[Perf] Linux/x64: 13 Regressions on 8/8/2024 11:52:00 PM

[performanceautofiler]

Run Information

Name	Value
Architecture	x64
OS	ubuntu 22.04
Queue	TigerUbuntu
Baseline	44b6b2ae056092d7759b068a9661b86627ec1024
Compare	48aa31535f0e5f318f061eb6f8ad4f25611e6133
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
SequenceCompareTo - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	22.27 ns	24.77 ns	1.11	0.35	False
LastIndexOfAnyValues - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	6.31 ns	9.74 ns	1.54	0.44	False
IndexOfValue - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	6.87 ns	10.67 ns	1.55	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.Memory.Span<Int32>*'

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

ETL Files

Histogram

JIT Disasms

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

ETL Files

Histogram

JIT Disasms

System.Memory.Span<Int32>.IndexOfValue(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	44b6b2ae056092d7759b068a9661b86627ec1024
Compare	48aa31535f0e5f318f061eb6f8ad4f25611e6133
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Numerics.Tests.Perf_BigInteger

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
Equals - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	34.68 ns	45.08 ns	1.30	0.26	False
Equals - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	19.02 ns	24.12 ns	1.27	0.38	False
Equals - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	22.20 ns	26.93 ns	1.21	0.35	False
Equals - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	19.94 ns	27.50 ns	1.38	0.40	False
Equals - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	26.65 ns	31.52 ns	1.18	0.31	False
Equals - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	22.38 ns	28.05 ns	1.25	0.36	False
Multiply - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	29.34 ns	32.39 ns	1.10	0.46	False
Remainder - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	29.62 ns	38.20 ns	1.29	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_BigInteger*'

System.Numerics.Tests.Perf_BigInteger.Equals(arguments: 259 bytes, DiffLastByte)

ETL Files

Histogram

JIT Disasms

System.Numerics.Tests.Perf_BigInteger.Equals(arguments: 67 bytes, DiffFirstByte)

ETL Files

Histogram

JIT Disasms

System.Numerics.Tests.Perf_BigInteger.Equals(arguments: 67 bytes, DiffLastByte)

ETL Files

Histogram

JIT Disasms

System.Numerics.Tests.Perf_BigInteger.Equals(arguments: 67 bytes, DiffMiddleByte)

ETL Files

Histogram

JIT Disasms

System.Numerics.Tests.Perf_BigInteger.Equals(arguments: 259 bytes, DiffMiddleByte)

ETL Files

Histogram

JIT Disasms

System.Numerics.Tests.Perf_BigInteger.Equals(arguments: 67 bytes, Same)

ETL Files

Histogram

JIT Disasms

System.Numerics.Tests.Perf_BigInteger.Multiply(arguments: 16,16 bits)

ETL Files

Histogram

JIT Disasms

System.Numerics.Tests.Perf_BigInteger.Remainder(arguments: 16,8 bits)

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	44b6b2ae056092d7759b068a9661b86627ec1024
Compare	48aa31535f0e5f318f061eb6f8ad4f25611e6133
Diff	Diff
Configs	AOT:true, CompilationMode:wasm, RunKind:micro

Regressions in System.Tests.Perf_Random

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
Next_long_unseeded - Duration of single invocation ADX - Test Multi Config Graph	32.81 ns	41.80 ns	1.27	0.47	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_Random*'

System.Tests.Perf_Random.Next_long_unseeded

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	44b6b2ae056092d7759b068a9661b86627ec1024
Compare	48aa31535f0e5f318f061eb6f8ad4f25611e6133
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
IndexOfAnyTwoValues - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	7.87 ns	10.46 ns	1.33	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<Byte>*'

System.Memory.Span<Byte>.IndexOfAnyTwoValues(Size: 4)

ETL Files

Histogram

JIT Disasms

Docs

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

[radekdoulik]

Range is dotnet/runtime@105bf4d...68511fd

Looks like dotnet/runtime#106080, @kg is that expected?

[kg]

Looks like dotnet/runtime#106080, @kg is that expected?

No, and it seems kind of arbitrary for it to only impact these.