{"id":"https://openalex.org/W4414909305","doi":"https://doi.org/10.1109/cluster59342.2025.11186476","title":"Scaling Deep Learning Molecular Dynamics to 500M Atoms on 4096-Node ARMv8 Clusters","display_name":"Scaling Deep Learning Molecular Dynamics to 500M Atoms on 4096-Node ARMv8 Clusters","publication_year":2025,"publication_date":"2025-09-02","ids":{"openalex":"https://openalex.org/W4414909305","doi":"https://doi.org/10.1109/cluster59342.2025.11186476"},"language":"en","primary_location":{"id":"doi:10.1109/cluster59342.2025.11186476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster59342.2025.11186476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Cluster Computing (CLUSTER)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5043677244","display_name":"Qizhen Du","orcid":"https://orcid.org/0000-0003-3913-763X"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Du","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University,Changsha,P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University,Changsha,P.R. China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087605084","display_name":"Feng Wang","orcid":"https://orcid.org/0000-0001-5827-2971"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Feng Wang","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University,Changsha,P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University,Changsha,P.R. China","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054335730","display_name":"Chengkun Wu","orcid":"https://orcid.org/0000-0002-9688-5311"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengkun Wu","raw_affiliation_strings":["College of Computer Science and Technology, National University of Defense Technology,Changsha,P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, National University of Defense Technology,Changsha,P.R. China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452643","display_name":"Han Wang","orcid":"https://orcid.org/0000-0001-5623-1148"},"institutions":[{"id":"https://openalex.org/I126792128","display_name":"Institute of Applied Physics","ror":"https://ror.org/01km14z09","country_code":"UA","type":"facility","lineage":["https://openalex.org/I126792128","https://openalex.org/I149851306"]},{"id":"https://openalex.org/I4210145278","display_name":"Institute of Applied Physics and Computational Mathematics","ror":"https://ror.org/03sxpbt26","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210145278"]}],"countries":["CN","UA"],"is_corresponding":false,"raw_author_name":"Han Wang","raw_affiliation_strings":["Institute of Applied Physics and Computational Mathematics,National Key Laboratory of Computational Physics,Beijing,P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Applied Physics and Computational Mathematics,National Key Laboratory of Computational Physics,Beijing,P.R. China","institution_ids":["https://openalex.org/I126792128","https://openalex.org/I4210145278"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016276126","display_name":"Yongpeng Liu","orcid":"https://orcid.org/0000-0002-4544-4217"},"institutions":[{"id":"https://openalex.org/I924451375","display_name":"Incyte (United States)","ror":"https://ror.org/00cvzzg84","country_code":"US","type":"company","lineage":["https://openalex.org/I924451375"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yongpeng Liu","raw_affiliation_strings":["Phytium Technology Co., Ltd.,Tianjin,P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Phytium Technology Co., Ltd.,Tianjin,P.R. China","institution_ids":["https://openalex.org/I924451375"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007197510","display_name":"Zhaoyin Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210112820","display_name":"Shanghai Institute of Materia Medica","ror":"https://ror.org/022syn853","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112820"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaoyin Zhou","raw_affiliation_strings":["Shanghai Institute of Materia Medica, Chinese Academy of Sciences,State Key Laboratory of Drug Research; Drug Discovery and Design Center,Shanghai,P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Shanghai Institute of Materia Medica, Chinese Academy of Sciences,State Key Laboratory of Drug Research; Drug Discovery and Design Center,Shanghai,P.R. China","institution_ids":["https://openalex.org/I4210112820"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078793726","display_name":"Kenli Li","orcid":"https://orcid.org/0000-0002-2635-7716"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]},{"id":"https://openalex.org/I198357462","display_name":"Changsha University","ror":"https://ror.org/011d8sm39","country_code":"CN","type":"education","lineage":["https://openalex.org/I198357462"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kenli Li","raw_affiliation_strings":["Hunan University,Changsha,P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hunan University,Changsha,P.R. China","institution_ids":["https://openalex.org/I16609230","https://openalex.org/I198357462"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1742789,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11948","display_name":"Machine Learning in Materials Science","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11949","display_name":"Nuclear Physics and Applications","score":0.9718000292778015,"subfield":{"id":"https://openalex.org/subfields/3108","display_name":"Radiation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12039","display_name":"Electron and X-Ray Spectroscopy Techniques","score":0.9656000137329102,"subfield":{"id":"https://openalex.org/subfields/2508","display_name":"Surfaces, Coatings and Films"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7055000066757202},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.546999990940094},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.5185999870300293},{"id":"https://openalex.org/keywords/molecular-dynamics","display_name":"Molecular dynamics","score":0.5016999840736389},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4699999988079071},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.40959998965263367},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4081000089645386},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.3806999921798706}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7282000184059143},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7055000066757202},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.546999990940094},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5336999893188477},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.5185999870300293},{"id":"https://openalex.org/C59593255","wikidata":"https://www.wikidata.org/wiki/Q901663","display_name":"Molecular dynamics","level":2,"score":0.5016999840736389},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4699999988079071},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.40959998965263367},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4081000089645386},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3935999870300293},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3806999921798706},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.38029998540878296},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.37209999561309814},{"id":"https://openalex.org/C145912823","wikidata":"https://www.wikidata.org/wiki/Q113558","display_name":"Dynamics (music)","level":2,"score":0.3659000098705292},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.322299987077713},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.3176000118255615},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C71559656","wikidata":"https://www.wikidata.org/wiki/Q671298","display_name":"Divide and conquer algorithms","level":2,"score":0.28040000796318054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26499998569488525}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cluster59342.2025.11186476","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster59342.2025.11186476","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Cluster Computing (CLUSTER)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3602879582","display_name":null,"funder_award_id":"2022YFA1004303","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1701369565","https://openalex.org/W1966465438","https://openalex.org/W2096221021","https://openalex.org/W2136434791","https://openalex.org/W2531348778","https://openalex.org/W2606722458","https://openalex.org/W2613264175","https://openalex.org/W2618530766","https://openalex.org/W2937177421","https://openalex.org/W2953763743","https://openalex.org/W2978510985","https://openalex.org/W3132277775","https://openalex.org/W3161198055","https://openalex.org/W4206525429","https://openalex.org/W4244254628","https://openalex.org/W4285340451","https://openalex.org/W4383995031","https://openalex.org/W4398217329","https://openalex.org/W4402484589"],"related_works":[],"abstract_inverted_index":{"Molecular":[0],"dynamics":[1],"(MD)":[2],"simulations":[3,40,115],"are":[4],"essential":[5],"tools":[6],"for":[7,35,54],"investigating":[8],"large-scale":[9,113],"molecular":[10],"systems,":[11],"yet":[12],"achieving":[13],"high":[14],"performance":[15,86,102],"and":[16,59,91],"scalability":[17],"on":[18,33,41],"CPU-based":[19],"architectures":[20],"remains":[21],"challenging.":[22],"In":[23],"this":[24,108],"study,":[25],"we":[26,111],"present":[27],"a":[28],"highly":[29],"optimized":[30,109],"framework":[31],"based":[32],"DeepMD-kit":[34,58],"conducting":[36],"500":[37],"millionatom":[38],"MD":[39,114],"an":[42],"ARMv8":[43,62,77,93],"SVE":[44,63,78,94],"high-performance":[45],"computing":[46,118],"(HPC)":[47],"system.":[48],"Key":[49],"optimizations":[50],"include":[51],"leveraging":[52],"OpenMP":[53],"multi-threaded":[55],"acceleration":[56],"of":[57,87,103],"utilizing":[60],"the":[61,84,100],"instruction":[64],"set":[65],"to":[66,81,97],"optimize":[67],"doubleprecision":[68],"matrix":[69],"multiplication":[70],"in":[71],"PyTorch.":[72],"These":[73],"enhancements":[74],"enable":[75],"single":[76],"64-core":[79,95],"processors":[80,96],"achieve":[82,98,112],"1.3x":[83],"training":[85],"NVIDIA":[88,104],"V100":[89,105],"GPU,":[90],"two":[92],"1.05x":[99],"inference":[101],"GPU.":[106],"Leveraging":[107],"framework,":[110],"across":[116],"4,096":[117],"nodes.":[119]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}