Preserving Locality for Optimal Parallelism in Task Allocation

Genetic Algorithms have been applied to several combinatorial optimisation problems, including the well known task allocation problem, originating from parallel computing. We introduce random task graphs as a model of applications which display irregular global communication patterns. Uniform crossover is the standard genetic recombination operator, that is applied to solution encoded chromosomes. However, application of a uniform crossover may heavily disrupt low cost sub-solutions, or building blocks, of a chromosome. Therefore, we define a locality preserving recombination operator, exploiting the connectivity of the task graph. Experiments show that this new operator increases the convergence rate of the Genetic Algorithm applied to the task allocation problem.