Benchmarking Modern Edge Devices for AI Applications

• Published in: IEICE Transactions on Information and Systems Vol. E104.D; no. 3; pp. 394 - 403
• Main Authors: JO, Jongmin, KANG, Pilsung
• Format: Journal Article
• Language: English
• Published: Tokyo The Institute of Electronics, Information and Communication Engineers 01.03.2021; Japan Science and Technology Agency
• Subjects: Artificial intelligence; deep learning; Edge computing; GPU (graphics processing unit); Graphics processing units; Hardware; performance benchmark; TPU (tensor processing unit)
• ISSN: 0916-8532; 1745-1361
• DOI: 10.1587/transinf.2020EDP7160

AI (artificial intelligence) has grown at an overwhelming speed for the last decade, to the extent that it has become one of the mainstream tools that drive the advancements in science and technology. Meanwhile, the paradigm of edge computing has emerged as one of the foremost areas in which applications using the AI technology are being most actively researched, due to its potential benefits and impact on today's widespread networked computing environments. In this paper, we evaluate two major entry-level offerings in the state-of-the-art edge device technology, which highlight increased computing power and specialized hardware support for AI applications. We perform a set of deep learning benchmarks on the devices to measure their performance. By comparing the performance with other GPU (graphics processing unit) accelerated systems in different platforms, we assess the computational capability of the modern edge devices featuring a significant amount of hardware parallelism.