Implementing FFT using SPMD style of OpenMP

In this paper, we introduce a parallel version of the Fast Fourier Transform that was created using OpenMP in SPMD style. Our implementation is non-recursive and is based on the conventional Cooley-Tukey algorithm written in C. The aim of this work is show the potential benefit of writing our FFT algorithm in SPMD style which enabled an efficient use of multi-core machines. Our experimental results are based on FFT code running on an AMD-Opteron TM8200 with four 2-core CPUs. The experimental results show that the performance of our new parallel code on an 8-core shared-memory machine is promising.