The Community for Technology Leaders
Green Image
ABSTRACT
<p>A general management framework for distributed heterogenous supercomputing systems (DHSSs) that is based on an application-characterization technique is presented. The technique uses code profiling and analytical benchmarking of supercomputers. An optimal scheduling of tasks in these systems is an NP-complete problem. The use of network caching to reduce the complexity associated with the scheduling decisions is discussed. An experimental prototype of a DHSS management system is described.</p>
INDEX TERMS
CITATION

J. Yang and A. Ghafoor, "A Distributed Heterogeneous Supercomputing Management System," in Computer, vol. 26, no. , pp. 78-86, 1993.
doi:10.1109/2.214443
90 ms
(Ver 3.3 (11022016))