Intel Core i3-10100 testing with a ASRock H510M-HVS (P1.60 BIOS) and Intel UHD 630 CML GT2 3GB on Ubuntu 20.04 via the Phoronix Test Suite.
Intel UHD 630 CML GT2 Processor: Intel Core i3-10100 @ 4.30GHz (4 Cores / 8 Threads), Motherboard: ASRock H510M-HVS (P1.60 BIOS), Chipset: Intel Device 43ef, Memory: 3584MB, Disk: 1000GB Western Digital WDS100T2B0A, Graphics: Intel UHD 630 CML GT2 3GB (1100MHz), Audio: Realtek ALC897, Monitor: G185BGEL01, Network: Realtek RTL8111/8168/8411
OS: Ubuntu 20.04, Kernel: 5.15.0-88-generic (x86_64), Desktop: GNOME Shell 3.36.9, Display Server: X Server 1.20.13, OpenGL: 4.6 Mesa 21.2.6, Vulkan: 1.2.182, Compiler: GCC 9.4.0, File-System: ext4, Screen Resolution: 1368x768
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-9QDOt0/gcc-9-9.4.0/debian/tmp-nvptx/usr,hsa --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_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xf8 - Thermald 1.9.1Python Notes: Python 3.8.10Security Notes: gather_data_sampling: Mitigation of Microcode + itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Mitigation of Enhanced IBRS + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Mitigation of Microcode + tsx_async_abort: Not affected
OpenCV This is a benchmark of the OpenCV (Computer Vision) library's built-in performance tests. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OpenCV 4.7 Test: DNN - Deep Neural Network Intel UHD 630 CML GT2 9K 18K 27K 36K 45K SE +/- 453.54, N = 15 40614 1. (CXX) g++ options: -fPIC -fsigned-char -pthread -fomit-frame-pointer -ffunction-sections -fdata-sections -msse -msse2 -msse3 -fvisibility=hidden -O3 -shared
Whisper.cpp Whisper.cpp is a port of OpenAI's Whisper model in C/C++. Whisper.cpp is developed by Georgi Gerganov for transcribing WAV audio files to text / speech recognition. Whisper.cpp supports ARM NEON, x86 AVX, and other advanced CPU features. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Whisper.cpp 1.4 Model: ggml-medium.en - Input: 2016 State of the Union Intel UHD 630 CML GT2 1000 2000 3000 4000 5000 SE +/- 15.31, N = 3 4481.69 1. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread
OpenBenchmarking.org Seconds, Fewer Is Better Whisper.cpp 1.4 Model: ggml-small.en - Input: 2016 State of the Union Intel UHD 630 CML GT2 300 600 900 1200 1500 SE +/- 1.20, N = 3 1335.21 1. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread
OpenBenchmarking.org Seconds, Fewer Is Better Whisper.cpp 1.4 Model: ggml-base.en - Input: 2016 State of the Union Intel UHD 630 CML GT2 90 180 270 360 450 SE +/- 0.30, N = 3 419.51 1. (CXX) g++ options: -O3 -std=c++11 -fPIC -pthread
OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Kernel PCA Solvers / Time vs. N Components Intel UHD 630 CML GT2 80 160 240 320 400 SE +/- 5.16, N = 9 355.19 1. (F9X) gfortran options: -O0
OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Kernel PCA Solvers / Time vs. N Samples Intel UHD 630 CML GT2 90 180 270 360 450 SE +/- 0.55, N = 3 430.92 1. (F9X) gfortran options: -O0
OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Hist Gradient Boosting Categorical Only Intel UHD 630 CML GT2 6 12 18 24 30 SE +/- 0.05, N = 3 23.30 1. (F9X) gfortran options: -O0
OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Plot Polynomial Kernel Approximation Intel UHD 630 CML GT2 60 120 180 240 300 SE +/- 0.84, N = 3 275.14 1. (F9X) gfortran options: -O0
OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: 20 Newsgroups / Logistic Regression Intel UHD 630 CML GT2 14 28 42 56 70 SE +/- 0.54, N = 8 62.13 1. (F9X) gfortran options: -O0
OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Plot Singular Value Decomposition Intel UHD 630 CML GT2 70 140 210 280 350 SE +/- 2.13, N = 3 330.98 1. (F9X) gfortran options: -O0
OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Hist Gradient Boosting Threading Intel UHD 630 CML GT2 80 160 240 320 400 SE +/- 3.09, N = 3 361.51 1. (F9X) gfortran options: -O0
OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Covertype Dataset Benchmark Intel UHD 630 CML GT2 120 240 360 480 600 SE +/- 0.59, N = 3 556.13 1. (F9X) gfortran options: -O0
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.
Numenta Anomaly Benchmark Numenta Anomaly Benchmark (NAB) is a benchmark for evaluating algorithms for anomaly detection in streaming, real-time applications. It is comprised of over 50 labeled real-world and artificial time-series data files plus a novel scoring mechanism designed for real-time applications. This test profile currently measures the time to run various detectors. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better Numenta Anomaly Benchmark 1.1 Detector: Contextual Anomaly Detector OSE Intel UHD 630 CML GT2 20 40 60 80 100 SE +/- 0.25, N = 3 99.65
OpenVINO This is a test of the Intel OpenVINO, a toolkit around neural networks, using its built-in benchmarking support and analyzing the throughput and latency for various models. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU Intel UHD 630 CML GT2 0.2115 0.423 0.6345 0.846 1.0575 SE +/- 0.01, N = 3 0.94 MIN: 0.49 / MAX: 23.05 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16-INT8 - Device: CPU Intel UHD 630 CML GT2 900 1800 2700 3600 4500 SE +/- 34.38, N = 3 4197.73 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16-INT8 - Device: CPU Intel UHD 630 CML GT2 20 40 60 80 100 SE +/- 0.53, N = 3 83.84 MIN: 71.98 / MAX: 109.3 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16-INT8 - Device: CPU Intel UHD 630 CML GT2 11 22 33 44 55 SE +/- 0.31, N = 3 47.69 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU Intel UHD 630 CML GT2 0.459 0.918 1.377 1.836 2.295 SE +/- 0.01, N = 3 2.04 MIN: 1.03 / MAX: 27.77 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Age Gender Recognition Retail 0013 FP16 - Device: CPU Intel UHD 630 CML GT2 400 800 1200 1600 2000 SE +/- 5.88, N = 3 1937.85 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16 - Device: CPU Intel UHD 630 CML GT2 20 40 60 80 100 SE +/- 0.51, N = 3 101.72 MIN: 54.27 / MAX: 134.84 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Handwritten English Recognition FP16 - Device: CPU Intel UHD 630 CML GT2 9 18 27 36 45 SE +/- 0.20, N = 3 39.30 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU Intel UHD 630 CML GT2 11 22 33 44 55 SE +/- 0.64, N = 3 46.56 MIN: 25.67 / MAX: 86.3 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Person Vehicle Bike Detection FP16 - Device: CPU Intel UHD 630 CML GT2 20 40 60 80 100 SE +/- 1.16, N = 3 85.89 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU Intel UHD 630 CML GT2 5 10 15 20 25 SE +/- 0.22, N = 3 18.58 MIN: 9.94 / MAX: 31.23 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16-INT8 - Device: CPU Intel UHD 630 CML GT2 50 100 150 200 250 SE +/- 2.50, N = 3 215.06 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU Intel UHD 630 CML GT2 80 160 240 320 400 SE +/- 2.90, N = 3 390.31 MIN: 182.4 / MAX: 427.67 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Machine Translation EN To DE FP16 - Device: CPU Intel UHD 630 CML GT2 3 6 9 12 15 SE +/- 0.08, N = 3 10.24 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16-INT8 - Device: CPU Intel UHD 630 CML GT2 20 40 60 80 100 SE +/- 0.79, N = 3 103.35 MIN: 47.57 / MAX: 127.44 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16-INT8 - Device: CPU Intel UHD 630 CML GT2 9 18 27 36 45 SE +/- 0.30, N = 3 38.69 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Face Detection Retail FP16-INT8 - Device: CPU Intel UHD 630 CML GT2 3 6 9 12 15 SE +/- 0.03, N = 3 10.31 MIN: 6 / MAX: 27.84 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Face Detection Retail FP16-INT8 - Device: CPU Intel UHD 630 CML GT2 80 160 240 320 400 SE +/- 1.31, N = 3 387.43 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16 - Device: CPU Intel UHD 630 CML GT2 9 18 27 36 45 SE +/- 0.18, N = 3 38.99 MIN: 21.94 / MAX: 59.77 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Weld Porosity Detection FP16 - Device: CPU Intel UHD 630 CML GT2 20 40 60 80 100 SE +/- 0.45, N = 3 102.52 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU Intel UHD 630 CML GT2 9 18 27 36 45 SE +/- 0.47, N = 4 39.27 MIN: 16.66 / MAX: 66.5 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Vehicle Detection FP16-INT8 - Device: CPU Intel UHD 630 CML GT2 20 40 60 80 100 SE +/- 1.23, N = 4 101.81 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16 - Device: CPU Intel UHD 630 CML GT2 80 160 240 320 400 SE +/- 0.76, N = 3 388.22 MIN: 194.63 / MAX: 454.99 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Road Segmentation ADAS FP16 - Device: CPU Intel UHD 630 CML GT2 3 6 9 12 15 SE +/- 0.02, N = 3 10.30 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Face Detection Retail FP16 - Device: CPU Intel UHD 630 CML GT2 7 14 21 28 35 SE +/- 0.18, N = 3 28.95 MIN: 10.02 / MAX: 74.15 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Face Detection Retail FP16 - Device: CPU Intel UHD 630 CML GT2 30 60 90 120 150 SE +/- 0.83, N = 3 138.04 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Face Detection FP16-INT8 - Device: CPU Intel UHD 630 CML GT2 400 800 1200 1600 2000 SE +/- 17.01, N = 3 1829.80 MIN: 1646.16 / MAX: 1966.52 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Face Detection FP16-INT8 - Device: CPU Intel UHD 630 CML GT2 0.4905 0.981 1.4715 1.962 2.4525 SE +/- 0.02, N = 3 2.18 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Vehicle Detection FP16 - Device: CPU Intel UHD 630 CML GT2 20 40 60 80 100 SE +/- 0.12, N = 3 91.92 MIN: 26.91 / MAX: 143.9 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Vehicle Detection FP16 - Device: CPU Intel UHD 630 CML GT2 10 20 30 40 50 SE +/- 0.06, N = 3 43.49 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Person Detection FP32 - Device: CPU Intel UHD 630 CML GT2 110 220 330 440 550 SE +/- 0.10, N = 3 502.32 MIN: 458.24 / MAX: 574.97 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Person Detection FP32 - Device: CPU Intel UHD 630 CML GT2 2 4 6 8 10 SE +/- 0.00, N = 3 7.96 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Person Detection FP16 - Device: CPU Intel UHD 630 CML GT2 110 220 330 440 550 SE +/- 1.06, N = 3 502.35 MIN: 452.28 / MAX: 549.57 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Person Detection FP16 - Device: CPU Intel UHD 630 CML GT2 2 4 6 8 10 SE +/- 0.02, N = 3 7.96 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org ms, Fewer Is Better OpenVINO 2023.2.dev Model: Face Detection FP16 - Device: CPU Intel UHD 630 CML GT2 800 1600 2400 3200 4000 SE +/- 36.52, N = 3 3660.46 MIN: 3432.69 / MAX: 4026.89 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better OpenVINO 2023.2.dev Model: Face Detection FP16 - Device: CPU Intel UHD 630 CML GT2 0.2453 0.4906 0.7359 0.9812 1.2265 SE +/- 0.01, N = 3 1.09 1. (CXX) g++ options: -fPIC -fsigned-char -ffunction-sections -fdata-sections -O3 -fno-strict-overflow -fwrapv -shared -ldl
OpenBenchmarking.org FPS, More Is Better PlaidML FP16: No - Mode: Inference - Network: VGG16 - Device: CPU Intel UHD 630 CML GT2 2 4 6 8 10 SE +/- 0.08, N = 9 6.09
TNN TNN is an open-source deep learning reasoning framework developed by Tencent. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v1.1 Intel UHD 630 CML GT2 70 140 210 280 350 SE +/- 0.62, N = 3 313.97 MIN: 312.4 / MAX: 317.35 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: SqueezeNet v2 Intel UHD 630 CML GT2 16 32 48 64 80 SE +/- 0.56, N = 3 70.17 MIN: 68.98 / MAX: 71.71 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: MobileNet v2 Intel UHD 630 CML GT2 80 160 240 320 400 SE +/- 0.51, N = 3 346.04 MIN: 343.36 / MAX: 348.14 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.org ms, Fewer Is Better TNN 0.3 Target: CPU - Model: DenseNet Intel UHD 630 CML GT2 900 1800 2700 3600 4500 SE +/- 9.20, N = 3 4010.89 MIN: 3963.22 / MAX: 4047.46 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -fvisibility=default -O3 -rdynamic -ldl
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: vision_transformer Intel UHD 630 CML GT2 40 80 120 160 200 SE +/- 1.11, N = 3 169.32 MIN: 167 / MAX: 180.91 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: regnety_400m Intel UHD 630 CML GT2 3 6 9 12 15 SE +/- 0.02, N = 3 10.31 MIN: 10.21 / MAX: 12.72 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: squeezenet_ssd Intel UHD 630 CML GT2 6 12 18 24 30 SE +/- 0.06, N = 3 25.97 MIN: 25.51 / MAX: 26.55 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: yolov4-tiny Intel UHD 630 CML GT2 13 26 39 52 65 SE +/- 0.04, N = 3 59.60 MIN: 59.31 / MAX: 69.65 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: resnet50 Intel UHD 630 CML GT2 12 24 36 48 60 SE +/- 0.08, N = 3 51.51 MIN: 50.97 / MAX: 62.63 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: alexnet Intel UHD 630 CML GT2 4 8 12 16 20 SE +/- 0.01, N = 3 18.12 MIN: 17.95 / MAX: 27.16 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: resnet18 Intel UHD 630 CML GT2 5 10 15 20 25 SE +/- 0.05, N = 3 22.04 MIN: 21.78 / MAX: 33.27 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: vgg16 Intel UHD 630 CML GT2 30 60 90 120 150 SE +/- 0.09, N = 3 148.83 MIN: 147.68 / MAX: 188.04 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: googlenet Intel UHD 630 CML GT2 6 12 18 24 30 SE +/- 0.04, N = 3 26.11 MIN: 25.89 / MAX: 29.34 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: blazeface Intel UHD 630 CML GT2 0.2228 0.4456 0.6684 0.8912 1.114 SE +/- 0.01, N = 3 0.99 MIN: 0.94 / MAX: 1.05 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: efficientnet-b0 Intel UHD 630 CML GT2 4 8 12 16 20 SE +/- 0.04, N = 3 13.91 MIN: 13.62 / MAX: 24.6 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: mnasnet Intel UHD 630 CML GT2 2 4 6 8 10 SE +/- 0.02, N = 3 6.77 MIN: 6.6 / MAX: 7.26 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: shufflenet-v2 Intel UHD 630 CML GT2 0.7155 1.431 2.1465 2.862 3.5775 SE +/- 0.00, N = 3 3.18 MIN: 3.13 / MAX: 4.35 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU-v3-v3 - Model: mobilenet-v3 Intel UHD 630 CML GT2 2 4 6 8 10 SE +/- 0.03, N = 3 6.55 MIN: 6.4 / MAX: 8.28 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU-v2-v2 - Model: mobilenet-v2 Intel UHD 630 CML GT2 3 6 9 12 15 SE +/- 0.02, N = 3 10.90 MIN: 10.73 / MAX: 12.95 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: Vulkan GPU - Model: mobilenet Intel UHD 630 CML GT2 9 18 27 36 45 SE +/- 0.10, N = 3 40.45 MIN: 40.09 / MAX: 42.18 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: FastestDet Intel UHD 630 CML GT2 2 4 6 8 10 SE +/- 0.06, N = 3 6.06 MIN: 5.87 / MAX: 15.58 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: vision_transformer Intel UHD 630 CML GT2 40 80 120 160 200 SE +/- 0.79, N = 3 168.97 MIN: 166.92 / MAX: 291 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: regnety_400m Intel UHD 630 CML GT2 3 6 9 12 15 SE +/- 0.01, N = 3 10.28 MIN: 10.19 / MAX: 12.4 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: squeezenet_ssd Intel UHD 630 CML GT2 6 12 18 24 30 SE +/- 0.06, N = 3 26.02 MIN: 25.58 / MAX: 30.46 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: yolov4-tiny Intel UHD 630 CML GT2 13 26 39 52 65 SE +/- 0.06, N = 3 59.47 MIN: 59.15 / MAX: 62.39 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: resnet50 Intel UHD 630 CML GT2 12 24 36 48 60 SE +/- 0.03, N = 3 51.46 MIN: 51.1 / MAX: 62.09 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: alexnet Intel UHD 630 CML GT2 4 8 12 16 20 SE +/- 0.01, N = 3 18.08 MIN: 17.91 / MAX: 19.65 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: resnet18 Intel UHD 630 CML GT2 5 10 15 20 25 SE +/- 0.03, N = 3 22.09 MIN: 21.88 / MAX: 24.41 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: vgg16 Intel UHD 630 CML GT2 30 60 90 120 150 SE +/- 0.17, N = 3 148.39 MIN: 147.62 / MAX: 159.26 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: googlenet Intel UHD 630 CML GT2 6 12 18 24 30 SE +/- 0.13, N = 3 26.08 MIN: 25.8 / MAX: 37.67 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: blazeface Intel UHD 630 CML GT2 0.2183 0.4366 0.6549 0.8732 1.0915 SE +/- 0.01, N = 3 0.97 MIN: 0.92 / MAX: 1.05 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: efficientnet-b0 Intel UHD 630 CML GT2 4 8 12 16 20 SE +/- 0.07, N = 3 13.84 MIN: 13.52 / MAX: 16.26 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: mnasnet Intel UHD 630 CML GT2 2 4 6 8 10 SE +/- 0.03, N = 3 6.75 MIN: 6.55 / MAX: 7.03 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: shufflenet-v2 Intel UHD 630 CML GT2 0.7133 1.4266 2.1399 2.8532 3.5665 SE +/- 0.01, N = 3 3.17 MIN: 3.11 / MAX: 3.28 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU-v3-v3 - Model: mobilenet-v3 Intel UHD 630 CML GT2 2 4 6 8 10 SE +/- 0.03, N = 3 6.53 MIN: 6.38 / MAX: 8.23 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU-v2-v2 - Model: mobilenet-v2 Intel UHD 630 CML GT2 3 6 9 12 15 SE +/- 0.06, N = 3 10.90 MIN: 10.69 / MAX: 21.48 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
OpenBenchmarking.org ms, Fewer Is Better NCNN 20230517 Target: CPU - Model: mobilenet Intel UHD 630 CML GT2 9 18 27 36 45 SE +/- 0.09, N = 3 40.47 MIN: 40.08 / MAX: 83.25 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread -pthread
Mobile Neural Network MNN is the Mobile Neural Network as a highly efficient, lightweight deep learning framework developed by Alibaba. This MNN test profile is building the OpenMP / CPU threaded version for processor benchmarking and not any GPU-accelerated test. MNN does allow making use of AVX-512 extensions. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: inception-v3 Intel UHD 630 CML GT2 13 26 39 52 65 SE +/- 0.28, N = 3 57.66 MIN: 56.01 / MAX: 109.59 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: mobilenet-v1-1.0 Intel UHD 630 CML GT2 1.3255 2.651 3.9765 5.302 6.6275 SE +/- 0.046, N = 3 5.891 MIN: 5.66 / MAX: 19.27 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: MobileNetV2_224 Intel UHD 630 CML GT2 1.2978 2.5956 3.8934 5.1912 6.489 SE +/- 0.045, N = 3 5.768 MIN: 5.61 / MAX: 20.21 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: SqueezeNetV1.0 Intel UHD 630 CML GT2 3 6 9 12 15 SE +/- 0.061, N = 3 9.364 MIN: 9.14 / MAX: 23.05 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: resnet-v2-50 Intel UHD 630 CML GT2 11 22 33 44 55 SE +/- 0.11, N = 3 49.75 MIN: 49.05 / MAX: 64.84 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: squeezenetv1.1 Intel UHD 630 CML GT2 0.9297 1.8594 2.7891 3.7188 4.6485 SE +/- 0.035, N = 3 4.132 MIN: 4.01 / MAX: 6.94 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: mobilenetV3 Intel UHD 630 CML GT2 0.4817 0.9634 1.4451 1.9268 2.4085 SE +/- 0.024, N = 3 2.141 MIN: 2.04 / MAX: 9.88 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
OpenBenchmarking.org ms, Fewer Is Better Mobile Neural Network 2.1 Model: nasnet Intel UHD 630 CML GT2 4 8 12 16 20 SE +/- 0.12, N = 3 15.10 MIN: 13.64 / MAX: 29.77 1. (CXX) g++ options: -std=c++11 -O3 -fvisibility=hidden -fomit-frame-pointer -fstrict-aliasing -ffunction-sections -fdata-sections -ffast-math -fno-rtti -fno-exceptions -rdynamic -pthread -ldl
Caffe This is a benchmark of the Caffe deep learning framework and currently supports the AlexNet and Googlenet model and execution on both CPUs and NVIDIA GPUs. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Milli-Seconds, Fewer Is Better Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 1000 Intel UHD 630 CML GT2 300K 600K 900K 1200K 1500K SE +/- 1702.77, N = 3 1546367 1. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
OpenBenchmarking.org Milli-Seconds, Fewer Is Better Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 200 Intel UHD 630 CML GT2 70K 140K 210K 280K 350K SE +/- 632.99, N = 3 309367 1. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
OpenBenchmarking.org Milli-Seconds, Fewer Is Better Caffe 2020-02-13 Model: GoogleNet - Acceleration: CPU - Iterations: 100 Intel UHD 630 CML GT2 30K 60K 90K 120K 150K SE +/- 66.36, N = 3 154104 1. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
OpenBenchmarking.org Milli-Seconds, Fewer Is Better Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 1000 Intel UHD 630 CML GT2 140K 280K 420K 560K 700K SE +/- 715.63, N = 3 662266 1. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
OpenBenchmarking.org Milli-Seconds, Fewer Is Better Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 200 Intel UHD 630 CML GT2 30K 60K 90K 120K 150K SE +/- 323.65, N = 3 131136 1. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
OpenBenchmarking.org Milli-Seconds, Fewer Is Better Caffe 2020-02-13 Model: AlexNet - Acceleration: CPU - Iterations: 100 Intel UHD 630 CML GT2 14K 28K 42K 56K 70K SE +/- 3.33, N = 3 65490 1. (CXX) g++ options: -fPIC -O3 -rdynamic -lglog -lgflags -lprotobuf -lpthread -lsz -lz -ldl -lm -llmdb -lopenblas
Neural Magic DeepSparse OpenBenchmarking.org ms/batch, Fewer Is Better Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream Intel UHD 630 CML GT2 80 160 240 320 400 SE +/- 0.31, N = 3 347.38
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Synchronous Single-Stream Intel UHD 630 CML GT2 0.6477 1.2954 1.9431 2.5908 3.2385 SE +/- 0.0025, N = 3 2.8786
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Token Classification, BERT base uncased conll2003 - Scenario: Asynchronous Multi-Stream Intel UHD 630 CML GT2 0.6586 1.3172 1.9758 2.6344 3.293 SE +/- 0.0047, N = 3 2.9270
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: CV Segmentation, 90% Pruned YOLACT Pruned - Scenario: Asynchronous Multi-Stream Intel UHD 630 CML GT2 0.8883 1.7766 2.6649 3.5532 4.4415 SE +/- 0.0071, N = 3 3.9479
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Synchronous Single-Stream Intel UHD 630 CML GT2 0.652 1.304 1.956 2.608 3.26 SE +/- 0.0089, N = 3 2.8978
OpenBenchmarking.org items/sec, More Is Better Neural Magic DeepSparse 1.5 Model: NLP Document Classification, oBERT base uncased on IMDB - Scenario: Asynchronous Multi-Stream Intel UHD 630 CML GT2 0.666 1.332 1.998 2.664 3.33 SE +/- 0.0082, N = 3 2.9599
TensorFlow This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: CPU - Batch Size: 256 - Model: GoogLeNet Intel UHD 630 CML GT2 1.089 2.178 3.267 4.356 5.445 SE +/- 0.06, N = 3 4.84
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: ResNet-50 Intel UHD 630 CML GT2 0.3915 0.783 1.1745 1.566 1.9575 SE +/- 0.05, N = 3 1.74
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: ResNet-50 Intel UHD 630 CML GT2 0.864 1.728 2.592 3.456 4.32 SE +/- 0.00, N = 3 3.84
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: CPU - Batch Size: 64 - Model: VGG-16 Intel UHD 630 CML GT2 0.2363 0.4726 0.7089 0.9452 1.1815 SE +/- 0.01, N = 3 1.05
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: VGG-16 Intel UHD 630 CML GT2 0.3555 0.711 1.0665 1.422 1.7775 SE +/- 0.02, N = 4 1.58
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: CPU - Batch Size: 16 - Model: VGG-16 Intel UHD 630 CML GT2 0.4163 0.8326 1.2489 1.6652 2.0815 SE +/- 0.02, N = 9 1.85
PyTorch OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 512 - Model: Efficientnet_v2_l Intel UHD 630 CML GT2 0.5108 1.0216 1.5324 2.0432 2.554 SE +/- 0.01, N = 3 2.27 MIN: 2.1 / MAX: 2.3
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 256 - Model: Efficientnet_v2_l Intel UHD 630 CML GT2 0.5063 1.0126 1.5189 2.0252 2.5315 SE +/- 0.01, N = 3 2.25 MIN: 2.07 / MAX: 2.3
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 64 - Model: Efficientnet_v2_l Intel UHD 630 CML GT2 0.5108 1.0216 1.5324 2.0432 2.554 SE +/- 0.00, N = 3 2.27 MIN: 2.11 / MAX: 2.32
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 32 - Model: Efficientnet_v2_l Intel UHD 630 CML GT2 0.5108 1.0216 1.5324 2.0432 2.554 SE +/- 0.00, N = 3 2.27 MIN: 1.95 / MAX: 2.32
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 16 - Model: Efficientnet_v2_l Intel UHD 630 CML GT2 0.4973 0.9946 1.4919 1.9892 2.4865 SE +/- 0.01, N = 3 2.21 MIN: 1.47 / MAX: 2.26
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 1 - Model: Efficientnet_v2_l Intel UHD 630 CML GT2 0.9968 1.9936 2.9904 3.9872 4.984 SE +/- 0.04, N = 3 4.43 MIN: 3.87 / MAX: 4.55
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 512 - Model: ResNet-152 Intel UHD 630 CML GT2 0.765 1.53 2.295 3.06 3.825 SE +/- 0.01, N = 3 3.40 MIN: 3.22 / MAX: 3.54
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 256 - Model: ResNet-152 Intel UHD 630 CML GT2 0.774 1.548 2.322 3.096 3.87 SE +/- 0.01, N = 3 3.44 MIN: 3.25 / MAX: 3.54
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 64 - Model: ResNet-152 Intel UHD 630 CML GT2 0.7875 1.575 2.3625 3.15 3.9375 SE +/- 0.01, N = 3 3.50 MIN: 3.08 / MAX: 3.55
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 512 - Model: ResNet-50 Intel UHD 630 CML GT2 2 4 6 8 10 SE +/- 0.03, N = 3 7.13 MIN: 6.8 / MAX: 7.27
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 32 - Model: ResNet-152 Intel UHD 630 CML GT2 0.7695 1.539 2.3085 3.078 3.8475 SE +/- 0.04, N = 4 3.42 MIN: 2.62 / MAX: 3.57
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 256 - Model: ResNet-50 Intel UHD 630 CML GT2 2 4 6 8 10 SE +/- 0.03, N = 3 7.13 MIN: 5.96 / MAX: 7.25
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 16 - Model: ResNet-152 Intel UHD 630 CML GT2 0.7673 1.5346 2.3019 3.0692 3.8365 SE +/- 0.03, N = 8 3.41 MIN: 2.68 / MAX: 3.64
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 64 - Model: ResNet-50 Intel UHD 630 CML GT2 2 4 6 8 10 SE +/- 0.03, N = 3 7.07 MIN: 5.87 / MAX: 7.19
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 32 - Model: ResNet-50 Intel UHD 630 CML GT2 2 4 6 8 10 SE +/- 0.03, N = 3 6.93 MIN: 6.1 / MAX: 7.05
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 16 - Model: ResNet-50 Intel UHD 630 CML GT2 2 4 6 8 10 SE +/- 0.05, N = 3 6.95 MIN: 5.81 / MAX: 7.09
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 1 - Model: ResNet-152 Intel UHD 630 CML GT2 1.3478 2.6956 4.0434 5.3912 6.739 SE +/- 0.05, N = 10 5.99 MIN: 4.82 / MAX: 6.56
OpenBenchmarking.org batches/sec, More Is Better PyTorch 2.1 Device: CPU - Batch Size: 1 - Model: ResNet-50 Intel UHD 630 CML GT2 3 6 9 12 15 SE +/- 0.14, N = 3 12.82 MIN: 11.44 / MAX: 13.27
TensorFlow Lite This is a benchmark of the TensorFlow Lite implementation focused on TensorFlow machine learning for mobile, IoT, edge, and other cases. The current Linux support is limited to running on CPUs. This test profile is measuring the average inference time. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Microseconds, Fewer Is Better TensorFlow Lite 2022-05-18 Model: Inception ResNet V2 Intel UHD 630 CML GT2 20K 40K 60K 80K 100K SE +/- 773.95, N = 3 88427.7
RNNoise RNNoise is a recurrent neural network for audio noise reduction developed by Mozilla and Xiph.Org. This test profile is a single-threaded test measuring the time to denoise a sample 26 minute long 16-bit RAW audio file using this recurrent neural network noise suppression library. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better RNNoise 2020-06-28 Intel UHD 630 CML GT2 6 12 18 24 30 SE +/- 0.06, N = 3 25.32 1. (CC) gcc options: -O2 -pedantic -fvisibility=hidden
DeepSpeech Mozilla DeepSpeech is a speech-to-text engine powered by TensorFlow for machine learning and derived from Baidu's Deep Speech research paper. This test profile times the speech-to-text process for a roughly three minute audio recording. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Seconds, Fewer Is Better DeepSpeech 0.6 Acceleration: CPU Intel UHD 630 CML GT2 20 40 60 80 100 SE +/- 0.17, N = 3 106.13
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Recurrent Neural Network Inference - Data Type: bf16bf16bf16 - Engine: CPU Intel UHD 630 CML GT2 1400 2800 4200 5600 7000 SE +/- 39.36, N = 3 6626.14 MIN: 6514 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Recurrent Neural Network Training - Data Type: bf16bf16bf16 - Engine: CPU Intel UHD 630 CML GT2 2K 4K 6K 8K 10K SE +/- 29.88, N = 3 10350.7 MIN: 10265.5 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Recurrent Neural Network Inference - Data Type: u8s8f32 - Engine: CPU Intel UHD 630 CML GT2 1400 2800 4200 5600 7000 SE +/- 31.44, N = 3 6632.54 MIN: 6538.67 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Recurrent Neural Network Training - Data Type: u8s8f32 - Engine: CPU Intel UHD 630 CML GT2 2K 4K 6K 8K 10K SE +/- 12.15, N = 3 10313.9 MIN: 10251.1 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Recurrent Neural Network Inference - Data Type: f32 - Engine: CPU Intel UHD 630 CML GT2 1400 2800 4200 5600 7000 SE +/- 15.81, N = 3 6656.38 MIN: 6584.3 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Recurrent Neural Network Training - Data Type: f32 - Engine: CPU Intel UHD 630 CML GT2 2K 4K 6K 8K 10K SE +/- 31.02, N = 3 10295.8 MIN: 10197.1 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Deconvolution Batch shapes_3d - Data Type: u8s8f32 - Engine: CPU Intel UHD 630 CML GT2 2 4 6 8 10 SE +/- 0.07881, N = 5 7.88714 MIN: 7.6 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Deconvolution Batch shapes_1d - Data Type: u8s8f32 - Engine: CPU Intel UHD 630 CML GT2 0.9786 1.9572 2.9358 3.9144 4.893 SE +/- 0.01766, N = 3 4.34929 MIN: 4.26 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Convolution Batch Shapes Auto - Data Type: u8s8f32 - Engine: CPU Intel UHD 630 CML GT2 12 24 36 48 60 SE +/- 0.03, N = 3 52.10 MIN: 51.76 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Deconvolution Batch shapes_3d - Data Type: f32 - Engine: CPU Intel UHD 630 CML GT2 4 8 12 16 20 SE +/- 0.10, N = 3 15.06 MIN: 14.67 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Convolution Batch Shapes Auto - Data Type: f32 - Engine: CPU Intel UHD 630 CML GT2 13 26 39 52 65 SE +/- 0.02, N = 3 59.67 MIN: 59.02 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: IP Shapes 3D - Data Type: u8s8f32 - Engine: CPU Intel UHD 630 CML GT2 1.2376 2.4752 3.7128 4.9504 6.188 SE +/- 0.02096, N = 3 5.50061 MIN: 5.14 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: IP Shapes 1D - Data Type: u8s8f32 - Engine: CPU Intel UHD 630 CML GT2 0.6978 1.3956 2.0934 2.7912 3.489 SE +/- 0.00765, N = 3 3.10155 MIN: 3.02 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: IP Shapes 3D - Data Type: f32 - Engine: CPU Intel UHD 630 CML GT2 7 14 21 28 35 SE +/- 0.10, N = 3 32.19 MIN: 31.63 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: IP Shapes 1D - Data Type: f32 - Engine: CPU Intel UHD 630 CML GT2 3 6 9 12 15 SE +/- 0.03, N = 3 12.78 MIN: 12.36 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Scikit-Learn Scikit-learn is a Python module for machine learning built on NumPy, SciPy, and is BSD-licensed. Learn more via the OpenBenchmarking.org test page.
Benchmark: Plot Non-Negative Matrix Factorization
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: KeyError:
OpenBenchmarking.org Seconds, Fewer Is Better Scikit-Learn 1.2.2 Benchmark: Hist Gradient Boosting Higgs Boson Intel UHD 630 CML GT2 40 80 120 160 200 SE +/- 21.85, N = 12 170.74 1. (F9X) gfortran options: -O0
Benchmark: Isotonic / Perturbed Logarithm
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.
Benchmark: RCV1 Logreg Convergencet
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: IndexError: list index out of range
Benchmark: Isotonic / Pathological
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.
Benchmark: Plot Parallel Pairwise
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: numpy.core._exceptions.MemoryError: Unable to allocate 74.5 GiB for an array with shape (100000, 100000) and data type float64
Benchmark: Isotonic / Logistic
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.
Benchmark: Plot Fast KMeans
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.
Benchmark: Isolation Forest
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.
Benchmark: SGDOneClassSVM
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.
Benchmark: Glmnet
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ModuleNotFoundError: No module named 'glmnet.elastic_net'
Mlpack Benchmark Mlpack benchmark scripts for machine learning libraries Learn more via the OpenBenchmarking.org test page.
Benchmark: scikit_linearridgeregression
Intel UHD 630 CML GT2: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
Benchmark: scikit_qda
Intel UHD 630 CML GT2: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
AI Benchmark Alpha AI Benchmark Alpha is a Python library for evaluating artificial intelligence (AI) performance on diverse hardware platforms and relies upon the TensorFlow machine learning library. Learn more via the OpenBenchmarking.org test page.
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. E: AttributeError: module 'numpy' has no attribute 'typeDict'
ONNX Runtime ONNX Runtime is developed by Microsoft and partners as a open-source, cross-platform, high performance machine learning inferencing and training accelerator. This test profile runs the ONNX Runtime with various models available from the ONNX Model Zoo. Learn more via the OpenBenchmarking.org test page.
OpenBenchmarking.org Inference Time Cost (ms), Fewer Is Better ONNX Runtime 1.14 Model: fcn-resnet101-11 - Device: CPU - Executor: Parallel Intel UHD 630 CML GT2 500 1000 1500 2000 2500 SE +/- 71.32, N = 12 2437.66 1. (CXX) g++ options: -ffunction-sections -fdata-sections -march=native -mtune=native -O3 -flto -fno-fat-lto-objects -ldl -lrt -lpthread -pthread
Model: yolov4 - Device: CPU - Executor: Standard
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnxruntime/onnxruntime/test/onnx/onnx_model_info.cc:45 void OnnxModelInfo::InitOnnxModelInfo(const PATH_CHAR_TYPE*) open file "yolov4/yolov4.onnx" failed: No such file or directory
Model: yolov4 - Device: CPU - Executor: Parallel
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: onnxruntime/onnxruntime/test/onnx/onnx_model_info.cc:45 void OnnxModelInfo::InitOnnxModelInfo(const PATH_CHAR_TYPE*) open file "yolov4/yolov4.onnx" failed: No such file or directory
ECP-CANDLE The CANDLE benchmark codes implement deep learning architectures relevant to problems in cancer. These architectures address problems at different biological scales, specifically problems at the molecular, cellular and population scales. Learn more via the OpenBenchmarking.org test page.
Benchmark: P3B2
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. E: ImportError: initialization failed
Benchmark: P3B1
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. E: ImportError: initialization failed
Benchmark: P1B2
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. E: ImportError: initialization failed
spaCy The spaCy library is an open-source solution for advanced neural language processing (NLP). The spaCy library leverages Python and is a leading neural language processing solution. This test profile times the spaCy CPU performance with various models. Learn more via the OpenBenchmarking.org test page.
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: TypeError: issubclass() arg 1 must be a class
Neural Magic DeepSparse Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Synchronous Single-Stream
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ValueError: No matching models found with stub: nlp/text_classification/bert-base/pytorch/huggingface/sst2/base-none.Please try another stub
Model: NLP Text Classification, BERT base uncased SST2 - Scenario: Asynchronous Multi-Stream
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ValueError: No matching models found with stub: nlp/text_classification/bert-base/pytorch/huggingface/sst2/base-none.Please try another stub
Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Synchronous Single-Stream
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ValueError: No matching models found with stub: nlp/question_answering/bert-base/pytorch/huggingface/squad/12layer_pruned90-none.Please try another stub
Model: NLP Question Answering, BERT base uncased SQuaD 12layer Pruned90 - Scenario: Asynchronous Multi-Stream
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ValueError: No matching models found with stub: nlp/question_answering/bert-base/pytorch/huggingface/squad/12layer_pruned90-none.Please try another stub
Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Synchronous Single-Stream
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ValueError: No matching models found with stub: nlp/sentiment_analysis/bert-base/pytorch/huggingface/sst2/12layer_pruned90-none.Please try another stub
Model: NLP Sentiment Analysis, 80% Pruned Quantized BERT Base Uncased - Scenario: Asynchronous Multi-Stream
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: ValueError: No matching models found with stub: nlp/sentiment_analysis/bert-base/pytorch/huggingface/sst2/12layer_pruned90-none.Please try another stub
TensorFlow This is a benchmark of the TensorFlow deep learning framework using the TensorFlow reference benchmarks (tensorflow/benchmarks with tf_cnn_benchmarks.py). Note with the Phoronix Test Suite there is also pts/tensorflow-lite for benchmarking the TensorFlow Lite binaries if desired for complementary metrics. Learn more via the OpenBenchmarking.org test page.
Device: CPU - Batch Size: 512 - Model: ResNet-50
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.
Device: CPU - Batch Size: 512 - Model: GoogLeNet
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.
Device: CPU - Batch Size: 256 - Model: ResNet-50
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status.
OpenBenchmarking.org images/sec, More Is Better TensorFlow 2.12 Device: CPU - Batch Size: 32 - Model: ResNet-50 Intel UHD 630 CML GT2 0.6638 1.3276 1.9914 2.6552 3.319 SE +/- 0.07, N = 9 2.95
Device: CPU - Batch Size: 512 - Model: VGG-16
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: Fatal Python error: Aborted
Device: CPU - Batch Size: 256 - Model: VGG-16
Intel UHD 630 CML GT2: The test quit with a non-zero exit status. The test quit with a non-zero exit status. The test quit with a non-zero exit status. E: Fatal Python error: Aborted
oneDNN This is a test of the Intel oneDNN as an Intel-optimized library for Deep Neural Networks and making use of its built-in benchdnn functionality. The result is the total perf time reported. Intel oneDNN was formerly known as DNNL (Deep Neural Network Library) and MKL-DNN before being rebranded as part of the Intel oneAPI toolkit. Learn more via the OpenBenchmarking.org test page.
Harness: Deconvolution Batch shapes_3d - Data Type: bf16bf16bf16 - Engine: CPU
Intel UHD 630 CML GT2: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
Harness: Deconvolution Batch shapes_1d - Data Type: bf16bf16bf16 - Engine: CPU
Intel UHD 630 CML GT2: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
Harness: Convolution Batch Shapes Auto - Data Type: bf16bf16bf16 - Engine: CPU
Intel UHD 630 CML GT2: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
OpenBenchmarking.org ms, Fewer Is Better oneDNN 3.3 Harness: Deconvolution Batch shapes_1d - Data Type: f32 - Engine: CPU Intel UHD 630 CML GT2 3 6 9 12 15 SE +/- 0.18, N = 13 10.44 MIN: 9.87 1. (CXX) g++ options: -O3 -march=native -fopenmp -msse4.1 -fPIC -pie -lpthread -ldl
Harness: IP Shapes 3D - Data Type: bf16bf16bf16 - Engine: CPU
Intel UHD 630 CML GT2: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
Harness: IP Shapes 1D - Data Type: bf16bf16bf16 - Engine: CPU
Intel UHD 630 CML GT2: The test run did not produce a result. The test run did not produce a result. The test run did not produce a result.
Intel UHD 630 CML GT2 Processor: Intel Core i3-10100 @ 4.30GHz (4 Cores / 8 Threads), Motherboard: ASRock H510M-HVS (P1.60 BIOS), Chipset: Intel Device 43ef, Memory: 3584MB, Disk: 1000GB Western Digital WDS100T2B0A, Graphics: Intel UHD 630 CML GT2 3GB (1100MHz), Audio: Realtek ALC897, Monitor: G185BGEL01, Network: Realtek RTL8111/8168/8411
OS: Ubuntu 20.04, Kernel: 5.15.0-88-generic (x86_64), Desktop: GNOME Shell 3.36.9, Display Server: X Server 1.20.13, OpenGL: 4.6 Mesa 21.2.6, Vulkan: 1.2.182, Compiler: GCC 9.4.0, File-System: ext4, Screen Resolution: 1368x768
Kernel Notes: Transparent Huge Pages: madviseCompiler Notes: --build=x86_64-linux-gnu --disable-vtable-verify --disable-werror --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++,gm2 --enable-libstdcxx-debug --enable-libstdcxx-time=yes --enable-multiarch --enable-multilib --enable-nls --enable-objc-gc=auto --enable-offload-targets=nvptx-none=/build/gcc-9-9QDOt0/gcc-9-9.4.0/debian/tmp-nvptx/usr,hsa --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_pstate powersave (EPP: balance_performance) - CPU Microcode: 0xf8 - Thermald 1.9.1Python Notes: Python 3.8.10Security Notes: gather_data_sampling: Mitigation of Microcode + itlb_multihit: KVM: Mitigation of VMX disabled + l1tf: Not affected + mds: Not affected + meltdown: Not affected + mmio_stale_data: Mitigation of Clear buffers; SMT vulnerable + retbleed: Mitigation of Enhanced IBRS + spec_rstack_overflow: Not affected + spec_store_bypass: Mitigation of SSB disabled via prctl and seccomp + spectre_v1: Mitigation of usercopy/swapgs barriers and __user pointer sanitization + spectre_v2: Mitigation of Enhanced IBRS IBPB: conditional RSB filling PBRSB-eIBRS: SW sequence + srbds: Mitigation of Microcode + tsx_async_abort: Not affected
Testing initiated at 21 November 2023 08:25 by user hertz.