A Framework for Developing Parallel Optimization Algorithms

S. Ribas, M.H. de P. Perché, I.M. Coelho, P.L. Araújo Munhoz, M.J.F. Souza, and A.L.L. Aquino (Brazil)


Framework, Parallel algorithms, Optimization algorithms


This paper introduces MaPI; a framework that implements MapReduce abstraction. By using this framework, the de veloper is able to implement parallel optimization algo rithms without worrying about message transmission be tween the processes, or about how the system will perform the parallelization. Furthermore, the algorithm can be de veloped without parallel code, since the parallelization is hidden by the framework. In order to demonstrate the ef ficiency of this framework, an optimization heuristic algo rithm is applied to the classical Traveling Salesman Prob lem. The results show the usability of the framework in the development of parallel optimization algorithms.

Important Links:

Go Back