Efficient mappings of pyramid networks

We consider primarily the simulation of large networks by smaller ones-an important consideration, because interconnection networks are typically of a fixed size, and yet applications may employ networks of a larger size. Current research (Dingle and Sudborough, 1993) describes methods to simulate common data structures and network architectures on the pyramid. However, these simulations assume that the pyramid grows with the size of the network or data structure. Because unbounded growth is not feasible, we address the issue of mapping several points of the guest data structure or network to a single host processor. We determine how a small pyramid may efficiently simulate the computation of a larger pyramid as well as that of tree networks