[Perf] Linux/x64: 3 Improvements on 3/21/2023 4:52:34 PM #14498
Description
Run Information
| Name | Value |
|---|---|
| Architecture | x64 |
| OS | ubuntu 18.04 |
| Queue | TigerUbuntu |
| Baseline | 8c5cf110b4d2fa0b98cad4b60e4abba5a6562c58 |
| Compare | 7b82cdf019aff3227d882a15c12eeb3c189bb22d |
| Diff | Diff |
| Configs | CompilationMode:tiered, RunKind:micro |
Improvements in Benchstone.MDBenchI.MDNDhrystone
| Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio | Baseline ETL | Compare ETL |
|---|---|---|---|---|---|---|---|---|---|---|
| Test - Duration of single invocation | 333.34 ms | 311.83 ms | 0.94 | 0.01 | False |
Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
Payloads
git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'Benchstone.MDBenchI.MDNDhrystone*'Details
Payloads
Histogram
Benchstone.MDBenchI.MDNDhrystone.Test
Description of detection logic
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed:Marked as improvement because 311.83386661538464 < 315.4366883892857.
IsChangePoint: Marked as a change because one of 3/21/2023 12:39:01 PM, 3/28/2023 8:13:28 AM falls between 3/19/2023 2:30:51 PM and 3/28/2023 8:13:28 AM.
IsImprovementStdDev: Marked as improvement because 25.72960653512733 (T) = (0 -312100969.1442067) / Math.Sqrt((29132194038137.39 / (299)) + (14193576359333.016 / (38))) is greater than 1.967070609662329 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (38) - 2, .975) and 0.053545607879973145 = (329758065.19858897 - 312100969.1442067) / 329758065.19858897 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.
Docs
Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository
Run Information
| Name | Value |
|---|---|
| Architecture | x64 |
| OS | ubuntu 18.04 |
| Queue | TigerUbuntu |
| Baseline | 8c5cf110b4d2fa0b98cad4b60e4abba5a6562c58 |
| Compare | 7b82cdf019aff3227d882a15c12eeb3c189bb22d |
| Diff | Diff |
| Configs | CompilationMode:tiered, RunKind:micro |
Improvements in System.Text.Json.Serialization.Tests.WriteJson<Int32>
| Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio | Baseline ETL | Compare ETL |
|---|---|---|---|---|---|---|---|---|---|---|
| SerializeToWriter - Duration of single invocation | 48.67 ns | 42.46 ns | 0.87 | 0.29 | False |
_1.png)
Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
Payloads
git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Text.Json.Serialization.Tests.WriteJson<Int32>*'Details
Payloads
Histogram
System.Text.Json.Serialization.Tests.WriteJson<Int32>.SerializeToWriter(Mode: Reflection)
Description of detection logic
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed:Marked as improvement because 42.459375017016434 < 46.24035827030511.
IsChangePoint: Marked as a change because one of 2/25/2023 8:26:37 PM, 2/26/2023 5:38:06 PM, 3/21/2023 12:39:01 PM, 3/28/2023 8:13:28 AM falls between 3/19/2023 2:30:51 PM and 3/28/2023 8:13:28 AM.
IsImprovementStdDev: Marked as improvement because 9.146602585147845 (T) = (0 -43.45480196392678) / Math.Sqrt((5.385515767490557 / (299)) + (4.162690276178317 / (39))) is greater than 1.9670493839589689 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (39) - 2, .975) and 0.0691982317613565 = (46.68534530843911 - 43.45480196392678) / 46.68534530843911 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.
Docs
Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository
Run Information
| Name | Value |
|---|---|
| Architecture | x64 |
| OS | ubuntu 18.04 |
| Queue | TigerUbuntu |
| Baseline | 8c5cf110b4d2fa0b98cad4b60e4abba5a6562c58 |
| Compare | 7b82cdf019aff3227d882a15c12eeb3c189bb22d |
| Diff | Diff |
| Configs | CompilationMode:tiered, RunKind:micro |
Improvements in System.Tests.Perf_String
| Benchmark | Baseline | Test | Test/Base | Test Quality | Edge Detector | Baseline IR | Compare IR | IR Ratio | Baseline ETL | Compare ETL |
|---|---|---|---|---|---|---|---|---|---|---|
| PadLeft - Duration of single invocation | 12.15 ns | 9.91 ns | 0.82 | 0.05 | False |
Repro
General Docs link: https://github.com/dotnet/performance/blob/main/docs/benchmarking-workflow-dotnet-runtime.md
Payloads
git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Tests.Perf_String*'Details
Payloads
Histogram
System.Tests.Perf_String.PadLeft(n: 18)
Description of detection logic
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsRegressionBase: Marked as not a regression because the compare was not 5% greater than the baseline, or the value was too small.
IsImprovementBase: Marked as improvement because the compare was 5% less than the baseline, and the value was not too small.
IsImprovementCheck: Marked as improvement because the three check build points were 0.05 less than the baseline.
IsImprovementWindowed:Marked as improvement because 9.913381933629395 < 11.460208663462376.
IsChangePoint: Marked as a change because one of 3/21/2023 12:39:01 PM, 3/28/2023 8:13:28 AM falls between 3/19/2023 2:30:51 PM and 3/28/2023 8:13:28 AM.
IsImprovementStdDev: Marked as improvement because 36.076071506817534 (T) = (0 -9.751476290749784) / Math.Sqrt((0.13976183004419415 / (299)) + (0.09003813134168909 / (39))) is greater than 1.9670493839589689 = MathNet.Numerics.Distributions.StudentT.InvCDF(0, 1, (299) + (39) - 2, .975) and 0.16312706312096031 = (11.652278214559168 - 9.751476290749784) / 11.652278214559168 is greater than 0.05.
IsChangeEdgeDetector: Marked not as a regression because Edge Detector said so.
Docs
Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository