期刊文献+

一种非可规约循环的投机并行方法 被引量:1

Exploiting Speculative Parallelism in Irreducible Loops
下载PDF
导出
摘要 传统的并行编译器在处理非可规约循环时一般使用结点分割法,但由此带来的代码复制是不可避免的。本文使用投机的方法来挖掘非可规约循环的并行性,该方法在编译时查找程序中的非可规约循环,在运行时使用"持续引用"策略预测该循环的入口,进而实现非可规约循环的并行化。 Irreducible loop is a kind of loop with multi-entries. These loops are called irreducible because dominated relationship does not exist among the nodes in them. Traditional paralhlized compiler techniques use node splitting to make irreducible loops reducible, but will make code duplicate inevitably. This paper proposes a speculative method to exploit parllelism in irredudbh loops. This method finds irreducible loops at compile time and predicts the entry at run time using a strategy called"persistency reference", then parallelizes irreducible loops as natural loops. Experimental results show that the method is effective and efficient.
出处 《计算机工程与科学》 CSCD 2007年第10期135-138,共4页 Computer Engineering & Science
基金 国家自然科学基金资助项目(60173026) 上海科委重大项目(03DZ15029) 上海高校网格技术E-研究院资助项目(200301-1)
关键词 非可规约循环 持续引用 投机并行 失败恢复 irreducible loop persistency reference speculative parallel ism recovery
  • 相关文献

参考文献11

  • 1Cocke J, Miller R E. Some Analysis Techniques for Optimizing Computer Prngrams[A]. Proc of the 2nd Hawaii Conf on System Sciences[C]. 1969. 143-146.
  • 2Aho A, Sethi R,Ullman J. Compilers:Principles,Techniques, and Tools[M].北京:人民邮电出版社,2002.
  • 3Janssen J,Corporaal H. Making Graphs Reducible with Controlled Node Splitting[J]. ACM Trans on Programming Languages and Systems, 1997,19(6):1031-1052.
  • 4Unger S, Mueller F. Handling Irreducible Loops: Optimized Node Splitting Versus DJ-Graphs[J]. ACM Trans on Programming Languages and Systems, 2002,24(4):299-333.
  • 5Liu Y, Zhang Z, Qiao R, et al. A Region-Based Compilation Infrastructure[A]. Proc of the 7th Workshop on Interaction Between Compilers and Computer Architecture[C]. 2003. 75-84.
  • 6Muchnick S.高级编译器设计与实现[M].赵克佳,沈志宇译.北京:机械工业出版社,2005.
  • 7Allen F, Cocke J. A Program Data Flow Analysis Procedure [J]. Communications of the ACM, 1976,19(3):137-147.
  • 8Allen F,Coeke J. A Basis for Program Optimization[A]. Proe of IFIP Congress[C]. 1971.385-390.
  • 9Tarjan R. Fast Algorithms for Solving Path Problems[J]. Journal of the ACM, 1981,28(3) :594-614.
  • 10http://www, gnu. org/,2006-03.

共引文献1

同被引文献11

  • 1董春丽,韩林,赵荣彩.并行编译中一种线性数据和计算划分算法[J].计算机工程,2006,32(24):26-28. 被引量:5
  • 2Johnson T A,Eigenmann R,Vijaykumar T N.Speculative Thread Decomposition Through Empirical Optimization[C]//Proc.of the 12th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming.New York,USA:ACM Press,2007:205-214.
  • 3de Alba M R,Kaeli D R.Runtime Predictability of Loops[C]//Proc.of IEEE International Workshop on Workload Characterization.Washington D.C.,USA:IEEE Press,2001:91-98.
  • 4Mafijul I M.Predicting Loop Termination to Boost Speculative Thread-level Parallelism in Embedded Applications[C]//Proc.of the 19th IEEE Int'l Workshop on Computer Architecture and High Performance Computing.Aizu,Japan:IEEE Press,2007:54-61.
  • 5Mafijul I M,Busck A,Engbom M,et al.Limits on Thread-level Parallelism in Embedded Applications[C]//Proc.of the 11th IEEE Int'l Workshop on Interaction Between Compliers and Computer Architectures.Phoenix,Arizona,USA:IEEE Press,2007:40-49.
  • 6Wang Yaobin,An Hong,Liang Bo,et al.Balancing Thread Partition for Efficiently Exploiting Speculative Thread-level Parallelism[C]// Proc.of International Symposium on Advances in Visual Computing.Lake Tahoe,NV,USA:[s.n.],2007.
  • 7Wang Shengyue,Dai Xiaoru,Yellajyosula K S.et al.Loop Selection for Thread-level Speculation[C]//Proc.of International Workshop on Languages and Compilers for Parallel Computing.Hawthorne,NY,USA:[s.n.],2005.
  • 8Zhong Hongtao,Mehrara M,Lieberman S,et al.Uncovering Hidden Loop Level Parallelism in Sequential Applications[C]// Proc.of the 14th International Symposium on High-performance Computer Architecture.Salt Lake City,USA:[s.n.],2008.
  • 9Kongetira P,Aingaran K,Olukotun K.Niagara:A 32-way Multithreaded Sparc Processor[J].IEEE Micro,2005,25(2):21-29.
  • 10Prabhu M K,Olukotun K.Exposing Speculative Thread Parallelism in SPEC2000[C]//Proc.of the 10th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming.Chicago,IL,USA:ACM Press,2005:142-152.

引证文献1

二级引证文献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