Design and Implementation of Floating Point FFT Processor using VHDL
IOSR Journal of VLSI and Signal processing · 2013
The Fast Fourier Transform (FFT) is a capable algorithm to compute the Discrete Fourier Transform (DFT) and it's inverse.It has a number of applications in the field of signal processing.The usual butterfly FFT design requires needless computations and data storage which lead to unnecessary power consumption.Use of the IEEE-754 standard 32-bit floating-point format also facilitates using the Fast Fourier Transform (FFT) processors.This paper describes two fused floating-point operations and applies them to the implementation of Fast Fourier Transform (FFT) processors using VHDL.The fused operations are a two-term dot product and add-subtract unit.The FFT processors use "butterfly" operations that consist of multiplications, additions, and subtractions of complex valued data.The statistical results of the fused implementations are slightly more accurate.