -2147483648)

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_Int32.Parse(value: "2147483647")

#### 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 | azurelinux 3.0
Queue | CobaltAzureLinux
Baseline | [643b8962835e549e8f6c88fd8b19f6f79685fba0](https://github.com/dotnet/runtime/commit/643b8962835e549e8f6c88fd8b19f6f79685fba0)
Compare | [633ab1a41439ad2405ba2eb241295ba1842fcf5a](https://github.com/dotnet/runtime/commit/633ab1a41439ad2405ba2eb241295ba1842fcf5a)
Diff | [Diff](https://github.com/dotnet/runtime/compare/643b8962835e549e8f6c88fd8b19f6f79685fba0...633ab1a41439ad2405ba2eb241295ba1842fcf5a)
Configs | CompilationMode:tiered, RunKind:micro

### Improvements in System.Collections.CtorDefaultSize<Int32>

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

  • [HashSet - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 11.24 ns | 7.14 ns | 0.64 | 0.32 | False | | |
|
  • [ConcurrentStack - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 7.86 ns | 5.17 ns | 0.66 | 0.26 | False | | |
|
  • [OrderedDictionary - Duration of single invocation]()
  • [ADX - Test Multi Config Graph]()
| 10.70 ns | 7.27 ns | 0.68 | 0.34 | False | | |
|
  • [Stack - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 8.70 ns | 6.05 ns | 0.70 | 0.21 | False | | |
|
  • [List - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 8.63 ns | 6.02 ns | 0.70 | 0.20 | False | | |
|
  • [Queue - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 9.22 ns | 6.59 ns | 0.72 | 0.24 | False | | |
|
  • [LinkedList - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 8.59 ns | 6.29 ns | 0.73 | 0.33 | False | | |
|
  • [SortedDictionary - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 29.67 ns | 23.09 ns | 0.78 | 0.24 | False | | |

![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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Collections.CtorDefaultSize*'
```

### System.Collections.CtorDefaultSize<Int32>.HashSet

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Collections.CtorDefaultSize<Int32>.ConcurrentStack

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Collections.CtorDefaultSize<Int32>.OrderedDictionary

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Collections.CtorDefaultSize<Int32>.Stack

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Collections.CtorDefaultSize<Int32>.List

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Collections.CtorDefaultSize<Int32>.Queue

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Collections.CtorDefaultSize<Int32>.LinkedList

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Collections.CtorDefaultSize<Int32>.SortedDictionary

#### 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 | azurelinux 3.0
Queue | CobaltAzureLinux
Baseline | [643b8962835e549e8f6c88fd8b19f6f79685fba0](https://github.com/dotnet/runtime/commit/643b8962835e549e8f6c88fd8b19f6f79685fba0)
Compare | [633ab1a41439ad2405ba2eb241295ba1842fcf5a](https://github.com/dotnet/runtime/commit/633ab1a41439ad2405ba2eb241295ba1842fcf5a)
Diff | [Diff](https://github.com/dotnet/runtime/compare/643b8962835e549e8f6c88fd8b19f6f79685fba0...633ab1a41439ad2405ba2eb241295ba1842fcf5a)
Configs | CompilationMode:tiered, RunKind:micro

### Improvements in System.Tests.Perf_UInt32

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

  • [Parse - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 16.46 ns | 9.17 ns | 0.56 | 0.26 | False | | |
|
  • [ParseSpan - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 16.71 ns | 9.32 ns | 0.56 | 0.24 | False | | |
|
  • [TryParse - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 16.55 ns | 9.54 ns | 0.58 | 0.19 | False | | |
|
  • [ParseSpan - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 20.48 ns | 13.39 ns | 0.65 | 0.16 | False | | |
|
  • [Parse - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 20.19 ns | 13.37 ns | 0.66 | 0.22 | False | | |
|
  • [TryParse - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 20.35 ns | 13.63 ns | 0.67 | 0.19 | False | | |

![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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Tests.Perf_UInt32*'
```

### System.Tests.Perf_UInt32.Parse(value: "0")

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_UInt32.ParseSpan(value: "0")

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_UInt32.TryParse(value: "0")

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_UInt32.ParseSpan(value: "12345")

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_UInt32.Parse(value: "12345")

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Tests.Perf_UInt32.TryParse(value: "12345")

#### 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 | azurelinux 3.0
Queue | CobaltAzureLinux
Baseline | [643b8962835e549e8f6c88fd8b19f6f79685fba0](https://github.com/dotnet/runtime/commit/643b8962835e549e8f6c88fd8b19f6f79685fba0)
Compare | [633ab1a41439ad2405ba2eb241295ba1842fcf5a](https://github.com/dotnet/runtime/commit/633ab1a41439ad2405ba2eb241295ba1842fcf5a)
Diff | [Diff](https://github.com/dotnet/runtime/compare/643b8962835e549e8f6c88fd8b19f6f79685fba0...633ab1a41439ad2405ba2eb241295ba1842fcf5a)
Configs | CompilationMode:tiered, RunKind:micro

### Improvements in System.Threading.Tasks.ValueTaskPerfTest

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

  • [Await_FromResult - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 20.02 ns | 7.68 ns | 0.38 | 0.14 | False | | |
|
  • [CreateAndAwait_FromResult_ConfigureAwait - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 19.85 ns | 12.13 ns | 0.61 | 0.17 | False | | |
|
  • [CreateAndAwait_FromResult - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 19.92 ns | 12.35 ns | 0.62 | 0.19 | False | | |
|
  • [Await_FromCompletedTask - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 32.95 ns | 21.65 ns | 0.66 | 0.27 | False | | |
|
  • [CreateAndAwait_FromCompletedTask_ConfigureAwait - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 22.28 ns | 14.84 ns | 0.67 | 0.19 | False | | |
|
  • [CreateAndAwait_FromCompletedTask - Duration of single invocation]()
  • πŸ“ - [Benchmark Source]()
  • [ADX - Test Multi Config Graph]()
| 21.35 ns | 15.24 ns | 0.71 | 0.19 | False | | |

![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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Threading.Tasks.ValueTaskPerfTest*'
```

### System.Threading.Tasks.ValueTaskPerfTest.Await_FromResult

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Threading.Tasks.ValueTaskPerfTest.CreateAndAwait_FromResult_ConfigureAwait

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Threading.Tasks.ValueTaskPerfTest.CreateAndAwait_FromResult

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Threading.Tasks.ValueTaskPerfTest.Await_FromCompletedTask

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Threading.Tasks.ValueTaskPerfTest.CreateAndAwait_FromCompletedTask_ConfigureAwait

#### ETL Files

#### Histogram

#### JIT Disasms

### System.Threading.Tasks.ValueTaskPerfTest.CreateAndAwait_FromCompletedTask

#### 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 benchmark source in src/benchmarks/micro/libraries/System.Runtime/Perf.Int32.cs at the listed Parse, TryParse, ParseSpan, TryParseSpan, and ToString entries. Compare the ARM64 AzureLinux baseline and test results using the linked history reports and commit diff; done means determining whether these improvements are expected and recording the triage outcome.

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
Quiet
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.