Optimization of task distribution on multicore systems

摘要

To use modern multiprocessor and distributed computer architectures effectively it is necessary to parallelize the program code in such a way as to achieve a minimum execution time of the program on a given architecture. In this case if the executing devices have different performance characteristics in a distributed system, during parallelization it should be taken into account this difference and the optimization of the execution time of the entire algorithm should be carried out. The method for solving such an optimization problem is proposed in the article.