The Impact of Voltage-Frequency Scaling for the Matrix-Vector Product on the IBM POWER8
The physical limitations of CMOS miniaturization have promoted understanding the interplay between performance and energy into a primary challenge. In this paper we contribute towards this goal by assessing the effect of voltage and frequency scaling (VFS) on the energy consumption of the dense and sparse matrix-vector products. The optimization of the sparse kernel, from the perspective of both performance and energy efficiency, is especially difficult due to its irregular memory access pattern, but the potential benefits are remarkable because of its varied applications.
Our experiments with a small synthetic training set show that it is possible to build a general classification of sparse matrices that governs the optimal VFS level from the point of view of energy efficiency. More importantly, this characterization can be leveraged to tune VFS for a major portion of the University of Florida Matrix Collection, when executed on the IBM Power8, yielding significant gains with respect to a (power-hungry) configuration that simply favours performance.
KeywordsEnergy efficiency Voltage-frequency scaling Performance prediction Performance metrics Matrix-vector product IBM POWER8
This work was supported by project Exa2Green (under grant agreement n\(^\circ \)318793) of the Future and Emerging Technologies (FET) programme within the ICT theme of the Seventh Framework Programme for Research (FP7/2007–2013) of the European Commission. The researchers from Universidad Jaume I were supported by project TIN2014-53495-R of the MINECO and FEDER, and the FPU program of MECD.
- 1.The University of Florida Sparse Matrix Collection, January 2016. http://www.cise.ufl.edu/research/sparse/matrices/
- 3.Asanovic, K., et al.: The landscape of parallel computing research: a view from berkeley. Technical report UCB/EECS-2006-183, EECS Department, University of California, Berkeley, December 2006Google Scholar
- 4.Bergner, P., et al.: Performance Optimization and Tuning Techniques for IBM Power Systems Processors Including IBM POWER8. IBM (2015). IBM Reed BooksGoogle Scholar
- 6.Byun, J.-H., Lin, R., Yelick, K.A., Demmel, J.: Autotuning sparse matrix-vector multiplication for multicore. Technical report UCB/EECS-2012-215, EECS Dept., Univ. California, Berkeley (2012)Google Scholar
- 7.Choi, J.W., Singh, A., Vuduc, R.W.: Model-driven autotuning of sparse matrix-vector multiply on GPUs. In Proceedings of the 15th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, PPopp 2010, pp. 115–126 (2010)Google Scholar
- 8.Dongarra, J., Heroux, M.A.: Toward a new metric for ranking high performance computing systems. Sandia report SAND2013-4744, Sandia National Laboratories, June 2013Google Scholar
- 9.Duranton, M., De Bosschere, K., Cohen, A., Maebe, J., Munk, H.: HiPEAC vision 2015 (2015). https://www.hipeac.org/publications/vision/
- 11.Hager, G., Treibig, J., Habich, J., Wellein, G.: Exploring performance and power properties of modern multi-core chips via simple machine models. Concurr. Comput. Pract. Exper. 28(2), 189–210 (2016)Google Scholar
- 13.Karakasis, V., Goumas, G., Koziris, N.: Exploring the performance-energy tradeoffs in sparse matrix-vector multiplication. In: Workshop on Emerging Supercomputing Technologies (WEST) - ICS 2011 (2011)Google Scholar
- 15.Lefurgy, C., Wang, X., Ware, M.: Server-level power control. In: Proceedings of the 4th IEEE Conference on Autonomic Computing (ICAC 2007), Jacksonville, Florida, USA, 11–15 June, 2007Google Scholar
- 16.Liu, X., Smelyanskiy, M., Chow, E., Dubey, P.: Efficient sparse matrix-vector multiplication on x86-based many-core processors. In: Proceedings of the 27th International Conference on Supercomputing, Eugene, Oregon, USA, pp. 273–282, June 2013Google Scholar
- 17.Lucas, R.: Top ten Exascale research challenges (2014). http://science.energy.gov/~/media/ascr/ascac/pdf/meetings/20140210/Top10reportFEB14.pdf
- 18.Malkowski, K.: Co-adapting Scientific Applications and Architectures Toward Energy-efficient High Performance Computing. Ph.D. thesis, University Park, PA, USA (2008) AI3346339Google Scholar
- 19.Malossi, A.C.I., Ineichen, Y., Bekas, C., Curioni, A., Quintana-Ortí, E.S.: Performance and energy-aware characterization of the sparse matrix-vector multiplication on multithreaded architectures. In Proceedings of 43rd International Conference on Parallel Processing (ICCP), Minneapolis (MN), USA, pp. 139–148 (2014)Google Scholar
- 22.Vuduc, R.: Automatic performance tuning of sparse matrix kernels. Ph.D. dissertation, Univ. California, Berkeley, January 2004Google Scholar