Scalable parallel FFT for spectral simulations on a Beowulf cluster

摘要

The implementation and performance of the multidimensional Fast Fourier Transform (FFT) on a distributed memory Bewulf cluster is examined. We focus on the three-dimen- sional (3D) real transform, an essential computational component of Galerkin and pseudo- spectral codes. The approach studied is a 1D domain decomposition algorithm that relies on communication-intensive transpose operation involving P processors.