Genetic Algorithm 相关 AI 资讯

10:54

官方账号arXiv cs.AI@Swetha Varadarajan, Darrell Whitley

This paper presents a fine-grain GPU implementation of the Generalized Partition Crossover (GPX) for large-scale TSP instances. The approach reformulates GPX partitioning as a graph-parallel problem and achieves speedups between 48x and 625x over a sequential CPU implementation. The GPU partitioning significantly reduces memory overhead while improving scalability on modern many-core architectures.

论文 TSP GPU parallelization Genetic Algorithm

推荐理由：This paper introduces a GPU-based solution for large-scale TSP problems, offering substantial speedups and reduced memory overhead compared to traditional CPU implementations. It's a must-read for those interested in GPU parallelization and optimization techniques for TSP solvers.

原文