一种全系统模拟器片上缓存动态功耗分析工具

上海交通大学学报（自然版） ›› 2013, Vol. 47 ›› Issue (01): 103-107.

• 自动化技术、计算机技术 • 上一篇下一篇

一种全系统模拟器片上缓存动态功耗分析工具

黄智濒，祝明发，肖利民

（北京航空航天大学软件开发环境国家重点实验室,计算机学院，北京 100191）

收稿日期:2012-06-30 出版日期:2013-01-30 发布日期:2013-01-30
基金资助:
软件开发环境国家重点实验室课题（SKLSDE2012ZX07）,北京市自然科学基金项目（4122042）,国家高技术研究发展计划(863)项目(2011AA01A205), 核高基重大专项课题(2010ZX01036001001),国家自然科学基金项目(60973008)资助

A Cache Dynamic Power Analysis Tool in Full-System Simics

HUANG Zhi-Bin, ZHU Ming-Fa, XIAO Li-Min

(State Key Laboratory of Software Development Environment, School of Computer Science and Engineering, Beihang University, Beijing 100191, China)

Received:2012-06-30 Online:2013-01-30 Published:2013-01-30

摘要/Abstract

摘要： 通过分析各种缓存逻辑结构和管理策略条件下的访存行为而得出5个原子操作；依据其对缓存数据阵列和标记阵列及其内部结构的操作，估算了原子操作的动态功耗并统计出缓存的动态功耗；基于修改的Cacti 6.5软件计算缓存数据阵列和标记阵列及其内部结构的功耗参数，提出了一种可用于全系统模拟器Simics的缓存动态功耗分析工具PowerGC.同时，经多组实验验证了PowerGC性能的有效性.结果表明，PowerGC可以有效评估Simics中各种缓存逻辑结构和管理策略的动态功耗.

关键词: 全系统模拟器, 动态功耗, 缓存

Abstract: A dynamic power analysis tool PowerGC based on Cache behavior for cycle-level full-system simics was proposed. The basic idea is dissembling the Cache behavior into five atomic operations. These operations independently drive the sub-components of data array and tag array, which can be estimated by Cacti 6.5 and support different Cache logic structures and Cache management policies. According to the evaluation results based on Simics, PowerGC works well to estimate the Cache dynamical power for different Cache structures and different management policies.

Key words: full-system simulator, dynamic power, Cache

中图分类号:

TP 332

黄智濒, 祝明发, 肖利民. 一种全系统模拟器片上缓存动态功耗分析工具 [J]. 上海交通大学学报（自然版）, 2013, 47(01): 103-107.

HUANG Zhi-Bin, ZHU Ming-Fa, XIAO Li-Min. A Cache Dynamic Power Analysis Tool in Full-System Simics[J]. Journal of Shanghai Jiaotong University, 2013, 47(01): 103-107.

参考文献

［1］DawsonHaggerty S, Krioukov A, Culler D. Power optimization: S reality checks ［EB/OL］. Berkeley, USA: University of California, 2009 ［20120620］. http:∥www.cs.berkeley.edu/~krioukov/realityCheck.pdf.
［2］Huang Z B, Zhu M F, Xiao L M. LvtPPP: Livetime protected pseudopartitioning of multicore shared Caches ［EB/OL］. ［20120801］.IEEE Transactions on Parallel and Distributed Systems. http:∥dx.doi.org/10.1109/TPDS.2012.230.
［3］Borkar S Y, Mulder H, Dubey P, et al. Platform 2015: Intel processor and platform evolution for the next decade ［EB/OL］. ［20120620］. http:∥heim.ifi.uio.no/~inf3410/docs/Intel_Corp_Platform_2015.pdf.
［4］Wentzlaff D, Beckmann N, Miller J, et al. Core count vs Cache size for manycore architectures in the cloud ［EB/OL］. ［20100211］. http:∥dspace.mit.edu/handle/1721.1/51733.
［5］Raveendran B K, Sudarshan T S B, Dilip Kumar P, et al. LLRU: Late LRU replacement strategy for power efficient embedded Cache ［C］ ∥ Advanced Computing and Communications. Guwahati, Assam: IEEE Computer Society Conference Publishing Services (CPS), 2007: 339344.
［6］Milidonis A, Porpodas V, Alachiotis N, et al. Lowpower architecture with scratchpad memory for accelerating embedded applications with runtime reuse ［J］. Computers and Digital Techniques, 2009, 3(1): 109123.
［7］Wang X, Ma K, Wang Y. Achieving fair or differentiated Cache sharing in powerconstrained chip multiprocessors ［C］ ∥ Proceedings of the 39th International Conference on Parallel Processing. Washington: IEEE Computer Society, 2010: 110.
［8］Brooks D, Tiwari V, Martonosi M. Wattch: A framework for architecturallevel power analysis and optimizations ［C］ ∥ Proceedings of the 27th Annual International Symposium on Computer Architecture. Vancouver, BC, Canada: IEEE Computer Society TCCA and ACM SIGARCH, 2000: 8394.
［9］Kotera I, Abe K, Egawa R, et al. Poweraware dynamic Cache partitioning for CMPs ［C］ ∥ Transactions on HighPerformance Embedded Architectures and Compilers III. Heidelberg: SpringerVerlag Berlin, 2011:135153.
［10］Binkert N L, Dreslinski R G, Hsu L R, et al. The M5 simulator: Modeling networked systems ［J］. IEEE Micro, 2006, 26(4): 5260.
［11］Muralimanohar N, Balasubramonian R, Jouppi N. Optimizing NUCA organizations and wiring alternatives for large Caches with CACTI 6.0 ［C］∥ Proc of the 40th IEEE/ACM International Symposium on Microarchitecture. Washington: IEEE Computer Society, 2007: 314.
［12］Burger D, Austin T M. The simplescalar toolset, Version 2.0 ［J］. ACM SIGARCH Computer Architecture News, 1997, 25(3): 1325.
［13］Magnusson P S, Christensson M, Eskilson J, et al. Simics: A full system simulator platform ［J］. Computer, 2002, 35(2): 5058.
［14］Khan S, Jiménez D A, Burger D, et al. Using dead blocks as a virtual victim Cache ［C］ ∥ Proceedings of the 19th International Conference on Parallel Architectures and Compilation Techniques. New York: ACM, 2010: 489500.
［15］Rolan D, Fraguela B B, Doallo R. Adaptive line placement with the set balancing Cache ［C］ ∥ Proc of the 42nd Annual IEEE/ACM International Symposium on Microarchitecture, New York: ACM, 2009: 529540.
［16］Jaleel A, Theobald K B, Steely S C, et al. High performance Cache replacement using rereference interval prediction (RRIP) ［C］ ∥ Proceedings of the 37th Annual International Symposium on Computer Architecture. New York: ACM, 2010: 6071.

[1]	田雪雁, 王孟雅, 潘尔顺. 基于马尔科夫决策过程的带缓存双机系统不完美维护策略[J]. 上海交通大学学报, 2021, 55(4): 480-488.
[2]	郭闻雨，张秀芳，修玉皎，夏唐斌，潘尔顺. 考虑动态性能退化的生产系统预防维护和缓存配置策略[J]. 上海交通大学学报, 2019, 53(9): 1107-1114.
[3]	刘波，王晓彤，张冬明，葛伟琪. 一种面向雷达应用可重构系统中的数据缓存结构和管理机制[J]. 上海交通大学学报（自然版）, 2017, 51(5): 628-.
[4]	李永进, 邓让钰, 晏小波, 衣晓飞, 周宏伟, 张英. 频率2 GHz的16核处理器二级缓存设计[J]. 上海交通大学学报（自然版）, 2013, 47(01): 108-112.

一种全系统模拟器片上缓存动态功耗分析工具

A Cache Dynamic Power Analysis Tool in Full-System Simics

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 4

编辑推荐

Metrics

本文评价