new stuff AMD Ryzen Threadripper 3970X 32-Core testing with a ASUS ROG ZENITH II EXTREME (1802 BIOS) and AMD Radeon RX 5700 8GB on Ubuntu 22.04 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2403075-NE-NEWSTUFF184&sor&grw .
new stuff Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Vulkan Compiler File-System Screen Resolution a b c d AMD Ryzen Threadripper 3970X 32-Core @ 3.70GHz (32 Cores / 64 Threads) ASUS ROG ZENITH II EXTREME (1802 BIOS) AMD Starship/Matisse 4 x 16GB DDR4-3600MT/s Corsair CMT64GX4M4Z3600C16 Samsung SSD 980 PRO 500GB AMD Radeon RX 5700 8GB (1750/875MHz) AMD Navi 10 HDMI Audio ASUS VP28U Aquantia AQC107 NBase-T/IEEE + Intel I211 + Intel Wi-Fi 6 AX200 Ubuntu 22.04 6.5.0-14-generic (x86_64) GNOME Shell 42.2 X Server + Wayland 4.6 Mesa 22.0.1 (LLVM 13.0.1 DRM 3.54) 1.2.204 GCC 11.4.0 ext4 3840x2160 6.5.0-21-generic (x86_64) 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-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 Processor Details - Scaling Governor: acpi-cpufreq schedutil (Boost: Enabled) - CPU Microcode: 0x830107a Python Details - Python 3.10.12 Security Details - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + retbleed: Mitigation of untrained return thunk; SMT enabled with STIBP protection + 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 Retpolines IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
new stuff 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: Face Detection Retail FP16 - CPU openvino: Face Detection Retail FP16 - CPU openvino: Road Segmentation ADAS FP16 - CPU openvino: Road Segmentation ADAS FP16 - 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: Face Detection Retail FP16-INT8 - CPU openvino: Face Detection Retail FP16-INT8 - CPU openvino: Road Segmentation ADAS FP16-INT8 - CPU openvino: Road Segmentation ADAS FP16-INT8 - 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: Noise Suppression Poconet-Like FP16 - CPU openvino: Noise Suppression Poconet-Like FP16 - CPU openvino: Handwritten English Recognition FP16 - CPU openvino: Handwritten English Recognition FP16 - CPU openvino: Person Re-Identification Retail FP16 - CPU openvino: Person Re-Identification Retail FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Handwritten English Recognition FP16-INT8 - CPU openvino: Handwritten English Recognition FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU v-ray: CPU a b c d 9.23 1719.51 89.15 179.17 86.96 183.8 614.84 25.97 11.34 1402.99 2717.99 5.87 106.98 149.41 910.77 17.56 883.82 18.09 2876.18 5.55 425.93 37.54 106.34 150.36 1126.24 28.4 1251.92 12.76 1238.99 12.86 424.99 75.24 1417.27 11.28 27516.98 1.15 440.43 72.6 38636.14 0.82 44616 9.26 1715.49 84.14 190 85.79 186.33 600.53 26.6 11.11 1430.4 2665.33 5.99 106.99 149.35 909.25 17.58 832.54 19.2 2872.53 5.56 422.8 37.81 105.92 150.91 1125.15 28.43 1234.39 12.94 1229.46 12.96 425.17 75.21 1408.89 11.34 27548.26 1.15 439.12 72.81 38674.2 0.82 45014 9.26 1713.28 86.46 184.78 85.64 186.69 613.30 26.04 11.3 1407.62 2706.29 5.9 106.65 149.85 905.63 17.65 880.22 18.16 2865.70 5.58 422.55 37.84 105.86 150.94 1125.49 28.42 1235.87 12.93 1224.10 13.02 424.36 75.35 1410.15 11.33 27449.65 1.15 439.92 72.69 38594.89 0.82 44507 9.22 1722.44 87.27 183.14 89.6 178.38 621.84 25.68 11.34 1404.93 2724.82 5.86 108.04 147.95 901.27 17.74 882.55 18.11 2877.44 5.55 426.49 37.48 106.37 150.23 1127.94 28.35 1253.78 12.74 1243.84 12.81 426.18 75.03 1417.73 11.27 26939.1 1.18 441.81 72.36 38686.33 0.82 44319 OpenBenchmarking.org
OpenVINO Model: Face Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Face Detection FP16 - Device: CPU c b a d 3 6 9 12 15 SE +/- 0.10, N = 3 9.26 9.26 9.23 9.22 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Face Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Face Detection FP16 - Device: CPU c b a d 400 800 1200 1600 2000 SE +/- 18.89, N = 3 1713.28 1715.49 1719.51 1722.44 MIN: 1446.63 / MAX: 1903.81 MIN: 1287.44 / MAX: 2021.14 MIN: 1582.15 / MAX: 1853.15 MIN: 1596.55 / MAX: 1846.55 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Person Detection FP16 - Device: CPU a d c b 20 40 60 80 100 SE +/- 0.66, N = 3 89.15 87.27 86.46 84.14 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Person Detection FP16 - Device: CPU a d c b 40 80 120 160 200 SE +/- 1.37, N = 3 179.17 183.14 184.78 190.00 MIN: 95.25 / MAX: 247.22 MIN: 83.31 / MAX: 246.65 MIN: 119.45 / MAX: 251.72 MIN: 111.52 / MAX: 326.32 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Person Detection FP32 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Person Detection FP32 - Device: CPU d a b c 20 40 60 80 100 SE +/- 0.87, N = 3 89.60 86.96 85.79 85.64 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Person Detection FP32 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Person Detection FP32 - Device: CPU d a b c 40 80 120 160 200 SE +/- 1.90, N = 3 178.38 183.80 186.33 186.69 MIN: 146.94 / MAX: 250.11 MIN: 147.02 / MAX: 250.69 MIN: 96.63 / MAX: 310.79 MIN: 94.93 / MAX: 249.57 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Vehicle Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Vehicle Detection FP16 - Device: CPU d a c b 130 260 390 520 650 SE +/- 0.78, N = 3 621.84 614.84 613.30 600.53 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Vehicle Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Vehicle Detection FP16 - Device: CPU d a c b 6 12 18 24 30 SE +/- 0.03, N = 3 25.68 25.97 26.04 26.60 MIN: 10.88 / MAX: 49.15 MIN: 11.33 / MAX: 47.95 MIN: 9.97 / MAX: 50.46 MIN: 10.56 / MAX: 94.11 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Face Detection FP16-INT8 - Device: CPU d a c b 3 6 9 12 15 SE +/- 0.00, N = 3 11.34 11.34 11.30 11.11 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Face Detection FP16-INT8 - Device: CPU a d c b 300 600 900 1200 1500 SE +/- 2.04, N = 3 1402.99 1404.93 1407.62 1430.40 MIN: 1370.56 / MAX: 1478.99 MIN: 1350.43 / MAX: 1472.85 MIN: 1357.63 / MAX: 1484.55 MIN: 785.99 / MAX: 1744.85 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Face Detection Retail FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Face Detection Retail FP16 - Device: CPU d a c b 600 1200 1800 2400 3000 SE +/- 0.21, N = 3 2724.82 2717.99 2706.29 2665.33 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Face Detection Retail FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Face Detection Retail FP16 - Device: CPU d a c b 1.3478 2.6956 4.0434 5.3912 6.739 SE +/- 0.00, N = 3 5.86 5.87 5.90 5.99 MIN: 3.63 / MAX: 17.81 MIN: 3.46 / MAX: 17.32 MIN: 3.17 / MAX: 17.28 MIN: 3.4 / MAX: 46.26 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Road Segmentation ADAS FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Road Segmentation ADAS FP16 - Device: CPU d b a c 20 40 60 80 100 SE +/- 0.16, N = 3 108.04 106.99 106.98 106.65 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Road Segmentation ADAS FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Road Segmentation ADAS FP16 - Device: CPU d b a c 30 60 90 120 150 SE +/- 0.23, N = 3 147.95 149.35 149.41 149.85 MIN: 94.93 / MAX: 168.94 MIN: 52.83 / MAX: 245.78 MIN: 101.1 / MAX: 173.59 MIN: 35.69 / MAX: 186.48 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Vehicle Detection FP16-INT8 - Device: CPU a b c d 200 400 600 800 1000 SE +/- 4.34, N = 3 910.77 909.25 905.63 901.27 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Vehicle Detection FP16-INT8 - Device: CPU a b c d 4 8 12 16 20 SE +/- 0.08, N = 3 17.56 17.58 17.65 17.74 MIN: 11.85 / MAX: 39.53 MIN: 10.29 / MAX: 96.98 MIN: 11.31 / MAX: 40.23 MIN: 9.37 / MAX: 38.68 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Weld Porosity Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Weld Porosity Detection FP16 - Device: CPU a d c b 200 400 600 800 1000 SE +/- 1.03, N = 3 883.82 882.55 880.22 832.54 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Weld Porosity Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Weld Porosity Detection FP16 - Device: CPU a d c b 5 10 15 20 25 SE +/- 0.02, N = 3 18.09 18.11 18.16 19.20 MIN: 17.28 / MAX: 37.48 MIN: 10.07 / MAX: 37.42 MIN: 9.49 / MAX: 43.66 MIN: 11.36 / MAX: 82.77 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Face Detection Retail FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Face Detection Retail FP16-INT8 - Device: CPU d a b c 600 1200 1800 2400 3000 SE +/- 0.32, N = 3 2877.44 2876.18 2872.53 2865.70 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Face Detection Retail FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Face Detection Retail FP16-INT8 - Device: CPU a d b c 1.2555 2.511 3.7665 5.022 6.2775 SE +/- 0.00, N = 3 5.55 5.55 5.56 5.58 MIN: 3.58 / MAX: 16.08 MIN: 3.56 / MAX: 16.83 MIN: 3.54 / MAX: 15.23 MIN: 3.53 / MAX: 19.53 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Road Segmentation ADAS FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU d a b c 90 180 270 360 450 SE +/- 0.26, N = 3 426.49 425.93 422.80 422.55 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Road Segmentation ADAS FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU d a b c 9 18 27 36 45 SE +/- 0.02, N = 3 37.48 37.54 37.81 37.84 MIN: 30.7 / MAX: 75.87 MIN: 20.55 / MAX: 74.35 MIN: 32.02 / MAX: 71.39 MIN: 26.41 / MAX: 74.94 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Machine Translation EN To DE FP16 - Device: CPU d a b c 20 40 60 80 100 SE +/- 0.11, N = 3 106.37 106.34 105.92 105.86 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Machine Translation EN To DE FP16 - Device: CPU d a b c 30 60 90 120 150 SE +/- 0.16, N = 3 150.23 150.36 150.91 150.94 MIN: 120.56 / MAX: 217.05 MIN: 89.32 / MAX: 216.43 MIN: 78.96 / MAX: 213.96 MIN: 78.92 / MAX: 221.74 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Weld Porosity Detection FP16-INT8 - Device: CPU d a c b 200 400 600 800 1000 SE +/- 0.63, N = 3 1127.94 1126.24 1125.49 1125.15 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Weld Porosity Detection FP16-INT8 - Device: CPU d a c b 7 14 21 28 35 SE +/- 0.02, N = 3 28.35 28.40 28.42 28.43 MIN: 15.52 / MAX: 66.78 MIN: 20.62 / MAX: 60.08 MIN: 14.21 / MAX: 61.28 MIN: 14.49 / MAX: 62.05 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Person Vehicle Bike Detection FP16 - Device: CPU d a c b 300 600 900 1200 1500 SE +/- 1.49, N = 3 1253.78 1251.92 1235.87 1234.39 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Person Vehicle Bike Detection FP16 - Device: CPU d a c b 3 6 9 12 15 SE +/- 0.01, N = 3 12.74 12.76 12.93 12.94 MIN: 9.26 / MAX: 26.4 MIN: 9.76 / MAX: 27.07 MIN: 9.26 / MAX: 27.17 MIN: 7.54 / MAX: 27 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Noise Suppression Poconet-Like FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Noise Suppression Poconet-Like FP16 - Device: CPU d a b c 300 600 900 1200 1500 SE +/- 1.12, N = 3 1243.84 1238.99 1229.46 1224.10 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Noise Suppression Poconet-Like FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Noise Suppression Poconet-Like FP16 - Device: CPU d a b c 3 6 9 12 15 SE +/- 0.01, N = 3 12.81 12.86 12.96 13.02 MIN: 9.05 / MAX: 27.08 MIN: 9.32 / MAX: 25.64 MIN: 10.12 / MAX: 26.41 MIN: 8.06 / MAX: 28.35 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Handwritten English Recognition FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Handwritten English Recognition FP16 - Device: CPU d b a c 90 180 270 360 450 SE +/- 0.56, N = 3 426.18 425.17 424.99 424.36 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Handwritten English Recognition FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Handwritten English Recognition FP16 - Device: CPU d b a c 20 40 60 80 100 SE +/- 0.10, N = 3 75.03 75.21 75.24 75.35 MIN: 60.4 / MAX: 122.05 MIN: 49.08 / MAX: 128.66 MIN: 56.86 / MAX: 120.08 MIN: 55.02 / MAX: 130.15 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Person Re-Identification Retail FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Person Re-Identification Retail FP16 - Device: CPU d a c b 300 600 900 1200 1500 SE +/- 0.82, N = 3 1417.73 1417.27 1410.15 1408.89 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Person Re-Identification Retail FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Person Re-Identification Retail FP16 - Device: CPU d a c b 3 6 9 12 15 SE +/- 0.01, N = 3 11.27 11.28 11.33 11.34 MIN: 9.11 / MAX: 23.28 MIN: 6.18 / MAX: 47.42 MIN: 6.12 / MAX: 23.65 MIN: 9.33 / MAX: 22.56 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU b a c d 6K 12K 18K 24K 30K SE +/- 9.65, N = 3 27548.26 27516.98 27449.65 26939.10 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU a b c d 0.2655 0.531 0.7965 1.062 1.3275 SE +/- 0.00, N = 3 1.15 1.15 1.15 1.18 MIN: 0.66 / MAX: 10.97 MIN: 0.64 / MAX: 10.76 MIN: 0.66 / MAX: 19.4 MIN: 0.68 / MAX: 12.11 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Handwritten English Recognition FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Handwritten English Recognition FP16-INT8 - Device: CPU d a c b 100 200 300 400 500 SE +/- 0.48, N = 3 441.81 440.43 439.92 439.12 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Handwritten English Recognition FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Handwritten English Recognition FP16-INT8 - Device: CPU d a c b 16 32 48 64 80 SE +/- 0.07, N = 3 72.36 72.60 72.69 72.81 MIN: 49.23 / MAX: 115.01 MIN: 49.27 / MAX: 110.31 MIN: 49.56 / MAX: 113.87 MIN: 62.37 / MAX: 109.35 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU d b a c 8K 16K 24K 32K 40K SE +/- 27.57, N = 3 38686.33 38674.20 38636.14 38594.89 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.0 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU a b c d 0.1845 0.369 0.5535 0.738 0.9225 SE +/- 0.00, N = 3 0.82 0.82 0.82 0.82 MIN: 0.51 / MAX: 10.18 MIN: 0.52 / MAX: 10.82 MIN: 0.5 / MAX: 10.62 MIN: 0.51 / MAX: 9.99 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
Chaos Group V-RAY Mode: CPU OpenBenchmarking.org vsamples, More Is Better Chaos Group V-RAY 6.0 Mode: CPU b a c d 10K 20K 30K 40K 50K SE +/- 211.54, N = 3 45014 44616 44507 44319
Phoronix Test Suite v10.8.5