ncnn7900 Intel Core i9-13900K testing with a ASUS ROG STRIX Z790-E GAMING WIFI (0502 BIOS) and AMD Radeon RX 7900 XT 20GB on Ubuntu 22.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2212222-NE-NCNN7900763&grt .
ncnn7900 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL OpenCL Vulkan Compiler File-System Screen Resolution RX 7900XT Intel Core i9-13900K @ 5.50GHz (24 Cores / 32 Threads) ASUS ROG STRIX Z790-E GAMING WIFI (0502 BIOS) Intel Device 7a27 32GB 4001GB Seagate ZP4000GP304001 + 2000GB CT2000BX500SSD1 AMD Radeon RX 7900 XT 20GB (3125/1249MHz) Intel Device 7a50 Cam Link Pro Intel I226-V + Intel Wi-Fi 6 AX210/AX211/AX411 Ubuntu 22.04 6.1.0-060100rc5-generic (x86_64) GNOME Shell 42.5 X Server 1.21.1.3 + Wayland 4.6 Mesa 22.3.0-devel (LLVM 15.0.3 DRM 3.49) OpenCL 2.1 AMD-APP (3513.0) 1.3.238 GCC 11.3.0 ext4 3840x2160 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-xKiWfi/gcc-11-11.3.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-xKiWfi/gcc-11-11.3.0/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: intel_pstate powersave (EPP: performance) - CPU Microcode: 0x10e - Thermald 2.4.9 - itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Not affected + 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 IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Not affected + tsx_async_abort: Not affected
ncnn7900 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 GPU - yolov4-tiny ncnn: Vulkan GPU - squeezenet_ssd ncnn: Vulkan GPU - regnety_400m ncnn: Vulkan GPU - vision_transformer ncnn: Vulkan GPU - FastestDet RX 7900XT 6.87 2.31 2.36 2.09 1.66 4.97 1.43 3.06 3.44 1.72 1.44 3.87 7.88 4.79 2.60 164.72 2.53 OpenBenchmarking.org
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: mobilenet RX 7900XT 2 4 6 8 10 SE +/- 1.37, N = 12 6.87 MIN: 4.28 / MAX: 50.62 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 RX 7900XT 0.5198 1.0396 1.5594 2.0792 2.599 SE +/- 0.44, N = 12 2.31 MIN: 1.41 / MAX: 25.44 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 RX 7900XT 0.531 1.062 1.593 2.124 2.655 SE +/- 0.23, N = 12 2.36 MIN: 1.88 / MAX: 25.9 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: shufflenet-v2 RX 7900XT 0.4703 0.9406 1.4109 1.8812 2.3515 SE +/- 0.27, N = 12 2.09 MIN: 1.5 / MAX: 23.34 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: mnasnet RX 7900XT 0.3735 0.747 1.1205 1.494 1.8675 SE +/- 0.13, N = 11 1.66 MIN: 1.45 / MAX: 21.78 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: efficientnet-b0 RX 7900XT 1.1183 2.2366 3.3549 4.4732 5.5915 SE +/- 0.23, N = 12 4.97 MIN: 3.97 / MAX: 29.24 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: blazeface RX 7900XT 0.3218 0.6436 0.9654 1.2872 1.609 SE +/- 0.16, N = 12 1.43 MIN: 1.03 / MAX: 31.12 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: googlenet RX 7900XT 0.6885 1.377 2.0655 2.754 3.4425 SE +/- 0.14, N = 12 3.06 MIN: 2.73 / MAX: 25.72 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: vgg16 RX 7900XT 0.774 1.548 2.322 3.096 3.87 SE +/- 0.08, N = 12 3.44 MIN: 3.26 / MAX: 26.59 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: resnet18 RX 7900XT 0.387 0.774 1.161 1.548 1.935 SE +/- 0.05, N = 12 1.72 MIN: 1.6 / MAX: 23.78 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: alexnet RX 7900XT 0.324 0.648 0.972 1.296 1.62 SE +/- 0.16, N = 12 1.44 MIN: 1.07 / MAX: 26.24 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: resnet50 RX 7900XT 0.8708 1.7416 2.6124 3.4832 4.354 SE +/- 0.38, N = 12 3.87 MIN: 2.83 / MAX: 27.56 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: yolov4-tiny RX 7900XT 2 4 6 8 10 SE +/- 0.65, N = 12 7.88 MIN: 5.73 / MAX: 56.25 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: squeezenet_ssd RX 7900XT 1.0778 2.1556 3.2334 4.3112 5.389 SE +/- 1.24, N = 12 4.79 MIN: 2.87 / MAX: 63.65 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: regnety_400m RX 7900XT 0.585 1.17 1.755 2.34 2.925 SE +/- 0.04, N = 12 2.60 MIN: 2.47 / MAX: 23.56 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vision_transformer OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: vision_transformer RX 7900XT 40 80 120 160 200 SE +/- 6.34, N = 12 164.72 MIN: 100.89 / MAX: 1667 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: FastestDet OpenBenchmarking.org ms, Fewer Is Better NCNN 20220729 Target: Vulkan GPU - Model: FastestDet RX 7900XT 0.5693 1.1386 1.7079 2.2772 2.8465 SE +/- 0.45, N = 11 2.53 MIN: 1.6 / MAX: 25.65 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Phoronix Test Suite v10.8.5