Hierarchically Parallelized Constrained Nonlinear Solvers with AutomatedSubstructuring

摘要

This paper develops a parallelizable multilevel multiple constrained nonlinearequation solver. The substructuring process is automated to yield appropriately balanced partitioning of each succeeding level. Due to the generality of the procedure,sequential, as well as partially and fully parallel environments can be handled. This includes both single and multiprocessor assignment per individual partition. Several benchmark examples are presented. These illustrate the robustness of the procedure as well as its capability to yield significant reductions in memory utilization and calculational effort due both to updating and inversion.