English  |  正體中文  |  简体中文  |  全文笔数/总笔数 : 61682/94631 (65%)
造访人次 : 1633009      在线人数 : 14
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
搜寻范围 查询小技巧:
  • 您可在西文检索词汇前后加上"双引号",以获取较精准的检索结果
  • 若欲以作者姓名搜寻,建议至进阶搜寻限定作者字段,可获得较完整数据
  • 进阶搜寻

    jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/78779

    题名: A refactoring method for cache-efficient swarm intelligence algorithms
    作者: Chang, Feng-Cheng;Huang, Hsiang-Cheh
    贡献者: 淡江大學資訊創新與科技學系
    关键词: Cache;Memory hierarchy;Miss rate;Swarm intelligence;Particle swarm optimization;Genetic algorithm
    日期: 2012-06
    上传时间: 2012-10-22 15:28:02 (UTC+8)
    出版者: Philadelphia, PA: Elsevier Inc.
    摘要: With advances in hardware technology, conventional approaches to software development are not effective for developing efficient algorithms for run-time environments. The problem comes from the overly simplified hardware abstraction model in the software development procedure. The mismatch between the hypothetical hardware model and real hardware design should be compensated for in designing an efficient algorithm. In this paper, we focus on two schemes: one is the memory hierarchy, and the other is the algorithm design. Both the cache properties and the cache-aware development are investigated. We then propose a few simple guidelines for revising a developed algorithm in order to increase the utilization of the cache. To verify the effectiveness of the guidelines proposed, optimization techniques, including particle swarm optimization (PSO) and the genetic algorithm (GA), are employed. Simulation results demonstrate that the guidelines are potentially helpful for revising various algorithms.
    關聯: Information Sciences 192, pp.39–49
    DOI: 10.1016/j.ins.2010.02.025
    显示于类别:[資訊創新與科技學系] 期刊論文


    档案 描述 大小格式浏览次数
    A refactoring method for cache-efficient swarm intelligence algorithms.pdf385KbAdobe PDF1检视/开启



    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - 回馈