Multicomputer type DSP system for super signal processing

Sadayasu Ono, Yukiharu Kanayama, Naoya Sakurai, Naohisa Ohta

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The architecture and performance of a massively parallel DSP system called NOVI-II is discussed. The NOVI-II system has been designed to examine methods for organizing parallel DSP systems and developing parallel programs for a wide range of super signal processing applications. NOVI-II adopts a multicomputer-type architecture, which allows the combination of more than 512 processing elements (PEs). In each PE, a transputer (T800) is used as a CPU, along with a vector processor, 2-MB external RAM, and parallel program development assistant (PDA) probe fabricated on two gate arrays. The PDA system facilitates powerful debugging functions that allow all program states to be observed. Optical links and optical networks are introduced to provide stable and flexible communications between PEs. The expected performance of the system with a large-grain scheduling technique for real-time video processing is discussed.

Original languageEnglish
Title of host publicationProceedings - IEEE International Symposium on Circuits and Systems
Editors Anon
PublisherPubl by IEEE
Pages1399-1402
Number of pages4
Volume2
Publication statusPublished - 1989
EventIEEE International Symposium on Circuits and Systems 1989, the 22nd ISCAS. Part 1 - Portland, OR, USA
Duration: 1989 May 81989 May 11

Other

OtherIEEE International Symposium on Circuits and Systems 1989, the 22nd ISCAS. Part 1
CityPortland, OR, USA
Period89/5/889/5/11

Fingerprint

Signal processing
Processing
Program processors
Transputers
Optical links
Random access storage
Fiber optic networks
Scheduling
Communication

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials

Cite this

Ono, S., Kanayama, Y., Sakurai, N., & Ohta, N. (1989). Multicomputer type DSP system for super signal processing. In Anon (Ed.), Proceedings - IEEE International Symposium on Circuits and Systems (Vol. 2, pp. 1399-1402). Publ by IEEE.

Multicomputer type DSP system for super signal processing. / Ono, Sadayasu; Kanayama, Yukiharu; Sakurai, Naoya; Ohta, Naohisa.

Proceedings - IEEE International Symposium on Circuits and Systems. ed. / Anon. Vol. 2 Publ by IEEE, 1989. p. 1399-1402.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ono, S, Kanayama, Y, Sakurai, N & Ohta, N 1989, Multicomputer type DSP system for super signal processing. in Anon (ed.), Proceedings - IEEE International Symposium on Circuits and Systems. vol. 2, Publ by IEEE, pp. 1399-1402, IEEE International Symposium on Circuits and Systems 1989, the 22nd ISCAS. Part 1, Portland, OR, USA, 89/5/8.
Ono S, Kanayama Y, Sakurai N, Ohta N. Multicomputer type DSP system for super signal processing. In Anon, editor, Proceedings - IEEE International Symposium on Circuits and Systems. Vol. 2. Publ by IEEE. 1989. p. 1399-1402
Ono, Sadayasu ; Kanayama, Yukiharu ; Sakurai, Naoya ; Ohta, Naohisa. / Multicomputer type DSP system for super signal processing. Proceedings - IEEE International Symposium on Circuits and Systems. editor / Anon. Vol. 2 Publ by IEEE, 1989. pp. 1399-1402
@inproceedings{cd0b3f0ca1054aa49a78df5f123732d6,
title = "Multicomputer type DSP system for super signal processing",
abstract = "The architecture and performance of a massively parallel DSP system called NOVI-II is discussed. The NOVI-II system has been designed to examine methods for organizing parallel DSP systems and developing parallel programs for a wide range of super signal processing applications. NOVI-II adopts a multicomputer-type architecture, which allows the combination of more than 512 processing elements (PEs). In each PE, a transputer (T800) is used as a CPU, along with a vector processor, 2-MB external RAM, and parallel program development assistant (PDA) probe fabricated on two gate arrays. The PDA system facilitates powerful debugging functions that allow all program states to be observed. Optical links and optical networks are introduced to provide stable and flexible communications between PEs. The expected performance of the system with a large-grain scheduling technique for real-time video processing is discussed.",
author = "Sadayasu Ono and Yukiharu Kanayama and Naoya Sakurai and Naohisa Ohta",
year = "1989",
language = "English",
volume = "2",
pages = "1399--1402",
editor = "Anon",
booktitle = "Proceedings - IEEE International Symposium on Circuits and Systems",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Multicomputer type DSP system for super signal processing

AU - Ono, Sadayasu

AU - Kanayama, Yukiharu

AU - Sakurai, Naoya

AU - Ohta, Naohisa

PY - 1989

Y1 - 1989

N2 - The architecture and performance of a massively parallel DSP system called NOVI-II is discussed. The NOVI-II system has been designed to examine methods for organizing parallel DSP systems and developing parallel programs for a wide range of super signal processing applications. NOVI-II adopts a multicomputer-type architecture, which allows the combination of more than 512 processing elements (PEs). In each PE, a transputer (T800) is used as a CPU, along with a vector processor, 2-MB external RAM, and parallel program development assistant (PDA) probe fabricated on two gate arrays. The PDA system facilitates powerful debugging functions that allow all program states to be observed. Optical links and optical networks are introduced to provide stable and flexible communications between PEs. The expected performance of the system with a large-grain scheduling technique for real-time video processing is discussed.

AB - The architecture and performance of a massively parallel DSP system called NOVI-II is discussed. The NOVI-II system has been designed to examine methods for organizing parallel DSP systems and developing parallel programs for a wide range of super signal processing applications. NOVI-II adopts a multicomputer-type architecture, which allows the combination of more than 512 processing elements (PEs). In each PE, a transputer (T800) is used as a CPU, along with a vector processor, 2-MB external RAM, and parallel program development assistant (PDA) probe fabricated on two gate arrays. The PDA system facilitates powerful debugging functions that allow all program states to be observed. Optical links and optical networks are introduced to provide stable and flexible communications between PEs. The expected performance of the system with a large-grain scheduling technique for real-time video processing is discussed.

UR - http://www.scopus.com/inward/record.url?scp=0024934693&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0024934693&partnerID=8YFLogxK

M3 - Conference contribution

VL - 2

SP - 1399

EP - 1402

BT - Proceedings - IEEE International Symposium on Circuits and Systems

A2 - Anon, null

PB - Publ by IEEE

ER -