PROCESSOR ALLOCATION IN EXTENDED HYPERCUBE MULTIPROCESSOR

Abstract

The Extended Hypercube (EH) architecture is suited for hierarchical expansion of multiprocessor systems. The basic module of EH consists of a k-cube and an additional node for handling communication - the Network Controller (NC). The NC in effect allows the Processor Element (FE) of each node to concentrate on computation rather than on communication. A particular advantage of EH is that they can support multiusers, each of which can be assigned an independent subcube of nodes by the operating system. In such an environment, especially one where requests for cubes of various dimensions arrive very frequently, it is of the prime importance to make judicious allocations of subcubes so that the EH does not become badly fragmented. Processor allocation problem is similar to the conventional memory allocation problem. The main objective in both the problems is to maximize the utilization of resources as well as minimize the inherent system fragmentation. Full recognition of various subcubes in the basic module i.e. hypercube is nontrivial due to specific structure of the hypercube. In this dissertation we address two processor allocation strategies namely Buddy strategy and Gray Code strategy and compare their performances.