论文信息 - Parallel out-of-core MLFMA on distributed-memory computer architectures

Parallel out-of-core MLFMA on distributed-memory computer architectures

We introduce a parallel implementation of the outof- core method for the multilevel fast multipole algorithm. This implementation utilizes disk space for storing large data structures, and it provides solutions of large-scale problems involving more than one billion unknowns within 2 TB memory.

Levent Gurel | Mert Hidayetoglu

[1] D. Wilton,et al. Electromagnetic scattering by surfaces of arbitrary shape , 1980 .

[2] Jiming Song,et al. Multilevel fast multipole algorithm for electromagnetic scattering by large complex objects , 1997 .

[3] Levent Gurel,et al. MLFMA memory reduction techniques for solving large-scale problems , 2014, 2014 IEEE Antennas and Propagation Society International Symposium (APSURSI).

[4] L. Gurel,et al. A Hierarchical Partitioning Strategy for an Efficient Parallelization of the Multilevel Fast Multipole Algorithm , 2009, IEEE Transactions on Antennas and Propagation.

[5] S. Velamparambil,et al. Analysis and performance of a distributed memory multilevel fast multipole algorithm , 2005, IEEE Transactions on Antennas and Propagation.