Big Threadripper AMD Ryzen Threadripper 3970X 32-Core testing with a ASUS ROG ZENITH II EXTREME (0702 BIOS) and llvmpipe 63GB on Ubuntu 19.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2003108-PTS-BIGTHREA46&grs .
Big Threadripper Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution Threadripper 3970X 16 Cores AMD Ryzen Threadripper 3970X 32-Core @ 3.70GHz (32 Cores / 64 Threads) ASUS ROG ZENITH II EXTREME (0702 BIOS) AMD Starship/Matisse 64GB 1000GB Force MP600 llvmpipe 63GB AMD Navi 10 HDMI Audio Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200 Ubuntu 19.10 5.3.0-18-generic (x86_64) GNOME Shell 3.34.1 X Server 1.20.5 modesetting 1.20.5 3.3 Mesa 19.2.8 (LLVM 9.0 128 bits) GCC 9.2.1 20191008 + Clang 9.0.0-2 ext4 3840x2160 AMD Ryzen Threadripper 3970X 32-Core @ 3.70GHz (16 Cores) 5.3.0-40-generic (x86_64) 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 - NONE / errors=remount-ro,relatime,rw Processor Details - Scaling Governor: acpi-cpufreq ondemand - CPU Microcode: 0x8301025 Java Details - OpenJDK Runtime Environment (build 11.0.6+10-post-Ubuntu-1ubuntu119.10.1) Python Details - Python 2.7.17 + Python 3.7.5 Security Details - Threadripper 3970X: 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 - 16 Cores: 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 RSB filling + tsx_async_abort: Not affected
Big Threadripper stress-ng: Forking leveldb: Rand Delete leveldb: Seq Fill leveldb: Overwrite leveldb: Rand Fill mysqlslap: 64 leveldb: Hot Read leveldb: Rand Read osbench: Launch Programs leveldb: Seek Rand blogbench: Write osbench: Create Threads cassandra: Writes leveldb: Fill Sync hpcc: G-Ptrans tungsten: Non-Exponential n-queens: Elapsed Time m-queens: Time To Solve stress-ng: Matrix Math pgbench: Buffer Test - Normal Load - Read Only stress-ng: Tsearch embree: Pathtracer - Crown systemd-boot-total: Loader stress-ng: Bsearch embree: Pathtracer ISPC - Crown ospray: NASA Streamlines - Path Tracer stress-ng: Glibc C String Functions ospray: XFrog Forest - SciVis ospray: San Miguel - SciVis stress-ng: Glibc Qsort Data Sorting blender: Barbershop - CPU-Only blender: Pabellon Barcelona - CPU-Only ospray: XFrog Forest - Path Tracer ospray: San Miguel - Path Tracer ospray: NASA Streamlines - SciVis indigobench: Bedroom blender: Classroom - CPU-Only coremark: CoreMark Size 666 - Iterations Per Second blender: Pabellon Barcelona - CPU-Only rocksdb: Read While Writing blender: Classroom - CPU-Only stockfish: Total Time blender: Barbershop - CPU-Only asmfish: 1024 Hash Memory, 26 Depth smallpt: Global Illumination Renderer; 128 Samples blender: BMW27 - CPU-Only stress-ng: Vector Math blender: Fishy Cat - CPU-Only compress-7zip: Compress Speed Test qmcpack: rocksdb: Rand Read cpuminer-opt: m7m ospray: Magnetic Reconnection - SciVis povray: Trace Time blender: Fishy Cat - CPU-Only stress-ng: CPU Stress blender: BMW27 - CPU-Only brl-cad: VGR Performance Metric tungsten: Volumetric Caustic stress-ng: Hsearch hackbench: 32 - Process tungsten: Hair rays1bench: Large Scene tachyon: Total Time mt-dgemm: Sustained Floating-Point Rate indigobench: Supercar go-benchmark: json v-ray: CPU cpuminer-opt: lbry build-mplayer: Time To Compile svt-vp9: Visual Quality Optimized - Bosphorus 1080p parboil: OpenMP CUTCP svt-hevc: 1080p 8-bit YUV To HEVC Video Encode stress-ng: Socket Activity pennant: leblancbig mkl-dnn: Recurrent Neural Network Training - f32 stress-ng: Memory Copying rbenchmark: stress-ng: Crypto cpuminer-opt: skein cpuminer-opt: sha256t appleseed: Emily appleseed: Disney Material c-ray: Total Time - 4K, 16 Rays Per Pixel sysbench: CPU aircrack-ng: primesieve: 1e12 Prime Number Generation pennant: sedovbig openssl: RSA 4096-bit Performance graphics-magick: Swirl build-linux-kernel: Time To Compile namd: ATPase Simulation - 327,506 Atoms rodinia: OpenMP LavaMD ebizzy: npb: EP.D svt-av1: Enc Mode 8 - 1080p rust-prime: Prime Number Test To 200,000,000 go-benchmark: http npb: EP.C intel-mpi: IMB-P2P PingPong build-llvm: Time To Compile graphics-magick: Enhanced graphics-magick: Sharpen dacapobench: Tradebeans hpcc: EP-STREAM Triad rodinia: OpenMP Streamcluster hpcc: Rand Ring Bandwidth graphics-magick: Noise-Gaussian ethr: HTTP - Bandwidth - 2 rocksdb: Rand Fill build-ffmpeg: Time To Compile lczero: BLAS arrayfire: BLAS CPU hpcc: EP-DGEMM build-gcc: Time To Compile build-imagemagick: Time To Compile john-the-ripper: Blowfish rocksdb: Seq Fill parboil: OpenMP MRI Gridding gromacs: Water Benchmark stress-ng: System V Message Passing t-test1: 2 t-test1: 1 compress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 xsbench: dav1d: Summer Nature 4K x264: H.264 Video Encoding mlpack: scikit_qda john-the-ripper: MD5 aom-av1: Speed 8 Realtime go-benchmark: garbage leveldb: Seq Fill hpcc: G-Rand Access mcperf: Set - 64 build-php: Time To Compile leveldb: Overwrite perl-benchmark: Interpreter mkl-dnn: IP Batch All - f32 dacapobench: H2 build-apache: Time To Compile leveldb: Rand Fill mcperf: Add - 64 parboil: OpenMP Stencil renaissance: In-Memory Database Shootout oidn: Memorial renaissance: Akka Unbalanced Cobwebbed Tree parboil: OpenMP LBM ffmpeg: H.264 HD To NTSC DV build2: Time To Compile mkl-dnn: Deconvolution Batch deconv_all - f32 hpcc: G-Ffte askap: tConvolve OpenMP - Gridding intel-mpi: IMB-MPI1 Exchange mkl-dnn: Convolution Batch conv_all - f32 mkl-dnn: Convolution Batch conv_3d - f32 npb: SP.B libgav1: Summer Nature 1080p mlpack: scikit_ica npb: BT.C lammps: Rhodopsin Protein fs-mark: 1000 Files, 1MB Size, No Sync/FSync mkl-dnn: Convolution Batch conv_googlenet_v3 - f32 appleseed: Material Tester gimp: unsharp-mask gimp: auto-levels sockperf: Latency Ping Pong hmmer: Pfam Database Search compilebench: Initial Create dav1d: Summer Nature 1080p intel-mpi: IMB-MPI1 Sendrecv mkl-dnn: Convolution Batch conv_alexnet - f32 tungsten: Water Caustic rsvg: SVG Files To PNG compress-xz: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 9 fio: Seq Read - POSIX AIO - Yes - No - 4KB - Default Test Directory fio: Seq Read - POSIX AIO - Yes - No - 4KB - Default Test Directory rust-mandel: Time To Complete Serial/Parallel Mandelbrot ctx-clock: Context Switch Time fio: Rand Read - POSIX AIO - Yes - No - 4KB - Default Test Directory iozone: 4Kb - 512MB - Write Performance fio: Rand Read - POSIX AIO - Yes - No - 4KB - Default Test Directory octave-benchmark: rodinia: OpenMP CFD Solver iozone: 64Kb - 512MB - Write Performance hpcc: G-HPL postmark: Disk Transaction Performance neatbench: CPU gimp: resize graphics-magick: Resizing darktable: Masskrug - CPU-only osbench: Create Files npb: LU.C mcperf: Delete stress-ng: Semaphores minife: Small ramspeed: Scale - Integer vpxenc: Speed 5 cp2k: Fayalite-FIST Data go-benchmark: build lulesh: mkl-dnn: Deconvolution Batch deconv_1d - f32 leveldb: Fill Sync deepspeech: CPU intel-mpi: IMB-MPI1 Exchange hpcc: Rand Ring Latency mcperf: Get askap: tConvolve MT - Gridding numenta-nab: Windowed Gaussian gegl: Scale compress-rar: Linux Source Tree Archiving To RAR askap: tConvolve MPI - Gridding apache: Static Web Page Serving fs-mark: 4000 Files, 32 Sub Dirs, 1MB Size x265: H.265 1080p Video Encoding mcperf: Get - 64 gimp: rotate npb: FT.C sysbench: Memory renaissance: Apache Spark ALS fio: Seq Write - IO_uring - No - Yes - 4KB - Default Test Directory numenta-nab: Earthgecko Skyline neat: node-express-loadtest: scimark2: Fast Fourier Transform mrbayes: Primate Phylogeny Analysis gegl: Tile Glass tensorflow: Cifar10 askap: tConvolve OpenMP - Degridding systemd-boot-total: Kernel ttsiod-renderer: Phong Rendering With Soft-Shadow Mapping askap: tConvolve MT - Degridding opencv-bench: qmlbench: Canvas Text Simple amg: perl-benchmark: Pod2html fio: Rand Read - IO_uring - No - Yes - 4KB - Default Test Directory gegl: Antialias fio: Rand Read - IO_uring - No - Yes - 4KB - Default Test Directory numenta-nab: Relative Entropy askap: tConvolve MPI - Degridding arrayfire: Conjugate Gradient CPU hpcg: gegl: Crop ior: Read Test fs-mark: 1000 Files, 1MB Size himeno: Poisson Pressure Solver stream: Copy graphics-magick: HWB Color Space ipc-benchmark: Unnamed Unix Domain Socket - 128 redis: GET graphics-magick: Rotate sudokut: Total Time systemd-boot-total: Total bork: File Encryption Time redis: LPUSH byte: Dhrystone 2 npb: MG.C systemd-boot-total: Userspace compress-zstd: Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 osbench: Memory Allocations stream: Triad stream: Scale fio: Seq Write - POSIX AIO - Yes - No - 4KB - Default Test Directory fio: Seq Write - POSIX AIO - Yes - No - 4KB - Default Test Directory ipc-benchmark: Unnamed Pipe - 128 inkscape: SVG Files To PNG scimark2: Dense LU Matrix Factorization rawtherapee: Total Benchmark Time plaidml: No - Inference - ResNet 50 - CPU mkl-dnn: IP Batch 1D - f32 npb: IS.D network-loopback: Time To Transfer 10GB Via Loopback stream: Add gegl: Wavelet Blur sqlite: 1 ipc-benchmark: TCP Socket - 128 mlpack: scikit_linearridgeregression luajit: Fast Fourier Transform memtier-benchmark: Redis darktable: Server Room - CPU-only pyperformance: float redis: SET node-octane: scimark2: Composite ramspeed: Copy - Integer dacapobench: Jython gegl: Cartoon luajit: Sparse Matrix Multiply dacapobench: Tradesoap hpcc: Max Ping Pong Bandwidth fhourstones: Complex Connect-4 Solving cython-bench: blake2: luajit: Monte Carlo luajit: Dense LU Matrix Factorization cpp-perf-bench: Stepanov Vector luajit: Composite git: Time To Complete Common Git Commands espeak: Text-To-Speech Synthesis gegl: Reflect lzbench: Zstd 8 - Compression libreoffice: 20 Documents To PDF blogbench: Read multichase: 1GB Array, 256 Byte Stride, 4 Threads scimark2: Jacobi Successive Over-Relaxation luajit: Jacobi Successive Over-Relaxation glibc-bench: ffs cpp-perf-bench: Atol botan: Twofish lzbench: Brotli 0 - Compression scimark2: Monte Carlo glibc-bench: asinh scimark2: Sparse Matrix Multiply glibc-bench: cos tscp: AI Chess Performance hint: FLOAT redis: SADD mbw: Memory Copy - 4096 MiB gegl: Rotate 90 Degrees java-scimark2: Sparse Matrix Multiply scikit-learn: optcarrot: Optimized Benchmark glibc-bench: sincos gegl: Color Enhance build-gdb: Time To Compile tesseract-ocr: Time To OCR 7 Images glibc-bench: atanh glibc-bench: ffsll radiance: SMP Parallel ipc-benchmark: FIFO Named Pipe - 128 bullet: Prim Trimesh bullet: 3000 Fall bullet: Convex Trimesh bullet: 136 Ragdolls polybench-c: Covariance Computation bullet: Raytests bullet: 1000 Convex minion: Quasigroup cpp-perf-bench: Math Library bullet: 1000 Stack numenta-nab: Bayesian Changepoint glibc-bench: modf glibc-bench: sqrt cpp-perf-bench: Stepanov Abstraction botan: Blowfish glibc-bench: exp lzbench: Crush 0 - Compression glibc-bench: pthread_once minion: Graceful lzbench: Brotli 0 - Decompression mbw: Memory Copy, Fixed Block Size - 4096 MiB renaissance: Apache Spark PageRank lzbench: XZ 0 - Decompression tinymembench: Standard Memcpy systemd-boot-total: Firmware botan: AES-256 cpp-perf-bench: Function Objects minion: Solitaire sqlite-speedtest: Timed Time - Size 1,000 npb: CG.C lzbench: Zstd 1 - Decompression cpp-perf-bench: Ctype gnupg: Linux 4.3 Package File Encryption cachebench: Write mlpack: scikit_svm glibc-bench: sin dcraw: RAW To PPM Image Conversion renaissance: Scala Dotty java-scimark2: Dense LU Matrix Factorization botan: CAST-256 encode-ogg: WAV To Ogg redis: SET swet: Average fftw: Stock - 2D FFT Size 4096 gmpbench: Total Time lzbench: Brotli 2 - Compression compress-lzma: 256MB File Compression compress-gzip: Linux Source Tree Archiving To .tar.gz cryptopp: Keyed Algorithms java-scimark2: Monte Carlo cpp-perf-bench: Rand Numbers glibc-bench: sinh mpcbench: Multi-Precision Benchmark lzbench: Brotli 2 - Decompression numpy: sockperf: Throughput unpack-linux: linux-4.15.tar.xz lzbench: Crush 0 - Decompression tinymembench: Standard Memset gnupg: 2GB File Encryption lzbench: Libdeflate 1 - Compression lzbench: Zstd 8 - Decompression renaissance: Rand Forest fftw: Float + SSE - 2D FFT Size 4096 cachebench: Read polyhedron: ac java-scimark2: Jacobi Successive Over-Relaxation pybench: Total For Average Test Times glibc-bench: tanh polybench-c: Correlation Computation glibc-bench: log2 crafty: Elapsed Time tjbench: Decompression Throughput botan: KASUMI cachebench: Read / Modify / Write encode-flac: WAV To FLAC polybench-c: 3 Matrix Multiplications nginx: Static Web Page Serving java-scimark2: Composite java-scimark2: Fast Fourier Transform radiance: Serial encode-mp3: WAV To MP3 lzbench: Libdeflate 1 - Decompression aobench: 2048 x 2048 - Total Time phpbench: PHP Benchmark Suite fio: Seq Write - POSIX AIO - Yes - No - 4KB - Default Test Directory fio: Seq Read - POSIX AIO - Yes - No - 4KB - Default Test Directory fio: Rand Write - POSIX AIO - Yes - No - 4KB - Default Test Directory fio: Rand Read - POSIX AIO - Yes - No - 4KB - Default Test Directory mutex: Semaphore Release And Acquire mutex: Shared Mutex Lock Shared system-libxml2: 1 MB ffte: N=256, 1D Complex FFT Routine lzbench: Zstd 1 - Compression lzbench: XZ 0 - Compression iperf: 5201 - 10 Seconds - UDP - 64 schbench: 8 - 8 osbench: Create Processes sunflow: Global Illumination + Image Synthesis apache-siege: 250 hbase: Rand Write - 16 hbase: Rand Write - 16 mcperf: Replace mcperf: Prepend mcperf: Append mcperf: Set mcperf: Add rocksdb: Rand Fill Sync cassandra: Reads redis: GET redis: LPOP stress-ng: Context Switching stress-ng: Lsearch darktable: Server Rack - CPU-only darktable: Boat - CPU-only pgbench: Buffer Test - Normal Load - Read Write intel-mpi: IMB-MPI1 Sendrecv intel-mpi: IMB-MPI1 PingPong keydb: cpuminer-opt: myr-gr cpuminer-opt: deep luxcorerender: Rainbow Colors and Prism luxcorerender: DLSC ospray: Magnetic Reconnection - Path Tracer mkl-dnn: Deconvolution Batch deconv_3d - f32 renaissance: Savina Reactors.IO renaissance: Apache Spark Bayes clomp: Static OMP Speedup cloverleaf: Lagrangian-Eulerian Hydrodynamics iperf: 5201 - 10 Seconds - TCP - 64 sockperf: Latency Under Load iozone: 4Kb - 512MB - Write Performance dbench: 12 tiobench: Write - 32MB - 4 iozone: 1MB - 512MB - Write Performance ior: Write Test dbench: 12 fs-mark: 5000 Files, 1MB Size, 4 Threads fio: Rand Write - POSIX AIO - Yes - No - 4KB - Default Test Directory fio: Rand Write - POSIX AIO - Yes - No - 4KB - Default Test Directory fio: Seq Write - IO_uring - No - Yes - 4KB - Default Test Directory fio: Seq Read - IO_uring - No - Yes - 4KB - Default Test Directory fio: Seq Read - IO_uring - No - Yes - 4KB - Default Test Directory fio: Rand Write - IO_uring - No - Yes - 4KB - Default Test Directory fio: Rand Write - IO_uring - No - Yes - 4KB - Default Test Directory Threadripper 3970X 16 Cores 97017.28 256.436 256.328 263.938 259.840 207 44.286 44.353 49.302578 68.592 49874 11.329651 293003 3.6 7.44119 2.64289 3.496 17.945 234235.76 792360.456059 1111.04 37.6572 9976 20222.03 35.5457 13.58 3406391.46 8.99 50 489.81 159.93 153.88 4.69 3.67 66.67 4.906 119.47 1331439.752235 146.02 6204076 109.39 95728787 194.17 95916197 2.894 47.57 88021.72 71.28 196186 2581.7 180626444 1624.30 32.62 13.235 67.04 12151.31 40.40 507345 3.56382 253747.42 31.389 8.18217 225.76 25.0353 10.868534 9.317 1564168 45841 89853 11.581 368.41 0.993342 174.75 22217.76 8623.651 299.858 8324.57 0.2858 9207.85 102703 223623 138.484957 70.304869 16.377 68765.3778 112289.300 6.123 8885.037 9307.4 1590 24.542 0.62357 8.337 2542372 2907.58 69.741 10.272 7825 2831.86 17789641.376812 122.766 669 468 4496 1.90348 20.401 2.20814 631 1844.58 1083225 21.969 2105.11 802.011 29.80307 589.109 13.430 43255 1147975 60.175187 3.288 26168429.69 8.743 25.600 8.544 6079554 324.66 205.31 53.02 2520750 40.88 589712 27.6 0.17138 48126.0 32.037 26.8 0.00136623 17.3297 3886 18.584 27.3 48669.6 5.282141 5898.137 21.96 12746.614 52.969236 7.331 49.576 1713.90 16.12307 4771.16 149.28 968.717 6.82846 33710.70 76.46 49.20 74815.99 17.274 2724.8 56.5800 131.522285 20.165 16.989 2.931 4.842 716.22 726.09 82.61 137.785 18.6835 23.870 18.652 459333 1794 32.093 148 56.2 1594.31 14400 13.067 9.784 1677.55 73.19643 7812 37.6 8.470 2243 3.088 11.446756 65854.97 74147.4 3379188.34 9322.75 42704.74 24.48 494.653 20067677101 9.3908987 2.78688 1938.167 56.68455 6258.07 0.46962 77680.2 2651.59 6.111 5.661 68.089 2682.40 36286.78 560.7 64.90 78526.0 12.437 34599.49 9119242.2266 4708.539 1052 69.663 12.818 10908 356.71 75.413 31.033 42.02 3764.47 5710 667.339 3738.11 66.355 358.8 24786.28 0.11410246 294333 39.003 1151 12.417 3795.21 25.18 10.6707 8.003 1047.58 576.3 4607.312790 52075.8 1499 2416213 2229021.42 693 12.904 37055 8.121 1417209.04 44416335.2 30218.91 31345 170.775 70.318381 57321.8 51667.1 307000 1200 3558893 26.271 983.93 40.810 7.40 3.41655 1464.45 10.404 56819.2 62.395 14.408 3578760 1.47 287.97 2351667.58 1.991 103 1674234.13 50125 718.03 41870.3 4023 90.949 1352.77 3301 21719.647 14702.3 40.858 8.35 526.75 3996.69 77.194 1659.51 4.914 27.353 29.983 107 6.663 1260198 74.561 1298.02 2133.37 1.75870 58.057 391.425 547 157.71 8.41835 793.80 42.2514 1336877 386120425.42117 1851271.35 21587.377 38.165 2683.18 7.973 103.98 12.2622 56.069 83.115 24.084 10.0914 1.75897 173.317 3388324 0.796787 3.394250 0.952042 2.173580 2.141 2.106475 3.787201 107.529621 273.232 4.094888 24.895 2.23442 2.22027 28.622 475.104 4.99317 121 1.76133 41.336115 633 12649.308 16363.844 131 12225.4 20002 5902.141 14.868 60.649045 58.588 10815.59 1503 32.166 12.384 31832.504183492 11.50 42.0366 39.655 5168.066 6674.41 154.147 5.225 1687462.13 811442548 6875.5 5794.6 216 221.246 33.914 696.162775 1686.79 1110.911 7.79696 9050 739 432.11 534240 4.984 500 20042.4 11.427 266 1656 3840.459 21610 3035.03 5.91 1957.92 958 10.6841 2.120 5.88218 8892788 218.899017 100.102 61162.938268635 7.761 2.139 36707.66 3009.12 2043.32 564.243 7.188 1245 31.708 641756 11 19 424 9483.92 543 41 67.1 3587 27.963718 0.517 55626.42 72 418033 47267.1 46495.9 49940.5 45117.5 45047.0 29167 20360 2005988.50 2175519.08 21267958.31 434.81 0.120 6.010 11196.802982 4955.00 5106.63 119630.18 13923 29323 2.07 2.51 444.44 4.91239 13551.880 2677.513 0.71 1.05 54840 13.234 1529.57 665.371 10.550 1554.84 182.76 595.261 485.9 263667 1030 269200 344533 1346 180633 706 10970.25 39.897 42.299 43.846 43.874 1080 8.974 9.313 228.575865 14.888 11700 46.120485 7744 1 2.12629 8.92215 11.321 55.084 76991.04 272392.974476 383.18 13.2284 3542 7239.75 12.8261 4.97 1252570.26 3.32 18.52 181.55 430.81 414.42 1.75 1.37 25 1.852 314.82 508354.399417 382.22 2381360 283.82 36932742 501.07 37415509 7.407 119.58 35109.17 178.46 78488 1039.4 72774397 654.62 13.16 32.246 163.13 5019.09 97.69 210066 8.56420 106584.80 74.353 19.2558 95.94 58.3198 4.666959 4.106 3523585 20433 41063 25.090 172.13 2.122203 82.13 10510.35 4088.414 142.350 3963.81 0.1361 4392.36 49073 106950 289.305987 146.682849 34.157 33077.1662 54172.197 12.538 4341.343 4550.9 784 49.357 1.23901 16.534 1284378 1480.10 35.890 19.958 4059 1486.44 9362495.7391305 232.33 357 252 2452 3.47614 11.266 3.97686 351 3314.792 606976 38.017 3630.24 481.368 49.58070 979.616 22.302 26111 702809 37.092418 2.048 16301159.73 5.449 16.059 13.565 3840404 205.50 131.88 34.16 1626000 62.37 897936 41.8 0.11362 72538.5 48.214 40.3 0.00091186 11.5687 2606 27.542 40.3 71799.0 7.782015 4006.599 14.97 8732.841 36.354837 5.041 71.883 1182.61 11.16673 3330.88 104.95 1369.92 9.50372 24225.64 105.76 36.05 54825.13 12.747 2012.9 76.3541 176.691013 15.116 12.772 2.210 3.678 548.75 556.99 63.49 178.666 24.1260 18.676 23.634 364333 1424 40.173 185 45.2 1283.874348958 11600 10.577 12.077 1361.61 89.99253 6357 30.7 6.923 1847 3.746 13.878943 54335.46 88516.6 3998333.22 10962.7 36372.44 28.62 423.751 17244462905 10.902115 3.22435 1677.707 49.10472 7217.49 0.40788 89370.8 2306.50 7.013 4.940 59.837 2368.48 41019.20 633.2 73.21 88109.7 11.188 31324.20 8262426.9829 4278.405 961 75.992 13.981 11858 328.58 69.520 28.687 45.44 3482.69 6170 617.846 3463.50 61.535 386.4 26671.34 0.12256629 315733 36.361 1234 11.590 3544.17 23.52 9.97276 7.491 1117.52 611.7 4880.015106 49216.8 1417 2555431 2108260.53 732 12.232 39048 8.556 1492623.12 42231623.5 28788.06 32878 163.052 67.155997 54847.9 49498.8 320333 1251 3701949 25.262 946.17 42.414 7.69 3.55042 1521.34 10.806 54720.5 60.114 13.915 3705204 1.42 278.18 2272891.42 2.057 99.7 1723424.59 51582 697.80 43057.69 3921 88.677 1319.00 3219 22271.542 15067.4 39.939 8.54 515.37 3910.40 78.890 1624.14 5.018 27.908 29.411 109 6.541 1283483 73.270 1275.97 2097.74 1.78754 58.987 385.677 539 155.44 8.53711 782.85 42.8141 1319372 381206340.36515 1874999.40 21862.426 37.691 2716.60 7.875 102.75 12.4053 55.429 82.193 23.823 10.2010 1.77800 171.489 3353946 0.804927 3.428156 0.961552 2.195278 2.120 2.127226 3.822767 108.516335 275.729 4.132133 24.671 2.25415 2.23979 28.867 471.104 4.95189 120 1.77594 41.672044 628 12748.608 16238.527 130 12317.7 20153 5858.029 14.978 61.094678 58.173 10888.19 1493 32.378 12.465 31631.791981349 11.43 42.2788 39.428 5197.597 6637.13 154.992 5.253 1696335.08 815597466 6841.8 5767.1 215 220.226 34.071 693.034360 1679.21 1115.816 7.82957 9013 736 430.36 532089 4.964 498 20120.6 11.470 267 1650 3826.803 21534 3024.68 5.89 1951.48 955 10.7165 2.114 5.89799 8869846 218.342705 99.849 61009.394690540 7.776 2.135 36762.59 3005.07 2040.93 564.78 7.182 1244 31.733 641380 319333 369000 273333 11600 11 19 424 543 41 67.1 46315 54.983298 0.954 54186.82 81 475673 84273.8 88961.4 85868.9 75424.0 72837.7 9106 3166 2184449.11 2097030.00 2258922.93 138.27 0.097 5.060 12881.179621 6263.73 5828.12 167550.10 15369.09 6879.91 2.40 2.30 250 3.69166 15896.118 3157.255 3.04 1.26 47216 10.775 1280.55 1382.09 10.409 1335.37 622.53 1466.07 602.3 277000 1082 245750 397600 1553 335000 1309 OpenBenchmarking.org
Stress-NG Test: Forking OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Forking Threadripper 3970X 16 Cores 20K 40K 60K 80K 100K SE +/- 1093.43, N = 3 SE +/- 11.00, N = 3 97017.28 10970.25 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
LevelDB Benchmark: Random Delete OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Random Delete Threadripper 3970X 16 Cores 60 120 180 240 300 SE +/- 0.71, N = 3 SE +/- 0.14, N = 3 256.44 39.90 1. (CXX) g++ options: -O3 -lsnappy -lpthread
LevelDB Benchmark: Sequential Fill OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Sequential Fill Threadripper 3970X 16 Cores 60 120 180 240 300 SE +/- 2.86, N = 3 SE +/- 0.17, N = 3 256.33 42.30 1. (CXX) g++ options: -O3 -lsnappy -lpthread
LevelDB Benchmark: Overwrite OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Overwrite Threadripper 3970X 16 Cores 60 120 180 240 300 SE +/- 3.84, N = 3 SE +/- 0.12, N = 3 263.94 43.85 1. (CXX) g++ options: -O3 -lsnappy -lpthread
LevelDB Benchmark: Random Fill OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Random Fill Threadripper 3970X 16 Cores 60 120 180 240 300 SE +/- 0.33, N = 3 SE +/- 0.15, N = 3 259.84 43.87 1. (CXX) g++ options: -O3 -lsnappy -lpthread
MariaDB Clients: 64 OpenBenchmarking.org Queries Per Second, More Is Better MariaDB 10.3.8 Clients: 64 Threadripper 3970X 16 Cores 200 400 600 800 1000 SE +/- 2.66, N = 3 SE +/- 1.35, N = 3 207 1080 1. (CXX) g++ options: -pie -fPIC -fstack-protector -fno-rtti -O2 -lpthread -llzma -lbz2 -laio -lnuma -lz -lm -lpcre -lcrypt -lssl -lcrypto -ldl
LevelDB Benchmark: Hot Read OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Hot Read Threadripper 3970X 16 Cores 10 20 30 40 50 SE +/- 0.383, N = 11 SE +/- 0.106, N = 15 44.286 8.974 1. (CXX) g++ options: -O3 -lsnappy -lpthread
LevelDB Benchmark: Random Read OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Random Read Threadripper 3970X 16 Cores 10 20 30 40 50 SE +/- 0.404, N = 10 SE +/- 0.093, N = 3 44.353 9.313 1. (CXX) g++ options: -O3 -lsnappy -lpthread
OSBench Test: Launch Programs OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Launch Programs Threadripper 3970X 16 Cores 50 100 150 200 250 SE +/- 0.36, N = 3 SE +/- 0.65, N = 3 49.30 228.58 1. (CC) gcc options: -lm
LevelDB Benchmark: Seek Random OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Seek Random Threadripper 3970X 16 Cores 15 30 45 60 75 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 68.59 14.89 1. (CXX) g++ options: -O3 -lsnappy -lpthread
BlogBench Test: Write OpenBenchmarking.org Final Score, More Is Better BlogBench 1.1 Test: Write Threadripper 3970X 16 Cores 11K 22K 33K 44K 55K SE +/- 1160.31, N = 3 SE +/- 102.18, N = 3 49874 11700 1. (CC) gcc options: -O2 -pthread
OSBench Test: Create Threads OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Threads Threadripper 3970X 16 Cores 10 20 30 40 50 SE +/- 0.05, N = 3 SE +/- 0.22, N = 3 11.33 46.12 1. (CC) gcc options: -lm
Apache Cassandra Test: Writes OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 3.11.4 Test: Writes Threadripper 3970X 16 Cores 60K 120K 180K 240K 300K SE +/- 3852.60, N = 5 SE +/- 21.67, N = 3 293003 7744
LevelDB Benchmark: Fill Sync OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Fill Sync Threadripper 3970X 16 Cores 0.81 1.62 2.43 3.24 4.05 SE +/- 0.00, N = 3 3.6 1.0 1. (CXX) g++ options: -O3 -lsnappy -lpthread
HPC Challenge Test / Class: G-Ptrans OpenBenchmarking.org GB/s, More Is Better HPC Challenge 1.5.0 Test / Class: G-Ptrans Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.01053, N = 3 SE +/- 0.00225, N = 3 7.44119 2.12629 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
Tungsten Renderer Scene: Non-Exponential OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Non-Exponential Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.00612, N = 3 SE +/- 0.01806, N = 3 2.64289 8.92215 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 -lGL -lGLU -lpthread -ldl
N-Queens Elapsed Time OpenBenchmarking.org Seconds, Fewer Is Better N-Queens 1.0 Elapsed Time Threadripper 3970X 16 Cores 3 6 9 12 15 SE +/- 0.006, N = 3 SE +/- 0.012, N = 3 3.496 11.321 1. (CC) gcc options: -static -fopenmp -O3 -march=native
m-queens Time To Solve OpenBenchmarking.org Seconds, Fewer Is Better m-queens 1.2 Time To Solve Threadripper 3970X 16 Cores 12 24 36 48 60 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 17.95 55.08 1. (CXX) g++ options: -fopenmp -O2 -march=native
Stress-NG Test: Matrix Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Matrix Math Threadripper 3970X 16 Cores 50K 100K 150K 200K 250K SE +/- 2518.16, N = 7 SE +/- 114.46, N = 3 234235.76 76991.04 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
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 3970X 16 Cores 200K 400K 600K 800K 1000K SE +/- 3547.45, N = 3 SE +/- 1543.39, N = 3 792360.46 272392.97 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
Stress-NG Test: Tsearch OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Tsearch Threadripper 3970X 16 Cores 200 400 600 800 1000 SE +/- 0.72, N = 3 SE +/- 2.00, N = 3 1111.04 383.18 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
Embree Binary: Pathtracer - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer - Model: Crown Threadripper 3970X 16 Cores 9 18 27 36 45 SE +/- 0.20, N = 3 SE +/- 0.01, N = 3 37.66 13.23 MIN: 34.74 / MAX: 39.17 MIN: 13.15 / MAX: 13.46
Systemd Total Boot Time Test: Loader OpenBenchmarking.org ms, Fewer Is Better Systemd Total Boot Time Test: Loader Threadripper 3970X 16 Cores 2K 4K 6K 8K 10K 9976 3542
Stress-NG Test: Bsearch OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Bsearch Threadripper 3970X 16 Cores 4K 8K 12K 16K 20K SE +/- 115.68, N = 3 SE +/- 66.23, N = 3 20222.03 7239.75 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
Embree Binary: Pathtracer ISPC - Model: Crown OpenBenchmarking.org Frames Per Second, More Is Better Embree 3.6.1 Binary: Pathtracer ISPC - Model: Crown Threadripper 3970X 16 Cores 8 16 24 32 40 SE +/- 0.09, N = 3 SE +/- 0.02, N = 3 35.55 12.83 MIN: 32.78 / MAX: 37.31 MIN: 12.72 / MAX: 13.03
OSPray Demo: NASA Streamlines - Renderer: Path Tracer OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: NASA Streamlines - Renderer: Path Tracer Threadripper 3970X 16 Cores 3 6 9 12 15 SE +/- 0.06, N = 3 SE +/- 0.00, N = 5 13.58 4.97 MIN: 13.33 / MAX: 13.89 MIN: 4.9 / MAX: 5.05
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 3970X 16 Cores 700K 1400K 2100K 2800K 3500K SE +/- 19841.27, N = 3 SE +/- 21196.38, N = 3 3406391.46 1252570.26 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
OSPray Demo: XFrog Forest - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: XFrog Forest - Renderer: SciVis Threadripper 3970X 16 Cores 3 6 9 12 15 SE +/- 0.02, N = 5 SE +/- 0.00, N = 4 8.99 3.32 MIN: 8.77 / MAX: 9.17 MIN: 3.27 / MAX: 3.38
OSPray Demo: San Miguel - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: SciVis Threadripper 3970X 16 Cores 11 22 33 44 55 SE +/- 0.00, N = 12 50.00 18.52 MIN: 43.48 / MAX: 52.63 MIN: 17.86 / MAX: 19.61
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 3970X 16 Cores 110 220 330 440 550 SE +/- 1.89, N = 3 SE +/- 2.46, N = 4 489.81 181.55 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.80 Blend File: Barbershop - Compute: CPU-Only Threadripper 3970X 16 Cores 90 180 270 360 450 SE +/- 0.33, N = 3 SE +/- 0.65, N = 3 159.93 430.81
Blender Blend File: Pabellon Barcelona - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.82 Blend File: Pabellon Barcelona - Compute: CPU-Only Threadripper 3970X 16 Cores 90 180 270 360 450 SE +/- 0.59, N = 3 SE +/- 0.44, N = 3 153.88 414.42
OSPray Demo: XFrog Forest - Renderer: Path Tracer OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: XFrog Forest - Renderer: Path Tracer Threadripper 3970X 16 Cores 1.0553 2.1106 3.1659 4.2212 5.2765 SE +/- 0.00, N = 12 SE +/- 0.00, N = 3 4.69 1.75 MIN: 4.65 / MAX: 4.76 MIN: 1.73 / MAX: 1.77
OSPray Demo: San Miguel - Renderer: Path Tracer OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: San Miguel - Renderer: Path Tracer Threadripper 3970X 16 Cores 0.8258 1.6516 2.4774 3.3032 4.129 SE +/- 0.00, N = 4 SE +/- 0.00, N = 3 3.67 1.37 MIN: 3.65 / MAX: 3.72 MIN: 1.36 / MAX: 1.38
OSPray Demo: NASA Streamlines - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: NASA Streamlines - Renderer: SciVis Threadripper 3970X 16 Cores 15 30 45 60 75 SE +/- 0.00, N = 12 66.67 25.00 MIN: 52.63 / MAX: 71.43 MIN: 23.81 / MAX: 25.64
IndigoBench Scene: Bedroom OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.0.64 Scene: Bedroom Threadripper 3970X 16 Cores 1.1039 2.2078 3.3117 4.4156 5.5195 SE +/- 0.006, N = 3 SE +/- 0.002, N = 3 4.906 1.852
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.82 Blend File: Classroom - Compute: CPU-Only Threadripper 3970X 16 Cores 70 140 210 280 350 SE +/- 0.31, N = 3 SE +/- 0.36, N = 3 119.47 314.82
Coremark CoreMark Size 666 - Iterations Per Second OpenBenchmarking.org Iterations/Sec, More Is Better Coremark 1.0 CoreMark Size 666 - Iterations Per Second Threadripper 3970X 16 Cores 300K 600K 900K 1200K 1500K SE +/- 6863.17, N = 3 SE +/- 1593.11, N = 3 1331439.75 508354.40 1. (CC) gcc options: -O2 -lrt" -lrt
Blender Blend File: Pabellon Barcelona - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.80 Blend File: Pabellon Barcelona - Compute: CPU-Only Threadripper 3970X 16 Cores 80 160 240 320 400 SE +/- 0.24, N = 3 SE +/- 0.17, N = 3 146.02 382.22
Facebook RocksDB Test: Read While Writing OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Read While Writing Threadripper 3970X 16 Cores 1.3M 2.6M 3.9M 5.2M 6.5M SE +/- 71829.99, N = 6 SE +/- 32658.12, N = 4 6204076 2381360 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
Blender Blend File: Classroom - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.80 Blend File: Classroom - Compute: CPU-Only Threadripper 3970X 16 Cores 60 120 180 240 300 SE +/- 0.18, N = 3 SE +/- 0.30, N = 3 109.39 283.82
Stockfish Total Time OpenBenchmarking.org Nodes Per Second, More Is Better Stockfish 9 Total Time Threadripper 3970X 16 Cores 20M 40M 60M 80M 100M SE +/- 914534.22, N = 3 SE +/- 303886.69, N = 3 95728787 36932742 1. (CXX) g++ options: -m64 -lpthread -fno-exceptions -std=c++11 -pedantic -O3 -msse -msse3 -mpopcnt -flto
Blender Blend File: Barbershop - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.82 Blend File: Barbershop - Compute: CPU-Only Threadripper 3970X 16 Cores 110 220 330 440 550 SE +/- 0.21, N = 3 SE +/- 0.54, N = 3 194.17 501.07
asmFish 1024 Hash Memory, 26 Depth OpenBenchmarking.org Nodes/second, More Is Better asmFish 2018-07-23 1024 Hash Memory, 26 Depth Threadripper 3970X 16 Cores 20M 40M 60M 80M 100M SE +/- 334321.64, N = 3 SE +/- 159073.11, N = 3 95916197 37415509
Smallpt Global Illumination Renderer; 128 Samples OpenBenchmarking.org Seconds, Fewer Is Better Smallpt 1.0 Global Illumination Renderer; 128 Samples Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.010, N = 3 SE +/- 0.008, N = 3 2.894 7.407 1. (CXX) g++ options: -fopenmp -O3
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.82 Blend File: BMW27 - Compute: CPU-Only Threadripper 3970X 16 Cores 30 60 90 120 150 SE +/- 0.09, N = 3 SE +/- 0.17, N = 3 47.57 119.58
Stress-NG Test: Vector Math OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Vector Math Threadripper 3970X 16 Cores 20K 40K 60K 80K 100K SE +/- 30.84, N = 3 SE +/- 10.48, N = 3 88021.72 35109.17 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.82 Blend File: Fishy Cat - Compute: CPU-Only Threadripper 3970X 16 Cores 40 80 120 160 200 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 71.28 178.46
7-Zip Compression Compress Speed Test OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 16.02 Compress Speed Test Threadripper 3970X 16 Cores 40K 80K 120K 160K 200K SE +/- 801.81, N = 3 SE +/- 152.64, N = 3 196186 78488 1. (CXX) g++ options: -pipe -lpthread
QMCPACK OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.8 Threadripper 3970X 16 Cores 600 1200 1800 2400 3000 2581.7 1039.4 1. (CXX) g++ options: -fopenmp -fomit-frame-pointer -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -march=native -O3 -ffast-math -lm
Facebook RocksDB Test: Random Read OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Read Threadripper 3970X 16 Cores 40M 80M 120M 160M 200M SE +/- 1599226.86, N = 3 SE +/- 155873.46, N = 3 180626444 72774397 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
Cpuminer-Opt Algorithm: m7m OpenBenchmarking.org kH/s - Hash Speed, More Is Better Cpuminer-Opt 3.8.8.1 Algorithm: m7m Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 3.06, N = 3 SE +/- 2.16, N = 3 1624.30 654.62 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
OSPray Demo: Magnetic Reconnection - Renderer: SciVis OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: Magnetic Reconnection - Renderer: SciVis Threadripper 3970X 16 Cores 8 16 24 32 40 SE +/- 0.36, N = 3 SE +/- 0.00, N = 12 32.62 13.16 MIN: 31.25 / MAX: 33.33 MIN: 12.5 / MAX: 13.51
POV-Ray Trace Time OpenBenchmarking.org Seconds, Fewer Is Better POV-Ray 3.7.0.7 Trace Time Threadripper 3970X 16 Cores 7 14 21 28 35 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 13.24 32.25 1. (CXX) g++ options: -pipe -O3 -ffast-math -march=native -pthread -lSDL -lSM -lICE -lX11 -lIlmImf -lImath -lHalf -lIex -lIexMath -lIlmThread -lpthread -ltiff -ljpeg -lpng -lz -lrt -lm -lboost_thread -lboost_system
Blender Blend File: Fishy Cat - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.80 Blend File: Fishy Cat - Compute: CPU-Only Threadripper 3970X 16 Cores 40 80 120 160 200 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 67.04 163.13
Stress-NG Test: CPU Stress OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: CPU Stress Threadripper 3970X 16 Cores 3K 6K 9K 12K 15K SE +/- 35.07, N = 3 SE +/- 4.68, N = 3 12151.31 5019.09 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
Blender Blend File: BMW27 - Compute: CPU-Only OpenBenchmarking.org Seconds, Fewer Is Better Blender 2.80 Blend File: BMW27 - Compute: CPU-Only Threadripper 3970X 16 Cores 20 40 60 80 100 SE +/- 0.05, N = 3 SE +/- 0.11, N = 3 40.40 97.69
BRL-CAD VGR Performance Metric OpenBenchmarking.org VGR Performance Metric, More Is Better BRL-CAD 7.28.0 VGR Performance Metric Threadripper 3970X 16 Cores 110K 220K 330K 440K 550K 507345 210066 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
Tungsten Renderer Scene: Volumetric Caustic OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Volumetric Caustic Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.00339, N = 3 SE +/- 0.00838, N = 3 3.56382 8.56420 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 -lGL -lGLU -lpthread -ldl
Stress-NG Test: Hsearch OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Hsearch Threadripper 3970X 16 Cores 50K 100K 150K 200K 250K SE +/- 134.40, N = 3 SE +/- 141.77, N = 3 253747.42 106584.80 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
Hackbench Count: 32 - Type: Process OpenBenchmarking.org Seconds, Fewer Is Better Hackbench Count: 32 - Type: Process Threadripper 3970X 16 Cores 20 40 60 80 100 SE +/- 0.40, N = 3 SE +/- 0.31, N = 3 31.39 74.35 1. (CC) gcc options: -lpthread
Tungsten Renderer Scene: Hair OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Hair Threadripper 3970X 16 Cores 5 10 15 20 25 SE +/- 0.03105, N = 3 SE +/- 0.01435, N = 3 8.18217 19.25580 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 -lGL -lGLU -lpthread -ldl
rays1bench Large Scene OpenBenchmarking.org mrays/s, More Is Better rays1bench 2020-01-09 Large Scene Threadripper 3970X 16 Cores 50 100 150 200 250 SE +/- 0.30, N = 3 SE +/- 0.15, N = 3 225.76 95.94
Tachyon Total Time OpenBenchmarking.org Seconds, Fewer Is Better Tachyon 0.99b6 Total Time Threadripper 3970X 16 Cores 13 26 39 52 65 SE +/- 0.41, N = 3 SE +/- 0.08, N = 3 25.04 58.32 1. (CC) gcc options: -m64 -O3 -fomit-frame-pointer -ffast-math -ltachyon -lm -lpthread
ACES DGEMM Sustained Floating-Point Rate OpenBenchmarking.org GFLOP/s, More Is Better ACES DGEMM 1.0 Sustained Floating-Point Rate Threadripper 3970X 16 Cores 3 6 9 12 15 SE +/- 0.169806, N = 3 SE +/- 0.029585, N = 3 10.868534 4.666959 1. (CC) gcc options: -O3 -march=native -fopenmp
IndigoBench Scene: Supercar OpenBenchmarking.org M samples/s, More Is Better IndigoBench 4.0.64 Scene: Supercar Threadripper 3970X 16 Cores 3 6 9 12 15 SE +/- 0.005, N = 3 SE +/- 0.005, N = 3 9.317 4.106
Go Benchmarks Test: json OpenBenchmarking.org Nanoseconds/Operation, Fewer Is Better Go Benchmarks Test: json Threadripper 3970X 16 Cores 800K 1600K 2400K 3200K 4000K SE +/- 7331.16, N = 3 SE +/- 16615.41, N = 3 1564168 3523585
Chaos Group V-RAY Mode: CPU OpenBenchmarking.org Ksamples, More Is Better Chaos Group V-RAY 4.10.07 Mode: CPU Threadripper 3970X 16 Cores 10K 20K 30K 40K 50K SE +/- 663.97, N = 3 SE +/- 86.26, N = 3 45841 20433
Cpuminer-Opt Algorithm: lbry OpenBenchmarking.org kH/s - Hash Speed, More Is Better Cpuminer-Opt 3.8.8.1 Algorithm: lbry Threadripper 3970X 16 Cores 20K 40K 60K 80K 100K SE +/- 464.63, N = 3 SE +/- 330.05, N = 15 89853 41063 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Timed MPlayer Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed MPlayer Compilation 1.4 Time To Compile Threadripper 3970X 16 Cores 6 12 18 24 30 SE +/- 0.04, N = 3 SE +/- 0.06, N = 3 11.58 25.09
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 3970X 16 Cores 80 160 240 320 400 SE +/- 4.19, N = 13 SE +/- 2.55, N = 3 368.41 172.13 1. (CC) gcc options: -fPIE -fPIC -fvisibility=hidden -O3 -pie -rdynamic -lpthread -lrt -lm
Parboil Test: OpenMP CUTCP OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP CUTCP Threadripper 3970X 16 Cores 0.4775 0.955 1.4325 1.91 2.3875 SE +/- 0.005586, N = 3 SE +/- 0.019941, N = 3 0.993342 2.122203 1. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
SVT-HEVC 1080p 8-bit YUV To HEVC Video Encode OpenBenchmarking.org Frames Per Second, More Is Better SVT-HEVC 1.4.1 1080p 8-bit YUV To HEVC Video Encode Threadripper 3970X 16 Cores 40 80 120 160 200 SE +/- 0.72, N = 3 SE +/- 0.38, N = 3 174.75 82.13 1. (CC) gcc options: -fPIE -fPIC -O3 -O2 -pie -rdynamic -lpthread -lrt
Stress-NG Test: Socket Activity OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Socket Activity Threadripper 3970X 16 Cores 5K 10K 15K 20K 25K SE +/- 93.30, N = 3 SE +/- 30.56, N = 3 22217.76 10510.35 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
Pennant Test: leblancbig OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: leblancbig Threadripper 3970X 16 Cores 2K 4K 6K 8K 10K SE +/- 2.82, N = 3 SE +/- 1.62, N = 3 8623.65 4088.41 1. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi
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 3970X 16 Cores 70 140 210 280 350 SE +/- 2.80, N = 10 SE +/- 0.28, N = 3 299.86 142.35 MIN: 188.07 MIN: 140.83 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
Stress-NG Test: Memory Copying OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Memory Copying Threadripper 3970X 16 Cores 2K 4K 6K 8K 10K SE +/- 46.71, N = 3 SE +/- 6.58, N = 3 8324.57 3963.81 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
R Benchmark OpenBenchmarking.org Seconds, Fewer Is Better R Benchmark Threadripper 3970X 16 Cores 0.0643 0.1286 0.1929 0.2572 0.3215 SE +/- 0.0005, N = 3 SE +/- 0.0007, N = 3 0.2858 0.1361 1. R scripting front-end version 3.6.1 (2019-07-05)
Stress-NG Test: Crypto OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Crypto Threadripper 3970X 16 Cores 2K 4K 6K 8K 10K SE +/- 23.39, N = 3 SE +/- 5.17, N = 3 9207.85 4392.36 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
Cpuminer-Opt Algorithm: skein OpenBenchmarking.org kH/s - Hash Speed, More Is Better Cpuminer-Opt 3.8.8.1 Algorithm: skein Threadripper 3970X 16 Cores 20K 40K 60K 80K 100K SE +/- 194.28, N = 3 SE +/- 200.78, N = 3 102703 49073 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: sha256t OpenBenchmarking.org kH/s - Hash Speed, More Is Better Cpuminer-Opt 3.8.8.1 Algorithm: sha256t Threadripper 3970X 16 Cores 50K 100K 150K 200K 250K SE +/- 26.03, N = 3 SE +/- 826.56, N = 3 223623 106950 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Appleseed Scene: Emily OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Emily Threadripper 3970X 16 Cores 60 120 180 240 300 138.48 289.31
Appleseed Scene: Disney Material OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Disney Material Threadripper 3970X 16 Cores 30 60 90 120 150 70.30 146.68
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 3970X 16 Cores 8 16 24 32 40 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 16.38 34.16 1. (CC) gcc options: -lm -lpthread -O3
Sysbench Test: CPU OpenBenchmarking.org Events Per Second, More Is Better Sysbench 2018-07-28 Test: CPU Threadripper 3970X 16 Cores 15K 30K 45K 60K 75K SE +/- 71.18, N = 3 SE +/- 26.51, N = 3 68765.38 33077.17 1. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -march=amdfam10 -rdynamic -ldl -laio -lm
Aircrack-ng OpenBenchmarking.org k/s, More Is Better Aircrack-ng 1.5.2 Threadripper 3970X 16 Cores 20K 40K 60K 80K 100K SE +/- 266.32, N = 3 SE +/- 141.94, N = 3 112289.30 54172.20 1. (CXX) g++ options: -O3 -fvisibility=hidden -masm=intel -rdynamic -lpthread -lz -lcrypto -lhwloc -ldl -lm -pthread
Primesieve 1e12 Prime Number Generation OpenBenchmarking.org Seconds, Fewer Is Better Primesieve 7.4 1e12 Prime Number Generation Threadripper 3970X 16 Cores 3 6 9 12 15 SE +/- 0.021, N = 3 SE +/- 0.033, N = 3 6.123 12.538 1. (CXX) g++ options: -O3 -lpthread
Pennant Test: sedovbig OpenBenchmarking.org Hydro Cycle Time - Seconds, Fewer Is Better Pennant 1.0.1 Test: sedovbig Threadripper 3970X 16 Cores 2K 4K 6K 8K 10K SE +/- 5.38, N = 3 SE +/- 4.90, N = 3 8885.04 4341.34 1. (CXX) g++ options: -fopenmp -pthread -lmpi_cxx -lmpi
OpenSSL RSA 4096-bit Performance OpenBenchmarking.org Signs Per Second, More Is Better OpenSSL 1.1.1 RSA 4096-bit Performance Threadripper 3970X 16 Cores 2K 4K 6K 8K 10K SE +/- 32.86, N = 3 SE +/- 10.52, N = 3 9307.4 4550.9 1. (CC) gcc options: -pthread -m64 -O3 -lssl -lcrypto -ldl
GraphicsMagick Operation: Swirl OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Swirl Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 1.86, N = 3 1590 784 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.4 Time To Compile Threadripper 3970X 16 Cores 11 22 33 44 55 SE +/- 0.31, N = 5 SE +/- 0.59, N = 3 24.54 49.36
NAMD ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.13 ATPase Simulation - 327,506 Atoms Threadripper 3970X 16 Cores 0.2788 0.5576 0.8364 1.1152 1.394 SE +/- 0.00773, N = 15 SE +/- 0.00167, N = 3 0.62357 1.23901
Rodinia Test: OpenMP LavaMD OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenMP LavaMD Threadripper 3970X 16 Cores 4 8 12 16 20 SE +/- 0.047, N = 3 SE +/- 0.025, N = 3 8.337 16.534 1. (CXX) g++ options: -O2 -lOpenCL
ebizzy OpenBenchmarking.org Records/s, More Is Better ebizzy 0.3 Threadripper 3970X 16 Cores 500K 1000K 1500K 2000K 2500K SE +/- 32997.66, N = 5 SE +/- 11166.46, N = 11 2542372 1284378 1. (CC) gcc options: -pthread -lpthread -O3 -march=native
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 3970X 16 Cores 600 1200 1800 2400 3000 SE +/- 2.52, N = 3 SE +/- 0.41, N = 3 2907.58 1480.10 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
SVT-AV1 Encoder Mode: Enc Mode 8 - Input: 1080p OpenBenchmarking.org Frames Per Second, More Is Better SVT-AV1 0.8 Encoder Mode: Enc Mode 8 - Input: 1080p Threadripper 3970X 16 Cores 16 32 48 64 80 SE +/- 0.37, N = 3 SE +/- 0.18, N = 3 69.74 35.89 1. (CXX) g++ options: -fPIE -fPIC -pie
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 Threadripper 3970X 16 Cores 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 10.27 19.96 1. (CC) gcc options: -m64 -pie -nodefaultlibs -ldl -lrt -lpthread -lgcc_s -lc -lm -lutil
Go Benchmarks Test: http OpenBenchmarking.org Nanoseconds/Operation, Fewer Is Better Go Benchmarks Test: http Threadripper 3970X 16 Cores 2K 4K 6K 8K 10K SE +/- 46.62, N = 3 SE +/- 6.17, N = 3 7825 4059
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 3970X 16 Cores 600 1200 1800 2400 3000 SE +/- 48.12, N = 3 SE +/- 2.47, N = 3 2831.86 1486.44 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
Intel MPI Benchmarks Test: IMB-P2P PingPong OpenBenchmarking.org Average Msg/sec, More Is Better Intel MPI Benchmarks 2019.3 Test: IMB-P2P PingPong Threadripper 3970X 16 Cores 4M 8M 12M 16M 20M SE +/- 175648.50, N = 3 SE +/- 15568.26, N = 3 17789641.38 9362495.74 MIN: 4183 / MAX: 42591960 MIN: 3568 / MAX: 21761153 1. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi
Timed LLVM Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed LLVM Compilation 6.0.1 Time To Compile Threadripper 3970X 16 Cores 50 100 150 200 250 122.77 232.33
GraphicsMagick Operation: Enhanced OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Enhanced Threadripper 3970X 16 Cores 140 280 420 560 700 SE +/- 2.91, N = 3 669 357 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 3970X 16 Cores 100 200 300 400 500 SE +/- 3.38, N = 3 SE +/- 0.33, N = 3 468 252 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
DaCapo Benchmark Java Test: Tradebeans OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Tradebeans Threadripper 3970X 16 Cores 1000 2000 3000 4000 5000 SE +/- 10.90, N = 4 SE +/- 14.45, N = 4 4496 2452
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 3970X 16 Cores 0.7821 1.5642 2.3463 3.1284 3.9105 SE +/- 0.00672, N = 3 SE +/- 0.00112, N = 3 1.90348 3.47614 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
Rodinia Test: OpenMP Streamcluster OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenMP Streamcluster Threadripper 3970X 16 Cores 5 10 15 20 25 SE +/- 0.29, N = 3 SE +/- 0.08, N = 3 20.40 11.27 1. (CXX) g++ options: -O2 -lOpenCL
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 3970X 16 Cores 0.8948 1.7896 2.6844 3.5792 4.474 SE +/- 0.02486, N = 3 SE +/- 0.00338, N = 3 2.20814 3.97686 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
GraphicsMagick Operation: Noise-Gaussian OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Noise-Gaussian Threadripper 3970X 16 Cores 140 280 420 560 700 SE +/- 2.00, N = 3 631 351 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
Ethr Server Address: localhost - Protocol: HTTP - Test: Bandwidth - Threads: 2 OpenBenchmarking.org Mbits/sec, More Is Better Ethr 2019-01-02 Server Address: localhost - Protocol: HTTP - Test: Bandwidth - Threads: 2 Threadripper 3970X 16 Cores 700 1400 2100 2800 3500 SE +/- 3.00, N = 3 SE +/- 6.36, N = 3 1844.58 3314.79 MIN: 1810 / MAX: 1910 MIN: 3240 / MAX: 3400
Facebook RocksDB Test: Random Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Fill Threadripper 3970X 16 Cores 200K 400K 600K 800K 1000K SE +/- 8852.93, N = 3 SE +/- 6931.83, N = 3 1083225 606976 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
Timed FFmpeg Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed FFmpeg Compilation 4.2.2 Time To Compile Threadripper 3970X 16 Cores 9 18 27 36 45 SE +/- 0.08, N = 3 SE +/- 0.02, N = 3 21.97 38.02
LeelaChessZero Backend: BLAS OpenBenchmarking.org Nodes Per Second, More Is Better LeelaChessZero 0.23.2 Backend: BLAS Threadripper 3970X 16 Cores 800 1600 2400 3200 4000 SE +/- 19.66, N = 3 SE +/- 26.84, N = 3 2105.11 3630.24 1. (CXX) g++ options: -lpthread
ArrayFire Test: BLAS CPU OpenBenchmarking.org GFLOPS, More Is Better ArrayFire 3.7 Test: BLAS CPU Threadripper 3970X 16 Cores 200 400 600 800 1000 SE +/- 7.27, N = 3 SE +/- 1.49, N = 3 802.01 481.37 1. (CXX) g++ options: -rdynamic
HPC Challenge Test / Class: EP-DGEMM OpenBenchmarking.org GFLOPS, More Is Better HPC Challenge 1.5.0 Test / Class: EP-DGEMM Threadripper 3970X 16 Cores 11 22 33 44 55 SE +/- 0.44, N = 3 SE +/- 0.43, N = 3 29.80 49.58 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
Timed GCC Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed GCC Compilation 8.2 Time To Compile Threadripper 3970X 16 Cores 200 400 600 800 1000 SE +/- 0.83, N = 3 SE +/- 1.05, N = 3 589.11 979.62
Timed ImageMagick Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed ImageMagick Compilation 6.9.0 Time To Compile Threadripper 3970X 16 Cores 5 10 15 20 25 SE +/- 0.06, N = 3 SE +/- 0.12, N = 3 13.43 22.30
John The Ripper Test: Blowfish OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: Blowfish Threadripper 3970X 16 Cores 9K 18K 27K 36K 45K SE +/- 236.95, N = 3 SE +/- 36.67, N = 3 43255 26111 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
Facebook RocksDB Test: Sequential Fill OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Sequential Fill Threadripper 3970X 16 Cores 200K 400K 600K 800K 1000K SE +/- 3258.34, N = 3 SE +/- 8372.80, N = 15 1147975 702809 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
Parboil Test: OpenMP MRI Gridding OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP MRI Gridding Threadripper 3970X 16 Cores 13 26 39 52 65 SE +/- 0.26, N = 3 SE +/- 0.64, N = 3 60.18 37.09 1. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
GROMACS Water Benchmark OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2020 Water Benchmark Threadripper 3970X 16 Cores 0.7398 1.4796 2.2194 2.9592 3.699 SE +/- 0.004, N = 3 SE +/- 0.002, N = 3 3.288 2.048 1. (CXX) g++ options: -O3 -pthread -lrt -lpthread -lm
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 3970X 16 Cores 6M 12M 18M 24M 30M SE +/- 271951.30, N = 15 SE +/- 23221.11, N = 3 26168429.69 16301159.73 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
t-test1 Threads: 2 OpenBenchmarking.org Seconds, Fewer Is Better t-test1 2017-01-13 Threads: 2 Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.005, N = 3 SE +/- 0.008, N = 3 8.743 5.449 1. (CC) gcc options: -pthread
t-test1 Threads: 1 OpenBenchmarking.org Seconds, Fewer Is Better t-test1 2017-01-13 Threads: 1 Threadripper 3970X 16 Cores 6 12 18 24 30 SE +/- 0.11, N = 3 SE +/- 0.04, N = 3 25.60 16.06 1. (CC) gcc options: -pthread
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 3970X 16 Cores 3 6 9 12 15 SE +/- 0.054, N = 3 SE +/- 0.020, N = 3 8.544 13.565 1. (CC) gcc options: -O3 -pthread -lz -llzma
Xsbench OpenBenchmarking.org Lookups/s, More Is Better Xsbench 2017-07-06 Threadripper 3970X 16 Cores 1.3M 2.6M 3.9M 5.2M 6.5M SE +/- 2938.92, N = 3 SE +/- 5142.30, N = 3 6079554 3840404 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 3970X 16 Cores 70 140 210 280 350 SE +/- 0.26, N = 3 SE +/- 0.51, N = 3 324.66 205.50 MIN: 214.04 / MAX: 344.18 MIN: 190.74 / MAX: 228.56 1. (CC) gcc options: -pthread
x264 H.264 Video Encoding OpenBenchmarking.org Frames Per Second, More Is Better x264 2019-12-17 H.264 Video Encoding Threadripper 3970X 16 Cores 50 100 150 200 250 SE +/- 3.52, N = 12 SE +/- 2.11, N = 3 205.31 131.88 1. (CC) gcc options: -ldl -lavformat -lavcodec -lavutil -lswscale -m64 -lm -lpthread -O3 -ffast-math -std=gnu99 -fPIC -fomit-frame-pointer -fno-tree-vectorize
Mlpack Benchmark Benchmark: scikit_qda OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_qda Threadripper 3970X 16 Cores 12 24 36 48 60 SE +/- 0.42, N = 3 SE +/- 0.21, N = 3 53.02 34.16
John The Ripper Test: MD5 OpenBenchmarking.org Real C/S, More Is Better John The Ripper 1.9.0-jumbo-1 Test: MD5 Threadripper 3970X 16 Cores 500K 1000K 1500K 2000K 2500K SE +/- 33415.00, N = 4 SE +/- 3055.05, N = 3 2520750 1626000 1. (CC) gcc options: -m64 -lssl -lcrypto -fopenmp -lgmp -pthread -lm -lz -ldl -lcrypt -lbz2
AOM AV1 Encoder Mode: Speed 8 Realtime OpenBenchmarking.org Frames Per Second, More Is Better AOM AV1 2020-01-10 Encoder Mode: Speed 8 Realtime Threadripper 3970X 16 Cores 14 28 42 56 70 SE +/- 0.21, N = 3 SE +/- 0.03, N = 3 40.88 62.37 1. (CXX) g++ options: -O3 -std=c++11 -U_FORTIFY_SOURCE -lm -lpthread
Go Benchmarks Test: garbage OpenBenchmarking.org Nanoseconds/Operation, Fewer Is Better Go Benchmarks Test: garbage Threadripper 3970X 16 Cores 200K 400K 600K 800K 1000K SE +/- 1243.04, N = 3 SE +/- 2753.72, N = 3 589712 897936
LevelDB Benchmark: Sequential Fill OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Sequential Fill Threadripper 3970X 16 Cores 10 20 30 40 50 SE +/- 0.32, N = 3 SE +/- 0.18, N = 3 27.6 41.8 1. (CXX) g++ options: -O3 -lsnappy -lpthread
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 3970X 16 Cores 0.0386 0.0772 0.1158 0.1544 0.193 SE +/- 0.00021, N = 3 SE +/- 0.00040, N = 3 0.17138 0.11362 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
Memcached mcperf Method: Set - Connections: 64 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.22 Method: Set - Connections: 64 Threadripper 3970X 16 Cores 16K 32K 48K 64K 80K SE +/- 524.58, N = 3 SE +/- 722.58, N = 3 48126.0 72538.5 1. (CC) gcc options: -O2 -lm -rdynamic
Timed PHP Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed PHP Compilation 7.4.2 Time To Compile Threadripper 3970X 16 Cores 11 22 33 44 55 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 32.04 48.21
LevelDB Benchmark: Overwrite OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Overwrite Threadripper 3970X 16 Cores 9 18 27 36 45 SE +/- 0.37, N = 3 SE +/- 0.10, N = 3 26.8 40.3 1. (CXX) g++ options: -O3 -lsnappy -lpthread
Perl Benchmarks Test: Interpreter OpenBenchmarking.org Seconds, Fewer Is Better Perl Benchmarks Test: Interpreter Threadripper 3970X 16 Cores 0.0003 0.0006 0.0009 0.0012 0.0015 SE +/- 0.00000312, N = 3 SE +/- 0.00000115, N = 3 0.00136623 0.00091186
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 3970X 16 Cores 4 8 12 16 20 SE +/- 0.09, N = 3 SE +/- 0.04, N = 3 17.33 11.57 MIN: 11.67 MIN: 11.24 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
DaCapo Benchmark Java Test: H2 OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: H2 Threadripper 3970X 16 Cores 800 1600 2400 3200 4000 SE +/- 34.65, N = 4 SE +/- 32.67, N = 5 3886 2606
Timed Apache Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Apache Compilation 2.4.41 Time To Compile Threadripper 3970X 16 Cores 6 12 18 24 30 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 18.58 27.54
LevelDB Benchmark: Random Fill OpenBenchmarking.org MB/s, More Is Better LevelDB 1.22 Benchmark: Random Fill Threadripper 3970X 16 Cores 9 18 27 36 45 SE +/- 0.03, N = 3 SE +/- 0.13, N = 3 27.3 40.3 1. (CXX) g++ options: -O3 -lsnappy -lpthread
Memcached mcperf Method: Add - Connections: 64 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.22 Method: Add - Connections: 64 Threadripper 3970X 16 Cores 15K 30K 45K 60K 75K SE +/- 803.43, N = 3 SE +/- 347.35, N = 3 48669.6 71799.0 1. (CC) gcc options: -O2 -lm -rdynamic
Parboil Test: OpenMP Stencil OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP Stencil Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.009377, N = 3 SE +/- 0.124137, N = 3 5.282141 7.782015 1. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
Renaissance Test: In-Memory Database Shootout OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: In-Memory Database Shootout Threadripper 3970X 16 Cores 1300 2600 3900 5200 6500 SE +/- 23.00, N = 5 SE +/- 10.28, N = 5 5898.14 4006.60
Intel Open Image Denoise Scene: Memorial OpenBenchmarking.org Images / Sec, More Is Better Intel Open Image Denoise 1.0.0 Scene: Memorial Threadripper 3970X 16 Cores 5 10 15 20 25 SE +/- 0.12, N = 3 SE +/- 0.06, N = 3 21.96 14.97
Renaissance Test: Akka Unbalanced Cobwebbed Tree OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Akka Unbalanced Cobwebbed Tree Threadripper 3970X 16 Cores 3K 6K 9K 12K 15K SE +/- 140.29, N = 7 SE +/- 104.84, N = 6 12746.61 8732.84
Parboil Test: OpenMP LBM OpenBenchmarking.org Seconds, Fewer Is Better Parboil 2.5 Test: OpenMP LBM Threadripper 3970X 16 Cores 12 24 36 48 60 SE +/- 0.75, N = 4 SE +/- 0.08, N = 3 52.97 36.35 1. (CXX) g++ options: -lm -lpthread -lgomp -O3 -ffast-math -fopenmp
FFmpeg H.264 HD To NTSC DV OpenBenchmarking.org Seconds, Fewer Is Better FFmpeg 4.0.2 H.264 HD To NTSC DV Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.056, N = 3 SE +/- 0.039, N = 3 7.331 5.041 1. (CC) gcc options: -lavdevice -lavfilter -lavformat -lavcodec -lswresample -lswscale -lavutil -lXv -lX11 -lXext -lm -lxcb -lxcb-shm -lxcb-shape -lxcb-xfixes -lasound -lSDL2 -lsndio -pthread -lbz2 -llzma -std=c11 -fomit-frame-pointer -fPIC -O3 -fno-math-errno -fno-signed-zeros -fno-tree-vectorize -MMD -MF -MT
Build2 Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Build2 0.12 Time To Compile Threadripper 3970X 16 Cores 16 32 48 64 80 SE +/- 0.08, N = 3 SE +/- 0.80, N = 3 49.58 71.88
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 3970X 16 Cores 400 800 1200 1600 2000 SE +/- 2.16, N = 3 SE +/- 0.54, N = 3 1713.90 1182.61 MIN: 1362.26 MIN: 1163.99 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
HPC Challenge Test / Class: G-Ffte OpenBenchmarking.org GFLOPS, More Is Better HPC Challenge 1.5.0 Test / Class: G-Ffte Threadripper 3970X 16 Cores 4 8 12 16 20 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 16.12 11.17 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
ASKAP Test: tConvolve OpenMP - Gridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve OpenMP - Gridding Threadripper 3970X 16 Cores 1000 2000 3000 4000 5000 SE +/- 42.14, N = 15 SE +/- 29.54, N = 11 4771.16 3330.88 1. (CXX) g++ options: -lpthread
Intel MPI Benchmarks Test: IMB-MPI1 Exchange OpenBenchmarking.org Average usec, More Is Better Intel MPI Benchmarks 2019.3 Test: IMB-MPI1 Exchange Threadripper 3970X 16 Cores 30 60 90 120 150 SE +/- 3.02, N = 3 SE +/- 0.54, N = 3 149.28 104.95 MIN: 0.65 / MAX: 5739.97 MIN: 0.58 / MAX: 3114.62 1. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi
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 3970X 16 Cores 300 600 900 1200 1500 SE +/- 4.86, N = 3 SE +/- 2.68, N = 3 968.72 1369.92 MIN: 791.36 MIN: 1354.97 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
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 3970X 16 Cores 3 6 9 12 15 SE +/- 0.08221, N = 3 SE +/- 0.09666, N = 3 6.82846 9.50372 MIN: 4.63 MIN: 9.16 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
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 3970X 16 Cores 7K 14K 21K 28K 35K SE +/- 446.30, N = 3 SE +/- 37.51, N = 3 33710.70 24225.64 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
libgav1 Video Input: Summer Nature 1080p OpenBenchmarking.org FPS, More Is Better libgav1 2019-10-05 Video Input: Summer Nature 1080p Threadripper 3970X 16 Cores 20 40 60 80 100 SE +/- 0.06, N = 3 SE +/- 0.11, N = 3 76.46 105.76 1. (CXX) g++ options: -O3 -lpthread
Mlpack Benchmark Benchmark: scikit_ica OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_ica Threadripper 3970X 16 Cores 11 22 33 44 55 SE +/- 0.31, N = 3 SE +/- 0.04, N = 3 49.20 36.05
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 3970X 16 Cores 16K 32K 48K 64K 80K SE +/- 105.14, N = 3 SE +/- 12.23, N = 3 74815.99 54825.13 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
LAMMPS Molecular Dynamics Simulator Model: Rhodopsin Protein OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 9Jan2020 Model: Rhodopsin Protein Threadripper 3970X 16 Cores 4 8 12 16 20 SE +/- 0.22, N = 15 SE +/- 0.05, N = 3 17.27 12.75 1. (CXX) g++ options: -O3 -rdynamic -ljpeg -lpng -lz -lfftw3 -lm
FS-Mark Test: 1000 Files, 1MB Size, No Sync/FSync OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 1000 Files, 1MB Size, No Sync/FSync Threadripper 3970X 16 Cores 600 1200 1800 2400 3000 SE +/- 6.09, N = 3 SE +/- 6.33, N = 3 2724.8 2012.9 1. (CC) gcc options: -static
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 3970X 16 Cores 20 40 60 80 100 SE +/- 0.89, N = 3 SE +/- 0.24, N = 3 56.58 76.35 MIN: 41.14 MIN: 75.02 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
Appleseed Scene: Material Tester OpenBenchmarking.org Seconds, Fewer Is Better Appleseed 2.0 Beta Scene: Material Tester Threadripper 3970X 16 Cores 40 80 120 160 200 131.52 176.69
GIMP Test: unsharp-mask OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.8 Test: unsharp-mask Threadripper 3970X 16 Cores 5 10 15 20 25 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 20.17 15.12
GIMP Test: auto-levels OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.8 Test: auto-levels Threadripper 3970X 16 Cores 4 8 12 16 20 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 16.99 12.77
Sockperf Test: Latency Ping Pong OpenBenchmarking.org usec, Fewer Is Better Sockperf 3.4 Test: Latency Ping Pong Threadripper 3970X 16 Cores 0.6595 1.319 1.9785 2.638 3.2975 SE +/- 0.026, N = 25 SE +/- 0.009, N = 5 2.931 2.210 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
Timed HMMer Search Pfam Database Search OpenBenchmarking.org Seconds, Fewer Is Better Timed HMMer Search 2.3.2 Pfam Database Search Threadripper 3970X 16 Cores 1.0895 2.179 3.2685 4.358 5.4475 SE +/- 0.059, N = 3 SE +/- 0.057, N = 3 4.842 3.678 1. (CC) gcc options: -O2 -pthread -lhmmer -lsquid -lm
Compile Bench Test: Initial Create OpenBenchmarking.org MB/s, More Is Better Compile Bench 0.6 Test: Initial Create Threadripper 3970X 16 Cores 150 300 450 600 750 SE +/- 1.98, N = 3 SE +/- 3.20, N = 3 716.22 548.75
dav1d Video Input: Summer Nature 1080p OpenBenchmarking.org FPS, More Is Better dav1d 0.5.0 Video Input: Summer Nature 1080p Threadripper 3970X 16 Cores 160 320 480 640 800 SE +/- 3.50, N = 3 SE +/- 1.76, N = 3 726.09 556.99 MIN: 460.2 / MAX: 805.89 MIN: 471.9 / MAX: 604.99 1. (CC) gcc options: -pthread
Intel MPI Benchmarks Test: IMB-MPI1 Sendrecv OpenBenchmarking.org Average usec, More Is Better Intel MPI Benchmarks 2019.3 Test: IMB-MPI1 Sendrecv Threadripper 3970X 16 Cores 20 40 60 80 100 SE +/- 0.48, N = 3 SE +/- 0.45, N = 15 82.61 63.49 MIN: 0.38 / MAX: 2576.08 MIN: 0.19 / MAX: 1638.64 1. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi
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 3970X 16 Cores 40 80 120 160 200 SE +/- 1.57, N = 6 SE +/- 0.48, N = 3 137.79 178.67 MIN: 97.04 MIN: 176.74 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
Tungsten Renderer Scene: Water Caustic OpenBenchmarking.org Seconds, Fewer Is Better Tungsten Renderer 0.2.2 Scene: Water Caustic Threadripper 3970X 16 Cores 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 18.68 24.13 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 -lGL -lGLU -lpthread -ldl
librsvg Operation: SVG Files To PNG OpenBenchmarking.org Seconds, Fewer Is Better librsvg Operation: SVG Files To PNG Threadripper 3970X 16 Cores 6 12 18 24 30 SE +/- 0.12, N = 3 SE +/- 0.12, N = 3 23.87 18.68 1. rsvg-convert version 2.44.14
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 3970X 16 Cores 6 12 18 24 30 SE +/- 0.08, N = 3 SE +/- 0.04, N = 3 18.65 23.63 1. (CC) gcc options: -pthread -fvisibility=hidden -O2
Flexible IO Tester Type: Sequential Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester Type: Sequential Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 100K 200K 300K 400K 500K SE +/- 1855.92, N = 3 SE +/- 3844.19, N = 3 459333 364333
Flexible IO Tester Type: Sequential Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.12 Type: Sequential Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 400 800 1200 1600 2000 SE +/- 7.64, N = 3 SE +/- 6.56, N = 3 1794 1442
Rust Mandelbrot Time To Complete Serial/Parallel Mandelbrot OpenBenchmarking.org Seconds, Fewer Is Better Rust Mandelbrot Time To Complete Serial/Parallel Mandelbrot Threadripper 3970X 16 Cores 9 18 27 36 45 SE +/- 0.04, N = 3 SE +/- 0.04, N = 3 32.09 40.17 1. (CC) gcc options: -m64 -pie -nodefaultlibs -lutil -ldl -lrt -lpthread -lgcc_s -lc -lm
ctx_clock Context Switch Time OpenBenchmarking.org Clocks, Fewer Is Better ctx_clock Context Switch Time Threadripper 3970X 16 Cores 40 80 120 160 200 148 185
Flexible IO Tester Type: Random Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.12 Type: Random Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 13 26 39 52 65 SE +/- 0.20, N = 3 SE +/- 0.15, N = 3 56.2 45.2
IOzone Record Size: 4Kb - File Size: 512MB - Disk Test: Write Performance OpenBenchmarking.org MB/s, More Is Better IOzone 3.465 Record Size: 4Kb - File Size: 512MB - Disk Test: Write Performance Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 20.79, N = 3 SE +/- 4.10, N = 3 1594.31 1283.87 1. (CC) gcc options: -O3
Flexible IO Tester Type: Random Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester Type: Random Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 3K 6K 9K 12K 15K SE +/- 57.74, N = 3 SE +/- 57.74, N = 3 14400 11600
GNU Octave Benchmark OpenBenchmarking.org Seconds, Fewer Is Better GNU Octave Benchmark 4.4.1 Threadripper 3970X 16 Cores 3 6 9 12 15 SE +/- 0.19, N = 3 SE +/- 0.01, N = 3 13.07 10.58
Rodinia Test: OpenMP CFD Solver OpenBenchmarking.org Seconds, Fewer Is Better Rodinia 2.4 Test: OpenMP CFD Solver Threadripper 3970X 16 Cores 3 6 9 12 15 SE +/- 0.095, N = 3 SE +/- 0.011, N = 3 9.784 12.077 1. (CXX) g++ options: -O2 -lOpenCL
IOzone Record Size: 64Kb - File Size: 512MB - Disk Test: Write Performance OpenBenchmarking.org MB/s, More Is Better IOzone 3.465 Record Size: 64Kb - File Size: 512MB - Disk Test: Write Performance Threadripper 3970X 16 Cores 400 800 1200 1600 2000 SE +/- 6.54, N = 3 SE +/- 3.66, N = 3 1677.55 1361.61 1. (CC) gcc options: -O3
HPC Challenge Test / Class: G-HPL OpenBenchmarking.org GFLOPS, More Is Better HPC Challenge 1.5.0 Test / Class: G-HPL Threadripper 3970X 16 Cores 20 40 60 80 100 SE +/- 0.17, N = 3 SE +/- 0.19, N = 3 73.20 89.99 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
PostMark Disk Transaction Performance OpenBenchmarking.org TPS, More Is Better PostMark 1.51 Disk Transaction Performance Threadripper 3970X 16 Cores 2K 4K 6K 8K 10K SE +/- 53.33, N = 3 7812 6357 1. (CC) gcc options: -O3
NeatBench Acceleration: CPU OpenBenchmarking.org FPS, More Is Better NeatBench 5 Acceleration: CPU Threadripper 3970X 16 Cores 9 18 27 36 45 SE +/- 0.22, N = 3 SE +/- 0.12, N = 3 37.6 30.7
GIMP Test: resize OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.8 Test: resize Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.137, N = 3 SE +/- 0.041, N = 3 8.470 6.923
GraphicsMagick Operation: Resizing OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Resizing Threadripper 3970X 16 Cores 500 1000 1500 2000 2500 SE +/- 8.01, N = 3 SE +/- 1.73, N = 3 2243 1847 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
Darktable Test: Masskrug - Acceleration: CPU-only OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.6.0 Test: Masskrug - Acceleration: CPU-only Threadripper 3970X 16 Cores 0.8429 1.6858 2.5287 3.3716 4.2145 SE +/- 0.017, N = 3 SE +/- 0.009, N = 3 3.088 3.746
OSBench Test: Create Files OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Files Threadripper 3970X 16 Cores 4 8 12 16 20 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 11.45 13.88 1. (CC) gcc options: -lm
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 3970X 16 Cores 14K 28K 42K 56K 70K SE +/- 279.99, N = 3 SE +/- 21.03, N = 3 65854.97 54335.46 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
Memcached mcperf Method: Delete OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Delete Threadripper 3970X 16 Cores 20K 40K 60K 80K 100K SE +/- 80.10, N = 3 SE +/- 702.49, N = 15 74147.4 88516.6 1. (CC) gcc options: -O2 -lm -rdynamic
Stress-NG Test: Semaphores OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Semaphores Threadripper 3970X 16 Cores 900K 1800K 2700K 3600K 4500K SE +/- 11364.25, N = 3 SE +/- 35197.46, N = 15 3379188.34 3998333.22 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
miniFE Problem Size: Small OpenBenchmarking.org CG Mflops, More Is Better miniFE 2.2 Problem Size: Small Threadripper 3970X 16 Cores 2K 4K 6K 8K 10K SE +/- 87.71, N = 3 SE +/- 6.07, N = 3 9322.75 10962.70 1. (CXX) g++ options: -O3 -fopenmp -pthread -lmpi_cxx -lmpi
RAMspeed SMP Type: Scale - Benchmark: Integer OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Scale - Benchmark: Integer Threadripper 3970X 16 Cores 9K 18K 27K 36K 45K 42704.74 36372.44 1. (CC) gcc options: -O3 -march=native
VP9 libvpx Encoding Speed: Speed 5 OpenBenchmarking.org Frames Per Second, More Is Better VP9 libvpx Encoding 1.8.2 Speed: Speed 5 Threadripper 3970X 16 Cores 7 14 21 28 35 SE +/- 0.24, N = 3 SE +/- 0.13, N = 3 24.48 28.62 1. (CXX) g++ options: -m64 -lm -lpthread -O3 -fPIC -U_FORTIFY_SOURCE -std=c++11
CP2K Molecular Dynamics Fayalite-FIST Data OpenBenchmarking.org Seconds, Fewer Is Better CP2K Molecular Dynamics 6.1 Fayalite-FIST Data Threadripper 3970X 16 Cores 110 220 330 440 550 494.65 423.75
Go Benchmarks Test: build OpenBenchmarking.org Nanoseconds/Operation, Fewer Is Better Go Benchmarks Test: build Threadripper 3970X 16 Cores 4000M 8000M 12000M 16000M 20000M SE +/- 170009930.60, N = 3 SE +/- 162720428.03, N = 3 20067677101 17244462905
LULESH OpenBenchmarking.org z/s, More Is Better LULESH 2.0.3 Threadripper 3970X 16 Cores 3 6 9 12 15 SE +/- 0.0012891, N = 3 SE +/- 0.0215340, N = 3 9.3908987 10.9021150 1. (CXX) g++ options: -O3 -fopenmp -lm -pthread -lmpi_cxx -lmpi
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 3970X 16 Cores 0.7255 1.451 2.1765 2.902 3.6275 SE +/- 0.02372, N = 14 SE +/- 0.00642, N = 3 2.78688 3.22435 MIN: 1.78 MIN: 3.13 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
LevelDB Benchmark: Fill Sync OpenBenchmarking.org Microseconds Per Op, Fewer Is Better LevelDB 1.22 Benchmark: Fill Sync Threadripper 3970X 16 Cores 400 800 1200 1600 2000 SE +/- 2.37, N = 3 SE +/- 4.63, N = 3 1938.17 1677.71 1. (CXX) g++ options: -O3 -lsnappy -lpthread
DeepSpeech Acceleration: CPU OpenBenchmarking.org Seconds, Fewer Is Better DeepSpeech 0.6 Acceleration: CPU Threadripper 3970X 16 Cores 13 26 39 52 65 SE +/- 0.10, N = 3 SE +/- 0.09, N = 3 56.68 49.10
Intel MPI Benchmarks Test: IMB-MPI1 Exchange OpenBenchmarking.org Average Mbytes/sec, More Is Better Intel MPI Benchmarks 2019.3 Test: IMB-MPI1 Exchange Threadripper 3970X 16 Cores 1500 3000 4500 6000 7500 SE +/- 53.06, N = 3 SE +/- 11.57, N = 3 6258.07 7217.49 MAX: 25730.7 MAX: 27690.75 1. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi
HPC Challenge Test / Class: Random Ring Latency OpenBenchmarking.org usecs, Fewer Is Better HPC Challenge 1.5.0 Test / Class: Random Ring Latency Threadripper 3970X 16 Cores 0.1057 0.2114 0.3171 0.4228 0.5285 SE +/- 0.00770, N = 3 SE +/- 0.00064, N = 3 0.46962 0.40788 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
Memcached mcperf Method: Get OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Get Threadripper 3970X 16 Cores 20K 40K 60K 80K 100K SE +/- 422.66, N = 3 SE +/- 689.43, N = 15 77680.2 89370.8 1. (CC) gcc options: -O2 -lm -rdynamic
ASKAP Test: tConvolve MT - Gridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MT - Gridding Threadripper 3970X 16 Cores 600 1200 1800 2400 3000 SE +/- 10.28, N = 3 SE +/- 1.91, N = 3 2651.59 2306.50 1. (CXX) g++ options: -lpthread
Numenta Anomaly Benchmark Detector: Windowed Gaussian OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Windowed Gaussian Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.034, N = 3 SE +/- 0.067, N = 3 6.111 7.013
GEGL Operation: Scale OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Scale Threadripper 3970X 16 Cores 1.2737 2.5474 3.8211 5.0948 6.3685 SE +/- 0.040, N = 3 SE +/- 0.031, N = 3 5.661 4.940
RAR Compression Linux Source Tree Archiving To RAR OpenBenchmarking.org Seconds, Fewer Is Better RAR Compression 5.6.1 Linux Source Tree Archiving To RAR Threadripper 3970X 16 Cores 15 30 45 60 75 SE +/- 0.63, N = 3 SE +/- 0.10, N = 3 68.09 59.84
ASKAP Test: tConvolve MPI - Gridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MPI - Gridding Threadripper 3970X 16 Cores 600 1200 1800 2400 3000 SE +/- 2.78, N = 3 SE +/- 1.16, N = 3 2682.40 2368.48 1. (CXX) g++ options: -lpthread
Apache Benchmark Static Web Page Serving OpenBenchmarking.org Requests Per Second, More Is Better Apache Benchmark 2.4.29 Static Web Page Serving Threadripper 3970X 16 Cores 9K 18K 27K 36K 45K SE +/- 25.01, N = 3 SE +/- 50.68, N = 3 36286.78 41019.20 1. (CC) gcc options: -shared -fPIC -O2 -pthread
FS-Mark Test: 4000 Files, 32 Sub Dirs, 1MB Size OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 4000 Files, 32 Sub Dirs, 1MB Size Threadripper 3970X 16 Cores 140 280 420 560 700 SE +/- 3.35, N = 3 SE +/- 4.34, N = 3 560.7 633.2 1. (CC) gcc options: -static
x265 H.265 1080p Video Encoding OpenBenchmarking.org Frames Per Second, More Is Better x265 3.1.2 H.265 1080p Video Encoding Threadripper 3970X 16 Cores 16 32 48 64 80 SE +/- 0.16, N = 3 SE +/- 0.40, N = 3 64.90 73.21 1. (CXX) g++ options: -O3 -rdynamic -lpthread -lrt -ldl -lnuma
Memcached mcperf Method: Get - Connections: 64 OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.22 Method: Get - Connections: 64 Threadripper 3970X 16 Cores 20K 40K 60K 80K 100K SE +/- 810.66, N = 3 SE +/- 238.31, N = 3 78526.0 88109.7 1. (CC) gcc options: -O2 -lm -rdynamic
GIMP Test: rotate OpenBenchmarking.org Seconds, Fewer Is Better GIMP 2.10.8 Test: rotate Threadripper 3970X 16 Cores 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 12.44 11.19
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 3970X 16 Cores 7K 14K 21K 28K 35K SE +/- 17.98, N = 3 SE +/- 46.20, N = 3 34599.49 31324.20 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
Sysbench Test: Memory OpenBenchmarking.org Events Per Second, More Is Better Sysbench 2018-07-28 Test: Memory Threadripper 3970X 16 Cores 2M 4M 6M 8M 10M SE +/- 37741.69, N = 3 SE +/- 81796.05, N = 3 9119242.23 8262426.98 1. (CC) gcc options: -pthread -O3 -funroll-loops -ggdb3 -march=amdfam10 -rdynamic -ldl -laio -lm
Renaissance Test: Apache Spark ALS OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Apache Spark ALS Threadripper 3970X 16 Cores 1000 2000 3000 4000 5000 SE +/- 46.56, N = 5 SE +/- 41.81, N = 5 4708.54 4278.41
Flexible IO Tester Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.18 Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 200 400 600 800 1000 SE +/- 12.94, N = 4 1052 961 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
Numenta Anomaly Benchmark Detector: Earthgecko Skyline OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Earthgecko Skyline Threadripper 3970X 16 Cores 20 40 60 80 100 SE +/- 0.44, N = 3 SE +/- 0.59, N = 3 69.66 75.99
Nebular Empirical Analysis Tool OpenBenchmarking.org Seconds, Fewer Is Better Nebular Empirical Analysis Tool 2020-02-29 Threadripper 3970X 16 Cores 4 8 12 16 20 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 12.82 13.98 1. (F9X) gfortran options: -cpp -ffree-line-length-0 -Jsource/ -fopenmp -O3 -fno-backtrace
Node.js Express HTTP Load Test OpenBenchmarking.org Requests Per Second, More Is Better Node.js Express HTTP Load Test Threadripper 3970X 16 Cores 3K 6K 9K 12K 15K SE +/- 82.23, N = 3 SE +/- 91.62, N = 3 10908 11858 1. Nodejs
v10.15.2
SciMark Computational Test: Fast Fourier Transform OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Fast Fourier Transform Threadripper 3970X 16 Cores 80 160 240 320 400 SE +/- 3.52, N = 3 SE +/- 0.60, N = 3 356.71 328.58 1. (CC) gcc options: -lm
Timed MrBayes Analysis Primate Phylogeny Analysis OpenBenchmarking.org Seconds, Fewer Is Better Timed MrBayes Analysis 3.2.7 Primate Phylogeny Analysis Threadripper 3970X 16 Cores 20 40 60 80 100 SE +/- 0.44, N = 3 SE +/- 0.16, N = 3 75.41 69.52 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 -lreadline
GEGL Operation: Tile Glass OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Tile Glass Threadripper 3970X 16 Cores 7 14 21 28 35 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 31.03 28.69
Tensorflow Build: Cifar10 OpenBenchmarking.org Seconds, Fewer Is Better Tensorflow Build: Cifar10 Threadripper 3970X 16 Cores 10 20 30 40 50 SE +/- 0.53, N = 5 SE +/- 0.07, N = 3 42.02 45.44
ASKAP Test: tConvolve OpenMP - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve OpenMP - Degridding Threadripper 3970X 16 Cores 800 1600 2400 3200 4000 SE +/- 8.15, N = 15 SE +/- 7.16, N = 11 3764.47 3482.69 1. (CXX) g++ options: -lpthread
Systemd Total Boot Time Test: Kernel OpenBenchmarking.org ms, Fewer Is Better Systemd Total Boot Time Test: Kernel Threadripper 3970X 16 Cores 1300 2600 3900 5200 6500 5710 6170
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 3970X 16 Cores 140 280 420 560 700 SE +/- 9.67, N = 13 SE +/- 0.91, N = 3 667.34 617.85 1. (CXX) g++ options: -O3 -fomit-frame-pointer -ffast-math -mtune=native -flto -msse -mrecip -mfpmath=sse -msse2 -mssse3 -lSDL -fopenmp -fwhole-program -lstdc++
ASKAP Test: tConvolve MT - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MT - Degridding Threadripper 3970X 16 Cores 800 1600 2400 3200 4000 SE +/- 12.65, N = 3 SE +/- 2.81, N = 3 3738.11 3463.50 1. (CXX) g++ options: -lpthread
OpenCV Benchmark OpenBenchmarking.org Seconds, Fewer Is Better OpenCV Benchmark 3.3.0 Threadripper 3970X 16 Cores 15 30 45 60 75 SE +/- 0.40, N = 3 SE +/- 0.10, N = 3 66.36 61.54 1. (CXX) g++ options: -std=c++11 -rdynamic
Qmlbench Test: Canvas Text Simple OpenBenchmarking.org Frames, More Is Better Qmlbench 2 Test: Canvas Text Simple Threadripper 3970X 16 Cores 80 160 240 320 400 358.8 386.4 1. (CXX) g++ options: -lpthread
Algebraic Multi-Grid Benchmark OpenBenchmarking.org Figure Of Merit, More Is Better Algebraic Multi-Grid Benchmark Threadripper 3970X 16 Cores 6K 12K 18K 24K 30K SE +/- 14.75, N = 3 SE +/- 24.90, N = 3 24786.28 26671.34 1. (CC) gcc options: -lparcsr_ls -lparcsr_mv -lseq_mv -lIJ_mv -lkrylov -lHYPRE_utilities -lm -fopenmp -pthread -lmpi
Perl Benchmarks Test: Pod2html OpenBenchmarking.org Seconds, Fewer Is Better Perl Benchmarks Test: Pod2html Threadripper 3970X 16 Cores 0.0276 0.0552 0.0828 0.1104 0.138 SE +/- 0.00045305, N = 3 SE +/- 0.00047037, N = 3 0.11410246 0.12256629
Flexible IO Tester Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.18 Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 70K 140K 210K 280K 350K SE +/- 881.92, N = 3 SE +/- 2820.78, N = 15 294333 315733 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
GEGL Operation: Antialias OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Antialias Threadripper 3970X 16 Cores 9 18 27 36 45 SE +/- 0.07, N = 3 SE +/- 0.01, N = 3 39.00 36.36
Flexible IO Tester Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.18 Type: Random Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 2.91, N = 3 SE +/- 10.95, N = 15 1151 1234 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
Numenta Anomaly Benchmark Detector: Relative Entropy OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Relative Entropy Threadripper 3970X 16 Cores 3 6 9 12 15 SE +/- 0.18, N = 3 SE +/- 0.10, N = 3 12.42 11.59
ASKAP Test: tConvolve MPI - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MPI - Degridding Threadripper 3970X 16 Cores 800 1600 2400 3200 4000 SE +/- 6.40, N = 3 SE +/- 0.00, N = 3 3795.21 3544.17 1. (CXX) g++ options: -lpthread
ArrayFire Test: Conjugate Gradient CPU OpenBenchmarking.org ms, Fewer Is Better ArrayFire 3.7 Test: Conjugate Gradient CPU Threadripper 3970X 16 Cores 6 12 18 24 30 SE +/- 0.25, N = 3 SE +/- 0.23, N = 3 25.18 23.52 1. (CXX) g++ options: -rdynamic
High Performance Conjugate Gradient OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 Threadripper 3970X 16 Cores 3 6 9 12 15 SE +/- 0.00239, N = 3 SE +/- 0.00185, N = 3 10.67070 9.97276 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi
GEGL Operation: Crop OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Crop Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.062, N = 3 SE +/- 0.043, N = 3 8.003 7.491
IOR Read Test OpenBenchmarking.org MB/s, More Is Better IOR 3.2.1 Read Test Threadripper 3970X 16 Cores 200 400 600 800 1000 SE +/- 23.08, N = 3 SE +/- 10.56, N = 15 1047.58 1117.52 MIN: 520.5 / MAX: 1149.41 MIN: 229.66 / MAX: 1510.8 1. (CC) gcc options: -O2 -lm -pthread -lmpi
FS-Mark Test: 1000 Files, 1MB Size OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 1000 Files, 1MB Size Threadripper 3970X 16 Cores 130 260 390 520 650 SE +/- 9.01, N = 3 SE +/- 7.97, N = 3 576.3 611.7 1. (CC) gcc options: -static
Himeno Benchmark Poisson Pressure Solver OpenBenchmarking.org MFLOPS, More Is Better Himeno Benchmark 3.0 Poisson Pressure Solver Threadripper 3970X 16 Cores 1000 2000 3000 4000 5000 SE +/- 17.46, N = 3 SE +/- 41.21, N = 3 4607.31 4880.02 1. (CC) gcc options: -O3 -mavx2
Stream Type: Copy OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Copy Threadripper 3970X 16 Cores 11K 22K 33K 44K 55K SE +/- 18.90, N = 5 SE +/- 4.33, N = 5 52075.8 49216.8 1. (CC) gcc options: -O3 -march=native -fopenmp
GraphicsMagick Operation: HWB Color Space OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: HWB Color Space Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 1.53, N = 3 SE +/- 1.33, N = 3 1499 1417 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
IPC_benchmark Type: Unnamed Unix Domain Socket - Message Bytes: 128 OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: Unnamed Unix Domain Socket - Message Bytes: 128 Threadripper 3970X 16 Cores 500K 1000K 1500K 2000K 2500K SE +/- 10877.55, N = 3 SE +/- 26516.90, N = 3 2416213 2555431
Redis Test: GET OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: GET Threadripper 3970X 16 Cores 500K 1000K 1500K 2000K 2500K SE +/- 14781.22, N = 3 SE +/- 27476.98, N = 15 2229021.42 2108260.53 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
GraphicsMagick Operation: Rotate OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.33 Operation: Rotate Threadripper 3970X 16 Cores 160 320 480 640 800 SE +/- 3.46, N = 3 SE +/- 1.53, N = 3 693 732 1. (CC) gcc options: -fopenmp -O2 -pthread -ljbig -lwebp -lwebpmux -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lbz2 -lxml2 -lz -lm -lpthread
Sudokut Total Time OpenBenchmarking.org Seconds, Fewer Is Better Sudokut 0.4 Total Time Threadripper 3970X 16 Cores 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 12.90 12.23
Systemd Total Boot Time Test: Total OpenBenchmarking.org ms, Fewer Is Better Systemd Total Boot Time Test: Total Threadripper 3970X 16 Cores 8K 16K 24K 32K 40K 37055 39048
Bork File Encrypter File Encryption Time OpenBenchmarking.org Seconds, Fewer Is Better Bork File Encrypter 1.4 File Encryption Time Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.005, N = 3 SE +/- 0.011, N = 3 8.121 8.556
Redis Test: LPUSH OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: LPUSH Threadripper 3970X 16 Cores 300K 600K 900K 1200K 1500K SE +/- 8830.13, N = 3 SE +/- 17705.07, N = 15 1417209.04 1492623.12
BYTE Unix Benchmark Computational Test: Dhrystone 2 OpenBenchmarking.org LPS, More Is Better BYTE Unix Benchmark 3.6 Computational Test: Dhrystone 2 Threadripper 3970X 16 Cores 10M 20M 30M 40M 50M SE +/- 385242.29, N = 3 SE +/- 411120.29, N = 3 44416335.2 42231623.5
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 3970X 16 Cores 6K 12K 18K 24K 30K SE +/- 110.51, N = 3 SE +/- 43.00, N = 3 30218.91 28788.06 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
Systemd Total Boot Time Test: Userspace OpenBenchmarking.org ms, Fewer Is Better Systemd Total Boot Time Test: Userspace Threadripper 3970X 16 Cores 7K 14K 21K 28K 35K 31345 32878
Zstd Compression Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 OpenBenchmarking.org Seconds, Fewer Is Better Zstd Compression Compressing ubuntu-16.04.3-server-i386.img, Compression Level 19 Threadripper 3970X 16 Cores 40 80 120 160 200 SE +/- 1.03, N = 3 SE +/- 0.45, N = 3 170.78 163.05
OSBench Test: Memory Allocations OpenBenchmarking.org Ns Per Event, Fewer Is Better OSBench Test: Memory Allocations Threadripper 3970X 16 Cores 16 32 48 64 80 SE +/- 0.29, N = 3 SE +/- 0.22, N = 3 70.32 67.16 1. (CC) gcc options: -lm
Stream Type: Triad OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Triad Threadripper 3970X 16 Cores 12K 24K 36K 48K 60K SE +/- 39.30, N = 5 SE +/- 13.13, N = 5 57321.8 54847.9 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 3970X 16 Cores 11K 22K 33K 44K 55K SE +/- 29.94, N = 5 SE +/- 11.54, N = 5 51667.1 49498.8 1. (CC) gcc options: -O3 -march=native -fopenmp
Flexible IO Tester Type: Sequential Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester Type: Sequential Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 70K 140K 210K 280K 350K SE +/- 4041.45, N = 3 SE +/- 2185.81, N = 3 307000 320333
Flexible IO Tester Type: Sequential Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.12 Type: Sequential Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 16.50, N = 3 SE +/- 2.73, N = 3 1200 1246
IPC_benchmark Type: Unnamed Pipe - Message Bytes: 128 OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: Unnamed Pipe - Message Bytes: 128 Threadripper 3970X 16 Cores 800K 1600K 2400K 3200K 4000K SE +/- 36545.27, N = 8 SE +/- 43879.72, N = 6 3558893 3701949
Inkscape Operation: SVG Files To PNG OpenBenchmarking.org Seconds, Fewer Is Better Inkscape Operation: SVG Files To PNG Threadripper 3970X 16 Cores 6 12 18 24 30 SE +/- 0.09, N = 3 SE +/- 0.05, N = 3 26.27 25.26 1. Inkscape 0.92.4 (5da689c313, 2019-01-14)
SciMark Computational Test: Dense LU Matrix Factorization OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Dense LU Matrix Factorization Threadripper 3970X 16 Cores 200 400 600 800 1000 SE +/- 13.80, N = 3 SE +/- 17.46, N = 3 983.93 946.17 1. (CC) gcc options: -lm
RawTherapee Total Benchmark Time OpenBenchmarking.org Seconds, Fewer Is Better RawTherapee Total Benchmark Time Threadripper 3970X 16 Cores 10 20 30 40 50 SE +/- 0.13, N = 3 SE +/- 0.03, N = 3 40.81 42.41 1. RawTherapee, version 5.6, command line.
PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: ResNet 50 - Device: CPU Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.05, N = 3 SE +/- 0.03, N = 3 7.40 7.69
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 3970X 16 Cores 0.7988 1.5976 2.3964 3.1952 3.994 SE +/- 0.05025, N = 15 SE +/- 0.02584, N = 3 3.41655 3.55042 MIN: 2.08 MIN: 3.4 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
NAS Parallel Benchmarks Test / Class: IS.D OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: IS.D Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 17.87, N = 3 SE +/- 1.71, N = 3 1464.45 1521.34 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
Loopback TCP Network Performance Time To Transfer 10GB Via Loopback OpenBenchmarking.org Seconds, Fewer Is Better Loopback TCP Network Performance Time To Transfer 10GB Via Loopback Threadripper 3970X 16 Cores 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.15, N = 3 10.40 10.81
Stream Type: Add OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Add Threadripper 3970X 16 Cores 12K 24K 36K 48K 60K SE +/- 47.58, N = 5 SE +/- 11.11, N = 5 56819.2 54720.5 1. (CC) gcc options: -O3 -march=native -fopenmp
GEGL Operation: Wavelet Blur OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Wavelet Blur Threadripper 3970X 16 Cores 14 28 42 56 70 SE +/- 0.18, N = 3 SE +/- 0.06, N = 3 62.40 60.11
SQLite Threads / Copies: 1 OpenBenchmarking.org Seconds, Fewer Is Better SQLite 3.30.1 Threads / Copies: 1 Threadripper 3970X 16 Cores 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 14.41 13.92 1. (CC) gcc options: -O2 -lreadline -ltermcap -lz -lm -ldl -lpthread
IPC_benchmark Type: TCP Socket - Message Bytes: 128 OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: TCP Socket - Message Bytes: 128 Threadripper 3970X 16 Cores 800K 1600K 2400K 3200K 4000K SE +/- 13943.76, N = 3 SE +/- 2955.16, N = 3 3578760 3705204
Mlpack Benchmark Benchmark: scikit_linearridgeregression OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_linearridgeregression Threadripper 3970X 16 Cores 0.3308 0.6616 0.9924 1.3232 1.654 SE +/- 0.02, N = 3 SE +/- 0.02, N = 12 1.47 1.42
LuaJIT Test: Fast Fourier Transform OpenBenchmarking.org Mflops, More Is Better LuaJIT 2.1-git Test: Fast Fourier Transform Threadripper 3970X 16 Cores 60 120 180 240 300 SE +/- 2.18, N = 3 SE +/- 1.67, N = 3 287.97 278.18 1. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector
Memtier_benchmark Protocol: Redis OpenBenchmarking.org Ops/sec, More Is Better Memtier_benchmark 1.2.17 Protocol: Redis Threadripper 3970X 16 Cores 500K 1000K 1500K 2000K 2500K SE +/- 34708.07, N = 4 SE +/- 8570.47, N = 3 2351667.58 2272891.42 1. (CXX) g++ options: -O2 -levent -lpthread -lz -lpcre
Darktable Test: Server Room - Acceleration: CPU-only OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.6.0 Test: Server Room - Acceleration: CPU-only Threadripper 3970X 16 Cores 0.4628 0.9256 1.3884 1.8512 2.314 SE +/- 0.009, N = 3 SE +/- 0.010, N = 3 1.991 2.057
PyPerformance Benchmark: float OpenBenchmarking.org Milliseconds, Fewer Is Better PyPerformance 1.0.0 Benchmark: float Threadripper 3970X 16 Cores 20 40 60 80 100 SE +/- 0.09, N = 3 103.0 99.7
Redis Test: SET OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: SET Threadripper 3970X 16 Cores 400K 800K 1200K 1600K 2000K SE +/- 10340.63, N = 3 SE +/- 20540.77, N = 15 1674234.13 1723424.59 1. (CXX) g++ options: -MM -MT -g3 -fvisibility=hidden -O3
Node.js Octane Benchmark OpenBenchmarking.org Score, More Is Better Node.js Octane Benchmark Threadripper 3970X 16 Cores 11K 22K 33K 44K 55K SE +/- 97.00, N = 3 SE +/- 179.38, N = 3 50125 51582 1. Nodejs
v10.15.2
SciMark Computational Test: Composite OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Composite Threadripper 3970X 16 Cores 150 300 450 600 750 SE +/- 7.72, N = 3 SE +/- 3.51, N = 3 718.03 697.80 1. (CC) gcc options: -lm
RAMspeed SMP Type: Copy - Benchmark: Integer OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Copy - Benchmark: Integer Threadripper 3970X 16 Cores 9K 18K 27K 36K 45K 41870.30 43057.69 1. (CC) gcc options: -O3 -march=native
DaCapo Benchmark Java Test: Jython OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Jython Threadripper 3970X 16 Cores 900 1800 2700 3600 4500 SE +/- 14.99, N = 4 SE +/- 2.74, N = 4 4023 3921
GEGL Operation: Cartoon OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Cartoon Threadripper 3970X 16 Cores 20 40 60 80 100 SE +/- 0.05, N = 3 SE +/- 0.08, N = 3 90.95 88.68
LuaJIT Test: Sparse Matrix Multiply OpenBenchmarking.org Mflops, More Is Better LuaJIT 2.1-git Test: Sparse Matrix Multiply Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 11.74, N = 3 SE +/- 1.25, N = 3 1352.77 1319.00 1. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector
DaCapo Benchmark Java Test: Tradesoap OpenBenchmarking.org msec, Fewer Is Better DaCapo Benchmark 9.12-MR1 Java Test: Tradesoap Threadripper 3970X 16 Cores 700 1400 2100 2800 3500 SE +/- 29.24, N = 11 SE +/- 23.31, N = 20 3301 3219
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 3970X 16 Cores 5K 10K 15K 20K 25K SE +/- 271.12, N = 3 SE +/- 607.12, N = 3 21719.65 22271.54 1. (CC) gcc options: -lblas -lm -pthread -lmpi -fomit-frame-pointer -funroll-loops 2. ATLAS + Open MPI 3.1.3
Fhourstones Complex Connect-4 Solving OpenBenchmarking.org Kpos / sec, More Is Better Fhourstones 3.1 Complex Connect-4 Solving Threadripper 3970X 16 Cores 3K 6K 9K 12K 15K SE +/- 35.91, N = 3 SE +/- 53.43, N = 3 14702.3 15067.4 1. (CC) gcc options: -O3
Cython benchmark OpenBenchmarking.org Seconds, Fewer Is Better Cython benchmark 0.27 Threadripper 3970X 16 Cores 9 18 27 36 45 SE +/- 0.04, N = 3 SE +/- 0.18, N = 3 40.86 39.94
BLAKE2 OpenBenchmarking.org Cycles Per Byte, Fewer Is Better BLAKE2 20170307 Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.12, N = 3 SE +/- 0.03, N = 3 8.35 8.54 1. (CC) gcc options: -O3 -march=native -lcrypto -lz
LuaJIT Test: Monte Carlo OpenBenchmarking.org Mflops, More Is Better LuaJIT 2.1-git Test: Monte Carlo Threadripper 3970X 16 Cores 110 220 330 440 550 SE +/- 4.85, N = 3 SE +/- 0.46, N = 3 526.75 515.37 1. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector
LuaJIT Test: Dense LU Matrix Factorization OpenBenchmarking.org Mflops, More Is Better LuaJIT 2.1-git Test: Dense LU Matrix Factorization Threadripper 3970X 16 Cores 900 1800 2700 3600 4500 SE +/- 27.57, N = 3 SE +/- 7.05, N = 3 3996.69 3910.40 1. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector
CppPerformanceBenchmarks Test: Stepanov Vector OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Stepanov Vector Threadripper 3970X 16 Cores 20 40 60 80 100 SE +/- 0.36, N = 3 SE +/- 0.37, N = 3 77.19 78.89 1. (CXX) g++ options: -std=c++11 -O3
LuaJIT Test: Composite OpenBenchmarking.org Mflops, More Is Better LuaJIT 2.1-git Test: Composite Threadripper 3970X 16 Cores 400 800 1200 1600 2000 SE +/- 12.94, N = 3 SE +/- 1.55, N = 3 1659.51 1624.14 1. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector
Git Time To Complete Common Git Commands OpenBenchmarking.org Seconds, Fewer Is Better Git Time To Complete Common Git Commands Threadripper 3970X 16 Cores 1.1291 2.2582 3.3873 4.5164 5.6455 SE +/- 0.014, N = 3 SE +/- 0.006, N = 3 4.914 5.018 1. git version 2.20.1
eSpeak Speech Engine Text-To-Speech Synthesis OpenBenchmarking.org Seconds, Fewer Is Better eSpeak Speech Engine 1.48.04 Text-To-Speech Synthesis Threadripper 3970X 16 Cores 7 14 21 28 35 SE +/- 0.14, N = 3 SE +/- 0.05, N = 3 27.35 27.91 1. (CXX) g++ options: -lstdc++ -lespeak -O2 -fpic -fvisibility=hidden -pedantic -fno-exceptions
GEGL Operation: Reflect OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Reflect Threadripper 3970X 16 Cores 7 14 21 28 35 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 29.98 29.41
lzbench Test: Zstd 8 - Process: Compression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Zstd 8 - Process: Compression Threadripper 3970X 16 Cores 20 40 60 80 100 SE +/- 0.67, N = 3 107 109 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
LibreOffice Test: 20 Documents To PDF OpenBenchmarking.org Seconds, Fewer Is Better LibreOffice Test: 20 Documents To PDF Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.052, N = 22 SE +/- 0.037, N = 22 6.663 6.541 1. LibreOffice 6.3.4.2 30(Build:2)
BlogBench Test: Read OpenBenchmarking.org Final Score, More Is Better BlogBench 1.1 Test: Read Threadripper 3970X 16 Cores 300K 600K 900K 1200K 1500K SE +/- 12676.46, N = 8 SE +/- 3455.51, N = 3 1260198 1283483 1. (CC) gcc options: -O2 -pthread
Multichase Pointer Chaser Test: 1GB Array, 256 Byte Stride, 4 Threads OpenBenchmarking.org ns, Fewer Is Better Multichase Pointer Chaser Test: 1GB Array, 256 Byte Stride, 4 Threads Threadripper 3970X 16 Cores 20 40 60 80 100 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 74.56 73.27 1. (CC) gcc options: -O2 -static -pthread -lrt
SciMark Computational Test: Jacobi Successive Over-Relaxation OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Jacobi Successive Over-Relaxation Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 12.34, N = 3 SE +/- 0.75, N = 3 1298.02 1275.97 1. (CC) gcc options: -lm
LuaJIT Test: Jacobi Successive Over-Relaxation OpenBenchmarking.org Mflops, More Is Better LuaJIT 2.1-git Test: Jacobi Successive Over-Relaxation Threadripper 3970X 16 Cores 500 1000 1500 2000 2500 SE +/- 18.57, N = 3 SE +/- 0.94, N = 3 2133.37 2097.74 1. (CC) gcc options: -lm -ldl -O2 -fomit-frame-pointer -U_FORTIFY_SOURCE -fno-stack-protector
glibc bench Benchmark: ffs OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: ffs Threadripper 3970X 16 Cores 0.4022 0.8044 1.2066 1.6088 2.011 SE +/- 0.01753, N = 3 SE +/- 0.00045, N = 3 1.75870 1.78754
CppPerformanceBenchmarks Test: Atol OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Atol Threadripper 3970X 16 Cores 13 26 39 52 65 SE +/- 0.26, N = 3 SE +/- 0.17, N = 3 58.06 58.99 1. (CXX) g++ options: -std=c++11 -O3
Botan Test: Twofish OpenBenchmarking.org MiB/s, More Is Better Botan 2.13.0 Test: Twofish Threadripper 3970X 16 Cores 80 160 240 320 400 SE +/- 3.16, N = 3 SE +/- 0.02, N = 3 391.43 385.68 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
lzbench Test: Brotli 0 - Process: Compression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Brotli 0 - Process: Compression Threadripper 3970X 16 Cores 120 240 360 480 600 SE +/- 3.67, N = 3 SE +/- 0.33, N = 3 547 539 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
SciMark Computational Test: Monte Carlo OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Monte Carlo Threadripper 3970X 16 Cores 30 60 90 120 150 SE +/- 1.57, N = 3 SE +/- 0.04, N = 3 157.71 155.44 1. (CC) gcc options: -lm
glibc bench Benchmark: asinh OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: asinh Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.07346, N = 3 SE +/- 0.00260, N = 3 8.41835 8.53711
SciMark Computational Test: Sparse Matrix Multiply OpenBenchmarking.org Mflops, More Is Better SciMark 2.0 Computational Test: Sparse Matrix Multiply Threadripper 3970X 16 Cores 200 400 600 800 1000 SE +/- 7.44, N = 3 SE +/- 0.56, N = 3 793.80 782.85 1. (CC) gcc options: -lm
glibc bench Benchmark: cos OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: cos Threadripper 3970X 16 Cores 10 20 30 40 50 SE +/- 0.27, N = 3 SE +/- 0.02, N = 3 42.25 42.81
TSCP AI Chess Performance OpenBenchmarking.org Nodes Per Second, More Is Better TSCP 1.81 AI Chess Performance Threadripper 3970X 16 Cores 300K 600K 900K 1200K 1500K SE +/- 3552.56, N = 5 SE +/- 12160.81, N = 5 1336877 1319372 1. (CC) gcc options: -O3 -march=native
Hierarchical INTegration Test: FLOAT OpenBenchmarking.org QUIPs, More Is Better Hierarchical INTegration 1.0 Test: FLOAT Threadripper 3970X 16 Cores 80M 160M 240M 320M 400M SE +/- 452031.90, N = 3 SE +/- 450887.49, N = 3 386120425.42 381206340.37 1. (CC) gcc options: -O3 -march=native -lm
Redis Test: SADD OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: SADD Threadripper 3970X 16 Cores 400K 800K 1200K 1600K 2000K SE +/- 20821.87, N = 6 SE +/- 19315.80, N = 15 1851271.35 1874999.40
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 3970X 16 Cores 5K 10K 15K 20K 25K SE +/- 72.04, N = 3 SE +/- 82.44, N = 3 21587.38 21862.43 1. (CC) gcc options: -O3 -march=native
GEGL Operation: Rotate 90 Degrees OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Rotate 90 Degrees Threadripper 3970X 16 Cores 9 18 27 36 45 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 38.17 37.69
Java SciMark Computational Test: Sparse Matrix Multiply OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Sparse Matrix Multiply Threadripper 3970X 16 Cores 600 1200 1800 2400 3000 SE +/- 4.74, N = 4 SE +/- 8.43, N = 4 2683.18 2716.60
Scikit-Learn OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 0.22.1 Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.021, N = 3 SE +/- 0.016, N = 3 7.973 7.875
Optcarrot Optimized Benchmark OpenBenchmarking.org FPS, More Is Better Optcarrot Optimized Benchmark Threadripper 3970X 16 Cores 20 40 60 80 100 SE +/- 0.29, N = 4 SE +/- 1.31, N = 4 103.98 102.75 1. ruby 2.5.5p157 (2019-03-15 revision 67260) [x86_64-linux-gnu]
glibc bench Benchmark: sincos OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: sincos Threadripper 3970X 16 Cores 3 6 9 12 15 SE +/- 0.02, N = 3 SE +/- 0.10, N = 13 12.26 12.41
GEGL Operation: Color Enhance OpenBenchmarking.org Seconds, Fewer Is Better GEGL Operation: Color Enhance Threadripper 3970X 16 Cores 13 26 39 52 65 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 56.07 55.43
Timed GDB GNU Debugger Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed GDB GNU Debugger Compilation 9.1 Time To Compile Threadripper 3970X 16 Cores 20 40 60 80 100 SE +/- 0.06, N = 3 SE +/- 0.03, N = 3 83.12 82.19
Tesseract OCR Time To OCR 7 Images OpenBenchmarking.org Seconds, Fewer Is Better Tesseract OCR 4.1.0 Time To OCR 7 Images Threadripper 3970X 16 Cores 6 12 18 24 30 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 24.08 23.82
glibc bench Benchmark: atanh OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: atanh Threadripper 3970X 16 Cores 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 10.09 10.20
glibc bench Benchmark: ffsll OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: ffsll Threadripper 3970X 16 Cores 0.4001 0.8002 1.2003 1.6004 2.0005 SE +/- 0.01102, N = 3 SE +/- 0.00227, N = 3 1.75897 1.77800
Radiance Benchmark Test: SMP Parallel OpenBenchmarking.org Seconds, Fewer Is Better Radiance Benchmark 5.0 Test: SMP Parallel Threadripper 3970X 16 Cores 40 80 120 160 200 173.32 171.49
IPC_benchmark Type: FIFO Named Pipe - Message Bytes: 128 OpenBenchmarking.org Messages Per Second, More Is Better IPC_benchmark Type: FIFO Named Pipe - Message Bytes: 128 Threadripper 3970X 16 Cores 700K 1400K 2100K 2800K 3500K SE +/- 32378.59, N = 15 SE +/- 30085.47, N = 15 3388324 3353946
Bullet Physics Engine Test: Prim Trimesh OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: Prim Trimesh Threadripper 3970X 16 Cores 0.1811 0.3622 0.5433 0.7244 0.9055 SE +/- 0.000329, N = 3 SE +/- 0.000909, N = 3 0.796787 0.804927 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 3970X 16 Cores 0.7713 1.5426 2.3139 3.0852 3.8565 SE +/- 0.002468, N = 3 SE +/- 0.003898, N = 3 3.394250 3.428156 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
Bullet Physics Engine Test: Convex Trimesh OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: Convex Trimesh Threadripper 3970X 16 Cores 0.2163 0.4326 0.6489 0.8652 1.0815 SE +/- 0.000443, N = 3 SE +/- 0.000327, N = 3 0.952042 0.961552 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 3970X 16 Cores 0.4939 0.9878 1.4817 1.9756 2.4695 SE +/- 0.001302, N = 3 SE +/- 0.001501, N = 3 2.173580 2.195278 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
PolyBench-C Test: Covariance Computation OpenBenchmarking.org Seconds, Fewer Is Better PolyBench-C 4.2 Test: Covariance Computation Threadripper 3970X 16 Cores 0.4817 0.9634 1.4451 1.9268 2.4085 SE +/- 0.004, N = 3 SE +/- 0.009, N = 3 2.141 2.120 1. (CC) gcc options: -O3 -march=native
Bullet Physics Engine Test: Raytests OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: Raytests Threadripper 3970X 16 Cores 0.4786 0.9572 1.4358 1.9144 2.393 SE +/- 0.001065, N = 3 SE +/- 0.001575, N = 3 2.106475 2.127226 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 3970X 16 Cores 0.8601 1.7202 2.5803 3.4404 4.3005 SE +/- 0.000553, N = 3 SE +/- 0.003706, N = 3 3.787201 3.822767 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
Minion Benchmark: Quasigroup OpenBenchmarking.org Seconds, Fewer Is Better Minion 1.8 Benchmark: Quasigroup Threadripper 3970X 16 Cores 20 40 60 80 100 SE +/- 0.37, N = 3 SE +/- 0.16, N = 3 107.53 108.52 1. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic
CppPerformanceBenchmarks Test: Math Library OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Math Library Threadripper 3970X 16 Cores 60 120 180 240 300 SE +/- 1.09, N = 3 SE +/- 0.39, N = 3 273.23 275.73 1. (CXX) g++ options: -std=c++11 -O3
Bullet Physics Engine Test: 1000 Stack OpenBenchmarking.org Seconds, Fewer Is Better Bullet Physics Engine 2.81 Test: 1000 Stack Threadripper 3970X 16 Cores 0.9297 1.8594 2.7891 3.7188 4.6485 SE +/- 0.005908, N = 3 SE +/- 0.002167, N = 3 4.094888 4.132133 1. (CXX) g++ options: -O3 -rdynamic -lglut -lGL -lGLU
Numenta Anomaly Benchmark Detector: Bayesian Changepoint OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Bayesian Changepoint Threadripper 3970X 16 Cores 6 12 18 24 30 SE +/- 0.22, N = 3 SE +/- 0.11, N = 3 24.90 24.67
glibc bench Benchmark: modf OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: modf Threadripper 3970X 16 Cores 0.5072 1.0144 1.5216 2.0288 2.536 SE +/- 0.00267, N = 3 SE +/- 0.00154, N = 3 2.23442 2.25415
glibc bench Benchmark: sqrt OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: sqrt Threadripper 3970X 16 Cores 0.504 1.008 1.512 2.016 2.52 SE +/- 0.00274, N = 3 SE +/- 0.00107, N = 3 2.22027 2.23979
CppPerformanceBenchmarks Test: Stepanov Abstraction OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Stepanov Abstraction Threadripper 3970X 16 Cores 7 14 21 28 35 SE +/- 0.01, N = 3 SE +/- 0.16, N = 3 28.62 28.87 1. (CXX) g++ options: -std=c++11 -O3
Botan Test: Blowfish OpenBenchmarking.org MiB/s, More Is Better Botan 2.13.0 Test: Blowfish Threadripper 3970X 16 Cores 100 200 300 400 500 SE +/- 0.50, N = 3 SE +/- 0.01, N = 3 475.10 471.10 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
glibc bench Benchmark: exp OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: exp Threadripper 3970X 16 Cores 1.1235 2.247 3.3705 4.494 5.6175 SE +/- 0.01485, N = 3 SE +/- 0.00851, N = 3 4.99317 4.95189
lzbench Test: Crush 0 - Process: Compression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Crush 0 - Process: Compression Threadripper 3970X 16 Cores 30 60 90 120 150 SE +/- 0.67, N = 3 SE +/- 0.58, N = 3 121 120 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
glibc bench Benchmark: pthread_once OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: pthread_once Threadripper 3970X 16 Cores 0.3996 0.7992 1.1988 1.5984 1.998 SE +/- 0.00270, N = 3 SE +/- 0.00019, N = 3 1.76133 1.77594
Minion Benchmark: Graceful OpenBenchmarking.org Seconds, Fewer Is Better Minion 1.8 Benchmark: Graceful Threadripper 3970X 16 Cores 10 20 30 40 50 SE +/- 0.10, N = 3 SE +/- 0.09, N = 3 41.34 41.67 1. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic
lzbench Test: Brotli 0 - Process: Decompression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Brotli 0 - Process: Decompression Threadripper 3970X 16 Cores 140 280 420 560 700 SE +/- 4.26, N = 3 SE +/- 2.33, N = 3 633 628 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
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 3970X 16 Cores 3K 6K 9K 12K 15K SE +/- 6.90, N = 3 SE +/- 2.58, N = 3 12649.31 12748.61 1. (CC) gcc options: -O3 -march=native
Renaissance Test: Apache Spark PageRank OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Apache Spark PageRank Threadripper 3970X 16 Cores 4K 8K 12K 16K 20K SE +/- 139.90, N = 5 SE +/- 74.89, N = 5 16363.84 16238.53
lzbench Test: XZ 0 - Process: Decompression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: XZ 0 - Process: Decompression Threadripper 3970X 16 Cores 30 60 90 120 150 131 130 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
Tinymembench Standard Memcpy OpenBenchmarking.org MB/s, More Is Better Tinymembench 2018-05-28 Standard Memcpy Threadripper 3970X 16 Cores 3K 6K 9K 12K 15K SE +/- 13.44, N = 3 SE +/- 3.80, N = 3 12225.4 12317.7 1. (CC) gcc options: -O2 -lm
Systemd Total Boot Time Test: Firmware OpenBenchmarking.org ms, Fewer Is Better Systemd Total Boot Time Test: Firmware Threadripper 3970X 16 Cores 4K 8K 12K 16K 20K 20002 20153
Botan Test: AES-256 OpenBenchmarking.org MiB/s, More Is Better Botan 2.13.0 Test: AES-256 Threadripper 3970X 16 Cores 1300 2600 3900 5200 6500 SE +/- 7.95, N = 3 SE +/- 14.95, N = 3 5902.14 5858.03 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
CppPerformanceBenchmarks Test: Function Objects OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Function Objects Threadripper 3970X 16 Cores 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.07, N = 3 14.87 14.98 1. (CXX) g++ options: -std=c++11 -O3
Minion Benchmark: Solitaire OpenBenchmarking.org Seconds, Fewer Is Better Minion 1.8 Benchmark: Solitaire Threadripper 3970X 16 Cores 14 28 42 56 70 SE +/- 0.14, N = 3 SE +/- 0.21, N = 3 60.65 61.09 1. (CXX) g++ options: -std=gnu++11 -O3 -fomit-frame-pointer -rdynamic
SQLite Speedtest Timed Time - Size 1,000 OpenBenchmarking.org Seconds, Fewer Is Better SQLite Speedtest 3.30 Timed Time - Size 1,000 Threadripper 3970X 16 Cores 13 26 39 52 65 SE +/- 0.32, N = 3 SE +/- 0.09, N = 3 58.59 58.17 1. (CC) gcc options: -O2 -ldl -lz -lpthread
NAS Parallel Benchmarks Test / Class: CG.C OpenBenchmarking.org Total Mop/s, More Is Better NAS Parallel Benchmarks 3.4 Test / Class: CG.C Threadripper 3970X 16 Cores 2K 4K 6K 8K 10K SE +/- 35.93, N = 3 SE +/- 13.07, N = 3 10815.59 10888.19 1. (F9X) gfortran options: -O3 -march=native -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi 2. Open MPI 3.1.3
lzbench Test: Zstd 1 - Process: Decompression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Zstd 1 - Process: Decompression Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 4.18, N = 3 1503 1493 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
CppPerformanceBenchmarks Test: Ctype OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Ctype Threadripper 3970X 16 Cores 8 16 24 32 40 SE +/- 0.03, N = 3 SE +/- 0.06, N = 3 32.17 32.38 1. (CXX) g++ options: -std=c++11 -O3
GnuPG Linux 4.3 Package File Encryption OpenBenchmarking.org Seconds, Fewer Is Better GnuPG Linux 4.3 Package File Encryption Threadripper 3970X 16 Cores 3 6 9 12 15 SE +/- 0.16, N = 5 SE +/- 0.17, N = 4 12.38 12.47
CacheBench Test: Write OpenBenchmarking.org MB/s, More Is Better CacheBench Test: Write Threadripper 3970X 16 Cores 7K 14K 21K 28K 35K SE +/- 14.14, N = 3 SE +/- 29.01, N = 3 31832.50 31631.79 MIN: 27271.39 / MAX: 33182.75 MIN: 27804.64 / MAX: 32902.03 1. (CC) gcc options: -lrt
Mlpack Benchmark Benchmark: scikit_svm OpenBenchmarking.org Seconds, Fewer Is Better Mlpack Benchmark Benchmark: scikit_svm Threadripper 3970X 16 Cores 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 11.50 11.43
glibc bench Benchmark: sin OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: sin Threadripper 3970X 16 Cores 10 20 30 40 50 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 42.04 42.28
dcraw RAW To PPM Image Conversion OpenBenchmarking.org Seconds, Fewer Is Better dcraw RAW To PPM Image Conversion Threadripper 3970X 16 Cores 9 18 27 36 45 SE +/- 0.09, N = 3 SE +/- 0.24, N = 3 39.66 39.43 1. (CC) gcc options: -lm
Renaissance Test: Scala Dotty OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Scala Dotty Threadripper 3970X 16 Cores 1100 2200 3300 4400 5500 SE +/- 45.89, N = 5 SE +/- 10.46, N = 5 5168.07 5197.60
Java SciMark Computational Test: Dense LU Matrix Factorization OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Dense LU Matrix Factorization Threadripper 3970X 16 Cores 1400 2800 4200 5600 7000 SE +/- 2.88, N = 4 SE +/- 22.75, N = 4 6674.41 6637.13
Botan Test: CAST-256 OpenBenchmarking.org MiB/s, More Is Better Botan 2.13.0 Test: CAST-256 Threadripper 3970X 16 Cores 30 60 90 120 150 SE +/- 1.54, N = 3 SE +/- 0.27, N = 3 154.15 154.99 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
Ogg Encoding WAV To Ogg OpenBenchmarking.org Seconds, Fewer Is Better Ogg Encoding 1.3.3 WAV To Ogg Threadripper 3970X 16 Cores 1.1819 2.3638 3.5457 4.7276 5.9095 SE +/- 0.009, N = 3 SE +/- 0.007, N = 3 5.225 5.253 1. (CC) gcc options: -O2 -ffast-math -fsigned-char -logg
Redis Test: SET OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: SET Threadripper 3970X 16 Cores 400K 800K 1200K 1600K 2000K SE +/- 12046.69, N = 3 SE +/- 19904.56, N = 3 1687462.13 1696335.08
Swet Average OpenBenchmarking.org Operations Per Second, More Is Better Swet 1.5.16 Average Threadripper 3970X 16 Cores 200M 400M 600M 800M 1000M SE +/- 1647184.49, N = 3 SE +/- 5620679.90, N = 3 811442548 815597466 1. (CC) gcc options: -lm -lpthread -lcurses -lrt
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 3970X 16 Cores 1500 3000 4500 6000 7500 SE +/- 2.20, N = 3 SE +/- 16.83, N = 3 6875.5 6841.8 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
GNU GMP GMPbench Total Time OpenBenchmarking.org GMPbench Score, More Is Better GNU GMP GMPbench 6.1.2 Total Time Threadripper 3970X 16 Cores 1200 2400 3600 4800 6000 5794.6 5767.1 1. (CC) gcc options: -O3 -fomit-frame-pointer -lm
lzbench Test: Brotli 2 - Process: Compression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Brotli 2 - Process: Compression Threadripper 3970X 16 Cores 50 100 150 200 250 SE +/- 0.67, N = 3 216 215 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
LZMA Compression 256MB File Compression OpenBenchmarking.org Seconds, Fewer Is Better LZMA Compression 256MB File Compression Threadripper 3970X 16 Cores 50 100 150 200 250 SE +/- 0.33, N = 3 SE +/- 0.09, N = 3 221.25 220.23 1. (CXX) g++ options: -O2
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 3970X 16 Cores 8 16 24 32 40 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 33.91 34.07
Crypto++ Test: Keyed Algorithms OpenBenchmarking.org MiB/second, More Is Better Crypto++ 8.2 Test: Keyed Algorithms Threadripper 3970X 16 Cores 150 300 450 600 750 SE +/- 1.50, N = 3 SE +/- 0.14, N = 3 696.16 693.03 1. (CXX) g++ options: -g2 -O3 -fPIC -pthread -pipe
Java SciMark Computational Test: Monte Carlo OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Monte Carlo Threadripper 3970X 16 Cores 400 800 1200 1600 2000 SE +/- 2.62, N = 4 SE +/- 2.89, N = 4 1686.79 1679.21
CppPerformanceBenchmarks Test: Random Numbers OpenBenchmarking.org Seconds, Fewer Is Better CppPerformanceBenchmarks 9 Test: Random Numbers Threadripper 3970X 16 Cores 200 400 600 800 1000 SE +/- 0.90, N = 3 SE +/- 0.28, N = 3 1110.91 1115.82 1. (CXX) g++ options: -std=c++11 -O3
glibc bench Benchmark: sinh OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: sinh Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.05215, N = 3 SE +/- 0.01214, N = 3 7.79696 7.82957
GNU MPC Multi-Precision Benchmark OpenBenchmarking.org Global Score, More Is Better GNU MPC 1.1.0 Multi-Precision Benchmark Threadripper 3970X 16 Cores 2K 4K 6K 8K 10K SE +/- 10.00, N = 3 SE +/- 17.64, N = 3 9050 9013 1. (CC) gcc options: -lm -O2 -pedantic -fomit-frame-pointer -m64 -mtune=k8 -march=k8 -MT -MD -MP -MF
lzbench Test: Brotli 2 - Process: Decompression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Brotli 2 - Process: Decompression Threadripper 3970X 16 Cores 160 320 480 640 800 SE +/- 1.20, N = 3 SE +/- 0.88, N = 3 739 736 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
Numpy Benchmark OpenBenchmarking.org Score, More Is Better Numpy Benchmark Threadripper 3970X 16 Cores 90 180 270 360 450 SE +/- 1.07, N = 3 SE +/- 0.33, N = 3 432.11 430.36
Sockperf Test: Throughput OpenBenchmarking.org Messages Per Second, More Is Better Sockperf 3.4 Test: Throughput Threadripper 3970X 16 Cores 110K 220K 330K 440K 550K SE +/- 3079.75, N = 5 SE +/- 5246.61, N = 5 534240 532089 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
Unpacking The Linux Kernel linux-4.15.tar.xz OpenBenchmarking.org Seconds, Fewer Is Better Unpacking The Linux Kernel linux-4.15.tar.xz Threadripper 3970X 16 Cores 1.1214 2.2428 3.3642 4.4856 5.607 SE +/- 0.010, N = 4 SE +/- 0.009, N = 4 4.984 4.964
lzbench Test: Crush 0 - Process: Decompression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Crush 0 - Process: Decompression Threadripper 3970X 16 Cores 110 220 330 440 550 SE +/- 1.15, N = 3 SE +/- 1.00, N = 3 500 498 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
Tinymembench Standard Memset OpenBenchmarking.org MB/s, More Is Better Tinymembench 2018-05-28 Standard Memset Threadripper 3970X 16 Cores 4K 8K 12K 16K 20K SE +/- 54.47, N = 3 SE +/- 20.00, N = 3 20042.4 20120.6 1. (CC) gcc options: -O2 -lm
GnuPG 2GB File Encryption OpenBenchmarking.org Seconds, Fewer Is Better GnuPG 1.4.22 2GB File Encryption Threadripper 3970X 16 Cores 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.02, N = 3 11.43 11.47 1. (CC) gcc options: -O2 -MT -MD -MP -MF
lzbench Test: Libdeflate 1 - Process: Compression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Libdeflate 1 - Process: Compression Threadripper 3970X 16 Cores 60 120 180 240 300 SE +/- 1.45, N = 3 266 267 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
lzbench Test: Zstd 8 - Process: Decompression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Zstd 8 - Process: Decompression Threadripper 3970X 16 Cores 400 800 1200 1600 2000 SE +/- 4.06, N = 3 SE +/- 4.18, N = 3 1656 1650 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
Renaissance Test: Random Forest OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Random Forest Threadripper 3970X 16 Cores 800 1600 2400 3200 4000 SE +/- 29.83, N = 25 SE +/- 37.21, N = 9 3840.46 3826.80
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 3970X 16 Cores 5K 10K 15K 20K 25K SE +/- 102.34, N = 3 SE +/- 48.64, N = 3 21610 21534 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
CacheBench Test: Read OpenBenchmarking.org MB/s, More Is Better CacheBench Test: Read Threadripper 3970X 16 Cores 700 1400 2100 2800 3500 SE +/- 4.12, N = 3 SE +/- 0.65, N = 3 3035.03 3024.68 MIN: 3020.86 / MAX: 3044.34 MIN: 3022.65 / MAX: 3028.8 1. (CC) gcc options: -lrt
Polyhedron Fortran Benchmarks Benchmark: ac OpenBenchmarking.org Seconds, Fewer Is Better Polyhedron Fortran Benchmarks Benchmark: ac Threadripper 3970X 16 Cores 1.3298 2.6596 3.9894 5.3192 6.649 5.91 5.89
Java SciMark Computational Test: Jacobi Successive Over-Relaxation OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Jacobi Successive Over-Relaxation Threadripper 3970X 16 Cores 400 800 1200 1600 2000 SE +/- 2.45, N = 4 SE +/- 1.78, N = 4 1957.92 1951.48
PyBench Total For Average Test Times OpenBenchmarking.org Milliseconds, Fewer Is Better PyBench 2018-02-16 Total For Average Test Times Threadripper 3970X 16 Cores 200 400 600 800 1000 SE +/- 0.88, N = 3 SE +/- 2.31, N = 3 958 955
glibc bench Benchmark: tanh OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: tanh Threadripper 3970X 16 Cores 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 10.68 10.72
PolyBench-C Test: Correlation Computation OpenBenchmarking.org Seconds, Fewer Is Better PolyBench-C 4.2 Test: Correlation Computation Threadripper 3970X 16 Cores 0.477 0.954 1.431 1.908 2.385 SE +/- 0.002, N = 3 SE +/- 0.003, N = 3 2.120 2.114 1. (CC) gcc options: -O3 -march=native
glibc bench Benchmark: log2 OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: log2 Threadripper 3970X 16 Cores 1.327 2.654 3.981 5.308 6.635 SE +/- 0.00811, N = 3 SE +/- 0.01183, N = 3 5.88218 5.89799
Crafty Elapsed Time OpenBenchmarking.org Nodes Per Second, More Is Better Crafty 25.2 Elapsed Time Threadripper 3970X 16 Cores 2M 4M 6M 8M 10M SE +/- 13510.52, N = 3 SE +/- 20746.21, N = 3 8892788 8869846 1. (CC) gcc options: -pthread -lstdc++ -fprofile-use -lm
libjpeg-turbo tjbench Test: Decompression Throughput OpenBenchmarking.org Megapixels/sec, More Is Better libjpeg-turbo tjbench 2.0.2 Test: Decompression Throughput Threadripper 3970X 16 Cores 50 100 150 200 250 SE +/- 0.42, N = 3 SE +/- 0.16, N = 3 218.90 218.34 1. (CC) gcc options: -O3 -rdynamic
Botan Test: KASUMI OpenBenchmarking.org MiB/s, More Is Better Botan 2.13.0 Test: KASUMI Threadripper 3970X 16 Cores 20 40 60 80 100 SE +/- 0.09, N = 3 SE +/- 0.13, N = 3 100.10 99.85 1. (CXX) g++ options: -fstack-protector -m64 -pthread -lbotan-2 -ldl -lrt
CacheBench Test: Read / Modify / Write OpenBenchmarking.org MB/s, More Is Better CacheBench Test: Read / Modify / Write Threadripper 3970X 16 Cores 13K 26K 39K 52K 65K SE +/- 167.50, N = 3 SE +/- 147.71, N = 3 61162.94 61009.39 MIN: 53743.85 / MAX: 65830.07 MIN: 55206.66 / MAX: 65416.9 1. (CC) gcc options: -lrt
FLAC Audio Encoding WAV To FLAC OpenBenchmarking.org Seconds, Fewer Is Better FLAC Audio Encoding 1.3.2 WAV To FLAC Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.024, N = 5 SE +/- 0.007, N = 5 7.761 7.776 1. (CXX) g++ options: -O2 -fvisibility=hidden -logg -lm
PolyBench-C Test: 3 Matrix Multiplications OpenBenchmarking.org Seconds, Fewer Is Better PolyBench-C 4.2 Test: 3 Matrix Multiplications Threadripper 3970X 16 Cores 0.4813 0.9626 1.4439 1.9252 2.4065 SE +/- 0.012, N = 3 SE +/- 0.023, N = 3 2.139 2.135 1. (CC) gcc options: -O3 -march=native
NGINX Benchmark Static Web Page Serving OpenBenchmarking.org Requests Per Second, More Is Better NGINX Benchmark 1.9.9 Static Web Page Serving Threadripper 3970X 16 Cores 8K 16K 24K 32K 40K SE +/- 177.49, N = 3 SE +/- 50.77, N = 3 36707.66 36762.59 1. (CC) gcc options: -lpthread -lcrypt -lcrypto -lz -O3 -march=native
Java SciMark Computational Test: Composite OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Composite Threadripper 3970X 16 Cores 600 1200 1800 2400 3000 SE +/- 1.94, N = 4 SE +/- 7.84, N = 4 3009.12 3005.07
Java SciMark Computational Test: Fast Fourier Transform OpenBenchmarking.org Mflops, More Is Better Java SciMark 2.0 Computational Test: Fast Fourier Transform Threadripper 3970X 16 Cores 400 800 1200 1600 2000 SE +/- 9.49, N = 4 SE +/- 14.00, N = 4 2043.32 2040.93
Radiance Benchmark Test: Serial OpenBenchmarking.org Seconds, Fewer Is Better Radiance Benchmark 5.0 Test: Serial Threadripper 3970X 16 Cores 120 240 360 480 600 564.24 564.78
LAME MP3 Encoding WAV To MP3 OpenBenchmarking.org Seconds, Fewer Is Better LAME MP3 Encoding 3.100 WAV To MP3 Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.020, N = 3 SE +/- 0.007, N = 3 7.188 7.182 1. (CC) gcc options: -O3 -ffast-math -funroll-loops -fschedule-insns2 -fbranch-count-reg -fforce-addr -pipe -lncurses -lm
lzbench Test: Libdeflate 1 - Process: Decompression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Libdeflate 1 - Process: Decompression Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 1.20, N = 3 SE +/- 0.67, N = 3 1245 1244 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
AOBench Size: 2048 x 2048 - Total Time OpenBenchmarking.org Seconds, Fewer Is Better AOBench Size: 2048 x 2048 - Total Time Threadripper 3970X 16 Cores 7 14 21 28 35 SE +/- 0.27, N = 14 SE +/- 0.05, N = 3 31.71 31.73 1. (CC) gcc options: -lm -O3
PHPBench PHP Benchmark Suite OpenBenchmarking.org Score, More Is Better PHPBench 0.8.1 PHP Benchmark Suite Threadripper 3970X 16 Cores 140K 280K 420K 560K 700K SE +/- 808.97, N = 3 SE +/- 266.61, N = 3 641756 641380
Flexible IO Tester Type: Sequential Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.12 Type: Sequential Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory 16 Cores 70K 140K 210K 280K 350K SE +/- 666.67, N = 3 319333
Flexible IO Tester Type: Sequential Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.12 Type: Sequential Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory 16 Cores 80K 160K 240K 320K 400K SE +/- 1527.53, N = 3 369000
Flexible IO Tester Type: Random Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.12 Type: Random Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory 16 Cores 60K 120K 180K 240K 300K SE +/- 2333.33, N = 3 273333
Flexible IO Tester Type: Random Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.12 Type: Random Read - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory 16 Cores 2K 4K 6K 8K 10K 11600
BenchmarkMutex Benchmark: Semaphore Release And Acquire OpenBenchmarking.org ns, Fewer Is Better BenchmarkMutex Benchmark: Semaphore Release And Acquire Threadripper 3970X 16 Cores 3 6 9 12 15 11 11 1. (CXX) g++ options: -std=c++17 -lbenchmark -pthread
BenchmarkMutex Benchmark: Shared Mutex Lock Shared OpenBenchmarking.org ns, Fewer Is Better BenchmarkMutex Benchmark: Shared Mutex Lock Shared Threadripper 3970X 16 Cores 5 10 15 20 25 19 19 1. (CXX) g++ options: -std=c++17 -lbenchmark -pthread
System Libxml2 Parsing Filesize: 1 MB OpenBenchmarking.org ms, Fewer Is Better System Libxml2 Parsing Filesize: 1 MB Threadripper 3970X 16 Cores 90 180 270 360 450 SE +/- 3.06, N = 3 SE +/- 5.08, N = 6 424 424
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 3970X 2K 4K 6K 8K 10K SE +/- 15.75, N = 3 9483.92 1. (F9X) gfortran options: -O3 -fomit-frame-pointer -fopenmp -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
lzbench Test: Zstd 1 - Process: Compression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: Zstd 1 - Process: Compression Threadripper 3970X 16 Cores 120 240 360 480 600 SE +/- 0.67, N = 3 SE +/- 1.53, N = 3 543 543 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
lzbench Test: XZ 0 - Process: Compression OpenBenchmarking.org MB/s, More Is Better lzbench 1.8 Test: XZ 0 - Process: Compression Threadripper 3970X 16 Cores 9 18 27 36 45 41 41 1. (CXX) g++ options: -pthread -fomit-frame-pointer -fstrict-aliasing -ffast-math -O3
iPerf Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 64 OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: UDP - Parallel: 64 Threadripper 3970X 16 Cores 15 30 45 60 75 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 67.1 67.1 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
Schbench Message Threads: 8 - Workers Per Message Thread: 8 OpenBenchmarking.org usec, 99.9th Latency Percentile, Fewer Is Better Schbench Message Threads: 8 - Workers Per Message Thread: 8 Threadripper 3970X 16 Cores 10K 20K 30K 40K 50K SE +/- 468.91, N = 12 SE +/- 740.24, N = 3 3587 46315 1. (CC) gcc options: -O2 -lpthread
OSBench Test: Create Processes OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Processes Threadripper 3970X 16 Cores 12 24 36 48 60 SE +/- 0.58, N = 12 SE +/- 0.76, N = 3 27.96 54.98 1. (CC) gcc options: -lm
Sunflow Rendering System Global Illumination + Image Synthesis OpenBenchmarking.org Seconds, Fewer Is Better Sunflow Rendering System 0.07.2 Global Illumination + Image Synthesis Threadripper 3970X 16 Cores 0.2147 0.4294 0.6441 0.8588 1.0735 SE +/- 0.005, N = 3 SE +/- 0.023, N = 15 0.517 0.954
Apache Siege Concurrent Users: 250 OpenBenchmarking.org Transactions Per Second, More Is Better Apache Siege 2.4.29 Concurrent Users: 250 Threadripper 3970X 16 Cores 12K 24K 36K 48K 60K SE +/- 1582.21, N = 15 SE +/- 579.13, N = 12 55626.42 54186.82 1. (CC) gcc options: -O2 -lpthread -ldl -lssl -lcrypto
Apache HBase Test: Random Write - Clients: 16 OpenBenchmarking.org Microseconds - Average Latency, Fewer Is Better Apache HBase 2.2.3 Test: Random Write - Clients: 16 Threadripper 3970X 16 Cores 20 40 60 80 100 SE +/- 20.61, N = 15 SE +/- 29.55, N = 15 72 81
Apache HBase Test: Random Write - Clients: 16 OpenBenchmarking.org Rows Per Second, More Is Better Apache HBase 2.2.3 Test: Random Write - Clients: 16 Threadripper 3970X 16 Cores 100K 200K 300K 400K 500K SE +/- 64718.62, N = 15 SE +/- 57800.53, N = 15 418033 475673
Memcached mcperf Method: Replace OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Replace Threadripper 3970X 16 Cores 20K 40K 60K 80K 100K SE +/- 677.13, N = 3 SE +/- 5340.89, N = 12 47267.1 84273.8 1. (CC) gcc options: -O2 -lm -rdynamic
Memcached mcperf Method: Prepend OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Prepend Threadripper 3970X 16 Cores 20K 40K 60K 80K 100K SE +/- 36.76, N = 3 SE +/- 5449.52, N = 12 46495.9 88961.4 1. (CC) gcc options: -O2 -lm -rdynamic
Memcached mcperf Method: Append OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Append Threadripper 3970X 16 Cores 20K 40K 60K 80K 100K SE +/- 1452.18, N = 12 SE +/- 4614.05, N = 15 49940.5 85868.9 1. (CC) gcc options: -O2 -lm -rdynamic
Memcached mcperf Method: Set OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Set Threadripper 3970X 16 Cores 16K 32K 48K 64K 80K SE +/- 556.85, N = 5 SE +/- 2447.09, N = 12 45117.5 75424.0 1. (CC) gcc options: -O2 -lm -rdynamic
Memcached mcperf Method: Add OpenBenchmarking.org Operations Per Second, More Is Better Memcached mcperf 1.5.10 Method: Add Threadripper 3970X 16 Cores 16K 32K 48K 64K 80K SE +/- 143.36, N = 3 SE +/- 1667.09, N = 12 45047.0 72837.7 1. (CC) gcc options: -O2 -lm -rdynamic
Facebook RocksDB Test: Random Fill Sync OpenBenchmarking.org Op/s, More Is Better Facebook RocksDB 6.3.6 Test: Random Fill Sync Threadripper 3970X 16 Cores 6K 12K 18K 24K 30K SE +/- 999.84, N = 15 SE +/- 17.38, N = 3 29167 9106 1. (CXX) g++ options: -O3 -march=native -std=c++11 -fno-builtin-memcmp -fno-rtti -rdynamic -lpthread
Apache Cassandra Test: Reads OpenBenchmarking.org Op/s, More Is Better Apache Cassandra 3.11.4 Test: Reads Threadripper 3970X 16 Cores 4K 8K 12K 16K 20K SE +/- 7579.05, N = 9 SE +/- 37.22, N = 3 20360 3166
Redis Test: GET OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: GET Threadripper 3970X 16 Cores 500K 1000K 1500K 2000K 2500K SE +/- 25232.39, N = 3 SE +/- 45838.11, N = 15 2005988.50 2184449.11
Redis Test: LPOP OpenBenchmarking.org Requests Per Second, More Is Better Redis 5.0.5 Test: LPOP Threadripper 3970X 16 Cores 500K 1000K 1500K 2000K 2500K SE +/- 5677.11, N = 3 SE +/- 106189.37, N = 12 2175519.08 2097030.00
Stress-NG Test: Context Switching OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Context Switching Threadripper 3970X 16 Cores 5M 10M 15M 20M 25M SE +/- 434072.66, N = 15 SE +/- 9547.22, N = 3 21267958.31 2258922.93 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
Stress-NG Test: Lsearch OpenBenchmarking.org Bogo Ops/s, More Is Better Stress-NG 0.07.26 Test: Lsearch Threadripper 3970X 16 Cores 90 180 270 360 450 SE +/- 3.61, N = 3 SE +/- 2.93, N = 15 434.81 138.27 1. (CC) gcc options: -O2 -std=gnu99 -lm -lz -lcrypt -lrt -lpthread -laio -lc
Darktable Test: Server Rack - Acceleration: CPU-only OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.6.0 Test: Server Rack - Acceleration: CPU-only Threadripper 3970X 16 Cores 0.027 0.054 0.081 0.108 0.135 SE +/- 0.004, N = 12 SE +/- 0.000, N = 3 0.120 0.097
Darktable Test: Boat - Acceleration: CPU-only OpenBenchmarking.org Seconds, Fewer Is Better Darktable 2.6.0 Test: Boat - Acceleration: CPU-only Threadripper 3970X 16 Cores 2 4 6 8 10 SE +/- 0.097, N = 15 SE +/- 0.007, N = 3 6.010 5.060
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 3970X 16 Cores 3K 6K 9K 12K 15K SE +/- 333.19, N = 15 SE +/- 1319.04, N = 15 11196.80 12881.18 1. (CC) gcc options: -fno-strict-aliasing -fwrapv -O2 -lpgcommon -lpgport -lpq -lpthread -lrt -lcrypt -ldl -lm
Intel MPI Benchmarks Test: IMB-MPI1 Sendrecv OpenBenchmarking.org Average Mbytes/sec, More Is Better Intel MPI Benchmarks 2019.3 Test: IMB-MPI1 Sendrecv Threadripper 3970X 16 Cores 1300 2600 3900 5200 6500 SE +/- 64.08, N = 3 SE +/- 114.95, N = 15 4955.00 6263.73 MAX: 30545.39 MAX: 41562.16 1. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi
Intel MPI Benchmarks Test: IMB-MPI1 PingPong OpenBenchmarking.org Average Mbytes/sec, More Is Better Intel MPI Benchmarks 2019.3 Test: IMB-MPI1 PingPong Threadripper 3970X 16 Cores 1200 2400 3600 4800 6000 SE +/- 139.42, N = 15 SE +/- 201.66, N = 15 5106.63 5828.12 MIN: 5.04 / MAX: 18618.89 MIN: 5.29 / MAX: 21984.97 1. (CXX) g++ options: -O0 -pedantic -fopenmp -pthread -lmpi_cxx -lmpi
KeyDB OpenBenchmarking.org Ops/sec, More Is Better KeyDB 5.3.1 Threadripper 3970X 16 Cores 40K 80K 120K 160K 200K SE +/- 2224.40, N = 15 SE +/- 1098.87, N = 3 119630.18 167550.10 1. (CXX) g++ options: -O2 -levent -lpthread -lz -lpcre
Cpuminer-Opt Algorithm: myr-gr OpenBenchmarking.org kH/s - Hash Speed, More Is Better Cpuminer-Opt 3.8.8.1 Algorithm: myr-gr Threadripper 3970X 16 Cores 3K 6K 9K 12K 15K SE +/- 71.26, N = 3 SE +/- 1707.65, N = 15 13923.00 15369.09 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
Cpuminer-Opt Algorithm: deep OpenBenchmarking.org kH/s - Hash Speed, More Is Better Cpuminer-Opt 3.8.8.1 Algorithm: deep Threadripper 3970X 16 Cores 6K 12K 18K 24K 30K SE +/- 31.80, N = 3 SE +/- 1488.63, N = 15 29323.00 6879.91 1. (CXX) g++ options: -O2 -lcurl -lz -lpthread -lssl -lcrypto -lgmp
LuxCoreRender Scene: Rainbow Colors and Prism OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.2 Scene: Rainbow Colors and Prism Threadripper 3970X 16 Cores 0.54 1.08 1.62 2.16 2.7 SE +/- 0.17, N = 15 SE +/- 0.02, N = 3 2.07 2.40 MIN: 1.13 / MAX: 3.1 MIN: 2.33 / MAX: 2.49
LuxCoreRender Scene: DLSC OpenBenchmarking.org M samples/sec, More Is Better LuxCoreRender 2.2 Scene: DLSC Threadripper 3970X 16 Cores 0.5648 1.1296 1.6944 2.2592 2.824 SE +/- 0.19, N = 15 SE +/- 0.02, N = 3 2.51 2.30 MIN: 1.3 / MAX: 3 MIN: 2.18 / MAX: 2.41
OSPray Demo: Magnetic Reconnection - Renderer: Path Tracer OpenBenchmarking.org FPS, More Is Better OSPray 1.8.5 Demo: Magnetic Reconnection - Renderer: Path Tracer Threadripper 3970X 16 Cores 100 200 300 400 500 SE +/- 21.00, N = 15 444.44 250.00 MIN: 43.48 / MAX: 500 MIN: 200 / MAX: 333.33
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 3970X 16 Cores 1.1053 2.2106 3.3159 4.4212 5.5265 SE +/- 0.26685, N = 12 SE +/- 0.02100, N = 3 4.91239 3.69166 MIN: 2.56 MIN: 3.53 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
Renaissance Test: Savina Reactors.IO OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Savina Reactors.IO Threadripper 3970X 16 Cores 3K 6K 9K 12K 15K SE +/- 227.73, N = 25 SE +/- 57.87, N = 5 13551.88 15896.12
Renaissance Test: Apache Spark Bayes OpenBenchmarking.org ms, Fewer Is Better Renaissance 0.10.0 Test: Apache Spark Bayes Threadripper 3970X 16 Cores 700 1400 2100 2800 3500 SE +/- 33.74, N = 5 SE +/- 38.62, N = 25 2677.51 3157.26
CLOMP Static OMP Speedup OpenBenchmarking.org Speedup, More Is Better CLOMP 3.3 Static OMP Speedup Threadripper 3970X 16 Cores 0.684 1.368 2.052 2.736 3.42 SE +/- 0.01, N = 25 SE +/- 0.05, N = 25 0.71 3.04 1. (CC) gcc options: --openmp -O3 -lm
CloverLeaf Lagrangian-Eulerian Hydrodynamics OpenBenchmarking.org Seconds, Fewer Is Better CloverLeaf Lagrangian-Eulerian Hydrodynamics Threadripper 3970X 16 Cores 0.2835 0.567 0.8505 1.134 1.4175 SE +/- 0.06, N = 12 SE +/- 0.00, N = 3 1.05 1.26 1. (F9X) gfortran options: -O3 -march=native -funroll-loops -fopenmp
iPerf Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 64 OpenBenchmarking.org Mbits/sec, More Is Better iPerf 3.7 Server Address: localhost - Server Port: 5201 - Duration: 10 Seconds - Test: TCP - Parallel: 64 Threadripper 3970X 16 Cores 12K 24K 36K 48K 60K SE +/- 423.19, N = 3 SE +/- 1271.94, N = 12 54840 47216 1. (CC) gcc options: -O3 -march=native -lssl -lcrypto -lm
Sockperf Test: Latency Under Load OpenBenchmarking.org usec, Fewer Is Better Sockperf 3.4 Test: Latency Under Load Threadripper 3970X 16 Cores 3 6 9 12 15 SE +/- 0.66, N = 25 SE +/- 0.41, N = 25 13.23 10.78 1. (CXX) g++ options: --param -O3 -rdynamic -ldl -lpthread
IOzone Record Size: 4Kb - File Size: 512MB - Disk Test: Write Performance OpenBenchmarking.org MB/s, More Is Better IOzone 3.465 Record Size: 4Kb - File Size: 512MB - Disk Test: Write Performance Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 62.42, N = 12 SE +/- 4.09, N = 3 1529.57 1280.55 1. (CC) gcc options: -O3
Dbench Client Count: 12 OpenBenchmarking.org MB/s, More Is Better Dbench 4.0 Client Count: 12 Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 26.66, N = 9 SE +/- 46.78, N = 9 665.37 1382.09
Threaded I/O Tester Test: Write - Size Per Thread: 32MB - Thread Count: 4 OpenBenchmarking.org MB/s, More Is Better Threaded I/O Tester 20170503 Test: Write - Size Per Thread: 32MB - Thread Count: 4 Threadripper 3970X 16 Cores 3 6 9 12 15 SE +/- 0.31, N = 15 SE +/- 0.21, N = 15 10.55 10.41 1. (CC) gcc options: -O2
IOzone Record Size: 1MB - File Size: 512MB - Disk Test: Write Performance OpenBenchmarking.org MB/s, More Is Better IOzone 3.465 Record Size: 1MB - File Size: 512MB - Disk Test: Write Performance Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 59.80, N = 12 SE +/- 0.83, N = 3 1554.84 1335.37 1. (CC) gcc options: -O3
IOR Write Test OpenBenchmarking.org MB/s, More Is Better IOR 3.2.1 Write Test Threadripper 3970X 16 Cores 130 260 390 520 650 SE +/- 0.80, N = 3 SE +/- 10.86, N = 15 182.76 622.53 MIN: 58.47 / MAX: 193.16 MIN: 13.63 / MAX: 942.3 1. (CC) gcc options: -O2 -lm -pthread -lmpi
Dbench Client Count: 12 OpenBenchmarking.org MB/s, More Is Better Dbench 4.0 Client Count: 12 Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 13.11, N = 9 SE +/- 14.76, N = 8 595.26 1466.07 1. (CC) gcc options: -lpopt -O2
FS-Mark Test: 5000 Files, 1MB Size, 4 Threads OpenBenchmarking.org Files/s, More Is Better FS-Mark 3.3 Test: 5000 Files, 1MB Size, 4 Threads Threadripper 3970X 16 Cores 130 260 390 520 650 SE +/- 28.74, N = 12 SE +/- 81.95, N = 12 485.9 602.3 1. (CC) gcc options: -static
Flexible IO Tester Type: Random Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester Type: Random Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 60K 120K 180K 240K 300K SE +/- 13593.30, N = 12 SE +/- 5033.22, N = 3 263667 277000
Flexible IO Tester Type: Random Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.12 Type: Random Write - IO Engine: POSIX AIO - Buffered: Yes - Direct: No - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 200 400 600 800 1000 SE +/- 53.12, N = 12 SE +/- 8.11, N = 3 1030 1068
Flexible IO Tester Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.18 Type: Sequential Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 60K 120K 180K 240K 300K SE +/- 10149.45, N = 15 SE +/- 3424.79, N = 4 269200 245750 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
Flexible IO Tester Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.18 Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 90K 180K 270K 360K 450K SE +/- 3928.97, N = 15 SE +/- 7133.29, N = 15 344533 397600 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
Flexible IO Tester Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.18 Type: Sequential Read - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 15.41, N = 15 SE +/- 27.78, N = 15 1346 1553 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
Flexible IO Tester Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org IOPS, More Is Better Flexible IO Tester 3.18 Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 70K 140K 210K 280K 350K SE +/- 26330.47, N = 12 180633 335000 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
Flexible IO Tester Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory OpenBenchmarking.org MB/s, More Is Better Flexible IO Tester 3.18 Type: Random Write - Engine: IO_uring - Buffered: No - Direct: Yes - Block Size: 4KB - Disk Target: Default Test Directory Threadripper 3970X 16 Cores 300 600 900 1200 1500 SE +/- 102.96, N = 12 706 1309 1. (CC) gcc options: -rdynamic -std=gnu99 -ffast-math -include -O3 -U_FORTIFY_SOURCE -march=native -ll -lcurl -lssl -lcrypto -lnuma -libverbs -lrt -laio -lz -lpthread -lm -ldl
Phoronix Test Suite v10.8.4