Parallel processing scheme for a Fortran program on a multiprocessor system OSCAR

Hiroki Honda, Akiyoshi Mogi, Akio Ogura, Hironori Kasahara, Seinosuke Narita

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

Abstract

A parallel processing scheme is proposed for a Fortran program on a multiprocessor system named OSCAR (Optimally SCheduled Advanced multiprocessoR). The scheme combines parallel processing of fine grain tasks (each of which consists of an assignment statement), macro-data-flow computation (which uses parallelism among coarse grain tasks), and the traditional loop concurrentization. A parallelizing compiler that accomplishes the proposed scheme has been implemented on OSCAR. OSCAR has been designed to effectively support task-scheduling, which has been an obstacle to the realization of efficient parallel processing. A performance evaluation of the scheme on OSCAR is also described.

Original languageEnglish
Title of host publicationIEEE Pacific Rim Conference on Communications, Computers and Signal Processing Conference Proceedings
Editors Anon
Place of PublicationPiscataway, NJ, United States
PublisherPubl by IEEE
Pages9-12
Number of pages4
ISBN (Print)0879426381
Publication statusPublished - 1991
Externally publishedYes
EventProceedings of the 1991 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing Processing. Conference Proceedings - Victoria, BC, USA
Duration: 1991 May 91991 May 10

Other

OtherProceedings of the 1991 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing Processing. Conference Proceedings
CityVictoria, BC, USA
Period91/5/991/5/10

Fingerprint

Processing
Macros
Scheduling

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Honda, H., Mogi, A., Ogura, A., Kasahara, H., & Narita, S. (1991). Parallel processing scheme for a Fortran program on a multiprocessor system OSCAR. In Anon (Ed.), IEEE Pacific Rim Conference on Communications, Computers and Signal Processing Conference Proceedings (pp. 9-12). Piscataway, NJ, United States: Publ by IEEE.

Parallel processing scheme for a Fortran program on a multiprocessor system OSCAR. / Honda, Hiroki; Mogi, Akiyoshi; Ogura, Akio; Kasahara, Hironori; Narita, Seinosuke.

IEEE Pacific Rim Conference on Communications, Computers and Signal Processing Conference Proceedings. ed. / Anon. Piscataway, NJ, United States : Publ by IEEE, 1991. p. 9-12.

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

Honda, H, Mogi, A, Ogura, A, Kasahara, H & Narita, S 1991, Parallel processing scheme for a Fortran program on a multiprocessor system OSCAR. in Anon (ed.), IEEE Pacific Rim Conference on Communications, Computers and Signal Processing Conference Proceedings. Publ by IEEE, Piscataway, NJ, United States, pp. 9-12, Proceedings of the 1991 IEEE Pacific Rim Conference on Communications, Computers and Signal Processing Processing. Conference Proceedings, Victoria, BC, USA, 91/5/9.
Honda H, Mogi A, Ogura A, Kasahara H, Narita S. Parallel processing scheme for a Fortran program on a multiprocessor system OSCAR. In Anon, editor, IEEE Pacific Rim Conference on Communications, Computers and Signal Processing Conference Proceedings. Piscataway, NJ, United States: Publ by IEEE. 1991. p. 9-12
Honda, Hiroki ; Mogi, Akiyoshi ; Ogura, Akio ; Kasahara, Hironori ; Narita, Seinosuke. / Parallel processing scheme for a Fortran program on a multiprocessor system OSCAR. IEEE Pacific Rim Conference on Communications, Computers and Signal Processing Conference Proceedings. editor / Anon. Piscataway, NJ, United States : Publ by IEEE, 1991. pp. 9-12
@inproceedings{85ab703a590f46fc819158089294d226,
title = "Parallel processing scheme for a Fortran program on a multiprocessor system OSCAR",
abstract = "A parallel processing scheme is proposed for a Fortran program on a multiprocessor system named OSCAR (Optimally SCheduled Advanced multiprocessoR). The scheme combines parallel processing of fine grain tasks (each of which consists of an assignment statement), macro-data-flow computation (which uses parallelism among coarse grain tasks), and the traditional loop concurrentization. A parallelizing compiler that accomplishes the proposed scheme has been implemented on OSCAR. OSCAR has been designed to effectively support task-scheduling, which has been an obstacle to the realization of efficient parallel processing. A performance evaluation of the scheme on OSCAR is also described.",
author = "Hiroki Honda and Akiyoshi Mogi and Akio Ogura and Hironori Kasahara and Seinosuke Narita",
year = "1991",
language = "English",
isbn = "0879426381",
pages = "9--12",
editor = "Anon",
booktitle = "IEEE Pacific Rim Conference on Communications, Computers and Signal Processing Conference Proceedings",
publisher = "Publ by IEEE",

}

TY - GEN

T1 - Parallel processing scheme for a Fortran program on a multiprocessor system OSCAR

AU - Honda, Hiroki

AU - Mogi, Akiyoshi

AU - Ogura, Akio

AU - Kasahara, Hironori

AU - Narita, Seinosuke

PY - 1991

Y1 - 1991

N2 - A parallel processing scheme is proposed for a Fortran program on a multiprocessor system named OSCAR (Optimally SCheduled Advanced multiprocessoR). The scheme combines parallel processing of fine grain tasks (each of which consists of an assignment statement), macro-data-flow computation (which uses parallelism among coarse grain tasks), and the traditional loop concurrentization. A parallelizing compiler that accomplishes the proposed scheme has been implemented on OSCAR. OSCAR has been designed to effectively support task-scheduling, which has been an obstacle to the realization of efficient parallel processing. A performance evaluation of the scheme on OSCAR is also described.

AB - A parallel processing scheme is proposed for a Fortran program on a multiprocessor system named OSCAR (Optimally SCheduled Advanced multiprocessoR). The scheme combines parallel processing of fine grain tasks (each of which consists of an assignment statement), macro-data-flow computation (which uses parallelism among coarse grain tasks), and the traditional loop concurrentization. A parallelizing compiler that accomplishes the proposed scheme has been implemented on OSCAR. OSCAR has been designed to effectively support task-scheduling, which has been an obstacle to the realization of efficient parallel processing. A performance evaluation of the scheme on OSCAR is also described.

UR - http://www.scopus.com/inward/record.url?scp=0026385999&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0026385999&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:0026385999

SN - 0879426381

SP - 9

EP - 12

BT - IEEE Pacific Rim Conference on Communications, Computers and Signal Processing Conference Proceedings

A2 - Anon, null

PB - Publ by IEEE

CY - Piscataway, NJ, United States

ER -