期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

面向OpenMP和OpenTM应用的并行数据重用理论 被引量：3

Parallel Data Reuse Theories for OpenMP and OpenTM Applications
下载PDF
导出
摘要 将经典的数据重用理论扩充到并行领域,分别提出了面向OpenMP和OpenTM应用的并行数据重用理论.针对重用在线程、事务中的关系,系统地讨论了并行应用中重用的分类、判定和求解方法.同时,应用这一理论研究了OpenTM循环的优化技术,以降低事务被回退的风险.最后,使用并行数据重用理论分析和统计了SPEComp2001中的数据重用.并行数据重用理论可以用于指导面向多核存储共享结构的并行程序分析和编译优化技术研究. This paper extends the famous data reuse theory to a parallel domain and proposes parallel data reuse theories for OpenMP and OpenTM applications, respectively. Through studying the relationships between threads and transactions, the parallel data reuse theories systemically discuss how to classify, judge, and compute reuses in parallel programs. Meanwhile, the optimization framework for reducing OpenTM transactions rolled back is studied. Finally, the data reuses in SPECornp2001 benchmarks are analyzed. The parallel data reuse theories can be used to direct the analysis of parallel applications and the research of compiler optimization techniques on multi-core shared memory architecture.
作者 吴俊杰 杨学军 刘光辉 唐玉华
机构地区 国防科学技术大学计算机学院并行与分布处理国家重点实验室 国防科学技术大学计算机学院计算机科学与技术系
出处 《软件学报》 EI CSCD 北大核心 2010年第12期3011-3028,共18页 Journal of Software
基金 国家自然科学基金Nos.60921062 60873014 61003082~~
关键词 并行应用 重用 局部性 多核 OPENMP OpenTM parallel application reuse locality multi-core OpenMP OpenTM
分类号 TP314 [自动化与计算机技术—计算机软件与理论]
  • 相关文献

参考文献4

二级参考文献67

  • 1McKinley Kathryn S, Carr Steve, Tseng Chau-Wen. Improving data locality with loop transformations [J]. ACM Trans on Programming Languages and Systems, 1996, 18 (4) : 424-453.
  • 2Seznec Andre. A case for two-way skewed-associative caches [C] //Proc of the 20th Annual Int Syrup on Computer Architecture (ISCA'93). New York: ACM, 1993: 169-178.
  • 3Abella Jaume, Gonzalez Antonio. Heterogeneous way-size cache [C] //Proc of the 20th Annual Int Conf on Supercomputing (ICS'06). New York: ACM, 2006: 239- 248.
  • 4Qureshi Moinuddin K, Thompson David, Patt Yale N. The v-way cache: Demand based assoeiativity via global replacement [C] //Proe of the 32nd Annual Int Syrup on Computer Architecture (ISCA'05). Washington, DC: IEEE Computer Society, 2005:544-555.
  • 5Varadarajan Keshavan, Nandy S K, Sharda Vishal, et al.Molecular caches: A caching structure for dynamic creation of application-specific heterogeneous cache regions [C]//Proc of the 39th Annual IEEE/ACM Int Symp on Microarchitecture (MICRO'06). Washington, DC: IEEE Computer Society, 2006:433-442.
  • 6Qureshi Moinuddin K, Jaleel Aamer, Patt Yale N, et al. Adaptive insertion policies for high performance caching [C] //Proc of the 34th Annual Int Syrup on Computer Architecture (ISCA'07). New York: ACM, 2007:381-391.
  • 7Witchel E, Asanovic K. The span cache: Software controlled tag checks and cache line size [C] //Proc of the 28th Workshop on Complexity Effective Design ( ISCA ). Washington, DC: IEEE Computer Society, 2001:1-12.
  • 8Gonzalez Antonio, Aliagas Carlos, Valero Mateo. A data cache with multiple caching strategies tuned to different types of locality [C] //Proc of the 9th Int Conf on Supercomputing (ICS'95). New York: ACM, 1995:338-347.
  • 9Kim S, Vijaykrishnan N, Kandemir M, et al. Power-aware partitioned cache architectures [C] //Proc of the 2001 Int Symp on Low Power Electronics and Design (ISLPED'01). New York: ACM, 2001:64-67.
  • 10Lee Hsien-Hsin S, Smelyanskiy Mikhail, Tyson Gary S, et al. Stack value file: Custom microarchitecture for the stack [C] //Proc of the 7th Int Symp on High Performance Computer Architecture ( HPCA'01 ). Washington, DC: IEEE Computer Society, 2001:5.

共引文献11

同被引文献26

  • 1张平,赵荣彩,李清宝.基于相关性的同步优化算法[J].计算机工程,2005,31(17):68-70. 被引量：5
  • 2Baek W,Minh C C,Trautmann M,et al. The OpenTM transactionalapplication programming interface. Parallel Architecture and Compila-tion Techniques, 16th International Conference on, IEEE, 2007 :376-387.
  • 3付明.低级并行代码中几种同步机制的验证.合肥:中国科学技术大学,2009.
  • 4李勇.基于软件事务内存的并行程序验证.合肥:中国科学技术大学,2011.
  • 5王堃.基于多核的并行程序设计及优化.南京:南京大学,2012.
  • 6McKenney P E,Michael M M,Triplett J,et al. Why the grass maynot be greener on the other side : A comparison of locking vs. transac-tional memory. ACM SIGOPS Operating Systems Review, 2010 ; 44(3); 93-101.
  • 7Nakano J, Montesinos P, Gharachorloo K, et al. ReViveI/0: effi-cient handling of I/O in highly-available rollback-recovery servers.High-Performance Computer Architecture. The Twelfth InternationalSymposium on, 2006:200-211.
  • 8Ni Y, Welc A, Adl-Tabatabai A R,ei al. Design and implementa-tion of transactional constructs for C/C++ . ACM Sigplan Notices,ACM, 2008; 43(10) : 195-212.
  • 9胡斌,袁道华.TBB多核编程及其混合编程模型的研究[J].计算机技术与发展,2009,19(2):98-101. 被引量：17
  • 10剡公孝,申卫昌,刘骊,刘伟明.一种基于MPICH的高效矩阵相乘并行算法[J].计算机工程与应用,2009,45(26):72-73. 被引量：2

引证文献3

二级引证文献5

软件学报
2010年 第12期

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