结构静力有限元分层并行计算方法

A HIERARCHICAL PARALLEL COMPUTING APPROACH FOR STRUCTURAL STATIC FINITE ELEMENT ANALYSIS

根据分布式存储并行计算机的体系结构特点,提出了一种结构静力有限元分层并行计算方法.该方法在两级分区两次缩聚策略的基础上不仅实现了大量数据的分布式存储,提高了数据的内存访问速率;而且实现了计算过程的三层并行,有效提高了通信效率;此外,它还进一步降低了界面方程的规模,大幅度减少了界面方程的求解时间.因此,它能够充分利用分布式存储并行计算机的体系结构特点提升大规模并行计算效率.最后通过典型数值算例验证了该方法的正确性和有效性.

According to the architecture characteristics of distributed memory parallel computers, a hierarchical parallel computing approach for structural static finite element analysis is proposed. Based on the two-level partitioning and twice condensation strategies, the proposed method not only improves memory access rate through the distributed storage of a large amount of data, but also significantly improves communication rate with the three-layer parallelization of the computational procedure. Moreover, the interface equations' size is further reduced and its solution time is considerably reduced. Thus, it can improve the efficiency rates of parallel computing of large-scale problems by fully exploiting the architecture characteristics of distributed memory parallel computers. Finally, typical numerical experiments were used to validate the correctness and efficiency of the proposed method.