Certain investigations on parallel Computing for engineering Applications

Abstract

The need for faster computers is driven by the demands of both newlineComputation intensive applications in science and engineering and dataintensive newlineapplications in commerce The main motivation of parallelization of newlineany sequential algorithm is the desire to reduce the total execution time of the newlinealgorithm Parallel computing provides a way to reduce the time taken to newlineexecute a task by dividing the task between multiple computers that can work newlinesimultaneously to complete the job As the cost of dedicated parallel machines newlineis high computing on a cluster of workstations is a viable alternative for a newlinewide range of engineering applications The thesis aims at finding cost newlineeffective parallel implementation of algorithms on a cluster to solve complex newlineapplications The first part of the thesis addresses the issues that arise in the newlineparallel implementations The major issues of concern are load balancing, a newlinewidely used technique to balance the workload among multiple processors newlineand fault tolerance the ability to tolerate failures The proposed load newlinebalancing approach is based on a central scheduler with hybrid genetic newlinealgorithms and genetic local search methods Replication approach has been newlineproposed to improve the performance and fault tolerance of a multiprocessor newlinesystem newline newline