基于IPC与公平性的共享Cache划分  

Shared Cache Partitioning Based on IPC and Fairness

作　　者：王震[1] 徐高潮[1] 

机构地区：[1]吉林大学计算机科学与技术学院,长春130012

出　　处：《吉林大学学报（理学版）》2011年第4期740-744,共5页Journal of Jilin University:Science Edition

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.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.

关 键 词：CACHE划分 公平性 Cache访问监控器 

分 类 号：TP302[自动化与计算机技术—计算机系统结构]