A domain decomposition method for scattered data approximation on a distributed memory multiprocessor
łThe problem of reconstructing a function f(x, y) from N experimental evaluations (xi, yi, fi), i=1, ..., N irregularly distributed in the plane, has been considered for very large values of N. In this case the known local methods give the best sequential algorithms, but are not well suited for parallel implementation due to their excessively large arithmetic overhead. In this work we present a domain decomposition parallel method, especially studied for distributed memory multiprocessors which also achieves high efficiency as a sequential algorithm. In fact, it is based on the decomposition strategy already used in the local methods, but a particular decomposition in slightly overlapping regions and appropriate choice of the limited support weight functions has been realized in order to reduce arithmetic, communication and synchronization overheads. A good performance of the coarse grained parallel algorithm is then achieved by means of a dynamic arithmetic load- balance. Timings and efficiency results from a large experimentation carried out on a Hypercube iPSC/2 are given.
Unable to display preview. Download preview PDF.
- 1. R.Franke: ”Smooth surface approximation by a local method of interpolation at scattered points”, Report Naval Postgraduate School 27-78-008 (1978)Google Scholar
- 2. L. Bacchelli Montefusco: ”Ricostruzione di superfici mediante funzioni di forma locali”, Calcolo v.19,p.169–191(1982)Google Scholar
- 3. G.A. Geist, M.T. Health, ”Matrix factorization on a Hypercubes Multiprocessors”, Hypercube 1986,pp.161–180.Google Scholar