Task allocation method for avoiding contentions by the information of concurrent communications

Yoshiyuki Morie; Takeshi Nanri; Motoyoshi Kurokawa

doi:10.2316/P.2011.719-025

Task allocation method for avoiding contentions by the information of concurrent communications

Yoshiyuki Morie, Takeshi Nanri, Motoyoshi Kurokawa

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

This paper proposes an optimization method of task-allocation for reducing contentions. There have been some attempts for optimizing task-allocation that minimizes the product of the amount of communications and the number of the communication hops. However, since those methods do not consider the occurrence of contentions, the effect has not been sufficient. The method proposed in this paper uses information of concurrent communication to estimate the effect of contentions to find the optimal task-allocation. In three environments examined on the experiments, the proposed method has shown a better effect than the existing method on two environments, tree and fat tree. On these environments, the maximum gain of performance over the existing method was about 25%. On the other hand, on a mesh environment, IBM BlueGene/L, the existing method better effect than the proposed method. As one of the reasons for this, the influence of the packet priority on the network of BlueGene/L to the behavior of the proposed method is discussed.

Original language	English
Title of host publication	Proceedings of the 10th IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2011
Pages	62-69
Number of pages	8
DOIs	https://doi.org/10.2316/P.2011.719-025
Publication status	Published - Jun 13 2011
Event	10th IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2011 - Innsbruck, Austria Duration: Feb 15 2011 → Feb 17 2011

Other

Other	10th IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2011
Country/Territory	Austria
City	Innsbruck
Period	2/15/11 → 2/17/11

All Science Journal Classification (ASJC) codes

Computer Networks and Communications

Access to Document

10.2316/P.2011.719-025

Cite this

Task allocation method for avoiding contentions by the information of concurrent communications. / Morie, Yoshiyuki; Nanri, Takeshi; Kurokawa, Motoyoshi.

Proceedings of the 10th IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2011. 2011. p. 62-69.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Morie, Y, Nanri, T & Kurokawa, M 2011, Task allocation method for avoiding contentions by the information of concurrent communications. in Proceedings of the 10th IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2011. pp. 62-69, 10th IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2011, Innsbruck, Austria, 2/15/11. https://doi.org/10.2316/P.2011.719-025

@inproceedings{b91c81c80ca64bc9aa2265f3fb191e36,

title = "Task allocation method for avoiding contentions by the information of concurrent communications",

abstract = "This paper proposes an optimization method of task-allocation for reducing contentions. There have been some attempts for optimizing task-allocation that minimizes the product of the amount of communications and the number of the communication hops. However, since those methods do not consider the occurrence of contentions, the effect has not been sufficient. The method proposed in this paper uses information of concurrent communication to estimate the effect of contentions to find the optimal task-allocation. In three environments examined on the experiments, the proposed method has shown a better effect than the existing method on two environments, tree and fat tree. On these environments, the maximum gain of performance over the existing method was about 25%. On the other hand, on a mesh environment, IBM BlueGene/L, the existing method better effect than the proposed method. As one of the reasons for this, the influence of the packet priority on the network of BlueGene/L to the behavior of the proposed method is discussed.",

author = "Yoshiyuki Morie and Takeshi Nanri and Motoyoshi Kurokawa",

year = "2011",

month = jun,

day = "13",

doi = "10.2316/P.2011.719-025",

language = "English",

isbn = "9780889868649",

pages = "62--69",

booktitle = "Proceedings of the 10th IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2011",

note = "10th IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2011 ; Conference date: 15-02-2011 Through 17-02-2011",

}

TY - GEN

T1 - Task allocation method for avoiding contentions by the information of concurrent communications

AU - Morie, Yoshiyuki

AU - Nanri, Takeshi

AU - Kurokawa, Motoyoshi

PY - 2011/6/13

Y1 - 2011/6/13

N2 - This paper proposes an optimization method of task-allocation for reducing contentions. There have been some attempts for optimizing task-allocation that minimizes the product of the amount of communications and the number of the communication hops. However, since those methods do not consider the occurrence of contentions, the effect has not been sufficient. The method proposed in this paper uses information of concurrent communication to estimate the effect of contentions to find the optimal task-allocation. In three environments examined on the experiments, the proposed method has shown a better effect than the existing method on two environments, tree and fat tree. On these environments, the maximum gain of performance over the existing method was about 25%. On the other hand, on a mesh environment, IBM BlueGene/L, the existing method better effect than the proposed method. As one of the reasons for this, the influence of the packet priority on the network of BlueGene/L to the behavior of the proposed method is discussed.

AB - This paper proposes an optimization method of task-allocation for reducing contentions. There have been some attempts for optimizing task-allocation that minimizes the product of the amount of communications and the number of the communication hops. However, since those methods do not consider the occurrence of contentions, the effect has not been sufficient. The method proposed in this paper uses information of concurrent communication to estimate the effect of contentions to find the optimal task-allocation. In three environments examined on the experiments, the proposed method has shown a better effect than the existing method on two environments, tree and fat tree. On these environments, the maximum gain of performance over the existing method was about 25%. On the other hand, on a mesh environment, IBM BlueGene/L, the existing method better effect than the proposed method. As one of the reasons for this, the influence of the packet priority on the network of BlueGene/L to the behavior of the proposed method is discussed.

UR - http://www.scopus.com/inward/record.url?scp=79958162428&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79958162428&partnerID=8YFLogxK

U2 - 10.2316/P.2011.719-025

DO - 10.2316/P.2011.719-025

M3 - Conference contribution

AN - SCOPUS:79958162428

SN - 9780889868649

SP - 62

EP - 69

BT - Proceedings of the 10th IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2011

T2 - 10th IASTED International Conference on Parallel and Distributed Computing and Networks, PDCN 2011

Y2 - 15 February 2011 through 17 February 2011

ER -

Task allocation method for avoiding contentions by the information of concurrent communications

Abstract

Other

All Science Journal Classification (ASJC) codes

Access to Document

Other files and links

Fingerprint

Cite this