Developing non-local iterative parallel algorithms for GIS on a workstation network

The use of parallel computing is gaining increasing popularity in geographic information systems applications. There exists a class of spatial analysis algorithms that are based on local computation and are single step, hence leading to simple and efficient parallel code. For another class of algorithms it is not possible to make any assumption about the locality of computation, for example when extracting complex or global terrain features, and a number of iteration may be necessary to satisfy a convergence criteria, giving rise to non-local iterative algorithms. An example is the algorithm to extract drainage basins from digital terrain models. Despite the increasing difficulties there is an interest in parallelising non-local iterative algorithms. In this paper we present and compare different approaches to the parallelisation of non-local iterative algorithms on a workstation network using the Linda model of parallel programming.