Using asynchronous and bulk communications to construct an optimizing compiler for distributed-memory machines with consideration given to communications costs

Hiroyuki Sato, Takeshi Nanri, Masaaki Shimasaki

研究成果: 会議への寄与タイプ論文

2 引用 (Scopus)

抄録

The very nature of distributed-memory parallel architectures demands the serious consideration of interprocessor communications, by which non-local memory access can be implemented. In this paper, we propose a method for optimization that utilizes asynchronous and bulk communications. We constructed an HPF- compiler, a subset of HPF, and evaluated it on the CM5, a true distributed-memory machine using three non-trivial benchmark programs. With optimized code, there was considerable improvement in communications over non-optimized code and we had much better results than when optimizing by means of CM Fortran.

元の言語英語
ページ185-189
ページ数5
出版物ステータス出版済み - 1 1 1995
イベントProceedings of the 1995 Conference on Supercomputing - Barcelona, Spain
継続期間: 7 3 19957 7 1995

その他

その他Proceedings of the 1995 Conference on Supercomputing
Barcelona, Spain
期間7/3/957/7/95

Fingerprint

Data storage equipment
Communication
Costs
Parallel architectures

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

これを引用

Sato, H., Nanri, T., & Shimasaki, M. (1995). Using asynchronous and bulk communications to construct an optimizing compiler for distributed-memory machines with consideration given to communications costs. 185-189. 論文発表場所 Proceedings of the 1995 Conference on Supercomputing, Barcelona, Spain, .

Using asynchronous and bulk communications to construct an optimizing compiler for distributed-memory machines with consideration given to communications costs. / Sato, Hiroyuki; Nanri, Takeshi; Shimasaki, Masaaki.

1995. 185-189 論文発表場所 Proceedings of the 1995 Conference on Supercomputing, Barcelona, Spain, .

研究成果: 会議への寄与タイプ論文

Sato, H, Nanri, T & Shimasaki, M 1995, 'Using asynchronous and bulk communications to construct an optimizing compiler for distributed-memory machines with consideration given to communications costs', 論文発表場所 Proceedings of the 1995 Conference on Supercomputing, Barcelona, Spain, 7/3/95 - 7/7/95 pp. 185-189.
Sato H, Nanri T, Shimasaki M. Using asynchronous and bulk communications to construct an optimizing compiler for distributed-memory machines with consideration given to communications costs. 1995. 論文発表場所 Proceedings of the 1995 Conference on Supercomputing, Barcelona, Spain, .
Sato, Hiroyuki ; Nanri, Takeshi ; Shimasaki, Masaaki. / Using asynchronous and bulk communications to construct an optimizing compiler for distributed-memory machines with consideration given to communications costs. 論文発表場所 Proceedings of the 1995 Conference on Supercomputing, Barcelona, Spain, .5 p.
@conference{5dda4195038747b7993b1dc390022042,
title = "Using asynchronous and bulk communications to construct an optimizing compiler for distributed-memory machines with consideration given to communications costs",
abstract = "The very nature of distributed-memory parallel architectures demands the serious consideration of interprocessor communications, by which non-local memory access can be implemented. In this paper, we propose a method for optimization that utilizes asynchronous and bulk communications. We constructed an HPF- compiler, a subset of HPF, and evaluated it on the CM5, a true distributed-memory machine using three non-trivial benchmark programs. With optimized code, there was considerable improvement in communications over non-optimized code and we had much better results than when optimizing by means of CM Fortran.",
author = "Hiroyuki Sato and Takeshi Nanri and Masaaki Shimasaki",
year = "1995",
month = "1",
day = "1",
language = "English",
pages = "185--189",
note = "Proceedings of the 1995 Conference on Supercomputing ; Conference date: 03-07-1995 Through 07-07-1995",

}

TY - CONF

T1 - Using asynchronous and bulk communications to construct an optimizing compiler for distributed-memory machines with consideration given to communications costs

AU - Sato, Hiroyuki

AU - Nanri, Takeshi

AU - Shimasaki, Masaaki

PY - 1995/1/1

Y1 - 1995/1/1

N2 - The very nature of distributed-memory parallel architectures demands the serious consideration of interprocessor communications, by which non-local memory access can be implemented. In this paper, we propose a method for optimization that utilizes asynchronous and bulk communications. We constructed an HPF- compiler, a subset of HPF, and evaluated it on the CM5, a true distributed-memory machine using three non-trivial benchmark programs. With optimized code, there was considerable improvement in communications over non-optimized code and we had much better results than when optimizing by means of CM Fortran.

AB - The very nature of distributed-memory parallel architectures demands the serious consideration of interprocessor communications, by which non-local memory access can be implemented. In this paper, we propose a method for optimization that utilizes asynchronous and bulk communications. We constructed an HPF- compiler, a subset of HPF, and evaluated it on the CM5, a true distributed-memory machine using three non-trivial benchmark programs. With optimized code, there was considerable improvement in communications over non-optimized code and we had much better results than when optimizing by means of CM Fortran.

UR - http://www.scopus.com/inward/record.url?scp=0029194713&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0029194713&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:0029194713

SP - 185

EP - 189

ER -