期刊文献+

一种多核系统上基于页着色的内存管理方法 被引量:1

A Memory Management Approach Based on Page Coloring for Multi-core Systems
下载PDF
导出
摘要 当今多核平台多采用共享cache架构,但运行在不同核心上的任务产生的cache冲突问题使得程序最坏执行时间的计算变得十分困难.因此提出了使用页着色技术解决多核cache上访存冲突问题的方法.此方法的优势是使已有单核上的WCET分析技术可以对多核上的程序执行时间进行判断.在Linux系统上实现了支持页着色划分方法的内存管理系统,并使用通用测试集对该方法进行了测试.实验结果表明,在Linux系统中使用该内存管理策略后,在相同多核平台上程序的执行时间变得可预测. Most multi-core platforms currently adopt shared cache among the processor cores. Due to the problem of cache contention, it is extremely difficult to predict the worst-case execution time of the computation tasks running on different cores. A page-coloring technique was proposed to avoid cache contention in memory access for multi-core platforms. The advantage is that the worst case execution time of tasks running on individual core can be estimated separately using the existing WCET analysis methods for uni-processor systems. A memory management system was designed based on the Linux to support page coloring mechanism, which is evaluated using the standard benchmarks. Experimental results shown that the execution time for different processor cores becomes deterministic when it is executed on the same platform running in the Linux supported with the management system.
出处 《东北大学学报(自然科学版)》 EI CAS CSCD 北大核心 2014年第3期351-355,共5页 Journal of Northeastern University(Natural Science)
基金 国家自然科学基金资助项目(61100023) 中央高校基本科研业务费专项资金资助项目(N120404008)
关键词 多核 CACHE 实时 页着色 操作系统 multi-core cache real-time page coloring operating system
  • 相关文献

参考文献13

  • 1Wilhelm R, EngblomJ, Ennedahl A, et al. The worst-case execution-time problem-overview of methods and survey of tools[J]. ACM Transactions on Embedded Computing Systems, 2008, 7 (3) : 1 - 53.
  • 2Li Y, Suhendra V, Liang Y, et al. Timing analysis of concurrent programs running on shared cache multi -cores[CJIIReal-Time Systems Symposium. Washington DC: IEEE, 2009 :57 - 67.
  • 3Kessler R E, Hill M D. Page placement algorithms for large real-indexed caches[J]. ACM Transactions on Computer Systems, 1992, 10(4) :338 - 359.
  • 4Cho S,Jin L. Managing distributed, shared 12 caches through OS-level page allocation[C]I lIEEE/ ACM International Symposium on Microarchitecture. Washington DC: IEEE, 2006:455 -468.
  • 5LinJ, Lu Q, Ding X, et al. Gaining insights into multicore cache partitioning: bridging the gap between simulation and real systems[C] IIHigh Performance Computer Architecture. Salt Lake City: IEEE, 2008:367 -378.
  • 6Soares L, Tam D, Stumm M. Reducing the harmful effects of last-level cache polluters with an OS-level, software-only pollute buffer[C] IIInternational Symposium on Microarchi?tecture. Washington DC: IEEE Computer Society, 2008: 258 - 269.
  • 7Zhang X, Dwarkadas S, Shen K. Towards practical page coloring-based multicore cache management[C] IIProceedings of the 4th ACM European Conference on Computer Systems. New York: ACM, 2009:89 -102.
  • 8Jeong M K, Yoon D H, Sunwoo D, et al. Balancing DRAM locality and parallelism in shared memory CMP systems[CJ II High Performance Computer Architecture. New Orleans: IEEE, 2012:1 -12.
  • 9Guan N, Stigge M, Yi W, et al. Cache-aware scheduling and analysis for multicores[C] IIProceedings of the seventh ACM International Conference on Embedded Software. New York:ACM, 2009:245 -254.
  • 10Yotov K, Pingali K, Stodghill P. Automatic measurement of memory hierarchy parameters[J]. ACM SIGMETRICS Performance Evaluation Review, 2005, 33 ( 1 ) : 181 - 192.

同被引文献8

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部