Ryzen 9 5950X oneDNN 2.0 AMD Ryzen 9 5950X 16-Core testing with a ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3003 BIOS) and AMD SIENNA_CICHLID 16GB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2012095-HA-RYZEN959559&sro .
Ryzen 9 5950X oneDNN 2.0 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Vulkan Compiler File-System Screen Resolution Ryzen 9 5950X 5950X AMD Ryzen 9 5950X AMD Ryzen 9 5950X 16-Core @ 3.40GHz (16 Cores / 32 Threads) ASUS ROG CROSSHAIR VIII HERO (WI-FI) (3003 BIOS) AMD Starship/Matisse 16GB 2000GB Corsair Force MP600 + 2000GB AMD SIENNA_CICHLID 16GB (2475/1000MHz) AMD Device ab28 ASUS MG28U Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200 Ubuntu 20.04 5.10.0-051000rc6daily20201205-generic (x86_64) 20201204 GNOME Shell 3.36.4 X Server 1.20.8 modesetting 1.20.8 4.6 Mesa 21.0.0-devel (git-ab0d6c9 2020-12-08 focal-oibaf-ppa) (LLVM 11.0.0) 1.2.145 GCC 9.3.0 ext4 2560x1440 OpenBenchmarking.org Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-HskZEa/gcc-9-9.3.0/debian/tmp-nvptx/usr,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 Processor Details - Scaling Governor: acpi-cpufreq performance (Boost: Enabled) - CPU Microcode: 0xa201009 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
Ryzen 9 5950X oneDNN 2.0 onednn: IP Shapes 1D - f32 - CPU onednn: IP Shapes 3D - f32 - CPU onednn: IP Shapes 1D - u8s8f32 - CPU onednn: IP Shapes 3D - u8s8f32 - CPU onednn: Convolution Batch Shapes Auto - f32 - CPU onednn: Deconvolution Batch shapes_1d - f32 - CPU onednn: Deconvolution Batch shapes_3d - f32 - CPU onednn: Convolution Batch Shapes Auto - u8s8f32 - CPU onednn: Deconvolution Batch shapes_1d - u8s8f32 - CPU onednn: Deconvolution Batch shapes_3d - u8s8f32 - CPU onednn: Recurrent Neural Network Training - f32 - CPU onednn: Recurrent Neural Network Inference - f32 - CPU onednn: Recurrent Neural Network Training - u8s8f32 - CPU onednn: Recurrent Neural Network Inference - u8s8f32 - CPU onednn: Matrix Multiply Batch Shapes Transformer - f32 - CPU onednn: Recurrent Neural Network Training - bf16bf16bf16 - CPU onednn: Recurrent Neural Network Inference - bf16bf16bf16 - CPU onednn: Matrix Multiply Batch Shapes Transformer - u8s8f32 - CPU Ryzen 9 5950X 5950X AMD Ryzen 9 5950X 4.88635 10.7981 0.923413 0.590576 17.2358 2.76049 3.73727 19.5530 3.25019 1.71043 3452.89 2278.07 3470.03 2311.85 0.749824 3430.66 2301.02 1.39888 4.94604 10.6396 0.921791 0.590725 17.3880 2.74784 3.76784 19.1957 3.24561 1.70081 2837.83 1783.44 2719.30 1792.44 0.633434 2725.67 1796.69 1.25288 3.99001 9.07806 0.819649 0.466624 15.2630 2.47316 3.56623 17.5362 2.87312 1.52908 2738.61 1792.81 2722.05 1789.88 0.639379 2722.51 1794.41 1.25478 OpenBenchmarking.org
oneDNN Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU 5950X AMD Ryzen 9 5950X Ryzen 9 5950X 1.1129 2.2258 3.3387 4.4516 5.5645 SE +/- 0.00835, N = 3 SE +/- 0.01234, N = 3 SE +/- 0.01184, N = 3 4.94604 3.99001 4.88635 MIN: 3.84 MIN: 3.74 MIN: 3.77 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU 5950X AMD Ryzen 9 5950X Ryzen 9 5950X 3 6 9 12 15 SE +/- 0.02284, N = 3 SE +/- 0.02957, N = 3 SE +/- 0.06286, N = 3 10.63960 9.07806 10.79810 MIN: 9.21 MIN: 8.88 MIN: 9.36 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU 5950X AMD Ryzen 9 5950X Ryzen 9 5950X 0.2078 0.4156 0.6234 0.8312 1.039 SE +/- 0.004155, N = 3 SE +/- 0.003079, N = 3 SE +/- 0.004129, N = 3 0.921791 0.819649 0.923413 MIN: 0.73 MIN: 0.74 MIN: 0.73 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU 5950X AMD Ryzen 9 5950X Ryzen 9 5950X 0.1329 0.2658 0.3987 0.5316 0.6645 SE +/- 0.007956, N = 3 SE +/- 0.004577, N = 3 SE +/- 0.008135, N = 4 0.590725 0.466624 0.590576 MIN: 0.43 MIN: 0.42 MIN: 0.43 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU 5950X AMD Ryzen 9 5950X Ryzen 9 5950X 4 8 12 16 20 SE +/- 0.10, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 17.39 15.26 17.24 MIN: 15.24 MIN: 14.96 MIN: 15.64 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU 5950X AMD Ryzen 9 5950X Ryzen 9 5950X 0.6211 1.2422 1.8633 2.4844 3.1055 SE +/- 0.00454, N = 3 SE +/- 0.00285, N = 3 SE +/- 0.00796, N = 3 2.74784 2.47316 2.76049 MIN: 2.32 MIN: 2.35 MIN: 2.33 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU 5950X AMD Ryzen 9 5950X Ryzen 9 5950X 0.8478 1.6956 2.5434 3.3912 4.239 SE +/- 0.00362, N = 3 SE +/- 0.01129, N = 3 SE +/- 0.02064, N = 3 3.76784 3.56623 3.73727 MIN: 3.44 MIN: 3.43 MIN: 3.45 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU 5950X AMD Ryzen 9 5950X Ryzen 9 5950X 5 10 15 20 25 SE +/- 0.07, N = 3 SE +/- 0.02, N = 3 SE +/- 0.18, N = 3 19.20 17.54 19.55 MIN: 17.49 MIN: 17.34 MIN: 17.64 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU 5950X AMD Ryzen 9 5950X Ryzen 9 5950X 0.7313 1.4626 2.1939 2.9252 3.6565 SE +/- 0.00415, N = 3 SE +/- 0.00979, N = 3 SE +/- 0.01109, N = 3 3.24561 2.87312 3.25019 MIN: 2.69 MIN: 2.69 MIN: 2.71 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU 5950X AMD Ryzen 9 5950X Ryzen 9 5950X 0.3848 0.7696 1.1544 1.5392 1.924 SE +/- 0.02055, N = 3 SE +/- 0.00305, N = 3 SE +/- 0.02353, N = 4 1.70081 1.52908 1.71043 MIN: 1.39 MIN: 1.42 MIN: 1.38 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU 5950X AMD Ryzen 9 5950X Ryzen 9 5950X 700 1400 2100 2800 3500 SE +/- 61.69, N = 15 SE +/- 8.59, N = 3 SE +/- 24.21, N = 3 2837.83 2738.61 3452.89 MIN: 2694.16 MIN: 2703.64 MIN: 3269.28 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU 5950X AMD Ryzen 9 5950X Ryzen 9 5950X 500 1000 1500 2000 2500 SE +/- 17.36, N = 3 SE +/- 16.22, N = 3 SE +/- 19.83, N = 3 1783.44 1792.81 2278.07 MIN: 1744.5 MIN: 1758.27 MIN: 2142.14 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU 5950X AMD Ryzen 9 5950X Ryzen 9 5950X 700 1400 2100 2800 3500 SE +/- 10.75, N = 3 SE +/- 1.91, N = 3 SE +/- 34.90, N = 3 2719.30 2722.05 3470.03 MIN: 2684.87 MIN: 2706.03 MIN: 3247.9 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU 5950X AMD Ryzen 9 5950X Ryzen 9 5950X 500 1000 1500 2000 2500 SE +/- 16.52, N = 3 SE +/- 14.95, N = 3 SE +/- 15.75, N = 3 1792.44 1789.88 2311.85 MIN: 1756.29 MIN: 1759.62 MIN: 2201.85 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: f32 - Engine: CPU 5950X AMD Ryzen 9 5950X Ryzen 9 5950X 0.1687 0.3374 0.5061 0.6748 0.8435 SE +/- 0.000694, N = 3 SE +/- 0.001565, N = 3 SE +/- 0.002893, N = 3 0.633434 0.639379 0.749824 MIN: 0.6 MIN: 0.6 MIN: 0.59 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU 5950X AMD Ryzen 9 5950X Ryzen 9 5950X 700 1400 2100 2800 3500 SE +/- 14.90, N = 3 SE +/- 7.34, N = 3 SE +/- 23.57, N = 3 2725.67 2722.51 3430.66 MIN: 2697.95 MIN: 2697.53 MIN: 3266.99 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU 5950X AMD Ryzen 9 5950X Ryzen 9 5950X 500 1000 1500 2000 2500 SE +/- 6.01, N = 3 SE +/- 14.93, N = 3 SE +/- 16.79, N = 3 1796.69 1794.41 2301.02 MIN: 1769.4 MIN: 1752.05 MIN: 2170.9 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
oneDNN Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU OpenBenchmarking.org ms, Fewer Is Better oneDNN 2.0 Harness: Matrix Multiply Batch Shapes Transformer - Data Type: u8s8f32 - Engine: CPU 5950X AMD Ryzen 9 5950X Ryzen 9 5950X 0.3147 0.6294 0.9441 1.2588 1.5735 SE +/- 0.00040, N = 3 SE +/- 0.00029, N = 3 SE +/- 0.00261, N = 3 1.25288 1.25478 1.39888 MIN: 1.16 MIN: 1.16 MIN: 1.15 1. (CXX) g++ options: -O3 -std=c++11 -fopenmp -msse4.1 -fPIC -pie -lpthread
Phoronix Test Suite v10.8.5