[Perf] Linux/x64: 37 Regressions on 8/23/2024 11:41:10 PM

[performanceautofiler]

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	205adaee20a873243076dee3ef66ad70e0ee563f
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Int16>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
ConditionalSelectBenchmark - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	3.77 ns	5.09 ns	1.35	0.56	False
LessThanOrEqualAnyBenchmark - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	0.71 ns	2.47 ns	3.49	0.72	False

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<Int16>*'

System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Int16>.ConditionalSelectBenchmark

ETL Files

Histogram

JIT Disasms

System.Runtime.Intrinsics.Tests.Perf_Vector128Of<Int16>.LessThanOrEqualAnyBenchmark

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	205adaee20a873243076dee3ef66ad70e0ee563f
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Numerics.Tests.Perf_Vector2

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
AbsBenchmark - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	3.02 ns	4.84 ns	1.60	0.65	False

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.Numerics.Tests.Perf_Vector2*'

System.Numerics.Tests.Perf_Vector2.AbsBenchmark

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	62835af00823d0f4d4138744dec90e65579f2e69
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Numerics.Tests.Perf_VectorOf<Single>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
EqualsStaticBenchmark - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	2.97 ns	6.01 ns	2.02	0.56	False

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.Numerics.Tests.Perf_VectorOf<Single>*'

System.Numerics.Tests.Perf_VectorOf<Single>.EqualsStaticBenchmark

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	205adaee20a873243076dee3ef66ad70e0ee563f
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Numerics.Tests.Perf_Matrix3x2

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
InvertBenchmark - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	7.88 ns	11.22 ns	1.42	0.54	False
CreateTranslationFromVectorBenchmark - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	4.13 ns	5.16 ns	1.25	0.59	False

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.Numerics.Tests.Perf_Matrix3x2*'

System.Numerics.Tests.Perf_Matrix3x2.InvertBenchmark

ETL Files

Histogram

JIT Disasms

System.Numerics.Tests.Perf_Matrix3x2.CreateTranslationFromVectorBenchmark

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	205adaee20a873243076dee3ef66ad70e0ee563f
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Numerics.Tensors.Tests.Perf_NumberTensorPrimitives<Int32>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
AddMultiply_ScalarAddend - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	57.39 ns	66.48 ns	1.16	0.19	False

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.Numerics.Tensors.Tests.Perf_NumberTensorPrimitives<Int32>*'

System.Numerics.Tensors.Tests.Perf_NumberTensorPrimitives<Int32>.AddMultiply_ScalarAddend(BufferLength: 128)

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	62835af00823d0f4d4138744dec90e65579f2e69
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Numerics.Tests.Perf_VectorOf<UInt32>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
BitwiseOrBenchmark - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	3.05 ns	5.72 ns	1.87	0.58	False
EqualsAllBenchmark - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	1.74 ns	2.83 ns	1.62	0.68	False

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.Numerics.Tests.Perf_VectorOf<UInt32>*'

System.Numerics.Tests.Perf_VectorOf<UInt32>.BitwiseOrBenchmark

ETL Files

Histogram

JIT Disasms

System.Numerics.Tests.Perf_VectorOf<UInt32>.EqualsAllBenchmark

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	205adaee20a873243076dee3ef66ad70e0ee563f
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Numerics.Tests.Constructor

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
ConstructorBenchmark_Int16 - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	4.53 ns	6.78 ns	1.50	0.60	False

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.Numerics.Tests.Constructor*'

System.Numerics.Tests.Constructor.ConstructorBenchmark_Int16

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	205adaee20a873243076dee3ef66ad70e0ee563f
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Collections.Perf_SingleCharFrozenDictionary

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
TryGetValue_True_FrozenDictionary - Duration of single invocation ADX - Test Multi Config Graph	3.88 μs	4.50 μs	1.16	0.33	False
TryGetValue_False_FrozenDictionary - Duration of single invocation ADX - Test Multi Config Graph	26.70 μs	33.12 μs	1.24	0.24	False

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.Perf_SingleCharFrozenDictionary*'

System.Collections.Perf_SingleCharFrozenDictionary.TryGetValue_True_FrozenDictionary(Count: 100)

ETL Files

Histogram

JIT Disasms

System.Collections.Perf_SingleCharFrozenDictionary.TryGetValue_False_FrozenDictionary(Count: 1000)

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	205adaee20a873243076dee3ef66ad70e0ee563f
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Memory.Span<Int32>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
IndexOfAnyThreeValues - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	6.91 ns	10.68 ns	1.54	0.43	False

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.Span<Int32>*'

System.Memory.Span<Int32>.IndexOfAnyThreeValues(Size: 4)

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	205adaee20a873243076dee3ef66ad70e0ee563f
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in GuardedDevirtualization.TwoClassInterface

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
Call - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	8.81 ns	9.89 ns	1.12	0.18	False

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 'GuardedDevirtualization.TwoClassInterface*'

GuardedDevirtualization.TwoClassInterface.Call(testInput: pB = 0.10)

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	62835af00823d0f4d4138744dec90e65579f2e69
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Numerics.Tests.Perf_VectorOf<Byte>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
LessThanOrEqualBenchmark - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	3.76 ns	5.10 ns	1.36	0.54	False
LessThanAllBenchmark - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	1.16 ns	2.31 ns	1.99	0.66	False

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.Numerics.Tests.Perf_VectorOf<Byte>*'

System.Numerics.Tests.Perf_VectorOf<Byte>.LessThanOrEqualBenchmark

ETL Files

Histogram

JIT Disasms

System.Numerics.Tests.Perf_VectorOf<Byte>.LessThanAllBenchmark

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	205adaee20a873243076dee3ef66ad70e0ee563f
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Buffers.Tests.ReadOnlySequenceTests<Char>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
IterateTryGetTenSegments - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	285.23 ns	321.15 ns	1.13	0.31	False
IterateForEachMemory - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	147.71 ns	164.93 ns	1.12	0.31	False
IterateForEachSingleSegment - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	97.54 ns	104.25 ns	1.07	0.27	False

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.Buffers.Tests.ReadOnlySequenceTests<Char>*'

System.Buffers.Tests.ReadOnlySequenceTests<Char>.IterateTryGetTenSegments

ETL Files

Histogram

JIT Disasms

System.Buffers.Tests.ReadOnlySequenceTests<Char>.IterateForEachMemory

ETL Files

Histogram

JIT Disasms

System.Buffers.Tests.ReadOnlySequenceTests<Char>.IterateForEachSingleSegment

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	205adaee20a873243076dee3ef66ad70e0ee563f
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Numerics.Tests.Perf_VectorOf<Int32>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
BitwiseOrBenchmark - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	3.27 ns	5.01 ns	1.53	0.55	False
SubtractBenchmark - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	3.06 ns	5.55 ns	1.81	0.55	False

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.Numerics.Tests.Perf_VectorOf<Int32>*'

System.Numerics.Tests.Perf_VectorOf<Int32>.BitwiseOrBenchmark

ETL Files

Histogram

JIT Disasms

System.Numerics.Tests.Perf_VectorOf<Int32>.SubtractBenchmark

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

[performanceautofiler]

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	62835af00823d0f4d4138744dec90e65579f2e69
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Numerics.Tests.Perf_VectorOf<UInt64>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
LessThanBenchmark - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	3.23 ns	6.34 ns	1.96	0.56	False
DivisionOperatorBenchmark - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	10.43 ns	15.52 ns	1.49	0.33	False

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.Numerics.Tests.Perf_VectorOf<UInt64>*'

System.Numerics.Tests.Perf_VectorOf<UInt64>.LessThanBenchmark

ETL Files

Histogram

JIT Disasms

System.Numerics.Tests.Perf_VectorOf<UInt64>.DivisionOperatorBenchmark

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	205adaee20a873243076dee3ef66ad70e0ee563f
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Threading.Channels.Tests.SpscUnboundedChannelPerfTests

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
TryWriteThenTryRead - Duration of single invocation ADX - Test Multi Config Graph	374.49 ns	432.21 ns	1.15	0.20	False

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.Channels.Tests.SpscUnboundedChannelPerfTests*'

System.Threading.Channels.Tests.SpscUnboundedChannelPerfTests.TryWriteThenTryRead

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	205adaee20a873243076dee3ef66ad70e0ee563f
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Memory.Span<Byte>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
EndsWith - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	26.67 ns	28.04 ns	1.05	0.27	False

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.Span<Byte>*'

System.Memory.Span<Byte>.EndsWith(Size: 512)

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	205adaee20a873243076dee3ef66ad70e0ee563f
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Runtime.Intrinsics.Tests.Perf_Vector128Of<UInt64>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
GreaterThanBenchmark - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	3.26 ns	6.51 ns	2.00	0.55	False

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<UInt64>*'

System.Runtime.Intrinsics.Tests.Perf_Vector128Of<UInt64>.GreaterThanBenchmark

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	62835af00823d0f4d4138744dec90e65579f2e69
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Numerics.Tests.Perf_VectorOf<Double>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
BitwiseAndBenchmark - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	4.23 ns	7.84 ns	1.85	0.55	False
EqualsStaticBenchmark - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	3.16 ns	5.68 ns	1.80	0.49	False

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.Numerics.Tests.Perf_VectorOf<Double>*'

System.Numerics.Tests.Perf_VectorOf<Double>.BitwiseAndBenchmark

ETL Files

Histogram

JIT Disasms

System.Numerics.Tests.Perf_VectorOf<Double>.EqualsStaticBenchmark

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	205adaee20a873243076dee3ef66ad70e0ee563f
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Tests.Perf_Lazy

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
ValueFromAlreadyInitialized - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	8.79 ns	11.18 ns	1.27	0.51	False

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_Lazy*'

System.Tests.Perf_Lazy.ValueFromAlreadyInitialized

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	205adaee20a873243076dee3ef66ad70e0ee563f
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Runtime.Intrinsics.Tests.Perf_Vector128

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
ConvertULongToDoubleBenchmark - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	3.79 ns	5.52 ns	1.46	0.54	False

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_Vector128*'

System.Runtime.Intrinsics.Tests.Perf_Vector128.ConvertULongToDoubleBenchmark

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	62835af00823d0f4d4138744dec90e65579f2e69
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Numerics.Tests.Perf_Matrix4x4

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
CreateFromAxisAngleBenchmark - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	6.44 ns	11.60 ns	1.80	0.52	False

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.Numerics.Tests.Perf_Matrix4x4*'

System.Numerics.Tests.Perf_Matrix4x4.CreateFromAxisAngleBenchmark

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	205adaee20a873243076dee3ef66ad70e0ee563f
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Collections.CtorDefaultSize<String>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
HashSet - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	32.47 ns	37.13 ns	1.14	0.38	False

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.CtorDefaultSize<String>*'

System.Collections.CtorDefaultSize<String>.HashSet

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	205adaee20a873243076dee3ef66ad70e0ee563f
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Tests.Perf_Int64

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
ParseSpan - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	60.36 ns	68.84 ns	1.14	0.35	False
ParseSpan - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	43.52 ns	59.22 ns	1.36	0.37	False

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_Int64*'

System.Tests.Perf_Int64.ParseSpan(value: "9223372036854775807")

ETL Files

Histogram

JIT Disasms

System.Tests.Perf_Int64.ParseSpan(value: "12345")

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	205adaee20a873243076dee3ef66ad70e0ee563f
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Collections.TryGetValueFalse<Int32, Int32>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
IDictionary - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	19.90 μs	23.19 μs	1.17	0.18	False

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.TryGetValueFalse<Int32, Int32>*'

System.Collections.TryGetValueFalse<Int32, Int32>.IDictionary(Size: 512)

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	205adaee20a873243076dee3ef66ad70e0ee563f
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Numerics.Tests.Perf_VectorOf<UInt16>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
MultiplyOperatorBenchmark - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	2.95 ns	5.27 ns	1.79	0.48	False

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.Numerics.Tests.Perf_VectorOf<UInt16>*'

System.Numerics.Tests.Perf_VectorOf<UInt16>.MultiplyOperatorBenchmark

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

---

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	f402418aaed508c1d77e41b942e3978675183bfc
Compare	62835af00823d0f4d4138744dec90e65579f2e69
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Numerics.Tests.Perf_VectorOf<SByte>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
MultiplyBenchmark - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	16.27 ns	19.37 ns	1.19	0.33	False

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.Numerics.Tests.Perf_VectorOf<SByte>*'

System.Numerics.Tests.Perf_VectorOf<SByte>.MultiplyBenchmark

ETL Files

Histogram

JIT Disasms

Docs

Profiling workflow for dotnet/runtime repository
Benchmarking workflow for dotnet/runtime repository

[radekdoulik]

range is dotnet/runtime@df2d213...8fd46b2

@lambdageek possibly dotnet/runtime#106660
@kg could that be jiterpreter part of above PR?

[lambdageek]

@kg ptal
/cc @steveisok

[radekdoulik]

there are also 14 improvements in #40376

[lambdageek]

I wonder if always using atomic instructions is penalizing ST perf

[kg]

None of this is concurrency code and it's AOT, so I don't see how jiterpreter atomics could be responsible.

[lambdageek]

Oh you're right. I missed this was AOT.

If these benchmarks don't have any interlocked ops, the regression seems unlikely to be due to my PR.

[lambdageek]

@radekdoulik unassign me, please. I don't have permissions anymore