A parallel implementation of a fast multipole based 3-D capacitance extraction program on distributed memory multicomputers

Abstract

Very fast and accurate 3-D capacitance extraction is essential for interconnect optimization in ultra deep sub-micro designs (UDSM). Parallel processing provides an approach to reducing the simulation turn-around time. This paper examines the parallelization of the well known fast multipole based 3-D capacitance extraction program FASTCAP, which employs new preconditioning and adaptive techniques. To account for the complicated data dependencies in the unstructured problems, we propose a generalized cost function model, which can be used to accurately measure the workload associated with each cube in the hierarchy. We then present two adaptive partitioning schemes, combined with efficient communication mechanisms with bounded buffer size, to reduce the parallel processing overhead. The overall load balance is achieved through balancing the load at each level of the multipole computation. We report detailed performance results using a variety of standard benchmarks on 3-D capacitance extraction, on an IBM SP2.