Abstract
Task-based parallel programming models based on compiler directives have proved their effectiveness at describing parallelism in High-Performance Computing (HPC) applications. Recent studies show that cutting-edge Real-Time applications, such as those for unmanned vehicles, can successfully exploit these models. In this scenario, OpenMP is a de facto standard for HPC, and is being studied for Real-Time systems due to its time-predictability and delimited functional safety. However, changes in OpenMP take time to be standardized because it sweeps along a large community. OmpSs, instead, is a task-based model for fast-prototyping that has been a forerunner of OpenMP since its inception. OmpSs-2, its successor, aims at the same goal, and defines several features that can be introduced in future versions of OpenMP. This work targets compiler-based optimizations to enhance the programmability and performance of OmpSs-2. Regarding the former, we present an algorithm to determine the data-sharing attributes of OmpSs-2 tasks. Regarding the latter, we introduce a new algorithm to automatically release OmpSs-2 task dependencies before a task has completed. This work evaluates both algorithms in a set of well-known benchmarks, and discusses their applicability to the current and future specifications of OpenMP.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
A task \(t_2\) synchronizes [19] a task \(t_1\) if \(t_2\) is created after \(t_1\), and either (a) \(t_1\) designates an out object that \(t_2\) designates as in or out, or (b) \(t_1\) designates an in object that \(t_2\) designates as out, or (c) \(t_1\) and \(t_2\) designate the same commutative object.
- 2.
The artifact with the LLVM tool-chain with the proposed algorithms, the Nanos runtime library, and the test-suit used for the evaluation is publicly available in https://gitlab.bsc.es/ppc-bsc/research/c3po-artifact/-/tags/v1.0. A stable version of Clang for OmpSs-2 and Nanos will be released in the next months.
References
Augonnet, C., Thibault, S., Namyst, R., Wacrenier, P.A.: StarPU: a unified platform for task scheduling on heterogeneous multicore architectures. Concurr. Comput. Pract. Exp. 23(2), 187–198 (2011)
Ayguadé, E., et al.: Extending OpenMP to survive the heterogeneous multi-core era. Int. J. Parallel Program. 38(5–6), 440–459 (2010)
Barcelona Supercomputing Center: Mercurium. https://pm.bsc.es/mcxx
Barcelona Supercomputing Center: Nanos++. https://pm.bsc.es/nanox
Barcelona Supercomputing Center: Ompss-2. https://pm.bsc.es/ompss-2
Dagum, L., Menon, R.: OpenMP: an industry standard API for shared-memory programming. IEEE Comput. Sci. Eng. 5(1), 46–55 (1998)
Duran, A., et al.: OmpSs: a proposal for programming heterogeneous multi-core architectures. Parallel Process. Lett. 21(02), 173–193 (2011)
Duran, A., Teruel, X., Ferrer, R., Martorell, X., Ayguade, E.: Barcelona OpenMP tasks suite: a set of benchmarks targeting the exploitation of task parallelism in OpenMP. In: International Conference on Parallel Processing, pp. 124–131 (2009)
González, C.H., Fraguela, B.B.: A framework for argument-based task synchronization with automatic detection of dependencies. Parallel Comput. 39(9), 475–489 (2013)
Kegel, P., Schellmann, M., Gorlatch, S.: Using OpenMP vs. threading building blocks for medical imaging on multi-cores. In: Europar, pp. 654–665 (2009)
Lin, Y., Terboven, C., Mey, D., Copty, N.: Automatic scoping of variables in parallel regions of an OpenMP program. In: Chapman, B.M. (ed.) WOMPAT 2004. LNCS, vol. 3349, pp. 83–97. Springer, Heidelberg (2005). https://doi.org/10.1007/978-3-540-31832-3_8
Martineau, M., McIntosh-Smith, S., Gaudin, W.: Evaluating OpenMP 4.0’s effectiveness as a heterogeneous parallel programming model. In: International Parallel and Distributed Processing Symposium Workshops, pp. 338–347 (2016)
OpenMP ARB: OpenMP Application Program Interface, version 5.0 (2018)
OpenMP ARB: OpenMP Technical Report 8: version 5.1 preview (2019)
Oracle: Oracle Solaris Studio 12.2: OpenMP API User’s Guide (2010). http://docs.oracle.com/cd/E18659_01/html/821-1381/toc.html
Royuela, S.: High-level compiler analysis for OpenMP. Ph.D. thesis (2018)
Royuela, S., Duran, A., Liao, C., Quinlan, D.J.: Auto-scoping for OpenMP tasks. In: Chapman, B.M., Massaioli, F., Müller, M.S., Rorro, M. (eds.) IWOMP 2012. LNCS, vol. 7312, pp. 29–43. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-30961-8_3
Royuela, S., Duran, A., Serrano, M.A., Quiñones, E., Martorell, X.: A functional safety OpenMP\(^{*}\) for critical real-time embedded systems. In: de Supinski, B.R., Olivier, S.L., Terboven, C., Chapman, B.M., Müller, M.S. (eds.) IWOMP 2017. LNCS, vol. 10468, pp. 231–245. Springer, Cham (2017). https://doi.org/10.1007/978-3-319-65578-9_16
Royuela, S., Ferrer, R., Caballero, D., Martorell, X.: Compiler analysis for OpenMP tasks correctness. In: Computing Frontiers, pp. 1–8 (2015)
Royuela, S., Pinho, L.M., Quiñones, E.: Enabling Ada and OpenMP runtimes interoperability through template-based execution. J. Syst. Arch. 105, 101702 (2020)
Serrano, M.A., Royuela, S., Quiñones, E.: Towards an OpenMP specification for critical real-time systems. In: International Workshop on OpenMP (2018)
Tagliavini, G., Cesarini, D., Marongiu, A.: Unleashing fine-grained parallelism on embedded many-core accelerators with lightweight OpenMP tasking. Trans. Parallel Distrib. Syst. 29(9), 2150–2163 (2018)
Toledo, L., Peña, A.J., Catalán, S., Valero-Lara, P.: Tasking in accelerators: performance evaluation. In: 20th International Conference on Parallel and Distributed Computing, Applications and Technologies, pp. 127–132. IEEE (2019)
Varbanescu, A.L., Hijma, P., Van Nieuwpoort, R., Bal, H.: Towards an effective unified programming model for many-cores. In: IPDPS, pp. 681–692. IEEE (2011)
Voss, M., Chiu, E., Chow, P.M.Y., Wong, C., Yuen, K.: An evaluation of auto-scoping in OpenMP. In: Chapman, B.M. (ed.) WOMPAT 2004. LNCS, vol. 3349, pp. 98–109. Springer, Heidelberg (2005). https://doi.org/10.1007/978-3-540-31832-3_9
Wang, C.K., Chen, P.S.: Automatic scoping of task clauses for the OpenMP tasking model. J. Supercomput. 71(3), 808–823 (2015)
Willhalm, T., Popovici, N.: Putting intel® threading building blocks to work. In: 1st International Workshop on Multicore Software Engineering, pp. 3–4 (2008)
Yu, C., Royuela, S., Quiñones, E.: OpenMP to CUDA graphs: a compiler-based transformation to enhance the programmability of NVIDIA devices. In: 23rd International Workshop on Software & Compilers for Embedded Systems (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Munera, A., Royuela, S., Ferrer, R., Peñacoba, R., Quiñones, E. (2020). Static Analysis to Enhance Programmability and Performance in OmpSs-2. In: Jagode, H., Anzt, H., Juckeland, G., Ltaief, H. (eds) High Performance Computing. ISC High Performance 2020. Lecture Notes in Computer Science(), vol 12321. Springer, Cham. https://doi.org/10.1007/978-3-030-59851-8_2
Download citation
DOI: https://doi.org/10.1007/978-3-030-59851-8_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-59850-1
Online ISBN: 978-3-030-59851-8
eBook Packages: Computer ScienceComputer Science (R0)