A functional memory type parallel processor for vector quantization

Author

Kobayashi, K. ; Kinoshita, M. ; Takeuchi, M. ; Onodera, H. ; Tamaru, K.

Author_Institution

Dept. of Electron. & Commun., Kyoto Univ., Japan

fYear

1997

fDate

28-31 Jan 1997

Firstpage

665

Lastpage

666

Abstract

We propose a memory-based parallel processor for vector quantization, called a functional memory type parallel processor for vector quantization (FMPP-VQ). It accelerates the nearest neighbour search of vector quantization. All distances between an input vector and reference vectors in a codebook are computed simultaneously in all PEs. The minimum value of all distances is searched in parallel. The nearest vector is obtained in O(k), where k stands for the dimension of vectors. An LSI including four PEs has been implemented. It operates at 25 MHz clock frequency

Keywords

CMOS memory circuits; computational complexity; digital signal processing chips; image coding; large scale integration; parallel architectures; vector quantisation; CMOS IC; LSI; codebook; computational complexity; functional memory type parallel processor; nearest neighbour search; processing elements; vector quantization; Acceleration; Clocks; Costs; Frequency; Hardware; Image coding; Large scale integration; Logic; Nearest neighbor searches; Vector quantization;

fLanguage

English

Publisher

ieee

Conference_Titel

Design Automation Conference, 1997. Proceedings of the ASP-DAC '97 Asia and South Pacific

Conference_Location

Chiba

Print_ISBN

0-7803-3662-3

Type

conf

DOI

10.1109/ASPDAC.1997.600354

Filename

600354