In: Simulation, Vol. 73, No. 2, pages 100-110. 1999.
Abstract: The major advantages of parallel processing systems are their great reliability and high performance. A class of massively parallel computing systems is the data flow machines. These machines work on the basis of data flow rather than control flow. This paper presents a reliability analysis of date flow machines using a graph theoretical approach. Three machines are considered here. They are the MIT, DDP and LAU static data flow machines. The data flow graph has been employed as a natural tool for representing that class of machines. The isomorphism between Petri nets and data flow graphs has been exploited to detect whether the consistency constraints are satisfied during various operational conditions. Such a graph is extended so that a timed data flow mode has been constructed. This model integrates both the reliability features dependent on the system structure and the performance characteristics dependent on the components behavior. Moreover, a productivity index is introduced for evaluating the three machines.
Keywords: Petri nets, graph theoretical approach, parallel processing, static dataflow machines, timed data flow model.
Back to the Petri Nets Bibliography