openvino16all 2 x INTEL XEON PLATINUM 8568Y+ testing with a Supermicro X13DAI-T v1.01 (2.4 BIOS) and NVIDIA A100-SXM4-40GB on Ubuntu 24.04 via the Phoronix Test Suite.
Compare your own system(s) to this result file with the
Phoronix Test Suite by running the command:
phoronix-test-suite benchmark 2411290-NE-OPENVINO186 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA Processor: 2 x INTEL XEON PLATINUM 8568Y+ @ 4.00GHz (96 Cores / 192 Threads), Motherboard: Supermicro X13DAI-T v1.01 (2.4 BIOS), Chipset: Intel Device 1bce, Memory: 2016GB, Disk: 2 x 15363GB SAMSUNG MZQL215THBLA-00A07 + 30725GB 9620-16i, Graphics: NVIDIA A100-SXM4-40GB, Audio: Realtek ALC888-VD, Monitor: HP 527sh, Network: 2 x Broadcom BCM57416 NetXtreme-E Dual-Media 10G RDMA
OS: Ubuntu 24.04, Kernel: 6.8.0-49-generic (x86_64), Desktop: GNOME Shell 46.0, Display Server: X Server 1.21.1.11, Display Driver: NVIDIA 550.127.08, OpenGL: 4.6.0, Compiler: GCC 13.2.0 + CUDA 12.6, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseEnvironment Notes: __GLX_VENDOR_LIBRARY_NAME=nvidiaCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-uJ7kn6/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-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 -vProcessor Notes: Scaling Governor: intel_cpufreq performance - CPU Microcode: 0x21000283Python Notes: Python 3.12.3Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: 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 Enhanced / Automatic IBRS; IBPB: conditional; RSB filling; PBRSB-eIBRS: SW sequence; BHI: BHI_DIS_S + srbds: Not affected + tsx_async_abort: Not affected
openvino16all OpenBenchmarking.org Phoronix Test Suite 2 x INTEL XEON PLATINUM 8568Y+ @ 4.00GHz (96 Cores / 192 Threads) Supermicro X13DAI-T v1.01 (2.4 BIOS) Intel Device 1bce 2016GB 2 x 15363GB SAMSUNG MZQL215THBLA-00A07 + 30725GB 9620-16i NVIDIA A100-SXM4-40GB Realtek ALC888-VD HP 527sh 2 x Broadcom BCM57416 NetXtreme-E Dual-Media 10G RDMA Ubuntu 24.04 6.8.0-49-generic (x86_64) GNOME Shell 46.0 X Server 1.21.1.11 NVIDIA 550.127.08 4.6.0 GCC 13.2.0 + CUDA 12.6 ext4 1920x1080 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver OpenGL Compiler File-System Screen Resolution Openvino16all Benchmarks System Logs - Transparent Huge Pages: madvise - __GLX_VENDOR_LIBRARY_NAME=nvidia - --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-uJ7kn6/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-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 - Scaling Governor: intel_cpufreq performance - CPU Microcode: 0x21000283 - Python 3.12.3 - gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: 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 Enhanced / Automatic IBRS; IBPB: conditional; RSB filling; PBRSB-eIBRS: SW sequence; BHI: BHI_DIS_S + srbds: Not affected + tsx_async_abort: Not affected
openvino16all 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 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 213.64 112.23 614.46 39.01 618.29 38.77 4752.80 5.04 484.30 197.93 15872.82 6.04 1690.04 14.18 7881.61 12.17 27196.66 3.51 22368.06 4.28 1918.18 49.97 1130.95 21.17 41774.02 2.20 9693.90 9.89 6846.31 13.88 4630.33 20.72 15773.94 6.07 109518.05 0.46 4787.63 20.04 119366.46 0.42 OpenBenchmarking.org
OpenVINO OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Face Detection FP16 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 50 100 150 200 250 SE +/- 0.51, N = 3 213.64 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Face Detection FP16 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 30 60 90 120 150 SE +/- 0.27, N = 3 112.23 MIN: 83.9 / MAX: 228.7 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Person Detection FP16 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 130 260 390 520 650 SE +/- 0.75, N = 3 614.46 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Person Detection FP16 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 9 18 27 36 45 SE +/- 0.05, N = 3 39.01 MIN: 29.17 / MAX: 79.47 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Person Detection FP32 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 130 260 390 520 650 SE +/- 0.88, N = 3 618.29 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Person Detection FP32 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 9 18 27 36 45 SE +/- 0.05, N = 3 38.77 MIN: 29.43 / MAX: 80.32 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Vehicle Detection FP16 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 1000 2000 3000 4000 5000 SE +/- 8.96, N = 3 4752.80 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Vehicle Detection FP16 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 1.134 2.268 3.402 4.536 5.67 SE +/- 0.01, N = 3 5.04 MIN: 4.41 / MAX: 24.12 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Face Detection FP16-INT8 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 100 200 300 400 500 SE +/- 1.70, N = 3 484.30 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Face Detection FP16-INT8 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 40 80 120 160 200 SE +/- 0.71, N = 3 197.93 MIN: 141.74 / MAX: 335.41 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Face Detection Retail FP16 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 3K 6K 9K 12K 15K SE +/- 7.84, N = 3 15872.82 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Face Detection Retail FP16 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 2 4 6 8 10 SE +/- 0.00, N = 3 6.04 MIN: 5.21 / MAX: 23.91 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Road Segmentation ADAS FP16 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 400 800 1200 1600 2000 SE +/- 1.02, N = 3 1690.04 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Road Segmentation ADAS FP16 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 4 8 12 16 20 SE +/- 0.01, N = 3 14.18 MIN: 12.33 / MAX: 55.89 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Vehicle Detection FP16-INT8 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 2K 4K 6K 8K 10K SE +/- 1.22, N = 3 7881.61 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Vehicle Detection FP16-INT8 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 3 6 9 12 15 SE +/- 0.00, N = 3 12.17 MIN: 10.26 / MAX: 40.48 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Weld Porosity Detection FP16 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 6K 12K 18K 24K 30K SE +/- 27.50, N = 3 27196.66 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Weld Porosity Detection FP16 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 0.7898 1.5796 2.3694 3.1592 3.949 SE +/- 0.00, N = 3 3.51 MIN: 2.93 / MAX: 55.23 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Face Detection Retail FP16-INT8 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 5K 10K 15K 20K 25K SE +/- 10.52, N = 3 22368.06 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Face Detection Retail FP16-INT8 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 0.963 1.926 2.889 3.852 4.815 SE +/- 0.00, N = 3 4.28 MIN: 3.69 / MAX: 21.91 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 400 800 1200 1600 2000 SE +/- 3.34, N = 3 1918.18 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Road Segmentation ADAS FP16-INT8 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 11 22 33 44 55 SE +/- 0.08, N = 3 49.97 MIN: 38.01 / MAX: 90.68 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Machine Translation EN To DE FP16 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 200 400 600 800 1000 SE +/- 5.32, N = 3 1130.95 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Machine Translation EN To DE FP16 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 5 10 15 20 25 SE +/- 0.10, N = 3 21.17 MIN: 15.54 / MAX: 68.27 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Weld Porosity Detection FP16-INT8 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 9K 18K 27K 36K 45K SE +/- 173.23, N = 3 41774.02 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Weld Porosity Detection FP16-INT8 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 0.495 0.99 1.485 1.98 2.475 SE +/- 0.01, N = 3 2.20 MIN: 1.84 / MAX: 28.87 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Person Vehicle Bike Detection FP16 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 2K 4K 6K 8K 10K SE +/- 8.40, N = 3 9693.90 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Person Vehicle Bike Detection FP16 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 3 6 9 12 15 SE +/- 0.01, N = 3 9.89 MIN: 8.43 / MAX: 35.66 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Noise Suppression Poconet-Like FP16 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 1500 3000 4500 6000 7500 SE +/- 15.49, N = 3 6846.31 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Noise Suppression Poconet-Like FP16 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 4 8 12 16 20 SE +/- 0.03, N = 3 13.88 MIN: 9.37 / MAX: 52.82 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Handwritten English Recognition FP16 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 1000 2000 3000 4000 5000 SE +/- 7.89, N = 3 4630.33 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Handwritten English Recognition FP16 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 5 10 15 20 25 SE +/- 0.04, N = 3 20.72 MIN: 18.61 / MAX: 57.15 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Person Re-Identification Retail FP16 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 3K 6K 9K 12K 15K SE +/- 8.62, N = 3 15773.94 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Person Re-Identification Retail FP16 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 2 4 6 8 10 SE +/- 0.00, N = 3 6.07 MIN: 5.47 / MAX: 15.86 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 20K 40K 60K 80K 100K SE +/- 535.78, N = 3 109518.05 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 0.1035 0.207 0.3105 0.414 0.5175 SE +/- 0.00, N = 3 0.46 MIN: 0.25 / MAX: 22.02 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Handwritten English Recognition FP16-INT8 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 1000 2000 3000 4000 5000 SE +/- 1.98, N = 3 4787.63 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Handwritten English Recognition FP16-INT8 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 5 10 15 20 25 SE +/- 0.01, N = 3 20.04 MIN: 18.38 / MAX: 43.74 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org FPS, More Is Better OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 30K 60K 90K 120K 150K SE +/- 438.66, N = 3 119366.46 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU 2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA 0.0945 0.189 0.2835 0.378 0.4725 SE +/- 0.00, N = 3 0.42 MIN: 0.2 / MAX: 18.64 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
2 x INTEL XEON PLATINUM 8568Y+ - NVIDIA Processor: 2 x INTEL XEON PLATINUM 8568Y+ @ 4.00GHz (96 Cores / 192 Threads), Motherboard: Supermicro X13DAI-T v1.01 (2.4 BIOS), Chipset: Intel Device 1bce, Memory: 2016GB, Disk: 2 x 15363GB SAMSUNG MZQL215THBLA-00A07 + 30725GB 9620-16i, Graphics: NVIDIA A100-SXM4-40GB, Audio: Realtek ALC888-VD, Monitor: HP 527sh, Network: 2 x Broadcom BCM57416 NetXtreme-E Dual-Media 10G RDMA
OS: Ubuntu 24.04, Kernel: 6.8.0-49-generic (x86_64), Desktop: GNOME Shell 46.0, Display Server: X Server 1.21.1.11, Display Driver: NVIDIA 550.127.08, OpenGL: 4.6.0, Compiler: GCC 13.2.0 + CUDA 12.6, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseEnvironment Notes: __GLX_VENDOR_LIBRARY_NAME=nvidiaCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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-backtrace --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-defaulted --enable-offload-targets=nvptx-none=/build/gcc-13-uJ7kn6/gcc-13-13.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-13-uJ7kn6/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-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 -vProcessor Notes: Scaling Governor: intel_cpufreq performance - CPU Microcode: 0x21000283Python Notes: Python 3.12.3Security Notes: gather_data_sampling: Not affected + itlb_multihit: Not affected + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Not affected + reg_file_data_sampling: Not affected + retbleed: Not affected + spec_rstack_overflow: 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 Enhanced / Automatic IBRS; IBPB: conditional; RSB filling; PBRSB-eIBRS: SW sequence; BHI: BHI_DIS_S + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 29 November 2024 22:44 by user odinn.