Issue No. 08 - August (1993 vol. 4)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/71.238626
<p>The authors present the scalability analysis of a parallel fast Fourier transform (FFT)algorithm on mesh and hypercube connected multicomputers using the isoefficiencymetric. The isoefficiency function of an algorithm architecture combination is defined asthe rate at which the problem size should grow with the number of processors to maintaina fixed efficiency. It is shown that it is more cost-effective to implement the FFTalgorithm on a hypercube rather than a mesh despite the fact that large scale meshesare cheaper to construct than large hypercubes. Although the scope of this work islimited to the Cooley-Tukey FFT algorithm on a few classes of architectures, themethodology can be used to study the performance of various FFT algorithms on avariety of architectures such as SIMD hypercube and mesh architectures and sharedmemory architecture.</p>
Index Termsscalability; FFT; parallel computers; parallel fast Fourier transform; mesh; hypercube;multicomputers; isoefficiency metric; problem size; Cooley-Tukey FFT algorithm; SIMDhypercube; shared memory architecture; fast Fourier transforms; parallel algorithms
V. Kumar and A. Gupta, "The Scalability of FFT on Parallel Computers," in IEEE Transactions on Parallel & Distributed Systems, vol. 4, no. , pp. 922-932, 1993.