›› 2015, Vol. 28 ›› Issue (1): 12-.

• 论文 • 上一篇    下一篇

可逆逻辑门进化设计方法的CUDA实现

俞经龙,赵曙光,王祥   

  1. (东华大学 信息科学与技术学院,上海 201620)
  • 出版日期:2015-01-15 发布日期:2015-01-22
  • 作者简介:俞经龙(1986—),男,硕士研究生。研究方向:可逆逻辑电路综合优化。E-mail:286809167@qq.com

Implementation of Reversible Logic Gates Evolutionary Design Approach Based on CUDA

YU Jinglong,ZHAO Shuguang,WANG Xiang   

  1. (College of Information Science and Technology,Donghua University,Shanghai 201620,China)
  • Online:2015-01-15 Published:2015-01-22

摘要:

可逆逻辑门优化程度将直接影响可逆逻辑电路的整体优化,目前已有的优化方法难以实现全局最优。文中基于NCV门库,对遗传算法编码方案和适应度进行了改进,并将进化设计方法改造为CUDA架构下的并行算法应用到可逆逻辑门的优化。其不仅发挥了电路进化设计的全局优化能力,且在不增加硬件规模的前提下,明显提高了电路的搜索速度。

关键词: 进化设计, CUDA, 可逆逻辑门

Abstract:

Optimization of the reversible logic gates will directly affect the overall optimization of reversible logic circuits.Existing optimization methods fail to achieve the overall optimization.Based on NCV gate library,the genetic algorithm coding schemes and fitness are improved to some extent,and the evolutionary design is upgraded to CUDA-based parallel algorithm,which is applied to the optimization of the reversible logic gates.This method not only gives full play to the overall optimization of the evolutionary design of circuit,but also significantly speeds up the circuit search without scaling up the size of hardware.

Key words: evolutionary design;CUDA;reversible logic gates

中图分类号: 

  • TN702