基于量子遗传算法的嵌入式系统软硬件划分算法  

HW-SW Partitioning Based on Quantum Genetic Algorithm

作　　者：邹谊[1] 庄镇泉[1] 李斌[1] 

机构地区：[1]中国科学技术大学电子科学与技术系,安徽合肥230026

出　　处：《电路与系统学报》2004年第5期1-7,共7页Journal of Circuits and Systems

基　　金：国家自然科学基金资助项目(60171029)

摘　　要：针对嵌入式系统软硬件协同设计中的软硬件划分问题,本文在改进了基于基本调度块图的软硬件划分模型的基础上,提出了一个基于量子遗传算法(QGA)的软硬件划分算法。通过采用自适应的适应度函数、惯性量子旋转角调整策略以及引入量子交叉操作,提高了算法的搜索效率,实验结果说明了该算法对解决软硬件划分问题的有效性。Based on system’s Basic Scheduling Block (BSB) graph, a HW-SW partitioning model is established. An approach using quantum genetic algorithm (QGA) is proposed to solve this partitioning problem. By adopting an adaptive fitness function definition, a novel quantum rotating angle adjustment strategy and quantum crossover operator, the efficiency of proposed algorithm is enhanced. Experiment results show that compared with conventional algorithm, QGA can be used to solve the HW-SW partitioning problem effectively and efficiently.

关 键 词：软硬件协同设计 软硬件划分 量子计算 量子遗传算法 

分 类 号：TP302[自动化与计算机技术—计算机系统结构]