{"id":"https://openalex.org/W3045566052","doi":"https://doi.org/10.1177/1094342020943652","title":"Implementation and performance of Barnes-hut n-body algorithm on extreme-scale heterogeneous many-core architectures","display_name":"Implementation and performance of Barnes-hut n-body algorithm on extreme-scale heterogeneous many-core architectures","publication_year":2020,"publication_date":"2020-07-27","ids":{"openalex":"https://openalex.org/W3045566052","doi":"https://doi.org/10.1177/1094342020943652","mag":"3045566052"},"language":"en","primary_location":{"id":"doi:10.1177/1094342020943652","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342020943652","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-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/A5070757616","display_name":"Masaki Iwasawa","orcid":"https://orcid.org/0000-0003-2635-9575"},"institutions":[{"id":"https://openalex.org/I4210131413","display_name":"National Institute of Technology, Matsue College","ror":"https://ror.org/03qhht705","country_code":"JP","type":"education","lineage":["https://openalex.org/I4210120810","https://openalex.org/I4210131413"]},{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]},{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Masaki Iwasawa","raw_affiliation_strings":["Graduate School of Science, Kobe University, Kobe, Japan","National Institute of Technology, Matsue College, Matsue, Japan","RIKEN Center for Computational Science, Kobe, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Science, Kobe University, Kobe, Japan","institution_ids":["https://openalex.org/I65837984"]},{"raw_affiliation_string":"National Institute of Technology, Matsue College, Matsue, Japan","institution_ids":["https://openalex.org/I4210131413"]},{"raw_affiliation_string":"RIKEN Center for Computational Science, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066408379","display_name":"Daisuke Namekata","orcid":"https://orcid.org/0000-0001-6969-2947"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Daisuke Namekata","raw_affiliation_strings":["RIKEN Center for Computational Science, Kobe, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086793857","display_name":"Ryo Sakamoto","orcid":"https://orcid.org/0000-0003-1382-8803"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ryo Sakamoto","raw_affiliation_strings":["PEZY Computing K. K., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"PEZY Computing K. K., Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022339965","display_name":"Takashi Nakamura","orcid":"https://orcid.org/0000-0003-0730-2290"},"institutions":[{"id":"https://openalex.org/I4210166566","display_name":"Preferred Networks (Japan)","ror":"https://ror.org/05xeefy56","country_code":"JP","type":"company","lineage":["https://openalex.org/I4210166566"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takashi Nakamura","raw_affiliation_strings":["Preferred Networks Inc., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Preferred Networks Inc., Tokyo, Japan","institution_ids":["https://openalex.org/I4210166566"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101649285","display_name":"Yasuyuki Kimura","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yasuyuki Kimura","raw_affiliation_strings":["ExaScaler Inc., Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"ExaScaler Inc., Tokyo, Japan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022962037","display_name":"Keigo Nitadori","orcid":"https://orcid.org/0000-0001-7374-4236"},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Keigo Nitadori","raw_affiliation_strings":["RIKEN Center for Computational Science, Kobe, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100447536","display_name":"Long Wang","orcid":"https://orcid.org/0000-0001-5600-8157"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]},{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Long Wang","raw_affiliation_strings":["Department of Astronomy, School of Science, The University of Tokyo, Tokyo, Japan","RIKEN Center for Computational Science, Kobe, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Astronomy, School of Science, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]},{"raw_affiliation_string":"RIKEN Center for Computational Science, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085550454","display_name":"Miyuki Tsubouchi","orcid":null},"institutions":[{"id":"https://openalex.org/I4210129730","display_name":"RIKEN Center for Computational Science","ror":"https://ror.org/03r519674","country_code":"JP","type":"facility","lineage":["https://openalex.org/I4210110652","https://openalex.org/I4210129730"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Miyuki Tsubouchi","raw_affiliation_strings":["RIKEN Center for Computational Science, Kobe, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041411730","display_name":"Junichiro Makino","orcid":"https://orcid.org/0000-0002-0411-4297"},"institutions":[{"id":"https://openalex.org/I65837984","display_name":"Kobe University","ror":"https://ror.org/03tgsfw79","country_code":"JP","type":"education","lineage":["https://openalex.org/I65837984"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Jun Makino","raw_affiliation_strings":["Graduate School of Science, Kobe University, Kobe, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Science, Kobe University, Kobe, Japan","institution_ids":["https://openalex.org/I65837984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011902413","display_name":"Zhao Liu","orcid":"https://orcid.org/0000-0002-5259-4504"},"institutions":[{"id":"https://openalex.org/I4210158984","display_name":"National Supercomputing Center in Wuxi","ror":"https://ror.org/04ypjrs34","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210158984"]},{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhao Liu","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China","National Supercomputing Center in Wuxi, Wuxi, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"National Supercomputing Center in Wuxi, Wuxi, China","institution_ids":["https://openalex.org/I4210158984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031545295","display_name":"Haohuan Fu","orcid":"https://orcid.org/0000-0002-6982-2235"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haohuan Fu","raw_affiliation_strings":["Department of Earth System Science, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Earth System Science, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101678397","display_name":"Guangwen Yang","orcid":"https://orcid.org/0000-0002-8673-8254"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangwen Yang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":12,"corresponding_author_ids":["https://openalex.org/A5070757616"],"corresponding_institution_ids":["https://openalex.org/I4210129730","https://openalex.org/I4210131413","https://openalex.org/I65837984"],"apc_list":null,"apc_paid":null,"fwci":0.3983,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.5821767,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"34","issue":"6","first_page":"615","last_page":"628"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13126","display_name":"Scientific Research and Discoveries","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13126","display_name":"Scientific Research and Discoveries","score":0.9966999888420105,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"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/T10039","display_name":"Stellar, planetary, and galactic studies","score":0.9696999788284302,"subfield":{"id":"https://openalex.org/subfields/3103","display_name":"Astronomy and Astrophysics"},"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/T10477","display_name":"Astrophysics and Star Formation Studies","score":0.965399980545044,"subfield":{"id":"https://openalex.org/subfields/3103","display_name":"Astronomy and Astrophysics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6100095510482788},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5972952842712402},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5780474543571472},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5262131690979004},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.5022950172424316},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.48884743452072144},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4875030219554901},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4391537010669708},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4342361390590668},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.1101965606212616}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6100095510482788},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5972952842712402},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5780474543571472},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5262131690979004},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5022950172424316},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.48884743452072144},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4875030219554901},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4391537010669708},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4342361390590668},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.1101965606212616},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342020943652","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342020943652","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1491617812","https://openalex.org/W1989741444","https://openalex.org/W1996949834","https://openalex.org/W2000621749","https://openalex.org/W2048787800","https://openalex.org/W2068306188","https://openalex.org/W2069849911","https://openalex.org/W2074551737","https://openalex.org/W2077930506","https://openalex.org/W2087246027","https://openalex.org/W2101902146","https://openalex.org/W2107852741","https://openalex.org/W2129003192","https://openalex.org/W2170059608","https://openalex.org/W2237102931","https://openalex.org/W2475126267","https://openalex.org/W2591464004","https://openalex.org/W2798928750","https://openalex.org/W2898825203","https://openalex.org/W2949165561","https://openalex.org/W3098198264","https://openalex.org/W3100507954","https://openalex.org/W3102870694","https://openalex.org/W3104928239","https://openalex.org/W3105788098","https://openalex.org/W4249563210"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W2329539859","https://openalex.org/W3191490922","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W3214280620","https://openalex.org/W1582436825","https://openalex.org/W1996803181","https://openalex.org/W2984139344","https://openalex.org/W1907136119"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"report":[4],"the":[5,34,58,65,90,131,139,152],"implementation":[6,50],"and":[7,21,28,72,77,82,111,116,123,147],"measured":[8,105],"performance":[9,106],"of":[10,62,64,133,138],"our":[11,54],"extreme-scale":[12],"whole":[13],"planetary":[14,134],"ring":[15],"simulation":[16,132],"code":[17,127],"on":[18,53,70,75,98,113],"Sunway":[19],"TaihuLight":[20,71],"two":[22],"PEZY-SC2":[23],"systems:":[24],"Shoubu":[25,117],"System":[26,118],"B":[27,119],"Gyoukou.":[29],"The":[30,104,125],"numerical":[31],"algorithm":[32],"is":[33,51,107,128],"parallel":[35],"Barnes-Hut":[36],"tree":[37],"algorithm,":[38],"which":[39],"has":[40],"been":[41],"used":[42,67],"in":[43,151],"many":[44],"large-scale":[45],"astrophysical":[46],"particle-based":[47],"simulations.":[48],"Our":[49],"based":[52],"FDPS":[55,153],"framework.":[56,154],"However,":[57],"extremely":[59],"large":[60],"numbers":[61],"cores":[63],"systems":[66],"(10":[68],"M":[69,74],"16":[73],"Gyoukou)":[76],"their":[78],"relatively":[79],"poor":[80],"memory":[81,102],"network":[83],"bandwidth":[84],"pose":[85],"new":[86,91,140],"challenges.":[87],"We":[88],"describe":[89],"algorithms":[92,141],"introduced":[93],"to":[94],"achieve":[95],"high":[96],"efficiency":[97],"machines":[99],"with":[100],"low":[101],"bandwidth.":[103],"47.9,":[108],"10.6":[109],"PF,":[110],"1.01PF":[112],"TaihuLight,":[114],"Gyoukou":[115],"(efficiency":[120],"40%,":[121],"23.5%":[122],"35.5%).":[124],"current":[126],"developed":[129],"for":[130,144],"rings,":[135],"but":[136],"most":[137],"are":[142,148],"useful":[143],"other":[145],"simulations,":[146],"now":[149],"available":[150]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
