[Perf] Windows/x64: 25 Improvements on 8/15/2024 12:39:36 AM

[performanceautofiler]

Run Information

Name	Value
Architecture	x64
OS	Windows 10.0.22631
Queue	ViperWindows
Baseline	0fbd81404d1f211572387498474063bc6f407f0f
Compare	bfffd58eeb204d368989038a19786bff86000b19
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Improvements in SciMark2.kernel

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
benchmarkLU - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	394.37 ms	303.71 ms	0.77	0.04	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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'SciMark2.kernel*'

SciMark2.kernel.benchmarkLU

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	Windows 10.0.22631
Queue	ViperWindows
Baseline	0fbd81404d1f211572387498474063bc6f407f0f
Compare	bfffd58eeb204d368989038a19786bff86000b19
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Improvements in Benchstone.BenchI.BenchE

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
Test - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	294.02 ms	226.25 ms	0.77	0.04	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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'Benchstone.BenchI.BenchE*'

Benchstone.BenchI.BenchE.Test

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	Windows 10.0.22631
Queue	ViperWindows
Baseline	0fbd81404d1f211572387498474063bc6f407f0f
Compare	bfffd58eeb204d368989038a19786bff86000b19
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Improvements in Loops.StrengthReduction

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
SumIntsSpan - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	5.42 μs	4.32 μs	0.80	0.15	False
SumS3Span - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	5.42 μs	4.35 μs	0.80	0.04	False
SumShortsSpan - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	5.42 μs	4.94 μs	0.91	0.16	False
SumS16Span - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	5.43 μs	4.29 μs	0.79	0.04	False
SumS12Span - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	5.43 μs	4.30 μs	0.79	0.04	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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'Loops.StrengthReduction*'

Loops.StrengthReduction.SumIntsSpan

ETL Files

Histogram

JIT Disasms

Loops.StrengthReduction.SumS3Span

ETL Files

Histogram

JIT Disasms

Loops.StrengthReduction.SumShortsSpan

ETL Files

Histogram

JIT Disasms

Loops.StrengthReduction.SumS16Span

ETL Files

Histogram

JIT Disasms

Loops.StrengthReduction.SumS12Span

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	Windows 10.0.22631
Queue	ViperWindows
Baseline	0fbd81404d1f211572387498474063bc6f407f0f
Compare	bfffd58eeb204d368989038a19786bff86000b19
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Improvements in System.Text.RegularExpressions.Tests.Perf_Regex_Industry_RustLang_Sherlock

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
Count - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	44.22 μs	40.20 μs	0.91	0.00	False
Count - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	38.22 μs	34.67 μs	0.91	0.00	True
Count - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	43.15 μs	39.46 μs	0.91	0.00	True
Count - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	38.23 μs	34.59 μs	0.90	0.00	True
Count - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	45.27 μs	41.66 μs	0.92	0.00	False
Count - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	38.20 μs	34.67 μs	0.91	0.00	True
Count - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	47.31 μs	44.66 μs	0.94	0.00	False
Count - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	47.20 μs	44.82 μs	0.95	0.00	False
Count - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	44.28 μs	40.04 μs	0.90	0.01	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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Text.RegularExpressions.Tests.Perf_Regex_Industry_RustLang_Sherlock*'

System.Text.RegularExpressions.Tests.Perf_Regex_Industry_RustLang_Sherlock.Count(Pattern: "Sherlock", Options: Compiled)

ETL Files

Histogram

JIT Disasms

System.Text.RegularExpressions.Tests.Perf_Regex_Industry_RustLang_Sherlock.Count(Pattern: "aqj", Options: Compiled)

ETL Files

Histogram

JIT Disasms

System.Text.RegularExpressions.Tests.Perf_Regex_Industry_RustLang_Sherlock.Count(Pattern: "(?m)^Sherlock Holmes|Sherlock Holmes$", Options: Compiled)

ETL Files

Histogram

JIT Disasms

System.Text.RegularExpressions.Tests.Perf_Regex_Industry_RustLang_Sherlock.Count(Pattern: "aei", Options: Compiled)

ETL Files

Histogram

JIT Disasms

System.Text.RegularExpressions.Tests.Perf_Regex_Industry_RustLang_Sherlock.Count(Pattern: "Sherlock\s+Holmes", Options: Compiled)

ETL Files

Histogram

JIT Disasms

System.Text.RegularExpressions.Tests.Perf_Regex_Industry_RustLang_Sherlock.Count(Pattern: "zqj", Options: Compiled)

ETL Files

Histogram

JIT Disasms

System.Text.RegularExpressions.Tests.Perf_Regex_Industry_RustLang_Sherlock.Count(Pattern: "(?i)Sherlock Holmes", Options: Compiled)

ETL Files

Histogram

JIT Disasms

System.Text.RegularExpressions.Tests.Perf_Regex_Industry_RustLang_Sherlock.Count(Pattern: "(?i)Sherlock", Options: Compiled)

ETL Files

Histogram

JIT Disasms

System.Text.RegularExpressions.Tests.Perf_Regex_Industry_RustLang_Sherlock.Count(Pattern: "Sherlock Holmes", Options: Compiled)

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	Windows 10.0.22631
Queue	ViperWindows
Baseline	0fbd81404d1f211572387498474063bc6f407f0f
Compare	bfffd58eeb204d368989038a19786bff86000b19
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Improvements in System.Text.RegularExpressions.Tests.Perf_Regex_Industry_Leipzig

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
Count - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	1.12 ms	1.03 ms	0.92	0.00	True
Count - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	1.22 ms	1.13 ms	0.93	0.01	False
Count - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	1.20 ms	1.12 ms	0.94	0.00	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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Text.RegularExpressions.Tests.Perf_Regex_Industry_Leipzig*'

System.Text.RegularExpressions.Tests.Perf_Regex_Industry_Leipzig.Count(Pattern: "Twain", Options: Compiled)

ETL Files

Histogram

JIT Disasms

System.Text.RegularExpressions.Tests.Perf_Regex_Industry_Leipzig.Count(Pattern: "[a-z]shing", Options: Compiled)

ETL Files

Histogram

JIT Disasms

System.Text.RegularExpressions.Tests.Perf_Regex_Industry_Leipzig.Count(Pattern: "(?i)Twain", Options: Compiled)

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	Windows 10.0.22631
Queue	ViperWindows
Baseline	0fbd81404d1f211572387498474063bc6f407f0f
Compare	bfffd58eeb204d368989038a19786bff86000b19
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Improvements in System.Memory.Span<Char>

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	14.49 ns	12.18 ns	0.84	0.17	False
IndexOfAnyFiveValues - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	27.76 ns	25.25 ns	0.91	0.05	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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Memory.Span<Char>*'

System.Memory.Span<Char>.IndexOfAnyTwoValues(Size: 512)

ETL Files

Histogram

JIT Disasms

System.Memory.Span<Char>.IndexOfAnyFiveValues(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	Windows 10.0.22631
Queue	ViperWindows
Baseline	0fbd81404d1f211572387498474063bc6f407f0f
Compare	bfffd58eeb204d368989038a19786bff86000b19
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Improvements in System.Memory.Span<Byte>

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
IndexOfAnyFiveValues - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	20.04 ns	13.15 ns	0.66	0.16	True
IndexOfAnyFourValues - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	15.22 ns	11.50 ns	0.76	0.15	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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Memory.Span<Byte>*'

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

ETL Files

Histogram

JIT Disasms

System.Memory.Span<Byte>.IndexOfAnyFourValues(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	Windows 10.0.22631
Queue	ViperWindows
Baseline	0fbd81404d1f211572387498474063bc6f407f0f
Compare	bfffd58eeb204d368989038a19786bff86000b19
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Improvements in System.Globalization.Tests.StringSearch

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
IsSuffix_DifferentLastChar - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	20.70 ns	16.93 ns	0.82	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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Globalization.Tests.StringSearch*'

System.Globalization.Tests.StringSearch.IsSuffix_DifferentLastChar(Options: (en-US, OrdinalIgnoreCase, False))

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	Windows 10.0.22631
Queue	ViperWindows
Baseline	0fbd81404d1f211572387498474063bc6f407f0f
Compare	bfffd58eeb204d368989038a19786bff86000b19
Diff	Diff
Configs	CompilationMode:tiered, RunKind:micro

Improvements in System.Text.RegularExpressions.Tests.Perf_Regex_Industry_SliceSlice

Benchmark	Baseline	Test	Test/Base	Test Quality	Edge Detector	Baseline IR	Compare IR	IR Ratio
Count - Duration of single invocation 📝 - Benchmark Source ADX - Test Multi Config Graph	376.56 ms	343.07 ms	0.91	0.00	True

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
py .\performance\scripts\benchmarks_ci.py -f net8.0 --filter 'System.Text.RegularExpressions.Tests.Perf_Regex_Industry_SliceSlice*'

System.Text.RegularExpressions.Tests.Perf_Regex_Industry_SliceSlice.Count(Options: Compiled)

ETL Files

Histogram

JIT Disasms

Docs

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

[AndyAyersMS]

Likely dotnet/runtime#106218