摘要：The parallel computing model used in this paper, the Collective Computing Model (CCM),is a variant of the well-known Bulk Synchronous Parallel (BSP) model. The synchronicityimposed by the BSP model restricts the set of available algorithms and prevents theoverlapping of computation and communication. Other models, like the LogP model, allowasynchronous computing and overlapping but depend on the use of specific libraries. TheCCM describes a system exploited through a standard software platform providing facilitiesfor group creation, collective operations and remote memory operations. Based in the BSPmodel, two kinds of supersteps are considered: Division supersteps and Normal supersteps.The structure of divisions produced by the Division Functions and the partnership relationamong processors give place to communication patterns among processors that aretopologically similar to a hypercube. We have named the resulting structures DynamicPolytopes To illustrate these concepts, the Fast Fourier Transform Algorithm is used.Computational results prove the accuracy of the model in four different parallel computers:a Parsytec Power PC, a Cray T3E, a Silicon Graphics Origin 2000 and a Digital AlphaServer
