Partition-Based Cache Replacement to Manage Shared L2 Caches  

作　　者：FANG Juan WANG Jing LI Chengyan YAO Zhicheng KE Weimao 

机构地区：[1]College of Computer Science, Beijing University of Technology [2]College of Information Engineering, Capital Normal University [3]College of Computing and Informatics, Drexel University

出　　处：《Chinese Journal of Electronics》2014年第3期464-467,共4页电子学报（英文版）

基　　金：supported by the National Natural Science Foundation of China(No.61202076,No.61202062);the General Program of Science and Technology Development Project of the Beijing Municipal Education Commission(No.KM201210005022)

摘　　要：The Least recently used （LRU） replacement has been widely employed by on-chip shared caches. With the increase of cache associativity, the performance gap between LRU and theoretical optimal replacement algorithm is significant, motivating us to design alternative replacement algorithms to improve cache performance. We propose a Partltlon-based cache replace- ment （PCR） algorithm to manage multi-core shared L2 caches. PCR takes into consideration recency and fre- quency information of cache access, and cache resource interference among multiple competing applications. PCR is effective to flter out the less frequently reused blocks through a dynamic insertion/promotlon policy based on the target partitions~ and ensures that some fraction of the working set is retained in the cache to contribute to more hits. Our evaluation shows that PCR improves performance of an 8-core system by an average of 11.3% over LRU-based cache.The Least recently used(LRU) replacement has been widely employed by on-chip shared caches. With the increase of cache associativity, the performance gap between LRU and theoretical optimal replacement algorithm is significant, motivating us to design alternative replacement algorithms to improve cache performance. We propose a Partition-based cache replacement(PCR) algorithm to manage multi-core shared L2 caches. PCR takes into consideration recency and frequency information of cache access, and cache resource interference among multiple competing applications. PCR is effective to filter out the less frequently reused blocks through a dynamic insertion/promotion policy based on the target partitions, and ensures that some fraction of the working set is retained in the cache to contribute to more hits. Our evaluation shows that PCR improves performance of an 8-core system by an average of 11.3% over LRU-based cache.

关 键 词：Multl-core Shared cache Replacement algorithm Cache partition. 

分 类 号：TP333[自动化与计算机技术—计算机系统结构]