Skylake-AVX512 Core i9 7900X Intel Core i7-7900X testing with a MSI X299 SLI PLUS (MS-7A93) v1.0 and Sapphire AMD Radeon R9 FURY / NANO 4096MB on Ubuntu 17.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/1706289-TR-SKYLAKEAV14 .
Skylake-AVX512 Core i9 7900X Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Vulkan Compiler File-System Screen Resolution -O3 -march=skylake -O3 -march=skylake-avx512 Intel Core i7-7900X @ 4.50GHz (20 Cores) MSI X299 SLI PLUS (MS-7A93) v1.0 Intel Device 2020 16384MB 240GB Force MP500 Sapphire AMD Radeon R9 FURY / NANO 4096MB Realtek ALC1220 DELL P2415Q Intel Connection Ubuntu 17.04 4.12.0-999-generic (x86_64) 20170618 Unity 7.5.0 X Server 1.19.3 modesetting 1.19.3 4.5 Mesa 17.2.0-devel- padoka PPA Gallium 0.4 (LLVM 5.0.0) 1.0.3 GCC 7.1.0 ext4 3840x2160 OpenBenchmarking.org Compiler Details - --disable-multilib --enable-checking=release --enable-languages=c,c++ Processor Details - Scaling Governor: intel_pstate performance
Skylake-AVX512 Core i9 7900X fftw: Float + SSE - 2D FFT Size 4096 hmmer: Pfam Database Search scimark2: Composite scimark2: Monte Carlo scimark2: Fast Fourier Transform scimark2: Sparse Matrix Multiply scimark2: Dense LU Matrix Factorization scimark2: Jacobi Successive Over-Relaxation john-the-ripper: Blowfish ttsiod-renderer: Phong Rendering With Soft-Shadow Mapping x264: H.264 Video Encoding graphics-magick: Blur graphics-magick: Sharpen graphics-magick: Resizing graphics-magick: HWB Color Space graphics-magick: Local Adaptive Thresholding himeno: Poisson Pressure Solver c-ray: Total Time smallpt: Global Illumination Renderer; 100 Samples encode-flac: WAV To FLAC encode-mp3: WAV To MP3 tjbench: Decompression Throughput pgbench: Buffer Test - Normal Load - Read Write pgbench: Buffer Test - Heavy Contention - Read Write caffe: CPU AlexNet caffe: CPU Googlenet -O3 -march=skylake -O3 -march=skylake-avx512 16988 5.06 1855.63 856.66 444.89 2689.88 3994.95 1291.78 19248 552.40 523.19 231 236 280 292 115 3167.47 5.54 8 4.31 8.13 192.15 22175.88 15816.98 517708 1954897 17286 4.95 1880.17 862.36 453.19 2736.27 4055.21 1293.80 19387 533.79 517.05 223 228 272 284 115 3185.09 6.70 8 4.54 8.72 200.02 18309.53 16380.75 922641 1997873 OpenBenchmarking.org
FFTW Build: Float + SSE - Size: 2D FFT Size 4096 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.4 Build: Float + SSE - Size: 2D FFT Size 4096 -O3 -march=skylake -O3 -march=skylake-avx512 4K 8K 12K 16K 20K SE +/- 95.91, N = 5 SE +/- 42.08, N = 5 16988 17286 -march=skylake 1. (CC) gcc options: -O3 -lm
Timed HMMer Search Pfam Database Search OpenBenchmarking.org Seconds, Fewer Is Better Timed HMMer Search 2.3.2 Pfam Database Search -O3 -march=skylake -O3 -march=skylake-avx512 1.1385 2.277 3.4155 4.554 5.6925 SE +/- 0.23, N = 6 SE +/- 0.01, N = 3 5.06 4.95 -march=skylake 1. (CC) gcc options: -O3 -pthread -lhmmer -lsquid -lm
SciMark Computational Test: Composite OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Composite -O3 -march=skylake -O3 -march=skylake-avx512 400 800 1200 1600 2000 SE +/- 7.39, N = 4 SE +/- 0.79, N = 4 1855.63 1880.17 -march=skylake 1. (CC) gcc options: -O3 -lm
SciMark Computational Test: Monte Carlo OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Monte Carlo -O3 -march=skylake -O3 -march=skylake-avx512 200 400 600 800 1000 SE +/- 0.38, N = 4 SE +/- 2.29, N = 4 856.66 862.36 -march=skylake 1. (CC) gcc options: -O3 -lm
SciMark Computational Test: Fast Fourier Transform OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Fast Fourier Transform -O3 -march=skylake -O3 -march=skylake-avx512 100 200 300 400 500 SE +/- 2.69, N = 4 SE +/- 1.11, N = 4 444.89 453.19 -march=skylake 1. (CC) gcc options: -O3 -lm
SciMark Computational Test: Sparse Matrix Multiply OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Sparse Matrix Multiply -O3 -march=skylake -O3 -march=skylake-avx512 600 1200 1800 2400 3000 SE +/- 14.28, N = 4 SE +/- 5.89, N = 4 2689.88 2736.27 -march=skylake 1. (CC) gcc options: -O3 -lm
SciMark Computational Test: Dense LU Matrix Factorization OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Dense LU Matrix Factorization -O3 -march=skylake -O3 -march=skylake-avx512 900 1800 2700 3600 4500 SE +/- 21.14, N = 4 SE +/- 2.97, N = 4 3994.95 4055.21 -march=skylake 1. (CC) gcc options: -O3 -lm
SciMark Computational Test: Jacobi Successive Over-Relaxation OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Jacobi Successive Over-Relaxation -O3 -march=skylake -O3 -march=skylake-avx512 300 600 900 1200 1500 SE +/- 0.23, N = 4 SE +/- 1.62, N = 4 1291.78 1293.80 -march=skylake 1. (CC) gcc options: -O3 -lm
John The Ripper Test: Blowfish OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.8.0 Test: Blowfish -O3 -march=skylake -O3 -march=skylake-avx512 4K 8K 12K 16K 20K SE +/- 86.53, N = 3 SE +/- 189.99, N = 3 19248 19387 1. (CC) gcc options: -fopenmp -lcrypt
TTSIOD 3D Renderer Phong Rendering With Soft-Shadow Mapping OpenBenchmarking.org FPS, More Is Better TTSIOD 3D Renderer 2.3a Phong Rendering With Soft-Shadow Mapping -O3 -march=skylake -O3 -march=skylake-avx512 120 240 360 480 600 SE +/- 2.27, N = 3 SE +/- 15.20, N = 6 552.40 533.79 -march=skylake 1. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -lstdc++
x264 H.264 Video Encoding OpenBenchmarking.org Frames Per Second, More Is Better x264 2017-05-19 H.264 Video Encoding -O3 -march=skylake -O3 -march=skylake-avx512 110 220 330 440 550 SE +/- 1.40, N = 5 SE +/- 2.06, N = 5 523.19 517.05 -march=skylake 1. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fomit-frame-pointer -fno-tree-vectorize
GraphicsMagick Operation: Blur OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.19 Operation: Blur -O3 -march=skylake -O3 -march=skylake-avx512 50 100 150 200 250 SE +/- 0.33, N = 3 SE +/- 3.00, N = 3 231 223 -march=skylake 1. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -lwebp -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -ldl -lpthread
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.19 Operation: Sharpen -O3 -march=skylake -O3 -march=skylake-avx512 50 100 150 200 250 SE +/- 1.67, N = 3 236 228 -march=skylake 1. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -lwebp -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -ldl -lpthread
GraphicsMagick Operation: Resizing OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.19 Operation: Resizing -O3 -march=skylake -O3 -march=skylake-avx512 60 120 180 240 300 SE +/- 0.33, N = 3 280 272 -march=skylake 1. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -lwebp -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -ldl -lpthread
GraphicsMagick Operation: HWB Color Space OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.19 Operation: HWB Color Space -O3 -march=skylake -O3 -march=skylake-avx512 60 120 180 240 300 SE +/- 0.58, N = 3 292 284 -march=skylake 1. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -lwebp -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -ldl -lpthread
GraphicsMagick Operation: Local Adaptive Thresholding OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.19 Operation: Local Adaptive Thresholding -O3 -march=skylake -O3 -march=skylake-avx512 30 60 90 120 150 115 115 -march=skylake 1. (CC) gcc options: -fopenmp -O3 -pthread -ljbig -lwebp -ltiff -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lz -lm -ldl -lpthread
Himeno Benchmark Poisson Pressure Solver OpenBenchmarking.org MFLOPS, More Is Better Himeno Benchmark 3.0 Poisson Pressure Solver -O3 -march=skylake -O3 -march=skylake-avx512 700 1400 2100 2800 3500 SE +/- 31.38, N = 3 SE +/- 27.75, N = 3 3167.47 3185.09 -march=skylake 1. (CC) gcc options: -O3 -mavx2
C-Ray Total Time OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time -O3 -march=skylake -O3 -march=skylake-avx512 2 4 6 8 10 SE +/- 0.03, N = 3 SE +/- 0.29, N = 6 5.54 6.70 -march=skylake 1. (CC) gcc options: -lm -lpthread -O3
Smallpt Global Illumination Renderer; 100 Samples OpenBenchmarking.org Seconds, Fewer Is Better Smallpt 1.0 Global Illumination Renderer; 100 Samples -O3 -march=skylake -O3 -march=skylake-avx512 2 4 6 8 10 8 8 -march=skylake 1. (CXX) g++ options: -fopenmp -O3
FLAC Audio Encoding WAV To FLAC OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.3.1 WAV To FLAC -O3 -march=skylake -O3 -march=skylake-avx512 1.0215 2.043 3.0645 4.086 5.1075 SE +/- 0.13, N = 10 SE +/- 0.18, N = 10 4.31 4.54 -march=skylake 1. (CXX) g++ options: -O3 -fvisibility=hidden -logg -lm
LAME MP3 Encoding WAV To MP3 OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.99.3 WAV To MP3 -O3 -march=skylake -O3 -march=skylake-avx512 2 4 6 8 10 SE +/- 0.18, N = 10 SE +/- 0.21, N = 10 8.13 8.72 -march=skylake 1. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lm
libjpeg-turbo tjbench Test: Decompression Throughput OpenBenchmarking.org Megapixels/sec, More Is Better libjpeg-turbo tjbench 1.5.1 Test: Decompression Throughput -O3 -march=skylake -O3 -march=skylake-avx512 40 80 120 160 200 SE +/- 8.83, N = 6 SE +/- 0.80, N = 3 192.15 200.02 -march=skylake 1. (CC) gcc options: -O3 -lm
PostgreSQL pgbench Scaling: Buffer Test - Test: Normal Load - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 9.6.3 Scaling: Buffer Test - Test: Normal Load - Mode: Read Write -O3 -march=skylake -O3 -march=skylake-avx512 5K 10K 15K 20K 25K SE +/- 294.08, N = 3 SE +/- 2231.42, N = 6 22175.88 18309.53 -march=skylake 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -fpic -lpgcommon -lpgport -lrt -lcrypt -ldl -lm
PostgreSQL pgbench Scaling: Buffer Test - Test: Heavy Contention - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 9.6.3 Scaling: Buffer Test - Test: Heavy Contention - Mode: Read Write -O3 -march=skylake -O3 -march=skylake-avx512 4K 8K 12K 16K 20K SE +/- 2394.39, N = 6 SE +/- 2071.14, N = 6 15816.98 16380.75 -march=skylake 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O3 -fpic -lpgcommon -lpgport -lrt -lcrypt -ldl -lm
Caffe Build: CPU AlexNet OpenBenchmarking.org Milli-Seconds, Fewer Is Better Caffe 2016-12-29 Build: CPU AlexNet -O3 -march=skylake -O3 -march=skylake-avx512 200K 400K 600K 800K 1000K SE +/- 734.98, N = 3 SE +/- 1440.13, N = 3 517708 922641 1. (CXX) g++ options: -pthread -fPIC -O2 -lcaffe -lglog -lgflags -lprotobuf -lboost_system -lboost_filesystem -lm -lhdf5_hl -lhdf5 -lleveldb -lsnappy -llmdb -lopencv_core -lopencv_highgui -lopencv_imgproc -lboost_thread -lstdc++ -lcblas -latlas
Caffe Build: CPU Googlenet OpenBenchmarking.org Milli-Seconds, Fewer Is Better Caffe 2016-12-29 Build: CPU Googlenet -O3 -march=skylake -O3 -march=skylake-avx512 400K 800K 1200K 1600K 2000K SE +/- 1368.41, N = 3 SE +/- 3437.71, N = 3 1954897 1997873 1. (CXX) g++ options: -pthread -fPIC -O2 -lcaffe -lglog -lgflags -lprotobuf -lboost_system -lboost_filesystem -lm -lhdf5_hl -lhdf5 -lleveldb -lsnappy -llmdb -lopencv_core -lopencv_highgui -lopencv_imgproc -lboost_thread -lstdc++ -lcblas -latlas
Phoronix Test Suite v10.8.4