As a heuristic method, the genetic algorithm provides promising solutions with impressive performance benefits for large-scale problems. In this study, we propose a highly scalable hybrid parallel genetic algorithm (HPGA) based on Sunway TaihuLight Supercomputer. First, the Cellular model is presented on a thread level, so that each individual can be processed by a single computing unit which is in charge of the parallel fitness calculation, crossover, and mutation operations. The information exchange between individuals is realized by register communication. Second, the Island model is assigned to a process level, so that each process accounts for a single sub-population, and the migration among sub-populations is implemented using MPI communication. The proposed approach can fully exploit the individual diversity of the genetic algorithm and reasonably maintain the communication overhead. Based on the widely used CEC2013 benchmark, the experimental results show that the algorithm presents a sound performance in terms of both accuracy and convergence speed.

作为一种启发式方法，遗传算法提供了有希望的解决方案，可解决大规模问题，并具有令人印象深刻的性能优势。在这项研究中，我们提出了一种基于双威TaihuLight超级计算机的高度可扩展的混合并行遗传算法（HPGA）。首先，蜂窝模型是在线程级别上呈现的，因此每个人都可以由负责并行适应度计算，交叉和变异操作的单个计算单元进行处理。个人之间的信息交换是通过注册通讯实现的。其次，将Island模型分配给一个流程级别，以便每个流程都占一个子种群，并且使用MPI通讯实现子种群之间的迁移。所提出的方法可以充分利用遗传算法的个体多样性，并合理地维持通信开销。实验结果表明，该算法基于广泛使用的CEC2013基准，在准确性和收敛速度方面均表现出良好的性能。