Memory-bank based radix-22 fast fourier transform

A memory-bank based reconfigurable radix-2
²
Fast Fourier Transform (FFT) is proposed in this paper. It can be configured to different size which ranges between 16 and 1024 points. Compared with the other methods, our experiments show that the proposed FFT processor can reduce more power consumption. It is very suitable to be applied in the speech processing, image processing, and communication system.