{"id":"https://openalex.org/W2726358723","doi":"https://doi.org/10.1109/ccgrid.2017.81","title":"Implementation and Evaluation of One-Sided PGAS Communication in XcalableACC for Accelerated Clusters","display_name":"Implementation and Evaluation of One-Sided PGAS Communication in XcalableACC for Accelerated Clusters","publication_year":2017,"publication_date":"2017-05-01","ids":{"openalex":"https://openalex.org/W2726358723","doi":"https://doi.org/10.1109/ccgrid.2017.81","mag":"2726358723"},"language":"en","primary_location":{"id":"doi:10.1109/ccgrid.2017.81","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccgrid.2017.81","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 17th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID)","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/A5041051226","display_name":"Akihiro Tabuchi","orcid":"https://orcid.org/0009-0009-3931-3817"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Akihiro Tabuchi","raw_affiliation_strings":["Tsukuba Daigaku, Tsukuba, Ibaraki, JP"],"affiliations":[{"raw_affiliation_string":"Tsukuba Daigaku, Tsukuba, Ibaraki, JP","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089793884","display_name":"Masahiro Nakao","orcid":"https://orcid.org/0000-0001-7848-1172"},"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":"Masahiro Nakao","raw_affiliation_strings":["RIKEN Advanced Institute for Computational Science, Kobe, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Advanced Institute for Computational Science, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103277015","display_name":"Hitoshi Murai","orcid":"https://orcid.org/0000-0002-6239-3968"},"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 Advanced Institute for Computational Science, Kobe, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Advanced Institute for Computational Science, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020716792","display_name":"Taisuke Boku","orcid":"https://orcid.org/0000-0001-8730-2228"},"institutions":[{"id":"https://openalex.org/I146399215","display_name":"University of Tsukuba","ror":"https://ror.org/02956yf07","country_code":"JP","type":"education","lineage":["https://openalex.org/I146399215"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Taisuke Boku","raw_affiliation_strings":["Tsukuba Daigaku, Tsukuba, Ibaraki, JP"],"affiliations":[{"raw_affiliation_string":"Tsukuba Daigaku, Tsukuba, Ibaraki, JP","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040254066","display_name":"Mitsuhisa Sato","orcid":"https://orcid.org/0000-0003-0543-7116"},"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":"Mitsuhisa Sato","raw_affiliation_strings":["RIKEN Adv. Inst. for Comput. Sci., Kobe, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Adv. Inst. for Comput. Sci., Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5041051226"],"corresponding_institution_ids":["https://openalex.org/I146399215"],"apc_list":null,"apc_paid":null,"fwci":1.1266,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.78604596,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"625","last_page":"634"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9995999932289124,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.998199999332428,"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/partitioned-global-address-space","display_name":"Partitioned global address space","score":0.9783109426498413},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8851776719093323},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7783578634262085},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.689113199710846},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6777156591415405},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.5889396667480469},{"id":"https://openalex.org/keywords/fortran","display_name":"Fortran","score":0.5777252316474915},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.5268933773040771},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.5018212795257568},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4736712574958801},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.4670851230621338},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.4306418299674988},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.42719998955726624},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.42133161425590515},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.33647245168685913},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.31503814458847046},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.27414941787719727},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2678867280483246}],"concepts":[{"id":"https://openalex.org/C60832428","wikidata":"https://www.wikidata.org/wiki/Q945818","display_name":"Partitioned global address space","level":3,"score":0.9783109426498413},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8851776719093323},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7783578634262085},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.689113199710846},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6777156591415405},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.5889396667480469},{"id":"https://openalex.org/C2778241615","wikidata":"https://www.wikidata.org/wiki/Q83303","display_name":"Fortran","level":2,"score":0.5777252316474915},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.5268933773040771},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.5018212795257568},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4736712574958801},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.4670851230621338},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.4306418299674988},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.42719998955726624},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.42133161425590515},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.33647245168685913},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.31503814458847046},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.27414941787719727},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2678867280483246},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ccgrid.2017.81","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccgrid.2017.81","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 17th IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGRID)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4000000059604645,"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W776158461","https://openalex.org/W1521571223","https://openalex.org/W1586422308","https://openalex.org/W1673512521","https://openalex.org/W1838011793","https://openalex.org/W1973698973","https://openalex.org/W1984096996","https://openalex.org/W2014325923","https://openalex.org/W2022039320","https://openalex.org/W2034946236","https://openalex.org/W2116447728","https://openalex.org/W2121504627","https://openalex.org/W2414917230","https://openalex.org/W2476472380","https://openalex.org/W2574918252","https://openalex.org/W2971491423","https://openalex.org/W3214920199","https://openalex.org/W6622481955","https://openalex.org/W6639023099","https://openalex.org/W6732038495"],"related_works":["https://openalex.org/W2119534391","https://openalex.org/W2503137108","https://openalex.org/W1966576946","https://openalex.org/W2023770367","https://openalex.org/W2765743988","https://openalex.org/W2062253548","https://openalex.org/W2393707426","https://openalex.org/W2056717482","https://openalex.org/W2030707850","https://openalex.org/W2393490604"],"abstract_inverted_index":{"Clusters":[0],"equipped":[1],"with":[2,30,49,111,162,194],"accelerators":[3],"such":[4,19],"as":[5],"graphics":[6],"processing":[7],"unit":[8],"(GPU)":[9],"and":[10,79,89,119,130,138,142,150,166,171],"Many":[11],"Integrated":[12],"Core":[13],"(MIC)":[14],"are":[15,168],"widely":[16],"used.":[17],"For":[18],"clusters,":[20],"programmers":[21,42,107],"write":[22],"programs":[23],"for":[24,135,214],"their":[25,45],"applications":[26,46],"by":[27,144],"combining":[28],"MPI":[29,55],"one":[31],"of":[32,69,101,158,189,201,210],"the":[33,104,112,159,163,174,178,187,195,199,203],"available":[34],"accelerator":[35],"programming":[36,62,85],"models.":[37],"In":[38,103],"particular,":[39],"OpenACC":[40,92],"enables":[41,83],"to":[43,53,95,98,123],"develop":[44],"easily,":[47],"but":[48],"lower":[50],"productivity":[51,143],"owing":[52],"complex":[54],"programming.":[56],"XcalableACC":[57],"(XACC)":[58],"is":[59,65],"a":[60,70,99],"new":[61],"model,":[63,106],"which":[64],"an":[66,132,207],"\"orthogonal\"":[67],"integration":[68],"partitioned":[71],"global":[72],"address":[73],"space":[74],"(PGAS)":[75],"language":[76],"XcalableMP":[77],"(XMP)":[78],"OpenACC.":[80],"While":[81],"XMP":[82],"distributed-memory":[84],"on":[86],"both":[87],"global-view":[88],"local-view":[90,105,175,190,204],"models,":[91],"allows":[93],"operations":[94],"be":[96],"offloaded":[97],"set":[100],"accelerators.":[102,126],"can":[108],"describe":[109],"communication":[110,124,185],"coarray":[113],"features":[114],"adopted":[115],"from":[116],"Fortran":[117],"2008,":[118],"we":[120],"extend":[121],"them":[122],"between":[125],"We":[127],"have":[128],"designed":[129],"implemented":[131],"XACC":[133,160],"compiler":[134],"NVIDIA":[136],"GPU":[137],"evaluated":[139],"its":[140],"performance":[141,157,188],"using":[145,183],"two":[146],"benchmarks,":[147],"Himeno":[148,164,196],"benchmark":[149,165],"NAS":[151],"Parallel":[152],"Benchmarks":[153],"CG":[154],"(NPB-CG).":[155],"The":[156],"version":[161,191],"NPB-CG":[167],"over":[169,192],"85%":[170],"97%":[172],"in":[173],"model":[176,205],"against":[177],"MPI+OpenACC":[179],"version,":[180],"respectively.":[181],"Moreover,":[182],"non-blocking":[184],"makes":[186],"89%":[193],"benchmark.":[197],"From":[198],"viewpoint":[200],"productivity,":[202],"provides":[206],"intuitive":[208],"form":[209],"array":[211],"assignment":[212],"statement":[213],"communication.":[215]},"counts_by_year":[{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}