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 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: corei7Processor 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
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.org Mflops, More Is Better SciMark 2.0 Computational Test: Composite LLVM Clang 3.4 SVN -fslp-vectorize 200 400 600 800 1000 SE +/- 1.47, N = 4 SE +/- 0.78, N = 4 976.45 977.27 -fslp-vectorize 1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Monte Carlo LLVM Clang 3.4 SVN -fslp-vectorize 80 160 240 320 400 SE +/- 0.38, N = 4 SE +/- 0.00, N = 4 378.75 379.41 -fslp-vectorize 1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Fast Fourier Transform LLVM Clang 3.4 SVN -fslp-vectorize 40 80 120 160 200 SE +/- 0.61, N = 4 SE +/- 0.40, N = 4 173.57 189.10 -fslp-vectorize 1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Sparse Matrix Multiply LLVM Clang 3.4 SVN -fslp-vectorize 300 600 900 1200 1500 SE +/- 0.93, N = 4 SE +/- 1.06, N = 4 1234.66 1228.19 -fslp-vectorize 1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Dense LU Matrix Factorization LLVM Clang 3.4 SVN -fslp-vectorize 400 800 1200 1600 2000 SE +/- 8.33, N = 4 SE +/- 3.58, N = 4 2003.23 1995.65 -fslp-vectorize 1. (CXX) g++ options: -O3 -march=native
OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Jacobi Successive Over-Relaxation LLVM Clang 3.4 SVN -fslp-vectorize 200 400 600 800 1000 SE +/- 0.98, N = 4 SE +/- 0.98, N = 4 1092.03 1093.98 -fslp-vectorize 1. (CXX) g++ options: -O3 -march=native
BLAKE2 OpenBenchmarking.org Cycles Per Byte, Fewer Is Better BLAKE2 20121223 Phoronix Test Suite v4.8.0m4 LLVM Clang 3.4 SVN -fslp-vectorize 0.945 1.89 2.835 3.78 4.725 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 4.20 4.20 1. (CC) gcc options: -std=gnu99 -O3 -march=native -lcrypto -lz
FLAC Audio Encoding OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.3.0 WAV To FLAC LLVM Clang 3.4 SVN -fslp-vectorize 2 4 6 8 10 SE +/- 0.01, N = 5 SE +/- 0.01, N = 5 8.86 8.86 -fslp-vectorize 1. (CXX) g++ options: -O3 -march=native -fvisibility=hidden -logg -lm
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.org Seconds, Fewer Is Better Timed HMMer Search 2.3.2 Pfam Database Search LLVM Clang 3.4 SVN -fslp-vectorize 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 27.33 27.30 -fslp-vectorize 1. (CC) gcc options: -O3 -march=native -pthread -lhmmer -lsquid -lm
Timed MAFFT Alignment OpenBenchmarking.org Seconds, Fewer Is Better Timed MAFFT Alignment 6.864 Multiple Sequence Alignment LLVM Clang 3.4 SVN -fslp-vectorize 4 8 12 16 20 SE +/- 0.25, N = 6 SE +/- 0.23, N = 5 15.42 15.44 1. (CC) gcc options: -O3 -lm -lpthread
Primesieve OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 4.2 1e12 Prime Number Generation LLVM Clang 3.4 SVN -fslp-vectorize 130 260 390 520 650 SE +/- 0.26, N = 3 SE +/- 0.14, N = 3 614.07 614.34 1. (CXX) g++ options: -O2
Timed PHP Compilation OpenBenchmarking.org Seconds, Fewer Is Better Timed PHP Compilation 5.2.9 Time To Compile LLVM Clang 3.4 SVN -fslp-vectorize 10 20 30 40 50 SE +/- 0.10, N = 3 SE +/- 0.07, N = 3 41.97 42.07 -fslp-vectorize 1. (CC) gcc options: -O3 -march=native -pedantic -ldl -lz -lm
GraphicsMagick OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.16 Operation: Blur LLVM Clang 3.4 SVN -fslp-vectorize 12 24 36 48 60 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 53 53 -fslp-vectorize 1. (CC) gcc options: -O3 -march=native -pthread -lXext -lSM -lICE -lX11 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.16 Operation: Sharpen LLVM Clang 3.4 SVN -fslp-vectorize 8 16 24 32 40 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 36 36 -fslp-vectorize 1. (CC) gcc options: -O3 -march=native -pthread -lXext -lSM -lICE -lX11 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.16 Operation: Resizing LLVM Clang 3.4 SVN -fslp-vectorize 15 30 45 60 75 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 66 66 -fslp-vectorize 1. (CC) gcc options: -O3 -march=native -pthread -lXext -lSM -lICE -lX11 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.16 Operation: HWB Color Space LLVM Clang 3.4 SVN -fslp-vectorize 20 40 60 80 100 SE +/- 0.00, N = 3 SE +/- 0.33, N = 3 80 80 -fslp-vectorize 1. (CC) gcc options: -O3 -march=native -pthread -lXext -lSM -lICE -lX11 -lxml2 -lz -lm -lpthread
OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.16 Operation: Local Adaptive Thresholding LLVM Clang 3.4 SVN -fslp-vectorize 7 14 21 28 35 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 32 32 -fslp-vectorize 1. (CC) gcc options: -O3 -march=native -pthread -lXext -lSM -lICE -lX11 -lxml2 -lz -lm -lpthread
x264 OpenBenchmarking.org Frames Per Second, More Is Better x264 2013-06-08 H.264 Video Encoding LLVM Clang 3.4 SVN -fslp-vectorize 13 26 39 52 65 SE +/- 0.14, N = 5 SE +/- 0.11, N = 5 59.63 59.83 -fslp-vectorize 1. (CC) gcc options: -ldl -m64 -lm -lpthread -O3 -ffast-math -march=native -std=gnu99 -fomit-frame-pointer -fno-tree-vectorize
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.org Seconds, Fewer Is Better C-Ray 1.1 Total Time LLVM Clang 3.4 SVN -fslp-vectorize 20 40 60 80 100 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 75.98 75.87 -fslp-vectorize 1. (CC) gcc options: -lm -lpthread -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.org Seconds, Fewer Is Better Smallpt 1.0 Global Illumination Renderer; 100 Samples LLVM Clang 3.4 SVN -fslp-vectorize 70 140 210 280 350 SE +/- 0.58, N = 3 SE +/- 0.88, N = 3 293 301 -fslp-vectorize 1. (CXX) g++ options: -fopenmp -O3 -march=native
Apache Benchmark OpenBenchmarking.org Requests Per Second, More Is Better Apache Benchmark 2.4.3 Static Web Page Serving LLVM Clang 3.4 SVN -fslp-vectorize 2K 4K 6K 8K 10K SE +/- 60.14, N = 3 SE +/- 44.32, N = 3 9830.61 9715.20 1. (CC) gcc options: -shared -fPIC -pthread -O3 -march=native
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: corei7Processor 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: corei7Processor Notes: Scaling Governor: acpi-cpufreq ondemand
Testing initiated at 29 July 2013 10:13 by user phoronix.