[Perf] Windows/arm64: 6 Improvements on 1/8/2024 10:15:44 PM #27116
Description
Run Information
| Name | Value |
|---|---|
| Architecture | arm64 |
| OS | Windows 10.0.19041 |
| Queue | SurfaceWindows |
| Baseline | 21b4a8585362c1bc12d545b63e62a0d9dd4e8673 |
| Compare | b4ec422386bd358602c7693ff4ab28c96a806ec0 |
| Diff | Diff |
| Configs | CompilationMode:tiered, RunKind:micro |
Improvements in System.Memory.ReadOnlySequence
| Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio |
|---|---|---|---|---|---|---|---|---|
| 9.97 ns | 8.59 ns | 0.86 | 0.32 | False | ||||
| 13.74 ns | 9.11 ns | 0.66 | 0.13 | False | ||||
| 14.05 ns | 9.62 ns | 0.68 | 0.12 | False | ||||
| 13.74 ns | 10.42 ns | 0.76 | 0.16 | False | ||||
| 64.83 ns | 41.79 ns | 0.64 | 0.02 | False | ||||
| 13.03 ns | 9.72 ns | 0.75 | 0.22 | False |
Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
git clone https://github.com/dotnet/performance.git
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Memory.ReadOnlySequence*'Payloads
System.Memory.ReadOnlySequence.Slice_Start_And_Length(Segment: Multiple)
ETL Files
Histogram
JIT Disasms
System.Memory.ReadOnlySequence.Slice_StartPosition_And_Length(Segment: Multiple)
ETL Files
Histogram
JIT Disasms
System.Memory.ReadOnlySequence.Slice_StartPosition_And_EndPosition(Segment: Multiple)
ETL Files
Histogram
JIT Disasms
System.Memory.ReadOnlySequence.Slice_Start_And_EndPosition(Segment: Multiple)
ETL Files
Histogram
JIT Disasms
System.Memory.ReadOnlySequence.Slice_Repeat_StartPosition_And_EndPosition(Segment: Multiple)
ETL Files
Histogram
JIT Disasms
System.Memory.ReadOnlySequence.Slice_StartPosition(Segment: Multiple)
ETL Files
Histogram
JIT Disasms
Docs
Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository