期刊文献+

一种改进的自适应时钟算法 被引量:2

An Improved Algorithm of Adaptive Clock
下载PDF
导出
摘要 针对LIRS算法结构复杂、适应性差的不足,提出一种改进的自适应时钟算法。在LIRS算法基础上借鉴Clock算法思想,简化算法组织结构,加强对不同数据访问模式的适应性和捕获高频数据的能力。实验结果证明,与LIRS算法及2种传统替换算法相比,自适应时钟算法在命中率上有更好的表现,较好地满足用户对Cache高命中率和占用额外计算资源少的要求。 To solve the problem that LIRS algorithm has the shortage of complex structure and poor adaptability, this paper proposes an Adaptive Clock algorithm based on LIRS algorithm. Adaptive Clock algorithm absorbs the Clock algorithm ideas to simplify the organizational structure of the algorithm to improve the adaptability of different data access patterns, as to enhance the ability to capture high-frequency data. Experimental results show that Adaptive Clock has better performance in hit rate than LIRS algorithm and two commonly used algorithms, and meets the requirements of the high Cache replacement ratio and less computing resource.
出处 《计算机工程》 CAS CSCD 2012年第20期286-289,共4页 Computer Engineering
基金 国家自然科学基金资助项目(61003036 60873138) 黑龙江省教育厅科学技术研究基金资助项目(12513048)
关键词 LIRS算法 自适应时钟算法 适应性 命中率 计算资源 Cache加速比 LIRS algorithm Adaptive Clock algorithm adaptability hit rate computing resource Cache acceleration ratio
  • 相关文献

参考文献8

二级参考文献52

  • 1金国华,陈福接.简单访问模式下假共享Cache行抖动的消除[J].计算机学报,1994,17(6):435-445. 被引量:1
  • 2Reinders J.Programming For Parallelism[EB/OL].2007.http://www.cajcd.edu.cn/pub/wml.txt/980810-2.html.
  • 3Stevens W R,Rago S A.Advanced Programming in the UNIX Environment[M].北京:人民邮电出版社,2006.
  • 4Doweck J.Inside Intd Core Microarchitecture and Smart Memory Access[EB/OL].2006.http://download.intel.com/technology/architecture/s-ma.pdf.
  • 5李晓明,臧斌宇,郑纬民,等.多核程序设计[M].北京:北京大学出版社,2007.
  • 6Love R.CPU affinity[EB/OL].2003.http://www.linuxiournal.com/article/6799.
  • 7Bovet D P,Cesati M.Understanding the Linux Kernel[M].北京:中国电力出版社,2007.
  • 8Wong W, Baer J L. Modified LRU policies for improving second-level cache behavior [J]. HPCA- 6, 2000 : 49-60.
  • 9Method for implementing a pseudo least recent used (LRU) mechanism in a four-way cache memory within a data processing system[EB/OL](2001) [2010-04 -26]. http://www, patentstorm, us/patents/6240489/description, html.
  • 10Renau J. SESC[EB/OL]. [2010-04-26]. fttp:// sesc. sourceforge, net, 2004.

共引文献43

同被引文献21

  • 1田小波,陈蜀宇.基于最小效用的流媒体缓存替换算法[J].计算机应用,2007,27(3):733-736. 被引量:13
  • 2Dan A, Towsley D. An Approximate Analysis of The Lru And Fifo Buffer Replacement Schemes[J]. ACM Sigmetrics Perform- ance Evaluation Review, 1990,18 : 143-152.
  • 3Song Jiang, Feng Chen, Zhang Xiao-dong. CLOCK-Pro:an effec- tive improvement of the CLOCK replaeement[C]//Proceedings of USENIX Annual Technical Conference, 2005 : 323-336.
  • 4Chierichetti F, Kumar R, Vassilvitskii S. Similarity caching [C]// Proceedings of the Twenty-Eigth ACM SIGMOD-SIGACT-SI- GART Symposium on Principles of Database Systems. Provi- dence, Rhode Island, USA, 2009 : 127-136.
  • 5Johnson T, Shasha D. 2Q: A Low Overhead High Performance Buffer Management Replacement Algorithm[C]// Proceedings of the 20th VLDB Conference. Santiago,Chile, 1994:439-450.
  • 6IBM. IBM enterprise storage server[OL], http://www, stor- age. ibm, com/hardsoft/produets/ess/ess, htm.
  • 7Megiddo N, Modha D. ARC: A Self-Tuning, Low Overhead Re- placement Cache[C]//Proeeedings of the 2003 Conference on File and Storage Technologies (FAST'03). San Franciso, CA, 2003 : 115-130.
  • 8Patil J B,Pawar B V. GDSF, A better caching algorithm that optimizes both hit rate and byte hit rate in web proxy servers [J]. International Journal of Computer Science& Applications, 2008,5(4):1-10.
  • 9Janapsatya A, Ignjatovic A, Peddersen J, et al. Dueling CLOCK: Adaptive cache replacement policy based on the CLOCK algo- rithm[C]//Proceedings of the Conference on Design, Automa- tion and Test in Europe. Dresden,Germany, 2010:920 - 925.
  • 10Kedzierski K, Moreto M, Cazorla F J, et al. Adapting cache par- titioning algorithms to pseudo-LRU replacement policies[C]// 2010 IEEE International Symposium on Parallel Distributed Processing (IPDPS). Atlanta,GA, 2010: 1-12.

引证文献2

二级引证文献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