ISOEFFICIENT CALCULATION METHOD FOR DISCRETE FOURIER TRANSFORM
Abstract
The paper considers the issue of isoefficiency of MPP systems and heterogeneous CPU-GPU systems on the problem discrete Fourier transform. The development of parallel applications as its goal can have not only reduction of execution time, but also provision of opportunities to solve problems of greater dimensions. Feature parallelization of the algorithm includes the effective use of hardware when increasing the dimensionality of the problem an important characteristic of parallel computing.
Key words: isoefficiency, heterogeneous calculations, Fourier transform