Efficient personalized communication on wormhole networks

Bridging models, such as the BSP (bulk synchronous parallel) model, tend to abstract the characteristics of interconnection networks using a small set of parameters, by dividing the computation into supersteps and organizing the communication into global patterns called h-relations. In this paper, we evaluate (through experimental results conducted on a wormhole-routed 2D torus and a quaternary fat-tree with 256 processing nodes) the execution time of three families of h-relations with variable degree of imbalance. We also prove a strong result that links the communication performance of the fat-tree with the BSP abstraction of the interconnection network. Given a generic h-relation, we can provide a value of g (the gap) that, in the worst case, slightly overestimates the completion time and is very close to optimality.