24th International Conference on Distributed Computing Systems Workshops - W7: EC (ICDCSW'04) A Scheduling Algorithm to Optimize Real-World Applications Hachioji, Tokyo, Japan March 23-March 24 ISBN: 0-7695-2087-1
This paper presents a scheduling algorithm that assigns tasks represented in a Directed Acyclic Graph (DAG). The behavior of the proposed algorithm is compared with the Dominant Sequence Clustering (DSC) algorithm on a set of DAG tests. The tests were carried out on two sets of DAGs, one with tasks of arbitrary duration, and the other with tasks of unit time duration. When comparing the results for each algorithm in terms of parallel computation time, the proposed algorithm is superior in 75% of the cases, equal in 20% of the tests, and in those cases in which DSC outperforms the proposed algorithm (5% of the cases), it can be seen that the planning carried out by DSC uses a greater number of processors than the proposed algorithm, so that the performance in terms of CPU use is lower for DSC. The results obtained show that the proposed algorithm is superior in 100% of the cases when considering the number of processors used.
Citation:
Mauricio Solar, Mario Inostroza, "A Scheduling Algorithm to Optimize Real-World Applications," icdcsw, vol. 7, pp.858-862, 24th International Conference on Distributed Computing Systems Workshops - W7: EC (ICDCSW'04), 2004 Usage of this product signifies your acceptance of the Terms of Use. | |||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||||
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb