期刊文献+

基于改进模拟退火算法的软硬件划分 被引量:2

Hardware/software partitioning based on improved simulated annealing algorithm
在线阅读 下载PDF
导出
摘要 软硬件划分是嵌入式系统协同设计中的关键问题,已经被证明是一个NP问题。模拟退火算法是解决该问题常用的启发式算法,但是其存在收敛速度过慢的问题。通过改进算法的扰动模型和退火进度,提出一种新的代价函数计算方法来提高它的收敛速度。实验结果表明,相对于基于经典的模拟退火算法和已有改进的算法,新算法运行时间大大减少,并且增大了找到近似最优解的概率。 Hardware/software partitioning is a key issue of embedded system design,and it has been proven to be a NP problem.Simulated annealing algorithm is a heuristic algorithm to solve this problem,but the simulated annealing algorithm has slow convergence.By improving the disturbance model and its annealing schedule,a new cost function method was proposed to accelerate the convergence speed.Compared to the classical simulated annealing algorithm and improved algorithms,the experimental results show that the new algorithm significantly reduces the running time and increases the probability of finding an approximately optimal solution.
出处 《计算机应用》 CSCD 北大核心 2011年第7期1797-1799,1803,共4页 journal of Computer Applications
基金 国家自然科学基金资助项目(60973030)
关键词 软硬件协同设计 软硬件划分 启发式算法 模拟退火 代价函数 hardware/software co-design hardware-software partitioning heuristic algorithm simulated annealing cost function
  • 相关文献

参考文献12

  • 1APAT P,MANN Z ,ORBáN A. Hardware-software co-design for Kohonen’s self organizing map[C] // Proceedings of the IEEE 7th International Conference on Intelligent Engineering Systems. New York: IEEE,2003:136-156.
  • 2BASSIRI M M,SHAHHOSEINI H S. On-line HW/SW partitioning and co-scheduling in reconfigurable computing systems[C] // 2nd IEEE International Conference on Computer Science and Information Technology. New York: IEEE,2009:557-562.
  • 3MEEUWS R. A quantitative model for hardware/software partitioning[D]. Julianalaan, NetherLands: Delft University of Technology,2007.
  • 4CHEHIDA K B,AUGUIN M. HW/SW partitioning approach for reconfigurable system design[C] // Proceedings of the 2002 International Conference on Compilers,Architecture,and Synthesis for Embedded Systems. New York: ACM,2002:247-251.
  • 5WU JIGANG,SRIKANTHAN T. Algorithmic aspects of hardware/software partitioning: 1D search algorithms[J]. IEEE Transactions on Computers,2010,59(4):532-544.
  • 6BANERJEE S,DUTT N. Efficient search space exploration for HW-SW partitioning[C] // The IEEE/ACM/IFIP International Conference on Hardware/Software Codesign and System Synthesis. New York: ACM,2004: 122-127.
  • 7邢冀鹏,邹雪城,刘政林,陈毅成.一种基于改进模拟退火算法的软硬件划分技术[J].微电子学与计算机,2006,23(5):31-33. 被引量:5
  • 8ELES P,PENG Z,KUCHCINSKI K,et al. System level hardware/software partitioning based on simulated annealing and tabu search[J]. Design Automation for Embedded Systems,1997,2(1):5-32.
  • 9KORYFIDIS I. Power aware HW/SW partitioning for DVB-H receiver module[D]. Julianalaan,Netherlands: Delft University of Technology,2006.
  • 10沈英哲,周学海.一种用于可重构计算系统的软硬件划分算法[J].中国科学技术大学学报,2009,39(2):182-188. 被引量:3

二级参考文献20

  • 1熊志辉,李思昆,陈吉华.遗传算法与蚂蚁算法动态融合的软硬件划分[J].软件学报,2005,16(4):503-512. 被引量:87
  • 2Bondalapati K, Prasanna V K. Reconfigurable computing: architectures, models and algorithms[J]. Current Science, 2000, 78(7): 828-837.
  • 3Compton K, Hauck S. Reconfigurable computing: a survey of systems and software[J]. ACM Computing Surveys, 2002, 34(2)..171-210.
  • 4Guo Z, Buyukkurt B, Najjar W, et al. Optimized generation of data-path from C codes for FPGAs[C]// Proceedings of Design, Automation and Test in Europe. Washington D C: IEEE Computer Society, 2005 : 112-117.
  • 5Callahan T J, Hauser J R, Wawrzynek J. The Garp architecture and C compiler [J]. IEEE Computer, 2000, 3(4):62-69.
  • 6Noguera J, Badia R. A HW/SW partitioning algorithm for dynamically reconfigurable architectures [ C] //Proceedings of the Conference on Design, Automation and Test in Europe. Piscataway, NJ: IEEE Press, 2001 : 729.
  • 7Li Y B, Callahan T, Darnell E, et al. Hardware-software co-design of embedded reconfigurable architectures[C]//Proceedings of the 37th Conference on Design Automation. New York.. ACM Press, 2000: 507-512.
  • 8Adam T L, Chandy K M, Dickson J R. A comparison of list schedules for parallel processing systems[J]. Communications of the ACM, 1974, 17(12) : 685-690.
  • 9Dittmann F,Gotz M. Applying single processor algorithms to schedule tasks on reconfigurable devices respecting reconfiguration times[C]// Proceedings of 20th International Parallel and Distributed Processing Symposium. Washington:IEEE Computer Society, 2006:4.
  • 10Danne K, Platzner M. Partitioned scheduling of periodic real-time tasks onto reconfigurable hardware [C]// Proceedings of 20th International Parallel and Distributed Processing Symposium. Washington: IEEE Computer Society, 20061 8.

共引文献6

同被引文献12

  • 1Wolf W. A Decade of Hardware/Software Codesign [M]. New York: IEEE Computer, 2003.
  • 2Dou Shuang, Ding Shan, Zhang Shi, et al. GA- based algorithm for hardwaresoftware partitioning with resource contentions [ C] // The 2nd Int Conf Advanced Computer Control, 2010 : 68-72.
  • 3Li Y, Callahan T, Darnell E, et al. Hardware-soft-ware co-design of embedded reconfigurable architec-tures[C] // Proceedings of the Design Automation Conference, 2000 : 507-512.
  • 4Stitt G. Hardware/software partitioning with multi- version implementation exploration [C] // Proceed- ings of Great Lakes Symposium in VLSI, Orlando, FL, USA, 2008 :143-146.
  • 5Li J, He H, Man H, et al. A general-purpose FP- GA-based reconfigurable platform for video and im- age processing[C] ff Proceedings of the 6th Interna- tional Symposium on Neural Networks: Advances in Neural Networks-Part III, 2009: 299-309.
  • 6Pellerin D, Thibault S. Evaluating hardware accel- eration strategies using C-to-hardware tools [J]. XCell Journal, 2006, 58..16-18.
  • 7Watkins C J C H, Dayan P. Technical note: Q - learning[J]. Machine Learning, 1992, 8(3-4): 279- 292.
  • 8Free Software Foundation, Inc. GNU profiler[EB/ OL]. [2011-11-21]. http//sourceware, org/binutils/ docs/gprof/index, html.
  • 9郭荣佐,黄君,王霖.基于π网的嵌入式系统软硬件划分方法[J].计算机应用,2012,32(3):855-860. 被引量:4
  • 10张丹,赵荣彩,单征,韩林,瞿进.可重构系统中软硬任务划分方法研究[J].计算机科学,2012,39(3):276-278. 被引量:2

引证文献2

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部