{"id":"https://openalex.org/W2907964014","doi":"https://doi.org/10.1177/1094342018821163","title":"Evaluation of XcalableACC with tightly coupled accelerators/InfiniBand hybrid communication on accelerated cluster","display_name":"Evaluation of XcalableACC with tightly coupled accelerators/InfiniBand hybrid communication on accelerated cluster","publication_year":2019,"publication_date":"2019-01-03","ids":{"openalex":"https://openalex.org/W2907964014","doi":"https://doi.org/10.1177/1094342018821163","mag":"2907964014"},"language":"en","primary_location":{"id":"doi:10.1177/1094342018821163","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342018821163","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/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":true,"raw_author_name":"Masahiro Nakao","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/A5085261318","display_name":"Tetsuya Odajima","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":"Tetsuya Odajima","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/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 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/A5041051226","display_name":"Akihiro Tabuchi","orcid":"https://orcid.org/0009-0009-3931-3817"},"institutions":[{"id":"https://openalex.org/I2252096349","display_name":"Fujitsu (Japan)","ror":"https://ror.org/038e2g226","country_code":"JP","type":"company","lineage":["https://openalex.org/I2252096349"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Akihiro Tabuchi","raw_affiliation_strings":["Fujitsu Laboratories Ltd, Kawasaki, Japan"],"affiliations":[{"raw_affiliation_string":"Fujitsu Laboratories Ltd, Kawasaki, Japan","institution_ids":["https://openalex.org/I2252096349"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084940217","display_name":"Norihisa Fujita","orcid":"https://orcid.org/0000-0002-5386-7623"},"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":"Norihisa Fujita","raw_affiliation_strings":["Center for Computational Sciences, University of Tsukuba, Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"Center for Computational Sciences, University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082103530","display_name":"Toshihiro Hanawa","orcid":"https://orcid.org/0000-0002-2970-6037"},"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"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Toshihiro Hanawa","raw_affiliation_strings":["Information Technology Center, The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Information Technology Center, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"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":["Center for Computational Sciences, University of Tsukuba, Tsukuba, Japan","Graduate School of Systems and Information Engineering, University of Tsukuba, Tsukuba, Japan"],"affiliations":[{"raw_affiliation_string":"Center for Computational Sciences, University of Tsukuba, Tsukuba, Japan","institution_ids":["https://openalex.org/I146399215"]},{"raw_affiliation_string":"Graduate School of Systems and Information Engineering, University of Tsukuba, Tsukuba, Japan","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 Center for Computational Science, Kobe, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Center for Computational Science, Kobe, Japan","institution_ids":["https://openalex.org/I4210129730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5089793884"],"corresponding_institution_ids":["https://openalex.org/I4210129730"],"apc_list":null,"apc_paid":null,"fwci":0.9631,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.71432298,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"33","issue":"5","first_page":"869","last_page":"884"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9994000196456909,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/infiniband","display_name":"InfiniBand","score":0.9259015321731567},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8695770502090454},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6722385883331299},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.532894492149353},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.5164154171943665},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.5011906623840332},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.48385846614837646},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.46882766485214233},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.45235636830329895},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4185808598995209},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.418521910905838},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.33349114656448364},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1714181900024414},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08369538187980652}],"concepts":[{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.9259015321731567},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8695770502090454},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6722385883331299},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.532894492149353},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.5164154171943665},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.5011906623840332},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.48385846614837646},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.46882766485214233},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.45235636830329895},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4185808598995209},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.418521910905838},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.33349114656448364},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1714181900024414},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08369538187980652}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342018821163","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342018821163","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":[{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1671636854","https://openalex.org/W1838011793","https://openalex.org/W1934320078","https://openalex.org/W1973698973","https://openalex.org/W1988378162","https://openalex.org/W1990090459","https://openalex.org/W1998739673","https://openalex.org/W2005111477","https://openalex.org/W2019782586","https://openalex.org/W2095823219","https://openalex.org/W2128994965","https://openalex.org/W2172949211","https://openalex.org/W2281558607","https://openalex.org/W2340344372","https://openalex.org/W2506485539","https://openalex.org/W2601752703","https://openalex.org/W2726358723","https://openalex.org/W2759896742","https://openalex.org/W3101695443","https://openalex.org/W3105798355"],"related_works":["https://openalex.org/W1517039268","https://openalex.org/W2751263050","https://openalex.org/W3150273738","https://openalex.org/W2068528924","https://openalex.org/W2141107779","https://openalex.org/W1970720081","https://openalex.org/W1449833061","https://openalex.org/W2395036643","https://openalex.org/W2049347805","https://openalex.org/W2039832902"],"abstract_inverted_index":{"Accelerated":[0],"clusters,":[1,111],"which":[2,104],"are":[3,9],"cluster":[4,148],"systems":[5,15],"equipped":[6],"with":[7,74,94,99,119,129,182,192],"accelerators,":[8],"one":[10],"of":[11,25,53,61,91,127,164,173,190,201,210,217],"the":[12,23,51,62,125,135,143,158,188,215,241,247,267],"most":[13],"common":[14],"in":[16],"parallel":[17,71,248],"computing.":[18],"In":[19,38,121],"order":[20,122],"to":[21,31,66,114,123,151,221,229,245,280],"exploit":[22],"performance":[24,55,126,189,216],"such":[26,57],"systems,":[27],"it":[28],"is":[29,41,65,88,105,196,272],"important":[30],"reduce":[32],"communication":[33,80,87,93,118,195],"latency":[34],"between":[35],"accelerator":[36],"memories.":[37],"addition,":[39],"there":[40],"also":[42,156],"a":[43,46,70,89,106,162],"need":[44],"for":[45,109,180],"programming":[47,72],"language":[48,108],"that":[49,172,187,200,209,234],"facilitates":[50],"maintenance":[52],"high":[54,97],"by":[56,224,226],"systems.":[58],"The":[59,101],"goal":[60],"present":[63],"article":[64],"evaluate":[67,124],"XcalableACC":[68],"(XACC),":[69],"language,":[73,103],"tightly":[75],"coupled":[76],"accelerators/InfiniBand":[77],"(TCAs/IB)":[78],"hybrid":[79,86,117,131,194],"on":[81,145],"an":[82],"accelerated":[83,110,147],"cluster.":[84],"TCA/IB":[85,116,130,193],"combination":[90,163],"low-latency":[92],"TCA":[95],"and":[96,141,166,171,175,205,255,275],"bandwidth":[98],"IB.":[100],"XACC":[102,128,191,218,235,261,271],"directive-based":[107,282],"enables":[112],"programmers":[113],"use":[115],"ease.":[120],"communication,":[132],"we":[133],"implemented":[134,157],"lattice":[136],"quantum":[137],"chromodynamics":[138],"(LQCD)":[139],"mini-application":[140,160],"evaluated":[142],"application":[144],"our":[146],"using":[149,161],"up":[150],"64":[152],"compute":[153],"nodes.":[154],"We":[155],"LQCD":[159,243,249],"CUDA":[165,202,252],"MPI":[167,176,204,254],"(CUDA":[168],"+":[169,178,203,212,253,257],"MPI)":[170,179],"OpenACC":[174,211,256],"(OpenACC":[177],"comparison":[181],"XACC.":[183,230],"Performance":[184],"evaluation":[185,232],"revealed":[186,233],"9%":[197],"better":[198,207],"than":[199,208,251],"18%":[206],"MPI.":[213,258],"Furthermore,":[214],"was":[219],"found":[220],"further":[222],"increase":[223],"7%":[225],"new":[227],"expansion":[228],"Productivity":[231],"requires":[236],"much":[237],"less":[238],"change":[239],"from":[240],"serial":[242],"code":[244,250,269],"implement":[246],"Moreover,":[259],"since":[260],"can":[262],"perform":[263],"parallelization":[264],"while":[265],"maintaining":[266],"sequential":[268],"image,":[270],"highly":[273],"readable":[274],"shows":[276],"excellent":[277],"portability":[278],"due":[279],"its":[281],"approach.":[283]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
