Abstract
Efficiently exploiting GPUs is increasingly essential in scientific computing, as many current and upcoming supercomputers are built using them. To facilitate this, there are a number of programming approaches, such as CUDA, OpenACC and OpenMP 4, supporting different programming languages (mainly C/C++ and Fortran). There are also several compiler suites (clang, nvcc, PGI, XL) each supporting different combinations of languages. In this study, we take a detailed look at some of the currently available options, and carry out a comprehensive analysis and comparison using computational loops and applications from the domain of unstructured mesh computations. Beyond runtimes and performance metrics (GB/s), we explore factors that influence performance such as register counts, occupancy, usage of different memory types, instruction counts, and algorithmic differences. Results of this work show how clang’s CUDA compiler frequently outperform NVIDIA’s nvcc, performance issues with directive-based approaches on complex kernels, and OpenMP 4 support maturing in clang and XL; currently around 10% slower than CUDA.
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
References
Nickolls, J., Buck, I., Garland, M., Skadron, K.: Scalable parallel programming with CUDA. Queue 6(2), 40–53 (2008). https://doi.org/10.1145/1365490.1365500. ISSN: 1542-7730
Stone, J.E., Gohara, D., Shi, G.: OpenCL: a parallel programming standard for heterogeneous computing systems. IEEE Des. Test 12(3), 66–73 (2010). https://doi.org/10.1109/MCSE.2010.69. ISSN: 0740-7475
Wienke, S., Springer, P., Terboven, C., an Mey, D.: OpenACC — first experiences with real-world applications. In: Kaklamanis, C., Papatheodorou, T., Spirakis, P.G. (eds.) Euro-Par 2012. LNCS, vol. 7484, pp. 859–870. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-32820-6_85
OpenMP 4.5 specification. http://www.openmp.org/wp-content/uploads/openmp-4.5.pdf
Wu, J., Belevich, A., Bendersky, E., Heffernan, M., Leary, C., Pienaar, J., Roune, B., Springer, R., Weng, X., Hundt, R.: Gpucc: an open-source GPGPU Compiler. In: Proceedings of the 2016 International Symposium on Code Generation and Optimization, CGO 2016, Barcelona, Spain, pp. 105–116. ACM (2016). https://doi.org/10.1145/2854038.2854041. ISBN: 978-1-4503-3778-6
The Portland Group. http://www.pgroup.com
Ruetsch, G., Fatica, M.: CUDA Fortran for Scientists and Engineers: Best Practices for Efficient CUDA Fortran Programming. Elsevier, Amsterdam (2013)
Getting Started with CUDA Fortran programming using XL Fortran for Little Endian Distributions. http://www-01.ibm.com/support/docview.wss?uid=swg27047958&aid=11
Clang with OpenMP 4 support. https://github.com/clang-ykt
Ledur, C.L., Zeve, C.M., dos Anjos, J.C.: Comparative analysis of OpenACC, OpenMP and CUDA using sequential and parallel algorithms. In: 11th Workshop on Parallel and Distributed Processing (WSPPD) (2013)
Herdman, J., Gaudin, W., McIntosh-Smith, S., Boulton, M., Beckingsale, D.A., Mallinson, A., Jarvis, S.A.: Accelerating hydrocodes with OpenACC, OpenCL and CUDA. In: High Performance Computing, Networking, Storage and Analysis (SCC), 2012 SC Companion, pp. 465–471. IEEE (2012)
Hoshino, T., Maruyama, N., Matsuoka, S., Takaki, R.: CUDA vs OpenACC: performance case studies with kernel benchmarks and a memory-bound CFD application. In: 2013 13th IEEE/ACM International Symposium on Cluster, Cloud, and Grid Computing, pp. 136–143, May 2013. https://doi.org/10.1109/CCGrid.2013.12
Norman, M., Larkin, J., Vose, A., Evans, K.: A case study of CUDA FORTRAN and OpenACC for an atmospheric climate kernel. J. Comput. Sci. 9, 1–6 (2015)
Kuan, L., Neves, J., Pratas, F., Tomás, P., Sousa, L.: Accelerating phylogenetic inference on GPUs: an OpenACC and CUDA comparison. In: IWBBIO 2014, pp. 589–600 (2014)
Gong, J., Markidis, S., Laure, E., Otten, M., Fischer, P., Min, M.: Nekbone performance on GPUs with OpenACC and CUDA fortran implementations. J. Supercomput. 72(11), 4160–4180 (2016)
Antao, S.F., Bataev, A., Jacob, A.C., Bercea, G.-T., Eichenberger, A.E., Rokos, G., Martineau, M., Jin, T., Ozen, G., Sura, Z., et al.: Offloading support for OpenMP in clang and LLVM. In: Proceedings of the Third Workshop on LLVM Compiler Infrastructure in HPC, pp. 1–11. IEEE Press (2016)
Martineau, M., Price, J., McIntosh-Smith, S., Gaudin, W.: Pragmatic performance portability with OpenMP 4.x. In: Maruyama, N., de Supinski, B.R., Wahib, M. (eds.) IWOMP 2016. LNCS, vol. 9903, pp. 253–267. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-45550-1_18
Karlin, I., et al.: Early experiences porting three applications to OpenMP 4.5. In: Maruyama, N., de Supinski, B.R., Wahib, M. (eds.) IWOMP 2016. LNCS, vol. 9903, pp. 281–292. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-45550-1_20
Hart, A.: First experiences porting a parallel application to a hybrid supercomputer with OpenMP4.0 device constructs. In: Terboven, C., de Supinski, B.R., Reble, P., Chapman, B.M., Müller, M.S. (eds.) IWOMP 2015. LNCS, vol. 9342, pp. 73–85. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24595-9_6
Reguly, I.Z., Keita, A.-K., Zurob, R., Giles, M.B.: High performance computing on the IBM power8 platform. In: Taufer, M., Mohr, B., Kunkel, J.M. (eds.) ISC High Performance 2016. LNCS, vol. 9945, pp. 235–254. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-46079-6_17
OP2 github repository. https://github.com/OP2/OP2-Common
Mudalige, G., Giles, M., Reguly, I., Bertolli, C., Kelly, P.: OP2: an active library framework for solving unstructured mesh-based applications on multi-core and many-core architectures. In: Innovative Parallel Computing (InPar), pp. 1–12. IEEE (2012)
Giles, M.B., Mudalige, G.R., Sharif, Z., Markall, G., Kelly, P.H.: Performance analysis and optimization of the OP2 framework on many-core architectures. Comput. J. 55(2), 168–180 (2011)
Giles, M., Mudalige, G., Reguly, I.: OP2 airfoil example (2012)
Dutykh, D., Poncet, R., Dias, F.: The VOLNA code for the numerical modeling of tsunami waves: generation, propagation and inundation. Euro. J. Mech. B Fluids 30(6), 598–615 (2011)
Uk mini-app consortium. https://uk-mac.github.io
Acknowledgements
The authors would like to thank the IBM Toronto compiler team, and Rafik Zurob in particular, for access to beta compilers and help with performance tuning, and Michal Iwanski and József Surányi at IBM for access to a Minsky system. Thanks to Carlo Bertolli at IBM TJ Watson for help with the clang OpenMP 4 compiler. This paper was supported by the János Bólyai Research Scholarship of the Hungarian Academy of Sciences. The authors would like to acknowledge the use of the University of Oxford Advanced Research Computing (ARC) facility in carrying out this work http://dx.doi.org/10.5281/zenodo.22558. The research has been supported by the European Union, co-financed by the European Social Fund (EFOP-3.6.2-16-2017-00013).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG
About this paper
Cite this paper
Balogh, G.D., Reguly, I.Z., Mudalige, G.R. (2018). Comparison of Parallelisation Approaches, Languages, and Compilers for Unstructured Mesh Algorithms on GPUs. In: Jarvis, S., Wright, S., Hammond, S. (eds) High Performance Computing Systems. Performance Modeling, Benchmarking, and Simulation. PMBS 2017. Lecture Notes in Computer Science(), vol 10724. Springer, Cham. https://doi.org/10.1007/978-3-319-72971-8_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-72971-8_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-72970-1
Online ISBN: 978-3-319-72971-8
eBook Packages: Computer ScienceComputer Science (R0)