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: 31 Improvements on 5/13/2024 11:16:59 AM #34755

Open performanceautofiler[bot] opened 4 months ago

performanceautofiler[bot] commented 4 months ago

Run Information

Name Value
Architecture x64
OS ubuntu 22.04
Queue TigerUbuntu
Baseline 42c2362ca7d6030a4f665bb309fe49ce6552502b
Compare 29cb8a61d395fe8cbf243f73eb78d3a5a526ee7d
Diff Diff
Configs CompilationMode:wasm, RunKind:micro

Improvements in System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Int32>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
23.89 ns 17.76 ns 0.74 0.50 False
36.47 ns 31.40 ns 0.86 0.21 False
7.24 ns 6.11 ns 0.84 0.63 False
13.80 ns 7.71 ns 0.56 0.70 False
13.64 ns 9.63 ns 0.71 0.61 False
11.73 ns 9.72 ns 0.83 0.63 False
20.97 ns 17.55 ns 0.84 0.46 False
23.74 ns 17.52 ns 0.74 0.48 False
20.57 ns 13.51 ns 0.66 0.56 False
12.24 ns 10.61 ns 0.87 0.61 False
31.53 ns 29.91 ns 0.95 0.37 False
33.92 ns 30.67 ns 0.90 0.29 False
37.12 ns 31.31 ns 0.84 0.31 False

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 'System.Runtime.Intrinsics.Tests.Perf_Vector128Of&lt;Int32&gt;*'
### System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Int32>.LessThanOrEqualAnyBenchmark #### ETL Files #### Histogram #### JIT Disasms ### System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Int32>.LessThanOrEqualBenchmark #### ETL Files #### Histogram #### JIT Disasms ### System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Int32>.EqualityOperatorBenchmark #### ETL Files #### Histogram #### JIT Disasms ### System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Int32>.EqualsAnyBenchmark #### ETL Files #### Histogram #### JIT Disasms ### System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Int32>.LessThanAllBenchmark #### ETL Files #### Histogram #### JIT Disasms ### System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Int32>.LessThanOrEqualAllBenchmark #### ETL Files #### Histogram #### JIT Disasms ### System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Int32>.DotBenchmark #### ETL Files #### Histogram #### JIT Disasms ### System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Int32>.GreaterThanOrEqualAllBenchmark #### ETL Files #### Histogram #### JIT Disasms ### System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Int32>.SumBenchmark #### ETL Files #### Histogram #### JIT Disasms ### System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Int32>.GreaterThanAnyBenchmark #### ETL Files #### Histogram #### JIT Disasms ### System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Int32>.AbsBenchmark #### ETL Files #### Histogram #### JIT Disasms ### System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Int32>.GreaterThanBenchmark #### ETL Files #### Histogram #### JIT Disasms ### System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Int32>.LessThanBenchmark #### 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 3de068c2be232960f4cb3b233dd2b4014e2ce7c3
Compare 29cb8a61d395fe8cbf243f73eb78d3a5a526ee7d
Diff Diff
Configs CompilationMode:wasm, RunKind:micro

Improvements in System.Collections.IterateForEach<Int32>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
31.36 μs 28.65 μs 0.91 0.22 False
48.10 μs 26.62 μs 0.55 0.29 False
253.82 μs 148.06 μs 0.58 0.19 False
80.85 μs 53.33 μs 0.66 0.15 False
258.05 μs 142.53 μs 0.55 0.22 False

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 'System.Collections.IterateForEach&lt;Int32&gt;*'
### System.Collections.IterateForEach<Int32>.ConcurrentStack(Size: 512) #### ETL Files #### Histogram #### JIT Disasms ### System.Collections.IterateForEach<Int32>.IEnumerable(Size: 512) #### ETL Files #### Histogram #### JIT Disasms ### System.Collections.IterateForEach<Int32>.ImmutableSortedSet(Size: 512) #### ETL Files #### Histogram #### JIT Disasms ### System.Collections.IterateForEach<Int32>.ConcurrentDictionary(Size: 512) #### ETL Files #### Histogram #### JIT Disasms ### System.Collections.IterateForEach<Int32>.ImmutableList(Size: 512) #### 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 42c2362ca7d6030a4f665bb309fe49ce6552502b
Compare 29cb8a61d395fe8cbf243f73eb78d3a5a526ee7d
Diff Diff
Configs CompilationMode:wasm, RunKind:micro

Improvements in System.Collections.ContainsTrue<String>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
1.38 ms 1.30 ms 0.94 0.15 False

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 'System.Collections.ContainsTrue&lt;String&gt;*'
### System.Collections.ContainsTrue<String>.ImmutableSortedSet(Size: 512) #### 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 3de068c2be232960f4cb3b233dd2b4014e2ce7c3
Compare 29cb8a61d395fe8cbf243f73eb78d3a5a526ee7d
Diff Diff
Configs CompilationMode:wasm, RunKind:micro

Improvements in System.Memory.ReadOnlySpan

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
81.93 ns 73.78 ns 0.90 0.31 False
22.01 ns 15.84 ns 0.72 0.53 False

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 'System.Memory.ReadOnlySpan*'
### System.Memory.ReadOnlySpan.Trim(input: " abcdefg ") #### ETL Files #### Histogram #### JIT Disasms ### System.Memory.ReadOnlySpan.Trim(input: "") #### 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 073e35e7e32624e0f841d94364d2f28c73662ff7
Compare 29cb8a61d395fe8cbf243f73eb78d3a5a526ee7d
Diff Diff
Configs CompilationMode:wasm, RunKind:micro

Improvements in System.Text.Json.Serialization.Tests.WriteJson<ClassRecord>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
5.12 μs 4.43 μs 0.87 0.15 False
8.59 μs 7.84 μs 0.91 0.10 False
9.60 μs 5.82 μs 0.61 0.15 False

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 'System.Text.Json.Serialization.Tests.WriteJson&lt;ClassRecord&gt;*'
### System.Text.Json.Serialization.Tests.WriteJson<ClassRecord>.SerializeToUtf8Bytes(Mode: SourceGen) #### ETL Files #### Histogram #### JIT Disasms ### System.Text.Json.Serialization.Tests.WriteJson<ClassRecord>.SerializeToString(Mode: Reflection) #### ETL Files #### Histogram #### JIT Disasms ### System.Text.Json.Serialization.Tests.WriteJson<ClassRecord>.SerializeToWriter(Mode: Reflection) #### 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 3de068c2be232960f4cb3b233dd2b4014e2ce7c3
Compare 29cb8a61d395fe8cbf243f73eb78d3a5a526ee7d
Diff Diff
Configs CompilationMode:wasm, RunKind:micro

Improvements in System.Memory.MemoryMarshal<Int32>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
24.89 ns 18.42 ns 0.74 0.53 False
141.72 ns 96.71 ns 0.68 0.25 False
23.32 ns 20.86 ns 0.89 0.49 False

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 'System.Memory.MemoryMarshal&lt;Int32&gt;*'
### System.Memory.MemoryMarshal<Int32>.CastToInt #### ETL Files #### Histogram #### JIT Disasms ### System.Memory.MemoryMarshal<Int32>.TryGetArray #### ETL Files #### Histogram #### JIT Disasms ### System.Memory.MemoryMarshal<Int32>.AsBytes #### 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 3de068c2be232960f4cb3b233dd2b4014e2ce7c3
Compare 29cb8a61d395fe8cbf243f73eb78d3a5a526ee7d
Diff Diff
Configs CompilationMode:wasm, RunKind:micro

Improvements in System.Threading.Tests.Perf_Lock

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
144.67 ns 135.33 ns 0.94 0.31 False

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 'System.Threading.Tests.Perf_Lock*'
### System.Threading.Tests.Perf_Lock.ReaderWriterLockSlimPerf #### 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 073e35e7e32624e0f841d94364d2f28c73662ff7
Compare 29cb8a61d395fe8cbf243f73eb78d3a5a526ee7d
Diff Diff
Configs CompilationMode:wasm, RunKind:micro

Improvements in System.Tests.Perf_Int128

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
105.47 ns 99.26 ns 0.94 0.31 False

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 'System.Tests.Perf_Int128*'
### System.Tests.Perf_Int128.TryFormat(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)
performanceautofiler[bot] commented 4 months ago

Run Information

Name Value
Architecture x64
OS ubuntu 22.04
Queue TigerUbuntu
Baseline 073e35e7e32624e0f841d94364d2f28c73662ff7
Compare 29cb8a61d395fe8cbf243f73eb78d3a5a526ee7d
Diff Diff
Configs CompilationMode:wasm, RunKind:micro

Improvements in System.Collections.Concurrent.Count<String>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
306.39 ns 183.80 ns 0.60 0.33 False

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 'System.Collections.Concurrent.Count&lt;String&gt;*'
### System.Collections.Concurrent.Count<String>.Queue_EnqueueCountDequeue(Size: 512) #### 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 42c2362ca7d6030a4f665bb309fe49ce6552502b
Compare 29cb8a61d395fe8cbf243f73eb78d3a5a526ee7d
Diff Diff
Configs CompilationMode:wasm, RunKind:micro

Improvements in MicroBenchmarks.Serializers.Json_ToStream<CollectionsOfPrimitives>

Benchmark Baseline Test Test/Base Test Quality Edge Detector Baseline IR Compare IR IR Ratio
1.94 ms 1.75 ms 0.91 0.14 False

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 'MicroBenchmarks.Serializers.Json_ToStream&lt;CollectionsOfPrimitives&gt;*'
### MicroBenchmarks.Serializers.Json_ToStream<CollectionsOfPrimitives>.SystemTextJson_Reflection_ #### 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)