Parallelization and performance analysis of the Cooley-Tukey FFT algorithm for shared-memory architectures
The authors present a study of parallelization of the Cooley-Tukey radix two FFT algorithm for MIMD (nonvector) architectures. Parallel algorithms are presented for one and multidimensional Fourier transforms. From instruction traces obtained by executing Fortran kernels derived from our algorithms, they determined the precise instructions to be executed by each processor in the parallel system. They used these instruction traces to predict the performance of the IBM Research Parallel Processing Prototype, RP3, as a computer of FFT's. The performance results are depicted in graphs included in this paper.