Design of bit-level systolic convolvers for image processing

  • Nikolay Petkov
Algorithms And Techniques
Part of the Lecture Notes in Computer Science book series (LNCS, volume 399)


A method for the design of bit-level systolic FIR filters with constant coefficients is presented. A convolution is represented as a sum of convolutions with coefficients which are powers of 2. It is then implemented in a two-dimensional bit-level systolic array of full adders. The worst-case space-time requirements of the algorithm involved are superior to the space-time requirements of the systolic convolution algorithms previously known.

Indexing terms

VLSI bit-level systolic arrays convolution 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. [1]
    GONZALEZ, R.C., and WINZ, P.: "Digital Image Processing" (Reading, Massachusetts: Addison-Wesley, 1987)Google Scholar
  2. [2]
    SLOBODA, F.: "Toeplitz matrices, homothety, and least-squares approximation", in D.J. Evans and C. Sutti (eds.), Proc. Int. Meeting on Parallel Computing, Verona, 1988 (Bristol: Adam Hilger, 1989)Google Scholar
  3. [3]
    PETKOV, N. and SLOBODA, F.: "Bit-level systolic array for digital curve smoothing", Parallel Computing (Amsterdam: North-Holland, 1989) in printGoogle Scholar
  4. [4]
    SLOBODA, F., and Priecel, J.: "String processing algorithms for length and curvature calculation of digital curves", 5th Int. Conf. Image Analysis and Processing, Positano, ItalyGoogle Scholar
  5. [5]
    DANIELSSON, P. E.: "Serial/parallel convolvers", IEEE Trans. Computers C-33 (1984) 7, pp. 652–667Google Scholar
  6. [6]
    KUNG, H.T., and LEISERSON, C.E.: "Systolic arrays (for VLSI)", Sparse Matrix Proc. 1978 (Society for Industrial and Applied Mathematics, 1979) pp.256–282.Google Scholar
  7. [7]
    KUNG, H. T., and LEISERSON, C. E.: "Algorithms for VLSI processor arrays", in C. Mead and L. Conway: "Introduction to VLSI Systems" (Reading, Massachusetts: Addison-Wesley, 1980) sect. 8.3Google Scholar
  8. [8]
    KUNG, H. T.: "Special-purpose devices for signal and image processing: an opportunity in very large scale integration (VLSI)", SPIE 241, Real-Time Signal Processing III (1980), pp. 76–84Google Scholar
  9. [9]
    KUNG, H. T.: "The structure of parallel algorithms", Advances in Computers 19 (New York: Academic, 1980), pp.65–111Google Scholar
  10. [10]
    FOSTER, M. J., and KUNG, H. T.: "The design of special purpose VLSI chips", Computer 13 (1980) 1, pp.26–40.Google Scholar
  11. [11]
    KUNG, H.T.: "Why systolic architectures", Computer 15 (1982) 1, pp. 37–46.Google Scholar
  12. [12]
    PETKOV, N.: "Systolische Algorithmen und Arrays" (Berlin: Akademie-Verlag, 1989)Google Scholar
  13. [13]
    McWHIRTER, J.G., WOOD, D., WOOD, K.W., EVANS, R.A., McCANNY, J.V., and McCABE, A.P.H.: "Multi-bit convolution using a bit level systolic array", IEEE Trans. Circuits & Systems, CAS-32 (1985) 1, pp.95–99Google Scholar
  14. [14]
    McCANNY, J.V., EVANS, R.A., and McWHIRTER, J.G.: "Uni-directional data flow applied to bit level systolic arrays for correlation/convolution", Proc. Int'l Workshop on Systolic Arrays, Oxford, 2–4 July 1986, pp.I.1.1-I.1.5Google Scholar
  15. [15]
    PETKOV-TURKED JIEV, N.: "Bit-organized systolic convolution algorithm", ibid., pp.I.1.1–I.1.10Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 1989

Authors and Affiliations

  • Nikolay Petkov
    • 1
  1. 1.Central Inst. of Cybernetics and Info. ProcessingInt'l Lab. for Image Proc. & Comput. GraphicsBerlinGDR

Personalised recommendations