| 消除低重用块和预测访问间隔的Cache管理策略 |
| |
| 引用本文： | 尹巍,吴俊敏,朱小东.消除低重用块和预测访问间隔的Cache管理策略[J].小型微型计算机系统,2012,33(6):1337-1342. |
| |
| 作者姓名： | 尹巍 吴俊敏 朱小东 |
| |
| 作者单位： | 1. 中国科学技术大学计算机科学与技术学院,合肥,230027
2. 中国科学技术大学计算机科学与技术学院,合肥230027;中国科学技术大学苏州研究院,江苏苏州215123 |
| |
| 基金项目： | 国家“八六三”高技术研究发展计划项目 |
| |
| 摘 要： | 设计一种被称之为消除低重用块和预测访问间隔的Cache管理策略ELRRIP.根据多核处理器的共享最后一级高速缓存中低重用块占用资源时间较长这一特点,ELRRIP策略:1)通过感知最后一级共享高速缓存的上一级Cache中的数据历史访问信息预测出低重用块并优先将其淘汰;2)通过改进的访问间隔预测技术预测出潜在的低重用块并将其优先淘汰.同时,本文还基于ELRRIP提出了TADELRRIP.实验表明,对于4核多核处理器而言,TADELRRIP可以将加权加速比平均提高9.14%.
|
| 关 键 词： | 多核处理器 最后一级高速缓存 访问间隔预测 淘汰 低重用块 |
Manage Last Level Cache with Eliminating Less Reused Blocks and Re-reference Interval Prediction Policy |
| |
| YIN Wei
,
WU Jun-min
,
ZHU Xiao-dong.Manage Last Level Cache with Eliminating Less Reused Blocks and Re-reference Interval Prediction Policy[J].Mini-micro Systems,2012,33(6):1337-1342. |
| |
| Authors: | YIN Wei WU Jun-min ZHU Xiao-dong |
| |
| Affiliation: | 1(School of Computer Science and Technology,University of Science and Technology of China,Hefei 230027,China) 2(Suzhou Institute for Advanced Study,University of Science and Technology of China,Suzhou 215123,China) |
| |
| Abstract: | The low utility data block wastes too many shared last level cache(LLC) resources of chip multi-processors(CMP).In this paper,we propose an Eliminating Less Reused Blocks and Re-Reference Interval Prediction Policy(ELRRIP) to solve the problem.ELRRIP can get the data reference information of its previous level cache.Then it predicts the low utility data block according to the information and evict them as early as possible.ELRRIP uses improved Re-Reference Interval Prediction Policy to predict potential low utility data block and tries its best to evict them as early as possible.We also proposed TADELRRIP to manage LLC more efficiently.Our evaluation on 4-way CMPs shows that TADELRRIP improves the overall performance by 9.14% on average over the LRU policy. |
| |
| Keywords: | CMP last level cache re-reference interval prediction evict low utility data block |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
