location: Current position: Home >> Scientific Research >> Paper Publications

一种基于GPU加速的细粒度并行蚁群算法

Hits:

Indexed by:期刊论文

Date of Publication:2009-08-15

Journal:控制与决策

Included Journals:EI、PKU、ISTIC、CSCD、Scopus

Volume:24

Issue:8

Page Number:1132-1136

ISSN No.:1001-0920

Key Words:蚁群算法;并行处理;图形处理器;细粒度

Abstract:为改善蚁群算法对大规模旅行商问题的求解性能,提出一种基于图形处理器(GPU)加速的细粒度并行蚁群算法.将并行蚁群算法求解过程转化为统一计算设备架构的线程块并行执行过程,使得蚁群算法在GPU中加速执行.实验结果表明,该算法能提高全局搜索能力,增大细粒度并行蚁群算法的蚂蚁规模,从而提高了算法的运算速度.

Pre One:A PARALLEL ANT COLONY OPTIMIZATION ALGORITHM BASED ON FINE-GRAINED MODEL WITH GPU-ACCELERATION

Next One:基于粒子系统和GPU加速的喷泉实时仿真