Dynamic vs static implementations of MPI on new trend computer architectures

Hyacinthe Nzigou Mamadou, Takeshi Nanri, Kazuaki Murakami

研究成果: 著書/レポートタイプへの貢献会議での発言

抄録

Nowadays, multi-core chips are becoming the norm for the computer market. When one considers MPI collective communications with several processor cores on a node, one also has to consider the impact of such new architecture on widely used MPI implementations, in order to realize the communication efficiently and achieve high performance computing. This paper provides a succinct comparative analysis between dynamic and static MPI implementations on multi-core computers. MPI Alltoall collective operation is used as an example to handle the communication process involved in a load unbalanced case, and then among different communicators. The experiments performed on clusters equipped with high performance interconnects, such as Infiniband and Gigabit Ethernet, revealed that the dynamic version is more likely to be adapted with the general and random behaviors of the system for this new trend of computer architectures.

元の言語英語
ホスト出版物のタイトルWMSCI 2008 - The 12th World Multi-Conference on Systemics, Cybernetics and Informatics, Jointly with the 14th International Conference on Information Systems Analysis and Synthesis, ISAS 2008 - Proc.
ページ113-118
ページ数6
出版物ステータス出版済み - 12 1 2008
イベント12th World Multi-Conference on Systemics, Cybernetics and Informatics, WMSCI 2008, Jointly with the 14th International Conference on Information Systems Analysis and Synthesis, ISAS 2008 - Orlando, FL, 米国
継続期間: 6 29 20087 2 2008

出版物シリーズ

名前WMSCI 2008 - The 12th World Multi-Conference on Systemics, Cybernetics and Informatics, Jointly with the 14th International Conference on Information Systems Analysis and Synthesis, ISAS 2008 - Proc.
5

その他

その他12th World Multi-Conference on Systemics, Cybernetics and Informatics, WMSCI 2008, Jointly with the 14th International Conference on Information Systems Analysis and Synthesis, ISAS 2008
米国
Orlando, FL
期間6/29/087/2/08

Fingerprint

Computer architecture
Communication
Static analysis
Ethernet
Dynamic analysis
Experiments

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Computer Networks and Communications

これを引用

Mamadou, H. N., Nanri, T., & Murakami, K. (2008). Dynamic vs static implementations of MPI on new trend computer architectures. : WMSCI 2008 - The 12th World Multi-Conference on Systemics, Cybernetics and Informatics, Jointly with the 14th International Conference on Information Systems Analysis and Synthesis, ISAS 2008 - Proc. (pp. 113-118). (WMSCI 2008 - The 12th World Multi-Conference on Systemics, Cybernetics and Informatics, Jointly with the 14th International Conference on Information Systems Analysis and Synthesis, ISAS 2008 - Proc.; 巻数 5).

Dynamic vs static implementations of MPI on new trend computer architectures. / Mamadou, Hyacinthe Nzigou; Nanri, Takeshi; Murakami, Kazuaki.

WMSCI 2008 - The 12th World Multi-Conference on Systemics, Cybernetics and Informatics, Jointly with the 14th International Conference on Information Systems Analysis and Synthesis, ISAS 2008 - Proc.. 2008. p. 113-118 (WMSCI 2008 - The 12th World Multi-Conference on Systemics, Cybernetics and Informatics, Jointly with the 14th International Conference on Information Systems Analysis and Synthesis, ISAS 2008 - Proc.; 巻 5).

研究成果: 著書/レポートタイプへの貢献会議での発言

Mamadou, HN, Nanri, T & Murakami, K 2008, Dynamic vs static implementations of MPI on new trend computer architectures. : WMSCI 2008 - The 12th World Multi-Conference on Systemics, Cybernetics and Informatics, Jointly with the 14th International Conference on Information Systems Analysis and Synthesis, ISAS 2008 - Proc.. WMSCI 2008 - The 12th World Multi-Conference on Systemics, Cybernetics and Informatics, Jointly with the 14th International Conference on Information Systems Analysis and Synthesis, ISAS 2008 - Proc., 巻. 5, pp. 113-118, 12th World Multi-Conference on Systemics, Cybernetics and Informatics, WMSCI 2008, Jointly with the 14th International Conference on Information Systems Analysis and Synthesis, ISAS 2008, Orlando, FL, 米国, 6/29/08.
Mamadou HN, Nanri T, Murakami K. Dynamic vs static implementations of MPI on new trend computer architectures. : WMSCI 2008 - The 12th World Multi-Conference on Systemics, Cybernetics and Informatics, Jointly with the 14th International Conference on Information Systems Analysis and Synthesis, ISAS 2008 - Proc.. 2008. p. 113-118. (WMSCI 2008 - The 12th World Multi-Conference on Systemics, Cybernetics and Informatics, Jointly with the 14th International Conference on Information Systems Analysis and Synthesis, ISAS 2008 - Proc.).
Mamadou, Hyacinthe Nzigou ; Nanri, Takeshi ; Murakami, Kazuaki. / Dynamic vs static implementations of MPI on new trend computer architectures. WMSCI 2008 - The 12th World Multi-Conference on Systemics, Cybernetics and Informatics, Jointly with the 14th International Conference on Information Systems Analysis and Synthesis, ISAS 2008 - Proc.. 2008. pp. 113-118 (WMSCI 2008 - The 12th World Multi-Conference on Systemics, Cybernetics and Informatics, Jointly with the 14th International Conference on Information Systems Analysis and Synthesis, ISAS 2008 - Proc.).
@inproceedings{734e379cc5b347c6a38231bd967eb4e9,
title = "Dynamic vs static implementations of MPI on new trend computer architectures",
abstract = "Nowadays, multi-core chips are becoming the norm for the computer market. When one considers MPI collective communications with several processor cores on a node, one also has to consider the impact of such new architecture on widely used MPI implementations, in order to realize the communication efficiently and achieve high performance computing. This paper provides a succinct comparative analysis between dynamic and static MPI implementations on multi-core computers. MPI Alltoall collective operation is used as an example to handle the communication process involved in a load unbalanced case, and then among different communicators. The experiments performed on clusters equipped with high performance interconnects, such as Infiniband and Gigabit Ethernet, revealed that the dynamic version is more likely to be adapted with the general and random behaviors of the system for this new trend of computer architectures.",
author = "Mamadou, {Hyacinthe Nzigou} and Takeshi Nanri and Kazuaki Murakami",
year = "2008",
month = "12",
day = "1",
language = "English",
isbn = "1934272353",
series = "WMSCI 2008 - The 12th World Multi-Conference on Systemics, Cybernetics and Informatics, Jointly with the 14th International Conference on Information Systems Analysis and Synthesis, ISAS 2008 - Proc.",
pages = "113--118",
booktitle = "WMSCI 2008 - The 12th World Multi-Conference on Systemics, Cybernetics and Informatics, Jointly with the 14th International Conference on Information Systems Analysis and Synthesis, ISAS 2008 - Proc.",

}

TY - GEN

T1 - Dynamic vs static implementations of MPI on new trend computer architectures

AU - Mamadou, Hyacinthe Nzigou

AU - Nanri, Takeshi

AU - Murakami, Kazuaki

PY - 2008/12/1

Y1 - 2008/12/1

N2 - Nowadays, multi-core chips are becoming the norm for the computer market. When one considers MPI collective communications with several processor cores on a node, one also has to consider the impact of such new architecture on widely used MPI implementations, in order to realize the communication efficiently and achieve high performance computing. This paper provides a succinct comparative analysis between dynamic and static MPI implementations on multi-core computers. MPI Alltoall collective operation is used as an example to handle the communication process involved in a load unbalanced case, and then among different communicators. The experiments performed on clusters equipped with high performance interconnects, such as Infiniband and Gigabit Ethernet, revealed that the dynamic version is more likely to be adapted with the general and random behaviors of the system for this new trend of computer architectures.

AB - Nowadays, multi-core chips are becoming the norm for the computer market. When one considers MPI collective communications with several processor cores on a node, one also has to consider the impact of such new architecture on widely used MPI implementations, in order to realize the communication efficiently and achieve high performance computing. This paper provides a succinct comparative analysis between dynamic and static MPI implementations on multi-core computers. MPI Alltoall collective operation is used as an example to handle the communication process involved in a load unbalanced case, and then among different communicators. The experiments performed on clusters equipped with high performance interconnects, such as Infiniband and Gigabit Ethernet, revealed that the dynamic version is more likely to be adapted with the general and random behaviors of the system for this new trend of computer architectures.

UR - http://www.scopus.com/inward/record.url?scp=84869487404&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84869487404&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84869487404

SN - 1934272353

SN - 9781934272350

T3 - WMSCI 2008 - The 12th World Multi-Conference on Systemics, Cybernetics and Informatics, Jointly with the 14th International Conference on Information Systems Analysis and Synthesis, ISAS 2008 - Proc.

SP - 113

EP - 118

BT - WMSCI 2008 - The 12th World Multi-Conference on Systemics, Cybernetics and Informatics, Jointly with the 14th International Conference on Information Systems Analysis and Synthesis, ISAS 2008 - Proc.

ER -