LLVM Clang 3.4 SVN - SLP Vectorizer

Benchmarking the SLP Vectorizer via -fslp-vectorize on LLVM Clang 3.4 SVN for a future article on Phoronix.com

Compare your own system(s) to this result file with the Phoronix Test Suite by running the command: phoronix-test-suite benchmark 1307291-SO-FSLPVECTO83
Jump To Table - Results

View

Do Not Show Noisy Results
Do Not Show Results With Incomplete Data
Do Not Show Results With Little Change/Spread
List Notable Results
Show Result Confidence Charts

Limit displaying results to tests within:

Audio Encoding 2 Tests
Bioinformatics 3 Tests
Timed Code Compilation 2 Tests
C/C++ Compiler Tests 12 Tests
CPU Massive 12 Tests
Creator Workloads 6 Tests
Encoding 3 Tests
HPC - High Performance Computing 3 Tests
Multi-Core 8 Tests
Programmer / Developer System Benchmarks 2 Tests
Renderers 2 Tests
Scientific Computing 3 Tests
Server CPU Tests 4 Tests
Single-Threaded 4 Tests

Statistics

Show Overall Harmonic Mean(s)
Show Overall Geometric Mean
Show Geometric Means Per-Suite/Category
Show Wins / Losses Counts (Pie Chart)
Normalize Results
Remove Outliers Before Calculating Averages

Graph Settings

Force Line Graphs Where Applicable
Convert To Scalar Where Applicable
Prefer Vertical Bar Graphs

Multi-Way Comparison

Condense Multi-Option Tests Into Single Result Graphs

Table

Show Detailed System Result Table

Run Management

Highlight
Result
Hide
Result
Result
Identifier
View Logs
Performance Per
Dollar
Date
Run
  Test
  Duration
LLVM Clang 3.4 SVN
July 28 2013
 
-fslp-vectorize
July 29 2013
 
Invert Hiding All Results Option
 
Only show results matching title/arguments (delimit multiple options with a comma):
Do not show results matching title/arguments (delimit multiple options with a comma):

LLVM Clang 3.4 SVN

Compiler Notes: Optimized build; Built Jul 28 2013 (21:43:17); Default target: x86_64-unknown-linux-gnu; Host CPU: corei7
Processor Notes: Scaling Governor: acpi-cpufreq ondemand

-fslp-vectorize

Processor: Intel Core i7 720Q @ 1.60GHz (8 Cores), Motherboard: LENOVO 4318CTO, Chipset: Intel Core DMI, Memory: 4096MB, Disk: 160GB INTEL SSDSA2M160, Graphics: NVIDIA Quadro FX 880M 1024MB (405/324MHz), Audio: Conexant CX20585, Network: Intel 82577LM Gigabit Connection + Intel Centrino Ultimate-N 6300

OS: Ubuntu 13.10, Kernel: 3.11.0-031100rc2-generic (x86_64), Desktop: Xfce 4.10, Display Server: X Server 1.14.2, Display Driver: nouveau 1.0.8, OpenGL: 3.0 Mesa 9.1.4 Gallium 0.4, Compiler: Clang 3.4 (SVN 187338) + LLVM 3.4svn, File-System: ext4, Screen Resolution: 1600x900

LLVM Clang 3.4 SVN - SLP VectorizerOpenBenchmarking.orgPhoronix Test SuiteIntel Core i7 720Q @ 1.60GHz (8 Cores)LENOVO 4318CTOIntel Core DMI4096MB160GB INTEL SSDSA2M160NVIDIA Quadro FX 880M 1024MB (405/324MHz)Conexant CX20585Intel 82577LM Gigabit Connection + Intel Centrino Ultimate-N 6300Ubuntu 13.103.11.0-031100rc2-generic (x86_64)Xfce 4.10X Server 1.14.2nouveau 1.0.83.0 Mesa 9.1.4 Gallium 0.4Clang 3.4 (SVN 187338) + LLVM 3.4svnext41600x900ProcessorMotherboardChipsetMemoryDiskGraphicsAudioNetworkOSKernelDesktopDisplay ServerDisplay DriverOpenGLCompilerFile-SystemScreen ResolutionLLVM Clang 3.4 SVN - SLP Vectorizer BenchmarksSystem Logs- Optimized build; Built Jul 28 2013 (21:43:17); Default target: x86_64-unknown-linux-gnu; Host CPU: corei7 - Scaling Governor: acpi-cpufreq ondemand

LLVM Clang 3.4 SVN vs. -fslp-vectorize ComparisonPhoronix Test SuiteBaseline+2.2%+2.2%+4.4%+4.4%+6.6%+6.6%+8.8%+8.8%8.9%6.9%F.F.TP.P.SG.I.R.1.S2.7%SciMarkHimeno BenchmarkSmallptLLVM Clang 3.4 SVN-fslp-vectorize

LLVM Clang 3.4 SVN - SLP Vectorizerscimark2: Fast Fourier Transformhimeno: Poisson Pressure Solversmallpt: Global Illumination Renderer; 100 Samplesapache: Static Web Page Servingbuild-imagemagick: Time To Compilen-queens: Elapsed Timeencode-mp3: WAV To MP3scimark2: Sparse Matrix Multiplyscimark2: Dense LU Matrix Factorizationx264: H.264 Video Encodingbuild-php: Time To Compilescimark2: Jacobi Successive Over-Relaxationscimark2: Monte Carloc-ray: Total Timemafft: Multiple Sequence Alignmenthmmer: Pfam Database Searchscimark2: Compositeprimesieve: 1e12 Prime Number Generationencode-flac: WAV To FLACgraphics-magick: Local Adaptive Thresholdinggraphics-magick: HWB Color Spacegraphics-magick: Resizinggraphics-magick: Sharpengraphics-magick: Blurblake2: Phoronix Test Suite v4.8.0m4LLVM Clang 3.4 SVN-fslp-vectorize173.571055.082939830.6165.88345.3822.641234.662003.2359.6341.971092.03378.7575.9815.4227.33976.45614.078.8632806636534.20189.101127.373019715.2066.31343.1522.781228.191995.6559.8342.071093.98379.4175.8715.4427.30977.27614.348.8632806636534.20OpenBenchmarking.org

SciMark

This test runs the ANSI C version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This test is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Fast Fourier Transform-fslp-vectorizeLLVM Clang 3.4 SVN4080120160200SE +/- 0.40, N = 4SE +/- 0.61, N = 4189.10173.57-fslp-vectorize1. (CXX) g++ options: -O3 -march=native

Himeno Benchmark

The Himeno benchmark is a linear solver of pressure Poisson using a point-Jacobi method. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMFLOPS, More Is BetterHimeno Benchmark 3.0Poisson Pressure Solver-fslp-vectorizeLLVM Clang 3.4 SVN2004006008001000SE +/- 0.79, N = 3SE +/- 5.78, N = 31127.371055.08-fslp-vectorize1. (CC) gcc options: -O3 -march=native

Smallpt

Smallpt is a C++ global illumination renderer written in less than 100 lines of code. Global illumination is done via unbiased Monte Carlo path tracing and there is multi-threading support via the OpenMP library. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterSmallpt 1.0Global Illumination Renderer; 100 Samples-fslp-vectorizeLLVM Clang 3.4 SVN70140210280350SE +/- 0.88, N = 3SE +/- 0.58, N = 3301293-fslp-vectorize1. (CXX) g++ options: -fopenmp -O3 -march=native

Apache Benchmark

OpenBenchmarking.orgRequests Per Second, More Is BetterApache Benchmark 2.4.3Static Web Page Serving-fslp-vectorizeLLVM Clang 3.4 SVN2K4K6K8K10KSE +/- 44.32, N = 3SE +/- 60.14, N = 39715.209830.611. (CC) gcc options: -shared -fPIC -pthread -O3 -march=native

Timed ImageMagick Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed ImageMagick Compilation 6.8.1-10Time To Compile-fslp-vectorizeLLVM Clang 3.4 SVN1530456075SE +/- 0.13, N = 3SE +/- 0.18, N = 366.3165.88

N-Queens

This is a test of the OpenMP version of a test that solves the N-queens problem. The board problem size is 18. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterN-Queens 1.0Elapsed Time-fslp-vectorizeLLVM Clang 3.4 SVN80160240320400SE +/- 0.03, N = 3SE +/- 0.89, N = 3343.15345.38-fslp-vectorize1. (CC) gcc options: -static -fopenmp -O3 -march=native

LAME MP3 Encoding

LAME is an MP3 encoder licensed under the LGPL. This test measures the time required to encode a WAV file to MP3 format. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterLAME MP3 Encoding 3.99.3WAV To MP3-fslp-vectorizeLLVM Clang 3.4 SVN510152025SE +/- 0.01, N = 5SE +/- 0.02, N = 522.7822.64-fslp-vectorize1. (CC) gcc options: -pipe -O3 -march=native -lm

SciMark

This test runs the ANSI C version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This test is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Sparse Matrix Multiply-fslp-vectorizeLLVM Clang 3.4 SVN30060090012001500SE +/- 1.06, N = 4SE +/- 0.93, N = 41228.191234.66-fslp-vectorize1. (CXX) g++ options: -O3 -march=native

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Dense LU Matrix Factorization-fslp-vectorizeLLVM Clang 3.4 SVN400800120016002000SE +/- 3.58, N = 4SE +/- 8.33, N = 41995.652003.23-fslp-vectorize1. (CXX) g++ options: -O3 -march=native

x264

OpenBenchmarking.orgFrames Per Second, More Is Betterx264 2013-06-08H.264 Video Encoding-fslp-vectorizeLLVM Clang 3.4 SVN1326395265SE +/- 0.11, N = 5SE +/- 0.14, N = 559.8359.63-fslp-vectorize1. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -march=native -std=gnu99 -fomit-frame-pointer -fno-tree-vectorize

Timed PHP Compilation

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed PHP Compilation 5.2.9Time To Compile-fslp-vectorizeLLVM Clang 3.4 SVN1020304050SE +/- 0.07, N = 3SE +/- 0.10, N = 342.0741.97-fslp-vectorize1. (CC) gcc options: -O3 -march=native -pedantic -ldl -lz -lm

SciMark

This test runs the ANSI C version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This test is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Jacobi Successive Over-Relaxation-fslp-vectorizeLLVM Clang 3.4 SVN2004006008001000SE +/- 0.98, N = 4SE +/- 0.98, N = 41093.981092.03-fslp-vectorize1. (CXX) g++ options: -O3 -march=native

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Monte Carlo-fslp-vectorizeLLVM Clang 3.4 SVN80160240320400SE +/- 0.00, N = 4SE +/- 0.38, N = 4379.41378.75-fslp-vectorize1. (CXX) g++ options: -O3 -march=native

C-Ray

This is a test of C-Ray, a simple raytracer designed to test the floating-point CPU performance. This test is multi-threaded (16 threads per core), will shoot 8 rays per pixel for anti-aliasing, and will generate a 1600 x 1200 image. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterC-Ray 1.1Total Time-fslp-vectorizeLLVM Clang 3.4 SVN20406080100SE +/- 0.01, N = 3SE +/- 0.04, N = 375.8775.98-fslp-vectorize1. (CC) gcc options: -lm -lpthread -O3 -march=native

Timed MAFFT Alignment

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed MAFFT Alignment 6.864Multiple Sequence Alignment-fslp-vectorizeLLVM Clang 3.4 SVN48121620SE +/- 0.23, N = 5SE +/- 0.25, N = 615.4415.421. (CC) gcc options: -O3 -lm -lpthread

Timed HMMer Search

This test searches through the Pfam database of profile hidden markov models. The search finds the domain structure of Drosophila Sevenless protein. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgSeconds, Fewer Is BetterTimed HMMer Search 2.3.2Pfam Database Search-fslp-vectorizeLLVM Clang 3.4 SVN612182430SE +/- 0.03, N = 3SE +/- 0.02, N = 327.3027.33-fslp-vectorize1. (CC) gcc options: -O3 -march=native -pthread -lhmmer -lsquid -lm

SciMark

This test runs the ANSI C version of SciMark 2.0, which is a benchmark for scientific and numerical computing developed by programmers at the National Institute of Standards and Technology. This test is made up of Fast Foruier Transform, Jacobi Successive Over-relaxation, Monte Carlo, Sparse Matrix Multiply, and dense LU matrix factorization benchmarks. Learn more via the OpenBenchmarking.org test page.

OpenBenchmarking.orgMflops, More Is BetterSciMark 2.0Computational Test: Composite-fslp-vectorizeLLVM Clang 3.4 SVN2004006008001000SE +/- 0.78, N = 4SE +/- 1.47, N = 4977.27976.45-fslp-vectorize1. (CXX) g++ options: -O3 -march=native

Primesieve

OpenBenchmarking.orgSeconds, Fewer Is BetterPrimesieve 4.21e12 Prime Number Generation-fslp-vectorizeLLVM Clang 3.4 SVN130260390520650SE +/- 0.14, N = 3SE +/- 0.26, N = 3614.34614.071. (CXX) g++ options: -O2

FLAC Audio Encoding

OpenBenchmarking.orgSeconds, Fewer Is BetterFLAC Audio Encoding 1.3.0WAV To FLAC-fslp-vectorizeLLVM Clang 3.4 SVN246810SE +/- 0.01, N = 5SE +/- 0.01, N = 58.868.86-fslp-vectorize1. (CXX) g++ options: -O3 -march=native -fvisibility=hidden -logg -lm

GraphicsMagick

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: Local Adaptive Thresholding-fslp-vectorizeLLVM Clang 3.4 SVN714212835SE +/- 0.00, N = 3SE +/- 0.00, N = 33232-fslp-vectorize1. (CC) gcc options: -O3 -march=native -pthread -lXext -lSM -lICE -lX11 -lxml2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: HWB Color Space-fslp-vectorizeLLVM Clang 3.4 SVN20406080100SE +/- 0.33, N = 3SE +/- 0.00, N = 38080-fslp-vectorize1. (CC) gcc options: -O3 -march=native -pthread -lXext -lSM -lICE -lX11 -lxml2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: Resizing-fslp-vectorizeLLVM Clang 3.4 SVN1530456075SE +/- 0.33, N = 3SE +/- 0.00, N = 36666-fslp-vectorize1. (CC) gcc options: -O3 -march=native -pthread -lXext -lSM -lICE -lX11 -lxml2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: Sharpen-fslp-vectorizeLLVM Clang 3.4 SVN816243240SE +/- 0.00, N = 3SE +/- 0.00, N = 33636-fslp-vectorize1. (CC) gcc options: -O3 -march=native -pthread -lXext -lSM -lICE -lX11 -lxml2 -lz -lm -lpthread

OpenBenchmarking.orgIterations Per Minute, More Is BetterGraphicsMagick 1.3.16Operation: Blur-fslp-vectorizeLLVM Clang 3.4 SVN1224364860SE +/- 0.00, N = 3SE +/- 0.00, N = 35353-fslp-vectorize1. (CC) gcc options: -O3 -march=native -pthread -lXext -lSM -lICE -lX11 -lxml2 -lz -lm -lpthread

BLAKE2

OpenBenchmarking.orgCycles Per Byte, Fewer Is BetterBLAKE2 20121223Phoronix Test Suite v4.8.0m4-fslp-vectorizeLLVM Clang 3.4 SVN0.9451.892.8353.784.725SE +/- 0.00, N = 3SE +/- 0.01, N = 34.204.201. (CC) gcc options: -std=gnu99 -O3 -march=native -lcrypto -lz

LLVM Clang 3.4 SVN

Compiler Notes: Optimized build; Built Jul 28 2013 (21:43:17); Default target: x86_64-unknown-linux-gnu; Host CPU: corei7
Processor Notes: Scaling Governor: acpi-cpufreq ondemand

Testing initiated at 28 July 2013 22:40 by user phoronix.

-fslp-vectorize

Processor: Intel Core i7 720Q @ 1.60GHz (8 Cores), Motherboard: LENOVO 4318CTO, Chipset: Intel Core DMI, Memory: 4096MB, Disk: 160GB INTEL SSDSA2M160, Graphics: NVIDIA Quadro FX 880M 1024MB (405/324MHz), Audio: Conexant CX20585, Network: Intel 82577LM Gigabit Connection + Intel Centrino Ultimate-N 6300

OS: Ubuntu 13.10, Kernel: 3.11.0-031100rc2-generic (x86_64), Desktop: Xfce 4.10, Display Server: X Server 1.14.2, Display Driver: nouveau 1.0.8, OpenGL: 3.0 Mesa 9.1.4 Gallium 0.4, Compiler: Clang 3.4 (SVN 187338) + LLVM 3.4svn, File-System: ext4, Screen Resolution: 1600x900

Compiler Notes: Optimized build; Built Jul 28 2013 (21:43:17); Default target: x86_64-unknown-linux-gnu; Host CPU: corei7
Processor Notes: Scaling Governor: acpi-cpufreq ondemand

Testing initiated at 29 July 2013 10:13 by user phoronix.