A Hopfield neural network based task mapping method

Citation
W. Zhu et al., A Hopfield neural network based task mapping method, COMPUT COMM, 22(11), 1999, pp. 1068-1079
Citations number
13
Categorie Soggetti
Information Tecnology & Communication Systems
Journal title
COMPUTER COMMUNICATIONS
ISSN journal
01403664 → ACNP
Volume
22
Issue
11
Year of publication
1999
Pages
1068 - 1079
Database
ISI
SICI code
0140-3664(19990715)22:11<1068:AHNNBT>2.0.ZU;2-X
Abstract
With a prior knowledge of a program, static mapping aims to identify an opt imal clustering strategy that can produce the best performance. In this pap er we present a static method that uses Hopfield neural network to cluster the tasks of a parallel program for a given system. This method takes into account both load balancing and communication minimization. The method has been tested on a distributed shared memory system against other three clust ering methods. Four programs, SOR, N-body, Gaussian Elimination and VQ, are used in the test. The result shows that our method is superior to the othe r three. (C) 1999 Elsevier Science B.V. All rights reserved.