AI on the Edge: Characterizing AI-based IoT Applications Using Specialized Edge Architectures
AI on the Edge: Characterizing AI-based IoT Applications Using Specialized Edge Architectures
复制标题
DOI：
10.1109/iiswc50251.2020.00023
复制
发表时间：
2020-10
期刊：
影响因子：
--
通讯作者：
Qianlin Liang;Prashant J. Shenoy;David E. Irwin
中科院分区：
文献类型：
--
作者：
Qianlin Liang;Prashant J. Shenoy;David E. Irwin
边缘计算已经成为支持低延迟或高带宽需求的移动和物联网应用的流行范例。边缘计算的吸引力已经进一步增强，由于最近可用的专用硬件来加速特定的计算任务，如深度学习推理，在边缘节点上。在本文中，我们通过实验比较了使用使用边缘加速器构建的专用边缘系统与更传统形式的边缘和云计算的优点和局限性。我们使用基于边缘的人工智能工作负载的实验研究表明，与传统的边缘和云服务器相比，今天的边缘加速器在功率或成本标准化时可以提供相当的性能，在许多情况下甚至更好。当使用模型压缩或模型分割时，它们还为跨层和层内的分割处理提供延迟和带宽优势，但需要动态方法来确定最佳的跨层分割。我们发现边缘加速器可以支持多租户推理应用程序的不同程度的并发性，但缺乏边缘云多租户托管所需的隔离机制。
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.