threadripper-3960x-reference AMD Ryzen Threadripper 3960X 24-Core testing with a MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS) and AMD Navi 10 8GB on Ubuntu 19.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/1911259-HU-THREADRIP53&sro&grr .
threadripper-3960x-reference Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution Threadripper 3960X AMD Ryzen Threadripper 3960X 24-Core AMD Ryzen Threadripper 3960X 24-Core @ 3.80GHz (24 Cores / 48 Threads) MSI Creator TRX40 (MS-7C59) v1.0 (1.12N1 BIOS) AMD Starship/Matisse 32768MB 240GB Force MP510 AMD Navi 10 8GB (2100/875MHz) AMD Navi 10 HDMI Audio ASUS PB278 Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Device 2723 Ubuntu 19.10 5.3.0-23-generic (x86_64) GNOME Shell 3.34.1 X Server 1.20.5 modesetting 1.20.5 4.5 Mesa 19.2.1 (LLVM 9.0.0) GCC 9.2.1 20191008 ext4 2560x1440 OpenBenchmarking.org Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-checking=release --enable-clocale=gnu --enable-default-pie --enable-gnu-unique-object --enable-languages=c,ada,c++,go,brig,d,fortran,objc,obj-c++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-offload-targets=nvptx-none,hsa --enable-plugin --enable-shared --enable-threads=posix --host=x86_64-linux-gnu --program-prefix=x86_64-linux-gnu- --target=x86_64-linux-gnu --with-abi=m64 --with-arch-32=i686 --with-default-libstdcxx-abi=new --with-gcc-major-version-only --with-multilib-list=m32,m64,mx32 --with-target-system-zlib=auto --with-tune=generic --without-cuda-driver -v Disk Details - Threadripper 3960X: NONE / errors=remount-ro,relatime,rw Processor Details - Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025 Java Details - OpenJDK Runtime Environment (build 11.0.5-ea+10-post-Ubuntu-0ubuntu1) Python Details - Python 2.7.17rc1 + Python 3.7.5rc1 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + tsx_async_abort: Not affected
threadripper-3960x-reference pennant: sedovbig pennant: leblancbig spec-jbb2015: SPECjbb2015-Composite critical-jOPS spec-jbb2015: SPECjbb2015-Composite max-jOPS hpcc: G-HPL cassandra: Mixed 1:3 cpp-perf-bench: Rand Numbers cassandra: Mixed 1:1 qmcpack: mkl-dnn: Convolution Batch conv_all - f32 build-gcc: Time To Compile libgav1: Chimera 1080p 10-bit cassandra: Reads mkl-dnn: Deconvolution Batch deconv_all - f32 pgbench: Buffer Test - Normal Load - Read Write fftw: Float + SSE - 2D FFT Size 4096 svt-av1: Enc Mode 0 - 1080p cpp-perf-bench: Math Library luxcorerender: Rainbow Colors and Prism blender: Barbershop - CPU-Only brl-cad: VGR Performance Metric compress-lzma: 256MB File Compression tinymembench: Standard Memset tinymembench: Standard Memcpy renaissance: Savina Reactors.IO blender: Pabellon Barcelona - CPU-Only radiance: Serial selenium: Jetstream - Firefox libgav1: Chimera 1080p selenium: Jetstream - Google Chrome apache-siege: 250 fftw: Stock - 2D FFT Size 4096 dav1d: Chimera 1080p 10-bit libgav1: Summer Nature 4K selenium: ARES-6 - Firefox blender: Classroom - CPU-Only stress-ng: Context Switching apache-siege: 200 cp2k: Fayalite-FIST Data asmfish: 1024 Hash Memory, 26 Depth mkl-dnn: Convolution Batch conv_googlenet_v3 - f32 cachebench: Read / Modify / Write cachebench: Write cachebench: Read byte: Dhrystone 2 ospray: San Miguel - SciVis memtier-benchmark: Redis appleseed: Emily cassandra: Writes minion: Quasigroup selenium: StyleBench - Google Chrome ospray: San Miguel - Path Tracer appleseed: Material Tester renaissance: Apache Spark Bayes ospray: NASA Streamlines - Path Tracer vpxenc: vpxenc VP9 1080p Video Encode blender: Fishy Cat - CPU-Only selenium: Speedometer - Firefox pgbench: Buffer Test - Normal Load - Read Only npb: SP.B gromacs: Water Benchmark cpp-perf-bench: Stepanov Vector askap: tConvolve MT - Degridding askap: tConvolve MT - Gridding fftw: Float + SSE - 2D FFT Size 2048 mrbayes: Primate Phylogeny Analysis v-ray: CPU opencv-bench: selenium: StyleBench - Firefox selenium: Speedometer - Google Chrome npb: EP.D rocksdb: Seq Fill indigobench: Bedroom luxcorerender: DLSC sqlite: 8 indigobench: Supercar minion: Solitaire ospray: XFrog Forest - Path Tracer rocksdb: Read While Writing graphics-magick: Resizing rocksdb: Rand Read graphics-magick: Noise-Gaussian graphics-magick: Sharpen graphics-magick: Enhanced graphics-magick: Rotate graphics-magick: Swirl graphics-magick: HWB Color Space blender: BMW27 - CPU-Only cpp-perf-bench: Atol sqlite-speedtest: Timed Time - Size 1,000 himeno: Poisson Pressure Solver appleseed: Disney Material radiance: SMP Parallel renaissance: Apache Spark PageRank nginx: Static Web Page Serving askap: tConvolve MPI - Degridding askap: tConvolve MPI - Gridding npb: BT.C libreoffice: 20 Documents To PDF build2: Time To Compile octave-benchmark: redis: SET redis: GET stockfish: Total Time libgav1: Summer Nature 1080p parboil: OpenMP MRI Gridding namd: ATPase Simulation - 327,506 Atoms selenium: ARES-6 - Google Chrome build-llvm: Time To Compile mkl-dnn: IP Batch All - f32 selenium: Octane - Firefox java-scimark2: Composite hackbench: 32 - Process lczero: BLAS ospray: XFrog Forest - SciVis rav1e: 1080p To AV1 Video Encode selenium: Octane - Google Chrome minion: Graceful npb: LU.C build-php: Time To Compile dcraw: RAW To PPM Image Conversion mkl-dnn: Convolution Batch conv_3d - f32 stream: Copy fftw: Stock - 2D FFT Size 2048 build-linux-kernel: Time To Compile compress-7zip: Compress Speed Test mbw: Memory Copy, Fixed Block Size - 4096 MiB mkl-dnn: Recurrent Neural Network Training - f32 renaissance: Akka Unbalanced Cobwebbed Tree minife: Small renaissance: In-Memory Database Shootout embree: Pathtracer ISPC - Asian Dragon Obj compress-gzip: Linux Source Tree Archiving To .tar.gz embree: Pathtracer - Asian Dragon Obj rust-mandel: Time To Complete Serial/Parallel Mandelbrot cpp-perf-bench: Ctype ttsiod-renderer: Phong Rendering With Soft-Shadow Mapping mkl-dnn: IP Batch 1D - f32 glibc-bench: exp stress-ng: CPU Stress stress-ng: Tsearch stress-ng: Crypto stress-ng: Vector Math stress-ng: System V Message Passing stress-ng: Semaphores stress-ng: Lsearch stress-ng: Bsearch stress-ng: Glibc C String Functions stress-ng: Memory Copying stress-ng: Hsearch stress-ng: Forking stress-ng: Matrix Math stress-ng: Glibc Qsort Data Sorting stress-ng: Socket Activity apache: Static Web Page Serving cpp-perf-bench: Stepanov Abstraction espeak: Text-To-Speech Synthesis mt-dgemm: Sustained Floating-Point Rate renaissance: Apache Spark ALS scimark2: Composite ospray: NASA Streamlines - SciVis coremark: CoreMark Size 666 - Iterations Per Second tesseract-ocr: Time To OCR 7 Images npb: FT.C m-queens: Time To Solve hackbench: 16 - Thread tensorflow: Cifar10 fftw: Float + SSE - 2D FFT Size 1024 hackbench: 16 - Process mbw: Memory Copy - 4096 MiB pybench: Total For Average Test Times embree: Pathtracer ISPC - Crown crafty: Elapsed Time c-ray: Total Time - 4K, 16 Rays Per Pixel mkl-dnn: Deconvolution Batch deconv_1d - f32 embree: Pathtracer - Crown tungsten: Water Caustic gimp: unsharp-mask compress-xz: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9 glibc-bench: cos glibc-bench: sincos glibc-bench: sin ebizzy: fftw: Float + SSE - 1D FFT Size 256 embree: Pathtracer - Asian Dragon embree: Pathtracer ISPC - Asian Dragon go-benchmark: build selenium: PSPDFKit WASM - Firefox dav1d: Chimera 1080p povray: Trace Time tungsten: Non-Exponential selenium: PSPDFKit WASM - Google Chrome selenium: Maze Solver - Firefox paraview: Many Spheres - 2560 x 1440 paraview: Many Spheres - 2560 x 1440 gimp: auto-levels ramspeed: Triad - Floating Point mkl-dnn: Convolution Batch conv_alexnet - f32 ramspeed: Average - Integer sqlite: 1 phpbench: PHP Benchmark Suite ramspeed: Copy - Floating Point rust-prime: Prime Number Test To 200,000,000 cpp-perf-bench: Function Objects build-imagemagick: Time To Compile ramspeed: Scale - Floating Point ramspeed: Add - Floating Point ramspeed: Average - Floating Point ramspeed: Add - Integer ramspeed: Scale - Integer ramspeed: Triad - Integer ramspeed: Copy - Integer fftw: Float + SSE - 1D FFT Size 64 fftw: Stock - 1D FFT Size 64 selenium: Maze Solver - Google Chrome compress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 encode-flac: WAV To FLAC hackbench: 1 - Process xsbench: dav1d: Summer Nature 4K gimp: rotate dacapobench: Tradebeans go-benchmark: json hackbench: 8 - Thread svt-av1: Enc Mode 4 - 1080p hackbench: 8 - Process askap: tConvolve OpenMP - Degridding askap: tConvolve OpenMP - Gridding dacapobench: Tradesoap lczero: Rand encode-opus: WAV, Opus Encode, Opus Decode glibc-bench: asinh glibc-bench: sinh glibc-bench: log2 glibc-bench: ffsll glibc-bench: tanh glibc-bench: atanh glibc-bench: sqrt glibc-bench: modf glibc-bench: ffs glibc-bench: pthread_once rodinia: OpenMP LavaMD tungsten: Hair fftw: Stock - 2D FFT Size 1024 dacapobench: H2 go-benchmark: http mbw: Memory Copy, Fixed Block Size - 1024 MiB ospray: Magnetic Reconnection - SciVis x265: H.265 1080p Video Encoding rodinia: OpenMP CFD Solver neatbench: CPU svt-vp9: VMAF Optimized - Bosphorus 1080p parboil: OpenMP Stencil gimp: resize go-benchmark: garbage bork: File Encryption Time npb: MG.C sunflow: Global Illumination + Image Synthesis encode-mp3: WAV To MP3 dacapobench: Jython darktable: Boat - CPU-only fftw: Float + SSE - 2D FFT Size 512 fftw: Float + SSE - 1D FFT Size 4096 ospray: Magnetic Reconnection - Path Tracer hackbench: 4 - Thread mbw: Memory Copy - 1024 MiB hackbench: 4 - Process osbench: Create Files dav1d: Summer Nature 1080p oidn: Memorial svt-av1: Enc Mode 8 - 1080p fftw: Float + SSE - 1D FFT Size 2048 osbench: Memory Allocations osbench: Create Processes osbench: Launch Programs osbench: Create Threads paraview: Wavelet Contour - 2560 x 1440 paraview: Wavelet Contour - 2560 x 1440 git: Time To Complete Common Git Commands mbw: Memory Copy, Fixed Block Size - 512 MiB fftw: Stock - 1D FFT Size 4096 fftw: Stock - 2D FFT Size 256 fftw: Float + SSE - 2D FFT Size 256 n-queens: Elapsed Time npb: EP.C tungsten: Volumetric Caustic darktable: Masskrug - CPU-only fftw: Float + SSE - 1D FFT Size 1024 fftw: Stock - 1D FFT Size 256 fftw: Stock - 2D FFT Size 32 bullet: Raytests fftw: Stock - 2D FFT Size 512 fftw: Float + SSE - 1D FFT Size 32 fftw: Float + SSE - 2D FFT Size 32 fftw: Float + SSE - 1D FFT Size 512 fftw: Stock - 1D FFT Size 32 hackbench: 2 - Thread fftw: Stock - 1D FFT Size 2048 smallpt: Global Illumination Renderer; 128 Samples fftw: Stock - 2D FFT Size 128 darktable: Server Rack - CPU-only fftw: Stock - 1D FFT Size 128 hackbench: 2 - Process darktable: Server Room - CPU-only x264: H.264 Video Encoding optcarrot: Optimized Benchmark mkl-dnn: Deconvolution Batch deconv_3d - f32 fftw: Float + SSE - 2D FFT Size 128 fftw: Stock - 1D FFT Size 1024 hackbench: 1 - Thread mbw: Memory Copy - 512 MiB fftw: Stock - 2D FFT Size 64 fftw: Stock - 1D FFT Size 512 fftw: Float + SSE - 1D FFT Size 128 fftw: Float + SSE - 2D FFT Size 64 svt-vp9: Visual Quality Optimized - Bosphorus 1080p ffte: N=256, 1D Complex FFT Routine tscp: AI Chess Performance svt-vp9: PSNR/SSIM Optimized - Bosphorus 1080p paraview: Wavelet Volume - 2560 x 1440 paraview: Wavelet Volume - 2560 x 1440 tachyon: Total Time parboil: OpenMP CUTCP mbw: Memory Copy, Fixed Block Size - 128 MiB mbw: Memory Copy - 128 MiB cloverleaf: Lagrangian-Eulerian Hydrodynamics ctx-clock: Context Switch Time bullet: Convex Trimesh bullet: Prim Trimesh bullet: 136 Ragdolls bullet: 1000 Convex bullet: 1000 Stack bullet: 3000 Fall hpcc: Max Ping Pong Bandwidth hpcc: Rand Ring Bandwidth hpcc: Rand Ring Latency hpcc: G-Rand Access hpcc: EP-STREAM Triad hpcc: G-Ptrans hpcc: EP-DGEMM hpcc: G-Ffte hpcc: G-Ffte stream: Add stream: Triad stream: Scale Threadripper 3960X AMD Ryzen Threadripper 3960X 24-Core 6502.564 6305.170 60.46073 171 1105.427 497 1875.8 1070.54 598.912 20.46 30078 1772.78 13768.050779 22314 0.064 270.690 2.29 237.55 393502 226.235 17756.9 10538.0 14138.775 191.48 558.724 217.57 49.67 217.50 6784.1 87.19 22.99 50.67 150.89 15705353.86 419.693 75540266 57.2830 61655.494100270 32059.699295746 3063.54 45423513.1 38.46 2912967.74 160.60522 230619 107.180494 36.6 2.88 136.804986 3355.907 10.75 201.36 84.00 97.1 662564.296528 23242.08 2.486 76.647 34104 71.133 39404 64.118 79.0 133 2214.27 1030368 3.926 2.79 61.410 8.104 60.510068 3.72 4877714 2263 143688270 565 379 569 710 1351 1462 57.99 57.761 58.430 4748.293606 87.464249 172.079 17245.119 36127.85 52747.62 6.788 54.083 13.306 1834121.40 2649622.70 75434528 74.29 49.067796 0.72235 19.97 141.557 16.7995 36739 3033.26 44.561 32.7349 7.08 1.369 47433 41.781302 51711.88 39.644 39.498 6.84735 33465.1 7864.3 28.538 150915 11493.070 226.819 12584.856 7790.67 6759.032 27.7394 33.754 28.7858 33.088 780.044 2.81769 4.84041 9167.11 964.42 7072.93 67241.37 23627101.30 3239494.25 357.06 16332.26 2449871.83 12234.52 199421.45 80851.06 151388.05 380.73 18734.34 34193.15 28.304 27.811 8.543887 6643.079 714.92 52.63 1069837.228639 24.136 17832.39 23.281 22.955 40897 22.737 19697.475 968 28.3694 9041729 21.059 2.59611 29.7673 19.3355 20.511 20.357 42.0206 12.1370 41.4168 38260 32.1520 32.1513 19291013759 1324 587.81 16.410 3.56422 1508 4.4 5900.232 58.85 17.125 37623.85 142.227 36961.63 15.738 658408 35940.89 14.677 14.539 37097.99 43043.84 40240.98 43028.44 38106.38 43894.26 37204.25 18900 9362.2 4.0 10.227 7.834 2.762 5029528 291.09 12.316 4643 1901078 11.666 8.043 11.146 3364 106908 6.272 8.42052 7.82634 5.83717 1.75307 10.5197 10.0172 2.16235 2.21984 1.75927 1.74395 10.103 9.79737 8097.9 3694 8619 11380.322 25 65.71 9.037 382.22 7.243440 8.609 702500 8.018 25120.08 0.685 7.117 3963 6.279 43049 58875 333.33 6.032 19435.382 5.468 11.538926 677.06 19.59 78.792 61112 70.596059 41.036606 48.146248 20.843347 2578.928 247.47 4.765 11306.184 8818.8 8674.1 42616 4.469 2208.11 4.15646 3.402 59937 8883.8 11113 2.114348 8684.6 15042 46123 51240 11237 3.736 9048.1 3.675 8902.3 0.130 8569.2 3.529 2.242 193.76 106.88 2.86390 46970 9356.2 2.858 19400.432 9585.4 9114.0 27460 47733 326.41 9627.34 1341412 392.87 2811.522 175.72 1.6899 1.264657 10863.421 10893.678 0.82 152 0.955188 0.798775 2.181623 3.81367 4.110941 3.416941 22107.913 3.36400 0.45683 0.14292 1.82228 5.54022 31.63690 10.73077 10.73077 36666.4 36725.1 33514.6 26415 52659 1103.853 271.787 57247.27 55723.63 76.767 3307.00 1911.41 59.302 3311.01 1865.03 33.3915 32.698 31.869 28.312 17.04 2254196 16.360 14.999 14.693 3915.53 4617.47 106669 35.3 19.75 OpenBenchmarking.org
Pennant Test: sedovbig OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: sedovbig Threadripper 3960X 1400 2800 4200 5600 7000 SE +/- 2.00, N = 3 6502.56 1. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi
Pennant Test: leblancbig OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: leblancbig Threadripper 3960X 1400 2800 4200 5600 7000 SE +/- 12.26, N = 3 6305.17 1. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi
SPECjbb 2015 SPECjbb2015-Composite critical-jOPS OpenBenchmarking.org jOPS, More Is Better SPECjbb 2015 SPECjbb2015-Composite critical-jOPS AMD Ryzen Threadripper 3960X 24-Core 6K 12K 18K 24K 30K 26415
SPECjbb 2015 SPECjbb2015-Composite max-jOPS OpenBenchmarking.org jOPS, More Is Better SPECjbb 2015 SPECjbb2015-Composite max-jOPS AMD Ryzen Threadripper 3960X 24-Core 11K 22K 33K 44K 55K 52659
HPC Challenge Test / Class: G-HPL OpenBenchmarking.org GFLOPS, More Is Better HPC Challenge 1.5.0 Test / Class: G-HPL Threadripper 3960X 14 28 42 56 70 SE +/- 0.16, N = 3 60.46 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
Apache Cassandra Test: Mixed 1:3 OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 3.11.4 Test: Mixed 1:3 Threadripper 3960X 40 80 120 160 200 SE +/- 5.83, N = 7 171
CppPerformanceBenchmarks Test: Random Numbers OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Random Numbers AMD Ryzen Threadripper 3960X 24-Core Threadripper 3960X 200 400 600 800 1000 SE +/- 1.36, N = 3 SE +/- 0.65, N = 3 1103.85 1105.43 1. (CXX) g++ options: -std=c++11 -O3
Apache Cassandra Test: Mixed 1:1 OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 3.11.4 Test: Mixed 1:1 Threadripper 3960X 110 220 330 440 550 SE +/- 77.62, N = 7 497
QMCPACK OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.8 Threadripper 3960X 400 800 1200 1600 2000 1875.8 1. (CXX) g++ options: -fopenmp -fomit-frame-pointer -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -march=native -O3 -ffast-math -lm
MKL-DNN DNNL Harness: Convolution Batch conv_all - Data Type: f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_all - Data Type: f32 Threadripper 3960X 200 400 600 800 1000 SE +/- 2.64, N = 3 1070.54 MIN: 997.44 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
Timed GCC Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed GCC Compilation 8.2 Time To Compile Threadripper 3960X 130 260 390 520 650 SE +/- 1.15, N = 3 598.91
libgav1 Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS, More Is Better libgav1 2019-10-05 Video Input: Chimera 1080p 10-bit Threadripper 3960X 5 10 15 20 25 SE +/- 0.11, N = 3 20.46 1. (CXX) g++ options: -O3 -lpthread
Apache Cassandra Test: Reads OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 3.11.4 Test: Reads Threadripper 3960X 6K 12K 18K 24K 30K SE +/- 12892.81, N = 9 30078
MKL-DNN DNNL Harness: Deconvolution Batch deconv_all - Data Type: f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_all - Data Type: f32 Threadripper 3960X 400 800 1200 1600 2000 SE +/- 6.22, N = 3 1772.78 MIN: 1677 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
PostgreSQL pgbench Scaling: Buffer Test - Test: Normal Load - Mode: Read Write OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Normal Load - Mode: Read Write Threadripper 3960X 3K 6K 9K 12K 15K SE +/- 1254.90, N = 12 13768.05 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
FFTW Build: Float + SSE - Size: 2D FFT Size 4096 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 4096 Threadripper 3960X 5K 10K 15K 20K 25K SE +/- 60.75, N = 3 22314 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
SVT-AV1 Encoder Mode: Enc Mode 0 - Input: 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.7 Encoder Mode: Enc Mode 0 - Input: 1080p Threadripper 3960X 0.0144 0.0288 0.0432 0.0576 0.072 SE +/- 0.000, N = 3 0.064 1. (CXX) g++ options: -fPIE -fPIC -pie
CppPerformanceBenchmarks Test: Math Library OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Math Library AMD Ryzen Threadripper 3960X 24-Core Threadripper 3960X 60 120 180 240 300 SE +/- 0.18, N = 3 SE +/- 2.14, N = 3 271.79 270.69 1. (CXX) g++ options: -std=c++11 -O3
LuxCoreRender Scene: Rainbow Colors and Prism OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.2 Scene: Rainbow Colors and Prism Threadripper 3960X 0.5153 1.0306 1.5459 2.0612 2.5765 SE +/- 0.15, N = 12 2.29 MIN: 1.36 / MAX: 2.94
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.81 Blend File: Barbershop - Compute: CPU-Only Threadripper 3960X 50 100 150 200 250 SE +/- 0.15, N = 3 237.55
BRL-CAD VGR Performance Metric OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.28.0 VGR Performance Metric Threadripper 3960X 80K 160K 240K 320K 400K 393502 1. (CXX) g++ options: -std=c++98 -pipe -fno-strict-aliasing -fno-common -fexceptions -ftemplate-depth-128 -m64 -ggdb3 -O3 -fipa-pta -fstrength-reduce -finline-functions -flto -pedantic -rdynamic -lSM -lICE -lXi -lGLU -lGL -lX11 -lXext -lXrender -lpthread -ldl -luuid -lm
LZMA Compression 256MB File Compression OpenBenchmarking.org Seconds, Fewer Is Better LZMA Compression 256MB File Compression Threadripper 3960X 50 100 150 200 250 SE +/- 0.29, N = 3 226.24 1. (CXX) g++ options: -O2
Tinymembench Standard Memset OpenBenchmarking.org MB/s, More Is Better Tinymembench 2018-05-28 Standard Memset Threadripper 3960X 4K 8K 12K 16K 20K SE +/- 18.62, N = 3 17756.9 1. (CC) gcc options: -O2 -lm
Tinymembench Standard Memcpy OpenBenchmarking.org MB/s, More Is Better Tinymembench 2018-05-28 Standard Memcpy Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 165.90, N = 3 10538.0 1. (CC) gcc options: -O2 -lm
Renaissance Test: Savina Reactors.IO OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.9.0 Test: Savina Reactors.IO Threadripper 3960X 3K 6K 9K 12K 15K SE +/- 209.59, N = 40 14138.78
Blender Blend File: Pabellon Barcelona - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.81 Blend File: Pabellon Barcelona - Compute: CPU-Only Threadripper 3960X 40 80 120 160 200 SE +/- 0.19, N = 3 191.48
Radiance Benchmark Test: Serial OpenBenchmarking.org Seconds, Fewer Is Better Radiance Benchmark 5.0 Test: Serial Threadripper 3960X 120 240 360 480 600 558.72
Selenium Benchmark: Jetstream - Browser: Firefox OpenBenchmarking.org Score, More Is Better Selenium Benchmark: Jetstream - Browser: Firefox Threadripper 3960X 50 100 150 200 250 SE +/- 0.36, N = 3 217.57 1. firefox 70.0.1
libgav1 Video Input: Chimera 1080p OpenBenchmarking.org FPS, More Is Better libgav1 2019-10-05 Video Input: Chimera 1080p Threadripper 3960X 11 22 33 44 55 SE +/- 0.18, N = 3 49.67 1. (CXX) g++ options: -O3 -lpthread
Selenium Benchmark: Jetstream - Browser: Google Chrome OpenBenchmarking.org Score, More Is Better Selenium Benchmark: Jetstream - Browser: Google Chrome Threadripper 3960X 50 100 150 200 250 SE +/- 0.77, N = 3 217.50 1. chrome 78.0.3904.108
Apache Siege Concurrent Users: 250 OpenBenchmarking.org Transactions Per Second, More Is Better Apache Siege 2.4.29 Concurrent Users: 250 AMD Ryzen Threadripper 3960X 24-Core 12K 24K 36K 48K 60K SE +/- 2486.04, N = 12 57247.27 1. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
FFTW Build: Stock - Size: 2D FFT Size 4096 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 4096 Threadripper 3960X 1500 3000 4500 6000 7500 SE +/- 8.75, N = 3 6784.1 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
dav1d Video Input: Chimera 1080p 10-bit OpenBenchmarking.org FPS, More Is Better dav1d 0.5.0 Video Input: Chimera 1080p 10-bit Threadripper 3960X 20 40 60 80 100 SE +/- 0.14, N = 3 87.19 MIN: 54.26 / MAX: 180.02 1. (CC) gcc options: -pthread
libgav1 Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better libgav1 2019-10-05 Video Input: Summer Nature 4K Threadripper 3960X 6 12 18 24 30 SE +/- 0.05, N = 3 22.99 1. (CXX) g++ options: -O3 -lpthread
Selenium Benchmark: ARES-6 - Browser: Firefox OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: ARES-6 - Browser: Firefox Threadripper 3960X 11 22 33 44 55 SE +/- 0.41, N = 3 50.67 1. firefox 70.0.1
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.81 Blend File: Classroom - Compute: CPU-Only Threadripper 3960X 30 60 90 120 150 SE +/- 0.20, N = 3 150.89
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Context Switching Threadripper 3960X 3M 6M 9M 12M 15M SE +/- 214670.64, N = 15 15705353.86 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
Apache Siege Concurrent Users: 200 OpenBenchmarking.org Transactions Per Second, More Is Better Apache Siege 2.4.29 Concurrent Users: 200 AMD Ryzen Threadripper 3960X 24-Core 12K 24K 36K 48K 60K SE +/- 2566.16, N = 12 55723.63 1. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
CP2K Molecular Dynamics Fayalite-FIST Data OpenBenchmarking.org Seconds, Fewer Is Better CP2K Molecular Dynamics 6.1 Fayalite-FIST Data Threadripper 3960X 90 180 270 360 450 419.69
asmFish 1024 Hash Memory, 26 Depth OpenBenchmarking.org Nodes/second, More Is Better asmFish 2018-07-23 1024 Hash Memory, 26 Depth Threadripper 3960X 16M 32M 48M 64M 80M SE +/- 575831.34, N = 3 75540266
MKL-DNN DNNL Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_googlenet_v3 - Data Type: f32 Threadripper 3960X 13 26 39 52 65 SE +/- 0.28, N = 3 57.28 MIN: 51.08 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
CacheBench Test: Read / Modify / Write OpenBenchmarking.org MB/s, More Is Better CacheBench Test: Read / Modify / Write Threadripper 3960X 13K 26K 39K 52K 65K SE +/- 95.04, N = 3 61655.49 MIN: 55797.19 / MAX: 66291.68 1. (CC) gcc options: -lrt
CacheBench Test: Write OpenBenchmarking.org MB/s, More Is Better CacheBench Test: Write Threadripper 3960X 7K 14K 21K 28K 35K SE +/- 55.58, N = 3 32059.70 MIN: 28046.66 / MAX: 33459.4 1. (CC) gcc options: -lrt
CacheBench Test: Read OpenBenchmarking.org MB/s, More Is Better CacheBench Test: Read Threadripper 3960X 700 1400 2100 2800 3500 SE +/- 3.47, N = 3 3063.54 MIN: 3047.77 / MAX: 3069.92 1. (CC) gcc options: -lrt
BYTE Unix Benchmark Computational Test: Dhrystone 2 OpenBenchmarking.org LPS, More Is Better BYTE Unix Benchmark 3.6 Computational Test: Dhrystone 2 Threadripper 3960X 10M 20M 30M 40M 50M SE +/- 405676.33, N = 3 45423513.1
OSPray Demo: San Miguel - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: SciVis Threadripper 3960X 9 18 27 36 45 SE +/- 0.00, N = 12 38.46 MIN: 35.71 / MAX: 40
Memtier_benchmark Protocol: Redis OpenBenchmarking.org Ops/sec, More Is Better Memtier_benchmark 1.2.17 Protocol: Redis Threadripper 3960X 600K 1200K 1800K 2400K 3000K SE +/- 26919.58, N = 3 2912967.74 1. (CXX) g++ options: -O2 -levent -lpthread -lz -lpcre
Appleseed Scene: Emily OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Emily Threadripper 3960X 40 80 120 160 200 160.61
Apache Cassandra Test: Writes OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 3.11.4 Test: Writes Threadripper 3960X 50K 100K 150K 200K 250K SE +/- 3283.40, N = 4 230619
Minion Benchmark: Quasigroup OpenBenchmarking.org Seconds, Fewer Is Better Minion 1.8 Benchmark: Quasigroup Threadripper 3960X 20 40 60 80 100 SE +/- 0.62, N = 3 107.18 1. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic
Selenium Benchmark: StyleBench - Browser: Google Chrome OpenBenchmarking.org Runs / Minute, More Is Better Selenium Benchmark: StyleBench - Browser: Google Chrome Threadripper 3960X 8 16 24 32 40 SE +/- 0.09, N = 3 36.6 1. chrome 78.0.3904.108
OSPray Demo: San Miguel - Renderer: Path Tracer OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: Path Tracer Threadripper 3960X 0.648 1.296 1.944 2.592 3.24 SE +/- 0.00, N = 3 2.88 MIN: 2.87 / MAX: 2.92
Appleseed Scene: Material Tester OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Material Tester Threadripper 3960X 30 60 90 120 150 136.80
Renaissance Test: Apache Spark Bayes OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.9.0 Test: Apache Spark Bayes Threadripper 3960X 700 1400 2100 2800 3500 SE +/- 30.14, N = 40 3355.91
OSPray Demo: NASA Streamlines - Renderer: Path Tracer OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: NASA Streamlines - Renderer: Path Tracer Threadripper 3960X 3 6 9 12 15 SE +/- 0.00, N = 12 10.75 MIN: 10.53 / MAX: 10.99
VP9 libvpx Encoding vpxenc VP9 1080p Video Encode OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.8.1 vpxenc VP9 1080p Video Encode Threadripper 3960X 40 80 120 160 200 SE +/- 0.93, N = 3 201.36 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.81 Blend File: Fishy Cat - Compute: CPU-Only Threadripper 3960X 20 40 60 80 100 SE +/- 0.11, N = 3 84.00
Selenium Benchmark: Speedometer - Browser: Firefox OpenBenchmarking.org Runs Per Minute, More Is Better Selenium Benchmark: Speedometer - Browser: Firefox Threadripper 3960X 20 40 60 80 100 SE +/- 0.27, N = 3 97.1 1. firefox 70.0.1
PostgreSQL pgbench Scaling: Buffer Test - Test: Normal Load - Mode: Read Only OpenBenchmarking.org TPS, More Is Better PostgreSQL pgbench 12.0 Scaling: Buffer Test - Test: Normal Load - Mode: Read Only Threadripper 3960X 140K 280K 420K 560K 700K SE +/- 1102.78, N = 3 662564.30 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
NAS Parallel Benchmarks Test / Class: SP.B OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: SP.B Threadripper 3960X 5K 10K 15K 20K 25K SE +/- 269.46, N = 15 23242.08 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
GROMACS Water Benchmark OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2019.4 Water Benchmark Threadripper 3960X 0.5594 1.1188 1.6782 2.2376 2.797 SE +/- 0.004, N = 3 2.486 1. (CXX) g++ options: -mavx2 -mfma -std=c++11 -O3 -funroll-all-loops -pthread -lrt -lpthread -lm
CppPerformanceBenchmarks Test: Stepanov Vector OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Stepanov Vector AMD Ryzen Threadripper 3960X 24-Core Threadripper 3960X 20 40 60 80 100 SE +/- 0.16, N = 3 SE +/- 0.17, N = 3 76.77 76.65 1. (CXX) g++ options: -std=c++11 -O3
ASKAP Test: tConvolve MT - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MT - Degridding AMD Ryzen Threadripper 3960X 24-Core 700 1400 2100 2800 3500 SE +/- 8.26, N = 3 3307.00 1. (CXX) g++ options: -lpthread
ASKAP Test: tConvolve MT - Gridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MT - Gridding AMD Ryzen Threadripper 3960X 24-Core 400 800 1200 1600 2000 SE +/- 9.48, N = 3 1911.41 1. (CXX) g++ options: -lpthread
FFTW Build: Float + SSE - Size: 2D FFT Size 2048 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 2048 Threadripper 3960X 7K 14K 21K 28K 35K SE +/- 375.01, N = 3 34104 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
Timed MrBayes Analysis Primate Phylogeny Analysis OpenBenchmarking.org Seconds, Fewer Is Better Timed MrBayes Analysis 3.2.7 Primate Phylogeny Analysis Threadripper 3960X 16 32 48 64 80 SE +/- 0.28, N = 3 71.13 1. (CC) gcc options: -mmmx -msse -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -msha -maes -mavx -mfma -mavx2 -mrdrnd -mbmi -mbmi2 -madx -mabm -O3 -std=c99 -pedantic -lm
Chaos Group V-RAY Mode: CPU OpenBenchmarking.org Ksamples, More Is Better Chaos Group V-RAY 4.10.03 Mode: CPU Threadripper 3960X 8K 16K 24K 32K 40K SE +/- 88.94, N = 3 39404
OpenCV Benchmark OpenBenchmarking.org Seconds, Fewer Is Better OpenCV Benchmark 3.3.0 Threadripper 3960X 14 28 42 56 70 SE +/- 0.13, N = 3 64.12 1. (CXX) g++ options: -std=c++11 -rdynamic
Selenium Benchmark: StyleBench - Browser: Firefox OpenBenchmarking.org Runs / Minute, More Is Better Selenium Benchmark: StyleBench - Browser: Firefox Threadripper 3960X 20 40 60 80 100 SE +/- 0.32, N = 3 79.0 1. firefox 70.0.1
Selenium Benchmark: Speedometer - Browser: Google Chrome OpenBenchmarking.org Runs Per Minute, More Is Better Selenium Benchmark: Speedometer - Browser: Google Chrome Threadripper 3960X 30 60 90 120 150 SE +/- 0.33, N = 3 133 1. chrome 78.0.3904.108
NAS Parallel Benchmarks Test / Class: EP.D OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.D Threadripper 3960X 500 1000 1500 2000 2500 SE +/- 7.75, N = 3 2214.27 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
Facebook RocksDB Test: Sequential Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Sequential Fill Threadripper 3960X 200K 400K 600K 800K 1000K SE +/- 13038.81, N = 4 1030368 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
IndigoBench Scene: Bedroom OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.0.64 Scene: Bedroom Threadripper 3960X 0.8834 1.7668 2.6502 3.5336 4.417 SE +/- 0.010, N = 3 3.926
LuxCoreRender Scene: DLSC OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.2 Scene: DLSC Threadripper 3960X 0.6278 1.2556 1.8834 2.5112 3.139 SE +/- 0.01, N = 3 2.79 MIN: 2.72 / MAX: 2.85
SQLite Threads / Copies: 8 OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.30.1 Threads / Copies: 8 Threadripper 3960X 14 28 42 56 70 SE +/- 0.32, N = 3 61.41 1. (CC) gcc options: -O2 -lz -lm -ldl -lpthread
IndigoBench Scene: Supercar OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.0.64 Scene: Supercar Threadripper 3960X 2 4 6 8 10 SE +/- 0.003, N = 3 8.104
Minion Benchmark: Solitaire OpenBenchmarking.org Seconds, Fewer Is Better Minion 1.8 Benchmark: Solitaire Threadripper 3960X 14 28 42 56 70 SE +/- 0.35, N = 3 60.51 1. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic
OSPray Demo: XFrog Forest - Renderer: Path Tracer OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: XFrog Forest - Renderer: Path Tracer Threadripper 3960X 0.837 1.674 2.511 3.348 4.185 SE +/- 0.01, N = 3 3.72 MIN: 3.66 / MAX: 3.76
Facebook RocksDB Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Read While Writing Threadripper 3960X 1000K 2000K 3000K 4000K 5000K SE +/- 40449.58, N = 3 4877714 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
GraphicsMagick Operation: Resizing OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Resizing Threadripper 3960X 500 1000 1500 2000 2500 SE +/- 12.39, N = 3 2263 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
Facebook RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Read Threadripper 3960X 30M 60M 90M 120M 150M SE +/- 1282448.37, N = 3 143688270 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
GraphicsMagick Operation: Noise-Gaussian OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Noise-Gaussian Threadripper 3960X 120 240 360 480 600 SE +/- 0.33, N = 3 565 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Sharpen Threadripper 3960X 80 160 240 320 400 SE +/- 2.19, N = 3 379 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Enhanced OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Enhanced Threadripper 3960X 120 240 360 480 600 SE +/- 0.67, N = 3 569 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Rotate OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Rotate Threadripper 3960X 150 300 450 600 750 SE +/- 3.84, N = 3 710 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: Swirl OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Swirl Threadripper 3960X 300 600 900 1200 1500 SE +/- 5.49, N = 3 1351 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
GraphicsMagick Operation: HWB Color Space OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: HWB Color Space Threadripper 3960X 300 600 900 1200 1500 SE +/- 1.86, N = 3 1462 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.81 Blend File: BMW27 - Compute: CPU-Only Threadripper 3960X 13 26 39 52 65 SE +/- 0.06, N = 3 57.99
CppPerformanceBenchmarks Test: Atol OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Atol AMD Ryzen Threadripper 3960X 24-Core Threadripper 3960X 13 26 39 52 65 SE +/- 0.64, N = 3 SE +/- 0.19, N = 3 59.30 57.76 1. (CXX) g++ options: -std=c++11 -O3
SQLite Speedtest Timed Time - Size 1,000 OpenBenchmarking.org Seconds, Fewer Is Better SQLite Speedtest 3.30 Timed Time - Size 1,000 Threadripper 3960X 13 26 39 52 65 SE +/- 0.15, N = 3 58.43 1. (CC) gcc options: -O2 -ldl -lz -lpthread
Himeno Benchmark Poisson Pressure Solver OpenBenchmarking.org MFLOPS, More Is Better Himeno Benchmark 3.0 Poisson Pressure Solver Threadripper 3960X 1000 2000 3000 4000 5000 SE +/- 50.65, N = 3 4748.29 1. (CC) gcc options: -O3 -mavx2
Appleseed Scene: Disney Material OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Disney Material Threadripper 3960X 20 40 60 80 100 87.46
Radiance Benchmark Test: SMP Parallel OpenBenchmarking.org Seconds, Fewer Is Better Radiance Benchmark 5.0 Test: SMP Parallel Threadripper 3960X 40 80 120 160 200 172.08
Renaissance Test: Apache Spark PageRank OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.9.0 Test: Apache Spark PageRank Threadripper 3960X 4K 8K 12K 16K 20K SE +/- 108.55, N = 8 17245.12
NGINX Benchmark Static Web Page Serving OpenBenchmarking.org Requests Per Second, More Is Better NGINX Benchmark 1.9.9 Static Web Page Serving Threadripper 3960X 8K 16K 24K 32K 40K SE +/- 62.41, N = 3 36127.85 1. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native
ASKAP Test: tConvolve MPI - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MPI - Degridding AMD Ryzen Threadripper 3960X 24-Core 700 1400 2100 2800 3500 SE +/- 9.46, N = 3 3311.01 1. (CXX) g++ options: -lpthread
ASKAP Test: tConvolve MPI - Gridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MPI - Gridding AMD Ryzen Threadripper 3960X 24-Core 400 800 1200 1600 2000 SE +/- 4.29, N = 3 1865.03 1. (CXX) g++ options: -lpthread
NAS Parallel Benchmarks Test / Class: BT.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: BT.C Threadripper 3960X 11K 22K 33K 44K 55K SE +/- 720.74, N = 3 52747.62 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
LibreOffice Test: 20 Documents To PDF OpenBenchmarking.org Seconds, Fewer Is Better LibreOffice Test: 20 Documents To PDF Threadripper 3960X 2 4 6 8 10 SE +/- 0.054, N = 24 6.788 1. LibreOffice 6.3.3.2 30(Build:2)
Build2 Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Build2 0.12 Time To Compile Threadripper 3960X 12 24 36 48 60 SE +/- 0.10, N = 3 54.08
GNU Octave Benchmark OpenBenchmarking.org Seconds, Fewer Is Better GNU Octave Benchmark 4.4.1 Threadripper 3960X 3 6 9 12 15 SE +/- 0.11, N = 12 13.31
Redis Test: SET OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: SET Threadripper 3960X 400K 800K 1200K 1600K 2000K SE +/- 31778.19, N = 15 1834121.40 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Redis Test: GET OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: GET Threadripper 3960X 600K 1200K 1800K 2400K 3000K SE +/- 58191.94, N = 15 2649622.70 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Stockfish Total Time OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 9 Total Time Threadripper 3960X 16M 32M 48M 64M 80M SE +/- 740558.08, N = 3 75434528 1. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto
libgav1 Video Input: Summer Nature 1080p OpenBenchmarking.org FPS, More Is Better libgav1 2019-10-05 Video Input: Summer Nature 1080p Threadripper 3960X 16 32 48 64 80 SE +/- 0.15, N = 3 74.29 1. (CXX) g++ options: -O3 -lpthread
Parboil Test: OpenMP MRI Gridding OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP MRI Gridding Threadripper 3960X 11 22 33 44 55 SE +/- 0.16, N = 3 49.07 1. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
NAMD ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.13b1 ATPase Simulation - 327,506 Atoms Threadripper 3960X 0.1625 0.325 0.4875 0.65 0.8125 SE +/- 0.00128, N = 3 0.72235
Selenium Benchmark: ARES-6 - Browser: Google Chrome OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: ARES-6 - Browser: Google Chrome Threadripper 3960X 5 10 15 20 25 SE +/- 0.05, N = 3 19.97 1. chrome 78.0.3904.108
Timed LLVM Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 6.0.1 Time To Compile Threadripper 3960X 30 60 90 120 150 141.56
MKL-DNN DNNL Harness: IP Batch All - Data Type: f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: IP Batch All - Data Type: f32 Threadripper 3960X 4 8 12 16 20 SE +/- 0.12, N = 3 16.80 MIN: 15.38 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
Selenium Benchmark: Octane - Browser: Firefox OpenBenchmarking.org Geometric Mean, More Is Better Selenium Benchmark: Octane - Browser: Firefox Threadripper 3960X 8K 16K 24K 32K 40K SE +/- 203.61, N = 3 36739 1. firefox 70.0.1
Java SciMark Computational Test: Composite OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Composite Threadripper 3960X 700 1400 2100 2800 3500 SE +/- 3.56, N = 4 3033.26
Hackbench Count: 32 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 32 - Type: Process Threadripper 3960X 10 20 30 40 50 SE +/- 0.08, N = 3 44.56 1. (CC) gcc options: -lpthread
LeelaChessZero Backend: BLAS OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.22.0 Backend: BLAS AMD Ryzen Threadripper 3960X 24-Core Threadripper 3960X 8 16 24 32 40 SE +/- 2.09, N = 12 SE +/- 0.94, N = 12 33.39 32.73 1. (CXX) g++ options: -lpthread
OSPray Demo: XFrog Forest - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: XFrog Forest - Renderer: SciVis Threadripper 3960X 2 4 6 8 10 SE +/- 0.01, N = 4 7.08 MIN: 6.94 / MAX: 7.19
rav1e 1080p To AV1 Video Encode OpenBenchmarking.org Frames Per Second, More Is Better rav1e 0.1 1080p To AV1 Video Encode Threadripper 3960X 0.308 0.616 0.924 1.232 1.54 SE +/- 0.002, N = 3 1.369
Selenium Benchmark: Octane - Browser: Google Chrome OpenBenchmarking.org Geometric Mean, More Is Better Selenium Benchmark: Octane - Browser: Google Chrome Threadripper 3960X 10K 20K 30K 40K 50K SE +/- 57.21, N = 3 47433 1. chrome 78.0.3904.108
Minion Benchmark: Graceful OpenBenchmarking.org Seconds, Fewer Is Better Minion 1.8 Benchmark: Graceful Threadripper 3960X 10 20 30 40 50 SE +/- 0.26, N = 3 41.78 1. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic
NAS Parallel Benchmarks Test / Class: LU.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: LU.C Threadripper 3960X 11K 22K 33K 44K 55K SE +/- 232.22, N = 3 51711.88 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
Timed PHP Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed PHP Compilation 7.1.9 Time To Compile Threadripper 3960X 9 18 27 36 45 SE +/- 0.04, N = 3 39.64 1. (CC) gcc options: -O2 -pedantic -ldl -lz -lm
dcraw RAW To PPM Image Conversion OpenBenchmarking.org Seconds, Fewer Is Better dcraw RAW To PPM Image Conversion Threadripper 3960X 9 18 27 36 45 SE +/- 0.06, N = 3 39.50 1. (CC) gcc options: -lm
MKL-DNN DNNL Harness: Convolution Batch conv_3d - Data Type: f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_3d - Data Type: f32 Threadripper 3960X 2 4 6 8 10 SE +/- 0.08494, N = 3 6.84735 MIN: 5.9 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
Stream Type: Copy OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Copy Threadripper 3960X 7K 14K 21K 28K 35K SE +/- 15.88, N = 5 33465.1 1. (CC) gcc options: -O3 -march=native -fopenmp
FFTW Build: Stock - Size: 2D FFT Size 2048 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 2048 Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 3.11, N = 3 7864.3 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.4 Time To Compile Threadripper 3960X 7 14 21 28 35 SE +/- 0.39, N = 4 28.54
7-Zip Compression Compress Speed Test OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 16.02 Compress Speed Test Threadripper 3960X 30K 60K 90K 120K 150K SE +/- 539.47, N = 3 150915 1. (CXX) g++ options: -pipe -lpthread
MBW Test: Memory Copy, Fixed Block Size - Array Size: 4096 MiB OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 4096 MiB Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 4.86, N = 3 11493.07 1. (CC) gcc options: -O3 -march=native
MKL-DNN DNNL Harness: Recurrent Neural Network Training - Data Type: f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Recurrent Neural Network Training - Data Type: f32 Threadripper 3960X 50 100 150 200 250 SE +/- 1.80, N = 3 226.82 MIN: 196.67 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
Renaissance Test: Akka Unbalanced Cobwebbed Tree OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.9.0 Test: Akka Unbalanced Cobwebbed Tree Threadripper 3960X 3K 6K 9K 12K 15K SE +/- 127.16, N = 8 12584.86
miniFE Problem Size: Small OpenBenchmarking.org CG Mflops, More Is Better miniFE 2.2 Problem Size: Small Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 16.76, N = 3 7790.67 1. (CXX) g++ options: -O3 -fopenmp -pthread -lmpi_cxx -lmpi
Renaissance Test: In-Memory Database Shootout OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.9.0 Test: In-Memory Database Shootout Threadripper 3960X 1400 2800 4200 5600 7000 SE +/- 52.85, N = 8 6759.03
Embree Binary: Pathtracer ISPC - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer ISPC - Model: Asian Dragon Obj Threadripper 3960X 7 14 21 28 35 SE +/- 0.02, N = 3 27.74 MIN: 27.42 / MAX: 28.3
Gzip Compression Linux Source Tree Archiving To .tar.gz OpenBenchmarking.org Seconds, Fewer Is Better Gzip Compression Linux Source Tree Archiving To .tar.gz Threadripper 3960X 8 16 24 32 40 SE +/- 0.01, N = 3 33.75
Embree Binary: Pathtracer - Model: Asian Dragon Obj OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer - Model: Asian Dragon Obj Threadripper 3960X 7 14 21 28 35 SE +/- 0.01, N = 3 28.79 MIN: 28.45 / MAX: 29.34
Rust Mandelbrot Time To Complete Serial/Parallel Mandelbrot OpenBenchmarking.org Seconds, Fewer Is Better Rust Mandelbrot Time To Complete Serial/Parallel Mandelbrot AMD Ryzen Threadripper 3960X 24-Core 8 16 24 32 40 SE +/- 0.11, N = 3 32.70 1. (CC) gcc options: -m64 -pie -nodefaultlibs -lutil -ldl -lrt -lpthread -lgcc_s -lc -lm
CppPerformanceBenchmarks Test: Ctype OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Ctype AMD Ryzen Threadripper 3960X 24-Core Threadripper 3960X 8 16 24 32 40 SE +/- 0.03, N = 3 SE +/- 0.33, N = 3 31.87 33.09 1. (CXX) g++ options: -std=c++11 -O3
TTSIOD 3D Renderer Phong Rendering With Soft-Shadow Mapping OpenBenchmarking.org FPS, More Is Better TTSIOD 3D Renderer 2.3b Phong Rendering With Soft-Shadow Mapping Threadripper 3960X 200 400 600 800 1000 SE +/- 9.82, N = 4 780.04 1. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++
MKL-DNN DNNL Harness: IP Batch 1D - Data Type: f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: IP Batch 1D - Data Type: f32 Threadripper 3960X 0.634 1.268 1.902 2.536 3.17 SE +/- 0.03365, N = 6 2.81769 MIN: 2.36 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
glibc bench Benchmark: exp OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: exp Threadripper 3960X 1.0891 2.1782 3.2673 4.3564 5.4455 SE +/- 0.05687, N = 3 4.84041
Stress-NG Test: CPU Stress OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: CPU Stress Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 16.14, N = 3 9167.11 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
Stress-NG Test: Tsearch OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Tsearch Threadripper 3960X 200 400 600 800 1000 SE +/- 1.41, N = 3 964.42 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
Stress-NG Test: Crypto OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Crypto Threadripper 3960X 1500 3000 4500 6000 7500 SE +/- 27.32, N = 3 7072.93 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
Stress-NG Test: Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Vector Math Threadripper 3960X 14K 28K 42K 56K 70K SE +/- 2.23, N = 3 67241.37 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
Stress-NG Test: System V Message Passing OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: System V Message Passing Threadripper 3960X 5M 10M 15M 20M 25M SE +/- 196376.22, N = 3 23627101.30 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
Stress-NG Test: Semaphores OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Semaphores Threadripper 3960X 700K 1400K 2100K 2800K 3500K SE +/- 8385.90, N = 3 3239494.25 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
Stress-NG Test: Lsearch OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Lsearch Threadripper 3960X 80 160 240 320 400 SE +/- 0.48, N = 3 357.06 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
Stress-NG Test: Bsearch OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Bsearch Threadripper 3960X 3K 6K 9K 12K 15K SE +/- 134.01, N = 3 16332.26 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
Stress-NG Test: Glibc C String Functions OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Glibc C String Functions Threadripper 3960X 500K 1000K 1500K 2000K 2500K SE +/- 28050.29, N = 3 2449871.83 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
Stress-NG Test: Memory Copying OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Memory Copying Threadripper 3960X 3K 6K 9K 12K 15K SE +/- 31.26, N = 3 12234.52 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
Stress-NG Test: Hsearch OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Hsearch Threadripper 3960X 40K 80K 120K 160K 200K SE +/- 582.97, N = 3 199421.45 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
Stress-NG Test: Forking OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Forking Threadripper 3960X 20K 40K 60K 80K 100K SE +/- 775.10, N = 3 80851.06 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
Stress-NG Test: Matrix Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Matrix Math Threadripper 3960X 30K 60K 90K 120K 150K SE +/- 505.47, N = 3 151388.05 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
Stress-NG Test: Glibc Qsort Data Sorting OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Glibc Qsort Data Sorting Threadripper 3960X 80 160 240 320 400 SE +/- 1.42, N = 3 380.73 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
Stress-NG Test: Socket Activity OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Socket Activity Threadripper 3960X 4K 8K 12K 16K 20K SE +/- 48.18, N = 3 18734.34 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -lc
Apache Benchmark Static Web Page Serving OpenBenchmarking.org Requests Per Second, More Is Better Apache Benchmark 2.4.29 Static Web Page Serving Threadripper 3960X 7K 14K 21K 28K 35K SE +/- 49.18, N = 3 34193.15 1. (CC) gcc options: -shared -fPIC -O2 -pthread
CppPerformanceBenchmarks Test: Stepanov Abstraction OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Stepanov Abstraction AMD Ryzen Threadripper 3960X 24-Core Threadripper 3960X 7 14 21 28 35 SE +/- 0.01, N = 3 SE +/- 0.15, N = 3 28.31 28.30 1. (CXX) g++ options: -std=c++11 -O3
eSpeak Speech Engine Text-To-Speech Synthesis OpenBenchmarking.org Seconds, Fewer Is Better eSpeak Speech Engine 1.48.04 Text-To-Speech Synthesis Threadripper 3960X 7 14 21 28 35 SE +/- 0.48, N = 3 27.81 1. (CXX) g++ options: -lstdc++ -lespeak -O2 -fpic -fvisibility=hidden -pedantic -fno-exceptions
ACES DGEMM Sustained Floating-Point Rate OpenBenchmarking.org GFLOP/s, More Is Better ACES DGEMM 1.0 Sustained Floating-Point Rate Threadripper 3960X 2 4 6 8 10 SE +/- 0.028924, N = 3 8.543887 1. (CC) gcc options: -O3 -march=native -fopenmp
Renaissance Test: Apache Spark ALS OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.9.0 Test: Apache Spark ALS Threadripper 3960X 1400 2800 4200 5600 7000 SE +/- 43.26, N = 8 6643.08
SciMark Computational Test: Composite OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Composite Threadripper 3960X 150 300 450 600 750 SE +/- 1.06, N = 3 714.92 1. (CC) gcc options: -lm
OSPray Demo: NASA Streamlines - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: NASA Streamlines - Renderer: SciVis Threadripper 3960X 12 24 36 48 60 SE +/- 0.00, N = 12 52.63 MIN: 43.48 / MAX: 55.56
Coremark CoreMark Size 666 - Iterations Per Second OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second Threadripper 3960X 200K 400K 600K 800K 1000K SE +/- 601.18, N = 3 1069837.23 1. (CC) gcc options: -O2 -lrt" -lrt
Tesseract OCR Time To OCR 7 Images OpenBenchmarking.org Seconds, Fewer Is Better Tesseract OCR 4.1.0 Time To OCR 7 Images Threadripper 3960X 6 12 18 24 30 SE +/- 0.05, N = 3 24.14
NAS Parallel Benchmarks Test / Class: FT.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: FT.C Threadripper 3960X 4K 8K 12K 16K 20K SE +/- 33.84, N = 3 17832.39 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
m-queens Time To Solve OpenBenchmarking.org Seconds, Fewer Is Better m-queens 1.2 Time To Solve Threadripper 3960X 6 12 18 24 30 SE +/- 0.02, N = 3 23.28 1. (CXX) g++ options: -fopenmp -O2 -march=native
Hackbench Count: 16 - Type: Thread OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 16 - Type: Thread Threadripper 3960X 5 10 15 20 25 SE +/- 0.01, N = 3 22.96 1. (CC) gcc options: -lpthread
Tensorflow Build: Cifar10 OpenBenchmarking.org Seconds, Fewer Is Better Tensorflow 2017-02-03 Build: Cifar10 AMD Ryzen Threadripper 3960X 24-Core 4 8 12 16 20 SE +/- 0.04, N = 3 17.04
FFTW Build: Float + SSE - Size: 2D FFT Size 1024 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 1024 Threadripper 3960X 9K 18K 27K 36K 45K SE +/- 199.23, N = 3 40897 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
Hackbench Count: 16 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 16 - Type: Process Threadripper 3960X 5 10 15 20 25 SE +/- 0.07, N = 3 22.74 1. (CC) gcc options: -lpthread
MBW Test: Memory Copy - Array Size: 4096 MiB OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 4096 MiB Threadripper 3960X 4K 8K 12K 16K 20K SE +/- 33.30, N = 3 19697.48 1. (CC) gcc options: -O3 -march=native
PyBench Total For Average Test Times OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times Threadripper 3960X 200 400 600 800 1000 SE +/- 10.69, N = 3 968
Embree Binary: Pathtracer ISPC - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer ISPC - Model: Crown Threadripper 3960X 7 14 21 28 35 SE +/- 0.02, N = 3 28.37 MIN: 27.81 / MAX: 29.1
Crafty Elapsed Time OpenBenchmarking.org Nodes Per Second, More Is Better Crafty 25.2 Elapsed Time Threadripper 3960X 2M 4M 6M 8M 10M SE +/- 53093.30, N = 3 9041729 1. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm
C-Ray Total Time - 4K, 16 Rays Per Pixel OpenBenchmarking.org Seconds, Fewer Is Better C-Ray 1.1 Total Time - 4K, 16 Rays Per Pixel Threadripper 3960X 5 10 15 20 25 SE +/- 0.03, N = 3 21.06 1. (CC) gcc options: -lm -lpthread -O3
MKL-DNN DNNL Harness: Deconvolution Batch deconv_1d - Data Type: f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_1d - Data Type: f32 Threadripper 3960X 0.5841 1.1682 1.7523 2.3364 2.9205 SE +/- 0.03171, N = 3 2.59611 MIN: 2.27 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
Embree Binary: Pathtracer - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer - Model: Crown Threadripper 3960X 7 14 21 28 35 SE +/- 0.07, N = 3 29.77 MIN: 29.2 / MAX: 30.55
Tungsten Renderer Scene: Water Caustic OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Water Caustic Threadripper 3960X 5 10 15 20 25 SE +/- 0.03, N = 3 19.34 1. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lpthread -ldl
GIMP Test: unsharp-mask OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.8 Test: unsharp-mask Threadripper 3960X 5 10 15 20 25 SE +/- 0.04, N = 3 20.51
XZ Compression Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9 OpenBenchmarking.org Seconds, Fewer Is Better XZ Compression 5.2.4 Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9 Threadripper 3960X 5 10 15 20 25 SE +/- 0.04, N = 3 20.36 1. (CC) gcc options: -pthread -fvisibility=hidden -O2
glibc bench Benchmark: cos OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: cos Threadripper 3960X 10 20 30 40 50 SE +/- 0.04, N = 3 42.02
glibc bench Benchmark: sincos OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: sincos Threadripper 3960X 3 6 9 12 15 SE +/- 0.01, N = 3 12.14
glibc bench Benchmark: sin OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: sin Threadripper 3960X 9 18 27 36 45 SE +/- 0.34, N = 3 41.42
ebizzy OpenBenchmarking.org Records/s, More Is Better ebizzy 0.3 AMD Ryzen Threadripper 3960X 24-Core 500K 1000K 1500K 2000K 2500K SE +/- 22054.77, N = 3 2254196 1. (CC) gcc options: -pthread -lpthread -O3 -march=native
FFTW Build: Float + SSE - Size: 1D FFT Size 256 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 256 Threadripper 3960X 8K 16K 24K 32K 40K SE +/- 412.34, N = 15 38260 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
Embree Binary: Pathtracer - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer - Model: Asian Dragon Threadripper 3960X 7 14 21 28 35 SE +/- 0.01, N = 3 32.15 MIN: 31.73 / MAX: 32.8
Embree Binary: Pathtracer ISPC - Model: Asian Dragon OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer ISPC - Model: Asian Dragon Threadripper 3960X 7 14 21 28 35 SE +/- 0.02, N = 3 32.15 MIN: 31.68 / MAX: 32.72
Go Benchmarks Test: build OpenBenchmarking.org Nanoseconds/Operation, Fewer Is Better Go Benchmarks Test: build Threadripper 3960X 4000M 8000M 12000M 16000M 20000M SE +/- 83434537.14, N = 3 19291013759
Selenium Benchmark: PSPDFKit WASM - Browser: Firefox OpenBenchmarking.org Score, Fewer Is Better Selenium Benchmark: PSPDFKit WASM - Browser: Firefox Threadripper 3960X 300 600 900 1200 1500 SE +/- 5.46, N = 3 1324 1. firefox 70.0.1
dav1d Video Input: Chimera 1080p OpenBenchmarking.org FPS, More Is Better dav1d 0.5.0 Video Input: Chimera 1080p Threadripper 3960X 130 260 390 520 650 SE +/- 1.35, N = 3 587.81 MIN: 448.01 / MAX: 721.98 1. (CC) gcc options: -pthread
POV-Ray Trace Time OpenBenchmarking.org Seconds, Fewer Is Better POV-Ray 3.7.0.7 Trace Time AMD Ryzen Threadripper 3960X 24-Core Threadripper 3960X 4 8 12 16 20 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 16.36 16.41 1. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -pthread -lSDL -lXpm -lSM -lICE -lX11 -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system
Tungsten Renderer Scene: Non-Exponential OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Non-Exponential Threadripper 3960X 0.8019 1.6038 2.4057 3.2076 4.0095 SE +/- 0.10003, N = 15 3.56422 1. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lpthread -ldl
Selenium Benchmark: PSPDFKit WASM - Browser: Google Chrome OpenBenchmarking.org Score, Fewer Is Better Selenium Benchmark: PSPDFKit WASM - Browser: Google Chrome Threadripper 3960X 300 600 900 1200 1500 SE +/- 3.28, N = 3 1508 1. chrome 78.0.3904.108
Selenium Benchmark: Maze Solver - Browser: Firefox OpenBenchmarking.org Seconds, Fewer Is Better Selenium Benchmark: Maze Solver - Browser: Firefox Threadripper 3960X 0.99 1.98 2.97 3.96 4.95 SE +/- 0.07, N = 3 4.4 1. firefox 70.0.1
ParaView Test: Many Spheres - Resolution: 2560 x 1440 OpenBenchmarking.org MiPolys / Sec, More Is Better ParaView 5.4.1 Test: Many Spheres - Resolution: 2560 x 1440 Threadripper 3960X 1300 2600 3900 5200 6500 SE +/- 4.91, N = 3 5900.23
ParaView Test: Many Spheres - Resolution: 2560 x 1440 OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.4.1 Test: Many Spheres - Resolution: 2560 x 1440 Threadripper 3960X 13 26 39 52 65 SE +/- 0.05, N = 3 58.85
GIMP Test: auto-levels OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.8 Test: auto-levels Threadripper 3960X 4 8 12 16 20 SE +/- 0.05, N = 3 17.13
RAMspeed SMP Type: Triad - Benchmark: Floating Point OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Triad - Benchmark: Floating Point Threadripper 3960X 8K 16K 24K 32K 40K 37623.85 1. (CC) gcc options: -O3 -march=native
MKL-DNN DNNL Harness: Convolution Batch conv_alexnet - Data Type: f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_alexnet - Data Type: f32 Threadripper 3960X 30 60 90 120 150 SE +/- 1.31, N = 3 142.23 MIN: 123.19 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
RAMspeed SMP Type: Average - Benchmark: Integer OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Average - Benchmark: Integer Threadripper 3960X 8K 16K 24K 32K 40K 36961.63 1. (CC) gcc options: -O3 -march=native
SQLite Threads / Copies: 1 OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.30.1 Threads / Copies: 1 Threadripper 3960X 4 8 12 16 20 SE +/- 0.10, N = 3 15.74 1. (CC) gcc options: -O2 -lz -lm -ldl -lpthread
PHPBench PHP Benchmark Suite OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite Threadripper 3960X 140K 280K 420K 560K 700K SE +/- 5664.15, N = 3 658408
RAMspeed SMP Type: Copy - Benchmark: Floating Point OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Copy - Benchmark: Floating Point Threadripper 3960X 8K 16K 24K 32K 40K 35940.89 1. (CC) gcc options: -O3 -march=native
Rust Prime Benchmark Prime Number Test To 200,000,000 OpenBenchmarking.org Seconds, Fewer Is Better Rust Prime Benchmark Prime Number Test To 200,000,000 AMD Ryzen Threadripper 3960X 24-Core 4 8 12 16 20 SE +/- 0.02, N = 3 15.00 1. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lrt -lpthread -lgcc_s -lc -lm -lutil
CppPerformanceBenchmarks Test: Function Objects OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Function Objects AMD Ryzen Threadripper 3960X 24-Core Threadripper 3960X 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.12, N = 3 14.69 14.68 1. (CXX) g++ options: -std=c++11 -O3
Timed ImageMagick Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed ImageMagick Compilation 6.9.0 Time To Compile Threadripper 3960X 4 8 12 16 20 SE +/- 0.12, N = 3 14.54
RAMspeed SMP Type: Scale - Benchmark: Floating Point OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Scale - Benchmark: Floating Point Threadripper 3960X 8K 16K 24K 32K 40K 37097.99 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Add - Benchmark: Floating Point OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Add - Benchmark: Floating Point Threadripper 3960X 9K 18K 27K 36K 45K 43043.84 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Average - Benchmark: Floating Point OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Average - Benchmark: Floating Point Threadripper 3960X 9K 18K 27K 36K 45K 40240.98 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Add - Benchmark: Integer OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Add - Benchmark: Integer Threadripper 3960X 9K 18K 27K 36K 45K 43028.44 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Scale - Benchmark: Integer OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Scale - Benchmark: Integer Threadripper 3960X 8K 16K 24K 32K 40K 38106.38 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Triad - Benchmark: Integer OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Triad - Benchmark: Integer Threadripper 3960X 9K 18K 27K 36K 45K 43894.26 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Copy - Benchmark: Integer OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Copy - Benchmark: Integer Threadripper 3960X 8K 16K 24K 32K 40K 37204.25 1. (CC) gcc options: -O3 -march=native
FFTW Build: Float + SSE - Size: 1D FFT Size 64 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 64 Threadripper 3960X 4K 8K 12K 16K 20K SE +/- 715.56, N = 15 18900 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Stock - Size: 1D FFT Size 64 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 64 Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 231.46, N = 15 9362.2 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
Selenium Benchmark: Maze Solver - Browser: Google Chrome OpenBenchmarking.org Seconds, Fewer Is Better Selenium Benchmark: Maze Solver - Browser: Google Chrome Threadripper 3960X 0.9 1.8 2.7 3.6 4.5 SE +/- 0.03, N = 3 4.0 1. chrome 78.0.3904.108
Zstd Compression Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 OpenBenchmarking.org Seconds, Fewer Is Better Zstd Compression 1.3.4 Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 Threadripper 3960X 3 6 9 12 15 SE +/- 0.15, N = 4 10.23 1. (CC) gcc options: -O3 -pthread -lz -llzma
FLAC Audio Encoding WAV To FLAC OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.3.2 WAV To FLAC Threadripper 3960X 2 4 6 8 10 SE +/- 0.013, N = 5 7.834 1. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm
Hackbench Count: 1 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 1 - Type: Process Threadripper 3960X 0.6215 1.243 1.8645 2.486 3.1075 SE +/- 0.027, N = 14 2.762 1. (CC) gcc options: -lpthread
Xsbench OpenBenchmarking.org Lookups/s, More Is Better Xsbench 2017-07-06 Threadripper 3960X 1.1M 2.2M 3.3M 4.4M 5.5M SE +/- 3935.07, N = 3 5029528 1. (CC) gcc options: -std=gnu99 -fopenmp -O3 -lm
dav1d Video Input: Summer Nature 4K OpenBenchmarking.org FPS, More Is Better dav1d 0.5.0 Video Input: Summer Nature 4K Threadripper 3960X 60 120 180 240 300 SE +/- 0.85, N = 3 291.09 MIN: 179.18 / MAX: 309.08 1. (CC) gcc options: -pthread
GIMP Test: rotate OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.8 Test: rotate Threadripper 3960X 3 6 9 12 15 SE +/- 0.02, N = 3 12.32
DaCapo Benchmark Java Test: Tradebeans OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Tradebeans Threadripper 3960X 1000 2000 3000 4000 5000 SE +/- 13.42, N = 4 4643
Go Benchmarks Test: json OpenBenchmarking.org Nanoseconds/Operation, Fewer Is Better Go Benchmarks Test: json Threadripper 3960X 400K 800K 1200K 1600K 2000K SE +/- 13151.09, N = 3 1901078
Hackbench Count: 8 - Type: Thread OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 8 - Type: Thread Threadripper 3960X 3 6 9 12 15 SE +/- 0.04, N = 3 11.67 1. (CC) gcc options: -lpthread
SVT-AV1 Encoder Mode: Enc Mode 4 - Input: 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.7 Encoder Mode: Enc Mode 4 - Input: 1080p Threadripper 3960X 2 4 6 8 10 SE +/- 0.027, N = 3 8.043 1. (CXX) g++ options: -fPIE -fPIC -pie
Hackbench Count: 8 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 8 - Type: Process Threadripper 3960X 3 6 9 12 15 SE +/- 0.07, N = 3 11.15 1. (CC) gcc options: -lpthread
ASKAP Test: tConvolve OpenMP - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve OpenMP - Degridding AMD Ryzen Threadripper 3960X 24-Core 800 1600 2400 3200 4000 SE +/- 0.00, N = 3 3915.53 1. (CXX) g++ options: -lpthread
ASKAP Test: tConvolve OpenMP - Gridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve OpenMP - Gridding AMD Ryzen Threadripper 3960X 24-Core 1000 2000 3000 4000 5000 SE +/- 26.85, N = 3 4617.47 1. (CXX) g++ options: -lpthread
DaCapo Benchmark Java Test: Tradesoap OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Tradesoap Threadripper 3960X 700 1400 2100 2800 3500 SE +/- 29.66, N = 4 3364
LeelaChessZero Backend: Random OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.22.0 Backend: Random AMD Ryzen Threadripper 3960X 24-Core Threadripper 3960X 20K 40K 60K 80K 100K SE +/- 557.11, N = 3 SE +/- 513.36, N = 3 106669 106908 1. (CXX) g++ options: -lpthread
Opus Codec Encoding WAV, Opus Encode, Opus Decode OpenBenchmarking.org Seconds, Fewer Is Better Opus Codec Encoding 1.0.1 WAV, Opus Encode, Opus Decode Threadripper 3960X 2 4 6 8 10 SE +/- 0.013, N = 5 6.272 1. (CC) gcc options: -O3 -ffast-math -fPIE -pie -logg -lm -lopus
glibc bench Benchmark: asinh OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: asinh Threadripper 3960X 2 4 6 8 10 SE +/- 0.00200, N = 3 8.42052
glibc bench Benchmark: sinh OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: sinh Threadripper 3960X 2 4 6 8 10 SE +/- 0.07381, N = 3 7.82634
glibc bench Benchmark: log2 OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: log2 Threadripper 3960X 1.3134 2.6268 3.9402 5.2536 6.567 SE +/- 0.00530, N = 3 5.83717
glibc bench Benchmark: ffsll OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: ffsll Threadripper 3960X 0.3944 0.7888 1.1832 1.5776 1.972 SE +/- 0.00365, N = 3 1.75307
glibc bench Benchmark: tanh OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: tanh Threadripper 3960X 3 6 9 12 15 SE +/- 0.11, N = 3 10.52
glibc bench Benchmark: atanh OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: atanh Threadripper 3960X 3 6 9 12 15 SE +/- 0.00, N = 3 10.02
glibc bench Benchmark: sqrt OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: sqrt Threadripper 3960X 0.4865 0.973 1.4595 1.946 2.4325 SE +/- 0.01495, N = 3 2.16235
glibc bench Benchmark: modf OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: modf Threadripper 3960X 0.4995 0.999 1.4985 1.998 2.4975 SE +/- 0.00220, N = 3 2.21984
glibc bench Benchmark: ffs OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: ffs Threadripper 3960X 0.3958 0.7916 1.1874 1.5832 1.979 SE +/- 0.00277, N = 3 1.75927
glibc bench Benchmark: pthread_once OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: pthread_once Threadripper 3960X 0.3924 0.7848 1.1772 1.5696 1.962 SE +/- 0.00112, N = 3 1.74395
Rodinia Test: OpenMP LavaMD OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenMP LavaMD Threadripper 3960X 3 6 9 12 15 SE +/- 0.01, N = 3 10.10 1. (CXX) g++ options: -O2 -lOpenCL
Tungsten Renderer Scene: Hair OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Hair Threadripper 3960X 3 6 9 12 15 SE +/- 0.02317, N = 3 9.79737 1. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lpthread -ldl
FFTW Build: Stock - Size: 2D FFT Size 1024 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 1024 Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 4.47, N = 3 8097.9 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
DaCapo Benchmark Java Test: H2 OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: H2 Threadripper 3960X 800 1600 2400 3200 4000 SE +/- 28.55, N = 4 3694
Go Benchmarks Test: http OpenBenchmarking.org Nanoseconds/Operation, Fewer Is Better Go Benchmarks Test: http Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 59.54, N = 3 8619
MBW Test: Memory Copy, Fixed Block Size - Array Size: 1024 MiB OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 1024 MiB Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 13.80, N = 3 11380.32 1. (CC) gcc options: -O3 -march=native
OSPray Demo: Magnetic Reconnection - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: Magnetic Reconnection - Renderer: SciVis Threadripper 3960X 6 12 18 24 30 25 MIN: 24.39 / MAX: 25.64
x265 H.265 1080p Video Encoding OpenBenchmarking.org Frames Per Second, More Is Better x265 3.1.2 H.265 1080p Video Encoding Threadripper 3960X 15 30 45 60 75 SE +/- 0.22, N = 3 65.71 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
Rodinia Test: OpenMP CFD Solver OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenMP CFD Solver Threadripper 3960X 3 6 9 12 15 SE +/- 0.025, N = 3 9.037 1. (CXX) g++ options: -O2 -lOpenCL
NeatBench Acceleration: CPU OpenBenchmarking.org FPS, More Is Better NeatBench 5 Acceleration: CPU AMD Ryzen Threadripper 3960X 24-Core 8 16 24 32 40 SE +/- 0.18, N = 3 35.3
SVT-VP9 Tuning: VMAF Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.1 Tuning: VMAF Optimized - Input: Bosphorus 1080p Threadripper 3960X 80 160 240 320 400 SE +/- 4.06, N = 13 382.22 1. (CC) gcc options: -fPIE -fPIC -fvisibility=hidden -O3 -pie -rdynamic -lpthread -lrt -lm
Parboil Test: OpenMP Stencil OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP Stencil Threadripper 3960X 2 4 6 8 10 SE +/- 0.018289, N = 3 7.243440 1. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
GIMP Test: resize OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.8 Test: resize Threadripper 3960X 2 4 6 8 10 SE +/- 0.135, N = 3 8.609
Go Benchmarks Test: garbage OpenBenchmarking.org Nanoseconds/Operation, Fewer Is Better Go Benchmarks Test: garbage Threadripper 3960X 150K 300K 450K 600K 750K SE +/- 2346.17, N = 3 702500
Bork File Encrypter File Encryption Time OpenBenchmarking.org Seconds, Fewer Is Better Bork File Encrypter 1.4 File Encryption Time Threadripper 3960X 2 4 6 8 10 SE +/- 0.021, N = 3 8.018
NAS Parallel Benchmarks Test / Class: MG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: MG.C Threadripper 3960X 5K 10K 15K 20K 25K SE +/- 41.78, N = 3 25120.08 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
Sunflow Rendering System Global Illumination + Image Synthesis OpenBenchmarking.org Seconds, Fewer Is Better Sunflow Rendering System 0.07.2 Global Illumination + Image Synthesis Threadripper 3960X 0.1541 0.3082 0.4623 0.6164 0.7705 SE +/- 0.010, N = 3 0.685
LAME MP3 Encoding WAV To MP3 OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.100 WAV To MP3 Threadripper 3960X 2 4 6 8 10 SE +/- 0.003, N = 3 7.117 1. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lm
DaCapo Benchmark Java Test: Jython OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Jython Threadripper 3960X 800 1600 2400 3200 4000 SE +/- 10.28, N = 4 3963
Darktable Test: Boat - Acceleration: CPU-only OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.6.0 Test: Boat - Acceleration: CPU-only Threadripper 3960X 2 4 6 8 10 SE +/- 0.046, N = 3 6.279
FFTW Build: Float + SSE - Size: 2D FFT Size 512 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 512 Threadripper 3960X 9K 18K 27K 36K 45K SE +/- 137.80, N = 3 43049 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 1D FFT Size 4096 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 4096 Threadripper 3960X 13K 26K 39K 52K 65K SE +/- 410.08, N = 3 58875 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OSPray Demo: Magnetic Reconnection - Renderer: Path Tracer OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: Magnetic Reconnection - Renderer: Path Tracer Threadripper 3960X 70 140 210 280 350 SE +/- 0.00, N = 12 333.33 MIN: 166.67 / MAX: 500
Hackbench Count: 4 - Type: Thread OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 4 - Type: Thread Threadripper 3960X 2 4 6 8 10 SE +/- 0.034, N = 3 6.032 1. (CC) gcc options: -lpthread
MBW Test: Memory Copy - Array Size: 1024 MiB OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 1024 MiB Threadripper 3960X 4K 8K 12K 16K 20K SE +/- 19.92, N = 3 19435.38 1. (CC) gcc options: -O3 -march=native
Hackbench Count: 4 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 4 - Type: Process Threadripper 3960X 1.2303 2.4606 3.6909 4.9212 6.1515 SE +/- 0.008, N = 3 5.468 1. (CC) gcc options: -lpthread
OSBench Test: Create Files OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Files Threadripper 3960X 3 6 9 12 15 SE +/- 0.01, N = 3 11.54 1. (CC) gcc options: -lm
dav1d Video Input: Summer Nature 1080p OpenBenchmarking.org FPS, More Is Better dav1d 0.5.0 Video Input: Summer Nature 1080p Threadripper 3960X 150 300 450 600 750 SE +/- 1.15, N = 3 677.06 MIN: 426.02 / MAX: 738.11 1. (CC) gcc options: -pthread
Intel Open Image Denoise Scene: Memorial OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.0.0 Scene: Memorial AMD Ryzen Threadripper 3960X 24-Core Threadripper 3960X 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 19.75 19.59
SVT-AV1 Encoder Mode: Enc Mode 8 - Input: 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.7 Encoder Mode: Enc Mode 8 - Input: 1080p Threadripper 3960X 20 40 60 80 100 SE +/- 0.12, N = 3 78.79 1. (CXX) g++ options: -fPIE -fPIC -pie
FFTW Build: Float + SSE - Size: 1D FFT Size 2048 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 2048 Threadripper 3960X 13K 26K 39K 52K 65K SE +/- 623.77, N = 3 61112 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
OSBench Test: Memory Allocations OpenBenchmarking.org Ns Per Event, Fewer Is Better OSBench Test: Memory Allocations Threadripper 3960X 16 32 48 64 80 SE +/- 0.15, N = 3 70.60 1. (CC) gcc options: -lm
OSBench Test: Create Processes OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Processes Threadripper 3960X 9 18 27 36 45 SE +/- 0.55, N = 3 41.04 1. (CC) gcc options: -lm
OSBench Test: Launch Programs OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Launch Programs Threadripper 3960X 11 22 33 44 55 SE +/- 0.47, N = 3 48.15 1. (CC) gcc options: -lm
OSBench Test: Create Threads OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Threads Threadripper 3960X 5 10 15 20 25 SE +/- 0.25, N = 3 20.84 1. (CC) gcc options: -lm
ParaView Test: Wavelet Contour - Resolution: 2560 x 1440 OpenBenchmarking.org MiPolys / Sec, More Is Better ParaView 5.4.1 Test: Wavelet Contour - Resolution: 2560 x 1440 Threadripper 3960X 600 1200 1800 2400 3000 SE +/- 1.76, N = 3 2578.93
ParaView Test: Wavelet Contour - Resolution: 2560 x 1440 OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.4.1 Test: Wavelet Contour - Resolution: 2560 x 1440 Threadripper 3960X 50 100 150 200 250 SE +/- 0.17, N = 3 247.47
Git Time To Complete Common Git Commands OpenBenchmarking.org Seconds, Fewer Is Better Git Time To Complete Common Git Commands Threadripper 3960X 1.0721 2.1442 3.2163 4.2884 5.3605 SE +/- 0.035, N = 3 4.765 1. git version 2.20.1
MBW Test: Memory Copy, Fixed Block Size - Array Size: 512 MiB OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 512 MiB Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 6.27, N = 3 11306.18 1. (CC) gcc options: -O3 -march=native
FFTW Build: Stock - Size: 1D FFT Size 4096 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 4096 Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 31.06, N = 3 8818.8 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Stock - Size: 2D FFT Size 256 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 256 Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 8.89, N = 3 8674.1 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 2D FFT Size 256 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 256 Threadripper 3960X 9K 18K 27K 36K 45K SE +/- 310.57, N = 3 42616 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
N-Queens Elapsed Time OpenBenchmarking.org Seconds, Fewer Is Better N-Queens 1.0 Elapsed Time Threadripper 3960X 1.0055 2.011 3.0165 4.022 5.0275 SE +/- 0.012, N = 3 4.469 1. (CC) gcc options: -static -fopenmp -O3 -march=native
NAS Parallel Benchmarks Test / Class: EP.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: EP.C Threadripper 3960X 500 1000 1500 2000 2500 SE +/- 5.95, N = 3 2208.11 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
Tungsten Renderer Scene: Volumetric Caustic OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Volumetric Caustic Threadripper 3960X 0.9352 1.8704 2.8056 3.7408 4.676 SE +/- 0.00428, N = 3 4.15646 1. (CXX) g++ options: -std=c++0x -march=znver1 -msse2 -msse3 -mssse3 -msse4.1 -msse4.2 -msse4a -mfma -mbmi2 -mno-avx -mno-avx2 -mno-xop -mno-fma4 -mno-avx512f -mno-avx512vl -mno-avx512pf -mno-avx512er -mno-avx512cd -mno-avx512dq -mno-avx512bw -mno-avx512ifma -mno-avx512vbmi -fstrict-aliasing -O3 -rdynamic -lIlmImf -lIlmThread -lImath -lHalf -lIex -lz -ljpeg -lpthread -ldl
Darktable Test: Masskrug - Acceleration: CPU-only OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.6.0 Test: Masskrug - Acceleration: CPU-only Threadripper 3960X 0.7655 1.531 2.2965 3.062 3.8275 SE +/- 0.027, N = 3 3.402
FFTW Build: Float + SSE - Size: 1D FFT Size 1024 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 1024 Threadripper 3960X 13K 26K 39K 52K 65K SE +/- 370.51, N = 3 59937 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Stock - Size: 1D FFT Size 256 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 256 Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 12.22, N = 3 8883.8 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Stock - Size: 2D FFT Size 32 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 32 Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 17.13, N = 3 11113 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
Bullet Physics Engine Test: Raytests OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: Raytests Threadripper 3960X 0.4757 0.9514 1.4271 1.9028 2.3785 SE +/- 0.004788, N = 3 2.114348 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
FFTW Build: Stock - Size: 2D FFT Size 512 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 512 Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 17.50, N = 3 8684.6 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 1D FFT Size 32 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 32 Threadripper 3960X 3K 6K 9K 12K 15K SE +/- 208.40, N = 4 15042 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 2D FFT Size 32 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 32 Threadripper 3960X 10K 20K 30K 40K 50K SE +/- 88.57, N = 3 46123 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 1D FFT Size 512 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 512 Threadripper 3960X 11K 22K 33K 44K 55K SE +/- 123.47, N = 3 51240 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Stock - Size: 1D FFT Size 32 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 32 Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 5.51, N = 3 11237 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
Hackbench Count: 2 - Type: Thread OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 2 - Type: Thread Threadripper 3960X 0.8406 1.6812 2.5218 3.3624 4.203 SE +/- 0.057, N = 3 3.736 1. (CC) gcc options: -lpthread
FFTW Build: Stock - Size: 1D FFT Size 2048 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 2048 Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 21.61, N = 3 9048.1 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
Smallpt Global Illumination Renderer; 128 Samples OpenBenchmarking.org Seconds, Fewer Is Better Smallpt 1.0 Global Illumination Renderer; 128 Samples Threadripper 3960X 0.8269 1.6538 2.4807 3.3076 4.1345 SE +/- 0.005, N = 3 3.675 1. (CXX) g++ options: -fopenmp -O3
FFTW Build: Stock - Size: 2D FFT Size 128 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 128 Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 14.00, N = 3 8902.3 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
Darktable Test: Server Rack - Acceleration: CPU-only OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.6.0 Test: Server Rack - Acceleration: CPU-only Threadripper 3960X 0.0293 0.0586 0.0879 0.1172 0.1465 SE +/- 0.002, N = 15 0.130
FFTW Build: Stock - Size: 1D FFT Size 128 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 128 Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 77.36, N = 3 8569.2 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
Hackbench Count: 2 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 2 - Type: Process Threadripper 3960X 0.794 1.588 2.382 3.176 3.97 SE +/- 0.014, N = 3 3.529 1. (CC) gcc options: -lpthread
Darktable Test: Server Room - Acceleration: CPU-only OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.6.0 Test: Server Room - Acceleration: CPU-only Threadripper 3960X 0.5045 1.009 1.5135 2.018 2.5225 SE +/- 0.016, N = 3 2.242
x264 H.264 Video Encoding OpenBenchmarking.org Frames Per Second, More Is Better x264 2018-09-25 H.264 Video Encoding Threadripper 3960X 40 80 120 160 200 SE +/- 1.86, N = 3 193.76 1. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize
Optcarrot Optimized Benchmark OpenBenchmarking.org FPS, More Is Better Optcarrot Optimized Benchmark Threadripper 3960X 20 40 60 80 100 SE +/- 0.64, N = 4 106.88 1. ruby 2.5.5p157 (2019-03-15 revision 67260) [x86_64-linux-gnu]
MKL-DNN DNNL Harness: Deconvolution Batch deconv_3d - Data Type: f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_3d - Data Type: f32 Threadripper 3960X 0.6444 1.2888 1.9332 2.5776 3.222 SE +/- 0.01436, N = 3 2.86390 MIN: 2.45 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
FFTW Build: Float + SSE - Size: 2D FFT Size 128 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 128 Threadripper 3960X 10K 20K 30K 40K 50K SE +/- 237.97, N = 3 46970 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Stock - Size: 1D FFT Size 1024 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 1024 Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 5.17, N = 3 9356.2 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
Hackbench Count: 1 - Type: Thread OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 1 - Type: Thread Threadripper 3960X 0.6431 1.2862 1.9293 2.5724 3.2155 SE +/- 0.030, N = 3 2.858 1. (CC) gcc options: -lpthread
MBW Test: Memory Copy - Array Size: 512 MiB OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 512 MiB Threadripper 3960X 4K 8K 12K 16K 20K SE +/- 62.41, N = 3 19400.43 1. (CC) gcc options: -O3 -march=native
FFTW Build: Stock - Size: 2D FFT Size 64 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 64 Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 21.91, N = 3 9585.4 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Stock - Size: 1D FFT Size 512 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 512 Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 39.54, N = 3 9114.0 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 1D FFT Size 128 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 128 Threadripper 3960X 6K 12K 18K 24K 30K SE +/- 98.24, N = 3 27460 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 2D FFT Size 64 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 64 Threadripper 3960X 10K 20K 30K 40K 50K SE +/- 259.03, N = 3 47733 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
SVT-VP9 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.1 Tuning: Visual Quality Optimized - Input: Bosphorus 1080p Threadripper 3960X 70 140 210 280 350 SE +/- 2.33, N = 3 326.41 1. (CC) gcc options: -fPIE -fPIC -fvisibility=hidden -O3 -pie -rdynamic -lpthread -lrt -lm
FFTE Test: N=256, 1D Complex FFT Routine OpenBenchmarking.org MFLOPS, More Is Better FFTE 6.0 Test: N=256, 1D Complex FFT Routine Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 86.87, N = 3 9627.34 1. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
TSCP AI Chess Performance OpenBenchmarking.org Nodes Per Second, More Is Better TSCP 1.81 AI Chess Performance Threadripper 3960X 300K 600K 900K 1200K 1500K SE +/- 2224.51, N = 5 1341412 1. (CC) gcc options: -O3 -march=native
SVT-VP9 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-VP9 0.1 Tuning: PSNR/SSIM Optimized - Input: Bosphorus 1080p Threadripper 3960X 90 180 270 360 450 SE +/- 2.37, N = 3 392.87 1. (CC) gcc options: -fPIE -fPIC -fvisibility=hidden -O3 -pie -rdynamic -lpthread -lrt -lm
ParaView Test: Wavelet Volume - Resolution: 2560 x 1440 OpenBenchmarking.org MiVoxels / Sec, More Is Better ParaView 5.4.1 Test: Wavelet Volume - Resolution: 2560 x 1440 Threadripper 3960X 600 1200 1800 2400 3000 SE +/- 15.86, N = 3 2811.52
ParaView Test: Wavelet Volume - Resolution: 2560 x 1440 OpenBenchmarking.org Frames / Sec, More Is Better ParaView 5.4.1 Test: Wavelet Volume - Resolution: 2560 x 1440 Threadripper 3960X 40 80 120 160 200 SE +/- 0.99, N = 3 175.72
Tachyon Total Time OpenBenchmarking.org Seconds, Fewer Is Better Tachyon 0.98.9 Total Time Threadripper 3960X 0.3802 0.7604 1.1406 1.5208 1.901 SE +/- 0.0039, N = 3 1.6899 1. (CC) gcc options: -m32 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread
Parboil Test: OpenMP CUTCP OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP CUTCP Threadripper 3960X 0.2845 0.569 0.8535 1.138 1.4225 SE +/- 0.000632, N = 3 1.264657 1. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
MBW Test: Memory Copy, Fixed Block Size - Array Size: 128 MiB OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 128 MiB Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 15.80, N = 3 10863.42 1. (CC) gcc options: -O3 -march=native
MBW Test: Memory Copy - Array Size: 128 MiB OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 128 MiB Threadripper 3960X 2K 4K 6K 8K 10K SE +/- 18.64, N = 3 10893.68 1. (CC) gcc options: -O3 -march=native
CloverLeaf Lagrangian-Eulerian Hydrodynamics OpenBenchmarking.org Seconds, Fewer Is Better CloverLeaf Lagrangian-Eulerian Hydrodynamics Threadripper 3960X 0.1845 0.369 0.5535 0.738 0.9225 SE +/- 0.00, N = 3 0.82 1. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
ctx_clock Context Switch Time OpenBenchmarking.org Clocks, Fewer Is Better ctx_clock Context Switch Time Threadripper 3960X 30 60 90 120 150 152
Bullet Physics Engine Test: Convex Trimesh OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: Convex Trimesh Threadripper 3960X 0.2149 0.4298 0.6447 0.8596 1.0745 SE +/- 0.001348, N = 3 0.955188 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
Bullet Physics Engine Test: Prim Trimesh OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: Prim Trimesh Threadripper 3960X 0.1797 0.3594 0.5391 0.7188 0.8985 SE +/- 0.000720, N = 3 0.798775 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
Bullet Physics Engine Test: 136 Ragdolls OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: 136 Ragdolls Threadripper 3960X 0.4909 0.9818 1.4727 1.9636 2.4545 SE +/- 0.002207, N = 3 2.181623 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
Bullet Physics Engine Test: 1000 Convex OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: 1000 Convex Threadripper 3960X 0.8581 1.7162 2.5743 3.4324 4.2905 SE +/- 0.01304, N = 3 3.81367 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
Bullet Physics Engine Test: 1000 Stack OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: 1000 Stack Threadripper 3960X 0.925 1.85 2.775 3.7 4.625 SE +/- 0.006196, N = 3 4.110941 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
Bullet Physics Engine Test: 3000 Fall OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: 3000 Fall Threadripper 3960X 0.7688 1.5376 2.3064 3.0752 3.844 SE +/- 0.005941, N = 3 3.416941 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
HPC Challenge Test / Class: Max Ping Pong Bandwidth OpenBenchmarking.org MB/s, More Is Better HPC Challenge 1.5.0 Test / Class: Max Ping Pong Bandwidth Threadripper 3960X 5K 10K 15K 20K 25K SE +/- 366.52, N = 3 22107.91 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
HPC Challenge Test / Class: Random Ring Bandwidth OpenBenchmarking.org GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: Random Ring Bandwidth Threadripper 3960X 0.7569 1.5138 2.2707 3.0276 3.7845 SE +/- 0.00987, N = 3 3.36400 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
HPC Challenge Test / Class: Random Ring Latency OpenBenchmarking.org usecs, Fewer Is Better HPC Challenge 1.5.0 Test / Class: Random Ring Latency Threadripper 3960X 0.1028 0.2056 0.3084 0.4112 0.514 SE +/- 0.00045, N = 3 0.45683 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
HPC Challenge Test / Class: G-Random Access OpenBenchmarking.org GUP/s, More Is Better HPC Challenge 1.5.0 Test / Class: G-Random Access Threadripper 3960X 0.0322 0.0644 0.0966 0.1288 0.161 SE +/- 0.00070, N = 3 0.14292 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
HPC Challenge Test / Class: EP-STREAM Triad OpenBenchmarking.org GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: EP-STREAM Triad Threadripper 3960X 0.41 0.82 1.23 1.64 2.05 SE +/- 0.00309, N = 3 1.82228 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
HPC Challenge Test / Class: G-Ptrans OpenBenchmarking.org GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: G-Ptrans Threadripper 3960X 1.2465 2.493 3.7395 4.986 6.2325 SE +/- 0.01609, N = 3 5.54022 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
HPC Challenge Test / Class: EP-DGEMM OpenBenchmarking.org GFLOPS, More Is Better HPC Challenge 1.5.0 Test / Class: EP-DGEMM Threadripper 3960X 7 14 21 28 35 SE +/- 0.45, N = 3 31.64 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
HPC Challenge Test / Class: G-Ffte OpenBenchmarking.org GFLOP/s, More Is Better HPC Challenge 1.5.0 Test / Class: G-Ffte Threadripper 3960X 3 6 9 12 15 SE +/- 0.19, N = 3 10.73 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
HPC Challenge Test / Class: G-Ffte OpenBenchmarking.org GFLOPS, More Is Better HPC Challenge 1.5.0 Test / Class: G-Ffte Threadripper 3960X 3 6 9 12 15 SE +/- 0.19, N = 3 10.73 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
Stream Type: Add OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Add Threadripper 3960X 8K 16K 24K 32K 40K SE +/- 12.82, N = 5 36666.4 1. (CC) gcc options: -O3 -march=native -fopenmp
Stream Type: Triad OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Triad Threadripper 3960X 8K 16K 24K 32K 40K SE +/- 19.57, N = 5 36725.1 1. (CC) gcc options: -O3 -march=native -fopenmp
Stream Type: Scale OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Scale Threadripper 3960X 7K 14K 21K 28K 35K SE +/- 16.43, N = 5 33514.6 1. (CC) gcc options: -O3 -march=native -fopenmp
Phoronix Test Suite v10.8.4