Abstract
This paper covers the design of processor arrays for algorithms with uniform dependencies. The design constraint is a limited latency of the resulting processor array. As objective of the design the minimization of the costs for an implementation of the processor array in silicon is considered.
Our approach starts with the determination of a set of proper linear allocation functions with respect to the number of processors. It follows the computation of a uniform affine scheduling function. Thereby, a module selection and the size of partitions of a following partitioning is determined. A proposed linearization of the arising optimization problems permits the application of integer linear programming.
The research was supported by the ”Deutsche Forschungsgemeinschaft”, in the project A1/SFB358.
Chapter PDF
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
A. Darte, Y. Robert: ”Constructive Methods for Scheduling Uniform Loop Nests”, IEEE Trans. on Parallel and Distributed Systems, Vol. 5, No. 8, pp. 814–822, 1994
D. Fimmel, R. Merker: ”Determination of the Processor Functionality in the Design of Processor Arrays”, Proc. Int. Conf. on Application-Specific Systems, Architectures and Processors, pp. 199–208, Zürich, 1997
D. Fimmel, R. Merker: ”Determination of an Optimal Processor Allocation in the Design of Massively Parallel Processor Arrays”, Proc. Int. Conf. on Algorithms and Parallel Processing, pp. 309–322, Melbourne, 1997
K. Jainandunsing: ”Optimal Partitioning Scheme for Wavefront/Systolic Array Processors”, IEEE Proc. Symp. on Circuits and Systems, 1986
R.M. Karp, R.E. Miller, S. Winograd: ”The organization of computations for uniform recurrence equations”, J. of the ACM, vol.14, pp. 563–590, 1967
D.I. Moldovan: ”On the Design of Algorithms for VLSI Systolic Arrays”, Proceedings of the IEEE, pp. 113–120, January 1983
P. Quinton: ”Automatic Synthesis of Systolic Arrays from Uniform Recurrent Equations”, IEEE 11-th Int. Symp. on Computer Architecture, Ann Arbor, pp. 208–214, 1984
S.K. Rao: ”Regular Iterative Algorithms and their Implementations on Processor Arrays”, PhD thesis, Stanford University, 1985
J. Rossel, F. Catthoor, H. De Man: ”Extension to Linear Mapping for Regular Arrays with Complex Processing Elements”, Proc. Int. Conf. on Application-Specific Systems, Architectures and Processors, pp. 156–167, Princeton, 1990
A. Schrijver: Theory of Linear and Integer Programming, John Wiley & Sons, New York, 1986
A. Schubert, R. Merker: ”Systolization of Recursive Algorithms with DESA”, in Proc. 5th Int. Workshop Parcella ’90, Mathematical Research, G. Wolf, T. Legendi, U. Schendel (eds.), vol. 2, Akademie-Verlag Berlin, 1990, pp. 267–276, 1994
J. Teich: ”A Compiler for Application-Specific Processor Arrays”, PhD thesis, Univ. of Saarland, Verlag Shaker, Aachen, 1993
L. Thiele: ”Resource Constraint Scheduling of Uniform Algorithms”, Int. Journal on VLSI and Signal Processing, Vol. 10, pp. 295–310, 1995
Y. Wong, J.M. Delosme: ”Optimal Systolic Implementation of n-dimensional Recurrences”, Proc. ICCD, pp. 618–621, 1985
Y. Wong, J.M. Delosme: ”Optimization of Processor Count for Systolic Arrays”, Research Report YALEU/DCS/RR-697, Yale Univ., 1989
X. Zhong, S. Rajopadhye, I. Wong: ”Systematic Generation of Linear Allocation Functions in Systolic Array Design”, J. of VLSI Signal Processing, Vol. 4, pp. 279–293, 1992
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Fimmel, D., Merker, R. (1998). Design of processor arrays for real-time applications. In: Pritchard, D., Reeve, J. (eds) Euro-Par’98 Parallel Processing. Euro-Par 1998. Lecture Notes in Computer Science, vol 1470. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0057962
Download citation
DOI: https://doi.org/10.1007/BFb0057962
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-64952-6
Online ISBN: 978-3-540-49920-6
eBook Packages: Springer Book Archive