Abstract
In this paper we present a method to implement one-dimensional Systolic Algorithms with data contraflow using Pipelined Functional Units. Some procedures are proposed which permit the systematic application of the method. The paper includes an example of application of the method to a one-dimensional systolic algorithm with data contraflow for QR decomposition.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
H.T. Kung and C.E. Leiserson, “Systolic Arrays (for VLSI)”, Sparse Matrix Proc. 1978, 1979,Society for Industrial and Applied Mathematics (SIAM), pp. 256–282; and inIntroduction to VLSI Systems, (C.A. Mead and L.A. Conway, eds.), Reading, MA: Addison-Wesley, 1980, Section 8.3.
D.I. Moldovan, “On the Analysis and Synthesis of VLSI Algorithms”,IEEE Trans. on Computers, vol. C-31, 1982, pp. 1121–1126.
P. Quinton, “Automatic Synthesis of Systolic Arrays from Uniform Recurrent Equations”,11th Int'l Annual Symp. on Computer Architecture, 1984, pp. 208–214.
J.A.B. Fortes, K.S. Fu, and B.W. Wah, “Systematic Design Approaches to Algorithmically Specified Systolic Arrays”,Computer Architecture Concepts and Systems, Amsterdam: North Holland 1988, pp. 455–494.
J.H. Moreno and T. Lang, “Matrix Computations on Systolic-Type Meshes: An Introduction to the Multimesh Graph Method”,Computer, vol. 23, 1990, pp. 32–51.
C.V. Ramamoorthy, “Pipeline Architecture”,Computing Surveys vol. 9, 1977, pp. 61–102.
C.E. Leiserson and J.B. Saxe, “Optimizing Synchronous Systems”,Proc. 22nd Annual Symp. on Foundations of Computer Science, Oct. 1981, pp. 23–26.
J.J. Navarro, J.M. Llaberiá y M. Valero, “Partitioning: An Essential Step in Mapping Algorithms Into Systolic Array Processors”,Computer, vol. 20, 1987, pp. 77–89.
J.J. Navarro, J.M. Llaberia, F. Núnez, and M. Valero, “LU Decomposition with No Size-Restriction Using a One-Dimensional Systolic Array Processor,”,Proc. Second Int'l Conf. Supercomputing, vol. 3, 1987, p. 218.
N. Torralba and J.J. Navarro, “A One-Dimensional Systolic Array for Solving Arbitrarily Large Lease Mean Square Problems,”Proc. Int'l Conf. on Systolic Arrays, 1988, pp. 103–112.
V.K. Prasanna Krumar and Y.C. Tsai, “Synthesizing Optimal Family of Linear Systolic Arrays for Matrix Computations,”Proc. International Conference on Systolic Arrays, 1988, pp. 51–60.
H.T. Kung and M.S. Lam, “Wafer-Scale Integration and Two-Level Pipelined Implementation of Systolic Arrays,”Journal of Parallel and Distributed Processing, Vol. 1, 1984.
D.I. Moldovan and J.A.B. Fortes “Partitioning and Mapping Algorithms into Fixed Size Systolic Arrays”,IEEE Trans. on Computers, Vol. C-35, 1986, pp. 1–12.
J.H. Moreno and T. Lang, “Graph-Based Partitioning of Matrix Algorithms for Systolic Arrays: Application to Transitive Closure”,Int'l Conf. on Parallel Processing 1988, pp. 28–31.
M. Valero-García, J.J. Navarro, J.M. Llabería y M. Valero, “Systematic Design of Two-level Pipelined Systolic Arrays with Data Contraflow”,Proc. IEEE Int'l Conf. on Circuits and Systems, 1988, pp. 2521–2525.
M. Valero-García, J.J. Navarro, J.M. Llabería y M. Valero, “Systematic Hardware Adaption of Systolic Algorithms”,Proc. 16th Annual Int'l Symp. on Computer Architecture 1989, pp 96–104.
M. Valero-García, J.J. Navarro, J.M. Llabería y M. Valero, “Implementation of Systolic Algorithms Using Pipelined Functional Units”,Int'l Conf. on Application Specific Array Processors 1990, pp. 272–283.
S.Y. Kung,VLSI Array Processors, Englewood Cliffs, NJ: Prentice Hall, 1988.
J.H. Patel and E.S. Davidson, “Improving the Throughput of a Pipeline by Insertion of Delays”,Proc. 3rd Annual Int'l Symp. on Computer Architecture, 1976, pp. 159–164.
D.H. Heller and I.C.F. Ipsen, “Systolic Networks for Orthogonal Equivalence Transformations and their Application”,Conference on Advanced Research in VLSI, Cambridge, MA: M.I.T. Press, 1982, pp. 113–122.
Floating Point Division/Square Root/IEEE Arithmetic WTL 1032/1033,Application Note, Weitek, 1983.
M. Valero-García, J.J. Navarro, J.M. Llabería, M. Valero, and Tomás Lang, “Mapping QR Decomposition of Banded Matrix on a 1D Systolic Array with Data Contraflow and Pipelined Functional Units”,Algorithms and Parallel VLSI Architectures II, Elsevier Science Publishers B.V. 1991.
M. Valero-García, N. Torralba, J.J. Navarro, and J.M. Llabería, “A Systolic Array for QR Decomposition Using Pipelined Functional Units”,Signal Processing V: Theories and Applications, Elsevier Science Publishers B.V. 1990. pp. 1595–1598.
Author information
Authors and Affiliations
Additional information
This work is supported by the Ministry of Education of Spain (CICYT TIC 299/89).
Rights and permissions
About this article
Cite this article
Valero-García, M., Navarro, J.J., Llabería, J.M. et al. A method for implementation of one-dimensional systolic algorithms with data contraflow using pipelined functional units. J VLSI Sign Process Syst Sign Image Video Technol 4, 7–25 (1992). https://doi.org/10.1007/BF00930615
Received:
Revised:
Published:
Issue Date:
DOI: https://doi.org/10.1007/BF00930615