Digit pipelined processors

Mary Jane Irwin, Robert Michael Owens

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Digit serial data transmission can be used to an advantage in the design of special purpose processors where communication issues dominate and where digit pipelining can be used to maintain high data rates. VLSI signal processing applications are one such problem domain. We have developed a family of VLSI components that have digit serial transmission and that can be pipelined at the digit level. These components can be used to construct VLSI processors that are especially suited to signal processing applications. One such particularly attractive processor is a structure we call the arithmetic cube. The arithmetic cube can be programmed to solve linear transformations such as convolutions and DFTs, and has nearest neighbor interconnects, regular layout, simple control, and a limited number of interconnections. Regular layout and simple control derive naturally from the algorithms on which the processor is based. Long wires are eliminated by the nearest neighbor interconnect. High throughput can be achieved by pipelining the processor at the digit level. The arithmetic cube is programmable in the problem size n; once implemented for a certain size N, smaller problems can be solved on the same implementation without a loss in performance. In addition, the architecture extends to larger N in a regular and automatic fashion.

Original languageEnglish (US)
Pages (from-to)61-86
Number of pages26
JournalThe Journal of Supercomputing
Volume1
Issue number1
DOIs
StatePublished - Mar 1 1987

Fingerprint

Digit
Signal processing
Linear transformations
Regular hexahedron
Pipelining
Convolution
Discrete Fourier transforms
Data communication systems
Interconnect
Throughput
Wire
Signal Processing
Layout
Nearest Neighbor
Communication
Linear transformation
Data Transmission
Interconnection
High Throughput

All Science Journal Classification (ASJC) codes

  • Software
  • Theoretical Computer Science
  • Information Systems
  • Hardware and Architecture

Cite this

Irwin, Mary Jane ; Owens, Robert Michael. / Digit pipelined processors. In: The Journal of Supercomputing. 1987 ; Vol. 1, No. 1. pp. 61-86.
@article{a612cede48324e7699ae6e8f0b40cb78,
title = "Digit pipelined processors",
abstract = "Digit serial data transmission can be used to an advantage in the design of special purpose processors where communication issues dominate and where digit pipelining can be used to maintain high data rates. VLSI signal processing applications are one such problem domain. We have developed a family of VLSI components that have digit serial transmission and that can be pipelined at the digit level. These components can be used to construct VLSI processors that are especially suited to signal processing applications. One such particularly attractive processor is a structure we call the arithmetic cube. The arithmetic cube can be programmed to solve linear transformations such as convolutions and DFTs, and has nearest neighbor interconnects, regular layout, simple control, and a limited number of interconnections. Regular layout and simple control derive naturally from the algorithms on which the processor is based. Long wires are eliminated by the nearest neighbor interconnect. High throughput can be achieved by pipelining the processor at the digit level. The arithmetic cube is programmable in the problem size n; once implemented for a certain size N, smaller problems can be solved on the same implementation without a loss in performance. In addition, the architecture extends to larger N in a regular and automatic fashion.",
author = "Irwin, {Mary Jane} and Owens, {Robert Michael}",
year = "1987",
month = "3",
day = "1",
doi = "10.1007/BF00138606",
language = "English (US)",
volume = "1",
pages = "61--86",
journal = "Journal of Supercomputing",
issn = "0920-8542",
publisher = "Springer Netherlands",
number = "1",

}

Irwin, MJ & Owens, RM 1987, 'Digit pipelined processors', The Journal of Supercomputing, vol. 1, no. 1, pp. 61-86. https://doi.org/10.1007/BF00138606

Digit pipelined processors. / Irwin, Mary Jane; Owens, Robert Michael.

In: The Journal of Supercomputing, Vol. 1, No. 1, 01.03.1987, p. 61-86.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Digit pipelined processors

AU - Irwin, Mary Jane

AU - Owens, Robert Michael

PY - 1987/3/1

Y1 - 1987/3/1

N2 - Digit serial data transmission can be used to an advantage in the design of special purpose processors where communication issues dominate and where digit pipelining can be used to maintain high data rates. VLSI signal processing applications are one such problem domain. We have developed a family of VLSI components that have digit serial transmission and that can be pipelined at the digit level. These components can be used to construct VLSI processors that are especially suited to signal processing applications. One such particularly attractive processor is a structure we call the arithmetic cube. The arithmetic cube can be programmed to solve linear transformations such as convolutions and DFTs, and has nearest neighbor interconnects, regular layout, simple control, and a limited number of interconnections. Regular layout and simple control derive naturally from the algorithms on which the processor is based. Long wires are eliminated by the nearest neighbor interconnect. High throughput can be achieved by pipelining the processor at the digit level. The arithmetic cube is programmable in the problem size n; once implemented for a certain size N, smaller problems can be solved on the same implementation without a loss in performance. In addition, the architecture extends to larger N in a regular and automatic fashion.

AB - Digit serial data transmission can be used to an advantage in the design of special purpose processors where communication issues dominate and where digit pipelining can be used to maintain high data rates. VLSI signal processing applications are one such problem domain. We have developed a family of VLSI components that have digit serial transmission and that can be pipelined at the digit level. These components can be used to construct VLSI processors that are especially suited to signal processing applications. One such particularly attractive processor is a structure we call the arithmetic cube. The arithmetic cube can be programmed to solve linear transformations such as convolutions and DFTs, and has nearest neighbor interconnects, regular layout, simple control, and a limited number of interconnections. Regular layout and simple control derive naturally from the algorithms on which the processor is based. Long wires are eliminated by the nearest neighbor interconnect. High throughput can be achieved by pipelining the processor at the digit level. The arithmetic cube is programmable in the problem size n; once implemented for a certain size N, smaller problems can be solved on the same implementation without a loss in performance. In addition, the architecture extends to larger N in a regular and automatic fashion.

UR - http://www.scopus.com/inward/record.url?scp=0023542671&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0023542671&partnerID=8YFLogxK

U2 - 10.1007/BF00138606

DO - 10.1007/BF00138606

M3 - Article

AN - SCOPUS:0023542671

VL - 1

SP - 61

EP - 86

JO - Journal of Supercomputing

JF - Journal of Supercomputing

SN - 0920-8542

IS - 1

ER -