Cited 0 time in
Cited 0 time in
A Study on Energy-Process-Latency Tradeoff in Embedded Artificial Intelligence
- A Study on Energy-Process-Latency Tradeoff in Embedded Artificial Intelligence
- Kim, Jinhwi; Galanopoulos, Apostolos; Joseph, Jude Vivek; Kwak, Jeongho
- DGIST Authors
- Kwak, Jeongho
- Issue Date
- 11th International Conference on Information and Communication Technology Convergence, ICTC 2020, 22-24
- 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.
- IEEE Computer Society
- Related Researcher
Intelligent Computing & Networking Laboratory
클라우드 컴퓨팅; 엣지컴퓨팅; 네트워크 자원관리; 모바일 시스템
There are no files associated with this item.
- Department of Information and Communication EngineeringIntelligent Computing & Networking Laboratory2. Conference Papers
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.