{"id":"https://openalex.org/W7119476307","doi":"https://doi.org/10.1145/3773656.3773672","title":"Rankmap optimization for large scale HPC applications with simulated annealing based on MPI trace information","display_name":"Rankmap optimization for large scale HPC applications with simulated annealing based on MPI trace information","publication_year":2026,"publication_date":"2026-01-09","ids":{"openalex":"https://openalex.org/W7119476307","doi":"https://doi.org/10.1145/3773656.3773672"},"language":null,"primary_location":{"id":"doi:10.1145/3773656.3773672","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773656.3773672","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3773656.3773672","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022767887","display_name":"Akiyoshi Kuroda","orcid":"https://orcid.org/0000-0002-3249-5592"},"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":true,"raw_author_name":"Akiyoshi Kuroda","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/A5102843444","display_name":"Yoshifumi Nakamura","orcid":"https://orcid.org/0000-0001-6799-1628"},"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":"Yoshifumi Nakamura","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/A5080621827","display_name":"Kazuto Ando","orcid":"https://orcid.org/0000-0003-2123-1177"},"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":"Kazuto Ando","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/A5122378640","display_name":"Hitoshi Murai","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":"Hitoshi Murai","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":"last","author":{"id":"https://openalex.org/A5108634964","display_name":"Chisachi KATO","orcid":null},"institutions":[{"id":"https://openalex.org/I104946051","display_name":"Nihon University","ror":"https://ror.org/05jk51a88","country_code":"JP","type":"education","lineage":["https://openalex.org/I104946051"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Chisachi Kato","raw_affiliation_strings":["NIHON UNIVERSITY, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"NIHON UNIVERSITY, Tokyo, Japan","institution_ids":["https://openalex.org/I104946051"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5022767887"],"corresponding_institution_ids":["https://openalex.org/I4210129730"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08987784,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"296","last_page":"307"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.679099977016449,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.679099977016449,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.18539999425411224,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","score":0.056299999356269836,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.8543999791145325},{"id":"https://openalex.org/keywords/network-topology","display_name":"Network topology","score":0.7129999995231628},{"id":"https://openalex.org/keywords/simulated-annealing","display_name":"Simulated annealing","score":0.6261000037193298},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.6158999800682068},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.5701000094413757},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5489000082015991},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.44209998846054077}],"concepts":[{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.8543999791145325},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8077999949455261},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.7129999995231628},{"id":"https://openalex.org/C126980161","wikidata":"https://www.wikidata.org/wiki/Q863783","display_name":"Simulated annealing","level":2,"score":0.6261000037193298},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.6158999800682068},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6019999980926514},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.5701000094413757},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5489000082015991},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4916999936103821},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.44209998846054077},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.43470001220703125},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.42160001397132874},{"id":"https://openalex.org/C139940560","wikidata":"https://www.wikidata.org/wiki/Q290036","display_name":"Network simulation","level":2,"score":0.38909998536109924},{"id":"https://openalex.org/C75291252","wikidata":"https://www.wikidata.org/wiki/Q1315756","display_name":"TRACE (psycholinguistics)","level":2,"score":0.37790000438690186},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.2736000120639801},{"id":"https://openalex.org/C192126672","wikidata":"https://www.wikidata.org/wiki/Q1068715","display_name":"Telecommunications network","level":2,"score":0.2720000147819519},{"id":"https://openalex.org/C184720557","wikidata":"https://www.wikidata.org/wiki/Q7825049","display_name":"Topology (electrical circuits)","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3773656.3773672","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773656.3773672","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3773656.3773672","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3773656.3773672","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Supercomputing Asia and International Conference on High Performance Computing in Asia Pacific Region","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1974962310","https://openalex.org/W1982386146","https://openalex.org/W1985922489","https://openalex.org/W2002735620","https://openalex.org/W2022819055","https://openalex.org/W2027305902","https://openalex.org/W2029377638","https://openalex.org/W2056760934","https://openalex.org/W2062712788","https://openalex.org/W2066672953","https://openalex.org/W2072605585","https://openalex.org/W2074447412","https://openalex.org/W2076077791","https://openalex.org/W2076988681","https://openalex.org/W2102062620","https://openalex.org/W2120465892","https://openalex.org/W2141654137","https://openalex.org/W2153432564","https://openalex.org/W2167657634","https://openalex.org/W2293154820","https://openalex.org/W2300484820","https://openalex.org/W2313590387","https://openalex.org/W2334862469","https://openalex.org/W2337234142","https://openalex.org/W2361798087","https://openalex.org/W2609983377","https://openalex.org/W2795894437","https://openalex.org/W2899187877","https://openalex.org/W2941016569","https://openalex.org/W2964326548","https://openalex.org/W2991536155","https://openalex.org/W3000615360","https://openalex.org/W4388699080","https://openalex.org/W4401974327"],"related_works":[],"abstract_inverted_index":{"We":[0,101],"propose":[1],"a":[2],"rank":[3],"mapping":[4,79],"optimization":[5],"tool":[6],"based":[7],"on":[8,59,132],"simulated":[9],"annealing":[10],"using":[11],"Message":[12],"Passing":[13],"Interface":[14],"(MPI)":[15],"trace":[16,99],"information.":[17],"In":[18],"distributed":[19],"parallel":[20],"executions":[21],"of":[22,80,123,159],"typical":[23],"high-performance":[24],"computing":[25],"(HPC)":[26],"applications,":[27],"such":[28,65,186],"as":[29,66,187],"unstructured-grid":[30],"simulations,":[31],"MPI":[32,81,98],"processes":[33],"responsible":[34],"for":[35],"adjacent":[36],"subdomains":[37],"are":[38],"often":[39],"mapped":[40],"to":[41,51,83,118,138,172,178],"physically":[42],"distant":[43],"nodes,":[44],"resulting":[45],"in":[46,147,150,163],"increased":[47],"communication":[48,73,94,124,148],"latency":[49],"due":[50],"network":[52,157,184],"congestion.":[53],"This":[54],"issue":[55],"is":[56,168],"particularly":[57],"pronounced":[58],"large":[60],"and":[61,109],"directly":[62,173],"connected":[63,174],"networks":[64,175],"the":[67,78,103,110,120,133,151,160,165],"supercomputer":[68,134,161],"Fugaku.":[69],"To":[70],"mitigate":[71],"these":[72],"issues,":[74],"our":[75],"method":[76,167],"optimizes":[77],"ranks":[82],"physical":[84],"node":[85],"coordinates":[86],"by":[87],"minimizing":[88],"an":[89],"evaluation":[90],"function":[91],"that":[92],"represents":[93],"costs":[95],"derived":[96],"from":[97],"logs.":[100],"employ":[102],"finite":[104,113],"element":[105],"simulation":[106,115],"software":[107,116],"FrontFlow/blue":[108],"hierarchically":[111],"structured":[112],"volume":[114],"CUBE":[117],"validate":[119],"effec":[121],"t":[122],"time":[125,149],"reduction.":[126],"The":[127],"proposed":[128,166],"approach":[129],"was":[130],"tested":[131],"Fugaku":[135,162],"with":[136,156,182],"up":[137],"3,072":[139],"nodes":[140],"(12,288":[141],"processes),":[142],"achieving":[143],"approximately":[144],"48%":[145],"reduction":[146],"best":[152],"case.":[153],"While":[154],"implemented":[155],"topology":[158],"mind,":[164],"applicable":[169],"not":[170],"only":[171],"but":[176],"also":[177],"large-scale":[179],"multi-hop":[180],"systems":[181],"complex":[183],"topologies":[185],"FugakuNEXT.":[188]},"counts_by_year":[],"updated_date":"2026-01-10T23:39:48.068659","created_date":"2026-01-09T00:00:00"}