new halloween AMD Ryzen 9 7950X 16-Core testing with a ASUS ROG STRIX X670E-E GAMING WIFI (1416 BIOS) and NVIDIA GeForce RTX 3060 Ti 8GB on Ubuntu 23.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2310318-PTS-NEWHALLO48&rdt&grs .
new halloween Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL OpenCL Compiler File-System Screen Resolution a b c d e AMD Ryzen 9 7950X 16-Core @ 5.88GHz (16 Cores / 32 Threads) ASUS ROG STRIX X670E-E GAMING WIFI (1416 BIOS) AMD Device 14d8 32GB Western Digital WD_BLACK SN850X 1000GB NVIDIA GeForce RTX 3060 Ti 8GB NVIDIA GA104 HD Audio ASUS MG28U Intel I225-V + Intel Wi-Fi 6 AX210/AX211/AX411 Ubuntu 23.10 6.6.0-060600rc5-generic (x86_64) GNOME Shell 45.0 X Server 1.21.1.7 NVIDIA 545.23.06 4.6.0 OpenCL 3.0 CUDA 12.3.68 GCC 13.2.0 ext4 3840x2160 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,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-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-XYspKM/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-XYspKM/gcc-13-13.2.0/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 Processor Details - Scaling Governor: amd-pstate-epp powersave (EPP: balance_performance) - CPU Microcode: 0xa601203 Python Details - Python 3.11.6 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: Not affected + spec_rstack_overflow: Mitigation of safe RET no microcode + 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 / Automatic IBRS IBPB: conditional STIBP: always-on RSB filling PBRSB-eIBRS: Not affected + srbds: Not affected + tsx_async_abort: Not affected
new halloween qmcpack: H4_ae openvino: Road Segmentation ADAS FP16-INT8 - CPU openvino: Road Segmentation ADAS FP16-INT8 - CPU qmcpack: O_ae_pyscf_UHF openvino: Person Detection FP16 - CPU openvino: Person Detection FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Vehicle Detection FP16 - CPU openvino: Vehicle Detection FP16 - CPU qmcpack: simple-H2O qmcpack: LiH_ae_MSD openvino: Person Detection FP32 - CPU openvino: Person Detection FP32 - CPU qmcpack: FeCO6_b3lyp_gms openvino: Handwritten English Recognition FP16 - CPU openvino: Handwritten English Recognition FP16 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Handwritten English Recognition FP16-INT8 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Handwritten English Recognition FP16-INT8 - CPU openvino: Face Detection Retail FP16-INT8 - CPU openvino: Road Segmentation ADAS FP16 - CPU openvino: Road Segmentation ADAS FP16 - CPU qmcpack: Li2_STO_ae openvino: Face Detection FP16 - CPU openvino: Vehicle Detection FP16-INT8 - CPU build-gem5: Time To Compile openvino: Face Detection FP16-INT8 - CPU openvino: Vehicle Detection FP16-INT8 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Face Detection Retail FP16-INT8 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Face Detection Retail FP16 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Face Detection FP16 - CPU openvino: Weld Porosity Detection FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Face Detection Retail FP16 - CPU a b c d e 10.89 507.90 15.69 121.29 92.40 86.49 140.26 56.95 10.29 774.21 17.555 47.802 95.10 84.08 69.665 21.44 744.80 4.91 642.38 1620.54 24.87 4839.02 25.40 313.92 124.80 14.39 4.59 225.707 27.87 1729.22 286.44 36245.24 51161.05 3.22 2824.38 3194.70 10.96 5.62 553.47 1457.26 0.27 0.39 2.40 11.68 527.22 15.12 117.55 93.95 85.06 137.09 58.21 10.24 777.58 17.756 47.779 95.37 83.8 69.609 21.56 740.4 4.89 642.55 1627.35 24.87 4810.38 25.24 315.84 124.94 14.35 4.58 225.942 27.97 1734.39 285.61 36324.48 51246.15 3.23 2825.42 3188.52 10.95 5.62 554.27 1458.58 0.27 0.39 2.4 11.46 515.05 15.47 123.1 92.28 86.59 141.65 56.39 10.11 787.59 17.373 47.699 93.53 85.43 69.104 21.7 736.08 4.87 648.42 1632.03 24.65 4831.35 25.31 315.04 125.02 14.42 4.57 226.641 27.98 1735.45 285.46 36230.3 51294.63 3.22 2830.79 3196.57 10.94 5.61 553.51 1458.87 0.27 0.39 2.4 11.57 525.38 15.17 122.65 95.72 83.5 140.32 56.91 10.34 770.4 17.679 48.099 93.65 85.32 70.031 21.66 737.25 4.92 646.72 1617.38 24.71 4796.56 25.4 313.8 125.19 14.4 4.58 225.958 27.9 1734.4 286.21 36346.13 51135.8 3.23 2826.61 3191.14 10.94 5.61 553.45 1459.39 0.27 0.39 2.4 11.04 502.19 15.85 118.41 93.69 85.29 138.48 57.64 10.13 786.07 17.405 48.743 95.52 83.68 69.585 21.63 738.32 4.88 647.21 1630.19 24.69 4800.32 25.21 316.15 125.71 14.43 4.58 225.803 27.92 1734.3 286.02 36295.37 51245.48 3.23 2832.73 3189.75 10.94 5.61 553.33 1459.36 0.27 0.39 2.4 OpenBenchmarking.org
QMCPACK Input: H4_ae OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.17.1 Input: H4_ae a b c d e 3 6 9 12 15 SE +/- 0.08, N = 3 10.89 11.68 11.46 11.57 11.04 1. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl
OpenVINO Model: Road Segmentation ADAS FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16-INT8 - Device: CPU a b c d e 110 220 330 440 550 SE +/- 6.07, N = 3 507.90 527.22 515.05 525.38 502.19 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Road Segmentation ADAS FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16-INT8 - Device: CPU a b c d e 4 8 12 16 20 SE +/- 0.18, N = 3 15.69 15.12 15.47 15.17 15.85 MIN: 8.31 / MAX: 26.11 MIN: 8.42 / MAX: 21.5 MIN: 8.28 / MAX: 19.35 MIN: 8.18 / MAX: 23.04 MIN: 12.18 / MAX: 19.81 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
QMCPACK Input: O_ae_pyscf_UHF OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.17.1 Input: O_ae_pyscf_UHF a b c d e 30 60 90 120 150 SE +/- 1.34, N = 4 121.29 117.55 123.10 122.65 118.41 1. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Person Detection FP16 - Device: CPU a b c d e 20 40 60 80 100 SE +/- 0.38, N = 3 92.40 93.95 92.28 95.72 93.69 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Person Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Person Detection FP16 - Device: CPU a b c d e 20 40 60 80 100 SE +/- 0.34, N = 3 86.49 85.06 86.59 83.50 85.29 MIN: 54.98 / MAX: 118.77 MIN: 66.32 / MAX: 117.18 MIN: 64.62 / MAX: 113.06 MIN: 63.05 / MAX: 117.82 MIN: 70.2 / MAX: 118.01 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU a b c d e 30 60 90 120 150 SE +/- 0.80, N = 3 140.26 137.09 141.65 140.32 138.48 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Machine Translation EN To DE FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU a b c d e 13 26 39 52 65 SE +/- 0.32, N = 3 56.95 58.21 56.39 56.91 57.64 MIN: 30.37 / MAX: 66.81 MIN: 26.52 / MAX: 65.1 MIN: 30.19 / MAX: 67.6 MIN: 29.72 / MAX: 68.2 MIN: 28.67 / MAX: 66.24 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Vehicle Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Vehicle Detection FP16 - Device: CPU a b c d e 3 6 9 12 15 SE +/- 0.03, N = 3 10.29 10.24 10.11 10.34 10.13 MIN: 4 / MAX: 27.02 MIN: 4.52 / MAX: 18.9 MIN: 3.8 / MAX: 17.63 MIN: 3.68 / MAX: 25.25 MIN: 3.68 / MAX: 15.99 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Vehicle Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Vehicle Detection FP16 - Device: CPU a b c d e 200 400 600 800 1000 SE +/- 2.47, N = 3 774.21 777.58 787.59 770.40 786.07 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
QMCPACK Input: simple-H2O OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.17.1 Input: simple-H2O a b c d e 4 8 12 16 20 SE +/- 0.03, N = 3 17.56 17.76 17.37 17.68 17.41 1. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl
QMCPACK Input: LiH_ae_MSD OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.17.1 Input: LiH_ae_MSD a b c d e 11 22 33 44 55 SE +/- 0.11, N = 3 47.80 47.78 47.70 48.10 48.74 1. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl
OpenVINO Model: Person Detection FP32 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Person Detection FP32 - Device: CPU a b c d e 20 40 60 80 100 SE +/- 0.75, N = 9 95.10 95.37 93.53 93.65 95.52 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Person Detection FP32 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Person Detection FP32 - Device: CPU a b c d e 20 40 60 80 100 SE +/- 0.65, N = 9 84.08 83.80 85.43 85.32 83.68 MIN: 44.6 / MAX: 118.93 MIN: 67.65 / MAX: 114 MIN: 64.52 / MAX: 116.02 MIN: 61.93 / MAX: 114.26 MIN: 62.49 / MAX: 116.95 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
QMCPACK Input: FeCO6_b3lyp_gms OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.17.1 Input: FeCO6_b3lyp_gms a b c d e 16 32 48 64 80 SE +/- 0.05, N = 3 69.67 69.61 69.10 70.03 69.59 1. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl
OpenVINO Model: Handwritten English Recognition FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16 - Device: CPU a b c d e 5 10 15 20 25 SE +/- 0.10, N = 3 21.44 21.56 21.70 21.66 21.63 MIN: 13.28 / MAX: 31.39 MIN: 13.17 / MAX: 30.52 MIN: 13.01 / MAX: 31.3 MIN: 13.2 / MAX: 28.45 MIN: 13.11 / MAX: 32.83 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Handwritten English Recognition FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16 - Device: CPU a b c d e 160 320 480 640 800 SE +/- 3.52, N = 3 744.80 740.40 736.08 737.25 738.32 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU a b c d e 1.107 2.214 3.321 4.428 5.535 SE +/- 0.03, N = 3 4.91 4.89 4.87 4.92 4.88 MIN: 3.22 / MAX: 27.28 MIN: 3.25 / MAX: 10.7 MIN: 3.32 / MAX: 9.37 MIN: 3.38 / MAX: 10.18 MIN: 3.37 / MAX: 8.43 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Handwritten English Recognition FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16-INT8 - Device: CPU a b c d e 140 280 420 560 700 SE +/- 2.03, N = 3 642.38 642.55 648.42 646.72 647.21 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Person Vehicle Bike Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU a b c d e 400 800 1200 1600 2000 SE +/- 9.42, N = 3 1620.54 1627.35 1632.03 1617.38 1630.19 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Handwritten English Recognition FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16-INT8 - Device: CPU a b c d e 6 12 18 24 30 SE +/- 0.08, N = 3 24.87 24.87 24.65 24.71 24.69 MIN: 16.57 / MAX: 35.23 MIN: 19.6 / MAX: 32.1 MIN: 16.79 / MAX: 31.49 MIN: 16.94 / MAX: 32.43 MIN: 19.74 / MAX: 30.85 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Face Detection Retail FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Face Detection Retail FP16-INT8 - Device: CPU a b c d e 1000 2000 3000 4000 5000 SE +/- 28.48, N = 3 4839.02 4810.38 4831.35 4796.56 4800.32 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Road Segmentation ADAS FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16 - Device: CPU a b c d e 6 12 18 24 30 SE +/- 0.18, N = 3 25.40 25.24 25.31 25.40 25.21 MIN: 9.37 / MAX: 33.86 MIN: 9.98 / MAX: 33.2 MIN: 14.58 / MAX: 31.52 MIN: 13.91 / MAX: 40.43 MIN: 14.72 / MAX: 31.93 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Road Segmentation ADAS FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16 - Device: CPU a b c d e 70 140 210 280 350 SE +/- 2.23, N = 3 313.92 315.84 315.04 313.80 316.15 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
QMCPACK Input: Li2_STO_ae OpenBenchmarking.org Total Execution Time - Seconds, Fewer Is Better QMCPACK 3.17.1 Input: Li2_STO_ae a b c d e 30 60 90 120 150 SE +/- 0.22, N = 3 124.80 124.94 125.02 125.19 125.71 1. (CXX) g++ options: -fopenmp -foffload=disable -finline-limit=1000 -fstrict-aliasing -funroll-all-loops -ffast-math -march=native -O3 -lm -ldl
OpenVINO Model: Face Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Face Detection FP16 - Device: CPU a b c d e 4 8 12 16 20 SE +/- 0.05, N = 3 14.39 14.35 14.42 14.40 14.43 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU a b c d e 1.0328 2.0656 3.0984 4.1312 5.164 SE +/- 0.01, N = 3 4.59 4.58 4.57 4.58 4.58 MIN: 2.61 / MAX: 12.94 MIN: 2.63 / MAX: 8.33 MIN: 2.6 / MAX: 11.67 MIN: 2.6 / MAX: 14.72 MIN: 2.63 / MAX: 8.42 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
Timed Gem5 Compilation Time To Compile OpenBenchmarking.org Seconds, Fewer Is Better Timed Gem5 Compilation 23.0.1 Time To Compile a b c d e 50 100 150 200 250 SE +/- 0.31, N = 3 225.71 225.94 226.64 225.96 225.80
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Face Detection FP16-INT8 - Device: CPU a b c d e 7 14 21 28 35 SE +/- 0.02, N = 3 27.87 27.97 27.98 27.90 27.92 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Vehicle Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU a b c d e 400 800 1200 1600 2000 SE +/- 2.35, N = 3 1729.22 1734.39 1735.45 1734.40 1734.30 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Face Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Face Detection FP16-INT8 - Device: CPU a b c d e 60 120 180 240 300 SE +/- 0.22, N = 3 286.44 285.61 285.46 286.21 286.02 MIN: 271.76 / MAX: 293.99 MIN: 269.96 / MAX: 294.04 MIN: 271.88 / MAX: 292.13 MIN: 275.05 / MAX: 291.64 MIN: 274.05 / MAX: 291.04 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU a b c d e 8K 16K 24K 32K 40K SE +/- 15.90, N = 3 36245.24 36324.48 36230.30 36346.13 36295.37 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU a b c d e 11K 22K 33K 44K 55K SE +/- 65.26, N = 3 51161.05 51246.15 51294.63 51135.80 51245.48 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Face Detection Retail FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Face Detection Retail FP16-INT8 - Device: CPU a b c d e 0.7268 1.4536 2.1804 2.9072 3.634 SE +/- 0.01, N = 3 3.22 3.23 3.22 3.23 3.23 MIN: 1.8 / MAX: 10.96 MIN: 1.78 / MAX: 12.09 MIN: 1.78 / MAX: 12.23 MIN: 1.78 / MAX: 11.34 MIN: 1.79 / MAX: 10.28 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU a b c d e 600 1200 1800 2400 3000 SE +/- 1.88, N = 3 2824.38 2825.42 2830.79 2826.61 2832.73 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Face Detection Retail FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Face Detection Retail FP16 - Device: CPU a b c d e 700 1400 2100 2800 3500 SE +/- 9.02, N = 3 3194.70 3188.52 3196.57 3191.14 3189.75 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Weld Porosity Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16 - Device: CPU a b c d e 3 6 9 12 15 SE +/- 0.00, N = 3 10.96 10.95 10.94 10.94 10.94 MIN: 5.79 / MAX: 22.05 MIN: 6 / MAX: 14.95 MIN: 5.66 / MAX: 18.01 MIN: 5.61 / MAX: 19.85 MIN: 6.65 / MAX: 18.2 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Weld Porosity Detection FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU a b c d e 1.2645 2.529 3.7935 5.058 6.3225 SE +/- 0.00, N = 3 5.62 5.62 5.61 5.61 5.61 MIN: 2.95 / MAX: 13.45 MIN: 2.93 / MAX: 14.07 MIN: 2.96 / MAX: 13.92 MIN: 2.99 / MAX: 13.89 MIN: 2.95 / MAX: 13.93 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Face Detection FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Face Detection FP16 - Device: CPU a b c d e 120 240 360 480 600 SE +/- 2.04, N = 3 553.47 554.27 553.51 553.45 553.33 MIN: 515.82 / MAX: 572.71 MIN: 526.03 / MAX: 573.73 MIN: 529.5 / MAX: 572.8 MIN: 540.2 / MAX: 567.97 MIN: 535.16 / MAX: 568.76 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Weld Porosity Detection FP16 - Device: CPU OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16 - Device: CPU a b c d e 300 600 900 1200 1500 SE +/- 0.48, N = 3 1457.26 1458.58 1458.87 1459.39 1459.36 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU a b c d e 0.0608 0.1216 0.1824 0.2432 0.304 SE +/- 0.00, N = 3 0.27 0.27 0.27 0.27 0.27 MIN: 0.15 / MAX: 6.48 MIN: 0.15 / MAX: 6.39 MIN: 0.15 / MAX: 3.99 MIN: 0.15 / MAX: 6.42 MIN: 0.15 / MAX: 6.35 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU a b c d e 0.0878 0.1756 0.2634 0.3512 0.439 SE +/- 0.00, N = 3 0.39 0.39 0.39 0.39 0.39 MIN: 0.21 / MAX: 8.33 MIN: 0.2 / MAX: 6.46 MIN: 0.2 / MAX: 6.43 MIN: 0.21 / MAX: 6.48 MIN: 0.2 / MAX: 6.46 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
OpenVINO Model: Face Detection Retail FP16 - Device: CPU OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Face Detection Retail FP16 - Device: CPU a b c d e 0.54 1.08 1.62 2.16 2.7 SE +/- 0.01, N = 3 2.40 2.40 2.40 2.40 2.40 MIN: 1.24 / MAX: 8.2 MIN: 1.24 / MAX: 9.32 MIN: 1.24 / MAX: 9.59 MIN: 1.24 / MAX: 9.36 MIN: 1.23 / MAX: 5.71 1. (CXX) g++ options: -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -pie
Phoronix Test Suite v10.8.5