Paper
4 April 1986 A Systolic Architecture For High-Speed Two-Dimensional Convolutions In Finite-Field Arithmetic
Harold A. Klotz Jr.
Author Affiliations +
Abstract
A two-dimensional linear-convolution algorithm is presented which couples the efficiency of the polynomial transform convolution-algorithm with the parallelism of finite-field arithmetic. This algorithm requires fewer arithmetic operations than most two-dimensional convolution algorithms, and possesses a structure which facilitates systolic architectures. Forming the polynomial transform in a finite field allows large numbers to be broken into small residues, each of which may be processed in parallel. A systolic architecture is described which may be used to evaluate two-dimensional convolutions in 0(N) processor cycles. This architecture is comprised of engagement processors, to form the polynomial transform, and pipelined processors, to form the polynomial product.
© (1986) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Harold A. Klotz Jr. "A Systolic Architecture For High-Speed Two-Dimensional Convolutions In Finite-Field Arithmetic", Proc. SPIE 0696, Advanced Algorithms and Architectures for Signal Processing I, (4 April 1986); https://doi.org/10.1117/12.936890
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Convolution

Image filtering

Signal processing

Fourier transforms

Filtering (signal processing)

Reconstruction algorithms

Parallel computing

Back to Top