Implementing algorithms for convolution on arrays of adders

Robert Michael Owens, Mary Jane Irwin

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

The authors consider the problem of developing VLSI signal processors for computing convolutions. Convolutions can be efficiently computed by VLSI processors that consist of arrays of adders when they are stated in terms of matrices with elements consisting of only 1, 0, or -1. Unfortunately, when stated in matrix form the published algorithms have matrices with elements other than 1, 0, or -1. The authors explore why this occurs and show how it can be prevented when an algorithm is developed. If this fails, they propose a technique for addressing this problem that consists of replacing each such matrix by the product of two or more matrices whose elements are 1, 0, or -1.

Original languageEnglish (US)
Pages (from-to)1127-1130
Number of pages4
JournalProceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing
Volume2
StatePublished - 1989

Fingerprint

Adders
Convolution
convolution integrals
matrices
very large scale integration
central processing units
products

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Electrical and Electronic Engineering
  • Acoustics and Ultrasonics

Cite this

@article{bccd522b963e49bf93b4237b470f0671,
title = "Implementing algorithms for convolution on arrays of adders",
abstract = "The authors consider the problem of developing VLSI signal processors for computing convolutions. Convolutions can be efficiently computed by VLSI processors that consist of arrays of adders when they are stated in terms of matrices with elements consisting of only 1, 0, or -1. Unfortunately, when stated in matrix form the published algorithms have matrices with elements other than 1, 0, or -1. The authors explore why this occurs and show how it can be prevented when an algorithm is developed. If this fails, they propose a technique for addressing this problem that consists of replacing each such matrix by the product of two or more matrices whose elements are 1, 0, or -1.",
author = "Owens, {Robert Michael} and Irwin, {Mary Jane}",
year = "1989",
language = "English (US)",
volume = "2",
pages = "1127--1130",
journal = "Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing",
issn = "0736-7791",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

Implementing algorithms for convolution on arrays of adders. / Owens, Robert Michael; Irwin, Mary Jane.

In: Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing, Vol. 2, 1989, p. 1127-1130.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Implementing algorithms for convolution on arrays of adders

AU - Owens, Robert Michael

AU - Irwin, Mary Jane

PY - 1989

Y1 - 1989

N2 - The authors consider the problem of developing VLSI signal processors for computing convolutions. Convolutions can be efficiently computed by VLSI processors that consist of arrays of adders when they are stated in terms of matrices with elements consisting of only 1, 0, or -1. Unfortunately, when stated in matrix form the published algorithms have matrices with elements other than 1, 0, or -1. The authors explore why this occurs and show how it can be prevented when an algorithm is developed. If this fails, they propose a technique for addressing this problem that consists of replacing each such matrix by the product of two or more matrices whose elements are 1, 0, or -1.

AB - The authors consider the problem of developing VLSI signal processors for computing convolutions. Convolutions can be efficiently computed by VLSI processors that consist of arrays of adders when they are stated in terms of matrices with elements consisting of only 1, 0, or -1. Unfortunately, when stated in matrix form the published algorithms have matrices with elements other than 1, 0, or -1. The authors explore why this occurs and show how it can be prevented when an algorithm is developed. If this fails, they propose a technique for addressing this problem that consists of replacing each such matrix by the product of two or more matrices whose elements are 1, 0, or -1.

UR - http://www.scopus.com/inward/record.url?scp=0024945032&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024945032&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:0024945032

VL - 2

SP - 1127

EP - 1130

JO - Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

JF - Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing

SN - 0736-7791

ER -