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: 52 Regressions on 2/11/2024 7:44:56 AM #28882

Open performanceautofiler[bot] opened 7 months ago

performanceautofiler[bot] commented 7 months ago

Run Information

Name Value
Architecture x64
OS ubuntu 22.04
Queue TigerUbuntu
Baseline 36287c22bc876a83e5dcbda97b6c4ca998bdc955
Compare bdd5d325729ae594cce94da56265c6667c861f37
Diff Diff
Configs CompilationMode:wasm, RunKind:blazor_scenarios

Regressions in SOD - Localized App - Publish - AOT

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
3.20 KB 3.16 KB 0.99 0.00 True
34.77 KB 35.27 KB 1.01 0.00 True
23.27 KB 23.77 KB 1.02 0.00 True
11.99 KB 12.17 KB 1.02 0.00 True
10.71 KB 10.87 KB 1.01 0.00 True
37.63 KB 38.33 KB 1.02 0.00 True

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 - Localized App - Publish - AOT*'
### Payloads [Baseline]() [Compare]() ### SOD - Localized App - Publish - AOT #### 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 x64
OS ubuntu 22.04
Queue TigerUbuntu
Baseline 36287c22bc876a83e5dcbda97b6c4ca998bdc955
Compare bdd5d325729ae594cce94da56265c6667c861f37
Diff Diff
Configs CompilationMode:wasm, RunKind:blazor_scenarios

Regressions in SOD - Pizza App - Publish

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
2.35 KB 2.27 KB 0.97 0.00 True
10.22 KB 10.05 KB 0.98 0.00 True
36.27 KB 35.77 KB 0.99 0.00 True
25.27 KB 25.77 KB 1.02 0.00 True
4.82 KB 4.90 KB 1.02 0.00 True
10.71 KB 10.87 KB 1.01 0.00 True
11.99 KB 12.17 KB 1.02 0.00 True
37.63 KB 38.33 KB 1.02 0.00 True

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 #### 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 36287c22bc876a83e5dcbda97b6c4ca998bdc955
Compare bdd5d325729ae594cce94da56265c6667c861f37
Diff Diff
Configs CompilationMode:wasm, RunKind:blazor_scenarios

Improvements in SOD - New Blazor Template - Publish - AOT

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
36.27 KB 35.77 KB 0.99 0.00 True
11.47 KB 11.35 KB 0.99 0.00 True
10.71 KB 10.87 KB 1.01 0.00 True
11.99 KB 12.17 KB 1.02 0.00 True
37.63 KB 38.33 KB 1.02 0.00 True

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 #### 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 36287c22bc876a83e5dcbda97b6c4ca998bdc955
Compare bdd5d325729ae594cce94da56265c6667c861f37
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
36.27 KB 35.77 KB 0.99 0.00 True
11.47 KB 11.35 KB 0.99 0.00 True
13.56 KB 13.36 KB 0.98 0.00 True
5.23 KB 5.14 KB 0.98 0.00 True
7.43 KB 7.54 KB 1.02 0.00 True
10.71 KB 10.87 KB 1.01 0.00 True
37.63 KB 38.33 KB 1.02 0.00 True
13.06 KB 13.25 KB 1.01 0.00 True
25.27 KB 25.77 KB 1.02 0.00 True
21.52 KB 21.91 KB 1.02 0.00 True
11.99 KB 12.17 KB 1.02 0.00 True
24.63 KB 24.98 KB 1.01 0.00 True

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 #### 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 7 months ago

Run Information

Name Value
Architecture x64
OS ubuntu 22.04
Queue TigerUbuntu
Baseline 36287c22bc876a83e5dcbda97b6c4ca998bdc955
Compare bdd5d325729ae594cce94da56265c6667c861f37
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
11.47 KB 11.35 KB 0.99 0.00 True
36.27 KB 35.77 KB 0.99 0.00 True
37.63 KB 38.33 KB 1.02 0.00 True
11.99 KB 12.17 KB 1.02 0.00 True
10.71 KB 10.87 KB 1.01 0.00 True

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 #### 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 36287c22bc876a83e5dcbda97b6c4ca998bdc955
Compare bdd5d325729ae594cce94da56265c6667c861f37
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
2.35 KB 2.27 KB 0.97 0.00 True
36.27 KB 35.77 KB 0.99 0.00 True
10.71 KB 10.87 KB 1.01 0.00 True
11.99 KB 12.17 KB 1.02 0.00 True
37.63 KB 38.33 KB 1.02 0.00 True

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*'
### Payloads [Baseline]() [Compare]() ### SOD - New Blazor Template - Publish #### 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 x64
OS ubuntu 22.04
Queue TigerUbuntu
Baseline 36287c22bc876a83e5dcbda97b6c4ca998bdc955
Compare bdd5d325729ae594cce94da56265c6667c861f37
Diff Diff
Configs CompilationMode:wasm, RunKind:blazor_scenarios

Regressions in SOD - Localized App - Publish

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
3.20 KB 3.16 KB 0.99 0.00 True
23.27 KB 23.77 KB 1.02 0.00 True
10.71 KB 10.87 KB 1.01 0.00 True
37.63 KB 38.33 KB 1.02 0.00 True
34.77 KB 35.27 KB 1.01 0.00 True
11.99 KB 12.17 KB 1.02 0.00 True

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 - Localized App - Publish*'
### Payloads [Baseline]() [Compare]() ### SOD - Localized App - Publish #### 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 x64
OS ubuntu 22.04
Queue TigerUbuntu
Baseline 36287c22bc876a83e5dcbda97b6c4ca998bdc955
Compare bdd5d325729ae594cce94da56265c6667c861f37
Diff Diff
Configs CompilationMode:wasm, RunKind:blazor_scenarios

Regressions in SOD - Minimum Blazor Template - Publish

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
2.35 KB 2.27 KB 0.97 0.00 True
36.27 KB 35.77 KB 0.99 0.00 True
10.71 KB 10.87 KB 1.01 0.00 True
11.99 KB 12.17 KB 1.02 0.00 True
37.63 KB 38.33 KB 1.02 0.00 True

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 #### 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)
radekdoulik commented 7 months ago

the range is https://github.com/dotnet/runtime/compare/339443b0408f45503380558aa2cf2a9ecc2cbaa9...a79c62ddc8089cf2879ed36eac9aa333b32bde5f

looks like https://github.com/dotnet/runtime/pull/97096 @lateralusX could you please take a look?

lateralusX commented 7 months ago

@radekdoulik I'm not working on the .net team anymore so won't have any bandwidth to investigate. What regressed? Most changes in that PR either adds PNSE implementation of unsupported X86 intrinsics or stubbing out additional is_supported functions on System.Runtime.Intrinsics.X86. Re-assign to @steveisok for load balancing.

vargaz commented 7 months ago

Many of the changes are changes in .dll sizes, or changes in non-AOT configurations, so not sure its https://github.com/dotnet/runtime/pull/97096.