Benchmarking Modern Edge Devices for AI Applications

Pilsung KANG; Jongmin JO

doi:10.1587/transinf.2020EDP7160

Benchmarking Modern Edge Devices for AI Applications

Pilsung KANG, Jongmin JO

Full Text Views

0

Cite this

Summary :

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.

Publication: IEICE TRANSACTIONS on Information Vol.E104-D No.3 pp.394-403

Publication Date: 2021/03/01

Publicized: 2020/12/08

Online ISSN: 1745-1361

DOI: 10.1587/transinf.2020EDP7160

Type of Manuscript: PAPER

Category: Computer System

Authors

Pilsung KANG
Sun Moon University
Jongmin JO
Sun Moon University

Keyword

edge computing, deep learning, performance benchmark, GPU (graphics processing unit), TPU (tensor processing unit)

Cite this

Copy

Pilsung KANG, Jongmin JO, "Benchmarking Modern Edge Devices for AI Applications" in IEICE TRANSACTIONS on Information, vol. E104-D, no. 3, pp. 394-403, March 2021, doi: 10.1587/transinf.2020EDP7160.
Abstract: 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.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020EDP7160/_p

Copy

@ARTICLE{e104-d_3_394,
author={Pilsung KANG, Jongmin JO, },
journal={IEICE TRANSACTIONS on Information},
title={Benchmarking Modern Edge Devices for AI Applications},
year={2021},
volume={E104-D},
number={3},
pages={394-403},
abstract={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.},
keywords={},
doi={10.1587/transinf.2020EDP7160},
ISSN={1745-1361},
month={March},}

Copy

TY - JOUR
TI - Benchmarking Modern Edge Devices for AI Applications
T2 - IEICE TRANSACTIONS on Information
SP - 394
EP - 403
AU - Pilsung KANG
AU - Jongmin JO
PY - 2021
DO - 10.1587/transinf.2020EDP7160
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 3
JA - IEICE TRANSACTIONS on Information
Y1 - March 2021
AB - 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.
ER -