Performance evaluation of parallel fast fourier transform on a multiprocessor workstation

Abstract

The fast Fourier transform (FFT) is very frequently used in various fields such as computer tomography, speech recognition, and image processing. As the area of computer applications has broadened, the quantity of data to be transformed has greatly increased. A parallel FFT is one way of achieving a fast transformation. Up until now, the experimental performance of parallel FFTs has not been sufficiently investigated on real multiprocessor systems. This paper describes an implementation of a parallel FFT on a multiprocessor workstation to investigate its real performance. The multiprocessor workstation provides parallel environments for both a multithread operating system and a multiprocess operating system. The performance of the parallel FFT is discussed with respect to cache protocols, floating-point coprocessors, and operating systems. © 1991.