Task allocation optimization for neighboring communication on fat tree

Yoshiyuki Morie, Takeshi Nanri

研究成果: 著書/レポートタイプへの貢献会議での発言

1 引用 (Scopus)

抄録

This paper proposes a task allocation optimization for neighboring communications on a fat tree. The proposed method finds an appropriate task allocation that reduces contentions to achieve better communication performance. Since neighboring communications assume that the logical topology of tasks is a mesh or torus, optimization of the task allocation on a tree-based physical topology is not straightforward. This paper describes the proposed task allocation optimization method, which considers the contentions on links for each given allocation to determine the bottleneck link. Then, this method finds the allocation that achieves as wide a bandwidth as possible at the bottleneck link. For comparison, three other allocation methods, TAHB, random, and default, are also examined. The experimental results show that the method proposed by the authors can achieve the same or better performance than can the three abovementioned methods. For example, task allocation with our method was a maximum of 45% faster than that with the TAHB method. The advantage of our method over the TAHB method depends on the number of uplinks on each leaf switch. Unlike TAHB, our method can appropriately consider multiple links.

元の言語英語
ホスト出版物のタイトルProceedings of the 14th IEEE International Conference on High Performance Computing and Communications, HPCC-2012 - 9th IEEE International Conference on Embedded Software and Systems, ICESS-2012
ページ1219-1225
ページ数7
DOI
出版物ステータス出版済み - 2012
イベント14th IEEE International Conference on High Performance Computing and Communications, HPCC-2012 - 9th IEEE International Conference on Embedded Software and Systems, ICESS-2012 - Liverpool, 英国
継続期間: 6 25 20126 27 2012

その他

その他14th IEEE International Conference on High Performance Computing and Communications, HPCC-2012 - 9th IEEE International Conference on Embedded Software and Systems, ICESS-2012
英国
Liverpool
期間6/25/126/27/12

Fingerprint

Trees (mathematics)
Oils and fats
Communication
Topology
Telecommunication links
Switches
Bandwidth

All Science Journal Classification (ASJC) codes

  • Software

これを引用

Morie, Y., & Nanri, T. (2012). Task allocation optimization for neighboring communication on fat tree. : Proceedings of the 14th IEEE International Conference on High Performance Computing and Communications, HPCC-2012 - 9th IEEE International Conference on Embedded Software and Systems, ICESS-2012 (pp. 1219-1225). [6332315] https://doi.org/10.1109/HPCC.2012.179

Task allocation optimization for neighboring communication on fat tree. / Morie, Yoshiyuki; Nanri, Takeshi.

Proceedings of the 14th IEEE International Conference on High Performance Computing and Communications, HPCC-2012 - 9th IEEE International Conference on Embedded Software and Systems, ICESS-2012. 2012. p. 1219-1225 6332315.

研究成果: 著書/レポートタイプへの貢献会議での発言

Morie, Y & Nanri, T 2012, Task allocation optimization for neighboring communication on fat tree. : Proceedings of the 14th IEEE International Conference on High Performance Computing and Communications, HPCC-2012 - 9th IEEE International Conference on Embedded Software and Systems, ICESS-2012., 6332315, pp. 1219-1225, 14th IEEE International Conference on High Performance Computing and Communications, HPCC-2012 - 9th IEEE International Conference on Embedded Software and Systems, ICESS-2012, Liverpool, 英国, 6/25/12. https://doi.org/10.1109/HPCC.2012.179
Morie Y, Nanri T. Task allocation optimization for neighboring communication on fat tree. : Proceedings of the 14th IEEE International Conference on High Performance Computing and Communications, HPCC-2012 - 9th IEEE International Conference on Embedded Software and Systems, ICESS-2012. 2012. p. 1219-1225. 6332315 https://doi.org/10.1109/HPCC.2012.179
Morie, Yoshiyuki ; Nanri, Takeshi. / Task allocation optimization for neighboring communication on fat tree. Proceedings of the 14th IEEE International Conference on High Performance Computing and Communications, HPCC-2012 - 9th IEEE International Conference on Embedded Software and Systems, ICESS-2012. 2012. pp. 1219-1225
@inproceedings{adc4ff509d0c4e65a93f645ad4c83ad2,
title = "Task allocation optimization for neighboring communication on fat tree",
abstract = "This paper proposes a task allocation optimization for neighboring communications on a fat tree. The proposed method finds an appropriate task allocation that reduces contentions to achieve better communication performance. Since neighboring communications assume that the logical topology of tasks is a mesh or torus, optimization of the task allocation on a tree-based physical topology is not straightforward. This paper describes the proposed task allocation optimization method, which considers the contentions on links for each given allocation to determine the bottleneck link. Then, this method finds the allocation that achieves as wide a bandwidth as possible at the bottleneck link. For comparison, three other allocation methods, TAHB, random, and default, are also examined. The experimental results show that the method proposed by the authors can achieve the same or better performance than can the three abovementioned methods. For example, task allocation with our method was a maximum of 45{\%} faster than that with the TAHB method. The advantage of our method over the TAHB method depends on the number of uplinks on each leaf switch. Unlike TAHB, our method can appropriately consider multiple links.",
author = "Yoshiyuki Morie and Takeshi Nanri",
year = "2012",
doi = "10.1109/HPCC.2012.179",
language = "English",
isbn = "9780769547497",
pages = "1219--1225",
booktitle = "Proceedings of the 14th IEEE International Conference on High Performance Computing and Communications, HPCC-2012 - 9th IEEE International Conference on Embedded Software and Systems, ICESS-2012",

}

TY - GEN

T1 - Task allocation optimization for neighboring communication on fat tree

AU - Morie, Yoshiyuki

AU - Nanri, Takeshi

PY - 2012

Y1 - 2012

N2 - This paper proposes a task allocation optimization for neighboring communications on a fat tree. The proposed method finds an appropriate task allocation that reduces contentions to achieve better communication performance. Since neighboring communications assume that the logical topology of tasks is a mesh or torus, optimization of the task allocation on a tree-based physical topology is not straightforward. This paper describes the proposed task allocation optimization method, which considers the contentions on links for each given allocation to determine the bottleneck link. Then, this method finds the allocation that achieves as wide a bandwidth as possible at the bottleneck link. For comparison, three other allocation methods, TAHB, random, and default, are also examined. The experimental results show that the method proposed by the authors can achieve the same or better performance than can the three abovementioned methods. For example, task allocation with our method was a maximum of 45% faster than that with the TAHB method. The advantage of our method over the TAHB method depends on the number of uplinks on each leaf switch. Unlike TAHB, our method can appropriately consider multiple links.

AB - This paper proposes a task allocation optimization for neighboring communications on a fat tree. The proposed method finds an appropriate task allocation that reduces contentions to achieve better communication performance. Since neighboring communications assume that the logical topology of tasks is a mesh or torus, optimization of the task allocation on a tree-based physical topology is not straightforward. This paper describes the proposed task allocation optimization method, which considers the contentions on links for each given allocation to determine the bottleneck link. Then, this method finds the allocation that achieves as wide a bandwidth as possible at the bottleneck link. For comparison, three other allocation methods, TAHB, random, and default, are also examined. The experimental results show that the method proposed by the authors can achieve the same or better performance than can the three abovementioned methods. For example, task allocation with our method was a maximum of 45% faster than that with the TAHB method. The advantage of our method over the TAHB method depends on the number of uplinks on each leaf switch. Unlike TAHB, our method can appropriately consider multiple links.

UR - http://www.scopus.com/inward/record.url?scp=84870432744&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84870432744&partnerID=8YFLogxK

U2 - 10.1109/HPCC.2012.179

DO - 10.1109/HPCC.2012.179

M3 - Conference contribution

AN - SCOPUS:84870432744

SN - 9780769547497

SP - 1219

EP - 1225

BT - Proceedings of the 14th IEEE International Conference on High Performance Computing and Communications, HPCC-2012 - 9th IEEE International Conference on Embedded Software and Systems, ICESS-2012

ER -