Abstract
We describe the modelling and simulation of a pseudosystolic processor for matrix algorithms. The processor follows the decoupled access/execute model of computation, and is therefore composed of two programmable units: an Access Unit (AU) and a Processing Unit (PU). Both units work independently and synchronize their operation through queues.
The modelling and simulation are based on a formal specification of the processor written in Verilog HDL, a high level language for hardware description. Such a specification describes the processor at the behavioral level (instruction set architecture) and at the structural level (register transfer architecture). Performance measures can be obtained through the simulation, making it possible to evaluate tradeoffs in the instruction set design as well as in lower levels of the architecture.
Hardware modelling and simulation are helping us to find bottlenecks in the architecture. Moreover, they are allowing us to evaluate the effectiveness of several features and their impact on overall system performance, thus proving to be an important tool in the development of complex digital systems.
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.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
R. Lipsett, E. Marschner, and M. Shahdad. VHDL-The Language. IEEE Design and Test of Computers, pages 28–41, April 1986.
E. Sternheim, R. Singh, and Y. Trivedi. Digital Design with Verilog HDL. Automata Publishing Company, Cupertino, CA, 95014, 1990.
D.R. Coelho. VHDL: a call for standards. In 25th ACM/IEEE Design Automation Conference, pages 40–47, 1988.
H.T. Kung. Why systolic architectures? IEEE Computer, 15(1):37–46, January 1982.
M. Annaratone, E. Arnould, T. Gross, H.T. Kung, M. Lam, O. Menzilcioglu, and J.A. Webb. The Warp computer: Architecture, implementation and performance. IEEE Transactions on Computers, C-36(12):1523–1538, December 1987.
J. G. Nash, K.W. Przytula, and S. Hansen. The systolic/cellular system for signal processing. IEEE Computer, 20(7):96–97, July 1987.
J. H. Moreno, M.E. Figueroa, and T. Lang. Linear pseudosystolic array for partitioned matrix algorithms. To be published in Journal of VLSI and Signal Processing, 1991.
J.H. Moreno and M.E. Figueroa. A decoupled access/execute processor for matrix algorithms: architecture and programming. In International Conference on Application-Specific Array Processors, Barcelona, Spain, September 1991.
J.H. Moreno and T. Lang. Matrix computations on systolic-type meshes: An introduction to the multi-mesh graph (MMG) method. IEEE Computer, 23(4):32–51, April 1990.
J.E. Smith. Decoupled access/execute computer architectures. ACM Transactions on Computer Systems, 2(4):289–308, November 1984.
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1992 Springer Science+Business Media New York
About this chapter
Cite this chapter
Figueroa, M.E., Moreno, J.H. (1992). Modelling and Simulation of a Pseudosystolic Processor for Matrix Algorithms. In: Baeza-Yates, R., Manber, U. (eds) Computer Science. Springer, Boston, MA. https://doi.org/10.1007/978-1-4615-3422-8_35
Download citation
DOI: https://doi.org/10.1007/978-1-4615-3422-8_35
Publisher Name: Springer, Boston, MA
Print ISBN: 978-1-4613-6513-6
Online ISBN: 978-1-4615-3422-8
eBook Packages: Springer Book Archive