Cited 0 time in webofscience Cited 0 time in scopus

A Study on Energy-Process-Latency Tradeoff in Embedded Artificial Intelligence

Title
A Study on Energy-Process-Latency Tradeoff in Embedded Artificial Intelligence
Authors
Kim, JinhwiGalanopoulos, ApostolosJoseph, Jude VivekKwak, Jeongho
DGIST Authors
Kwak, Jeongho
Issue Date
2020-10-21
Citation
11th International Conference on Information and Communication Technology Convergence, ICTC 2020, 22-24
Type
Conference
ISBN
9781728167589
ISSN
2162-1233
Abstract
In this paper, we explore an impact of GPU/CPU scaling of a state-of-the-art AI embedded device on its energy consumption and AI performance. We use Nvidia Jetson TX2 as an experiment device thanks to its tractability to scale GPU/CPU and modify AI framework and libraries. Via extensive experiment in various ML (Machine Learning) scenarios, i.e., face recognition and objective detection, we demonstrate a clear tradeoff between GPU/CPU scaling, energy consumption (of GPU/CPU as well as entire device) and training/inference speed. Finally, we envision a future work aiming to optimize processing and networking resources simultaneously at an extended scenario that multiple AI embedded devices cooperate with each other for a common AI application. © 2020 IEEE.
URI
http://hdl.handle.net/20.500.11750/12888
DOI
10.1109/ICTC49870.2020.9289270
Publisher
IEEE Computer Society
Related Researcher
  • Author Kwak, Jeongho Intelligent Computing & Networking Laboratory
  • Research Interests 클라우드 컴퓨팅; 엣지컴퓨팅; 네트워크 자원관리; 모바일 시스템
Files:
There are no files associated with this item.
Collection:
Department of Information and Communication EngineeringIntelligent Computing & Networking Laboratory2. Conference Papers


qrcode mendeley

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

BROWSE