Efficient embedding of interprocessor communications in parallel implementations of intermediate level vision tasks

Issues related to the efficient embedding of interprocessor communications required by parallel implementations of intermediate-level vision tasks are discussed. The performance of alternative embeddings of the interprocessor communications required by specific tasks at the intermediate level of vision has been analyzed, and quantitative results have been obtained and compared to the results of corresponding implementations on the Connection Machine. In the quantitative analysis, the cost of communication primitives supported by this machine, characteristics of the task, and parameters which are characteristic of image content are taken into account. Based on the result of this analysis, a methodology is suggested for selecting the most efficient implementation of interprocessor communications among different alternatives