ABSTRACT:
Communication overhead is one of the most important factors affecting
the performance of message passing multicomputers. We present evidence
(through the analysis of several parallel benchmarks) that there exists
communications locality, and that this locality is "structured". We
have devised a number of heuristics that can "predict" the target of
subsequent communication requests. This technique, can be applied to
reconfigurable interconnects to hide the communications latency by
reconfiguring the interconnect concurrently to the computation. By
comparing the inter-communication computation times of a number of
parallel benchmarks with some specific reconfiguration times, we argue
that the computation interval can be used to hide the concurrent
reconfiguration of the interconnect, and present the performance
enhancements of the proposed heuristics.