285v-openvino Intel Core Ultra 7 258V testing with a KHADAS MIND-2-AI-MAKER-KIT-K1019 (0.05 BIOS) and Intel LNL 15GB on Ubuntu 24.10 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 2412224-NE-285VOPENV31 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS Processor: Intel Core Ultra 7 258V @ 4.70GHz (8 Cores), Motherboard: KHADAS MIND-2-AI-MAKER-KIT-K1019 (0.05 BIOS), Chipset: Intel Device a87f, Memory: 32GB, Disk: 1024GB Western Digital WD PC SN740 SDDPTQD-1T00 + 2 x 0GB MassStorageClass, Graphics: Intel LNL 15GB, Audio: Intel Lunar Lake-M HD Audio, Monitor: K3-1, Network: Intel Device a840
OS: Ubuntu 24.10, Kernel: 6.12.3-061203-generic (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.3.2 kisak-mesa PPA, Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --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,rust --enable-libphobos-checking=release --enable-libstdcxx-backtrace --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-14-zdkDXv/gcc-14-14.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-14-zdkDXv/gcc-14-14.2.0/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 -vProcessor Notes: Scaling Governor: intel_pstate powersave (EPP: performance) - CPU Microcode: 0x114 - Thermald 2.5.8Python Notes: Python 3.12.7Security 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: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
285v-openvino OpenBenchmarking.org Phoronix Test Suite Intel Core Ultra 7 258V @ 4.70GHz (8 Cores) KHADAS MIND-2-AI-MAKER-KIT-K1019 (0.05 BIOS) Intel Device a87f 32GB 1024GB Western Digital WD PC SN740 SDDPTQD-1T00 + 2 x 0GB MassStorageClass Intel LNL 15GB Intel Lunar Lake-M HD Audio K3-1 Intel Device a840 Ubuntu 24.10 6.12.3-061203-generic (x86_64) GNOME Shell 47.0 X Server + Wayland 4.6 Mesa 24.3.2 kisak-mesa PPA GCC 14.2.0 ext4 1920x1080 Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server OpenGL Compiler File-System Screen Resolution 285v-openvino Benchmarks System Logs - Transparent Huge Pages: madvise - --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,rust --enable-libphobos-checking=release --enable-libstdcxx-backtrace --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-14-zdkDXv/gcc-14-14.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-14-zdkDXv/gcc-14-14.2.0/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 - Scaling Governor: intel_pstate powersave (EPP: performance) - CPU Microcode: 0x114 - Thermald 2.5.8 - Python 3.12.7 - 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: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
285v-openvino 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 - CPU openvino: Face Detection FP16 - CPU openvino: Handwritten English Recognition FP16 - CPU openvino: Handwritten English Recognition FP16 - CPU openvino: Noise Suppression Poconet-Like FP16 - CPU openvino: Noise Suppression Poconet-Like FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Machine Translation EN To DE FP16 - CPU openvino: Road Segmentation ADAS FP16 - CPU openvino: Road Segmentation ADAS FP16 - CPU openvino: Road Segmentation ADAS FP16-INT8 - CPU openvino: Road Segmentation ADAS FP16-INT8 - CPU openvino: Vehicle Detection FP16-INT8 - CPU openvino: Vehicle Detection FP16-INT8 - CPU openvino: Person Re-Identification Retail FP16 - CPU openvino: Person Re-Identification Retail FP16 - CPU openvino: Handwritten English Recognition FP16-INT8 - CPU openvino: Handwritten English Recognition FP16-INT8 - CPU openvino: Face Detection Retail FP16 - CPU openvino: Face Detection Retail FP16 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Face Detection FP16-INT8 - CPU openvino: Person Vehicle Bike Detection FP16 - CPU openvino: Person Vehicle Bike Detection FP16 - 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: Weld Porosity Detection FP16-INT8 - CPU openvino: Weld Porosity Detection FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16-INT8 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU openvino: Age Gender Recognition Retail 0013 FP16 - CPU Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 378.98 10.53 387.21 10.31 55.24 72.28 3449.01 1.13 109.31 54.80 24.65 161.58 277.79 14.37 121.66 32.83 48.03 83.01 18.08 220.30 23.81 167.35 94.03 63.71 13.44 295.86 870.02 4.58 29.04 137.40 55.07 108.73 5.93 669.66 14.72 404.51 0.76 7321.93 2.22 2623.32 OpenBenchmarking.org
OpenVINO OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2024.5 Model: Person Detection FP16 - Device: CPU Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 80 160 240 320 400 SE +/- 2.18, N = 14 378.98 MIN: 235.54 / MAX: 555.97 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 3 6 9 12 15 SE +/- 0.06, N = 14 10.53 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 80 160 240 320 400 SE +/- 3.00, N = 12 387.21 MIN: 231.83 / MAX: 615.32 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: Person Detection FP32 - Device: CPU Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 3 6 9 12 15 SE +/- 0.08, N = 12 10.31 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: Vehicle Detection FP16 - Device: CPU Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 12 24 36 48 60 SE +/- 0.41, N = 10 55.24 MIN: 26.25 / MAX: 88.9 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 16 32 48 64 80 SE +/- 0.56, N = 10 72.28 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 700 1400 2100 2800 3500 SE +/- 24.24, N = 7 3449.01 MIN: 2723.26 / MAX: 4349.59 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 - Device: CPU Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 0.2543 0.5086 0.7629 1.0172 1.2715 SE +/- 0.01, N = 7 1.13 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 20 40 60 80 100 SE +/- 0.94, N = 7 109.31 MIN: 71.06 / MAX: 140.42 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 12 24 36 48 60 SE +/- 0.49, N = 7 54.80 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: Noise Suppression Poconet-Like FP16 - Device: CPU Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 6 12 18 24 30 SE +/- 0.22, N = 6 24.65 MIN: 11.2 / MAX: 45.12 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: Noise Suppression Poconet-Like FP16 - Device: CPU Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 40 80 120 160 200 SE +/- 1.51, N = 6 161.58 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 60 120 180 240 300 SE +/- 2.84, N = 5 277.79 MIN: 200.51 / MAX: 355.92 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 4 8 12 16 20 SE +/- 0.15, N = 5 14.37 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 30 60 90 120 150 SE +/- 1.22, N = 5 121.66 MIN: 52.79 / MAX: 301.42 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 8 16 24 32 40 SE +/- 0.34, N = 5 32.83 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 11 22 33 44 55 SE +/- 0.49, N = 5 48.03 MIN: 24.94 / MAX: 68.62 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 20 40 60 80 100 SE +/- 0.88, N = 5 83.01 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 4 8 12 16 20 SE +/- 0.20, N = 4 18.08 MIN: 8.97 / MAX: 35.77 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 50 100 150 200 250 SE +/- 2.54, N = 4 220.30 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: Person Re-Identification Retail FP16 - Device: CPU Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 6 12 18 24 30 SE +/- 0.28, N = 4 23.81 MIN: 11.1 / MAX: 48.28 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 40 80 120 160 200 SE +/- 1.99, N = 4 167.35 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 20 40 60 80 100 SE +/- 1.09, N = 4 94.03 MIN: 58.52 / MAX: 123.6 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 14 28 42 56 70 SE +/- 0.76, N = 4 63.71 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 3 6 9 12 15 SE +/- 0.15, N = 4 13.44 MIN: 5.6 / MAX: 26.86 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: Face Detection Retail FP16 - Device: CPU Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 60 120 180 240 300 SE +/- 3.43, N = 4 295.86 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 200 400 600 800 1000 SE +/- 4.21, N = 3 870.02 MIN: 724.75 / MAX: 1043.48 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: Face Detection FP16-INT8 - Device: CPU Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 1.0305 2.061 3.0915 4.122 5.1525 SE +/- 0.03, N = 3 4.58 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 7 14 21 28 35 SE +/- 0.35, N = 3 29.04 MIN: 13.42 / MAX: 49.91 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: Person Vehicle Bike Detection FP16 - Device: CPU Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 30 60 90 120 150 SE +/- 1.67, N = 3 137.40 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 12 24 36 48 60 SE +/- 0.69, N = 3 55.07 MIN: 33.38 / MAX: 78.01 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 20 40 60 80 100 SE +/- 1.39, N = 3 108.73 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 1.3343 2.6686 4.0029 5.3372 6.6715 SE +/- 0.08, N = 3 5.93 MIN: 2.49 / MAX: 18.39 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 140 280 420 560 700 SE +/- 8.42, N = 3 669.66 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-INT8 - Device: CPU Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 4 8 12 16 20 SE +/- 0.19, N = 3 14.72 MIN: 8.13 / MAX: 32.2 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 90 180 270 360 450 SE +/- 5.48, N = 3 404.51 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 0.171 0.342 0.513 0.684 0.855 SE +/- 0.01, N = 3 0.76 MIN: 0.35 / MAX: 7.79 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 1600 3200 4800 6400 8000 SE +/- 66.31, N = 3 7321.93 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 0.4995 0.999 1.4985 1.998 2.4975 SE +/- 0.03, N = 3 2.22 MIN: 0.99 / MAX: 11.14 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 Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS 600 1200 1800 2400 3000 SE +/- 36.24, N = 3 2623.32 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl -lstdc++fs
Intel Core Ultra 7 258V - Intel LNL 15GB - KHADAS Processor: Intel Core Ultra 7 258V @ 4.70GHz (8 Cores), Motherboard: KHADAS MIND-2-AI-MAKER-KIT-K1019 (0.05 BIOS), Chipset: Intel Device a87f, Memory: 32GB, Disk: 1024GB Western Digital WD PC SN740 SDDPTQD-1T00 + 2 x 0GB MassStorageClass, Graphics: Intel LNL 15GB, Audio: Intel Lunar Lake-M HD Audio, Monitor: K3-1, Network: Intel Device a840
OS: Ubuntu 24.10, Kernel: 6.12.3-061203-generic (x86_64), Desktop: GNOME Shell 47.0, Display Server: X Server + Wayland, OpenGL: 4.6 Mesa 24.3.2 kisak-mesa PPA, Compiler: GCC 14.2.0, File-System: ext4, Screen Resolution: 1920x1080
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --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,rust --enable-libphobos-checking=release --enable-libstdcxx-backtrace --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-14-zdkDXv/gcc-14-14.2.0/debian/tmp-nvptx/usr,amdgcn-amdhsa=/build/gcc-14-zdkDXv/gcc-14-14.2.0/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 -vProcessor Notes: Scaling Governor: intel_pstate powersave (EPP: performance) - CPU Microcode: 0x114 - Thermald 2.5.8Python Notes: Python 3.12.7Security 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: Not affected; BHI: Not affected + srbds: Not affected + tsx_async_abort: Not affected
Testing initiated at 22 December 2024 19:39 by user paul.