...
首页> 外文期刊>Computing >HW/SW co-design of reconfigurable hardware-based genetic algorithm in FPGAs applicable to a variety of problems
【24h】

HW/SW co-design of reconfigurable hardware-based genetic algorithm in FPGAs applicable to a variety of problems

机译:在FPGA中基于硬件的可重构遗传算法的硬件/软件协同设计,适用于各种问题

获取原文
获取原文并翻译 | 示例
           

摘要

This paper describes the implementation of a reconfigurable hardware-based genetic algorithm (HGA) accelerator using the hardware-software (HW/SW) co-design methodology. This HGA is coupled with a unique TRNG that extracts random jitters from a phase lock loop (PLL) to ensure proper GA operation. It is then applied and benchmarked with several case studies, which include the optimization of a simple fitness function, a constrained Michalewicz function, and the tuning of parameters in finger-vein biometrics. A HGA solution is necessary in systems that demand high performance during the optimization process. However, implementations that are completely designed in hardware will result in a very rigid architecture, making it difficult to reconfigure the system for use in different applications. This paper aims to solve this issue by proposing a HGA design that provides reconfigurability and flexibility by moving problem-dependent processes into software. The prototyping platform used is an Altera Stratix IIEP2S60 FPGA prototyping board with a clock frequency of 50 MHz. The HW/SW co-design technique is applied, and system partitioning is done based on aspects such as system constraints, operational intensity, process sequencing, hardware logic utilization, and reconfigurability. Experimental results show that the proposed HGA outperforms equivalent software implementations compiled with an open-sourced C++ GA component library (GAlib) running on the same prototyping platform by 102 times at most. In the final case study, the application of the proposed HGA in tunable parameter optimization in finger-vein biometrics improved the matching rate, reducing the equal error rate (EER) value from 1.004% down to 0.101 %.
机译:本文介绍了使用硬件-软件(HW / SW)协同设计方法实现可重构的基于硬件的遗传算法(HGA)加速器。该HGA与独特的TRNG结合,可从锁相环(PLL)提取随机抖动,以确保GA正常运行。然后将其应用并通过几个案例研究进行基准测试,其中包括简单适应度函数的优化,受限的Michalewicz函数以及指静脉生物特征学参数的调整。在优化过程中需要高性能的系统中,HGA解决方案是必需的。但是,完全用硬件设计的实现将导致非常僵化的体系结构,从而难以重新配置系统以用于不同的应用程序。本文旨在通过提出一种HGA设计来解决此问题,该设计通过将与问题相关的过程转移到软件中来提供可重新配置性和灵活性。所使用的原型平台是时钟频率为50 MHz的Altera Stratix IIEP2S60 FPGA原型板。应用硬件/软件协同设计技术,并基于系统约束,操作强度,过程顺序,硬件逻辑利用率和可重新配置性等方面完成系统分区。实验结果表明,所提出的HGA优于使用在同一原型平台上运行的开源C ++ GA组件库(GAlib)编译的等效软件实现最多可进行102次。在最后的案例研究中,拟议的HGA在手指静脉生物特征参数的可调参数优化中的应用提高了匹配率,将等错误率(EER)值从1.004%降低到0.101%。

著录项

  • 来源
    《Computing》 |2013年第9期|863-896|共34页
  • 作者单位

    Department of Microelectronics & Computer Engineering (MiCE), Faculty of Electrical Engineering, Universiti Teknologi Malaysia, 81310 Skudai, Johor, Malaysia;

    Department of Microelectronics & Computer Engineering (MiCE), Faculty of Electrical Engineering, Universiti Teknologi Malaysia, 81310 Skudai, Johor, Malaysia;

    Department of Microelectronics & Computer Engineering (MiCE), Faculty of Electrical Engineering, Universiti Teknologi Malaysia, 81310 Skudai, Johor, Malaysia;

    Department of Microelectronics & Computer Engineering (MiCE), Faculty of Electrical Engineering, Universiti Teknologi Malaysia, 81310 Skudai, Johor, Malaysia;

  • 收录信息 美国《科学引文索引》(SCI);美国《工程索引》(EI);
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

    FPGA; Genetic algorithm; HW/SW co-design; Finger-vein biometrics; Image processing; Embedded systems; System-on-chip; Benchmarking;

    机译:FPGA;遗传算法硬件/软件协同设计;指静脉生物特征识别;图像处理;嵌入式系统;片上系统;标杆管理;

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号