AI Chat Paper
Note: Please note that the following content is generated by AMiner AI. SciOpen does not take any responsibility related to this content.
{{lang === 'zh_CN' ? '文章概述' : 'Summary'}}
{{lang === 'en_US' ? '中' : 'Eng'}}
Chat more with AI
Powered by AMiner. Clicking this button will take you away from SciOpen.
Home Journal of Computer Science and Technology Article
Article Link
Cite
EndNote(RIS) BibTeX
Collect
Submit Manuscript
Show Outline
Outline
Show full outline
Hide outline
Outline
Show full outline
Hide outline
Regular Paper

Towards Efficient Short-Range Pair Interaction on Sunway Many-Core Architecture

School of Computer Science and Technology, University of Science and Technology of China, Hefei 230026, China
National Research Center of Parallel Computer Engineering and Technology, Beijing 100080, China
Show Author Information

Abstract

The short-range pair interaction consumes most of the CPU time in molecular dynamics (MD) simulations. The inherent computation sparsity makes it challenging to achieve high-performance kernel on the emerging many-core architecture. In this paper, we present a highly efficient short-range force kernel on the Sunway, a novel many-core architecture with many unique features. The parallel efficiency of this algorithm on the Sunway many-core processor is strongly limited by the poor data locality and write conflicts. To enhance the data locality, we adopt a super cluster based neighbor list with an appropriate granularity that fits in the local memory of computing cores. In the absence of a low overhead locking mechanism, using data-privatization force array is a more feasible method to avoid write conflicts, but results in the large overhead of data reduction. We adopt a dual-slice partitioning scheme for both hardware resources and computing tasks, which utilizes the on-chip data communication to reduce data reduction overhead and provide load balancing. Moreover, we exploit the single instruction multiple data (SIMD) parallelism and perform instruction reordering of the force kernel on this many-core processor. The experimental results show that the optimized force kernel obtains a performance speedup of 226x compared with the reference implementation and achieves 20% of peak flop rate on the Sunway many-core processor.

Keywords

molecular dynamicssunway many-corepair interactionparallel algorithm

Electronic Supplementary Material

Download File(s)
jcst-36-1-123-Highlights.pdf (758.2 KB)

References

[1]

Hollingsworth S A, Dror R O. Molecular dynamics simulation for all. Neuron, 2018, 99(6): 1129-1143. DOI: 10.1016/j.neuron.2018.08.011.
Crossref Google Scholar
[2]

Kumar S, Huang C, Zheng G et al. Scalable molecular dynamics with NAMD on the IBM Blue Gene/L system. IBM Journal of Research and Development, 2008, 52(1/2): 177-188. DOI: 10.1147/rd.521.0177.
Crossref Google Scholar
[3]
Shaw D E, Grossman J P, Bank J A et al. Anton 2: Raising the bar for performance and programmability in a special-purpose molecular dynamics supercomputer. In Proc. the International Conference for High Performance Computing, Networking, Storage and Analysis, November 2014, pp.41-53. DOI: 10.1109/SC.2014.9.
Crossref
[4]

Shaw D E, Deneroff M M, Dror R O et al. Anton, a special-purpose machine for molecular dynamics simulation. Commun. ACM, 2008, 51(7): 91-97. DOI: 10.1145/1364782.1364802.
Crossref Google Scholar
[5]

Götz A W, Williamson M J, Xu D et al. Routine microsecond molecular dynamics simulations with AMBER on GPUs. 1. generalized born. Journal of Chemical Theory and Computation, 2012, 8(5): 1542-1555. DOI: 10.1021/ct200909j.
Crossref Google Scholar
[6]
Pennycook S J, Hughes C J, Smelyanskiy M, Jarvis S A. Exploring SIMD for molecular dynamics, using Intel® Xeon® and Intel® Xeon Phi coprocessors. In Proc. the 27th IEEE International Symposium on Parallel and Distributed Processing, May 2013, pp.1085-1097. DOI: 10.1109/IPDPS.2013.44.
Crossref
[7]
Wang H Q, Peng S L, Zhu X Q et al. A method to accelerate GROMACS in offload mode on Tianhe-2 supercomputer. In Proc. the 15th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing, May 2015, pp.781-784. DOI: 10.1109/CCGrid.2015.65.
Crossref
[8]

Hu C J, Wang X M, Li J J et al. Kernel optimization for short-range molecular dynamics. Computer Physics Communications, 2017, 211: 31-40. DOI: 10.1016/j.cpc.2016.07.010.
Crossref Google Scholar
[9]

Law T R, Hancox J, Wright S A, Jarvis S A. An algorithm for computing short-range forces in molecular dynamics simulations with non-uniform particle densities. Journal of Parallel and Distributed Computing, 2019, 130: 1-11. DOI: 10.1016/j.jpdc.2019.03.008.
Crossref Google Scholar
[10]

Peng S L, Cui Y B, Yang S Y et al. A CPU/MIC collaborated parallel framework for GROMACS on Tianhe-2 supercomputer. IEEE/ACM Trans. Comput. Biology Bioinform., 2019, 16(2): 425-433. DOI: 10.1109/TCBB.2017.2713362.
Crossref Google Scholar
[11]

Anderson J A, Lorenz C D, Travesset A. General purpose molecular dynamics simulations fully implemented on graphics processing units. Journal of Computational Physics, 2008, 227(10): 5342-5359. DOI: 10.1016/j.jcp.2008.01.047.
Crossref Google Scholar
[12]

Friedrichs M S, Eastman P, Vaidyanathan V et al. Accelerating molecular dynamic simulation on graphics processing units. Journal of Computational Chemistry, 2009, 30(6): 864-872. DOI: 10.1002/jcc.21209.
Crossref Google Scholar
[13]

Minkin A S, Knizhnik A A, Potapkin B V. GPU implementations of some many-body potentials for molecular dynamics simulations. Advances in Engineering Software, 2017, 111: 43-51. DOI: 10.1016/j.advengsoft.2016.05.013.
Crossref Google Scholar
[14]

Spellings M, Marson R L, Anderson J A, Glotzer S C. GPU accelerated Discrete Element Method (DEM) molecular dynamics for conservative, faceted particle simulations. Journal of Computational Physics, 2017, 334: 460-467. DOI: 10.1016/j.jcp.2017.01.014.
Crossref Google Scholar
[15]

Fu H H, Liao J F, Yang J Z et al. The Sunway TaihuLight supercomputer: System and applications. Science China Information Sciences, 2016, 59(7): Article No. 072001. DOI: 10.1007/s11432-016-5588-7.
Crossref Google Scholar
[16]
Dong W Q, Kang L T, Quan Z et al. Implementing molecular dynamics simulation on Sunway TaihuLight system. In Proc. the 18th IEEE International Conference on High Performance Computing and Communications, December 2016, pp.443-450. DOI: 10.1109/HPCC-SmartCity-DSS.2016.0070.
Crossref
[17]

Dong W Q, Li K L, Kang L T, Quan Z, Li K Q. Implementing molecular dynamics simulation on the Sunway TaihuLight system with heterogeneous many-core processors. Concurrency and Computation: Practice and Experience, 2018, 30(16): Article No. e4468. DOI: 10.1002/cpe.4468.
Crossref Google Scholar
[18]
Yu Y, An H, Chen J S et al. Pipelining computation and optimization strategies for scaling GROMACS on the Sunway many-core processor. In Proc. the 17th International Conference on Algorithms and Architectures for Parallel Processing, August 2017, pp.18-32. DOI: 10.1007/978-3-319-65482-9_2.
Crossref
[19]
Duan X H, Gao P, Zhang T J et al. Redesigning LAMMPS for peta-scale and hundred-billion-atom simulation on Sunway TaihuLight. In Proc. the International Conference for High Performance Computing, Networking, Storage, and Analysis, November 2018, Article No. 12. DOI: 10.1109/SC.2018.00015.
Crossref
[20]

Páll S, Hess B. A flexible algorithm for calculating pair interactions on SIMD architectures. Computer Physics Communications, 2013, 184(12): 2641-2650. DOI: 10.1016/j.cpc.2013.06.003.
Crossref Google Scholar
[21]

Abraham M J, Murtola T, Schulz R et al. GROMACS: High performance molecular simulations through multilevel parallelism from laptops to supercomputers. SoftwareX, 2015, 1/2: 19-25. DOI: 10.1016/j.softx.2015.06.001.
Crossref Google Scholar
[22]

Phillips J C, Braun R, Wang W, Gumbart J et al. Scalable molecular dynamics with NAMD. Journal of Computational Chemistry, 2005, 26: 1781-1802. 10.1002/jcc.20289.
Crossref Google Scholar
[23]

Plimpton S. Fast parallel algorithms for short-range molecular dynamics. Journal of Computational Physics, 1995, 117: 1-19. DOI: 10.1006/jcph.1995.1039.
Crossref Google Scholar
[24]

Yao Z H, Wang J S, Liu G R, Cheng M. Improved neighbor list algorithm in molecular simulations using cell decomposition and data sorting method. Computer Physics Communications, 2004, 161(1/2): 27-35. DOI: 10.1016/j.cpc.2004.04.004.
Crossref Google Scholar
[25]

Nguyen T D. GPU-accelerated Tersoff potentials for massively parallel Molecular Dynamics simulations. Computer Physics Communications, 2017, 212: 113-122. DOI: 10.1016/j.cpc.2016.10.020.
Crossref Google Scholar
[26]
Jia Z, Maggioni M, Staiger B, Scarpazza D P. Dissecting the NVIDIA volta GPU architecture via microbenchmarking. arXiv: 1804.06826, 2018. https://arxiv.org/abs/1804.06826, April 2020.
[27]

Kunaseth M, Richards D F, Glosli J N et al. Analysis of scalable data-privatization threading algorithms for hybrid MPI/OpenMP parallelization of molecular dynamics. The Journal of Supercomputing, 2013, 66(1): 406-430. DOI: 10.1007/s11227-013-0915-x.
Crossref Google Scholar
[28]

Lin J, Xu Z G, Cai L J, Nukada A, Satoshi M. Evaluating the SW26010 many-core processor with a micro-benchmark suite for performance optimizations. Parallel Computing, 2018, 77: 128-143. DOI: 10.1016/j.parco.2018.06.001.
Crossref Google Scholar
Journal of Computer Science and Technology
Volume 36 Issue 1,
January 2021
Pages 123-139
DOI: 10.1007/s11390-020-9826-z
Cite this article:
Chen J-S, An H, Han W-T, et al. Towards Efficient Short-Range Pair Interaction on Sunway Many-Core Architecture. Journal of Computer Science and Technology, 2021, 36(1): 123-139. https://doi.org/10.1007/s11390-020-9826-z

513

Views

2

Crossref

2

Web of Science

3

Scopus

0

CSCD

Altmetrics
Received: 08 July 2020
Accepted: 08 July 2020
Published: 05 January 2021
© Institute of Computing Technology, Chinese Academy of Sciences 2021
Return