Abstract
We present one-dimensional systolic arrays for performing two- or higher-dimensional convolution and resampling. These one-dimensional arrays are characterized by the fact that their I/0 bandwidth requirement is independent of the size of the convolution kernel. This contrasts with alternate two-dimensional array solutions, for which the I/0 bandwidth must increase as the kernel size increases. The proposed architecture is ideal for VLSI implementation—an arbitrarily large kernel can be handled by simply extending the linear systolic array with simple processors of the same type, so that one processor corresponds to each kernel element.
H.T. Kung was supported in part by the Office of Naval Research under Contracts N00014-76-C-0370, NR 044-422 and N00014-80-C-0236, NR 048-659
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
Similar content being viewed by others
References
H.T. Kung: Why Systolic Architectures? Computer Mag. 15, 37–46 (January 1982)
H.T. Kung, C.E. Leiserson: Systolic Arrays (for VLSI), in Sparse Matrix Proceedings 1978, ed. by I.S. Duff and G.W. Stewart (Soc. for Industrial and Applied Mathematics, 1979 ) pp. 256–282
A slightly different version appears in Introduction to VLSI Systems, ed. by C.A. Mead and L.A. Conway (Addison-Wesley, Reading, MA 1980) Sect.8.3
H.T. Kung, S.W. Song: A Systolic 2-D Convòlution Chip, in Multicomputers and Image Processing: Algorithms and Programs, ed. by K. Preston, Jr. and L. Uhr ( Academic, New York 1982 ) pp. 373–384
H.T. Kung, L.M. Ruane, D.W.L. Yen: Two-Level Pipelined Systolic Array for Multidimensional Convolution. Image and Vision Computing 1, 30–36 (1983)
An improved version appears as a CMU Computer Science Department technical report November 1982
R.A. Monzingo, T.W. Miller: Introduction to Adaptive Arrays ( Wiley, New York 1980 )
W.M. Gentleman, H.T. Kung: Matrix Triangularization by Systolic Arrays, in Real-Time Signal Processing IV, SPIE Symp. 298, 16–26 ( Soc. Photo-Optical Instrumentation Engineers, 1981 )
J.J. Symanski: NOSC Systolic Processor Testbed. Technical Report NOSC TD 588, Naval Ocean Systems Center (June 1983)
D.W.L. Yen, A.V. Kulkarni: Systolic Processing and an Implementation for Signal and Image Processing. IEEE Trans. C-31, 1000–1009 (1982)
A.L. Fisher, H.T. Kung, L.M. Monier, Y. Dohi: Architecture of the PSC: Architecture of the PSC, in Proc. 10th Annual Intern. Symp. Computer Architecture (June 1983) pp. 48–53
A.L. Fisher, H.T. Kung, L.M. Monier, H. Walker, Y. Dohi: Design of the PSC: A Programmable Systolic Chip, in Proc. 3rd Caltech Conf. on Very Large Scale Integration, ed. by R. Bryant ( Computer Science Press, Rockville, MD 1983 ) pp. 287–302
H.T. Kung, M. Lam: Fault-Tolerance and Two-Level Pipelining in VLSI Systolic Arrays, in Proc. Conf. Advanced Research in VLSI ( Artech House, Inc., Cambridge, MA, January 1984 ) pp. 74–83
H.T. Kung, W.T. Lin: An Algebra for VLSI Computation, in Elliptic Problem Solvers II, ed. by G. Birkhoff and A.L. Schoenstadt (Academic, New York 1983 ). Proc. Conf. on Elliptic Problem Solvers, January 1983
C.E. Leiserson, J.B. Saxe: Optimizing Synchronous Systems. J. VLSI and Computer Syst. 1, 41–68 (1983)
U. Weiser, A. Davis: A Wavefront Notation Tool for VLSI Array Design, in VLSI Systems and Computations, ed. by H.T. Kung, R.F. Sproull, and G.L. Steele, Jr. ( Computer Science Press, Rockville, MD 1981 ) pp. 226–234
A.L. Fisher, H.T. Kung: Special-Purpose VLSI Architectures: General Discussions and a Case Study, in VLSI and Modern Signal Processing ( Prentice-Hall, Reading, MA 1982 )
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1984 Springer-Verlag Berlin Heidelberg
About this chapter
Cite this chapter
Kung, H.T., Picard, R.L. (1984). One-Dimensional Systolic Arrays for Multidimensional Convolution and Resampling. In: Fu, Ks. (eds) VLSI for Pattern Recognition and Image Processing. Springer Series in Information Sciences, vol 13. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-47523-8_2
Download citation
DOI: https://doi.org/10.1007/978-3-642-47523-8_2
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-47527-6
Online ISBN: 978-3-642-47523-8
eBook Packages: Springer Book Archive