J4 ›› 2011, Vol. 49 ›› Issue (04): 740-744.

• 计算机科学 • 上一篇    下一篇

基于IPC与公平性的共享Cache划分

王震, 徐高潮   

  1. 吉林大学 计算机科学与技术学院, 长春 130012
  • 收稿日期:2010-08-25 出版日期:2011-07-26 发布日期:2011-08-16
  • 通讯作者: 徐高潮 E-mail:xugc@jlu.edu.cn

Shared Cache Partitioning Based on IPC and Fairness

WANG Zhen, XU Gaochao   

  1. College of Computer Science and Technology, Jilin University, Changchun 130012, China
  • Received:2010-08-25 Online:2011-07-26 Published:2011-08-16
  • Contact: XU Gaochao E-mail:xugc@jlu.edu.cn

摘要:

提出一种兼顾高速缓冲存储器(Cache)公平性及系统吞吐率的划分方法, 使用Cache访问监控器记录各应用访问Cache的命中及失效次数, 通过动态划分算法决定每个应用占用的Cache数量, 解决了共享Cache访问冲突导致的Cache污染. 实验表明: 在吞吐率方面, 该方法较传统的LRU替换策略可获得最高37.90%, 平均15.71%的提升, 比公平性最优的划分算法可获得最大47.37%, 平均14.11%的吞吐率提升; 在公平性方面, 较传统的LRU替换策略可获得最大4倍, 平均77%的提升; 比失效率最优的划分算法可获得最大9倍, 平均229倍的公平性提升.

关键词: Cache划分, 公平性, Cache访问监控器

Abstract:

This paper proposes a shared Cache partitioning algorithm, based on throughput (IPC) and fairness, which in order to find a balance between fairness and throughput. We used the Cache access monitor to collect the missing rate information, and then decide the amount of Cache resources allocated to each application by the dynamic partitioning algorithm to resolve the problem of Cache pollution. Experiments show that shared Cache partitioning  based on IPC and fairness improves throughput by 15.71% on average (up to 37.90%)  over least recently used and by 14.11% on average (up to 47.37%) over fairness based Cache partitioning, and improves fairness by 77% on average (up to 4 times) over least recently used and by a factor of 2.29 on average (up to 9 times) over utility based Cache partitioning.

Key words: Cache partitioning, fairness, Cache access monitor

中图分类号: 

  • TP302