Inverse-distance-weighted spatial interpolation using parallel supercomputers

Interpolation is a computationally intensive activity that may require hours of execution time to produce results when large problems are considered. In this paper we describe a strategy to reduce computation times through the use of parollel processing. To acheive this goal, a serial algorithm that performs two-dimensional inverse-distance-weighted interpolation is decomposed into a form suitable for parallel processing in two shared memory computing environments. The first uses a conventional architecture with a single monolithic memory, while the second uses a hierarchically organized collection of local caches to implement a large shared virtual address space. A series of computational experiments was conducted in which the number of processors used in parallel is systematically increased