Experimental evaluation of hypercube-based range analysis tools

Parallel range segmentation tools are analyzed in terms of a general model for distributed-memory algorithms using n-cube topologies. The model explicitly relates the concepts of speedup, efficiency and load balancing and provides criteria for optimum assignment of nodes. Low-level computer vision functions are classified as either local or global. Experimental results are given showing that the efficiency of local operators is determined by load balancing, while the efficiency of global operators is more dependent on communication overhead.<
>