On the Performance of Combined Data Flow and Control Flow Systems: Experiments Using Two Iterative Algorithms

Abstract Improved multiprocessor performance can be attained by combining data flow and control flow concepts. This type of combined architecture is characterized and several examples of previously proposed machines are given. A new model that permits the analysis of such systems is presented and performance measures are defined. This model is then used to analyze the performance of the algorithms under a wide variety of combined systems. The results of these experiments show that partition size is a major factor in the performance of such systems and an optimal size may be found for given system parameters.

[1]  C. A. Petri.  Communication with automata , 1966 .

[2]  Robert M. Keller,et al.  Simulated Performance of a Reduction-Based Multiprocessor , 1984, Computer.

[3]  C. Petri.  Kommunikation mit Automaten , 1962 .

[4]  W Händler,et al.  The impact of classification schemes on computer architecture , 1986 .

[5]  Daniel Gajski,et al.  Essential Issues in Multiprocessor Systems , 1985, Computer.

[6]  David A. Padua,et al.  A Second Opinion on Data Flow Machines and Languages , 1982, Computer.

[7]  C. V. Ramamoorthy,et al.  Performance Evaluation of Asynchronous Concurrent Systems Using Petri Nets , 1980, IEEE Transactions on Software Engineering.

[8]  David J. Kuck,et al.  DEPENDENCE DRIVEN COMPUTATION. , 1981 .

[9]  Michael J. Flynn,et al.  Very high-speed computing systems , 1966 .

[10]  John W. Backus,et al.  Can programming be liberated from the von Neumann style?: a functional style and its algebra of programs , 1978, CACM.

[11]  C. Ramchandani,et al.  Analysis of asynchronous concurrent systems by timed petri nets , 1974 .

[12]  R. Karp,et al.  Properties of a model for parallel computations: determinacy , 1966 .

[13]  James R. McGraw,et al.  The Piecewise Data Flow Architecture: Architectural Concepts , 1983, IEEE Transactions on Computers.

[14]  Michael K. Molloy.  Discrete Time Stochastic Petri Nets , 1985, IEEE Transactions on Software Engineering.

[15]  Zhiwei Xu,et al.  Remps: A Reconfigurable Multiprocessor for Scientific Supercomputing , 1985, ICPP.