Fault-tolerant broadcasting in wormhole-routed torus networks

Seungjin Park, S. Seidel, Jong-Hoon Youn

Research output: Chapter in Book/Report/Conference proceedingConference contribution

6 Citations (Scopus)

Abstract

This paper describes a fault-tolerant broadcast algorithm for wormhole-routed torus networks for which there is only local knowledge of faulty components. This algorithm tolerates tip to k-1 faulty nodes in a k-ary n-cube provided the faults do not cause the network to be disconnected. Based on the fault-tolerant dimension-order unicast communication, this algorithm is deadlock-free and no additional virtual channels are needed. The first stage of this algorithm is itself an optimal broadcast algorithm for a torus if no faults are present. The second stage overcomes the presence of up to k-1 faults with a fixed number of additional message transmissions. Thus, the cost of this algorithm is within a constant factor of the cost of optimal non-fault-tolerant broadcast algorithms.

Original languageEnglish (US)
Title of host publicationProceedings - International Parallel and Distributed Processing Symposium, IPDPS 2002
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages371-376
Number of pages6
ISBN (Print)0769515738, 9780769515731
DOIs
StatePublished - 2002
Externally publishedYes
Event16th International Parallel and Distributed Processing Symposium, IPDPS 2002 - Ft. Lauderdale, United States
Duration: Apr 15 2002Apr 19 2002

Other

Other16th International Parallel and Distributed Processing Symposium, IPDPS 2002
CountryUnited States
CityFt. Lauderdale
Period4/15/024/19/02

Fingerprint

Wormhole
Broadcasting
Fault-tolerant
Torus
Broadcast
Fault
K-ary N-cubes
Order Dimension
Virtual Channel
Deadlock
Costs
Communication
Vertex of a graph

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Modeling and Simulation

Cite this

Park, S., Seidel, S., & Youn, J-H. (2002). Fault-tolerant broadcasting in wormhole-routed torus networks. In Proceedings - International Parallel and Distributed Processing Symposium, IPDPS 2002 (pp. 371-376). [1015517] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IPDPS.2002.1015517

Fault-tolerant broadcasting in wormhole-routed torus networks. / Park, Seungjin; Seidel, S.; Youn, Jong-Hoon.

Proceedings - International Parallel and Distributed Processing Symposium, IPDPS 2002. Institute of Electrical and Electronics Engineers Inc., 2002. p. 371-376 1015517.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Park, S, Seidel, S & Youn, J-H 2002, Fault-tolerant broadcasting in wormhole-routed torus networks. in Proceedings - International Parallel and Distributed Processing Symposium, IPDPS 2002., 1015517, Institute of Electrical and Electronics Engineers Inc., pp. 371-376, 16th International Parallel and Distributed Processing Symposium, IPDPS 2002, Ft. Lauderdale, United States, 4/15/02. https://doi.org/10.1109/IPDPS.2002.1015517
Park S, Seidel S, Youn J-H. Fault-tolerant broadcasting in wormhole-routed torus networks. In Proceedings - International Parallel and Distributed Processing Symposium, IPDPS 2002. Institute of Electrical and Electronics Engineers Inc. 2002. p. 371-376. 1015517 https://doi.org/10.1109/IPDPS.2002.1015517
Park, Seungjin ; Seidel, S. ; Youn, Jong-Hoon. / Fault-tolerant broadcasting in wormhole-routed torus networks. Proceedings - International Parallel and Distributed Processing Symposium, IPDPS 2002. Institute of Electrical and Electronics Engineers Inc., 2002. pp. 371-376
@inproceedings{2720ea5895524ed18969b06797211dac,
title = "Fault-tolerant broadcasting in wormhole-routed torus networks",
abstract = "This paper describes a fault-tolerant broadcast algorithm for wormhole-routed torus networks for which there is only local knowledge of faulty components. This algorithm tolerates tip to k-1 faulty nodes in a k-ary n-cube provided the faults do not cause the network to be disconnected. Based on the fault-tolerant dimension-order unicast communication, this algorithm is deadlock-free and no additional virtual channels are needed. The first stage of this algorithm is itself an optimal broadcast algorithm for a torus if no faults are present. The second stage overcomes the presence of up to k-1 faults with a fixed number of additional message transmissions. Thus, the cost of this algorithm is within a constant factor of the cost of optimal non-fault-tolerant broadcast algorithms.",
author = "Seungjin Park and S. Seidel and Jong-Hoon Youn",
year = "2002",
doi = "10.1109/IPDPS.2002.1015517",
language = "English (US)",
isbn = "0769515738",
pages = "371--376",
booktitle = "Proceedings - International Parallel and Distributed Processing Symposium, IPDPS 2002",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Fault-tolerant broadcasting in wormhole-routed torus networks

AU - Park, Seungjin

AU - Seidel, S.

AU - Youn, Jong-Hoon

PY - 2002

Y1 - 2002

N2 - This paper describes a fault-tolerant broadcast algorithm for wormhole-routed torus networks for which there is only local knowledge of faulty components. This algorithm tolerates tip to k-1 faulty nodes in a k-ary n-cube provided the faults do not cause the network to be disconnected. Based on the fault-tolerant dimension-order unicast communication, this algorithm is deadlock-free and no additional virtual channels are needed. The first stage of this algorithm is itself an optimal broadcast algorithm for a torus if no faults are present. The second stage overcomes the presence of up to k-1 faults with a fixed number of additional message transmissions. Thus, the cost of this algorithm is within a constant factor of the cost of optimal non-fault-tolerant broadcast algorithms.

AB - This paper describes a fault-tolerant broadcast algorithm for wormhole-routed torus networks for which there is only local knowledge of faulty components. This algorithm tolerates tip to k-1 faulty nodes in a k-ary n-cube provided the faults do not cause the network to be disconnected. Based on the fault-tolerant dimension-order unicast communication, this algorithm is deadlock-free and no additional virtual channels are needed. The first stage of this algorithm is itself an optimal broadcast algorithm for a torus if no faults are present. The second stage overcomes the presence of up to k-1 faults with a fixed number of additional message transmissions. Thus, the cost of this algorithm is within a constant factor of the cost of optimal non-fault-tolerant broadcast algorithms.

UR - http://www.scopus.com/inward/record.url?scp=84966659600&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84966659600&partnerID=8YFLogxK

U2 - 10.1109/IPDPS.2002.1015517

DO - 10.1109/IPDPS.2002.1015517

M3 - Conference contribution

SN - 0769515738

SN - 9780769515731

SP - 371

EP - 376

BT - Proceedings - International Parallel and Distributed Processing Symposium, IPDPS 2002

PB - Institute of Electrical and Electronics Engineers Inc.

ER -