Automatic scoping of task clauses for the OpenMP tasking model

详细信息    查看全文

• 作者：Chun-Kun Wang (1)
  Peng-Sheng Chen (2)
  
  1. Department of Computer Science and Information Engineering ; National Chung Cheng University ; Chiayi ; 621 ; Taiwan
  2. Department of Computer Science and Information Engineering ; Advanced Institute of Manufacturing for High-tech Innovations ; National Chung Cheng University ; Chiayi ; 621 ; Taiwan
  
• 关键词：OpenMP ; Tasking model ; Parallelization ; Validation
• 刊名：The Journal of Supercomputing
• 出版年：2015
• 出版时间：March 2015
• 年：2015
• 卷：71
• 期：3
• 页码：808-823
• 全文大小：616 KB
• 参考文献：1. Aho AV, Sethi R, Ullman JD (1986) Compilers: principles, techniques, and tools. Addison Wesley
  2. Allen R, Kennedy K (2001) Optimizing compilers for modern architectures: a dependence-based approach. Morgan Kaufmann
  3. Arabnia H, Smith JW (1993) A reconfigurable interconnection network for imaging operations and its implementation using a multi-stage switching box. In: International conference on high performance computing: New Horizons (Alberta, Canada, 1993), pp 349鈥?57
  4. Arabnia, HR (1990) A parallel algorithm for the arbitrary rotation of digitized images using process-and-data-decomposition approach. J Parallel Distrib Comput 10: pp. 188-192 CrossRef
  5. Aslot V, Domeika MJ, Eigenmann R, Gaertner G, Jones WB, Parady B (2001) Specomp: a new benchmark suite for measuring parallel computer performance. In: Proceedings of the international workshop on OpenMP applications and tools: OpenMP shared memory parallel programming (London, UK, UK, 2001), WOMPAT 鈥?1, Springer, pp 1鈥?0
  6. Ayguad茅, E, Copty, N, Duran, A, Hoeflinger, J, Lin, Y, Massaioli, F, Teruel, X, Unnikrishnan, P, Zhang, G (2009) The design of openmp tasks. IEEE Trans Parallel Distrib Syst 20: pp. 404-418 CrossRef
  7. Bhandarkar, SM, Arabnia, HR (1995) The refine multiprocessor theoretical properties and algorithms. Parallel Comput 21: pp. 1783-1805 CrossRef
  8. Bik, A, Girkar, M, Grey, P, Tian, X (2001) Efficient exploitation of parallelism on Pentium III and Pentium 4 processor-based systems. Intel Technol J Q1: pp. 9
  9. Bondhugula U, Baskaran M, Krishnamoorthy S, Ramanujam J, Rountev A, Sadayappan P (2008) Automatic transformations for communication-minimized parallelization and locality optimization in the polyhedral model. In: International conference on compiler construction (ETAPS CC)
  10. Duran A, Corbalan J, Ayguade E (2008) Evaluation of openmp task scheduling strategies. In: OpenMP in a new era of parallelism (4th IWOMP鈥?8), Eigenmann R, de Supinski BR eds vol 5004 of lecture notes in computer science (LNCS). Springer, New York, West Lafayette, IN, USA, pp 100鈥?10
  11. Duran A, Teruel X, Ferrer R, Martorell X, Ayguade E (2009) Barcelona openmp tasks suite: a set of benchmarks targeting the exploitation of task parallelism in openmp. In: Proceedings of 2009 international conference on parallel processing (38th ICPP鈥?9) CD-ROM (Vienna, Austria, Sept. 2009), IEEE Computer Society
  12. Intel. Automatic parallelization with intel compilers. http://software.intel.com/en-us/articles/automatic-parallelization-with-intel-compilers/. [Online; Accessed 1 July 2011]
  13. Jin, H, Jost, G, Yan, J, Ayguade, E, Gonzalez, M, Martorell, X (2003) Automatic multilevel parallelization using openmp. Sci Progr 11: pp. 177-190
  14. Johnson S, Evans E, Jin H, Ierotheou C (2005) The parawise expert assistant - widening accessibility to efficient and scalable tool generated openmp code. In: Proceedings of the 5th international conference on OpenMP applications and tools: shared memory parallel programming with OpenMP (Berlin, 2005), WOMPAT鈥?4, Springer, pp 67鈥?2
  15. Karpov A (2009) Peaceful coexistence of pc-lint and vivamp. http://www.viva64.com/en/b/0005/ [Online; Accessed 1 July 2011]
  16. Liao C, Quinlan DJ, Panas T, de Supinski BR (2010) A ROSE-based openmp 3.0 research compiler supporting multiple runtime libraries. In: IWOMP, Sato M, Hanawa T, M眉ller MS, Chapman BM, de Supinski BR eds vol 6132 of lecture notes in computer science, Springer, pp 15鈥?8
  17. Liao, C, Quinlan, DJ, Willcock, J, Panas, T (2010) Semantic-aware automatic parallelization of modern applications using high-level abstractions. Int J Parallel Program 38: pp. 361-378 CrossRef
  18. Lin Y, Terboven C, Mey DA, Copty N (2005) Automatic scoping of variables in parallel regions of an openmp program. In: Proceedings of the 5th international conference on OpenMP applications and tools: shared memory parallel programming with OpenMP, WOMPAT鈥?4, Springer, Berlin, pp 83鈥?7
  19. Mattson T, Sanders B, Massingill B (2004) Patterns for parallel programming, 1st edn Addison-Wesley Professional
  20. Muchnick S (1997) Advanced compiler design and implementation. Morgan Kaufmann
  21. M眉ller, MS, Neytchev, P (2003) An openmp validation suite. Aachen University, Germany
  22. OpenMP architecture review board (2011) OpenMP application program interface, 3.1 edn. Online available at http://www.openmp.org
  23. Oracle (2012) Oracle solaris studio 12.3: OpenMP API USer鈥檚 Guide. http://docs.oracle.com/cd/E24457_01/html/E21996/, [Online; Accessed 1 Sept 2013]
  24. Padua, DA, Wolfe, MJ (1986) Advanced compiler optimizations for supercomputers. Commun ACM 29: pp. 1184-1201 CrossRef
  25. Quinlan, DJ (2000) ROSE: compiler support for object-oriented frameworks. Parallel Process Lett 10: pp. 215-226 CrossRef
  26. Royuela S, Duran A, Liao C, Quinlan DJ (2012) Auto-scoping for openmp tasks. In: Proceedings of the 8th international conference on OpenMP in a heterogeneous World, IWOMP鈥?2, Springer, Berlin, pp 29鈥?3
  27. Voss M, Chiu E, Chow PMY, Wong C, Yuen K (2005) An evaluation of auto-scoping in openmp. In: Proceedings of the 5th international conference on OpenMP applications and tools: shared memory parallel programming with OpenMP, WOMPAT鈥?4, Springer, Berlin, pp 98鈥?09
  28. Website. Programming of parallel computers, assignment 3, gram-schmidt. https://github.com/yohannteston/Parallel-course-Ass3/. [Online; Accessed 1 July 2011]
  29. Wolfe, MJ (1995) High performance compilers for parallel computing. Addison Wesley, Boston
  
• 刊物类别：Computer Science
• 刊物主题：Programming Languages, Compilers and Interpreters
  Processor Architectures
  Computer Science, general
  
• 出版者：Springer Netherlands
• ISSN：1573-0484

文摘

OpenMP provides an easy-to-learn and powerful programming environment for the development of parallel programs. We propose here an algorithm for the automatic correction of the OpenMP tasking model. Assuming a compiler or programmer has identified task regions in the source programs, the proposed algorithm will automatically generate correct task clauses and synchronization. The proposed algorithm is implemented here based on the ROSE compiler infrastructure; 14 benchmark programs are tested, each of which has had all clauses in the task directives removed for the evaluation. The results of this experimental evaluation show that the proposed technique can successfully generate correct clauses for the tested benchmark programs. The proposed technique can simplify the parallelizing of programs using the OpenMP tasking model, making parallel programming more effective and productive.