MoDNN: Local Distributed Mobile Computing System for Deep Neural Network
Jiachen Mao1, Xiang Chen2, Kent W. Nixon1, Christopher Krieger3 and Yiran Chen1
1University of Pittsburgh, USA.
ajim35@pitt.edu
bkwn2@pitt.edu
cyic52@pitt.edu
2George Mason University, USA.
xchen26@gmu.edu
3qUniversity of Maryland, USA.
Krieger@lps.umd.edu
ABSTRACT
Although Deep Neural Networks (DNN) are ubiquitously utilized in many applications, it is generally difficult to deploy DNNs on resource-constrained devices, e.g., mobile platforms. Some existing attempts mainly focus on client-server computing paradigm or DNN model compression, which require either infrastructure supports or special training phases, respectively. In this work, we propose MoDNN - a local distributed mobile computing system for DNN applications. MoDNN can partition already trained DNN models onto several mobile devices to accelerate DNN computations by alleviating device-level computing cost and memory usage. Two model partition schemes are also designed to minimize non-parallel data delivery time, including both wakeup time and transmission time. Experimental results show that when the number of worker nodes increases from 2 to 4, MoDNN can accelerate the DNN computation by 2.17-4.28 38 215. Besides the parallel execution, the performance speedup also partially comes from the reduction of the data delivery time, e.g., 30.02% w.r.t. conventional 2D-grids partition.
