MeDNN: A distributed mobile system with enhanced partition and deployment for large-scale DNNs
Authors:
- 1 November 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 751-756
Abstract
Deep Neural Networks (DNNs) are pervasively used in a significant number of applications and platforms. To enhance the execution efficiency of large-scale DNNs, previous attempts focus mainly on client-server paradigms, relying on powerful external infrastructure, or model compression, with complicated pre-processing phases. Though effective, these methods overlook the optimization of DNNs on distributed mobile devices. In this work, we design and implement MeDNN, a local distributed mobile computing system with enhanced partitioning and deployment tailored for large-scale DNNs. In MeDNN, we first propose Greedy Two Dimensional Partition (GTDP), which can adaptively partition DNN models onto several mobile devices w.r.t. individual resource constraints. We also propose Structured Model Compact Deployment (SMCD), a mobile-friendly compression scheme which utilizes a structured sparsity pruning technique to further accelerate DNN execution. Experimental results show that, GTDP can accelerate the original DNN execution time by 1.86-2.44x with 2-4 worker nodes. By utilizing SMCD, 26.5% of additional computing time and 14.2% of extra communication time are saved, on average, with negligible effect on the model accuracy.Keywords
This publication has 10 references indexed in Scilit:
- MoDNN: Local distributed mobile computing system for Deep Neural Network2017
- Going Deeper with Embedded FPGA Platform for Convolutional Neural Network2016
- Learning the Structure of Deep Convolutional Networks2015
- Going deeper with convolutions2015
- Integrated Imaging and Vision Techniques for Industrial Inspection2015
- Caffe2014
- Scaling Distributed Machine Learning with the Parameter Server2014
- MapReduceCommunications of the ACM, 2008
- Open MPI: Goals, Concept, and Design of a Next Generation MPI Implementation2004
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998