北京大学学报(自然科学版)

一种降低末级高速缓存污染的分阶段自适应动态插入策略

黄涛1,2,王晶1,3,王克义1   

  1. 1. 北京大学微处理器研究开发中心, 北京 100871; 2. 公安部网络安全保卫局, 北京 100741; 3. 首都师范大学信息工程学院, 北京 100048;
  • 收稿日期:2013-01-21 出版日期:2014-03-20 发布日期:2014-03-20

A Phase-Based Adaptive Dynamic Insertion Policy for Reducing Last Level Cache Pollution

HUANG Tao1,2, WANG Jing1,3, WANG Keyi1   

  1. 1. MicroProcessor Research and Development Center, Peking University, Beijing 100871; 2. Cyber Security Department, Ministry of Public Security of PRC, Beijing 100741; 3. College of Information Engineering, Capital Normal University, Beijing 100048;
  • Received:2013-01-21 Online:2014-03-20 Published:2014-03-20

摘要: 对多种末级高速缓存插入策略进行分析, 并在动态插入策略DIP的基础上提出一种分阶段自我调整的动态插入策略, 用于消除局部性差数据访问末级高速缓存造成的不良影响。实验结果表明, 与现有LRU替换算法相比, 此方法将末级高速缓存的MPKI平均降低了7.07%, 即使与动态插入策略DIP相比, 此方法也获得进一步的性能提升, 末级高速缓存MPKI平均降低了4.36%。

关键词: 末级高速缓存污染, 软硬件协作, 插入策略

Abstract: The authors analyze multiple last level cache insertion policies and propose a phase-based adaptive dynamic insertion policy based on DIP (dynamic insertion policy) for eliminating the harmful effect of non-reusable data. The experiment result shows that in comparison with LRU (least recently used), the proposed approach can reduce the last level cache misses per thousand instructions, MPKI, 7.07% on average; even in comparison with DIP policy, the new approach can also improve last level cache performance in further, and average MPKI is reduced by 4.36%.

Key words: last level cache pollution, software and hardware collaboration, insertion policy

中图分类号: