Expandable MDC-based FFT architecture and its generator for high-performance applications

Fast Fourier Transform (FFT) cores are extensively used in digital signal processing (DSP) applications like communication systems. Many pipelined FFT architectures optimized for different objectives have been proposed in past few decades. Though a fixed pipelined FFT architecture can generally provide good throughput at reasonable hardware cost, it may still fail to meet the performance demand for throughput-hungry design cases. In this paper, we propose an expandable MDC-based FFT architecture as well as the corresponding hardware design generator, which is capable of automatically producing an FFT core under a given throughput constraint. The experimental results show that the proposed methodology can generate smaller and power-efficient implementations than the existing foldable MDC-based FFT architecture.

[1]  Alvin M. Despain,et al.  Fourier Transform Computers Using CORDIC Iterations , 1974, IEEE Transactions on Computers.

[2]  Franz Franchetti,et al.  Formal datapath representation and manipulation for implementing DSP transforms , 2008, 2008 45th ACM/IEEE Design Automation Conference.

[3]  James C. Hoe,et al.  Automatic generation of customized discrete Fourier transform IPs , 2005, Proceedings. 42nd Design Automation Conference, 2005..

[4]  J. Tukey,et al.  An algorithm for the machine calculation of complex Fourier series , 1965 .

[5]  Shousheng He,et al.  Designing pipeline FFT processor for OFDM (de)modulation , 1998, 1998 URSI International Symposium on Signals, Systems, and Electronics. Conference Proceedings (Cat. No.98EX167).

[6]  J. F. Sevillano,et al.  Radix $r^{k} $ FFTs: Matricial Representation and SDC/SDF Pipeline Implementation , 2009, IEEE Transactions on Signal Processing.

[7]  C. K. Yuen,et al.  Theory and Application of Digital Signal Processing , 1978, IEEE Transactions on Systems, Man, and Cybernetics.

[8]  Mats Torkelson,et al.  A new approach to pipeline FFT processor , 1996, Proceedings of International Conference on Parallel Processing.

[9]  Rainer Storn Radix-2 FFT-pipeline architecture with reduced noise-to-signal ratio , 1994 .

[10]  Alvin M. Despain,et al.  Pipeline and Parallel-Pipeline FFT Processors for VLSI Implementations , 1984, IEEE Transactions on Computers.

[11]  Keshab K. Parhi,et al.  High-Throughput VLSI Architecture for FFT Computation , 2007, IEEE Transactions on Circuits and Systems II: Express Briefs.