Regular Research ArticlesNo Access

Revisiting OpenMP Auto-Scoping Rules

Vassilios V. Dimakopoulos

https://orcid.org/0000-0001-8420-1878

Department of Computer Science and Engineering, University of Ioannina, P. O. Box 1186, Ioannina, GR-45110, Greece

E-mail Address: dimako@cse.uoi.gr

Corresponding author.

Search for more papers by this author

and

Agelos Mourelis

BETA CAE Systems SA, Kato Scholari, Thessaloniki, GR-57500 Epanomi, Greece

Search for more papers by this author

https://doi.org/10.1142/S0129626423500020Cited by:0 (Source: Crossref)

Abstract

Auto-scoping in OpenMP has been proposed as a means for relieving the programmer from the non-trivial effort of identifying the data sharing attributes of variables used within code regions that produce concurrency, such as parallel and task constructs. In this work we reconsider autoscoping on parallel constructs, including combined parallel-worksharing constructs. We first show that the current implementations do not always scope variables correctly in the presence of nested parallel constructs. We then proceed to extend the set of rules that guide the autoscoping decisions so as to handle nested constructs successfully. We also discuss how this functionality is implemented in the OMPi source-to-source OpenMP compiler.

Communicated by Andrew Adamatzky

Keywords:

References

1. OpenMP ARB, OpenMP Application Program Interface V5.2 (November 2021). Google Scholar
2. Y. Lin, C. Terboven, D. A. Mey and N. Copty, Automatic scoping of variables in parallel regions of an OpenMP program, in WOMPAT ’04, 5th Workshop on OpenMP Applications and Tools, ed. B. M. Chapman (Berlin, Heidelberg, 2004), pp. 83–97. Google Scholar
3. M. Süß and C. Leopold, Common mistakes in OpenMP and how to avoid them, in Proc. IWOMP 2006, 2nd International Workshop on OpenMP (Reims, France, 2006), pp. 312–323. Google Scholar
4. V. V. Dimakopoulos, E. Leontiadis and G. Tzoumas, A portable C compiler for OpenMP V.2.0, in Proc. of EWOMP 2003, 5th European Workshop on OpenMP (Aachen, Germany, 2003), pp. 5–11. Google Scholar
5. Oracle, Oracle Developer Studio 12.6: OpenMP API User’s Guide (June 2017). Google Scholar
6. S. Royuela, A. Duran, C. Liao and D. J. Quinlan, Auto-scoping for OpenMP tasks, in Proc. IWOMP’12, 8th International Workshop on OpenMP (Berlin, Heidelberg, 2012), pp. 29–43. Crossref, Google Scholar
7. C.-K. Wang and P.-S. Chen, Automatic scoping of task clauses for the OpenMP tasking model, The Journal of Supercomputing 71(3) (2015) 808–823. Crossref, Web of Science, Google Scholar
8. A. Munera, S. Royuela, R. Ferrer, R. Peñacoba and E. Quiñones, Static analysis to enhance programmability and performance in OmpSs-2, in Proc. ISC High Performance 2020 International Workshops (Cham, 2020), pp. 19–33. Crossref, Google Scholar
9. C. Liao, D. J. Quinlan, J. J. Willcock and T. Panas, Semantic-aware automatic parallelization of modern applications using high-level abstractions, International Journal of Parallel Programming 38(5–6) (2010) 361–378. Crossref, Web of Science, Google Scholar
10. T. G. Mattson, Y. H. He and A. E. Koniges, The OpenMP Common Core: Making OpenMP Simple Again (MIT Press, Cambridge, Massachusetts, 2019). Google Scholar
11. M. Voss, E. Chiu, P. M. Y. Chow, C. Wong and K. Yuen, An evaluation of auto-scoping in OpenMP, in Proc. WOMPAT ’04, 5th Workshop on OpenMP Applications and Tools (Berlin, Heidelberg, 2004), pp. 98–109. Google Scholar
12. M. Popov, C. Akel, F. Conti, W. Jalby and P. De Oliveira Castro, PCERE: Fine-grained parallel benchmark decomposition for scalability prediction, in Proc. 2015 IEEE International Parallel and Distributed Processing Symposium (Hyderabad, India, 2015), pp. 1151–1160. Available at: https://github.com/benchmark-subsetting/NPB3.0-omp-C (accessed May 2022). Crossref, Google Scholar