Xeon E NN Intel Xeon E-2288G testing with a Compulab SBC-ATCFL v1.2 (ATOP3.PRD.0.29.2 BIOS) and NVIDIA Quadro RTX 4000 8GB on Ubuntu 19.10 via the Phoronix Test Suite.
HTML result view exported from: https://openbenchmarking.org/result/2009244-FI-XEONENN7631&grw&sro&rro .
Xeon E NN Processor Motherboard Chipset Memory Disk Graphics Audio Monitor Network OS Kernel Desktop Display Server Display Driver Compiler File-System Screen Resolution 1 2 3 Intel Xeon E-2288G @ 5.00GHz (8 Cores / 16 Threads) Compulab SBC-ATCFL v1.2 (ATOP3.PRD.0.29.2 BIOS) Intel Cannon Lake PCH 2 x 32 GB DDR4-2667MT/s Samsung M378A4G43MB1-CTD Samsung SSD 970 EVO Plus 250GB NVIDIA Quadro RTX 4000 8GB Intel Cannon Lake PCH cAVS VE228 Intel I219-LM + Intel I210 Ubuntu 19.10 5.3.0-64-generic (x86_64) GNOME Shell 3.34.1 X Server 1.20.5 modesetting 1.20.5 GCC 11.0.0 20200924 ext4 1920x1080 OpenBenchmarking.org Compiler Details - --disable-multilib --enable-checking=release --enable-languages=c,c++,fortran Processor Details - Scaling Governor: intel_pstate powersave - CPU Microcode: 0xd6 Security Details - itlb_multihit: KVM: Mitigation of Split huge pages + l1tf: Not affected + mds: Not affected + meltdown: 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 + srbds: Mitigation of TSX disabled + tsx_async_abort: Mitigation of TSX disabled
Xeon E NN tnn: CPU - MobileNet v2 tnn: CPU - SqueezeNet v1.1 ncnn: CPU - squeezenet ncnn: CPU - mobilenet ncnn: CPU-v2-v2 - mobilenet-v2 ncnn: CPU-v3-v3 - mobilenet-v3 ncnn: CPU - shufflenet-v2 ncnn: CPU - mnasnet ncnn: CPU - efficientnet-b0 ncnn: CPU - blazeface ncnn: CPU - googlenet ncnn: CPU - vgg16 ncnn: CPU - resnet18 ncnn: CPU - alexnet ncnn: CPU - resnet50 ncnn: CPU - yolov4-tiny 1 2 3 279.012 268.469 29.76 18.95 5.32 4.19 3.20 4.22 6.68 1.64 48.63 108.54 24.48 15.08 107.84 28.69 279.040 268.466 30.21 19.18 5.43 4.31 3.42 4.19 6.65 1.58 50.07 109.08 24.71 15.15 108.74 28.89 278.770 268.480 30.24 19.00 5.39 4.25 3.25 4.27 6.70 1.59 49.07 108.70 24.52 15.02 107.99 28.90 OpenBenchmarking.org
TNN Target: CPU - Model: MobileNet v2 OpenBenchmarking.org ms, Fewer Is Better TNN 0.2.3 Target: CPU - Model: MobileNet v2 3 2 1 60 120 180 240 300 SE +/- 0.18, N = 3 SE +/- 0.37, N = 3 SE +/- 0.57, N = 3 278.77 279.04 279.01 MIN: 277.88 / MAX: 291.39 MIN: 278.11 / MAX: 280.17 MIN: 277.84 / MAX: 282.46 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
TNN Target: CPU - Model: SqueezeNet v1.1 OpenBenchmarking.org ms, Fewer Is Better TNN 0.2.3 Target: CPU - Model: SqueezeNet v1.1 3 2 1 60 120 180 240 300 SE +/- 0.11, N = 3 SE +/- 0.03, N = 3 SE +/- 0.15, N = 3 268.48 268.47 268.47 MIN: 267.85 / MAX: 273.07 MIN: 267.98 / MAX: 272.63 MIN: 267.85 / MAX: 274.55 1. (CXX) g++ options: -fopenmp -pthread -fvisibility=hidden -O3 -rdynamic -ldl
NCNN Target: CPU - Model: squeezenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: squeezenet 3 2 1 7 14 21 28 35 SE +/- 0.36, N = 3 SE +/- 0.13, N = 3 SE +/- 0.13, N = 3 30.24 30.21 29.76 MIN: 29.47 / MAX: 33.06 MIN: 29.85 / MAX: 34.27 MIN: 29.17 / MAX: 30.5 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mobilenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: mobilenet 3 2 1 5 10 15 20 25 SE +/- 0.09, N = 3 SE +/- 0.09, N = 3 SE +/- 0.05, N = 3 19.00 19.18 18.95 MIN: 18.71 / MAX: 22.64 MIN: 18.83 / MAX: 21.83 MIN: 18.74 / MAX: 19.4 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v2-v2 - Model: mobilenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU-v2-v2 - Model: mobilenet-v2 3 2 1 1.2218 2.4436 3.6654 4.8872 6.109 SE +/- 0.13, N = 3 SE +/- 0.15, N = 3 SE +/- 0.11, N = 3 5.39 5.43 5.32 MIN: 5.02 / MAX: 14.79 MIN: 5.03 / MAX: 6.02 MIN: 5.02 / MAX: 5.64 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU-v3-v3 - Model: mobilenet-v3 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU-v3-v3 - Model: mobilenet-v3 3 2 1 0.9698 1.9396 2.9094 3.8792 4.849 SE +/- 0.10, N = 3 SE +/- 0.16, N = 3 SE +/- 0.10, N = 3 4.25 4.31 4.19 MIN: 3.98 / MAX: 5.83 MIN: 3.99 / MAX: 4.66 MIN: 3.94 / MAX: 4.52 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: shufflenet-v2 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: shufflenet-v2 3 2 1 0.7695 1.539 2.3085 3.078 3.8475 SE +/- 0.11, N = 3 SE +/- 0.16, N = 3 SE +/- 0.12, N = 3 3.25 3.42 3.20 MIN: 2.97 / MAX: 3.73 MIN: 2.99 / MAX: 3.81 MIN: 2.92 / MAX: 3.58 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: mnasnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: mnasnet 3 2 1 0.9608 1.9216 2.8824 3.8432 4.804 SE +/- 0.17, N = 3 SE +/- 0.10, N = 3 SE +/- 0.14, N = 3 4.27 4.19 4.22 MIN: 3.89 / MAX: 5.78 MIN: 3.91 / MAX: 5.18 MIN: 3.83 / MAX: 13.89 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: efficientnet-b0 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: efficientnet-b0 3 2 1 2 4 6 8 10 SE +/- 0.17, N = 3 SE +/- 0.15, N = 3 SE +/- 0.16, N = 3 6.70 6.65 6.68 MIN: 6.31 / MAX: 7.08 MIN: 6.29 / MAX: 9.12 MIN: 6.32 / MAX: 8.01 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: blazeface OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: blazeface 3 2 1 0.369 0.738 1.107 1.476 1.845 SE +/- 0.05, N = 3 SE +/- 0.05, N = 3 SE +/- 0.04, N = 3 1.59 1.58 1.64 MIN: 1.47 / MAX: 3.34 MIN: 1.46 / MAX: 1.85 MIN: 1.55 / MAX: 1.79 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: googlenet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: googlenet 3 2 1 11 22 33 44 55 SE +/- 1.18, N = 3 SE +/- 0.39, N = 3 SE +/- 0.92, N = 3 49.07 50.07 48.63 MIN: 46.27 / MAX: 59.36 MIN: 48.83 / MAX: 58.78 MIN: 45.43 / MAX: 54.28 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: vgg16 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: vgg16 3 2 1 20 40 60 80 100 SE +/- 0.14, N = 3 SE +/- 0.36, N = 3 SE +/- 0.26, N = 3 108.70 109.08 108.54 MIN: 107.81 / MAX: 117.8 MIN: 108 / MAX: 117.74 MIN: 107.59 / MAX: 117.87 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet18 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: resnet18 3 2 1 6 12 18 24 30 SE +/- 0.08, N = 3 SE +/- 0.01, N = 3 SE +/- 0.04, N = 3 24.52 24.71 24.48 MIN: 24.18 / MAX: 25.92 MIN: 24.31 / MAX: 26.77 MIN: 24.17 / MAX: 27.76 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: alexnet OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: alexnet 3 2 1 4 8 12 16 20 SE +/- 0.02, N = 3 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 15.02 15.15 15.08 MIN: 14.93 / MAX: 17.58 MIN: 14.99 / MAX: 22.08 MIN: 14.95 / MAX: 17.24 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: resnet50 OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: resnet50 3 2 1 20 40 60 80 100 SE +/- 0.19, N = 3 SE +/- 0.19, N = 3 SE +/- 0.24, N = 3 107.99 108.74 107.84 MIN: 107.34 / MAX: 117.6 MIN: 108 / MAX: 118.14 MIN: 107.04 / MAX: 116.56 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
NCNN Target: CPU - Model: yolov4-tiny OpenBenchmarking.org ms, Fewer Is Better NCNN 20200916 Target: CPU - Model: yolov4-tiny 3 2 1 7 14 21 28 35 SE +/- 0.02, N = 3 SE +/- 0.04, N = 3 SE +/- 0.05, N = 3 28.90 28.89 28.69 MIN: 28.49 / MAX: 36.56 MIN: 28.68 / MAX: 38.45 MIN: 28.44 / MAX: 32.79 1. (CXX) g++ options: -O3 -rdynamic -lgomp -lpthread
Phoronix Test Suite v10.8.5