期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

一种新型的单芯片级可进化硬件系统 被引量：1

A Novel on-Chip Evolvable Hardware(EHW) System
原文传递
导出
摘要 针对可进化硬件(EHW)系统的需求,设计实现了FDP-2-SOPC芯片,芯片中嵌入了CPU和FPGA两种IP核,可实现硬件电路的重构和进化;以该芯片为系统核心建立了一种新型的软硬件结合的单芯片级EHW系统.为了提高电路重构速度,设计了针对EHW需求的快速局部重配置技术;为提高遗传算法的执行速度,设计了专用的随机数产生器;为了减少软硬件开发相关性并降低系统开发的难度,满足不同适应度评估方案的需求,提出了一种灵活友好的数据交互技术;并开发了合适的遗传算法.在此单芯片级EHW系统上进行了电路自进化实验,实验结果表明,该系统可正确地实现硬件电路的自重构、自进化,在进化速度上优势明显:针对同样的目标电路进化,在进化算法性能相近的前提下,该系统的进化时间相比FPGA+PC系统提高了一个数量级. To meet the requirement of the evolvable hardware（EHW）system,the FDP-2-SOPC chip was designed and implemented,in which a PowerPC405 IP core and a self-developed FPGA IP core were embedded for reconfiguration and evolution.Based on the system,an on-chip EHW system was built.To accelerate the reconfiguration,a quick partially reconfiguration technique was proposed,and a dedicated random number generator was designed to accelerate the genetic algorithm.To make the software/hardware co-developing easier and meet the requirement for different fitness evaluation strategy,a flexible and user-friendly interface for data exchanging was proposed.A proper genetic algorithm on this system and some EHW experiments were carried out.Results have showed that the proposed on-chip EHW system works correctly in the EHW application and is fast in evolving.When evolving towards the same target circuit and with a similar algorithm performance,the proposed system is an order of magnitude faster than the PC-FPGA joint system.
作者 杨华秋 段欣 来金梅
机构地区 复旦大学专用集成电路与系统国家重点实验室
出处 《复旦学报（自然科学版）》 CAS CSCD 北大核心 2012年第1期43-49,76,共8页 Journal of Fudan University：Natural Science
基金 国家高技术研究发展计划("863"计划)(2007AA01Z285)资助项目
关键词 可进化硬件 单芯片级可进化硬件 可重构硬件 加速进化 evolvable hardware EHW SOC reconfigurable hardware accelerate evolving
分类号 TP302 [自动化与计算机技术—计算机系统结构]
  • 相关文献

参考文献15

  • 1Hwang,K S,Cho,S B.Evolving diverse hardwares using speciated genetic algorithm[C]∥Proceedingsof the 2002Congress on Evolutionary Computation,Volume 1.Hilton,Hawaiian,USA:IEEE ComputerSociety Press,2002:437-442.
  • 2Vassilev V K,Job D,Miller J F.Towards the automatic design of more efficient digital circuits[C]∥Proceedings of the 2nd NASA/DoD Workshop on Evolvable Hardware.Palo Alto,California,USA:IEEE Computer Society Press,2000:151-160.
  • 3Xilinx Inc.Virtex-II Pro and Virtex-II Pro X platform FPGA User Guide V4.2[EB/OL].(2000-02-19)[2009-7-24].http:∥www.xilinx.com/support/documentation/user_guides/ug012.pdf.
  • 4Altera Corp.Nios II Processor Reference Handbook V10.0[EB/OL].(2010-03-05)[2010-05-07].http:∥www.altera.com/literature/hb/nios2/n2cpu_nii5v1.pdf.
  • 5Vinger K A,Torresen J.Implementing evolution of FIR-filters efficiently in an FPGA[C]∥Proceedingsof the 5th NASA/Dod Conference on Evolvable Hardware.Chicago,Illinois,USA:IEEE ComputerSociety,2003:26-29.
  • 6Fan Xiong,Rafla N I.On-chip intrinsic evolution methodology for sequential logic circuit design[C]∥Proceeding of the 52nd IEEE International Midwest Symposium on Circuits and Systems.Cancun,Mexico:Institute of Electrical and Electronics Engineers Inc.,2009:200-203.
  • 7Glette.K,Torresen J.Online evolution for a high-speed image recognition system implemented on aVirtex-II Pro FPGA[C]∥Proceedings of the 2nd NASA/ESA Conference on Adaptive Hardware andSystems.Edinburgh,United Kingdom:Inst.of Elec.and Elec.Eng.Computer Society,2007:463-470.
  • 8Salami M,Sakanashi H,Tanaka M,et al.On-line compression of high precision printer images byevolvable hardware[C]∥Proceedings of the 1998Data Compression Conference.Snowbird,UT,USA:IEEE,Piscataway,1998:219-228.
  • 9Higuchi T,Iwata M,Kajitani I,et al.Evolvable hardware with genetic learning[C]∥Proceeding ofIEEE International Symposium on Circuits and Systems,Vol.4.Atlanta,Georgia,USA:IEEE,Piscataway,1996:29-32.
  • 10Yang Hua-qiu,Chen Li-guang,Liu Shao-teng et al.A flexible bit-stream level evolvable hardwareplatform based on FPGA[C]∥Proceeding of NASA/ESA Conference on Adaptive Hardware andSystems.San Francisco,CA,USA:IEEE Computer Society,2009:51-56.

同被引文献21

  • 1Golub T R, Slonim D K, Tamayo P, et al. Molecular classi- fication of cancer: class discovery and class prediction by gene expression monitoring. Science, 1999,286 ( 5439 ) : 531-537.
  • 2Shen Q, Shi W M, Kong W, et al. Hybrid particle swarm optimization and tabu search approach for selecting genes for tumor classification using gene expression data. Com- putational Biology and Chemistry,2008,32( 1 ) :53-60.
  • 3Sandin I, Andrade G, Viegas F, et al. Aggressive and ef- fective feature selection using genetic programming. In: Proceedings of the IEEE Congress on Evolutionary Com- putation, Brisbane, Australia ,2012.1-8.
  • 4Piao H Y. A correlational Bayesian network for DNA mi- croarray data analysis. In:Proceedings of the International Conference on Biomedical Engineering and Informatics, Shanghai, China,2011. 1702-1705.
  • 5Helman P,Veroff R, Atlas S R, et al. A Bayesian network classification methodology for gene expression data. Jour- nal of Computational Biology,2004,11 (4) : 581-615.
  • 6Tan A C, Gilbert D. Ensemble machine learning on gene expression data for cancer classification. Applied Bioinfor- matics,2003,2(2 suppl) :75-83.
  • 7Chao S B, Won H. Cancer classification using ensemble of neural networks with multiple significant gene subsets. Ap- plied Intelligence, 2007,26 ( 3 ) : 243-250.
  • 8Glette K, Torresen J, Yasunaga M. An online EHW pattern recognition system applied to sonar spectrum classifica- tion. In: Proceedings of the International Conference on Evolvable Systems:From Biology to Hardware, Wuhan, China,2007.1-12.
  • 9Wang J,Jung J K,Lee Y M ,et al. Using reconfigurable ar- chitecture-based intrinsic incremental evolution to evolve a character system. In: Proceedings of the International Conference on Computational Intelligence and Security, Xi' an,China,2005. 216-223.
  • 10I Sekanina L, Frienl S. An evolvable combinational unit for FPGAs. Computing and Informatics, 2004,23 ( 5 ) : 461- 486.

引证文献1

复旦学报（自然科学版）
2012年 第1期

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