Parallel Remapping Algorithms for Adaptive Problems

In this paper we present fast parallel algorithms for remapping a class of irregular and adaptive problems on coarse-grained distributed memory machines. We show that the remapping of these applications, using simple index-based mapping algorithm, can be reduced to sorting a nearly sorted list of integers or merging an unsorted list of integers with a sorted list of integers. By using the algorithms we have developed, the remapping of these problems can be achieved at a fraction of the cost of mapping from scratch. Experimental results are presented on the CM-5. 1 Introduction The key problem in efficiently executing data parallel applications is that of partitioning the data among the processors such that the computation load on each node is balanced, while communication is minimized. Partitioning such applications can be posed as a graphpartitioning problem. The nodes of a graph constitute a set of computations that can be executed concurrently, and the edges comprise the interact..