Эффективность процессоров архитектуры ARM для расчетов классической молекулярной динамики
Авторы
-
В.П. Никольский
-
В.В. Стегайлов
Ключевые слова:
архитектура ARM
операции с числами с плавающей точкой
эффективность
молекулярная динамика
Advanced RISC Machine
Аннотация
Суперкомпьютерные вычисления экзафлопсной эры будут неизбежно ограничены энергоэффективностью. Сегодня в качестве возможных кандидатов для этих целей рассматриваются различные микропроцессорные архитектуры. Недавно микропроцессоры с архитектурой ARM в своем развитии достигли момента, когда уже можно серьезно обсуждать их применение для высокопроизводительных вычислений. В настоящей статье представлен анализ эффективности последних версий ARM-микропроцессоров и их производительности для задач классической молекулярной динамики.
Раздел
Раздел 1. Вычислительные методы и приложения
Библиографические ссылки
- V. Sadovnichy, A. Tikhonravov, Vl. Voevodin, and V. Opanasenko, “’Lomonosov’: Supercomputing at Moscow State University,” in Contemporary High Performance Computing: From Petascale toward Exascale (CRC Press, Boca Raton, 2013), pp. 283-307.
- V. V. Stegailov and G. E. Norman, “Challenges to the Supercomputer Development in Russia: a HPC User Perspective,” Program. Sistemy: Teoriya Prilozh. 5 (1), 111-152 (2014).
- J. Fitzpatrick, “An Interview with Steve Furber,” Commun. ACM 54 (5), 34-39 (2011).
- G. Mitra, B. Johnston, A. P. Rendell, et al., “Use of SIMD Vector Operations to Accelerate Application Code Performance on Low-Powered ARM and Intel Platforms,” in Proc. IEEE 27th Int. Symposium on Parallel and Distributed Processing Workshops and PhD Forum, Cambridge, MA, USA, May 20-24, 2013 (IEEE Press, Washington, DC, 2013), pp. 1107-1116.
- A. V. Yanilkin, P. A. Zhilyaev, A. Yu. Kuxin, et al, “Application of Supercomputers for the Molecular Dynamics Simulation of Processes in Condensed Matter,” Vychisl. Metody Programm. 11, 111-116 (2010).
- P. A. Zhilyaev and V. V. Stegailov, “Ab Initio Molecular Dynamics: Application Perspectives of Multi-CPU and Hybrid Supercomputers,” Vychisl. Metody Programm. 13, 37-45 (2012).
- A. Y. Kuksin, A. V. Lankin, I. V. Morozov, et al., “Predictive Modeling and Simulation of Properties and Multi-Scale Processes in Materials Science. Tasks for Exaflops-Era Supercomputers,” Program. Sistemy: Teoriya Prilozh. 5 (1), 191-244 (2014).
- G. E. Norman and V. V. Stegailov, “Stochastic Theory of the Classical Molecular Dynamics Method,” Mat. Model. 24 (6), 3-44 (2012) [Math. Models Comput. Simul. 5 (4), 305-333 (2013)].
- W. Eckhardt, A. Heinecke, R. Bader, et al., “591 TFLOPS Multi-Trillion Particles Simulation on SuperMUC,” in Lecture Notes in Computer Science (Springer, Heidelberg, 2013), Vol. 7905, pp. 1-12.
- S. Piana, J. L. Klepeis, and D. E. Shaw, “Assessing the Accuracy of Physical Models Used in Protein-Folding Simulations: Quantitative Evidence from Long Molecular Dynamics Simulations,” Curr. Opin. Struct. Biol. 24, 98-105 (2014).
- V. O. Podryga, S. V. Polyakov, and D. V. Puzyrkov, “Supercomputer Molecular Modeling of Thermodynamic Equilibrium in Gas-Metal Microsystems,” Vychisl. Metody Programm. 16, 123-138 (2015).
- H. J. Curnow and B. A. Wichmann, “A Synthetic Benchmark,” Comput. J. 19 (1), 43-49 (1976).
- D. Kozlov-Kononov, “Processor Core Cortex: Combination of High Performance and Low Power Consumption,” Elektronika, No. 8, 16-24 (2010).
- R. Garg, “Exploring the Floating Point Performance of Modern ARM Processors,”
http://www.anandtech.com/show/6971/exploring-the-floating-point-performance-of-modern-arm-processors . Cited October 30, 2015.
- R. Garg, “RgbenchMM - Android Apps on Google Play,”
https://play.google.com/store/apps/details?id=org.codedivine.rgbench{&}hl=en . Cited October 30, 2015.
- R. Garg, “Prelim Analysis of RgbenchMM,”
http://codedivine.org/2012/09/25/prelim-analysis-rgbenchmm . Cited October 30, 2015.
- Swedroid - Nordens Största Android-Community.
http://www.swedroid.se . Cited October 30, 2015.
- V. A. Mikheev, S. P. Izgalin, A. I. Slutskin, et al., “Preliminary Results of Evaluation Testing of the Angara High-Speed Communication Network,”
http://2014.nscf.ru/TesisAll/1_Apparatura/05_165_SemenovAS.pdf . Cited October 30, 2015.
- V. V. Stegailov, N. D. Orehkov, and G. S. Smirnov, “HPC Hardware Efficiency for Quantum and Classical Molecular Dynamics,” in Lecture Notes in Computer Science (Springer, Heidelberg, 2013), Vol. 9251, pp. 469-473.
- G. S. Smirnov and V. V. Stegailov, “Efficiency of Classical Molecular Dynamics on HPC Hardware,” Mat. Model. 28 (2016) (in press).
- One-Processor Timings on the Lennard-Jones Liquid Benchmark.
http://lammps.sandia.gov/bench/lj_one.html . Cited October 30, 2015.
- D. Abdurachmanov, K. Arya, J. Bendavid, et al., “Explorations of the Viability of ARM and Xeon Phi for Physics Processing,” J. Phys.: Conf. Ser. 513 (2014).
doi 10.1088/1742-6596/513/5/052008
- Supermicro - Ivy Bridge Based DCO SuperServer Power {&} Cost Savings.
http://www.supermicro.com/white_paper/white_paper_Ivy-Bridge-Power.pdf . Cited October 30, 2015.
- Intel Xeon E5-2600 V3 Review: Haswell-EP Redefines Fast.
http://www.tomshardware.com/reviews/intel-xeon-e5-2600-v3-haswell-ep, 3932-9.html . Cited October 30, 2015.