AMD Ryzen 3 3200U testing with a MOTILE PF4PU1F (N.1.03 BIOS) and AMD Picasso 512MB on Ubuntu 20.04 via the Phoronix Test Suite.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2012184-HA-NCNN3200U73 ncnn 3200u dec - Phoronix Test Suite ncnn 3200u dec AMD Ryzen 3 3200U testing with a MOTILE PF4PU1F (N.1.03 BIOS) and AMD Picasso 512MB on Ubuntu 20.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2012184-HA-NCNN3200U73&grw&rdt .
ncnn 3200u dec Processor Motherboard Chipset Memory Disk Graphics Audio Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution 1 2 3 4 AMD Ryzen 3 3200U @ 2.60GHz (2 Cores / 4 Threads) MOTILE PF4PU1F (N.1.03 BIOS) AMD Raven/Raven2 3584MB 128GB BIWIN SSD AMD Picasso 512MB (1200/1200MHz) AMD Raven/Raven2/Fenghuang Realtek RTL8111/8168/8411 + Intel Dual Band-AC 3168NGW Ubuntu 20.04 5.4.0-53-generic (x86_64) GNOME Shell 3.36.4 X Server 1.20.8 amdgpu 19.1.0 4.6 Mesa 20.0.4 (LLVM 9.0.1) GCC 9.3.0 ext4 1920x1080 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 ondemand (Boost: Enabled) - CPU Microcode: 0x8108102 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: disabled RSB filling + srbds: Not affected + tsx_async_abort: Not affected
ncnn 3200u dec ncnn: CPU - mobilenet ncnn: CPU-v2-v2 - mobilenet-v2 ncnn: CPU-v3-v3 - mobilenet-v3 ncnn: CPU - shufflenet-v2 ncnn: CPU - mnasnet ncnn: CPU - efficientnet-b0 ncnn: CPU - blazeface ncnn: CPU - googlenet ncnn: CPU - vgg16 ncnn: CPU - resnet18 ncnn: CPU - alexnet ncnn: CPU - resnet50 ncnn: CPU - yolov4-tiny ncnn: CPU - squeezenet_ssd ncnn: CPU - regnety_400m 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 1 2 3 4 99.85 24.07 20.02 24.75 46.80 35.75 6.40 73.23 253.43 65.22 51.91 181.95 112.29 86.86 35.82 101.08 24.85 20.44 25.67 23.21 35.97 5.68 74.44 249.72 66.66 53.20 186.04 112.68 89.35 33.44 101.22 23.79 20.41 25.07 22.93 35.78 5.82 73.49 247.69 65.33 52.13 183.61 113.08 88.43 33.16 101.14 24.95 21.27 25.15 24.01 36.25 6.22 74.18 249.07 67.21 53.10 186.50 113.01 89.90 33.48 101.74 24.27 20.36 25.20 23.26 36.08 5.98 74.00 247.94 66.09 52.71 184.88 113.05 89.40 33.23 101.10 24.52 21.10 25.32 23.37 36.29 5.65 74.35 300.89 66.29 53.12 186.51 113.20 112.39 35.31 101.30 24.42 20.84 25.52 23.45 36.55 6.03 73.91 247.04 66.12 52.67 184.75 112.98 88.29 36.52 101.63 24.52 20.70 25.55 23.65 36.31 6.08 74.38 248.81 66.85 53.29 186.33 113.55 89.54 35.17 OpenBenchmarking.org
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: mobilenet 1 2 3 4 20 40 60 80 100 SE +/- 0.68, N = 3 SE +/- 0.35, N = 3 SE +/- 0.51, N = 3 SE +/- 0.40, N = 3 99.85 101.22 101.74 101.30 MIN: 95.92 / MAX: 115.61 MIN: 96.96 / MAX: 160.85 MIN: 96.92 / MAX: 152.42 MIN: 97.08 / MAX: 158.21 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU-v2-v2 - Model: mobilenet-v2 1 2 3 4 6 12 18 24 30 SE +/- 0.78, N = 3 SE +/- 0.99, N = 3 SE +/- 0.88, N = 3 SE +/- 1.01, N = 3 24.07 23.79 24.27 24.42 MIN: 21.34 / MAX: 37.34 MIN: 21.03 / MAX: 26.87 MIN: 21.41 / MAX: 38.85 MIN: 21.02 / MAX: 40.68 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU-v3-v3 - Model: mobilenet-v3 1 2 3 4 5 10 15 20 25 SE +/- 0.44, N = 3 SE +/- 0.88, N = 3 SE +/- 0.47, N = 3 SE +/- 0.91, N = 3 20.02 20.41 20.36 20.84 MIN: 18.04 / MAX: 26.98 MIN: 17.59 / MAX: 24.28 MIN: 18.11 / MAX: 37.03 MIN: 17.95 / MAX: 25.39 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: shufflenet-v2 1 2 3 4 6 12 18 24 30 SE +/- 0.62, N = 3 SE +/- 0.84, N = 3 SE +/- 0.58, N = 3 SE +/- 0.90, N = 3 24.75 25.07 25.20 25.52 MIN: 22.12 / MAX: 27.35 MIN: 22.2 / MAX: 41.75 MIN: 22.56 / MAX: 29.9 MIN: 21.94 / MAX: 37.38 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: mnasnet 1 2 3 4 11 22 33 44 55 SE +/- 23.79, N = 3 SE +/- 0.20, N = 3 SE +/- 0.44, N = 3 SE +/- 0.63, N = 3 46.80 22.93 23.26 23.45 MIN: 20.73 / MAX: 428.35 MIN: 20.79 / MAX: 26.68 MIN: 20.63 / MAX: 40.95 MIN: 20.64 / MAX: 28.89 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: efficientnet-b0 1 2 3 4 8 16 24 32 40 SE +/- 0.23, N = 3 SE +/- 0.47, N = 3 SE +/- 0.23, N = 3 SE +/- 0.21, N = 3 35.75 35.78 36.08 36.55 MIN: 33.4 / MAX: 53.37 MIN: 32.76 / MAX: 39.37 MIN: 33.79 / MAX: 100.97 MIN: 34.01 / MAX: 50.7 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: blazeface 1 2 3 4 2 4 6 8 10 SE +/- 0.40, N = 3 SE +/- 0.18, N = 3 SE +/- 0.41, N = 3 SE +/- 0.26, N = 3 6.40 5.82 5.98 6.03 MIN: 5.05 / MAX: 7.52 MIN: 5.18 / MAX: 7.05 MIN: 4.97 / MAX: 7.38 MIN: 5.14 / MAX: 21.37 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: googlenet 1 2 3 4 16 32 48 64 80 SE +/- 0.96, N = 3 SE +/- 1.22, N = 3 SE +/- 1.28, N = 3 SE +/- 1.17, N = 3 73.23 73.49 74.00 73.91 MIN: 68.62 / MAX: 91.66 MIN: 68.93 / MAX: 90.75 MIN: 69.03 / MAX: 92.42 MIN: 69.36 / MAX: 92.02 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: vgg16 1 2 3 4 60 120 180 240 300 SE +/- 8.59, N = 3 SE +/- 1.61, N = 3 SE +/- 1.27, N = 3 SE +/- 1.26, N = 3 253.43 247.69 247.94 247.04 MIN: 238.37 / MAX: 519.94 MIN: 239.18 / MAX: 267.29 MIN: 241.46 / MAX: 265.3 MIN: 241.04 / MAX: 257.55 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: resnet18 1 2 3 4 15 30 45 60 75 SE +/- 0.91, N = 3 SE +/- 1.41, N = 3 SE +/- 1.17, N = 3 SE +/- 1.30, N = 3 65.22 65.33 66.09 66.12 MIN: 61.1 / MAX: 77.57 MIN: 61.16 / MAX: 81.83 MIN: 61.66 / MAX: 78.45 MIN: 61.5 / MAX: 81.02 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: alexnet 1 2 3 4 12 24 36 48 60 SE +/- 0.58, N = 3 SE +/- 0.92, N = 3 SE +/- 0.67, N = 3 SE +/- 0.69, N = 3 51.91 52.13 52.71 52.67 MIN: 48.63 / MAX: 61.53 MIN: 48.14 / MAX: 58.95 MIN: 48.99 / MAX: 59.33 MIN: 49.39 / MAX: 58.85 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: resnet50 1 2 3 4 40 80 120 160 200 SE +/- 1.98, N = 3 SE +/- 3.64, N = 3 SE +/- 2.21, N = 3 SE +/- 1.90, N = 3 181.95 183.61 184.88 184.75 MIN: 173.06 / MAX: 255.42 MIN: 171.87 / MAX: 215.45 MIN: 174.55 / MAX: 208.13 MIN: 174.42 / MAX: 210.46 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: yolov4-tiny 1 2 3 4 30 60 90 120 150 SE +/- 0.39, N = 3 SE +/- 0.15, N = 3 SE +/- 0.11, N = 3 SE +/- 0.33, N = 3 112.29 113.08 113.05 112.98 MIN: 106.46 / MAX: 122.02 MIN: 108.1 / MAX: 162.9 MIN: 107.43 / MAX: 127.21 MIN: 107.11 / MAX: 132.25 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: squeezenet_ssd 1 2 3 4 20 40 60 80 100 SE +/- 1.59, N = 3 SE +/- 1.97, N = 3 SE +/- 0.73, N = 3 SE +/- 1.31, N = 3 86.86 88.43 89.40 88.29 MIN: 80.94 / MAX: 100.22 MIN: 80.88 / MAX: 110.25 MIN: 81.82 / MAX: 101.96 MIN: 82 / MAX: 112.35 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: CPU - Model: regnety_400m 1 2 3 4 8 16 24 32 40 SE +/- 1.93, N = 3 SE +/- 0.30, N = 3 SE +/- 0.20, N = 3 SE +/- 0.59, N = 3 35.82 33.16 33.23 36.52 MIN: 31.82 / MAX: 70.3 MIN: 30.87 / MAX: 51.3 MIN: 31.33 / MAX: 37.72 MIN: 32.33 / MAX: 51.53 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: mobilenet 1 2 3 4 20 40 60 80 100 SE +/- 0.15, N = 3 SE +/- 0.31, N = 3 SE +/- 0.16, N = 3 SE +/- 0.12, N = 3 101.08 101.14 101.10 101.63 MIN: 96.39 / MAX: 128.75 MIN: 96.83 / MAX: 115.37 MIN: 96.8 / MAX: 117.39 MIN: 97.01 / MAX: 116.36 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 1 2 3 4 6 12 18 24 30 SE +/- 0.18, N = 3 SE +/- 0.48, N = 3 SE +/- 0.51, N = 3 SE +/- 0.65, N = 3 24.85 24.95 24.52 24.52 MIN: 23.13 / MAX: 29.91 MIN: 22.51 / MAX: 40.99 MIN: 21.86 / MAX: 28.47 MIN: 21.87 / MAX: 39.35 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 1 2 3 4 5 10 15 20 25 SE +/- 0.22, N = 3 SE +/- 0.24, N = 3 SE +/- 0.61, N = 3 SE +/- 0.54, N = 3 20.44 21.27 21.10 20.70 MIN: 19 / MAX: 37.54 MIN: 19.25 / MAX: 25.88 MIN: 18.74 / MAX: 35.77 MIN: 18.71 / MAX: 29.27 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: shufflenet-v2 1 2 3 4 6 12 18 24 30 SE +/- 0.33, N = 3 SE +/- 0.13, N = 3 SE +/- 0.65, N = 3 SE +/- 0.67, N = 3 25.67 25.15 25.32 25.55 MIN: 24.3 / MAX: 29.43 MIN: 23.03 / MAX: 41.63 MIN: 22.2 / MAX: 29.3 MIN: 22.82 / MAX: 43.15 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: mnasnet 1 2 3 4 6 12 18 24 30 SE +/- 0.04, N = 3 SE +/- 0.53, N = 3 SE +/- 0.27, N = 3 SE +/- 0.61, N = 3 23.21 24.01 23.37 23.65 MIN: 21.63 / MAX: 41.61 MIN: 21.04 / MAX: 28.85 MIN: 21.46 / MAX: 41.39 MIN: 20.96 / MAX: 31.66 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: efficientnet-b0 1 2 3 4 8 16 24 32 40 SE +/- 0.23, N = 3 SE +/- 0.19, N = 3 SE +/- 0.33, N = 3 SE +/- 0.28, N = 3 35.97 36.25 36.29 36.31 MIN: 34.43 / MAX: 50.08 MIN: 33.86 / MAX: 50.79 MIN: 34.26 / MAX: 54.2 MIN: 33.06 / MAX: 51.31 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: blazeface 1 2 3 4 2 4 6 8 10 SE +/- 0.04, N = 3 SE +/- 0.33, N = 3 SE +/- 0.05, N = 3 SE +/- 0.40, N = 3 5.68 6.22 5.65 6.08 MIN: 5.13 / MAX: 7.83 MIN: 5.19 / MAX: 8.39 MIN: 5.11 / MAX: 6.36 MIN: 5.04 / MAX: 9.46 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: googlenet 1 2 3 4 20 40 60 80 100 SE +/- 0.23, N = 3 SE +/- 0.53, N = 3 SE +/- 0.62, N = 3 SE +/- 0.55, N = 3 74.44 74.18 74.35 74.38 MIN: 71.44 / MAX: 93.01 MIN: 71.16 / MAX: 92.31 MIN: 70.06 / MAX: 94.82 MIN: 71.54 / MAX: 94.51 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: vgg16 1 2 3 4 70 140 210 280 350 SE +/- 0.54, N = 3 SE +/- 0.47, N = 3 SE +/- 52.32, N = 3 SE +/- 0.62, N = 3 249.72 249.07 300.89 248.81 MIN: 242.63 / MAX: 269.82 MIN: 242.7 / MAX: 281.97 MIN: 242.69 / MAX: 602 MIN: 243.88 / MAX: 296.4 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: resnet18 1 2 3 4 15 30 45 60 75 SE +/- 0.18, N = 3 SE +/- 0.37, N = 3 SE +/- 0.52, N = 3 SE +/- 0.51, N = 3 66.66 67.21 66.29 66.85 MIN: 61.99 / MAX: 83.21 MIN: 62.23 / MAX: 111.2 MIN: 61.85 / MAX: 81.32 MIN: 62.24 / MAX: 81.97 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: alexnet 1 2 3 4 12 24 36 48 60 SE +/- 0.12, N = 3 SE +/- 0.46, N = 3 SE +/- 0.43, N = 3 SE +/- 0.32, N = 3 53.20 53.10 53.12 53.29 MIN: 51.15 / MAX: 67.57 MIN: 50.99 / MAX: 65.71 MIN: 51.3 / MAX: 60.11 MIN: 51.39 / MAX: 71.48 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: resnet50 1 2 3 4 40 80 120 160 200 SE +/- 0.76, N = 3 SE +/- 0.97, N = 3 SE +/- 1.42, N = 3 SE +/- 0.74, N = 3 186.04 186.50 186.51 186.33 MIN: 174.41 / MAX: 255.07 MIN: 173.57 / MAX: 211.06 MIN: 175.35 / MAX: 222.67 MIN: 176.1 / MAX: 210.09 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: yolov4-tiny 1 2 3 4 30 60 90 120 150 SE +/- 0.02, N = 3 SE +/- 0.64, N = 3 SE +/- 0.47, N = 3 SE +/- 0.24, N = 3 112.68 113.01 113.20 113.55 MIN: 107.09 / MAX: 137.39 MIN: 107.12 / MAX: 126.13 MIN: 107.45 / MAX: 129.08 MIN: 107.82 / MAX: 127.26 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: squeezenet_ssd OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: squeezenet_ssd 1 2 3 4 30 60 90 120 150 SE +/- 0.12, N = 3 SE +/- 0.35, N = 3 SE +/- 21.83, N = 3 SE +/- 0.44, N = 3 89.35 89.90 112.39 89.54 MIN: 82.83 / MAX: 120.48 MIN: 83.68 / MAX: 105.97 MIN: 82.79 / MAX: 668.67 MIN: 83 / MAX: 102.78 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: regnety_400m OpenBenchmarking.org ms, Fewer Is Better NCNN 20201218 Target: Vulkan GPU - Model: regnety_400m 1 2 3 4 8 16 24 32 40 SE +/- 0.12, N = 3 SE +/- 0.03, N = 3 SE +/- 1.23, N = 3 SE +/- 0.76, N = 3 33.44 33.48 35.31 35.17 MIN: 31.5 / MAX: 57.47 MIN: 31.52 / MAX: 52.94 MIN: 31.72 / MAX: 51.99 MIN: 32.01 / MAX: 80.44 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Phoronix Test Suite v10.8.4