Data-parallel message-passing algorithms can be used to implement a high-performance GIS. This article reports on the performance of a key GIS operation made parallel through systematic declustering.
Bibliographical noteFunding Information:
This work is sponsored in part by the Army High Performance ComputingR esearch Center under the auspices of the US Army, Army Research Laboratory cooperative agreement DAAH04-95-2-0003/contracDt AAH04-95-C-0008. This work does not necessarily reflect the position or policy of the US government. This work is also supported in part by NSF grant CDA9414015.