Proceedings of the 22nd International Conference on Parallel Architectures and Compilation Techniques (1998)
Oct. 12, 1998 to Oct. 18, 1998
Jing-Chiou Liou , AT&T Laboratories
Michael A. Palis , Rutgers University
In this paper, we present an efficient algorithm, called CASS-II, for task clustering without task duplication. Unlike the DSC algorithm, which is empirically the best known algorithm to date in terms of both speed and solution quality, CASS-II uses only limited ``global'' information and does not recompute the critical path in each refinement step. Therefore, the algorithm runs in $O(|E| + |V| lg |V|)$ which is faster than $O((|V|+|E|)lg |V|)$ of the DSC algorithm. Indeed, our experimental results show that CASS-II is between 3 to 5 times faster than DSC. (It is worth pointing out that we used the C code for DSC developed by the authors of the DSC algorithm. The C code for CASS-II was developed by the authors of this paper.) With respect to solution quality, experimental results show that CASS-II is virtually as good as DSC and, in fact, even outperforms DSC for very fine grain DAGs (granularity less than 0.6).
Resource management, clustering, scheduling, distributed memory multiprocessor, compiler.
Jing-Chiou Liou, Michael A. Palis, "A New Heuristic for Scheduling Parallel Programs on Multiprocessor", Proceedings of the 22nd International Conference on Parallel Architectures and Compilation Techniques, vol. 00, no. , pp. 358, 1998, doi:10.1109/PACT.1998.727277