Compilation scheme for near fine grain parallel processing on a multiprocessor system without explicit synchronization

Wataru Ogata; Kensaku Fujimoto; Masato Oota; Hironori Kasahara

Compilation scheme for near fine grain parallel processing on a multiprocessor system without explicit synchronization

Wataru Ogata^*, Kensaku Fujimoto, Masato Oota, Hironori Kasahara

^*Corresponding author for this work

School of Fundamental Science and Engineering

Research output: Contribution to conference › Paper › peer-review

1 Citation (Scopus)

Abstract

A multigrain parallel processing scheme is proposed which combines coarse-grain parallel processing or macro-dataflow processing, loop concurrentization, and near-fine-grain parallel processing hierarchically. A static scheduling algorithm is used to minimize the data transfer overhead and total processing time. Synchronization overhead is minimized by eliminating all synchronization codes and using a machine-clock level precise code scheduling for a target multiprocessor system OSCAR.

Original language	English
Pages	327-332
Number of pages	6
Publication status	Published - 1995 Jan 1
Event	Proceedings of the 1995 IEEE Pacific RIM Conference on Communications, Computers, and Signal Processing - Victoria, BC, Can Duration: 1995 May 17 → 1995 May 19

Other

Other	Proceedings of the 1995 IEEE Pacific RIM Conference on Communications, Computers, and Signal Processing
City	Victoria, BC, Can
Period	95/5/17 → 95/5/19

ASJC Scopus subject areas

Signal Processing
Computer Networks and Communications

Cite this

Compilation scheme for near fine grain parallel processing on a multiprocessor system without explicit synchronization. / Ogata, Wataru; Fujimoto, Kensaku; Oota, Masato et al.

1995. 327-332 Paper presented at Proceedings of the 1995 IEEE Pacific RIM Conference on Communications, Computers, and Signal Processing, Victoria, BC, Can.

Research output: Contribution to conference › Paper › peer-review

@conference{42acce4f668b47398a6692c22002cecc,

title = "Compilation scheme for near fine grain parallel processing on a multiprocessor system without explicit synchronization",

abstract = "A multigrain parallel processing scheme is proposed which combines coarse-grain parallel processing or macro-dataflow processing, loop concurrentization, and near-fine-grain parallel processing hierarchically. A static scheduling algorithm is used to minimize the data transfer overhead and total processing time. Synchronization overhead is minimized by eliminating all synchronization codes and using a machine-clock level precise code scheduling for a target multiprocessor system OSCAR.",

author = "Wataru Ogata and Kensaku Fujimoto and Masato Oota and Hironori Kasahara",

year = "1995",

month = jan,

day = "1",

language = "English",

pages = "327--332",

note = "Proceedings of the 1995 IEEE Pacific RIM Conference on Communications, Computers, and Signal Processing ; Conference date: 17-05-1995 Through 19-05-1995",

}

TY - CONF

T1 - Compilation scheme for near fine grain parallel processing on a multiprocessor system without explicit synchronization

AU - Ogata, Wataru

AU - Fujimoto, Kensaku

AU - Oota, Masato

AU - Kasahara, Hironori

PY - 1995/1/1

Y1 - 1995/1/1

N2 - A multigrain parallel processing scheme is proposed which combines coarse-grain parallel processing or macro-dataflow processing, loop concurrentization, and near-fine-grain parallel processing hierarchically. A static scheduling algorithm is used to minimize the data transfer overhead and total processing time. Synchronization overhead is minimized by eliminating all synchronization codes and using a machine-clock level precise code scheduling for a target multiprocessor system OSCAR.

AB - A multigrain parallel processing scheme is proposed which combines coarse-grain parallel processing or macro-dataflow processing, loop concurrentization, and near-fine-grain parallel processing hierarchically. A static scheduling algorithm is used to minimize the data transfer overhead and total processing time. Synchronization overhead is minimized by eliminating all synchronization codes and using a machine-clock level precise code scheduling for a target multiprocessor system OSCAR.

UR - http://www.scopus.com/inward/record.url?scp=0029221387&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029221387&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0029221387

SP - 327

EP - 332

T2 - Proceedings of the 1995 IEEE Pacific RIM Conference on Communications, Computers, and Signal Processing

Y2 - 17 May 1995 through 19 May 1995

ER -

Compilation scheme for near fine grain parallel processing on a multiprocessor system without explicit synchronization

Abstract

Other

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this