ncnn R7-7950X AMD Ryzen 9 7950X3D 16-Core testing with a MSI MAG X670E TOMAHAWK WIFI (MS-7E12) v1.0 (1.80 BIOS) and NVIDIA RTX A6000 48GB on Ubuntu 22.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2407054-SIDD-NCNNR7788&gru .
ncnn R7-7950X Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Vulkan Compiler File-System Screen Resolution A6000 48GB AMD Ryzen 9 7950X3D 16-Core @ 5.76GHz (16 Cores / 32 Threads) MSI MAG X670E TOMAHAWK WIFI (MS-7E12) v1.0 (1.80 BIOS) AMD Device 14d8 4 x 32GB DRAM-3600MT/s F5-6800J3445G32G 2000GB Samsung SSD 990 PRO 2TB + 2 x 6001GB TOSHIBA MG08ADA6 NVIDIA RTX A6000 48GB NVIDIA GA102 HD Audio BenQ GW2480L Realtek RTL8125 2.5GbE + MEDIATEK Device 0616 Ubuntu 22.04 6.5.0-41-generic (x86_64) GNOME Shell 42.9 X Server 1.21.1.4 NVIDIA 535.183.01 4.6.0 1.3.242 GCC 11.4.0 + CUDA 12.2 ext4 1920x1080 OpenBenchmarking.org - Transparent Huge Pages: madvise - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --enable-cet --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++,m2 --enable-libphobos-checking=release --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-link-serialization=2 --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-XeT9lY/gcc-11-11.4.0/debian/tmp-gcn/usr --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: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601206 - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + spec_rstack_overflow: Mitigation of Safe RET + spec_store_bypass: Mitigation of SSB disabled via prctl + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced / Automatic IBRS; IBPB: conditional; STIBP: always-on; RSB filling; PBRSB-eIBRS: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
ncnn R7-7950X ncnn: Vulkan GPU - mobilenet ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 ncnn: Vulkan GPU - shufflenet-v2 ncnn: Vulkan GPU - mnasnet ncnn: Vulkan GPU - efficientnet-b0 ncnn: Vulkan GPU - blazeface ncnn: Vulkan GPU - googlenet ncnn: Vulkan GPU - vgg16 ncnn: Vulkan GPU - resnet18 ncnn: Vulkan GPU - alexnet ncnn: Vulkan GPU - resnet50 ncnn: Vulkan GPUv2-yolov3v2-yolov3 - mobilenetv2-yolov3 ncnn: Vulkan GPU - yolov4-tiny ncnn: Vulkan GPU - squeezenet_ssd ncnn: Vulkan GPU - regnety_400m ncnn: Vulkan GPU - vision_transformer ncnn: Vulkan GPU - FastestDet A6000 48GB 10.52 3.96 3.96 4.14 3.80 5.13 1.60 9.84 36.92 6.48 5.51 13.33 10.52 16.72 9.06 10.59 41.81 3.83 OpenBenchmarking.org
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: mobilenet A6000 48GB 3 6 9 12 15 SE +/- 0.14, N = 3 10.52 MIN: 8.86 / MAX: 113.31 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 A6000 48GB 0.891 1.782 2.673 3.564 4.455 SE +/- 0.05, N = 3 3.96 MIN: 3.11 / MAX: 116.17 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 A6000 48GB 0.891 1.782 2.673 3.564 4.455 SE +/- 0.31, N = 3 3.96 MIN: 2.93 / MAX: 216.73 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: shufflenet-v2 A6000 48GB 0.9315 1.863 2.7945 3.726 4.6575 SE +/- 0.11, N = 3 4.14 MIN: 3.65 / MAX: 99.02 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: mnasnet A6000 48GB 0.855 1.71 2.565 3.42 4.275 SE +/- 0.04, N = 3 3.80 MIN: 3.1 / MAX: 56.04 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: efficientnet-b0 A6000 48GB 1.1543 2.3086 3.4629 4.6172 5.7715 SE +/- 0.29, N = 3 5.13 MIN: 4.29 / MAX: 142.46 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: blazeface A6000 48GB 0.36 0.72 1.08 1.44 1.8 SE +/- 0.15, N = 3 1.60 MIN: 1.26 / MAX: 61.79 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: googlenet A6000 48GB 3 6 9 12 15 SE +/- 0.14, N = 3 9.84 MIN: 8.2 / MAX: 125.75 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: vgg16 A6000 48GB 8 16 24 32 40 SE +/- 0.66, N = 3 36.92 MIN: 28.79 / MAX: 237.06 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: resnet18 A6000 48GB 2 4 6 8 10 SE +/- 0.11, N = 3 6.48 MIN: 5.04 / MAX: 126.35 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: alexnet A6000 48GB 1.2398 2.4796 3.7194 4.9592 6.199 SE +/- 0.16, N = 3 5.51 MIN: 4.25 / MAX: 71.93 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: resnet50 A6000 48GB 3 6 9 12 15 SE +/- 0.22, N = 3 13.33 MIN: 11.19 / MAX: 131.29 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPUv2-yolov3v2-yolov3 - Model: mobilenetv2-yolov3 A6000 48GB 3 6 9 12 15 SE +/- 0.14, N = 3 10.52 MIN: 8.86 / MAX: 113.31 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: yolov4-tiny A6000 48GB 4 8 12 16 20 SE +/- 0.31, N = 3 16.72 MIN: 13.94 / MAX: 163.44 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: squeezenet_ssd A6000 48GB 3 6 9 12 15 SE +/- 0.19, N = 3 9.06 MIN: 7.52 / MAX: 128.79 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: regnety_400m A6000 48GB 3 6 9 12 15 SE +/- 0.18, N = 3 10.59 MIN: 9.36 / MAX: 100.57 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: vision_transformer A6000 48GB 10 20 30 40 50 SE +/- 0.55, N = 3 41.81 MIN: 35.48 / MAX: 161.34 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: FastestDet A6000 48GB 0.8618 1.7236 2.5854 3.4472 4.309 SE +/- 0.41, N = 3 3.83 MIN: 2.89 / MAX: 57.76 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Phoronix Test Suite v10.8.5