Framework design of reconfigurable convolution neural network acceleration system for edge computing

Yibing Liao; Yu Wang; Yuxuan Zhao; Chengyu Zhang; Bende Xiao; Jiamei Yang; Hui Wang; Jiaxuan Li

doi:10.1117/12.2684680

21 July 2023 Framework design of reconfigurable convolution neural network acceleration system for edge computing

Yibing Liao, Yu Wang, Yuxuan Zhao, Chengyu Zhang, Bende Xiao, Jiamei Yang, Hui Wang, Jiaxuan Li

Proceedings Volume 12717, 3rd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2023); 127172B (2023) https://doi.org/10.1117/12.2684680
Event: 3rd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2023), 2023, Wuhan, China

Abstract

In this paper, we propose a reconfigurable framework optimized for resource-constrained platforms to accelerate CNNs using the high concurrency and data-proximate characteristics of edge computing devices. The framework is designed from three aspects: control flow, data flow, and storage flow. To address the impact of memory access cost on network computation efficiency, we introduce a parallel ping-pong data scheduling framework to compensate for it. Experimental results show that the system can support convolutional kernel operations of any size under structural constraints, and the computational efficiency is improved 2.28 times compared to CNN acceleration systems based on traditional data scheduling schemes.

Citation Download Citation

Yibing Liao, Yu Wang, Yuxuan Zhao, Chengyu Zhang, Bende Xiao, Jiamei Yang, Hui Wang, and Jiaxuan Li "Framework design of reconfigurable convolution neural network acceleration system for edge computing", Proc. SPIE 12717, 3rd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2023), 127172B (21 July 2023); https://doi.org/10.1117/12.2684680

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available