Shared Memory Multistage Clustering Structure: An Efficient Structure for Massively Parallel Processing Systems

In this paper a new structure is proposed for the massive parallel processing systems. This structure is expandable in vertical and horizontal manner and cover many of the previous computer designs. The queuing theory and Jackson queuing network is applied for constructing an analytical model for the proposed structure. This model gives a closed-form solution for the system performance metrics, such as processor’s waiting time, system processing power, and so on. Two novel points in development of these analytical models are: application of open queuing network rules for analyzing a closed queuing network, and calculation of the input rate of each service center as a function of the input rate for previous center. The model can be used for evaluating the MPP system or optimizing its specification on design space.