作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2012, Vol. 38 ›› Issue (22): 283-286. doi: 10.3969/j.issn.1000-3428.2012.22.071

• 开发研究与设计技术 • 上一篇    下一篇

Boltzmann-NSGAⅡ算法的NoC映射研究

易宏波1,罗兴国1,储慧琳2,赵 凯3   

  1. (1. 国家数字交换系统工程技术研究中心,郑州 450002;2. 中国人民解放军61726部队,武汉 430060; 3. 中国人民解放军95951部队,广东 汕头 515065)
  • 收稿日期:2012-02-15 修回日期:2012-03-27 出版日期:2012-11-20 发布日期:2012-11-17
  • 作者简介:易宏波(1986-),男,硕士研究生,主研方向:智能算法,数字通信;罗兴国,教授;储慧琳、赵 凯,助理工程师
  • 基金资助:
    国家“863”计划基金资助项目(2009AA012201);上海市科委重大科技攻关计划基金资助项目(08dz501600)

Research of Network-on-Chip Mapping for Boltzmann-NSGAⅡ Algorithm

YI Hong-bo 1, LUO Xing-guo 1, CHU Hui-lin 2, ZHAO Kai 3   

  1. (1. National Digital Switch System Engineering & Technological R&D Center, Zhengzhou 450002, China; 2. PLA 61726 Army, Wuhan 430060, China; 3. PLA 95951 Army, Shantou 515065, China)
  • Received:2012-02-15 Revised:2012-03-27 Online:2012-11-20 Published:2012-11-17

摘要: 传统NSGAⅡ算法在解决NoC映射问题时容易出现局部最优和种群多样性的问题。为此,提出一个均衡优化时延模型和一种基于Boltzmann-NSGAⅡ的映射算法,时延模型从宏观链路负载和单个节点排队时延进行优化,映射算法引入Boltzmann机制、多点交叉算子、随机变异算子,以保持种群多样性并提高局部搜索能力。实验结果表明,Boltzmann-NSGAⅡ算法能获得更好的映射效果,最优解集的收敛性和均匀性更好。

关键词: 片上网络, 映射, 时延模型, Boltzmann机制, NSGAⅡ算法, 盒图

Abstract: Traditional NSGAⅡalgorithms are easy to get local optimization and less diversity of the population. Aiming at the problems, this paper proposes a balanced optimized delay model and the Boltzmann-NSGAⅡ mapping algorithm. The delay model is constructed from the macroscopic link load distribution and the single node queue latency. The Boltzmann mechanism, multi-point crossover operator, random mutation operator are introduced into the algorithm to maintain the diversity of the population and increase the local search capability. Simulation results prove that the optimal solution set obtained by the Boltzmann-NSGAⅡ algorithm is better in the convergence and uniformity, and the mapping effect of the Boltzmann-NSGAⅡ algorithm is better.

Key words: Network-on-Chip(NoC), mapping, delay model, Boltzmann mechanism, NSGAⅡ algorithm, boxplot

中图分类号: