Performance optimization for pattern recognition using associative neural memory

Author

Wu, Qing ; Mukre, Prakash ; Linderman, Richard ; Renz, Tom ; Burns, Daniel ; Moore, Michael ; Qiu, Qinru

Author_Institution

Dept. of Electr. & Comput. Eng., Binghamton Univ., Binghamton, NY

fYear

2008

fDate

June 23 2008-April 26 2008

Firstpage

1

Lastpage

4

Abstract

In this paper, we present our work in the implementation and performance optimization of the recall operation of the brain-state-in-a-box (BSB) model on the cell broadband engine processor. We have applied optimization techniques on different parts of the algorithm to improve the overall computing and communication performance of the BSB recall algorithm. Runtime measurements show that, we have been able to achieve about 70% of the theoretical peak performance of the processor.

Keywords

content-addressable storage; microprocessor chips; neural chips; optimisation; pattern recognition; BSB recall algorithm; associative neural memory; brain-state-in-a-box model; cell broadband engine processor; optimization techniques; pattern recognition; recall operation; Bandwidth; Brain modeling; Computer architecture; Engines; High performance computing; Large-scale systems; Mathematical model; Optimization; Pattern recognition; Samarium;

fLanguage

English

Publisher

ieee

Conference_Titel

Multimedia and Expo, 2008 IEEE International Conference on

Conference_Location

Hannover

Print_ISBN

978-1-4244-2570-9

Electronic_ISBN

978-1-4244-2571-6

Type

conf

DOI

10.1109/ICME.2008.4607356

Filename

4607356