http://worldcat.org/entity/work/id/31814803

Rectilinear partitioning of irregular data parallel computations

Abstract: "This paper describes new mapping algorithms for domain-oriented data-parallel computations, where the workload is distributed irregularly throughout the domain, but exhibits localized communication patterns. We consider the problem of partitioning the domain for parallel processing in such a way that the workload on the most heavily loaded processor is minimized, subject to the constraint that the partition be perfectly rectilinear. Rectilinear partitions are useful on architectures that have a fast local mesh network and a relatively slower global network; these partitions heuristically attempt to maximize the fraction of communication carried by the local network. This paper provides an improved algorithm for finding the optimal partition in one dimension, new algorithms for partitioning in two dimensions, and shows that optimal partitioning in three dimensions is NP-complete. We discuss our application of these algorithms to real problems."

Open All Close All