{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T10:24:26Z","timestamp":1771064666098,"version":"3.50.1"},"reference-count":29,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2025,1,5]],"date-time":"2025-01-05T00:00:00Z","timestamp":1736035200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/pages\/standard-publication-reuse-rights"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,12]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Large-scale atomic\/molecular massively parallel simulator (LAMMPS) is a prevalent software package employed for molecular dynamics simulations, enabling the study of materials at the atomic and molecular scale. Its performance is paramount in numerous industrial applications, driving the need for ongoing enhancements in simulation speed and parallel efficiency. Previous works heavily rely on hardware accelerators, which lead to limited parallel and high costs. To address this, this work optimizes the message passing interface (MPI) and memory copy functions, while deploying LAMMPS on high-performance computing (HPC) systems. We propose a new adaptive broadcast algorithm to improve the parallelism efficiency of the interconnect topology. We also discuss how to realize the mutual hiding of computation and communication of the Packing algorithm in LAMMPS, and optimize the memory copy function and MPI operators to facilitate the execution of the program. The resulting components are integrated into the MPICH4 software and deployed on the MT-3000 HPC system. The experimental results show a significant performance improvement, with up to four orders of magnitude speedup on 1024, and more than 90% parallel efficiencies, demonstrating the effectiveness of our proposed optimization scheme. The adaptive broadcast algorithm and the portability of computation and communication hiding are also discussed. The adaptive broadcast algorithm is applied to SPEC MPI2007, and the average performance improvement is 23.91 and 27.29% on ARMv8 cluster and x86_64 cluster, respectively.<\/jats:p>","DOI":"10.1093\/comjnl\/bxae143","type":"journal-article","created":{"date-parts":[[2025,1,6]],"date-time":"2025-01-06T07:16:46Z","timestamp":1736147806000},"page":"706-716","source":"Crossref","is-referenced-by-count":7,"title":["Improving LAMMPS performance for molecular dynamic simulation on large-scale HPC systems"],"prefix":"10.1093","volume":"68","author":[{"given":"Du","family":"Qi","sequence":"first","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University , Lushan Gate, Lushan South Road, Yuelu District, Changsha 410082, Hunan ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Feng","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Electronic Engineering, Hunan University , Lushan Gate, Lushan South Road, Yuelu District, Changsha 410082, Hunan ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hui","family":"Huang","sequence":"additional","affiliation":[{"name":"Science and Technology Resource Sharing Service Center, Hunan Institute of Scientific and Technical Information , 59 Bayi Road, Furong District, Changsha 410001, Hunan ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinlin","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computing, The Hong Kong Polytechnic University , 11 Yuk Choi Road, Hung Hom, Kowloon, Hong Kong 00852 ,","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,1,5]]},"reference":[{"key":"2025062421184007400_ref1","doi-asserted-by":"publisher","first-page":"108171","DOI":"10.1016\/j.cpc.2021.108171","article-title":"LAMMPS-a flexible simulation tool for particle-based materials modeling at the atomic, meso, and continuum scales","volume":"271","author":"Thompson","year":"2022","journal-title":"Comput Phys Commun"},{"key":"2025062421184007400_ref2","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s42514-022-00109-9","article-title":"Status, challenges and trends of data-intensive supercomputing","volume":"4","author":"Wei","year":"2022","journal-title":"CCF Trans HPC"},{"key":"2025062421184007400_ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-29769-4","volume-title":"High Performance Computing in Clouds: Moving HPC Applications to a Scalable and Cost-Effective Environment","author":"Borin","year":"2023"},{"key":"2025062421184007400_ref4","doi-asserted-by":"publisher","first-page":"3237","DOI":"10.1021\/acs.jctc.1c00118","article-title":"Recent advances for improving the accuracy, transferability, and efficiency of reactive force fields","volume":"17","author":"Leven","year":"2021","journal-title":"J Chem Theory Comput"},{"key":"2025062421184007400_ref5","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1177\/10943420211008288","article-title":"GPU-accelerated molecular dynamics: state-of-art software performance and porting from Nvidia CUDA to AMD HIP","volume":"35","author":"Kondratyuk","year":"2021","journal-title":"Int J High Perform Comput Appl"},{"key":"2025062421184007400_ref6","doi-asserted-by":"publisher","first-page":"e7895","DOI":"10.1002\/cpe.7895","article-title":"Studying performance portability of LAMMPS across diverse GPU-based platforms","volume":"35","author":"Hagerty","year":"2023","journal-title":"Concurr Comput. Pract Exp"},{"key":"2025062421184007400_ref7","doi-asserted-by":"publisher","first-page":"074801","DOI":"10.1063\/5.0063880","article-title":"AENET\u2013LAMMPS and AENET\u2013TINKER: interfaces for accurate and efficient molecular dynamics simulations with machine learning potentials","volume":"155","author":"Chen","year":"2021","journal-title":"J Chem Phys"},{"key":"2025062421184007400_ref8","doi-asserted-by":"publisher","first-page":"5118","DOI":"10.21105\/joss.05118","article-title":"FitSNAP: atomistic machine learning with LAMMPS","volume":"8","author":"Rohskopf","year":"2023","journal-title":"J Open Source Softw"},{"key":"2025062421184007400_ref9","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1021\/acs.jctc.0c01003","article-title":"Relative resolution: a computationally efficient implementation in LAMMPS","volume":"17","author":"Chaimovich","year":"2021","journal-title":"J Chem Theory Comput"},{"key":"2025062421184007400_ref10","doi-asserted-by":"publisher","first-page":"9184","DOI":"10.1007\/s11227-021-04214-4","article-title":"Hybrid parallelization of molecular dynamics simulations to reduce load imbalance","volume":"78","author":"Morillo","year":"2022","journal-title":"J Supercomput"},{"key":"2025062421184007400_ref11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3491418.3530766","article-title":"Anvil-system architecture and experiences from deployment and early user operations","volume-title":"Practice and Experience in Advanced Research Computing","author":"Song","year":"2022"},{"key":"2025062421184007400_ref12","doi-asserted-by":"publisher","first-page":"110187","DOI":"10.1016\/j.jcp.2021.110187","article-title":"Parallel load-balancing for combustion with spray for large-scale simulation","volume":"434","author":"Thari","year":"2021","journal-title":"J Comput Phys"},{"key":"2025062421184007400_ref13","doi-asserted-by":"crossref","first-page":"374","DOI":"10.1109\/HPCMP-UGC.2006.56","article-title":"Optimization of LAMMPS","volume-title":"2006 HPCMP Users Group Conference (HPCMP-UGC\u201906)","author":"Fischer","year":"2006"},{"key":"2025062421184007400_ref14","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1109\/ICSEC.2014.6978132","article-title":"Simple optimizations for LAMMPS","volume-title":"2014 International Computer Science and Engineering Conference (ICSEC)","author":"Kaewtes","year":"2014"},{"key":"2025062421184007400_ref15","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/j.cpc.2015.05.004","article-title":"Optimizing legacy molecular dynamics software with directive-based offload","volume":"195","author":"Brown","year":"2015","journal-title":"Comput Phys Commun"},{"key":"2025062421184007400_ref16","doi-asserted-by":"crossref","first-page":"1274","DOI":"10.1109\/IPDPSW.2017.7","article-title":"Exploring the effect of compiler optimizations on the reliability of HPC applications","volume-title":"2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","author":"Ashraf","year":"2017"},{"key":"2025062421184007400_ref17","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1007\/s00366-009-0156-z","article-title":"Software components for parallel multiscale simulation: an example with LAMMPS","volume":"26","author":"FrantzDale","year":"2010","journal-title":"Eng Comput"},{"key":"2025062421184007400_ref18","doi-asserted-by":"publisher","first-page":"106862","DOI":"10.1016\/j.cpc.2019.106862","article-title":"Parallel point defect identification in molecular dynamics simulations without post-processing: a compute and dump style for LAMMPS","volume":"247","author":"Hammond","year":"2020","journal-title":"Comput Phys Commun"},{"key":"2025062421184007400_ref19","doi-asserted-by":"publisher","first-page":"1290","DOI":"10.1021\/acs.jcim.8b00939","article-title":"OCTP: a tool for on-the-fly calculation of transport properties of fluids with the order-n algorithm in LAMMPS","volume":"59","author":"Jamali","year":"2019","journal-title":"J Chem Inf Model"},{"key":"2025062421184007400_ref20","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1016\/j.cpc.2015.02.028","article-title":"Strong scaling of general-purpose molecular dynamics simulations on GPUs","volume":"192","author":"Glaser","year":"2015","journal-title":"Comput Phys Commun"},{"key":"2025062421184007400_ref21","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/j.cpc.2016.10.020","article-title":"GPU-accelerated Tersoff potentials for massively parallel molecular dynamics simulations","volume":"212","author":"Nguyen","year":"2017","journal-title":"Comput Phys Commun"},{"key":"2025062421184007400_ref22","first-page":"33","article-title":"Machine-aware atomic broadcast trees for multicores","volume-title":"12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16)","author":"Kaestle","year":"2016"},{"key":"2025062421184007400_ref23","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1007\/s42514-022-00095-y","article-title":"MT-3000: a heterogeneous multi-zone processor for HPC","volume":"4","author":"Lu","year":"2022","journal-title":"CCF Trans HPC"},{"key":"2025062421184007400_ref24","first-page":"2096","article-title":"User\u2019s guide for mpich, a portable implementation of mpi","author":"Gropp","year":"2017"},{"key":"2025062421184007400_ref25","volume-title":"An Introduction to GCC","author":"Gough","year":"2004"},{"key":"2025062421184007400_ref26","doi-asserted-by":"publisher","first-page":"507","DOI":"10.1016\/S1097-2765(03)00047-9","article-title":"EGF activates its receptor by removing interactions that autoinhibit ectodomain dimerization","volume":"11","author":"Ferguson","year":"2003","journal-title":"Mol Cell"},{"key":"2025062421184007400_ref27","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1177\/1094342006064482","article-title":"The TAU parallel performance system","volume":"20","author":"Shende","year":"2006","journal-title":"Int J High Perform Comput Appl"},{"key":"2025062421184007400_ref28","volume-title":"Enhancing OSU micro-benchmarks to be an all-in-one solution for MPI benchmarking.","author":"Paniraja Guptha","year":"2023"},{"key":"2025062421184007400_ref29","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1002\/cpe.1535","article-title":"SPEC MPI2007\u2014an application benchmark suite for parallel systems using MPI","volume":"22","author":"M\u00fcller","year":"2010","journal-title":"Concurr Comput Pract Exp"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/68\/6\/706\/61330950\/bxae143.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/comjnl\/article-pdf\/68\/6\/706\/61330950\/bxae143.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T01:18:49Z","timestamp":1750814329000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/68\/6\/706\/7942797"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,5]]},"references-count":29,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,1,5]]},"published-print":{"date-parts":[[2025,6,12]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxae143","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"value":"0010-4620","type":"print"},{"value":"1460-2067","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2025,6]]},"published":{"date-parts":[[2025,1,5]]}}}