Memory Access Optimization of Molecular Dynamics Simulation Software Crystal-MD on Sunway TaihuLight

Jianjiang Li; Jie Lin; Panpan Du; Kai Zhang; Jie Wu

doi:10.26599/TST.2019.9010074

Tsinghua Science and Technology 2021, 26(3): 296-308 https://doi.org/10.26599/TST.2019.9010074

Open Access | Issue | Published: 12 October 2020

Memory Access Optimization of Molecular Dynamics Simulation Software Crystal-MD on Sunway TaihuLight

Show Author's Information Hide Author's Information Jianjiang Li, Jie Lin, Panpan Du(

), Kai Zhang, Jie Wu

Department of Computer Science and Technology, University of Science and Technology Beijing, Beijing 100083, China.

Dawning Information Industry Co., Ltd., Tianjin 300384, China.

Beijing Sogou Technology Development Co., Ltd., Beijing 100084, China.

Department of Computer and Information Sciences, Temple University, Philadelphia, PA 19122, USA.

Keywords:

molecular dynamics simulation, Crystal-MD, Sunway TaihuLight, memory access optimization

Cite this article:

Li J, Lin J, Du P, et al. Memory Access Optimization of Molecular Dynamics Simulation Software Crystal-MD on Sunway TaihuLight. Tsinghua Science and Technology, 2021, 26(3): 296-308. https://doi.org/10.26599/TST.2019.9010074

Download citation

EndNote(RIS)

BibTeX

893

Views

Downloads

Citations

Crossref

N/A

WoS

Scopus

CSCD

Abstract Full text About this article

Abstract

The radiation damage effect of key structural materials is one of the main research subjects of the numerical reactor. From the perspective of experimental safety and feasibility, Molecular Dynamics (MD) in the materials field is an ideal method for simulating the radiation damage of structural materials. The Crystal-MD represents a massive parallel MD simulation software based on the key material characteristics of reactors. Compared with the Large-scale Atomic/Molecurlar Massively Parallel Simulator (LAMMPS) and ITAP Molecular Dynamics (IMD) software, the Crystal-MD reduces the memory required for software operation to a certain extent, but it is very time-consuming. Moreover, the calculation results of the Crystal-MD have large deviations, and there are also some problems, such as memory limitation and frequent communication during its migration and optimization. In this paper, in order to solve the above problems, the memory access mode of the Crystal-MD software is studied. Based on the memory access mode, a memory access optimization strategy is proposed for a unique architecture of China’s supercomputer Sunway TaihuLight. The proposed optimization strategy is verified by the experiments, and experimental results show that the running speed of the Crystal-MD is increased significantly by using the proposed optimization strategy.

Full text

Abstract

Full text

Outline

About this article

Memory Access Optimization of Molecular Dynamics Simulation Software Crystal-MD on Sunway TaihuLight

Show Author's information Hide Author's Information Jianjiang Li, Jie Lin, Panpan Du(

), Kai Zhang, Jie Wu

Department of Computer Science and Technology, University of Science and Technology Beijing, Beijing 100083, China.

Dawning Information Industry Co., Ltd., Tianjin 300384, China.

Beijing Sogou Technology Development Co., Ltd., Beijing 100084, China.

Department of Computer and Information Sciences, Temple University, Philadelphia, PA 19122, USA.

Abstract

Keywords: molecular dynamics simulation, Crystal-MD, Sunway TaihuLight, memory access optimization

References(25)

[1]

B. J. Alder and T. E. Wainwright, Studies in molecular dynamics. I. General method, J. Chem. Phys., vol. 31, no. 2, pp. 459-466, 1959.

DOI Google Scholar

[2]

S. Plimpton, LAMMPS molecular dynamics simulator, http://lammps.sandia.gov/, 2004.

[3]

J. Roth, F. Gähler, and H. R. Trebin, A molecular dynamics run with 5 180 116 000 particles, Int. J. Mod. Phys. C, vol. 11, no. 2, pp. 317-322, 2000.

DOI Google Scholar

[4]

H. Bai, C. J. Hu, X. F. He, B. Y. Zhang, and J. Wang, Crystal MD: Molecular dynamic simulation software for metal with BCC structure, in Proc. 1st National Conf. Big Data Technology and Applications, Harbin, China, 2015, pp. 247-258.

DOI

[5]

C. J. Hu, H. Bai, X. F. He, B. Y. Zhang, N. M. Nie, X. M. Wang, and Y. W. Ren, Crystal MD: The massively parallel molecular dynamics software for metal with bcc structure, Comput. Phys. Commun., vol. 211, pp. 73-78, 2017.

DOI Google Scholar

[6]

D. X. Chen and X. Liu, Parallel Programming Design and Optimization of Sunway Taihulight, (in Chinese). Wuxi, China: National Super-computing Wuxi Center, 2017.

[7]

W. Q. Dong, L. T. Kang, Z. Quan, K. L. Li, K. Q. Li, Z. Y. Hao, and X. H. Xie, Implementing molecular dynamics simulation on Sunway Taihulight system, in Proc. 2016 IEEE 18th Int. Conf. on High Performance Computing and Communications; IEEE 14th Int. Conf. Smart City; IEEE 2nd Int. Conf. Data Science and Systems, Sydney, Australia, 2016, pp. 443-450.

[8]

C. Yang, W. Xue, H. H. Fu, H. T. You, X. L. Wang, Y. L. Ao, F. F. Liu, L. Gan, P. Xu, L. N. Wang, et al., 10M-core scalable fully-implicit solver for nonhydrostatic atmospheric dynamics, in Proc. Int. Conf. for High Performance Computing, Networking, Storage and Analysis, Salt Lake City, UT, USA, 2016, p. 6.

DOI

[9]

W. J. Hong, K. L. Li, Z. Quan, W. D. Yang, K. Q. Li, Z. Y. Hao, and X. T. Xie, PETSc’s heterogeneous parallel algorithm design and performance optimization on the Sunway Taihulight system, (in Chinese), Chin. J. Comput., vol. 40, no. 9, pp. 2057-2069, 2017.

Google Scholar

[10]

L. J. Jiang, C. Yang, Y. L. Ao, W. W. Yin, W. J. Ma, Q. Sun, F. F. Liu, R. F. Lin, and P. Zhang, Towards highly efficient DGEMM on the emerging SW26010 many-core processor, in 2017 46th Int. Conf. Parallel Processing, Bristol, UK, 2017, pp. 422-431.

DOI

[11]

Y. L. Ao, C. Yang, F. F. Liu, W. W. Yin, L. J. Jiang, and Q. Sun, Performance optimization of the HPCG benchmark on the Sunway Taihulight supercomputer, ACM Trans. Arch. Code Optim., vol. 15, no. 1, p. 11, 2018.

DOI Google Scholar

[12]

Y. Yu, H. An, J. S. Chen, W. H. Liang, Q. Q. Xu, and Y. Chen, Pipelining computation and optimization strategies for scaling GROMACS on the Sunway many-core processor, in Proc. 17th Int. Conf. Algorithms and Architectures for Parallel Processing, Helsinki, Finland, 2017, pp. 18-32.

DOI

[13]

S. M. Chen, L. Peng, S. Irving, Z. Zhao, W. H. Zhang, and A. Srivastava, qSwitch: Dynamical off-chip bandwidth allocation between local and remote accesses, IEEE Trans. Comput. Aided Des. Integr. Circuits Syst., vol. 37, no. 1, pp. 75-87, 2018.

DOI Google Scholar

[14]

W. H. Zhang, X. F. Ji, B. Song, S. Q. Yu, H. B. Chen, T. Li, P. C. Yew, and W. Y. Zhao. VarCatcher: A framework for tackling performance variability of parallel workloads on multi-core, IEEE Trans. Parallel Distrib. Syst., vol. 28, no. 4, pp. 1215-1228, 2017.

DOI Google Scholar

[15]

Y. P. Lu, X. Wang, W. H. Zhang, H. B. Chen, L. Peng, and W. Y. Zhao, Performance analysis of multimedia retrieval workloads running on multicores, IEEE Trans. Parallel Distrib. Syst., vol. 27, no. 1, pp. 3323-3337, 2016.

DOI Google Scholar

[16]

J. N. Glosli, D. F. Richards, K. J. Caspersen, R. E. Rudd, J. A. Gunnels, and F. H. Streitz, Extending stability beyond CPU millennium: A micron-scale atomistic simulation of Kelvin-Helmholtz instability, in SC’07: Proc. 2007 ACM/IEEE Conf. Supercomputing, Reno, NV, USA, 2007, pp. 1-11.

DOI

[17]

S. Plimpton, Fast parallel algorithms for short-range molecular dynamics, J. Comput. Phys., vol. 117, no. 1, pp. 1-19, 1995.

DOI Google Scholar

[18]

D. Fincham, Parallel computers and molecular simulation, Mol. Simul., vol. 1, nos. 1&2, pp. 1-45, 1987.

DOI Google Scholar

[19]

E. Fermi, P. Pasta, S. Ulam, and M. Tsingou, Studies of the NonLinear Problems. I. Los Alamos Report LA-1940. Los Alamos, NM, USA: Los Alamos Scientific Laboratoryz, 1955.

DOI

[20]

L. Verlet, Computer “experiments” on classical fluids. I. Thermodynamical properties of lennard-jones molecules, Phys. Rev, vol. 159, pp. 98-103, 1967.

DOI Google Scholar

[21]

M. S. Daw and M. I. Baskes, Semiempirical, quantum mechanical calculation of hydrogen embrittlement in metals, Phys. Rev. Lett., vol. 50, no. 17, pp. 1285-1288, 1983.

DOI Google Scholar

[22]

M. S. Daw and M. I. Baskes, Embedded-atom method: Derivation and application to impurities, surfaces, and other defects in metals, Phys. Rev. B, vol. 29, no. 12, pp. 6443-6453, 1984.

DOI Google Scholar

[23]

J. Stadler, R. Mikulla, and H. R. Trebin, IMD: A software package for molecular dynamics studies on parallel computers, Int. J. Mod. Phys. C, vol. 8, no. 5, pp. 1131-1140, 1997.

DOI Google Scholar

[24]

Large systems 1: Molecular dynamics, https://www.ls1-mardyn.de/, 2019.

[25]

Comd, http://find.nlc.cn/search/showDocDetails?docId=6785449989126485706&dataSource=crfd&query=%20Comd, 2008.

About this article

Publication history

Acknowledgements

Rights and permissions

Publication history

Received: 08 October 2019

Accepted: 05 December 2019

Published: 12 October 2020

Issue date: June 2021

Copyright

Acknowledgements

This work was supported by the National Key R&D Program of China (No. 2017YFB0202003).

Rights and permissions

The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).