Fault tolerance in scheduling through interval ordered tasks for multiprocessors

Mohana Desiraju, Hesham H Ali

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

1 Citation (Scopus)

Abstract

While precedence constrained scheduling is NP-hard in general, it is known that optimal scheduling algorithms exist for special cases such as for trees, Interval Orders or when number of processors is limited to two. In this paper, we employ these optimal algorithms to address the important issue of fault tolerance for scheduling general graphs. The input precedence graphs are augmented into Interval Orders and then scheduled optimally while incorporating fault tolerance measures. It is proved that for the case where the graph is already an Interval Order, the fault tolerant schedule generated is optimal. For general precedence graphs, the obtained schedules are shown to be near optimal by comparing them with a standard list scheduling algorithm.

Original languageEnglish (US)
Title of host publicationProceedings of the IASTED International Conference on Parallel and Distributed Computing and Systems
EditorsT. Gonzalez
Pages467-472
Number of pages6
Volume16
StatePublished - 2004
EventProceedings of the 16th IASTED International Conference on Parallel and Distributed Computing and Systems - Cambridge, MA, United States
Duration: Nov 9 2004Nov 11 2004

Other

OtherProceedings of the 16th IASTED International Conference on Parallel and Distributed Computing and Systems
CountryUnited States
CityCambridge, MA
Period11/9/0411/11/04

Fingerprint

Fault tolerance
Scheduling algorithms
Scheduling

Keywords

  • Augmented Graph
  • Backup task
  • Fault Tolerant Scheduling
  • Predecessor
  • Primary task
  • Successor

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Desiraju, M., & Ali, H. H. (2004). Fault tolerance in scheduling through interval ordered tasks for multiprocessors. In T. Gonzalez (Ed.), Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Systems (Vol. 16, pp. 467-472). [439-122]

Fault tolerance in scheduling through interval ordered tasks for multiprocessors. / Desiraju, Mohana; Ali, Hesham H.

Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Systems. ed. / T. Gonzalez. Vol. 16 2004. p. 467-472 439-122.

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

Desiraju, M & Ali, HH 2004, Fault tolerance in scheduling through interval ordered tasks for multiprocessors. in T Gonzalez (ed.), Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Systems. vol. 16, 439-122, pp. 467-472, Proceedings of the 16th IASTED International Conference on Parallel and Distributed Computing and Systems, Cambridge, MA, United States, 11/9/04.
Desiraju M, Ali HH. Fault tolerance in scheduling through interval ordered tasks for multiprocessors. In Gonzalez T, editor, Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Systems. Vol. 16. 2004. p. 467-472. 439-122
Desiraju, Mohana ; Ali, Hesham H. / Fault tolerance in scheduling through interval ordered tasks for multiprocessors. Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Systems. editor / T. Gonzalez. Vol. 16 2004. pp. 467-472
@inproceedings{7dea198d6b424a45935e2017e46b62cc,
title = "Fault tolerance in scheduling through interval ordered tasks for multiprocessors",
abstract = "While precedence constrained scheduling is NP-hard in general, it is known that optimal scheduling algorithms exist for special cases such as for trees, Interval Orders or when number of processors is limited to two. In this paper, we employ these optimal algorithms to address the important issue of fault tolerance for scheduling general graphs. The input precedence graphs are augmented into Interval Orders and then scheduled optimally while incorporating fault tolerance measures. It is proved that for the case where the graph is already an Interval Order, the fault tolerant schedule generated is optimal. For general precedence graphs, the obtained schedules are shown to be near optimal by comparing them with a standard list scheduling algorithm.",
keywords = "Augmented Graph, Backup task, Fault Tolerant Scheduling, Predecessor, Primary task, Successor",
author = "Mohana Desiraju and Ali, {Hesham H}",
year = "2004",
language = "English (US)",
volume = "16",
pages = "467--472",
editor = "T. Gonzalez",
booktitle = "Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Systems",

}

TY - GEN

T1 - Fault tolerance in scheduling through interval ordered tasks for multiprocessors

AU - Desiraju, Mohana

AU - Ali, Hesham H

PY - 2004

Y1 - 2004

N2 - While precedence constrained scheduling is NP-hard in general, it is known that optimal scheduling algorithms exist for special cases such as for trees, Interval Orders or when number of processors is limited to two. In this paper, we employ these optimal algorithms to address the important issue of fault tolerance for scheduling general graphs. The input precedence graphs are augmented into Interval Orders and then scheduled optimally while incorporating fault tolerance measures. It is proved that for the case where the graph is already an Interval Order, the fault tolerant schedule generated is optimal. For general precedence graphs, the obtained schedules are shown to be near optimal by comparing them with a standard list scheduling algorithm.

AB - While precedence constrained scheduling is NP-hard in general, it is known that optimal scheduling algorithms exist for special cases such as for trees, Interval Orders or when number of processors is limited to two. In this paper, we employ these optimal algorithms to address the important issue of fault tolerance for scheduling general graphs. The input precedence graphs are augmented into Interval Orders and then scheduled optimally while incorporating fault tolerance measures. It is proved that for the case where the graph is already an Interval Order, the fault tolerant schedule generated is optimal. For general precedence graphs, the obtained schedules are shown to be near optimal by comparing them with a standard list scheduling algorithm.

KW - Augmented Graph

KW - Backup task

KW - Fault Tolerant Scheduling

KW - Predecessor

KW - Primary task

KW - Successor

UR - http://www.scopus.com/inward/record.url?scp=11844294892&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=11844294892&partnerID=8YFLogxK

M3 - Conference contribution

VL - 16

SP - 467

EP - 472

BT - Proceedings of the IASTED International Conference on Parallel and Distributed Computing and Systems

A2 - Gonzalez, T.

ER -