Summary

International Symposium on Nonlinear Theory and Its Applications

2015

Session Number:A2L-E

Session:

Number:A2L-E-3

GPU Implementation of Asynchronous Discrete-Time Cellular Neural Networks

Kenichiro Tanaka,  Yuichi Tanji,  

pp.81-84

Publication Date:2015/12/1

Online ISSN:2188-5079

DOI:10.34385/proc.47.A2L-E-3

PDF download (431.9KB)

Summary:
GPU implementation of asynchronous type of discrete-time cellular neural networks for image processing is presented. To accelerate the operation, the parallel computation scheme for updating the cells of networks is provided. Furthermore, the techniques that utilize shared memory of GPU are presented in order to speed up further. In illustrative examples, we compare the performance of GPU implementation with CPU and confirm its efficiency.