Paper Info
Title
AI on the Edge: Characterizing AI-based IoT Applications Using Specialized Edge Architectures
Abstract
Edge computing has emerged as a popular paradigm for supporting mobile and IoT applications with low latency or high bandwidth needs. The attractiveness of edge computing has been further enhanced due to the recent availability of special-purpose hardware to accelerate specific compute tasks, such as deep learning inference, on edge nodes. In this paper, we experimentally compare the benefits and limitations of using specialized edge systems, built using edge accelerators, to more traditional forms of edge and cloud computing. Our experimental study using edge-based AI workloads shows that today's edge accelerators can provide comparable, and in many cases better, performance, when normalized for power or cost, than traditional edge and cloud servers. They also provide latency and bandwidth benefits for split processing, across and within tiers, when using model compression or model splitting, but require dynamic methods to determine the optimal split across tiers. We find that edge accelerators can support varying degrees of concurrency for multi-tenant inference applications, but lack isolation mechanisms necessary for edge cloud multi-tenant hosting.
Year
DOI
Venue
2020
10.1109/IISWC50251.2020.00023
2020 IEEE International Symposium on Workload Characterization (IISWC)
Keywords
DocType
ISBN
specialized edge architectures,edge computing,mobile IoT applications,special-purpose hardware,specific compute tasks,edge nodes,specialized edge systems,edge accelerators,cloud computing,edge-based AI workloads,edge servers,multitenant inference applications,edge cloud multitenant hosting,AI-based IoT applications,deep learning inference,cloud servers,split processing,model compression,model splitting,dynamic methods
Conference
978-1-7281-7646-8
Citations 
PageRank 
References 
0
0.34
3
Authors
3
Name
Order
Citations
PageRank
Qianlin Liang100.34
Prashant J. Shenoy26386521.30
David E. Irwin389998.12