MoDNN: Local distributed mobile computing system for Deep Neural Network.
DATE(2017)
摘要
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×. 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.
更多查看译文
关键词
MoDNN,local distributed mobile computing system for deep neural network,resource-constrained devices,mobile platforms,client-server computing paradigm,DNN model compression,local distributed mobile computing system,mobile devices,DNN computations,device-level computing cost,memory usage,nonparallel data delivery time minimization,2D-grid partition,parallel execution,transmission time,wakeup time
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要