Embedded FFT hardware algorithm development using automated bi-dimensional scalable folding

This paper presents an original and unique embedded FFT hardware algorithm development process based on a systematic and scalable procedure for generating permutation-based address patterns for any power-of-2 transform size algorithm and any folding factor in a Kronecker Pease FFT hardware implementation. This is coupled by a procedure to perform automatic code generation of Kronecker FFT cores. The paper presents important results about twiddle address pattern generation and data switch multiplexing techniques. The paper also presents analyses and comparisons of the architecture design performance in terms of clock latency, accuracy, and hardware resources for benchmarking implementation efforts performed on the Xilinx Virtex-7 FPGA.

[1]  Pei-Yun Tsai,et al.  A Generalized Conflict-Free Memory Addressing Scheme for Continuous-Flow Parallel-Processing FFT Processors With Rescheduling , 2011, IEEE Transactions on Very Large Scale Integration (VLSI) Systems.

[2]  Martin Margala,et al.  A Novel Coefficient Address Generation Algorithm for Split-Radix FFT (Abstract Only) , 2015, FPGA.

[3]  Franz Franchetti,et al.  Computer Generation of Hardware for Linear Digital Signal Processing Transforms , 2012, TODE.

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

[5]  Keshab K. Parhi,et al.  An In-Place FFT Architecture for Real-Valued Signals , 2013, IEEE Transactions on Circuits and Systems II: Express Briefs.

[6]  R. W. Johnson,et al.  A methodology for designing, modifying, and implementing Fourier transform algorithms on various architectures , 1990 .

[7]  Chao Yang,et al.  A New Memory Address Transformation for Continuous-Flow FFT Processors with SIMD Extension , 2015, NCCET.

[8]  Bin Wu,et al.  A generalized conflict-free address scheme for arbitrary 2k-point memory-based FFT processors , 2016, 2016 IEEE International Symposium on Circuits and Systems (ISCAS).

[9]  Dionysios I. Reisis,et al.  Conflict free, parallel memory access for radix-2 FFT processors , 2012, 2012 19th IEEE International Conference on Electronics, Circuits, and Systems (ICECS 2012).

[10]  Sau-Gee Chen,et al.  A high-parallelism memory-based FFT processor with high SQNR and novel addressing scheme , 2016, 2016 IEEE International Symposium on Circuits and Systems (ISCAS).

[11]  Marshall C. Pease,et al.  An Adaptation of the Fast Fourier Transform for Parallel Processing , 1968, JACM.

[12]  Lewis Johnson,et al.  Conflict free memory addressing for dedicated FFT hardware , 1992 .

[13]  Mark Horowitz,et al.  Building Conflict-Free FFT Schedules , 2015, IEEE Transactions on Circuits and Systems I: Regular Papers.

[14]  M. Jimenez,et al.  An address generator approach to the hardware implementation of a scalable Pease FFT core , 2012, 2012 IEEE 55th International Midwest Symposium on Circuits and Systems (MWSCAS).