3300X NN + More AMD Ryzen 7 1700 Eight-Core testing with a MSI B350 TOMAHAWK (MS-7A34) v1.0 (1.H0 BIOS) and AMD Radeon RX 470/480/570/570X/580/580X/590 8GB on Ubuntu 19.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2009269-FI-3300XNNMO11&grs&sro&rro .
3300X NN + More Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Vulkan Compiler File-System Screen Resolution 1 2 3 4 AMD Ryzen 7 1700 Eight-Core @ 3.00GHz (8 Cores / 16 Threads) MSI B350 TOMAHAWK (MS-7A34) v1.0 (1.H0 BIOS) AMD 17h 16GB 120GB Samsung SSD 840 AMD Radeon RX 470/480/570/570X/580/580X/590 8GB (1266/2000MHz) AMD Ellesmere HDMI Audio VA2431 Realtek RTL8111/8168/8411 Ubuntu 19.10 5.9.0-050900rc2-generic (x86_64) 20200823 GNOME Shell 3.34.1 X Server 1.20.5 amdgpu 19.0.1 4.5 Mesa 19.2.8 (LLVM 9.0.0) 1.1.107 GCC 9.2.1 20191008 ext4 1920x1080 OpenBenchmarking.org Compiler Details - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --enable-bootstrap --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-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: 0x8001137 Graphics Details - GLAMOR Python Details - Python 2.7.17rc1 + Python 3.7.5 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
3300X NN + More influxdb: 64 - 10000 - 2,5000,1 - 10000 osbench: Launch Programs ncnn: CPU - resnet50 ncnn: Vulkan GPU - blazeface ncnn: CPU - efficientnet-b0 lammps: Rhodopsin Protein ncnn: CPU - mnasnet ncnn: CPU - alexnet osbench: Create Processes webp: Quality 100, Lossless, Highest Compression mnn: inception-v3 osbench: Create Threads osbench: Create Files mnn: SqueezeNetV1.0 ncnn: CPU - mobilenet mnn: MobileNetV2_224 lammps: 20k Atoms webp: Quality 100, Lossless mnn: resnet-v2-50 ncnn: CPU - vgg16 dcraw: RAW To PPM Image Conversion ncnn: CPU - squeezenet ncnn: Vulkan GPU - efficientnet-b0 incompact3d: Cylinder webp: Quality 100 ncnn: CPU - shufflenet-v2 ncnn: Vulkan GPU - yolov4-tiny gpaw: Carbon Nanotube ncnn: Vulkan GPU - shufflenet-v2 ncnn: Vulkan GPU - resnet18 tnn: CPU - SqueezeNet v1.1 ncnn: Vulkan GPU - resnet50 mnn: mobilenet-v1-1.0 mpv: Big Buck Bunny Sunflower 1080p - Software Only webp: Default tnn: CPU - MobileNet v2 ncnn: Vulkan GPU - alexnet libraw: Post-Processing Benchmark ncnn: Vulkan GPU-v2-v2 - mobilenet-v2 glmark2: 1280 x 1024 ncnn: Vulkan GPU - mnasnet mpv: Big Buck Bunny Sunflower 4K - Software Only osbench: Memory Allocations ncnn: Vulkan GPU-v3-v3 - mobilenet-v3 ncnn: CPU - yolov4-tiny glmark2: 1920 x 1080 ncnn: Vulkan GPU - mobilenet ncnn: Vulkan GPU - squeezenet webp: Quality 100, Highest Compression realsr-ncnn: 4x - No ncnn: Vulkan GPU - vgg16 ncnn: Vulkan GPU - googlenet realsr-ncnn: 4x - Yes kripke: mocassin: Dust 2D tau100.0 influxdb: 1024 - 10000 - 2,5000,1 - 10000 influxdb: 4 - 10000 - 2,5000,1 - 10000 opencv: DNN - Deep Neural Network ncnn: CPU - resnet18 ncnn: CPU - googlenet ncnn: CPU - blazeface ncnn: CPU-v3-v3 - mobilenet-v3 ncnn: CPU-v2-v2 - mobilenet-v2 espeak: Text-To-Speech Synthesis 1 2 3 4 897546.8 57.036877 56.22 1.78 14.12 4.377 9.91 29.08 35.312017 49.640 75.264 16.569297 19.150593 12.499 37.46 6.843 4.571 23.735 70.600 111.92 53.807 30.75 19.33 532.993001 2.947 7.43 28.52 518.236 5.68 11.55 304.720 28.59 13.386 1496.59 1.976 333.936 12.02 24.24 8.12 5886 8.99 558.92 91.620366 9.76 50.54 4443 17.86 18.86 9.456 58.452 66.60 20.77 443.805 2274229 283 963918.4 571253.4 21458 24.09 31.08 2.86 9.34 10.77 41.484 848484.3 56.003730 52.76 1.73 14.12 4.381 9.69 29.58 34.882704 50.313 73.795 16.277631 19.078225 12.276 38.03 6.873 4.557 23.666 69.864 111.22 53.810 30.87 19.18 532.589945 2.969 7.38 28.44 515.265 5.65 11.61 306.242 28.45 13.428 1497.78 1.975 333.412 11.99 24.29 8.13 5896 8.96 559.45 91.819684 9.76 50.46 4438 17.84 18.83 9.447 58.413 66.55 20.76 443.827 283 899150.3 528243.2 20024 23.57 29.05 2.74 9.67 10.77 43.635 764198.1 60.716470 56.21 1.74 13.75 4.490 9.93 29.73 35.650253 50.630 73.968 16.246637 18.783694 12.452 37.54 6.940 4.510 23.440 69.864 110.78 54.359 30.57 19.36 537.422607 2.943 7.37 28.61 517.886 5.67 11.57 306.045 28.46 13.365 1490.85 1.967 332.492 12.04 24.19 8.10 5875 8.96 558.11 91.783682 9.78 50.44 4435 17.87 18.86 9.445 58.385 66.55 20.76 443.843 283 507255.7 21553 24.98 29.02 3.29 9.57 11.09 38.142 OpenBenchmarking.org
InfluxDB Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 OpenBenchmarking.org val/sec, More Is Better InfluxDB 1.8.2 Concurrent Streams: 64 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 4 2 1 200K 400K 600K 800K 1000K SE +/- 13119.06, N = 12 SE +/- 14288.50, N = 12 SE +/- 7142.37, N = 3 764198.1 848484.3 897546.8
OSBench Test: Launch Programs OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Launch Programs 4 2 1 14 28 42 56 70 SE +/- 0.74, N = 3 SE +/- 0.70, N = 3 SE +/- 0.36, N = 3 60.72 56.00 57.04 1. (CC) gcc options: -lm
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: resnet50 4 2 1 13 26 39 52 65 SE +/- 0.13, N = 3 SE +/- 1.78, N = 3 SE +/- 0.17, N = 3 56.21 52.76 56.22 MIN: 47.44 / MAX: 100.48 MIN: 47.28 / MAX: 120.42 MIN: 47.73 / MAX: 101.17 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 4 2 1 0.4005 0.801 1.2015 1.602 2.0025 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 1.74 1.73 1.78 MIN: 1.54 / MAX: 3.29 MIN: 1.51 / MAX: 3.65 MIN: 1.52 / MAX: 4.36 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: efficientnet-b0 4 2 1 4 8 12 16 20 SE +/- 0.14, N = 3 SE +/- 0.45, N = 3 SE +/- 0.38, N = 3 13.75 14.12 14.12 MIN: 12.89 / MAX: 86.55 MIN: 12.97 / MAX: 29.34 MIN: 12.85 / MAX: 66.8 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
LAMMPS Molecular Dynamics Simulator Model: Rhodopsin Protein OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 24Aug2020 Model: Rhodopsin Protein 4 2 1 1.0103 2.0206 3.0309 4.0412 5.0515 SE +/- 0.036, N = 3 SE +/- 0.068, N = 15 SE +/- 0.048, N = 3 4.490 4.381 4.377 1. (CXX) g++ options: -O3 -pthread -lm
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: mnasnet 4 2 1 3 6 9 12 15 SE +/- 0.24, N = 3 SE +/- 0.26, N = 3 SE +/- 0.18, N = 3 9.93 9.69 9.91 MIN: 8.86 / MAX: 45.83 MIN: 8.77 / MAX: 11.64 MIN: 9.06 / MAX: 23.96 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: alexnet 4 2 1 7 14 21 28 35 SE +/- 0.43, N = 3 SE +/- 0.80, N = 3 SE +/- 0.19, N = 3 29.73 29.58 29.08 MIN: 18.19 / MAX: 94.45 MIN: 18.17 / MAX: 59.76 MIN: 18.15 / MAX: 57.79 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
OSBench Test: Create Processes OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Processes 4 2 1 8 16 24 32 40 SE +/- 0.54, N = 15 SE +/- 0.39, N = 15 SE +/- 0.47, N = 15 35.65 34.88 35.31 1. (CC) gcc options: -lm
WebP Image Encode Encode Settings: Quality 100, Lossless, Highest Compression OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100, Lossless, Highest Compression 4 2 1 11 22 33 44 55 SE +/- 0.35, N = 3 SE +/- 0.17, N = 3 SE +/- 0.30, N = 3 50.63 50.31 49.64 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: inception-v3 4 2 1 20 40 60 80 100 SE +/- 0.47, N = 3 SE +/- 0.11, N = 3 SE +/- 1.22, N = 3 73.97 73.80 75.26 MIN: 70.72 / MAX: 107.56 MIN: 70.29 / MAX: 128.12 MIN: 70.86 / MAX: 132.02 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OSBench Test: Create Threads OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Threads 4 2 1 4 8 12 16 20 SE +/- 0.17, N = 3 SE +/- 0.16, N = 3 SE +/- 0.13, N = 3 16.25 16.28 16.57 1. (CC) gcc options: -lm
OSBench Test: Create Files OpenBenchmarking.org us Per Event, Fewer Is Better OSBench Test: Create Files 4 2 1 5 10 15 20 25 SE +/- 0.06, N = 3 SE +/- 0.15, N = 3 SE +/- 0.22, N = 3 18.78 19.08 19.15 1. (CC) gcc options: -lm
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: SqueezeNetV1.0 4 2 1 3 6 9 12 15 SE +/- 0.05, N = 3 SE +/- 0.13, N = 3 SE +/- 0.09, N = 3 12.45 12.28 12.50 MIN: 11.56 / MAX: 29.12 MIN: 11.47 / MAX: 30.07 MIN: 11.62 / MAX: 26.02 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: mobilenet 4 2 1 9 18 27 36 45 SE +/- 0.13, N = 3 SE +/- 0.47, N = 3 SE +/- 0.21, N = 3 37.54 38.03 37.46 MIN: 34.06 / MAX: 82.61 MIN: 34.21 / MAX: 102.74 MIN: 33.76 / MAX: 70.94 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: MobileNetV2_224 4 2 1 2 4 6 8 10 SE +/- 0.030, N = 3 SE +/- 0.064, N = 3 SE +/- 0.017, N = 3 6.940 6.873 6.843 MIN: 6.37 / MAX: 10.3 MIN: 6.37 / MAX: 8.93 MIN: 6.34 / MAX: 22.76 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
LAMMPS Molecular Dynamics Simulator Model: 20k Atoms OpenBenchmarking.org ns/day, More Is Better LAMMPS Molecular Dynamics Simulator 24Aug2020 Model: 20k Atoms 4 2 1 1.0285 2.057 3.0855 4.114 5.1425 SE +/- 0.049, N = 9 SE +/- 0.015, N = 3 SE +/- 0.024, N = 3 4.510 4.557 4.571 1. (CXX) g++ options: -O3 -pthread -lm
WebP Image Encode Encode Settings: Quality 100, Lossless OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100, Lossless 4 2 1 6 12 18 24 30 SE +/- 0.05, N = 3 SE +/- 0.18, N = 3 SE +/- 0.19, N = 3 23.44 23.67 23.74 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: resnet-v2-50 4 2 1 16 32 48 64 80 SE +/- 0.35, N = 3 SE +/- 0.16, N = 3 SE +/- 0.45, N = 3 69.86 69.86 70.60 MIN: 65.78 / MAX: 106.91 MIN: 67.17 / MAX: 89.11 MIN: 66.38 / MAX: 106.89 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: vgg16 4 2 1 30 60 90 120 150 SE +/- 0.98, N = 3 SE +/- 0.30, N = 3 SE +/- 0.91, N = 3 110.78 111.22 111.92 MIN: 84.59 / MAX: 174.23 MIN: 86.34 / MAX: 166.75 MIN: 87.88 / MAX: 165.26 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
dcraw RAW To PPM Image Conversion OpenBenchmarking.org Seconds, Fewer Is Better dcraw RAW To PPM Image Conversion 4 2 1 12 24 36 48 60 SE +/- 0.12, N = 3 SE +/- 0.29, N = 3 SE +/- 0.02, N = 3 54.36 53.81 53.81 1. (CC) gcc options: -lm
NCNN Target: CPU - Model: squeezenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: squeezenet 4 2 1 7 14 21 28 35 SE +/- 0.30, N = 3 SE +/- 0.26, N = 3 SE +/- 0.13, N = 3 30.57 30.87 30.75 MIN: 26.49 / MAX: 75.98 MIN: 27.17 / MAX: 74.24 MIN: 27.03 / MAX: 82.21 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 4 2 1 5 10 15 20 25 SE +/- 0.09, N = 3 SE +/- 0.08, N = 3 SE +/- 0.09, N = 3 19.36 19.18 19.33 MIN: 17.63 / MAX: 26.89 MIN: 17.58 / MAX: 25.38 MIN: 17.83 / MAX: 25.94 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Incompact3D Input: Cylinder OpenBenchmarking.org Seconds, Fewer Is Better Incompact3D 2020-09-17 Input: Cylinder 4 2 1 120 240 360 480 600 SE +/- 4.14, N = 3 SE +/- 3.03, N = 3 SE +/- 2.71, N = 3 537.42 532.59 532.99 1. (F9X) gfortran options: -cpp -funroll-loops -floop-optimize -fcray-pointer -fbacktrace -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
WebP Image Encode Encode Settings: Quality 100 OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100 4 2 1 0.668 1.336 2.004 2.672 3.34 SE +/- 0.012, N = 3 SE +/- 0.004, N = 3 SE +/- 0.016, N = 3 2.943 2.969 2.947 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: shufflenet-v2 4 2 1 2 4 6 8 10 SE +/- 0.07, N = 3 SE +/- 0.06, N = 3 SE +/- 0.05, N = 3 7.37 7.38 7.43 MIN: 6.87 / MAX: 17.87 MIN: 6.85 / MAX: 8.04 MIN: 6.94 / MAX: 8.1 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: Vulkan GPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: yolov4-tiny 4 2 1 7 14 21 28 35 SE +/- 0.05, N = 3 SE +/- 0.09, N = 3 SE +/- 0.05, N = 3 28.61 28.44 28.52 MIN: 24.14 / MAX: 32.68 MIN: 24.22 / MAX: 32.89 MIN: 24.35 / MAX: 33.26 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
GPAW Input: Carbon Nanotube OpenBenchmarking.org Seconds, Fewer Is Better GPAW 20.1 Input: Carbon Nanotube 4 2 1 110 220 330 440 550 SE +/- 0.91, N = 3 SE +/- 1.72, N = 3 SE +/- 1.11, N = 3 517.89 515.27 518.24 1. (CC) gcc options: -pthread -shared -lxc -lblas -lmpi
NCNN Target: Vulkan GPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: shufflenet-v2 4 2 1 1.278 2.556 3.834 5.112 6.39 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.01, N = 3 5.67 5.65 5.68 MIN: 4.91 / MAX: 7.76 MIN: 4.79 / MAX: 7.91 MIN: 4.95 / MAX: 7.6 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 4 2 1 3 6 9 12 15 SE +/- 0.00, N = 3 SE +/- 0.05, N = 3 SE +/- 0.02, N = 3 11.57 11.61 11.55 MIN: 10.49 / MAX: 16.83 MIN: 10.49 / MAX: 17.22 MIN: 10.44 / MAX: 17.06 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
TNN Target: CPU - Model: SqueezeNet v1.1 OpenBenchmarking.org ms, Fewer Is Better TNN 0.2.3 Target: CPU - Model: SqueezeNet v1.1 4 2 1 70 140 210 280 350 SE +/- 0.40, N = 3 SE +/- 1.73, N = 3 SE +/- 0.98, N = 3 306.05 306.24 304.72 MIN: 293.97 / MAX: 314.93 MIN: 294.08 / MAX: 321.12 MIN: 294.26 / MAX: 317.02 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
NCNN Target: Vulkan GPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: resnet50 4 2 1 7 14 21 28 35 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 SE +/- 0.05, N = 3 28.46 28.45 28.59 MIN: 26.08 / MAX: 35.56 MIN: 26.33 / MAX: 35.78 MIN: 26.36 / MAX: 37.83 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2020-09-17 Model: mobilenet-v1-1.0 4 2 1 3 6 9 12 15 SE +/- 0.09, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 13.37 13.43 13.39 MIN: 10.78 / MAX: 28.87 MIN: 13.04 / MAX: 29.42 MIN: 12.62 / MAX: 27.98 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
MPV Video Input: Big Buck Bunny Sunflower 1080p - Decode: Software Only OpenBenchmarking.org FPS, More Is Better MPV Video Input: Big Buck Bunny Sunflower 1080p - Decode: Software Only 4 2 1 300 600 900 1200 1500 SE +/- 0.82, N = 3 SE +/- 3.04, N = 3 SE +/- 4.23, N = 3 1490.85 1497.78 1496.59 MIN: 901.12 / MAX: 2234.81 MIN: 916.25 / MAX: 2144.91 MIN: 890.33 / MAX: 2242.83 1. mpv 0.29.1
WebP Image Encode Encode Settings: Default OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Default 4 2 1 0.4446 0.8892 1.3338 1.7784 2.223 SE +/- 0.010, N = 3 SE +/- 0.014, N = 3 SE +/- 0.006, N = 3 1.967 1.975 1.976 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
TNN Target: CPU - Model: MobileNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.2.3 Target: CPU - Model: MobileNet v2 4 2 1 70 140 210 280 350 SE +/- 0.92, N = 3 SE +/- 1.19, N = 3 SE +/- 0.97, N = 3 332.49 333.41 333.94 MIN: 320.63 / MAX: 353.14 MIN: 320.39 / MAX: 360.51 MIN: 322.28 / MAX: 361.07 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
NCNN Target: Vulkan GPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: alexnet 4 2 1 3 6 9 12 15 SE +/- 0.05, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 12.04 11.99 12.02 MIN: 11.3 / MAX: 16.33 MIN: 11.31 / MAX: 15.43 MIN: 11.21 / MAX: 15.88 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
LibRaw Post-Processing Benchmark OpenBenchmarking.org Mpix/sec, More Is Better LibRaw 0.20 Post-Processing Benchmark 4 2 1 6 12 18 24 30 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 SE +/- 0.06, N = 3 24.19 24.29 24.24 1. (CXX) g++ options: -O2 -fopenmp -ljpeg -lz -lm
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 4 2 1 2 4 6 8 10 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 8.10 8.13 8.12 MIN: 7.51 / MAX: 10.82 MIN: 7.57 / MAX: 11.54 MIN: 7.45 / MAX: 11.88 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
GLmark2 Resolution: 1280 x 1024 OpenBenchmarking.org Score, More Is Better GLmark2 2020.04 Resolution: 1280 x 1024 4 2 1 1300 2600 3900 5200 6500 5875 5896 5886
NCNN Target: Vulkan GPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: mnasnet 4 2 1 3 6 9 12 15 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 SE +/- 0.03, N = 3 8.96 8.96 8.99 MIN: 8.26 / MAX: 11.88 MIN: 8.14 / MAX: 12.22 MIN: 8.26 / MAX: 12.37 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
MPV Video Input: Big Buck Bunny Sunflower 4K - Decode: Software Only OpenBenchmarking.org FPS, More Is Better MPV Video Input: Big Buck Bunny Sunflower 4K - Decode: Software Only 4 2 1 120 240 360 480 600 SE +/- 0.60, N = 3 SE +/- 0.83, N = 3 SE +/- 0.53, N = 3 558.11 559.45 558.92 MIN: 354.93 / MAX: 741.6 MIN: 355.56 / MAX: 751.21 MIN: 353.51 / MAX: 741.98 1. mpv 0.29.1
OSBench Test: Memory Allocations OpenBenchmarking.org Ns Per Event, Fewer Is Better OSBench Test: Memory Allocations 4 2 1 20 40 60 80 100 SE +/- 0.38, N = 3 SE +/- 0.21, N = 3 SE +/- 0.03, N = 3 91.78 91.82 91.62 1. (CC) gcc options: -lm
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 4 2 1 3 6 9 12 15 SE +/- 0.04, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 9.78 9.76 9.76 MIN: 8.84 / MAX: 14.34 MIN: 8.8 / MAX: 13.68 MIN: 8.77 / MAX: 14 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: yolov4-tiny 4 2 1 11 22 33 44 55 SE +/- 0.16, N = 3 SE +/- 0.13, N = 3 SE +/- 0.15, N = 3 50.44 50.46 50.54 MIN: 43.22 / MAX: 70.77 MIN: 42.79 / MAX: 79.82 MIN: 42.79 / MAX: 71.94 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
GLmark2 Resolution: 1920 x 1080 OpenBenchmarking.org Score, More Is Better GLmark2 2020.04 Resolution: 1920 x 1080 4 2 1 1000 2000 3000 4000 5000 4435 4438 4443
NCNN Target: Vulkan GPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: mobilenet 4 2 1 4 8 12 16 20 SE +/- 0.17, N = 3 SE +/- 0.10, N = 3 SE +/- 0.03, N = 3 17.87 17.84 17.86 MIN: 14.98 / MAX: 22.57 MIN: 14.88 / MAX: 23.2 MIN: 14.9 / MAX: 24.7 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 4 2 1 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 SE +/- 0.03, N = 3 18.86 18.83 18.86 MIN: 17.79 / MAX: 22.35 MIN: 17.59 / MAX: 21.01 MIN: 17.74 / MAX: 23.12 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
WebP Image Encode Encode Settings: Quality 100, Highest Compression OpenBenchmarking.org Encode Time - Seconds, Fewer Is Better WebP Image Encode 1.1 Encode Settings: Quality 100, Highest Compression 4 2 1 3 6 9 12 15 SE +/- 0.016, N = 3 SE +/- 0.026, N = 3 SE +/- 0.030, N = 3 9.445 9.447 9.456 1. (CC) gcc options: -fvisibility=hidden -O2 -pthread -lm -ljpeg -lpng16 -ltiff
RealSR-NCNN Scale: 4x - TAA: No OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: No 4 2 1 13 26 39 52 65 SE +/- 0.02, N = 3 SE +/- 0.03, N = 3 SE +/- 0.07, N = 3 58.39 58.41 58.45
NCNN Target: Vulkan GPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: Vulkan GPU - Model: vgg16 4 2 1 15 30 45 60 75 SE +/- 0.03, N = 3 SE +/- 0.02, N = 3 SE +/- 0.05, N = 3 66.55 66.55 66.60 MIN: 65.79 / MAX: 69.29 MIN: 65.83 / MAX: 69.88 MIN: 65.77 / MAX: 69.74 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 4 2 1 5 10 15 20 25 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 SE +/- 0.03, N = 3 20.76 20.76 20.77 MIN: 19.47 / MAX: 25.41 MIN: 19.53 / MAX: 25.18 MIN: 19.45 / MAX: 25.92 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
RealSR-NCNN Scale: 4x - TAA: Yes OpenBenchmarking.org Seconds, Fewer Is Better RealSR-NCNN 20200818 Scale: 4x - TAA: Yes 4 2 1 100 200 300 400 500 SE +/- 0.03, N = 3 SE +/- 0.01, N = 3 SE +/- 0.01, N = 3 443.84 443.83 443.81
Kripke OpenBenchmarking.org Throughput FoM, More Is Better Kripke 1.2.4 1 500K 1000K 1500K 2000K 2500K SE +/- 40613.50, N = 2 2274229 1. (CXX) g++ options: -O3 -fopenmp
Monte Carlo Simulations of Ionised Nebulae Input: Dust 2D tau100.0 OpenBenchmarking.org Seconds, Fewer Is Better Monte Carlo Simulations of Ionised Nebulae 2019-03-24 Input: Dust 2D tau100.0 4 2 1 60 120 180 240 300 SE +/- 0.88, N = 3 283 283 283 1. (F9X) gfortran options: -cpp -Jsource/ -ffree-line-length-0 -lm -std=legacy -O3 -O2 -pthread -lmpi_usempif08 -lmpi_mpifh -lmpi
InfluxDB Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 OpenBenchmarking.org val/sec, More Is Better InfluxDB 1.8.2 Concurrent Streams: 1024 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 2 1 200K 400K 600K 800K 1000K SE +/- 39090.53, N = 13 SE +/- 4179.09, N = 3 899150.3 963918.4
InfluxDB Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 OpenBenchmarking.org val/sec, More Is Better InfluxDB 1.8.2 Concurrent Streams: 4 - Batch Size: 10000 - Tags: 2,5000,1 - Points Per Series: 10000 4 2 1 120K 240K 360K 480K 600K SE +/- 18076.30, N = 12 SE +/- 21790.68, N = 12 SE +/- 18598.16, N = 12 507255.7 528243.2 571253.4
OpenCV Test: DNN - Deep Neural Network OpenBenchmarking.org ms, Fewer Is Better OpenCV 4.4 Test: DNN - Deep Neural Network 4 2 1 5K 10K 15K 20K 25K SE +/- 324.81, N = 3 SE +/- 400.07, N = 15 SE +/- 431.59, N = 15 21553 20024 21458 1. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: resnet18 4 2 1 6 12 18 24 30 SE +/- 0.66, N = 3 SE +/- 0.91, N = 3 SE +/- 0.60, N = 3 24.98 23.57 24.09 MIN: 21.61 / MAX: 75.77 MIN: 19.44 / MAX: 72.07 MIN: 19.49 / MAX: 77.09 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: googlenet 4 2 1 7 14 21 28 35 SE +/- 1.45, N = 3 SE +/- 1.68, N = 3 SE +/- 0.32, N = 3 29.02 29.05 31.08 MIN: 23.86 / MAX: 69.21 MIN: 23.64 / MAX: 72.29 MIN: 27.19 / MAX: 97.75 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: blazeface 4 2 1 0.7403 1.4806 2.2209 2.9612 3.7015 SE +/- 0.10, N = 3 SE +/- 0.05, N = 3 SE +/- 0.14, N = 3 3.29 2.74 2.86 MIN: 2.55 / MAX: 92 MIN: 2.51 / MAX: 9.36 MIN: 2.54 / MAX: 18.63 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU-v3-v3 - Model: mobilenet-v3 4 2 1 3 6 9 12 15 SE +/- 0.37, N = 3 SE +/- 0.12, N = 3 SE +/- 0.05, N = 3 9.57 9.67 9.34 MIN: 8.51 / MAX: 64.81 MIN: 8.5 / MAX: 32.82 MIN: 8.58 / MAX: 23.21 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU-v2-v2 - Model: mobilenet-v2 4 2 1 3 6 9 12 15 SE +/- 0.34, N = 3 SE +/- 0.54, N = 3 SE +/- 0.10, N = 3 11.09 10.77 10.77 MIN: 9.74 / MAX: 30.81 MIN: 9.36 / MAX: 64.52 MIN: 9.68 / MAX: 26.18 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
eSpeak-NG Speech Engine Text-To-Speech Synthesis OpenBenchmarking.org Seconds, Fewer Is Better eSpeak-NG Speech Engine 20200907 Text-To-Speech Synthesis 4 2 1 10 20 30 40 50 SE +/- 0.51, N = 5 SE +/- 1.05, N = 20 SE +/- 0.90, N = 16 38.14 43.64 41.48 1. (CC) gcc options: -O2 -std=c99
Phoronix Test Suite v10.8.5