VkFFT + Caffe + Other GPU Tests - AMD vs. NVIDIA AMD Ryzen 9 3950X 16-Core testing with a ASUS ROG CROSSHAIR VIII HERO (WI-FI) (1302 BIOS) and Sapphire AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 6GB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2010013-PTS-VKFFTAMD84&rdt&grr .
VkFFT + Caffe + Other GPU Tests - AMD vs. NVIDIA Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL OpenCL Vulkan Compiler File-System Screen Resolution GTX 1660 RTX 2070 RTX 2080 SUPER RTX 2080 GTX 1650 SUPER RTX 2070 SUPER RTX 2060 SUPER RTX 2060 GTX 1660 Ti RTX 2080 Ti GTX 1060 GTX 1080 GTX 1660 SUPER GTX 1650 TITAN RTX Radeon VII RX 5700 RX 5700 XT RX Vega 56 RX 5600 XT AMD Ryzen 9 3950X 16-Core @ 3.50GHz (16 Cores / 32 Threads) ASUS ROG CROSSHAIR VIII HERO (WI-FI) (1302 BIOS) AMD Starship/Matisse 16GB 2000GB Corsair Force MP600 + 2000GB ASUS NVIDIA GeForce GTX 1660 6GB (405/405MHz) NVIDIA TU116 HD Audio DELL P2415Q Realtek RTL8125 2.5GbE + Intel I211 + Intel Wi-Fi 6 AX200 Ubuntu 20.04 5.4.0-48-generic (x86_64) GNOME Shell 3.36.4 X Server 1.20.8 NVIDIA 450.66 4.6.0 OpenCL 2.0 AMD-APP (3182.0) + OpenCL 1.2 CUDA 11.0.228 1.2.133 GCC 9.3.0 + CUDA 11.0 ext4 3840x2160 ASUS NVIDIA GeForce RTX 2070 8GB (420/405MHz) NVIDIA TU106 HD Audio NVIDIA GeForce RTX 2080 SUPER 8GB (390/405MHz) NVIDIA TU104 HD Audio Zotac NVIDIA GeForce RTX 2080 8GB (1515/7000MHz) ASUS NVIDIA GeForce GTX 1650 SUPER 4GB (1530/6000MHz) NVIDIA TU116 HD Audio NVIDIA GeForce RTX 2070 SUPER 8GB (1605/7000MHz) NVIDIA TU104 HD Audio NVIDIA GeForce RTX 2060 SUPER 8GB (1470/7000MHz) NVIDIA TU106 HD Audio NVIDIA GeForce RTX 2060 6GB (435/405MHz) eVGA NVIDIA GeForce GTX 1660 Ti 6GB (390/405MHz) NVIDIA TU116 HD Audio NVIDIA GeForce RTX 2080 Ti 11GB (420/405MHz) NVIDIA TU102 HD Audio NVIDIA GeForce GTX 1060 6GB (1506/4006MHz) NVIDIA GP106 HD Audio NVIDIA GeForce GTX 1080 8GB (1607/5005MHz) NVIDIA GP104 HD Audio eVGA NVIDIA GeForce GTX 1660 SUPER 6GB (435/405MHz) NVIDIA TU116 HD Audio ASUS NVIDIA GeForce GTX 1650 4GB (525/405MHz) NVIDIA Device 10fa NVIDIA TITAN RTX 24GB (420/405MHz) NVIDIA TU102 HD Audio AMD Radeon VII 16GB (1801/1000MHz) AMD Vega 20 HDMI Audio 5.9.0-050900rc7daily20201001-generic (x86_64) 20200930 4.6 Mesa 20.3.0-devel (git-3173367 2020-09-25 focal-oibaf-ppa) (LLVM 10.0.1) OpenCL 2.0 AMD-APP (3182.0) 1.2.145 AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (1750/875MHz) AMD Navi 10 HDMI Audio AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 8GB (2100/875MHz) AMD Radeon RX 56/64 8GB (1590/800MHz) AMD Vega 10 HDMI Audio Sapphire AMD Radeon RX 5600 OEM/5600 XT / 5700/5700 6GB (1780/875MHz) AMD Navi 10 HDMI Audio 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,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 ondemand - CPU Microcode: 0x8701013 Python Details - GTX 1660, RTX 2070, RTX 2080 SUPER, RTX 2080, GTX 1650 SUPER, RTX 2070 SUPER, RTX 2060 SUPER, RTX 2060, GTX 1660 Ti, RTX 2080 Ti, GTX 1060, GTX 1080, GTX 1660 SUPER, GTX 1650, TITAN RTX, RX 5700, RX 5700 XT, RX Vega 56, RX 5600 XT: Python 3.8.2 Security Details - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Full AMD retpoline IBPB: conditional STIBP: conditional RSB filling + srbds: Not affected + tsx_async_abort: Not affected
VkFFT + Caffe + Other GPU Tests - AMD vs. NVIDIA glmark2: 1920 x 1080 glmark2: 3840 x 2160 glmark2: 2560 x 1440 realsr-ncnn: 4x - Yes vkfft: ncnn: Vulkan GPU - yolov4-tiny ncnn: Vulkan GPU - resnet50 ncnn: Vulkan GPU - alexnet ncnn: Vulkan GPU - resnet18 ncnn: Vulkan GPU - vgg16 ncnn: Vulkan GPU - googlenet ncnn: Vulkan GPU - blazeface ncnn: Vulkan GPU - efficientnet-b0 ncnn: Vulkan GPU - mnasnet ncnn: Vulkan GPU - shufflenet-v2 ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 ncnn: Vulkan GPU - mobilenet ncnn: Vulkan GPU - squeezenet realsr-ncnn: 4x - No GTX 1660 RTX 2070 RTX 2080 SUPER RTX 2080 GTX 1650 SUPER RTX 2070 SUPER RTX 2060 SUPER RTX 2060 GTX 1660 Ti RTX 2080 Ti GTX 1060 GTX 1080 GTX 1660 SUPER GTX 1650 TITAN RTX Radeon VII RX 5700 RX 5700 XT RX Vega 56 RX 5600 XT 13765 27044 31364 28987 13073 28070 27018 21217 18213 37847 12916 20887 18733 9495 40210 10659 3903 7341 41.299 33252 9.73 6.74 3.99 2.07 10.27 7.18 0.94 11.21 3.20 2.65 4.08 2.90 9.87 5.07 7.257 8831 2707 5563 59.255 19749 8.50 5.04 5.45 1.71 15.05 4.27 0.77 7.45 2.24 1.86 3.13 2.15 6.60 3.57 9.413 9308 2798 5805 55.734 20739 8.29 4.44 4.79 1.56 12.97 3.87 0.73 6.21 2.05 1.71 2.82 1.95 6.56 3.31 8.994 7209 2315 4595 66.098 18696 7.68 6.57 4.40 2.19 11.61 5.74 0.87 10.56 2.80 2.35 3.71 2.61 6.25 4.91 10.266 7399 2062 4507 80.081 16593 8.51 5.00 5.20 1.73 15.31 4.23 0.76 7.16 2.23 1.83 3.09 2.14 6.58 3.60 12.029 OpenBenchmarking.org
GLmark2 Resolution: 1920 x 1080 OpenBenchmarking.org Score, More Is Better GLmark2 2020.04 Resolution: 1920 x 1080 Radeon VII RX 5700 RX 5700 XT RX Vega 56 RX 5600 XT 2K 4K 6K 8K 10K 10659 8831 9308 7209 7399
GLmark2 Resolution: 3840 x 2160 OpenBenchmarking.org Score, More Is Better GLmark2 2020.04 Resolution: 3840 x 2160 Radeon VII RX 5700 RX 5700 XT RX Vega 56 RX 5600 XT 800 1600 2400 3200 4000 3903 2707 2798 2315 2062
GLmark2 Resolution: 2560 x 1440 OpenBenchmarking.org Score, More Is Better GLmark2 2020.04 Resolution: 2560 x 1440 Radeon VII RX 5700 RX 5700 XT RX Vega 56 RX 5600 XT 1600 3200 4800 6400 8000 7341 5563 5805 4595 4507
RealSR-NCNN Scale: 4x - TAA: Yes OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: Yes Radeon VII RX 5700 RX 5700 XT RX Vega 56 RX 5600 XT 20 40 60 80 100 SE +/- 0.08, N = 3 SE +/- 0.32, N = 3 SE +/- 0.21, N = 3 SE +/- 0.14, N = 3 SE +/- 0.10, N = 3 41.30 59.26 55.73 66.10 80.08
VkFFT OpenBenchmarking.org Benchmark Score, More Is Better VkFFT 2020-09-29 GTX 1660 RTX 2070 RTX 2080 SUPER RTX 2080 GTX 1650 SUPER RTX 2070 SUPER RTX 2060 SUPER RTX 2060 GTX 1660 Ti RTX 2080 Ti GTX 1060 GTX 1080 GTX 1660 SUPER GTX 1650 TITAN RTX Radeon VII RX 5700 RX 5700 XT RX Vega 56 RX 5600 XT 9K 18K 27K 36K 45K SE +/- 20.28, N = 3 SE +/- 70.64, N = 3 SE +/- 9.64, N = 3 SE +/- 94.29, N = 3 SE +/- 12.06, N = 3 SE +/- 41.73, N = 3 SE +/- 39.01, N = 3 SE +/- 47.07, N = 3 SE +/- 28.10, N = 3 SE +/- 62.20, N = 3 SE +/- 30.94, N = 3 SE +/- 41.53, N = 3 SE +/- 50.89, N = 3 SE +/- 12.41, N = 3 SE +/- 130.48, N = 3 SE +/- 44.69, N = 3 SE +/- 1.86, N = 3 SE +/- 110.33, N = 3 SE +/- 30.14, N = 3 SE +/- 20.99, N = 3 13765 27044 31364 28987 13073 28070 27018 21217 18213 37847 12916 20887 18733 9495 40210 33252 19749 20739 18696 16593
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: yolov4-tiny Radeon VII RX 5700 RX 5700 XT RX Vega 56 RX 5600 XT 3 6 9 12 15 SE +/- 0.15, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 9.73 8.50 8.29 7.68 8.51 MIN: 9.25 / MAX: 17.97 MIN: 8.43 / MAX: 9.12 MIN: 8.2 / MAX: 8.46 MIN: 7.59 / MAX: 17.7 MIN: 8.45 / MAX: 9.17 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: resnet50 Radeon VII RX 5700 RX 5700 XT RX Vega 56 RX 5600 XT 2 4 6 8 10 SE +/- 0.16, N = 3 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.08, N = 3 SE +/- 0.05, N = 3 6.74 5.04 4.44 6.57 5.00 MIN: 6.05 / MAX: 28.02 MIN: 4.94 / MAX: 20.04 MIN: 4.4 / MAX: 4.62 MIN: 6.13 / MAX: 20.05 MIN: 4.9 / MAX: 20.02 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: alexnet Radeon VII RX 5700 RX 5700 XT RX Vega 56 RX 5600 XT 1.2263 2.4526 3.6789 4.9052 6.1315 SE +/- 0.19, N = 3 SE +/- 0.08, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 3.99 5.45 4.79 4.40 5.20 MIN: 3.62 / MAX: 21.47 MIN: 5.1 / MAX: 15.28 MIN: 4.55 / MAX: 5.54 MIN: 4.29 / MAX: 5.04 MIN: 4.91 / MAX: 13.16 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: resnet18 Radeon VII RX 5700 RX 5700 XT RX Vega 56 RX 5600 XT 0.4928 0.9856 1.4784 1.9712 2.464 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 2.07 1.71 1.56 2.19 1.73 MIN: 2.02 / MAX: 2.26 MIN: 1.68 / MAX: 2 MIN: 1.54 / MAX: 3.04 MIN: 2.11 / MAX: 2.62 MIN: 1.7 / MAX: 6.56 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: vgg16 Radeon VII RX 5700 RX 5700 XT RX Vega 56 RX 5600 XT 4 8 12 16 20 SE +/- 0.06, N = 3 SE +/- 0.13, N = 3 SE +/- 0.13, N = 3 SE +/- 0.06, N = 3 SE +/- 0.08, N = 3 10.27 15.05 12.97 11.61 15.31 MIN: 8.89 / MAX: 31.17 MIN: 13.68 / MAX: 35.48 MIN: 12.15 / MAX: 32.38 MIN: 10.68 / MAX: 28.02 MIN: 14.47 / MAX: 34.92 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: googlenet Radeon VII RX 5700 RX 5700 XT RX Vega 56 RX 5600 XT 2 4 6 8 10 SE +/- 0.28, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 7.18 4.27 3.87 5.74 4.23 MIN: 6.67 / MAX: 29.14 MIN: 4.24 / MAX: 5.75 MIN: 3.83 / MAX: 9.58 MIN: 5.7 / MAX: 6.62 MIN: 4.21 / MAX: 4.44 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: blazeface Radeon VII RX 5700 RX 5700 XT RX Vega 56 RX 5600 XT 0.2115 0.423 0.6345 0.846 1.0575 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 0.94 0.77 0.73 0.87 0.76 MIN: 0.92 / MAX: 1.46 MIN: 0.75 / MAX: 1.11 MIN: 0.7 / MAX: 1.11 MIN: 0.85 / MAX: 1.56 MIN: 0.74 / MAX: 1.1 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: efficientnet-b0 Radeon VII RX 5700 RX 5700 XT RX Vega 56 RX 5600 XT 3 6 9 12 15 SE +/- 0.21, N = 3 SE +/- 0.18, N = 3 SE +/- 0.02, N = 3 SE +/- 0.30, N = 3 SE +/- 0.03, N = 3 11.21 7.45 6.21 10.56 7.16 MIN: 9.77 / MAX: 33.86 MIN: 6.81 / MAX: 27.08 MIN: 6.07 / MAX: 11.02 MIN: 9.2 / MAX: 27.19 MIN: 6.68 / MAX: 24.27 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: mnasnet Radeon VII RX 5700 RX 5700 XT RX Vega 56 RX 5600 XT 0.72 1.44 2.16 2.88 3.6 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 3.20 2.24 2.05 2.80 2.23 MIN: 3.17 / MAX: 4.84 MIN: 2.21 / MAX: 2.47 MIN: 2.01 / MAX: 2.47 MIN: 2.75 / MAX: 3.88 MIN: 2.18 / MAX: 4.11 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: shufflenet-v2 Radeon VII RX 5700 RX 5700 XT RX Vega 56 RX 5600 XT 0.5963 1.1926 1.7889 2.3852 2.9815 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 2.65 1.86 1.71 2.35 1.83 MIN: 2.63 / MAX: 2.88 MIN: 1.84 / MAX: 2.07 MIN: 1.69 / MAX: 2 MIN: 2.31 / MAX: 3.34 MIN: 1.81 / MAX: 2.02 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 Radeon VII RX 5700 RX 5700 XT RX Vega 56 RX 5600 XT 0.918 1.836 2.754 3.672 4.59 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 4.08 3.13 2.82 3.71 3.09 MIN: 4.04 / MAX: 9.72 MIN: 3.08 / MAX: 3.74 MIN: 2.78 / MAX: 3.06 MIN: 3.67 / MAX: 4.44 MIN: 3.05 / MAX: 3.31 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 Radeon VII RX 5700 RX 5700 XT RX Vega 56 RX 5600 XT 0.6525 1.305 1.9575 2.61 3.2625 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 2.90 2.15 1.95 2.61 2.14 MIN: 2.6 / MAX: 4.84 MIN: 2.11 / MAX: 3.05 MIN: 1.92 / MAX: 2.19 MIN: 2.57 / MAX: 3.31 MIN: 2.09 / MAX: 2.36 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: mobilenet Radeon VII RX 5700 RX 5700 XT RX Vega 56 RX 5600 XT 3 6 9 12 15 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.00, N = 3 9.87 6.60 6.56 6.25 6.58 MIN: 6.98 / MAX: 25.45 MIN: 6.54 / MAX: 6.76 MIN: 6.49 / MAX: 6.71 MIN: 6.17 / MAX: 6.44 MIN: 6.54 / MAX: 6.77 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: squeezenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: squeezenet Radeon VII RX 5700 RX 5700 XT RX Vega 56 RX 5600 XT 1.1408 2.2816 3.4224 4.5632 5.704 SE +/- 0.01, N = 3 SE +/- 0.00, N = 3 SE +/- 0.02, N = 3 SE +/- 0.00, N = 3 SE +/- 0.01, N = 3 5.07 3.57 3.31 4.91 3.60 MIN: 4.71 / MAX: 9.34 MIN: 3.46 / MAX: 3.77 MIN: 3.21 / MAX: 3.5 MIN: 4.76 / MAX: 5.78 MIN: 3.48 / MAX: 5.3 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
RealSR-NCNN Scale: 4x - TAA: No OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: No Radeon VII RX 5700 RX 5700 XT RX Vega 56 RX 5600 XT 3 6 9 12 15 SE +/- 0.006, N = 3 SE +/- 0.019, N = 3 SE +/- 0.035, N = 3 SE +/- 0.025, N = 3 SE +/- 0.013, N = 3 7.257 9.413 8.994 10.266 12.029
Phoronix Test Suite v10.8.4