|
|
论文:2012,Vol:30,Issue(3):461-465 |
|
|
引用本文： |
|
|
李兵哲, 朱怡安, 刘琪, 黄姝娟 . 一种渐变的多核共享Cache划分算法[J]. 西北工业大学 |
|
|
Li Bingzhe, Zhu Yi'an, Liu Qi, Huang Shujuan. Proposing an Effective "Gradual Runtime Shared Cache Partitioning Algorithm"for Multi-Core[J]. Northwestern polytechnical university |
|
|
|
|
|
|
|
| 一种渐变的多核共享Cache划分算法 |
|
| 李兵哲1,2, 朱怡安1, 刘琪3, 黄姝娟 1 |
|
1. 西北工业大学 计算机学院,陕西 西安 710072;
2. 解放军西安政治学院,陕西 西安 710068;
3. 中国人民解放军空军装备部科研订货部,北京 100843 |
| 摘要: |
| 针对多核共享 Cache 动态划分技术存在硬件存储开销较大、划分颠簸等问题, 提出了一种渐变的多核共享 Cache 动态划分算法。渐变算法旨在追求最优划分性能的同时, 减小划分机制实现的硬件开销。渐变算法采用基于组相联 Cache 路的划分机制, 每次划分时最多只允许 1 路的 Cache 转移。具有硬件存储开销小、划分稳定、易于实现等特点。例如, 对于 1MB 的 16 路组相联 L2Cache, 渐变的 Cache 动态划分机制仅增加0. 01%的硬件存储开销, 与 UCP 方法比较, 增加的硬件存储开销可减小至6. 25%。 |
| 关键词:
多核
Cache 划分
算法
|
|
| Proposing an Effective "Gradual Runtime Shared Cache Partitioning Algorithm"for Multi-Core |
|
| Li Bingzhe1,2, Zhu Yi'an1, Liu Qi3, Huang Shujuan1 |
|
1. Department of Computer Science and Engineering,Northwestern Polytechnical University,Xi'an 710072,China;
2. PLA Xi'an Institute of Politics,Xi'an 710068,China;
3. Airforce Equip Department Scientific Research Indent Branch,Beijing 100843,China |
| Abstract: |
| The runtime shared cache partitioning is an effective way to reduce conflicting accesses for simultaneousmultiple execution applications. However, the existing cache partitioning monitor always has big hardware overheadand is prone to thrash. Aiming to reduce the hardware overhead,while keeping the IPC (instruction per clock)performance optimal,we propose a gradual runtime shared cache partitioning algorithm. Section 1 of the full paperexplains the algorithm mentioned in the title, which we believe is effective; section 1 consists of four subsections.Its core consists of: our partitioning algorithm uses the partitioning mechanism based on group-association cacheways,each partitioning only permitting at most one way of cache transfer. Section 2 evaluates the performance ofour partitioning algorithm,explaining that, for a typical L2cache configuration,our partitioning algorithm can re-duce hardware overhead to only 6. 25%; The simulation results,given in Fig. 2,and their analysis show prelimi-narily that our partitioning algorithm can effectively eliminate partitioning thrash,while keeping the IPC perform-ance optimal. |
| Key words:
algorithms
cache memory
decision making
efficiency
evaluation
hardware
mechanisms
monior-ing
schematic diagrams;cache partitioning algorithm
multi-core
simulation
|
|
| 收稿日期: 2011-06-08
修回日期:
|
| DOI: |
| 基金项目: 航空科学基金(20100753022)；西北工业大学基础研究基金(JC20110283)与航天科技创新基金(2011XR160001)资助 |
| 通讯作者:
Email： |
| 作者简介: 李兵哲(1975-),西北工业大学博士研究生,主要从事多核Cache、多核片上网络等的研究。
|
|
|
|
|
|
|
|
参考文献: |
|
|
[1] Kim S，Chandra D，Solihin Y.Fair Cache Sharing and Partitioning in a Chip Multiprocessor Architecture.Proceedings of the13th International Conference on Parallel Architectures and Compilation Techniques，2004，111-122
[2] Suh G E，Rudolph L，Devadas S.Dynamic Partitioning of Shared Cache Memory.Journal of Supercomputing，2004，28(1): 7-26
[3] Suh G E，Devadas S，Rudolph L.A New Memory Monitoring Scheme for Memory Aware Scheduling and Partitioning.Proceed-ing of 2002 ACM Conference on High Performance Computing，2002: 117-128
[4] Qureshi M K，Patt Y N.Utility-Based Cache Partitioning: A Low-Overhead，High-Performance，Runtime Mechanism to Parti-tion Shared Caches.39th Annual IEEE/ACM International Symposium on Microarchitecture，2006，423-432
[5] Mattson R I，et a1.Evaluation Techniques for Storage Hierarchies.IBM Systems Journal，1970，9(2): 78-117
[6] 贾小敏，张民选，齐树波，赵天磊.片上多核 Cache 资源管理机制研究.计算机科学，2011，1: 295-301Jia Xiaomin，Zhang Minxuan，Qi Shubo，Zhao Tianlei.Cache Resource Management Mechanisms of Chip Multiprocessors.Computer Science，2011，1: 295-301 (in Chinese)
[7] Nathan L Binkert，Ronald G Dreslinski，Lisa R Hsu，et al.The M5 Simulator: Modeling Networked Systems.IEEE Micro，26(4): 52-60 |
|
|
|
相关文献: |
|
|
1．黄姝娟, 朱怡安, 李兵哲, 陆伟.基于利用率和负载均衡的多核实时调度算法研究[J]. 西北工业大学, 2012,30(1): 117-123 |
|
|
|
|
|
|
