Ryzen 9 3950X AMD Ryzen 9 3950X 16-Core testing with a ASUS ROG CROSSHAIR VIII HERO (WI-FI) (1201 BIOS) and llvmpipe 16GB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2002013-VE-RYZEN939535&grw .
Ryzen 9 3950X Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution Ryzen 9 3950X AMD Ryzen 9 3950X 16-Core @ 3.50GHz (16 Cores / 32 Threads) ASUS ROG CROSSHAIR VIII HERO (WI-FI) (1201 BIOS) AMD Starship/Matisse 16GB 2000GB Force MP600 + 2000GB SABRENT llvmpipe 16GB AMD Navi 10 HDMI Audio Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200 Ubuntu 20.04 5.4.0-12-generic (x86_64) GNOME Shell 3.34.3 X Server 1.20.6 modesetting 1.20.6 3.3 Mesa 20.0.0-devel (git-d3fa18a 2020-01-30 focal-oibaf-ppa) (LLVM 9.0.1 128 bits) GCC 9.2.1 20200123 ext4 3840x2160 OpenBenchmarking.org - --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-link-mutex --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --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-build-config=bootstrap-lto-lean --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 - Scaling Governor: acpi-cpufreq performance - CPU Microcode: 0x8701013 - + Python 3.7.6 - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + tsx_async_abort: Not affected
Ryzen 9 3950X selenium: ARES-6 - Firefox selenium: Kraken - Firefox selenium: Octane - Firefox selenium: WebXPRT - Firefox selenium: Basemark - Firefox selenium: Jetstream - Firefox selenium: CanvasMark - Firefox selenium: MotionMark - Firefox selenium: StyleBench - Firefox selenium: Jetstream 2 - Firefox selenium: Maze Solver - Firefox selenium: Speedometer - Firefox selenium: ARES-6 - Google Chrome selenium: Kraken - Google Chrome selenium: Octane - Google Chrome selenium: PSPDFKit WASM - Firefox selenium: WebXPRT - Google Chrome selenium: Jetstream - Google Chrome selenium: CanvasMark - Google Chrome mkl-dnn: Deconvolution Batch deconv_3d - f32 selenium: MotionMark - Google Chrome selenium: StyleBench - Google Chrome selenium: Jetstream 2 - Google Chrome selenium: Maze Solver - Google Chrome selenium: Speedometer - Google Chrome selenium: PSPDFKit WASM - Google Chrome selenium: WASM imageConvolute - Firefox selenium: GUIMark3 HTML5 Bitmap - Firefox selenium: GUIMark3 HTML5 Vector - Firefox selenium: GUIMark3 HTML5 Compute - Firefox selenium: WASM collisionDetection - Firefox selenium: WASM imageConvolute - Google Chrome selenium: GUIMark3 HTML5 Bitmap - Google Chrome selenium: GUIMark3 HTML5 Vector - Google Chrome selenium: GUIMark3 HTML5 Compute - Google Chrome selenium: WASM collisionDetection - Google Chrome mkl-dnn: IP Batch All - u8s8f32 mbw: Memory Copy - 128 MiB mbw: Memory Copy, Fixed Block Size - 4096 MiB tinymembench: Standard Memcpy mkl-dnn: Convolution Batch conv_3d - u8s8f32 tinymembench: Standard Memset ramspeed: Copy - Integer mkl-dnn: Convolution Batch conv_all - u8s8f32 ramspeed: Scale - Integer ramspeed: Triad - Integer ramspeed: Average - Integer ramspeed: Add - Floating Point mkl-dnn: Deconvolution Batch deconv_1d - u8s8f32 ramspeed: Copy - Floating Point mkl-dnn: IP Batch All - f32 mkl-dnn: IP Batch 1D - u8s8f32 mkl-dnn: Convolution Batch conv_googlenet_v3 - f32 mkl-dnn: IP Batch 1D - f32 ramspeed: Scale - Floating Point mkl-dnn: Recurrent Neural Network Training - f32 ramspeed: Triad - Floating Point ramspeed: Average - Floating Point stream: Copy stream: Scale stream: Triad mkl-dnn: Convolution Batch conv_3d - f32 stream: Add glibc-bench: cos glibc-bench: exp glibc-bench: ffs mkl-dnn: Convolution Batch conv_all - f32 mbw: Memory Copy - 512 MiB mkl-dnn: Deconvolution Batch deconv_1d - f32 mbw: Memory Copy - 1024 MiB mkl-dnn: Convolution Batch conv_alexnet - f32 mbw: Memory Copy - 4096 MiB mkl-dnn: Deconvolution Batch deconv_all - f32 mbw: Memory Copy, Fixed Block Size - 128 MiB mkl-dnn: Deconvolution Batch deconv_3d - u8s8f32 mbw: Memory Copy, Fixed Block Size - 512 MiB mkl-dnn: Convolution Batch conv_alexnet - u8s8f32 mbw: Memory Copy, Fixed Block Size - 1024 MiB mkl-dnn: Convolution Batch conv_googlenet_v3 - u8s8f32 ramspeed: Add - Integer glibc-bench: sin glibc-bench: log2 glibc-bench: modf glibc-bench: sinh glibc-bench: sqrt glibc-bench: tanh glibc-bench: asinh glibc-bench: atanh glibc-bench: ffsll glibc-bench: sincos glibc-bench: pthread_once fftw: Stock - 1D FFT Size 32 fftw: Stock - 1D FFT Size 64 fftw: Stock - 2D FFT Size 32 fftw: Stock - 2D FFT Size 64 fftw: Stock - 1D FFT Size 128 fftw: Stock - 1D FFT Size 256 fftw: Stock - 1D FFT Size 512 fftw: Stock - 2D FFT Size 128 fftw: Stock - 2D FFT Size 256 fftw: Stock - 2D FFT Size 512 fftw: Stock - 1D FFT Size 1024 fftw: Stock - 1D FFT Size 2048 fftw: Stock - 1D FFT Size 4096 fftw: Stock - 2D FFT Size 1024 fftw: Stock - 2D FFT Size 2048 fftw: Stock - 2D FFT Size 4096 fftw: Float + SSE - 1D FFT Size 32 fftw: Float + SSE - 1D FFT Size 64 fftw: Float + SSE - 2D FFT Size 32 fftw: Float + SSE - 2D FFT Size 64 fftw: Float + SSE - 1D FFT Size 128 fftw: Float + SSE - 1D FFT Size 256 fftw: Float + SSE - 1D FFT Size 512 fftw: Float + SSE - 2D FFT Size 128 fftw: Float + SSE - 2D FFT Size 256 fftw: Float + SSE - 2D FFT Size 512 fftw: Float + SSE - 1D FFT Size 1024 fftw: Float + SSE - 1D FFT Size 2048 fftw: Float + SSE - 1D FFT Size 4096 fftw: Float + SSE - 2D FFT Size 1024 fftw: Float + SSE - 2D FFT Size 2048 fftw: Float + SSE - 2D FFT Size 4096 hmmer: Pfam Database Search mrbayes: Primate Phylogeny Analysis himeno: Poisson Pressure Solver gromacs: Water Benchmark hpcg: namd: ATPase Simulation - 327,506 Atoms askap: tConvolve MT - Gridding askap: tConvolve MT - Degridding askap: tConvolve MPI - Gridding askap: tConvolve MPI - Degridding askap: tConvolve OpenMP - Gridding askap: tConvolve OpenMP - Degridding qmcpack: minife: Small build-llvm: Time To Compile build-gcc: Time To Compile build-linux-kernel: Time To Compile build2: Time To Compile Ryzen 9 3950X 46.33 701.9 37200 292 296.42 234.79 15300 296.83 97.9 104.354 4 101.9 18.61 715.3 51049 1260 270 238.19 22867 4.31209 720.43 37.63 156.590 3.7 140.6 1497 26.4 62.26 62.26 62.27 351.0 36.7623 62.54 62.57 62.58 279.9828 241.510 19260.215 10754.354 10251.0 7098.24 15049.5 25517.99 24131.0 25730.21 32006.15 29440.54 29418.08 2656.61 25499.23 28.2229 36.5454 96.8605 4.27010 25507.1 233.096 29428.74 27421.71 16196.7 16107.4 17878.7 17.5270 17889.2 40.4447 4.92244 1.68579 1800.53 19291.407 3.34958 19425.045 211.642 19435.782 2555.34 10120.877 4463.78 10649.433 3545.76 10773.647 1131.22 32023.71 40.0366 5.65081 2.12752 7.61954 2.10867 10.1685 8.03424 9.68353 1.89780 11.6952 1.67623 11358 10720 11302 9827.8 8853.7 9397.3 9358.3 9164.5 8701.0 8650.7 9316.8 8968.5 8837.0 8346.1 6472.7 6744.2 16053 21101 47570 48558 28588 39699 53628 47397 43817 45573 59426 62053 60056 45585 24045 21129 4.639 70.154 5114.771055 1.226 4.57952 1.10492 886.357 1644.20 893.040 1656.55 2377.41 2176.51 1236.4 3810.13 209.468 548.446 38.907 60.387 OpenBenchmarking.org
Selenium Benchmark: ARES-6 - Browser: Firefox OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: ARES-6 - Browser: Firefox Ryzen 9 3950X 11 22 33 44 55 SE +/- 0.21, N = 3 46.33 1. firefox 72.0.1
Selenium Benchmark: Kraken - Browser: Firefox OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: Kraken - Browser: Firefox Ryzen 9 3950X 150 300 450 600 750 SE +/- 3.24, N = 3 701.9 1. firefox 72.0.1
Selenium Benchmark: Octane - Browser: Firefox OpenBenchmarking.org Geometric Mean, More Is Better Selenium Benchmark: Octane - Browser: Firefox Ryzen 9 3950X 8K 16K 24K 32K 40K SE +/- 87.56, N = 3 37200 1. firefox 72.0.1
Selenium Benchmark: WebXPRT - Browser: Firefox OpenBenchmarking.org Score, More Is Better Selenium Benchmark: WebXPRT - Browser: Firefox Ryzen 9 3950X 60 120 180 240 300 SE +/- 1.53, N = 3 292 1. firefox 72.0.1
Selenium Benchmark: Basemark - Browser: Firefox OpenBenchmarking.org Overall Score, More Is Better Selenium Benchmark: Basemark - Browser: Firefox Ryzen 9 3950X 60 120 180 240 300 SE +/- 1.42, N = 3 296.42 1. firefox 72.0.1
Selenium Benchmark: Jetstream - Browser: Firefox OpenBenchmarking.org Score, More Is Better Selenium Benchmark: Jetstream - Browser: Firefox Ryzen 9 3950X 50 100 150 200 250 SE +/- 0.73, N = 3 234.79 1. firefox 72.0.1
Selenium Benchmark: CanvasMark - Browser: Firefox OpenBenchmarking.org Score, More Is Better Selenium Benchmark: CanvasMark - Browser: Firefox Ryzen 9 3950X 3K 6K 9K 12K 15K SE +/- 139.55, N = 3 15300 1. firefox 72.0.1
Selenium Benchmark: MotionMark - Browser: Firefox OpenBenchmarking.org Score, More Is Better Selenium Benchmark: MotionMark - Browser: Firefox Ryzen 9 3950X 60 120 180 240 300 SE +/- 1.09, N = 3 296.83 1. firefox 72.0.1
Selenium Benchmark: StyleBench - Browser: Firefox OpenBenchmarking.org Runs / Minute, More Is Better Selenium Benchmark: StyleBench - Browser: Firefox Ryzen 9 3950X 20 40 60 80 100 SE +/- 0.22, N = 3 97.9 1. firefox 72.0.1
Selenium Benchmark: Jetstream 2 - Browser: Firefox OpenBenchmarking.org Score, More Is Better Selenium Benchmark: Jetstream 2 - Browser: Firefox Ryzen 9 3950X 20 40 60 80 100 SE +/- 1.40, N = 3 104.35 1. firefox 72.0.1
Selenium Benchmark: Maze Solver - Browser: Firefox OpenBenchmarking.org Seconds, Fewer Is Better Selenium Benchmark: Maze Solver - Browser: Firefox Ryzen 9 3950X 0.9 1.8 2.7 3.6 4.5 4 1. firefox 72.0.1
Selenium Benchmark: Speedometer - Browser: Firefox OpenBenchmarking.org Runs Per Minute, More Is Better Selenium Benchmark: Speedometer - Browser: Firefox Ryzen 9 3950X 20 40 60 80 100 SE +/- 0.07, N = 3 101.9 1. firefox 72.0.1
Selenium Benchmark: ARES-6 - Browser: Google Chrome OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: ARES-6 - Browser: Google Chrome Ryzen 9 3950X 5 10 15 20 25 SE +/- 0.07, N = 3 18.61 1. chrome 79.0.3945.130
Selenium Benchmark: Kraken - Browser: Google Chrome OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: Kraken - Browser: Google Chrome Ryzen 9 3950X 150 300 450 600 750 SE +/- 5.34, N = 3 715.3 1. chrome 79.0.3945.130
Selenium Benchmark: Octane - Browser: Google Chrome OpenBenchmarking.org Geometric Mean, More Is Better Selenium Benchmark: Octane - Browser: Google Chrome Ryzen 9 3950X 11K 22K 33K 44K 55K SE +/- 177.54, N = 3 51049 1. chrome 79.0.3945.130
Selenium Benchmark: PSPDFKit WASM - Browser: Firefox OpenBenchmarking.org Score, Fewer Is Better Selenium Benchmark: PSPDFKit WASM - Browser: Firefox Ryzen 9 3950X 300 600 900 1200 1500 SE +/- 5.21, N = 3 1260 1. firefox 72.0.1
Selenium Benchmark: WebXPRT - Browser: Google Chrome OpenBenchmarking.org Score, More Is Better Selenium Benchmark: WebXPRT - Browser: Google Chrome Ryzen 9 3950X 60 120 180 240 300 SE +/- 0.88, N = 3 270 1. chrome 79.0.3945.130
Selenium Benchmark: Jetstream - Browser: Google Chrome OpenBenchmarking.org Score, More Is Better Selenium Benchmark: Jetstream - Browser: Google Chrome Ryzen 9 3950X 50 100 150 200 250 SE +/- 1.12, N = 3 238.19 1. chrome 79.0.3945.130
Selenium Benchmark: CanvasMark - Browser: Google Chrome OpenBenchmarking.org Score, More Is Better Selenium Benchmark: CanvasMark - Browser: Google Chrome Ryzen 9 3950X 5K 10K 15K 20K 25K SE +/- 133.22, N = 3 22867 1. chrome 79.0.3945.130
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 Ryzen 9 3950X 0.9702 1.9404 2.9106 3.8808 4.851 SE +/- 0.00935, N = 3 4.31209 MIN: 4.2 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
Selenium Benchmark: MotionMark - Browser: Google Chrome OpenBenchmarking.org Score, More Is Better Selenium Benchmark: MotionMark - Browser: Google Chrome Ryzen 9 3950X 160 320 480 640 800 SE +/- 9.63, N = 4 720.43 1. chrome 79.0.3945.130
Selenium Benchmark: StyleBench - Browser: Google Chrome OpenBenchmarking.org Runs / Minute, More Is Better Selenium Benchmark: StyleBench - Browser: Google Chrome Ryzen 9 3950X 9 18 27 36 45 SE +/- 0.16, N = 3 37.63 1. chrome 79.0.3945.130
Selenium Benchmark: Jetstream 2 - Browser: Google Chrome OpenBenchmarking.org Score, More Is Better Selenium Benchmark: Jetstream 2 - Browser: Google Chrome Ryzen 9 3950X 30 60 90 120 150 SE +/- 0.56, N = 3 156.59 1. chrome 79.0.3945.130
Selenium Benchmark: Maze Solver - Browser: Google Chrome OpenBenchmarking.org Seconds, Fewer Is Better Selenium Benchmark: Maze Solver - Browser: Google Chrome Ryzen 9 3950X 0.8325 1.665 2.4975 3.33 4.1625 SE +/- 0.00, N = 3 3.7 1. chrome 79.0.3945.130
Selenium Benchmark: Speedometer - Browser: Google Chrome OpenBenchmarking.org Runs Per Minute, More Is Better Selenium Benchmark: Speedometer - Browser: Google Chrome Ryzen 9 3950X 30 60 90 120 150 SE +/- 0.26, N = 3 140.6 1. chrome 79.0.3945.130
Selenium Benchmark: PSPDFKit WASM - Browser: Google Chrome OpenBenchmarking.org Score, Fewer Is Better Selenium Benchmark: PSPDFKit WASM - Browser: Google Chrome Ryzen 9 3950X 300 600 900 1200 1500 SE +/- 2.60, N = 3 1497 1. chrome 79.0.3945.130
Selenium Benchmark: WASM imageConvolute - Browser: Firefox OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: WASM imageConvolute - Browser: Firefox Ryzen 9 3950X 6 12 18 24 30 SE +/- 0.03, N = 3 26.4 1. firefox 72.0.1
Selenium Benchmark: GUIMark3 HTML5 Bitmap - Browser: Firefox OpenBenchmarking.org fps, More Is Better Selenium Benchmark: GUIMark3 HTML5 Bitmap - Browser: Firefox Ryzen 9 3950X 14 28 42 56 70 SE +/- 0.04, N = 3 62.26 1. firefox 72.0.1
Selenium Benchmark: GUIMark3 HTML5 Vector - Browser: Firefox OpenBenchmarking.org fps, More Is Better Selenium Benchmark: GUIMark3 HTML5 Vector - Browser: Firefox Ryzen 9 3950X 14 28 42 56 70 SE +/- 0.04, N = 3 62.26 1. firefox 72.0.1
Selenium Benchmark: GUIMark3 HTML5 Compute - Browser: Firefox OpenBenchmarking.org fps, More Is Better Selenium Benchmark: GUIMark3 HTML5 Compute - Browser: Firefox Ryzen 9 3950X 14 28 42 56 70 SE +/- 0.01, N = 3 62.27 1. firefox 72.0.1
Selenium Benchmark: WASM collisionDetection - Browser: Firefox OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: WASM collisionDetection - Browser: Firefox Ryzen 9 3950X 80 160 240 320 400 SE +/- 5.58, N = 3 351.0 1. firefox 72.0.1
Selenium Benchmark: WASM imageConvolute - Browser: Google Chrome OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: WASM imageConvolute - Browser: Google Chrome Ryzen 9 3950X 8 16 24 32 40 SE +/- 0.54, N = 3 36.76 1. chrome 79.0.3945.130
Selenium Benchmark: GUIMark3 HTML5 Bitmap - Browser: Google Chrome OpenBenchmarking.org fps, More Is Better Selenium Benchmark: GUIMark3 HTML5 Bitmap - Browser: Google Chrome Ryzen 9 3950X 14 28 42 56 70 SE +/- 0.02, N = 3 62.54 1. chrome 79.0.3945.130
Selenium Benchmark: GUIMark3 HTML5 Vector - Browser: Google Chrome OpenBenchmarking.org fps, More Is Better Selenium Benchmark: GUIMark3 HTML5 Vector - Browser: Google Chrome Ryzen 9 3950X 14 28 42 56 70 SE +/- 0.01, N = 3 62.57 1. chrome 79.0.3945.130
Selenium Benchmark: GUIMark3 HTML5 Compute - Browser: Google Chrome OpenBenchmarking.org fps, More Is Better Selenium Benchmark: GUIMark3 HTML5 Compute - Browser: Google Chrome Ryzen 9 3950X 14 28 42 56 70 SE +/- 0.01, N = 3 62.58 1. chrome 79.0.3945.130
Selenium Benchmark: WASM collisionDetection - Browser: Google Chrome OpenBenchmarking.org ms, Fewer Is Better Selenium Benchmark: WASM collisionDetection - Browser: Google Chrome Ryzen 9 3950X 60 120 180 240 300 SE +/- 3.66, N = 3 279.98 1. chrome 79.0.3945.130
MKL-DNN DNNL Harness: IP Batch All - Data Type: u8s8f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: IP Batch All - Data Type: u8s8f32 Ryzen 9 3950X 50 100 150 200 250 SE +/- 0.46, N = 3 241.51 MIN: 238.34 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
MBW Test: Memory Copy - Array Size: 128 MiB OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 128 MiB Ryzen 9 3950X 4K 8K 12K 16K 20K SE +/- 40.56, N = 3 19260.22 1. (CC) gcc options: -O3 -march=native
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 Ryzen 9 3950X 2K 4K 6K 8K 10K SE +/- 62.67, N = 3 10754.35 1. (CC) gcc options: -O3 -march=native
Tinymembench Standard Memcpy OpenBenchmarking.org MB/s, More Is Better Tinymembench 2018-05-28 Standard Memcpy Ryzen 9 3950X 2K 4K 6K 8K 10K SE +/- 18.25, N = 3 10251.0 1. (CC) gcc options: -O2 -lm
MKL-DNN DNNL Harness: Convolution Batch conv_3d - Data Type: u8s8f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_3d - Data Type: u8s8f32 Ryzen 9 3950X 1500 3000 4500 6000 7500 SE +/- 7.66, N = 3 7098.24 MIN: 7079.57 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
Tinymembench Standard Memset OpenBenchmarking.org MB/s, More Is Better Tinymembench 2018-05-28 Standard Memset Ryzen 9 3950X 3K 6K 9K 12K 15K SE +/- 45.87, N = 3 15049.5 1. (CC) gcc options: -O2 -lm
RAMspeed SMP Type: Copy - Benchmark: Integer OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Copy - Benchmark: Integer Ryzen 9 3950X 5K 10K 15K 20K 25K 25517.99 1. (CC) gcc options: -O3 -march=native
MKL-DNN DNNL Harness: Convolution Batch conv_all - Data Type: u8s8f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_all - Data Type: u8s8f32 Ryzen 9 3950X 5K 10K 15K 20K 25K SE +/- 35.85, N = 3 24131.0 MIN: 23792.3 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
RAMspeed SMP Type: Scale - Benchmark: Integer OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Scale - Benchmark: Integer Ryzen 9 3950X 6K 12K 18K 24K 30K 25730.21 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Triad - Benchmark: Integer OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Triad - Benchmark: Integer Ryzen 9 3950X 7K 14K 21K 28K 35K 32006.15 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Average - Benchmark: Integer OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Average - Benchmark: Integer Ryzen 9 3950X 6K 12K 18K 24K 30K 29440.54 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Add - Benchmark: Floating Point OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Add - Benchmark: Floating Point Ryzen 9 3950X 6K 12K 18K 24K 30K 29418.08 1. (CC) gcc options: -O3 -march=native
MKL-DNN DNNL Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_1d - Data Type: u8s8f32 Ryzen 9 3950X 600 1200 1800 2400 3000 SE +/- 1.98, N = 3 2656.61 MIN: 2648.1 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
RAMspeed SMP Type: Copy - Benchmark: Floating Point OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Copy - Benchmark: Floating Point Ryzen 9 3950X 5K 10K 15K 20K 25K 25499.23 1. (CC) gcc options: -O3 -march=native
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 Ryzen 9 3950X 7 14 21 28 35 SE +/- 0.32, N = 3 28.22 MIN: 27.03 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
MKL-DNN DNNL Harness: IP Batch 1D - Data Type: u8s8f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: IP Batch 1D - Data Type: u8s8f32 Ryzen 9 3950X 8 16 24 32 40 SE +/- 0.15, N = 3 36.55 MIN: 34.83 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
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 Ryzen 9 3950X 20 40 60 80 100 SE +/- 0.08, N = 3 96.86 MIN: 94.98 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
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 Ryzen 9 3950X 0.9608 1.9216 2.8824 3.8432 4.804 SE +/- 0.03452, N = 3 4.27010 MIN: 4.12 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
RAMspeed SMP Type: Scale - Benchmark: Floating Point OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Scale - Benchmark: Floating Point Ryzen 9 3950X 5K 10K 15K 20K 25K 25507.1 1. (CC) gcc options: -O3 -march=native
MKL-DNN DNNL Harness: Recurrent Neural Network Training - Data Type: f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Recurrent Neural Network Training - Data Type: f32 Ryzen 9 3950X 50 100 150 200 250 SE +/- 0.19, N = 3 233.10 MIN: 231.28 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
RAMspeed SMP Type: Triad - Benchmark: Floating Point OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Triad - Benchmark: Floating Point Ryzen 9 3950X 6K 12K 18K 24K 30K 29428.74 1. (CC) gcc options: -O3 -march=native
RAMspeed SMP Type: Average - Benchmark: Floating Point OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Average - Benchmark: Floating Point Ryzen 9 3950X 6K 12K 18K 24K 30K 27421.71 1. (CC) gcc options: -O3 -march=native
Stream Type: Copy OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Copy Ryzen 9 3950X 3K 6K 9K 12K 15K SE +/- 17.61, N = 5 16196.7 1. (CC) gcc options: -O3 -march=native -fopenmp
Stream Type: Scale OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Scale Ryzen 9 3950X 3K 6K 9K 12K 15K SE +/- 2.49, N = 5 16107.4 1. (CC) gcc options: -O3 -march=native -fopenmp
Stream Type: Triad OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Triad Ryzen 9 3950X 4K 8K 12K 16K 20K SE +/- 4.56, N = 5 17878.7 1. (CC) gcc options: -O3 -march=native -fopenmp
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 Ryzen 9 3950X 4 8 12 16 20 SE +/- 0.04, N = 3 17.53 MIN: 17.11 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
Stream Type: Add OpenBenchmarking.org MB/s, More Is Better Stream 2013-01-17 Type: Add Ryzen 9 3950X 4K 8K 12K 16K 20K SE +/- 11.23, N = 5 17889.2 1. (CC) gcc options: -O3 -march=native -fopenmp
glibc bench Benchmark: cos OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: cos Ryzen 9 3950X 9 18 27 36 45 SE +/- 0.05, N = 3 40.44
glibc bench Benchmark: exp OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: exp Ryzen 9 3950X 1.1075 2.215 3.3225 4.43 5.5375 SE +/- 0.04340, N = 3 4.92244
glibc bench Benchmark: ffs OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: ffs Ryzen 9 3950X 0.3793 0.7586 1.1379 1.5172 1.8965 SE +/- 0.00579, N = 3 1.68579
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 Ryzen 9 3950X 400 800 1200 1600 2000 SE +/- 2.40, N = 3 1800.53 MIN: 1779.61 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
MBW Test: Memory Copy - Array Size: 512 MiB OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 512 MiB Ryzen 9 3950X 4K 8K 12K 16K 20K SE +/- 49.39, N = 3 19291.41 1. (CC) gcc options: -O3 -march=native
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 Ryzen 9 3950X 0.7537 1.5074 2.2611 3.0148 3.7685 SE +/- 0.00589, N = 3 3.34958 MIN: 3.29 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
MBW Test: Memory Copy - Array Size: 1024 MiB OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy - Array Size: 1024 MiB Ryzen 9 3950X 4K 8K 12K 16K 20K SE +/- 64.86, N = 3 19425.05 1. (CC) gcc options: -O3 -march=native
MKL-DNN DNNL Harness: Convolution Batch conv_alexnet - Data Type: f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_alexnet - Data Type: f32 Ryzen 9 3950X 50 100 150 200 250 SE +/- 0.32, N = 3 211.64 MIN: 208.86 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
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 Ryzen 9 3950X 4K 8K 12K 16K 20K SE +/- 55.46, N = 3 19435.78 1. (CC) gcc options: -O3 -march=native
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 Ryzen 9 3950X 500 1000 1500 2000 2500 SE +/- 2.40, N = 3 2555.34 MIN: 2521.91 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
MBW Test: Memory Copy, Fixed Block Size - Array Size: 128 MiB OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 128 MiB Ryzen 9 3950X 2K 4K 6K 8K 10K SE +/- 16.22, N = 3 10120.88 1. (CC) gcc options: -O3 -march=native
MKL-DNN DNNL Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Deconvolution Batch deconv_3d - Data Type: u8s8f32 Ryzen 9 3950X 1000 2000 3000 4000 5000 SE +/- 28.91, N = 3 4463.78 MIN: 4426.06 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
MBW Test: Memory Copy, Fixed Block Size - Array Size: 512 MiB OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 512 MiB Ryzen 9 3950X 2K 4K 6K 8K 10K SE +/- 36.52, N = 3 10649.43 1. (CC) gcc options: -O3 -march=native
MKL-DNN DNNL Harness: Convolution Batch conv_alexnet - Data Type: u8s8f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_alexnet - Data Type: u8s8f32 Ryzen 9 3950X 800 1600 2400 3200 4000 SE +/- 12.74, N = 3 3545.76 MIN: 3490.3 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
MBW Test: Memory Copy, Fixed Block Size - Array Size: 1024 MiB OpenBenchmarking.org MiB/s, More Is Better MBW 2018-09-08 Test: Memory Copy, Fixed Block Size - Array Size: 1024 MiB Ryzen 9 3950X 2K 4K 6K 8K 10K SE +/- 13.96, N = 3 10773.65 1. (CC) gcc options: -O3 -march=native
MKL-DNN DNNL Harness: Convolution Batch conv_googlenet_v3 - Data Type: u8s8f32 OpenBenchmarking.org ms, Fewer Is Better MKL-DNN DNNL 1.1 Harness: Convolution Batch conv_googlenet_v3 - Data Type: u8s8f32 Ryzen 9 3950X 200 400 600 800 1000 SE +/- 1.21, N = 3 1131.22 MIN: 1097.86 1. (CXX) g++ options: -O3 -march=native -std=c++11 -msse4.1 -fPIC -fopenmp -pie -lpthread -ldl
RAMspeed SMP Type: Add - Benchmark: Integer OpenBenchmarking.org MB/s, More Is Better RAMspeed SMP 3.5.0 Type: Add - Benchmark: Integer Ryzen 9 3950X 7K 14K 21K 28K 35K 32023.71 1. (CC) gcc options: -O3 -march=native
glibc bench Benchmark: sin OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: sin Ryzen 9 3950X 9 18 27 36 45 SE +/- 0.07, N = 3 40.04
glibc bench Benchmark: log2 OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: log2 Ryzen 9 3950X 1.2714 2.5428 3.8142 5.0856 6.357 SE +/- 0.00812, N = 3 5.65081
glibc bench Benchmark: modf OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: modf Ryzen 9 3950X 0.4787 0.9574 1.4361 1.9148 2.3935 SE +/- 0.00485, N = 3 2.12752
glibc bench Benchmark: sinh OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: sinh Ryzen 9 3950X 2 4 6 8 10 SE +/- 0.09100, N = 3 7.61954
glibc bench Benchmark: sqrt OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: sqrt Ryzen 9 3950X 0.4745 0.949 1.4235 1.898 2.3725 SE +/- 0.00611, N = 3 2.10867
glibc bench Benchmark: tanh OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: tanh Ryzen 9 3950X 3 6 9 12 15 SE +/- 0.03, N = 3 10.17
glibc bench Benchmark: asinh OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: asinh Ryzen 9 3950X 2 4 6 8 10 SE +/- 0.06275, N = 3 8.03424
glibc bench Benchmark: atanh OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: atanh Ryzen 9 3950X 3 6 9 12 15 SE +/- 0.03028, N = 3 9.68353
glibc bench Benchmark: ffsll OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: ffsll Ryzen 9 3950X 0.427 0.854 1.281 1.708 2.135 SE +/- 0.00321, N = 3 1.89780
glibc bench Benchmark: sincos OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: sincos Ryzen 9 3950X 3 6 9 12 15 SE +/- 0.08, N = 3 11.70
glibc bench Benchmark: pthread_once OpenBenchmarking.org nanoseconds, Fewer Is Better glibc bench 1.0 Benchmark: pthread_once Ryzen 9 3950X 0.3772 0.7544 1.1316 1.5088 1.886 SE +/- 0.00589, N = 3 1.67623
FFTW Build: Stock - Size: 1D FFT Size 32 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 32 Ryzen 9 3950X 2K 4K 6K 8K 10K SE +/- 20.74, N = 3 11358 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Stock - Size: 1D FFT Size 64 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 64 Ryzen 9 3950X 2K 4K 6K 8K 10K SE +/- 10.17, N = 3 10720 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Stock - Size: 2D FFT Size 32 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 32 Ryzen 9 3950X 2K 4K 6K 8K 10K SE +/- 1.15, N = 3 11302 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Stock - Size: 2D FFT Size 64 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 64 Ryzen 9 3950X 2K 4K 6K 8K 10K SE +/- 4.98, N = 3 9827.8 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Stock - Size: 1D FFT Size 128 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 128 Ryzen 9 3950X 2K 4K 6K 8K 10K SE +/- 27.40, N = 3 8853.7 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Stock - Size: 1D FFT Size 256 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 256 Ryzen 9 3950X 2K 4K 6K 8K 10K SE +/- 32.37, N = 3 9397.3 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Stock - Size: 1D FFT Size 512 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 512 Ryzen 9 3950X 2K 4K 6K 8K 10K SE +/- 5.08, N = 3 9358.3 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Stock - Size: 2D FFT Size 128 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 128 Ryzen 9 3950X 2K 4K 6K 8K 10K SE +/- 5.37, N = 3 9164.5 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Stock - Size: 2D FFT Size 256 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 256 Ryzen 9 3950X 2K 4K 6K 8K 10K SE +/- 22.85, N = 3 8701.0 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Stock - Size: 2D FFT Size 512 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 512 Ryzen 9 3950X 2K 4K 6K 8K 10K SE +/- 53.32, N = 3 8650.7 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Stock - Size: 1D FFT Size 1024 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 1024 Ryzen 9 3950X 2K 4K 6K 8K 10K SE +/- 37.11, N = 3 9316.8 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Stock - Size: 1D FFT Size 2048 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 2048 Ryzen 9 3950X 2K 4K 6K 8K 10K SE +/- 16.71, N = 3 8968.5 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Stock - Size: 1D FFT Size 4096 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 1D FFT Size 4096 Ryzen 9 3950X 2K 4K 6K 8K 10K SE +/- 91.38, N = 3 8837.0 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Stock - Size: 2D FFT Size 1024 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 1024 Ryzen 9 3950X 2K 4K 6K 8K 10K SE +/- 15.21, N = 3 8346.1 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Stock - Size: 2D FFT Size 2048 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 2048 Ryzen 9 3950X 1400 2800 4200 5600 7000 SE +/- 41.46, N = 3 6472.7 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Stock - Size: 2D FFT Size 4096 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Stock - Size: 2D FFT Size 4096 Ryzen 9 3950X 1400 2800 4200 5600 7000 SE +/- 98.03, N = 3 6744.2 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 1D FFT Size 32 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 32 Ryzen 9 3950X 3K 6K 9K 12K 15K SE +/- 109.52, N = 3 16053 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 1D FFT Size 64 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 64 Ryzen 9 3950X 5K 10K 15K 20K 25K SE +/- 202.41, N = 3 21101 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 2D FFT Size 32 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 32 Ryzen 9 3950X 10K 20K 30K 40K 50K SE +/- 90.52, N = 3 47570 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 2D FFT Size 64 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 64 Ryzen 9 3950X 10K 20K 30K 40K 50K SE +/- 326.59, N = 3 48558 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 1D FFT Size 128 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 128 Ryzen 9 3950X 6K 12K 18K 24K 30K SE +/- 25.85, N = 3 28588 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 1D FFT Size 256 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 256 Ryzen 9 3950X 9K 18K 27K 36K 45K SE +/- 516.07, N = 15 39699 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 1D FFT Size 512 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 512 Ryzen 9 3950X 11K 22K 33K 44K 55K SE +/- 284.30, N = 3 53628 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 2D FFT Size 128 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 128 Ryzen 9 3950X 10K 20K 30K 40K 50K SE +/- 413.32, N = 3 47397 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 2D FFT Size 256 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 256 Ryzen 9 3950X 9K 18K 27K 36K 45K SE +/- 439.92, N = 3 43817 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 2D FFT Size 512 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 512 Ryzen 9 3950X 10K 20K 30K 40K 50K SE +/- 96.06, N = 3 45573 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 1D FFT Size 1024 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 1024 Ryzen 9 3950X 13K 26K 39K 52K 65K SE +/- 439.49, N = 3 59426 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 1D FFT Size 2048 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 2048 Ryzen 9 3950X 13K 26K 39K 52K 65K SE +/- 192.73, N = 3 62053 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 1D FFT Size 4096 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 1D FFT Size 4096 Ryzen 9 3950X 13K 26K 39K 52K 65K SE +/- 602.13, N = 3 60056 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 2D FFT Size 1024 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 1024 Ryzen 9 3950X 10K 20K 30K 40K 50K SE +/- 451.76, N = 3 45585 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 2D FFT Size 2048 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 2048 Ryzen 9 3950X 5K 10K 15K 20K 25K SE +/- 57.47, N = 3 24045 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
FFTW Build: Float + SSE - Size: 2D FFT Size 4096 OpenBenchmarking.org Mflops, More Is Better FFTW 3.3.6 Build: Float + SSE - Size: 2D FFT Size 4096 Ryzen 9 3950X 5K 10K 15K 20K 25K SE +/- 187.29, N = 3 21129 1. (CC) gcc options: -pthread -O3 -fomit-frame-pointer -mtune=native -malign-double -fstrict-aliasing -fno-schedule-insns -ffast-math -lm
Timed HMMer Search Pfam Database Search OpenBenchmarking.org Seconds, Fewer Is Better Timed HMMer Search 2.3.2 Pfam Database Search Ryzen 9 3950X 1.0438 2.0876 3.1314 4.1752 5.219 SE +/- 0.007, N = 3 4.639 1. (CC) gcc options: -O2 -pthread -lhmmer -lsquid -lm
Timed MrBayes Analysis Primate Phylogeny Analysis OpenBenchmarking.org Seconds, Fewer Is Better Timed MrBayes Analysis 3.2.7 Primate Phylogeny Analysis Ryzen 9 3950X 16 32 48 64 80 SE +/- 0.14, N = 3 70.15 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
Himeno Benchmark Poisson Pressure Solver OpenBenchmarking.org MFLOPS, More Is Better Himeno Benchmark 3.0 Poisson Pressure Solver Ryzen 9 3950X 1100 2200 3300 4400 5500 SE +/- 46.15, N = 3 5114.77 1. (CC) gcc options: -O3 -mavx2
GROMACS Water Benchmark OpenBenchmarking.org Ns Per Day, More Is Better GROMACS 2019.4 Water Benchmark Ryzen 9 3950X 0.2759 0.5518 0.8277 1.1036 1.3795 SE +/- 0.005, N = 3 1.226 1. (CXX) g++ options: -mavx2 -mfma -pthread -std=c++11 -O3 -funroll-all-loops -lrt -lpthread -lm
High Performance Conjugate Gradient OpenBenchmarking.org GFLOP/s, More Is Better High Performance Conjugate Gradient 3.1 Ryzen 9 3950X 1.0304 2.0608 3.0912 4.1216 5.152 SE +/- 0.00049, N = 9 4.57952 1. (CXX) g++ options: -O3 -ffast-math -ftree-vectorize -pthread -lmpi_cxx -lmpi
NAMD ATPase Simulation - 327,506 Atoms OpenBenchmarking.org days/ns, Fewer Is Better NAMD 2.13b1 ATPase Simulation - 327,506 Atoms Ryzen 9 3950X 0.2486 0.4972 0.7458 0.9944 1.243 SE +/- 0.00309, N = 3 1.10492
ASKAP Test: tConvolve MT - Gridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MT - Gridding Ryzen 9 3950X 200 400 600 800 1000 SE +/- 1.69, N = 3 886.36 1. (CXX) g++ options: -lpthread
ASKAP Test: tConvolve MT - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MT - Degridding Ryzen 9 3950X 400 800 1200 1600 2000 SE +/- 2.91, N = 3 1644.20 1. (CXX) g++ options: -lpthread
ASKAP Test: tConvolve MPI - Gridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MPI - Gridding Ryzen 9 3950X 200 400 600 800 1000 SE +/- 0.50, N = 3 893.04 1. (CXX) g++ options: -lpthread
ASKAP Test: tConvolve MPI - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve MPI - Degridding Ryzen 9 3950X 400 800 1200 1600 2000 SE +/- 0.21, N = 3 1656.55 1. (CXX) g++ options: -lpthread
ASKAP Test: tConvolve OpenMP - Gridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve OpenMP - Gridding Ryzen 9 3950X 500 1000 1500 2000 2500 SE +/- 12.25, N = 3 2377.41 1. (CXX) g++ options: -lpthread
ASKAP Test: tConvolve OpenMP - Degridding OpenBenchmarking.org Million Grid Points Per Second, More Is Better ASKAP 2018-11-10 Test: tConvolve OpenMP - Degridding Ryzen 9 3950X 500 1000 1500 2000 2500 SE +/- 5.92, N = 3 2176.51 1. (CXX) g++ options: -lpthread
QMCPACK OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.8 Ryzen 9 3950X 300 600 900 1200 1500 1236.4 1. (CXX) g++ options: -fopenmp -fomit-frame-pointer -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -march=native -O3 -ffast-math -lm
miniFE Problem Size: Small OpenBenchmarking.org CG Mflops, More Is Better miniFE 2.2 Problem Size: Small Ryzen 9 3950X 800 1600 2400 3200 4000 SE +/- 0.87, N = 3 3810.13 1. (CXX) g++ options: -O3 -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 Ryzen 9 3950X 50 100 150 200 250 209.47
Timed GCC Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed GCC Compilation 8.2 Time To Compile Ryzen 9 3950X 120 240 360 480 600 SE +/- 0.63, N = 3 548.45
Timed Linux Kernel Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Linux Kernel Compilation 5.4 Time To Compile Ryzen 9 3950X 9 18 27 36 45 SE +/- 0.37, N = 3 38.91
Build2 Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Build2 0.12 Time To Compile Ryzen 9 3950X 14 28 42 56 70 SE +/- 0.12, N = 3 60.39
Phoronix Test Suite v10.8.5