Abstract
Portable parallel programming models provide the potential for high performance and productivity, however they come with a multitude of runtime parameters that can have significant impact on execution performance. Selecting the optimal set of those parameters is non-trivial, so that HPC applications perform well in different system environments and on different input data sets, without the need of time consuming parameter exploration or major algorithmic adjustments.
We present Artemis, a method for online, feedback-driven, automatic parameter tuning using machine learning that is generalizable and suitable for integration into high-performance codes. Artemis monitors execution at runtime and creates adaptive models for tuning execution parameters, while being minimally invasive in application development and runtime overhead. We demonstrate the effectiveness of Artemis by optimizing the execution times of three HPC proxy applications: Cleverleaf, LULESH, and Kokkos Kernels SpMV. Evaluation shows that Artemis selects the optimal execution policy with over 85% accuracy, has modest monitoring overhead of less than 9%, and increases execution speed by up to 47% despite its runtime overhead.
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
Similar content being viewed by others
References
Hydrodynamics Challenge Problem, Lawrence Livermore National Laboratory. Tech. Rep. LLNL-TR-490254, Lawrence Livermore National Laboratory
Ansel, J., et al.: Opentuner: an extensible framework for program autotuning. In: Proceedings of the 23rd International Conference on Parallel Architectures and Compilation, pp. 303–316 (2014)
Balaprakash, P., Dongarra, J., Gamblin, T., Hall, M., Hollingsworth, J.K., Norris, B., Vuduc, R.: Autotuning in high-performance computing applications. Proc. IEEE 106(11), 2068–2083 (2018)
Baldeschwieler, J.E., Blumofe, R.D., Brewer, E.A.: Atlas: an infrastructure for global computing. In: Proceedings of the 7th Workshop on ACM SIGOPS European Workshop: Systems Support for Worldwide Applications, pp. 165–172 (1996)
Bari, M.A.S., Chaimov, N., Malik, A.M., Huck, K.A., Chapman, B., Malony, A.D., Sarood, O.: Arcs: adaptive runtime configuration selection for power-constrained openmp applications. In: 2016 IEEE International Conference on Cluster Computing, pp. 461–470. IEEE (2016)
Beckingsale, D.A., Gaudin, W.P., Herdman, J.A., Jarvis, S.A.: Resident block-structured adaptive mesh refinement on thousands of graphics processing units. In: 44th International Conference on Parallel Processing, pp. 61–70 (2015)
Beckingsale, D., Gaudin, W., Herdman, A., Jarvis, S.: Resident block-structured adaptive mesh refinement on thousands of graphics processing units. In: 2015 44th International Conference on Parallel Processing, pp. 61–70. IEEE (2015)
Beckingsale, D.A., Hornung, R.D., Scogland, T.R.W., Vargas, A.: Performance portable C++ programming with RAJA. In: Proceedings of the 24th Symposium on Principles and Practice of Parallel Programming, pp. 455–456 (2019)
Beckingsale, D.A., Pearce, O., Laguna, I., Gamblin, T.: Apollo: reusable models for fast, dynamic tuning of input-dependent code. In: 31st IEEE International Parallel & Distributed Processing Symposium, pp. 307–316 (2017)
Beckingsale, D.A.: Towards scalable adaptive mesh refinement on future parallel architectures. Ph.D. thesis, University of Warwick (2015)
Creech, T., Kotha, A., Barua, R.: Efficient multiprogramming for multicores with scaf. In: 2013 46th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO), pp. 334–345 (2013)
Creech, T., Barua, R.: Transparently space sharing a multicore among multiple processes. ACM Trans. Parallel Comput. 3(3) (Nov 2016). https://doi.org/10.1145/3001910
Edwards, H.C., Trott, C.R.: Kokkos: Enabling performance portability across manycore architectures. In: 2013 Extreme Scaling Workshop (xsw 2013), pp. 18–24. IEEE (2013)
Edwards, H.C., Trott, C.R., Sunderland, D.: Kokkos: enabling manycore performance portability through polymorphic memory access patterns. J. Parallel Distrib. Comput. 74(12), 3202–3216 (2014)
Frigo, M., Johnson, S.G.: FFTW an adaptive software architecture for the FFT. In: Proceedings of the 1998 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 1998) (Cat. No. 98CH36181). vol. 3, pp. 1381–1384. IEEE (1998)
Georgakoudis, G., Vandierendonck, H., Thoman, P., Supinski, B.R.D., Fahringer, T., Nikolopoulos, D.S.: Scalo: scalability-aware parallelism orchestration for multi-threaded workloads. ACM Trans. Archit. Code Optim. 14(4) (Dec 2017). https://doi.org/10.1145/3158643
Hartono, A., Norris, B., Sadayappan, P.: Annotation-based empirical performance tuning using orio. In: 2009 IEEE International Symposium on Parallel & Distributed Processing, pp. 1–11. IEEE (2009)
Hollingsworth, J., Tiwari, A.: End-to-end auto-tuning with active harmony. In: Performance Tuning of Scientific Applications, pp. 217–238, CRC Press, Boca Raton (2010)
Hornung, R.D., Keasler, J.A.: The RAJA Portability Layer: Overview and Status. Tech. Rep, Lawrence Livermore National Lab (2014)
Karlin, I., Keasler, J.A., Neely, R.: Lulesh 2.0 updates and changes. Tech. Rep. LLNL-TR-641973, Lawrence Livermore National Laboratory (August 2013)
Meng, K., Norris, B.: Mira: a framework for static performance analysis. In: 2017 IEEE International Conference on Cluster Computing (CLUSTER), pp. 103–113. IEEE (2017)
Menon, H., Bhatele, A., Gamblin, T.: Auto-tuning parameter choices in HPC applications using Bayesian optimization. In: 2020 IEEE International Parallel and Distributed Processing Symposium (IPDPS) (2020)
Pfander, D., Brunn, M., Pflüger, D.: AutoTuneTmp: auto-tuning in C++ with runtime template metaprogramming. In: 2018 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW), pp. 1123–1132. IEEE (2018)
Rajamanickam, S.: Kokkos kernels: Performance portable kernels for sparse/dense linear algebra graph and machine learning kernels. Tech. Rep., Sandia National Lab. (SNL-NM), Albuquerque, NM (United States) (2020)
Rasch, A., Gorlatch, S.: ATW a generic directive-based auto-tuning framework. Concurr. Comput. Prac. Exp. 31, e4423 (2019)
Rasch, A., Haidl, M., Gorlatch, S.: AFT: a generic auto-tuning framework. In: 2017 IEEE 19th International Conference on High Performance Computing and Communications; IEEE 15th International Conference on Smart City; IEEE 3rd International Conference on Data Science and Systems (HPCC/SmartCity/DSS), pp. 64–71. IEEE (2017)
Sreenivasan, V., Javali, R., Hall, M., Balaprakash, P., Scogland, T.R.W., de Supinski, B.R.: A framework for enabling openMP autotuning. In: Fan, X., de Supinski, B.R., Sinnen, O., Giacaman, N. (eds.) IWOMP 2019. LNCS, vol. 11718, pp. 50–60. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-28596-8_4
Vuduc, R., Demmel, J.W., Yelick, K.A.: OSKI: a library of automatically tuned sparse matrix kernels. J. Phys. Conf. Ser. 16, 521 (2005)
Whaley, R.C., Petitet, A., Dongarra, J.J.: Automated empirical optimizations of software and the atlas project. Parallel Comput. 27(1–2), 3–35 (2001)
Acknowledgment
This work was performed under the auspices of the U.S. Department of Energy by Lawrence Livermore National Laboratory under Contract DE-AC52-07NA27344 (LLNL-CONF-809192). Additional support was provided by a LLNL subcontract to the University of Oregon, No. B631536. This document was prepared as an account of work sponsored by an agency of the United States government. Neither the United States government nor Lawrence Livermore National Security, LLC, nor any of their employees makes any warranty, expressed or implied, or assumes any legal liability or responsibility for the accuracy, completeness, or usefulness of any information, apparatus, product, or process disclosed, or represents that its use would not infringe privately owned rights. Reference herein to any specific commercial product, process, or service by trade name, trademark, manufacturer, or otherwise does not necessarily constitute or imply its endorsement, recommendation, or favoring by the United States government or Lawrence Livermore National Security, LLC. The views and opinions of authors expressed herein do not necessarily state or reflect those of the United States government or Lawrence Livermore National Security, LLC, and shall not be used for advertising or product endorsement purposes.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 National Technology & Engineering Solutions of Sandia, LLC
About this paper
Cite this paper
Wood, C. et al. (2021). Artemis: Automatic Runtime Tuning of Parallel Execution Parameters Using Machine Learning. In: Chamberlain, B.L., Varbanescu, AL., Ltaief, H., Luszczek, P. (eds) High Performance Computing. ISC High Performance 2021. Lecture Notes in Computer Science(), vol 12728. Springer, Cham. https://doi.org/10.1007/978-3-030-78713-4_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-78713-4_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-78712-7
Online ISBN: 978-3-030-78713-4
eBook Packages: Computer ScienceComputer Science (R0)