vino AMD Ryzen Threadripper PRO 5965WX 24-Cores testing with a ASUS Pro WS WRX80E-SAGE SE WIFI (1003 BIOS) and ASUS NVIDIA NV106 2GB on Ubuntu 22.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2209013-NE-VINO6110802&sor .
vino Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Vulkan Compiler File-System Screen Resolution A B C D AMD Ryzen Threadripper PRO 5965WX 24-Cores @ 3.80GHz (24 Cores / 48 Threads) ASUS Pro WS WRX80E-SAGE SE WIFI (1003 BIOS) AMD Starship/Matisse 128GB 1000GB Western Digital WDS100T1X0E-00AFY0 ASUS NVIDIA NV106 2GB AMD Starship/Matisse VA2431 2 x Intel 10G X550T + Intel Wi-Fi 6 AX200 Ubuntu 22.04 5.19.0-051900daily20220809-generic (x86_64) GNOME Shell 42.2 X Server 1.21.1.3 + Wayland nouveau 4.3 Mesa 22.0.1 1.2.204 GCC 11.2.0 ext4 1920x1080 OpenBenchmarking.org Kernel Details - Transparent Huge Pages: madvise Compiler Details - --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-gBFGDP/gcc-11-11.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-11-gBFGDP/gcc-11-11.2.0/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 Disk Details - NONE / errors=remount-ro,relatime,rw / Block Size: 4096 Processor Details - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0xa008203 Python Details - Python 3.10.4 Security Details - 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 Retpolines IBPB: conditional IBRS_FW STIBP: always-on RSB filling + srbds: Not affected + tsx_async_abort: Not affected
vino unpack-linux: linux-5.19.tar.xz graphics-magick: Swirl graphics-magick: Rotate graphics-magick: Sharpen graphics-magick: Enhanced graphics-magick: Resizing graphics-magick: Noise-Gaussian graphics-magick: HWB Color Space compress-7zip: Compression Rating compress-7zip: Decompression Rating mnn: nasnet mnn: mobilenetV3 mnn: squeezenetv1.1 mnn: resnet-v2-50 mnn: SqueezeNetV1.0 mnn: MobileNetV2_224 mnn: mobilenet-v1-1.0 mnn: inception-v3 openvino: Face Detection FP16 - CPU openvino: Face Detection FP16 - CPU openvino: Person Detection FP16 - CPU openvino: Person Detection FP16 - CPU openvino: Person Detection FP32 - CPU openvino: Person Detection FP32 - CPU openvino: Vehicle Detection FP16 - CPU openvino: Vehicle Detection FP16 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Vehicle Detection FP16-INT8 - CPU openvino: Vehicle Detection FP16-INT8 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU natron: Spaceship build-nodejs: Time To Compile build-php: Time To Compile build-python: Default build-python: Released Build, PGO + LTO Optimized build-erlang: Time To Compile build-wasmer: Time To Compile A B C D 5.574 1320 840 340 624 2284 629 1259 198562 222201 13.916 2.268 3.843 18.927 6.068 3.985 2.795 22.430 6.52 1818.29 4.78 2472.49 4.77 2483.86 577.26 20.76 16.40 728.85 1103.94 10.86 694.19 17.27 78.33 153.09 1619.19 14.81 968.55 12.37 23485.17 1.01 41071.45 0.58 6.5 224.681 37.039 13.033 220.827 73.684 43.219 5.564 1314 820 341 625 2298 623 1207 200497 223222 13.721 2.3 3.967 19.113 5.759 3.809 2.674 22.416 6.65 1785.85 4.8 2456.03 4.78 2467.59 577.32 20.76 16.52 723.86 1108.33 10.82 698.64 17.16 77.87 153.96 1624.55 14.76 969.27 12.36 23527.09 1.01 41249.46 0.57 6.4 225.267 37.534 13.01 220.259 74.542 43.071 5.614 1316 826 341 623 2302 624 1207 199043 223558 13.678 2.267 3.615 17.671 6.348 3.974 2.839 22.82 6.59 1797.72 4.79 2463.06 4.76 2481.27 578.69 20.71 16.49 726.07 1111.51 10.79 696.19 17.22 79.15 151.4 1622.61 14.78 966.24 12.4 23480.68 1.01 41139.65 0.57 6.6 226.301 37.771 13.133 220.575 75.003 43.326 5.591 1307 821 341 622 2308 619 1165 200015 223348 13.977 2.304 3.668 18.61 6.029 4.15 2.759 23.404 6.5 1820.76 4.81 2465.84 4.77 2483.39 581.12 20.63 16.4 727.94 1101.88 10.88 695.86 17.23 76.98 155.68 1622.61 14.78 968.1 12.38 23466.66 1.01 41101.48 0.57 6.6 225.674 37.736 13.029 221.05 73.979 43.072 OpenBenchmarking.org
Unpacking The Linux Kernel linux-5.19.tar.xz OpenBenchmarking.org Seconds, Fewer Is Better Unpacking The Linux Kernel 5.19 linux-5.19.tar.xz B A D C 1.2632 2.5264 3.7896 5.0528 6.316 SE +/- 0.013, N = 4 5.564 5.574 5.591 5.614
GraphicsMagick Operation: Swirl OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Swirl A C B D 300 600 900 1200 1500 SE +/- 4.00, N = 3 1320 1316 1314 1307 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lz -lm -lpthread
GraphicsMagick Operation: Rotate OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Rotate A C D B 200 400 600 800 1000 SE +/- 3.93, N = 3 840 826 821 820 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lz -lm -lpthread
GraphicsMagick Operation: Sharpen OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Sharpen D C B A 70 140 210 280 350 SE +/- 0.88, N = 3 341 341 341 340 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lz -lm -lpthread
GraphicsMagick Operation: Enhanced OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Enhanced B A C D 130 260 390 520 650 SE +/- 0.58, N = 3 625 624 623 622 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lz -lm -lpthread
GraphicsMagick Operation: Resizing OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Resizing D C B A 500 1000 1500 2000 2500 SE +/- 4.70, N = 3 2308 2302 2298 2284 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lz -lm -lpthread
GraphicsMagick Operation: Noise-Gaussian OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: Noise-Gaussian A C B D 140 280 420 560 700 SE +/- 0.88, N = 3 629 624 623 619 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lz -lm -lpthread
GraphicsMagick Operation: HWB Color Space OpenBenchmarking.org Iterations Per Minute, More Is Better GraphicsMagick 1.3.38 Operation: HWB Color Space A C B D 300 600 900 1200 1500 SE +/- 13.12, N = 3 1259 1207 1207 1165 1. (CC) gcc options: -fopenmp -O2 -ljbig -ltiff -lfreetype -ljpeg -lXext -lSM -lICE -lX11 -llzma -lz -lm -lpthread
7-Zip Compression Test: Compression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Compression Rating B D C A 40K 80K 120K 160K 200K SE +/- 573.75, N = 3 200497 200015 199043 198562 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
7-Zip Compression Test: Decompression Rating OpenBenchmarking.org MIPS, More Is Better 7-Zip Compression 22.01 Test: Decompression Rating C D B A 50K 100K 150K 200K 250K SE +/- 484.04, N = 3 223558 223348 223222 222201 1. (CXX) g++ options: -lpthread -ldl -O2 -fPIC
Mobile Neural Network Model: nasnet OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: nasnet C B A D 4 8 12 16 20 SE +/- 0.22, N = 12 13.68 13.72 13.92 13.98 MIN: 13.58 / MAX: 14.27 MIN: 13.62 / MAX: 15.13 MIN: 12.59 / MAX: 16.3 MIN: 13.89 / MAX: 14.68 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
Mobile Neural Network Model: mobilenetV3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: mobilenetV3 C A B D 0.5184 1.0368 1.5552 2.0736 2.592 SE +/- 0.023, N = 12 2.267 2.268 2.300 2.304 MIN: 2.23 / MAX: 3.46 MIN: 2.06 / MAX: 3.69 MIN: 2.26 / MAX: 3.88 MIN: 2.26 / MAX: 2.41 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
Mobile Neural Network Model: squeezenetv1.1 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: squeezenetv1.1 C D A B 0.8926 1.7852 2.6778 3.5704 4.463 SE +/- 0.092, N = 12 3.615 3.668 3.843 3.967 MIN: 3.57 / MAX: 4.46 MIN: 3.64 / MAX: 3.71 MIN: 3.12 / MAX: 5.36 MIN: 3.86 / MAX: 5.15 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
Mobile Neural Network Model: resnet-v2-50 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: resnet-v2-50 C D A B 5 10 15 20 25 SE +/- 0.29, N = 12 17.67 18.61 18.93 19.11 MIN: 17.51 / MAX: 18.9 MIN: 18.44 / MAX: 20.02 MIN: 17.19 / MAX: 21.89 MIN: 18.86 / MAX: 20.42 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
Mobile Neural Network Model: SqueezeNetV1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: SqueezeNetV1.0 B D A C 2 4 6 8 10 SE +/- 0.061, N = 12 5.759 6.029 6.068 6.348 MIN: 5.55 / MAX: 6.77 MIN: 5.83 / MAX: 7.01 MIN: 5.61 / MAX: 7.69 MIN: 6.24 / MAX: 7.2 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
Mobile Neural Network Model: MobileNetV2_224 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: MobileNetV2_224 B C A D 0.9338 1.8676 2.8014 3.7352 4.669 SE +/- 0.048, N = 12 3.809 3.974 3.985 4.150 MIN: 3.75 / MAX: 4.98 MIN: 3.94 / MAX: 4.9 MIN: 3.72 / MAX: 5.31 MIN: 4.11 / MAX: 4.19 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
Mobile Neural Network Model: mobilenet-v1-1.0 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: mobilenet-v1-1.0 B D A C 0.6388 1.2776 1.9164 2.5552 3.194 SE +/- 0.020, N = 12 2.674 2.759 2.795 2.839 MIN: 2.64 / MAX: 3.43 MIN: 2.72 / MAX: 2.86 MIN: 2.67 / MAX: 4.07 MIN: 2.81 / MAX: 3.36 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
Mobile Neural Network Model: inception-v3 OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: inception-v3 B A C D 6 12 18 24 30 SE +/- 0.33, N = 12 22.42 22.43 22.82 23.40 MIN: 22.19 / MAX: 24.09 MIN: 20.51 / MAX: 25.15 MIN: 22.62 / MAX: 24.1 MIN: 23.22 / MAX: 24.71 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
OpenVINO Model: Face Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Face Detection FP16 - Device: CPU B C A D 2 4 6 8 10 SE +/- 0.01, N = 3 6.65 6.59 6.52 6.50 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Face Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Face Detection FP16 - Device: CPU B C A D 400 800 1200 1600 2000 SE +/- 2.86, N = 3 1785.85 1797.72 1818.29 1820.76 MIN: 1658.96 / MAX: 1926.78 MIN: 1663.31 / MAX: 1898.24 MIN: 1619.35 / MAX: 1931.27 MIN: 1605.92 / MAX: 1925.98 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Detection FP16 - Device: CPU D B C A 1.0823 2.1646 3.2469 4.3292 5.4115 SE +/- 0.01, N = 3 4.81 4.80 4.79 4.78 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Detection FP16 - Device: CPU B C D A 500 1000 1500 2000 2500 SE +/- 4.42, N = 3 2456.03 2463.06 2465.84 2472.49 MIN: 1526.34 / MAX: 2830.32 MIN: 1624.72 / MAX: 2817.75 MIN: 1580.85 / MAX: 2798.03 MIN: 1321.38 / MAX: 2817.23 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Person Detection FP32 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Detection FP32 - Device: CPU B D A C 1.0755 2.151 3.2265 4.302 5.3775 SE +/- 0.01, N = 3 4.78 4.77 4.77 4.76 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Person Detection FP32 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Detection FP32 - Device: CPU B C D A 500 1000 1500 2000 2500 SE +/- 2.20, N = 3 2467.59 2481.27 2483.39 2483.86 MIN: 1641 / MAX: 2783.09 MIN: 1462.37 / MAX: 2797.71 MIN: 1434.63 / MAX: 2828.42 MIN: 1481.45 / MAX: 2861.26 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Vehicle Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16 - Device: CPU D C B A 130 260 390 520 650 SE +/- 0.67, N = 3 581.12 578.69 577.32 577.26 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Vehicle Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16 - Device: CPU D C A B 5 10 15 20 25 SE +/- 0.02, N = 3 20.63 20.71 20.76 20.76 MIN: 8.75 / MAX: 40.7 MIN: 15.1 / MAX: 39.13 MIN: 8.88 / MAX: 37.47 MIN: 9.86 / MAX: 34.37 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Face Detection FP16-INT8 - Device: CPU B C D A 4 8 12 16 20 SE +/- 0.02, N = 3 16.52 16.49 16.40 16.40 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Face Detection FP16-INT8 - Device: CPU B C D A 160 320 480 640 800 SE +/- 0.26, N = 3 723.86 726.07 727.94 728.85 MIN: 675.27 / MAX: 752.29 MIN: 587.6 / MAX: 754.27 MIN: 683.94 / MAX: 750.57 MIN: 596.87 / MAX: 764.66 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU C B A D 200 400 600 800 1000 SE +/- 1.84, N = 3 1111.51 1108.33 1103.94 1101.88 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU C B A D 3 6 9 12 15 SE +/- 0.02, N = 3 10.79 10.82 10.86 10.88 MIN: 8.13 / MAX: 23.55 MIN: 5.77 / MAX: 24.75 MIN: 5.79 / MAX: 25.51 MIN: 5.73 / MAX: 24.3 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Weld Porosity Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16 - Device: CPU B C D A 150 300 450 600 750 SE +/- 1.13, N = 3 698.64 696.19 695.86 694.19 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Weld Porosity Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16 - Device: CPU B C D A 4 8 12 16 20 SE +/- 0.03, N = 3 17.16 17.22 17.23 17.27 MIN: 8.08 / MAX: 34.85 MIN: 8.13 / MAX: 34.37 MIN: 15.16 / MAX: 25.56 MIN: 9.49 / MAX: 34.94 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU C A B D 20 40 60 80 100 SE +/- 0.49, N = 3 79.15 78.33 77.87 76.98 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU C A B D 30 60 90 120 150 SE +/- 0.95, N = 3 151.40 153.09 153.96 155.68 MIN: 100 / MAX: 187.06 MIN: 77.55 / MAX: 191.7 MIN: 101.95 / MAX: 203.7 MIN: 89.79 / MAX: 236.37 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU B D C A 300 600 900 1200 1500 SE +/- 1.32, N = 3 1624.55 1622.61 1622.61 1619.19 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU B C D A 4 8 12 16 20 SE +/- 0.01, N = 3 14.76 14.78 14.78 14.81 MIN: 8.08 / MAX: 26.85 MIN: 11.62 / MAX: 20.7 MIN: 9.14 / MAX: 25.19 MIN: 7.83 / MAX: 27.1 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU B A D C 200 400 600 800 1000 SE +/- 0.93, N = 3 969.27 968.55 968.10 966.24 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU B A D C 3 6 9 12 15 SE +/- 0.01, N = 3 12.36 12.37 12.38 12.40 MIN: 7.9 / MAX: 28.32 MIN: 6.55 / MAX: 27.42 MIN: 6.91 / MAX: 31.3 MIN: 8.25 / MAX: 28.43 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU B A C D 5K 10K 15K 20K 25K SE +/- 23.02, N = 3 23527.09 23485.17 23480.68 23466.66 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU A B C D 0.2273 0.4546 0.6819 0.9092 1.1365 SE +/- 0.00, N = 3 1.01 1.01 1.01 1.01 MIN: 0.62 / MAX: 13.38 MIN: 0.63 / MAX: 5.37 MIN: 0.63 / MAX: 13.21 MIN: 0.63 / MAX: 4.62 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU B C D A 9K 18K 27K 36K 45K SE +/- 37.38, N = 3 41249.46 41139.65 41101.48 41071.45 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2022.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU B C D A 0.1305 0.261 0.3915 0.522 0.6525 SE +/- 0.00, N = 3 0.57 0.57 0.57 0.58 MIN: 0.36 / MAX: 13.13 MIN: 0.37 / MAX: 7.33 MIN: 0.36 / MAX: 11.46 MIN: 0.36 / MAX: 12.42 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie -ldl
Natron Input: Spaceship OpenBenchmarking.org FPS, More Is Better Natron 2.4.3 Input: Spaceship D C A B 2 4 6 8 10 SE +/- 0.03, N = 3 6.6 6.6 6.5 6.4
Timed Node.js Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Node.js Compilation 18.8 Time To Compile A B D C 50 100 150 200 250 SE +/- 0.38, N = 3 224.68 225.27 225.67 226.30
Timed PHP Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed PHP Compilation 8.1.9 Time To Compile A B D C 9 18 27 36 45 SE +/- 0.31, N = 3 37.04 37.53 37.74 37.77
Timed CPython Compilation Build Configuration: Default OpenBenchmarking.org Seconds, Fewer Is Better Timed CPython Compilation 3.10.6 Build Configuration: Default B D A C 3 6 9 12 15 13.01 13.03 13.03 13.13
Timed CPython Compilation Build Configuration: Released Build, PGO + LTO Optimized OpenBenchmarking.org Seconds, Fewer Is Better Timed CPython Compilation 3.10.6 Build Configuration: Released Build, PGO + LTO Optimized B C A D 50 100 150 200 250 220.26 220.58 220.83 221.05
Timed Erlang/OTP Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Erlang/OTP Compilation 25.0 Time To Compile A D B C 20 40 60 80 100 SE +/- 0.86, N = 3 73.68 73.98 74.54 75.00
Timed Wasmer Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Wasmer Compilation 2.3 Time To Compile B D A C 10 20 30 40 50 SE +/- 0.03, N = 3 43.07 43.07 43.22 43.33 1. (CC) gcc options: -m64 -ldl -lgcc_s -lutil -lrt -lpthread -lm -lc -pie -nodefaultlibs
Phoronix Test Suite v10.8.4