search

dotnet / perf-autofiling-issues

A landing place for auto-filed performance issues before they receive triage
MIT License
9 stars 4 forks source link

[Perf] Linux/x64: 81 Regressions on 10/21/2023 7:43:10 AM #23420

Open performanceautofiler[bot] opened 8 months ago

performanceautofiler[bot] commented 8 months ago

Run Information

Name Value
Architecture x64
OS ubuntu 22.04
Queue TigerUbuntu
Baseline 0a188ddec97348608844e078da9fda07b3eec1aa
Compare 5f653ddd5d9bc0544fbf3ff712244e3f5a398a9f
Diff Diff
Configs CompilationMode:wasm, RunKind:blazor_scenarios

Regressions in SOD - New Blazor Template - Publish - AOT

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
134.77 KB 130.27 KB 0.97 0.00 True
18.27 KB 14.27 KB 0.78 0.00 True
59.02 KB 56.74 KB 0.96 0.00 True
8.58 KB 6.55 KB 0.76 0.00 True
7.63 KB 5.79 KB 0.76 0.00 True
51.43 KB 49.41 KB 0.96 0.00 True
14.55 KB 14.84 KB 1.02 0.00 True
16.69 KB 17.08 KB 1.02 0.00 True
37.77 KB 38.27 KB 1.01 0.00 True

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

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'SOD - New Blazor Template - Publish - AOT*'
### Payloads [Baseline](<>) [Compare](<>) ### SOD - New Blazor Template - Publish - AOT #### ETL Files #### Histogram #### Description of detection logic ``` IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsImprovementBase: Marked as improvement because the compare was 1% less than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsImprovementBase: Marked as improvement because the compare was 1% less than the baseline, and the value was not too small. ``` #### 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 TigerUbuntu
Baseline 0a188ddec97348608844e078da9fda07b3eec1aa
Compare 5f653ddd5d9bc0544fbf3ff712244e3f5a398a9f
Diff Diff
Configs CompilationMode:wasm, RunKind:blazor_scenarios

Regressions in SOD - Pizza App - Publish - AOT

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
2.90 KB 2.81 KB 0.97 0.00 True
1.85 KB 1.75 KB 0.95 0.00 True
8.32 KB 8.20 KB 0.99 0.00 True
11.46 KB 7.49 KB 0.65 0.00 True
18.50 KB 17.35 KB 0.94 0.00 True
25.77 KB 16.27 KB 0.63 0.00 True
2.24 KB 2.14 KB 0.96 0.00 True
60.10 KB 57.80 KB 0.96 0.00 True
16.44 KB 15.41 KB 0.94 0.00 True
22.27 KB 21.77 KB 0.98 0.00 True
3.24 KB 3.14 KB 0.97 0.00 True
10.05 KB 6.60 KB 0.66 0.00 True
137.77 KB 133.27 KB 0.97 0.00 True
8.36 KB 8.26 KB 0.99 0.00 True
2.11 KB 2.00 KB 0.95 0.00 True
4.01 KB 3.93 KB 0.98 0.00 True
8.94 KB 8.83 KB 0.99 0.00 True
7.53 KB 7.34 KB 0.97 0.00 True
2.58 KB 2.48 KB 0.96 0.00 True
4.52 KB 4.42 KB 0.98 0.00 True
52.34 KB 50.31 KB 0.96 0.00 True
39.77 KB 38.77 KB 0.97 0.00 True
58.61 KB 54.80 KB 0.93 0.00 True
6.38 KB 6.27 KB 0.98 0.00 True
17.00 KB 17.38 KB 1.02 0.00 True
14.90 KB 15.12 KB 1.02 0.00 True
10.10 KB 10.28 KB 1.02 0.00 True
38.27 KB 38.77 KB 1.01 0.00 True

graph graph graph graph graph graph graph graph graph graph graph graph graph graph graph graph graph graph graph graph 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

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'SOD - Pizza App - Publish - AOT*'
### Payloads [Baseline]() [Compare]() ### SOD - Pizza App - Publish - AOT #### ETL Files #### Histogram #### Description of detection logic ``` IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsImprovementBase: Marked as improvement because the compare was 1% less than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsImprovementBase: Marked as improvement because the compare was 1% less than the baseline, and the value was not too small. ``` #### 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)
performanceautofiler[bot] commented 8 months ago

Run Information

Name Value
Architecture x64
OS ubuntu 22.04
Queue TigerUbuntu
Baseline 0a188ddec97348608844e078da9fda07b3eec1aa
Compare 5f653ddd5d9bc0544fbf3ff712244e3f5a398a9f
Diff Diff
Configs CompilationMode:wasm, RunKind:blazor_scenarios

Improvements in SOD - Minimum Blazor Template - Publish

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
18.27 KB 14.27 KB 0.78 0.00 True
8.58 KB 6.55 KB 0.76 0.00 True
7.63 KB 5.79 KB 0.76 0.00 True
134.77 KB 130.27 KB 0.97 0.00 True
51.43 KB 49.41 KB 0.96 0.00 True
59.02 KB 56.74 KB 0.96 0.00 True
16.69 KB 17.08 KB 1.02 0.00 True
37.77 KB 38.27 KB 1.01 0.00 True
14.55 KB 14.84 KB 1.02 0.00 True

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

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'SOD - Minimum Blazor Template - Publish*'
### Payloads [Baseline](<>) [Compare](<>) ### SOD - Minimum Blazor Template - Publish #### ETL Files #### Histogram #### Description of detection logic ``` IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsImprovementBase: Marked as improvement because the compare was 1% less than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsImprovementBase: Marked as improvement because the compare was 1% less than the baseline, and the value was not too small. ``` #### 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 TigerUbuntu
Baseline 0a188ddec97348608844e078da9fda07b3eec1aa
Compare 5f653ddd5d9bc0544fbf3ff712244e3f5a398a9f
Diff Diff
Configs CompilationMode:wasm, RunKind:blazor_scenarios

Improvements in SOD - Pizza App - Publish

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
6.38 KB 6.27 KB 0.98 0.00 True
8.94 KB 8.83 KB 0.99 0.00 True
1.85 KB 1.75 KB 0.95 0.00 True
4.52 KB 4.42 KB 0.98 0.00 True
3.24 KB 3.14 KB 0.97 0.00 True
8.36 KB 8.26 KB 0.99 0.00 True
18.50 KB 17.35 KB 0.94 0.00 True
4.01 KB 3.93 KB 0.98 0.00 True
16.44 KB 15.41 KB 0.94 0.00 True
39.77 KB 38.77 KB 0.97 0.00 True
2.11 KB 2.00 KB 0.95 0.00 True
8.32 KB 8.20 KB 0.99 0.00 True
58.61 KB 54.80 KB 0.93 0.00 True
2.90 KB 2.81 KB 0.97 0.00 True
2.58 KB 2.48 KB 0.96 0.00 True
7.53 KB 7.34 KB 0.97 0.00 True
2.24 KB 2.14 KB 0.96 0.00 True
22.27 KB 21.77 KB 0.98 0.00 True
17.00 KB 17.38 KB 1.02 0.00 True
14.90 KB 15.12 KB 1.02 0.00 True
10.10 KB 10.28 KB 1.02 0.00 True
38.27 KB 38.77 KB 1.01 0.00 True
3.10 KB 3.14 KB 1.01 0.00 True

graph graph graph graph graph graph graph graph graph graph graph graph graph graph graph 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

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'SOD - Pizza App - Publish*'
### Payloads [Baseline]() [Compare]() ### SOD - Pizza App - Publish #### ETL Files #### Histogram #### Description of detection logic ``` IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsImprovementBase: Marked as improvement because the compare was 1% less than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsImprovementBase: Marked as improvement because the compare was 1% less than the baseline, and the value was not too small. ``` #### 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)
performanceautofiler[bot] commented 8 months ago

Run Information

Name Value
Architecture x64
OS ubuntu 22.04
Queue TigerUbuntu
Baseline 0a188ddec97348608844e078da9fda07b3eec1aa
Compare 5f653ddd5d9bc0544fbf3ff712244e3f5a398a9f
Diff Diff
Configs CompilationMode:wasm, RunKind:blazor_scenarios

Regressions in SOD - Minimum Blazor Template - Publish - AOT

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
134.77 KB 130.27 KB 0.97 0.00 True
59.02 KB 56.74 KB 0.96 0.00 True
7.63 KB 5.79 KB 0.76 0.00 True
8.58 KB 6.55 KB 0.76 0.00 True
18.27 KB 14.27 KB 0.78 0.00 True
51.43 KB 49.41 KB 0.96 0.00 True
16.69 KB 17.08 KB 1.02 0.00 True
37.77 KB 38.27 KB 1.01 0.00 True
14.55 KB 14.84 KB 1.02 0.00 True

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

git clone https://github.com/dotnet/performance.git
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'SOD - Minimum Blazor Template - Publish - AOT*'
### Payloads [Baseline](<>) [Compare](<>) ### SOD - Minimum Blazor Template - Publish - AOT #### ETL Files #### Histogram #### Description of detection logic ``` IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsImprovementBase: Marked as improvement because the compare was 1% less than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsImprovementBase: Marked as improvement because the compare was 1% less than the baseline, and the value was not too small. ``` #### 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 TigerUbuntu
Baseline 0a188ddec97348608844e078da9fda07b3eec1aa
Compare 5f653ddd5d9bc0544fbf3ff712244e3f5a398a9f
Diff Diff
Configs CompilationMode:wasm, RunKind:blazor_scenarios

Regressions in SOD - New Blazor Template - Publish

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
14.55 KB 14.84 KB 1.02 0.00 True
37.77 KB 38.27 KB 1.01 0.00 True
16.69 KB 17.08 KB 1.02 0.00 True

graph graph graph Test Report

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
python3 .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'SOD - New Blazor Template - Publish*'
### Payloads [Baseline](<>) [Compare]() ### SOD - New Blazor Template - Publish #### ETL Files #### Histogram #### Description of detection logic ``` IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsImprovementBase: Marked as not an improvement because the compare was not 1% less than the baseline, or the value was too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsRegressionBase: Marked as regression because the compare was 1% greater than the baseline, and the value was not too small. IsImprovementBase: Marked as not an improvement because the compare was not 1% less than the baseline, or the value was too small. ``` #### 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)