Abstract
An expandable two-dimensional systolic array consisting of N homogeneous processing elements in a rectangular sturcture to compute the one-dimensional DFT transform is proposed. DFT of size N = M2 can be computed in 2M steps of pipelined operations, achieving the optimal Area–Time complexity of AT2 = O(N2). The architecture is based on a new approach that exploits the symbiosis between the one-dimensional systolic arrays of Kung [6] and Chang [7]. After a two-dimensional formulation with Common Factor Algorithm, recursive time and frequency extractions are applied to the column and row transforms respectively. Twiddle factor multiplication is integrated gracefully into the row recursion. The rearrangement of the input data enables the recursive operations to be pipelined orthogonally in the “dual-mode” processing elements. The proposed array structure is modular and expandable. A DFT of size 2LN can be readily computed with 2L N-size arrays abutted together without reconfiguration. VHDL modules have been written and simulated successfully for the proposed architecture.
Similar content being viewed by others
References
J.D. Ullman, Computational Aspects of VLSI, Computer Science Press, 1984.
C.D. Thompson, "Fourier transform in VLSI," IEEE Trans. Comput., Vol. 32, No. 11, pp. 1047–1057, Nov. 1983.
G. Bilardi and M. Sarrafzadeh, "Optimal discrete Fourier transform in VLSI," VLSI: Algorithms and Architectures, P. Bertolazzi and F. Luccio <nt>(Eds.)</nt>, North-Holland, pp. 79–89, 1985.
H. Stone, "Parallel processing with the perfect shuffle," IEEE Trans. Comput., Vol. 20, No. 2, pp. 153–161, Feb. 1971.
F.P. Preparata and J. Vuillemin, "The cube-connected cycles: A versatile network for parallel computation," Communication of the ACM, Vol. 24, No. 5, pp. 300–309, May 1981.
H.T. Kung, "Special-purpose device for signal and image processing: An opportunity in very large scale integration (VLSI)," Proc. SPIE Int. Soc. Opt. Eng., Vol. 241, pp. 74–84, 1980.
L.-W. Chang and M.-Y. Chen, "A new systolic array for Discrete Fourier transform," IEEE Trans. Acoust., Speech, Signal Processing, Vol. 36, No. 10, pp. 1665–1666, Oct. 1988.
C.S. Burrus, "Index mapping for multidimensional formulation of the DFT and convolution," IEEE Trans. Acoust., Speech, Signal Processing, Vol. 25, No. 3, pp. 239–242, June 1977.
E.E. Swartzlander, W.K.W. Young, and S.J. Joseph, "A radix 4 delay commutator for fast Fourier transform processor implementation," IEEE J. Solid-State Circuits,Vol. 19, No. 5, pp. 702–709, Oct. 1984.
G. Bi and E.V. Jones, "A pipelined FFT processor for wordsequential data," IEEE Trans. Acoust., Speech, Signal Processing, Vol. 37, No. 12, pp. 1982–1985, Dec. 1989.
J. Choi and V. Boriakoff, "A new linear systolic array for FFT computation," IEEE Trans. Circuits Syst. II, Vol. 39, No. 4, pp. 236–239, April 1992.
E.E. Swartzlander, V.K. Jain, and H. Hikawa, "A radix 8 wafer scale FFT processor," J. VLSI Signal Processing,Vol. 4, Nos. 2/3, pp. 165–176, May 1992.
T. Chen and L. Zhu, "An expandable column FFT architecture using circuit switching networks," Journal of VLSI Signal Processing, Vol. 6, No. 3, pp. 243–257, Dec. 1993.
V. Szwarc, L. Desormeaux, W. Wang, C.P.S. Yeung, C.H. Chan, and T.A. Kwasniewski, "A chip set for pipeline and parallel pipeline FFT architechtures," J. VLSI Signal Processing, Vol. 8, No. 3, pp. 253–265, Dec. 1994.
F.P. Preparata, "Amesh-connected area–time optimal VLSI multiplier of large integers," IEEE Trans. Comput., Vol. 32, No. 2, pp. 194–198, Feb. 1983.
H.C. Card, "VLSI computations: From physics to algorithms," INTEGRATION, the VLSI journal, Vol. 5, pp. 247–273, 1987.
M.-K. Lee, K.-W. Shin, and J.-K. Lee, "A VLSI array procesor for 16-point FFT," IEEE J. Solid-State Circuits, Vol. 26, No. 9, pp. 1286–1292, Sep. 1991.
H.F. Silverman, "An introduction to programming the wingrad fourier transform algorithm (WFTA)," IEEE Trans. Acoust., Speech, Signal Processing, Vol. 25, No. 2, pp. 152–165, April 1977.
R.M. Owens and M.J. Irwin, "The arithmetic cube," IEEE Trans. Comput., Vol. 36, No. 11, pp. 1342–1348, Nov. 1987.
J.L. Aravena, "Tripple matrix product architecture for fast signal processing," IEEE Trans. Circuits Syst., Vol. 35, No. 1, pp. 119–122, Jan. 1988.
K.J. Jones, "2D systolic solution to discrete Fourier transform," IEE Proc. E, Vol. 136, No. 3, pp. 211–216, 1989.
K.J. Jones, "Parallel DFT computation on bit-serial systolic processor array," IEE Proc. E, Vol. 140, No. 1, pp. 10–18, 1993.
H. Lim and E. Swartzlander, "A systolic array for 2D DFT and 2D DCT," Proc. ICASAP'94, pp. 123–131, Aug. 1994.
C. Moraga, "On a case of symbiosis between systolic arrays" INTEGRATION, The VLSI Journal, Vol. 2, pp. 243–253, 1984.
H. Lim and E. Swartzlander, "Efficient systolic arrays for FFT algorithms," Proc. 29th Asilomar Conf. on Signal System and Computers, pp. 141–145, Oct. 1995.
S. He and M. Torkelson, "A systolic array implementation of common factor algorithm to compute DFT," Proc. ISPAN'94, Kanazawa, Japan, pp. 374–381, Dec. 1994.
S. He, "Concurrent VLSI architectures for DFT computing and algorithms for multi-output logic decomposition," Ph.D. thesis, Lund University, Dept. of Applied Electronics, Nov. 1995.
S. He and M. Torkelson, "A new expandable 2D systolic array for DFT computation based on symbiosis of 1D arrays," Proc. IEEE ICA3 PP'95, Brisbane, Australia, pp. 12–19, April 1995.
Rights and permissions
About this article
Cite this article
He, S., Torkelson, M. An Orthogonal Time-Frequency Extraction Approach to 2D Systolic Architecture for 1D DFT Computation. The Journal of VLSI Signal Processing-Systems for Signal, Image, and Video Technology 21, 61–70 (1999). https://doi.org/10.1023/A:1008027706032
Published:
Issue Date:
DOI: https://doi.org/10.1023/A:1008027706032