Full-Text Search:
Home|About CNKI|User Service|中文
Add to Favorite Get Latest Update

Implementing Dynamical Pattern Recognition Algorithm on GPU

LIN Wen-yu,WANG Cong(School of Automation Science & Engineering,South China University of Technology,Guangzhou 510640,China)  
This paper presents an implementation of the rapid dynamical pattern recognition algorithm on the GPU platform.GPGPU has emerged as a powerful computation device for its particular parallel architecture,and the massive parallel computing technology based on GPU is considered to be a suitable method dealing with the large scale computation the algorithm brings.In this paper,the rapid dynamical pattern recognition algorithm is briefly introduced,the main computing problems are discussed,and the detailed procedure of parallelizing the algorithm to the Jacket platform is presented.Specific experiments are made and the results indicate that the parallelized algorithm running on GPU has huge speed-ups compared with the old serial versions on CPU and the efficiency of the parallelized algorithm has practical engineering value.
Download(CAJ format) Download(PDF format)
CAJViewer7.0 supports all the CNKI file formats; AdobeReader only supports the PDF format.
©CNKI All Rights Reserved