J. Fridman et Es. Manolakos, Distributed memory parallel architecture based on modular linear arrays for 2-D separable transforms computation, J VLSI S P, 28(3), 2001, pp. 187-203
Citations number
36
Categorie Soggetti
Eletrical & Eletronics Engineeing
Journal title
JOURNAL OF VLSI SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY
A framework for mapping systematically 2-dimensional (2-D) separable transf
orms into a parallel architecture consisting of fully pipelined linear arra
y stages is presented. The resulting model architecture is characterized by
its generality, high degree of modularity, high throughput, and the exclus
ive use of distributed memory and control. There is no central shared memor
y block to facilitate the transposition of intermediate results, as it is c
ommonly the case in row-column image processing architectures. Avoiding sha
red central memory has positive implications for speed, area, power dissipa
tion and scalability of the architecture. The architecture presented here m
ay be used to realize any separable 2-D transform by only changing the coef
ficients stored in the processing elements. Pipelined linear arrays for com
puting the 2-D Discrete Fourier Transform and 2-D separable convolution are
presented as examples and their performance is evaluated.