摘要
提出并实现了一种基于共享内存并行平台的OpenMP并行多层快速多极子算法.结合OpenMP并行算法开发的要点和多层快速多极子算法数据分布的特性,对多层快速多极子的填充矩阵模块、矩阵向量相乘中的远相互作用部分进行了OpenMP并行化设计.在分析调度方式和循环次序对计算效率的影响的基础上,提出了一种高效的OpenMP并行多层快速多极子方案.数值实验表明,并行算法与串行精度一致,OpenMP并行算法具有较好的并行效率.
A parallel multilevel fast multipole algorithm（MLFMA） based on OpenMP is proposed and implemented for shared memory parallel platform.According to requirements of efficient OpenMP parallelization and different numerical characteristics of different parts in MLFMA,the parallelization scheme is carefully designed for the establishment of near-field interaction matrix as well as the far-field interaction in matrix vector multiplication in MLFMA.Numerical experiments show that the parallel MLFMA is efficient and has a consistent accuracy with the sequential MLFMA.
出处
《北京理工大学学报》
EI
CAS
CSCD
北大核心
2012年第2期164-169,共6页
Transactions of Beijing Institute of Technology
基金
国家自然科学基金重点资助项目(10832002)
国家自然科学基金资助项目(60901005)
北京理工大学优秀青年资助计划(2008Y0102)
北京理工大学基础研究基金资助项目(20090542001)
