Chapter 1: Invited Addresses and Tutorials on Signals, Coding,
  Systems and Intelligent Techniques

Title: A Distributed Arithmetic Architecture for Fast Implementation of Vector or Matrix Products

Author(s): Grigoris Grigoriadis, Yiannis Boutalis, Basil Mertzios

Address: Department of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece | Department of Electrical and Computer Engineering, Democritus University of Thrace, Xanthi, Greece | Department of Automation, Laboratory of Control Systems and Comp. Intell. Thessaloniki Institute of Technology, Thessaloniki, Greece

Reference: 12th International Workshop on Systems, Signals and Image Processing pp. 165 - 169

Abstract/Summary: Fast implementations of the inner product of two (nx1) vectors, of the (nxn) MVM (matrix vector multiplication) operation and (nxn) MMM (matrix matrix multiplication) operation are of paramount importance in many research fields such as signal processing, control systems and robotics. So far, the proposed distributed arithmetic (DA) architectures provide fast implementation of such products, but they require that the elements of one of the vectors contain constant a-priori known values. In this paper we propose a new general purpose DA architecture which considers that both vector or matrix elements are variable. The block diagram of the proposed hardware design is given and its performance is theoretically estimated.

Order a copy of this article