Parallelization of the multilevel fast multipole algorithm using the OpenMP and VALU acceleration

Abstract

In this paper, a parallelization scheme by the combined use of the OpenMP and Vector Arithmetic Logic Unit (VALU) hardware acceleration is proposed to speed up the multilevel fast multipole algorithm (MLFMA) on the multicore computer architectures. This accelerating technology doesn't need to add any additional hardware equipment and could be applied to any other multicore computers whose all can obtain good accelerating effect. In addition, the spherical harmonics expansion based MLFMA is applied for reducing the memory costed. Some numerical results of typical objects are shown, through which comparative analyses are performed to give some concluding remarks.