An efficient radix-2 fast Fourier transform processor with ganged butterfly engines on field programmable gate arrays
- 22 April 2011
- journal article
- Published by Zhejiang University Press in Journal of Zhejiang University SCIENCE C
- Vol. 12 (4) , 323-329
Abstract
We present a novel method to implement the radix-2 fast Fourier transform (FFT) algorithm on field programmable gate arrays (FPGA). The FFT architecture exploits parallelism by having more pipelined units in the stages, and more parallel units within a stage. It has the noticeable advantages of high speed and more efficient resource utilization by employing four ganged butterfly engines (GBEs), and can be well matched to the placement of the resources on the FPGA. We adopt the decimation-infrequency (DIF) radix-2 FFT algorithm and implement the FFT processor on a state-of-the-art FPGA. Experimental results show that the processor can compute 1024-point complex radix-2 FFT in about 11 µs with a clock frequency of 200 MHz.Keywords
This publication has 14 references indexed in Scilit:
- A pipelined architecture for normal I/O order FFTJournal of Zhejiang University SCIENCE C, 2011
- Resource-efficient acceleration of 2-dimensional Fast Fourier Transform computations on FPGAs2009
- Implementation of a reconfigurable Fast Fourier Transform application to digital terrestrial television broadcasting2009
- Performance comparison of FPGA, GPU and CPU in image processing2009
- Low-power application-specific processor for FFT computations2009
- A Pipelined FFT Architecture for Real-Valued SignalsIEEE Transactions on Circuits and Systems I: Regular Papers, 2009
- Flexible-length Fast Fourier Transform for COFDM2008
- Design and implementation of a 1024-point pipeline FFT processor1998
- A new approach to pipeline FFT processor1996
- An algorithm for the machine calculation of complex Fourier seriesMathematics of Computation, 1965