DEVELOPING OF MULTISTAGE VIRTUAL SHARED MEMORY MODEL FOR CLUSTER BASED PARALLEL SYSTEMS

摘要

In this paper, we proposed a new multistage virtual shared memory model for cluster based parallel systems. This model can be expanded in hierarchical manner and covered many of the previous clusters of parallel system designs. Queuing theory and Jackson queuing networks are applied for constructing an analytical model. This model gives a closed-form solution for the system performance metrics, such as processor waiting time and system processing power. In development of this analytical model we used open queuing network rules for analyzing a closed queuing network and calculate the input rate of each service centre as a function of the input rate for previous service centre. The model can be used for evaluating the cluster based parallel processing systems or optimizing its specification on design space.