{"id":"https://openalex.org/W2788733687","doi":"https://doi.org/10.1145/3176364.3176372","title":"Performance evaluation for omni XcalableMP compiler on many-core cluster system based on knights landing","display_name":"Performance evaluation for omni XcalableMP compiler on many-core cluster system based on knights landing","publication_year":2018,"publication_date":"2018-01-31","ids":{"openalex":"https://openalex.org/W2788733687","doi":"https://doi.org/10.1145/3176364.3176372","mag":"2788733687"},"language":"en","primary_location":{"id":"doi:10.1145/3176364.3176372","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3176364.3176372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of Workshops of HPC Asia","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/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 Advanced Institute for Computational Science, Hyogo, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Advanced Institute for Computational Science, Hyogo, 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, Hyogo, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Advanced Institute for Computational Science, Hyogo, 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":["University of Tsukuba, Ibaraki, Japan"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba, Ibaraki, 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 Advanced Institute for Computational Science, Hyogo, Japan"],"affiliations":[{"raw_affiliation_string":"RIKEN Advanced Institute for Computational Science, Hyogo, Japan","institution_ids":["https://openalex.org/I4210129730"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5089793884"],"corresponding_institution_ids":["https://openalex.org/I4210129730"],"apc_list":null,"apc_paid":null,"fwci":0.2525,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.45746761,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"52","last_page":"58"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991000294685364,"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/compiler","display_name":"Compiler","score":0.9144909381866455},{"id":"https://openalex.org/keywords/partitioned-global-address-space","display_name":"Partitioned global address space","score":0.8616608381271362},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8514887690544128},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.701460063457489},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.48671653866767883},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.4657467305660248},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.43367087841033936},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.4136103689670563},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.4060305058956146},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.35857564210891724}],"concepts":[{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.9144909381866455},{"id":"https://openalex.org/C60832428","wikidata":"https://www.wikidata.org/wiki/Q945818","display_name":"Partitioned global address space","level":3,"score":0.8616608381271362},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8514887690544128},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.701460063457489},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.48671653866767883},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.4657467305660248},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.43367087841033936},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.4136103689670563},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.4060305058956146},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.35857564210891724}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3176364.3176372","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3176364.3176372","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of Workshops of HPC Asia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2119148081","https://openalex.org/W2145843807","https://openalex.org/W2148590584","https://openalex.org/W2172949211","https://openalex.org/W2566357335","https://openalex.org/W2601752703","https://openalex.org/W2759896742","https://openalex.org/W6685340640"],"related_works":["https://openalex.org/W2166185777","https://openalex.org/W2494227547","https://openalex.org/W2913497647","https://openalex.org/W2913919777","https://openalex.org/W2072270916","https://openalex.org/W2043059266","https://openalex.org/W2018988446","https://openalex.org/W2171525159","https://openalex.org/W2236289510","https://openalex.org/W3150557277"],"abstract_inverted_index":{"To":[0],"reduce":[1],"the":[2,27,36,41,44,70,89,92,109,127,135,138,150],"programming":[3,120],"cost":[4],"on":[5,47,55,59,103],"a":[6,51,60,74,87],"cluster":[7,52,63],"system,":[8],"Partitioned":[9],"Global":[10],"Address":[11],"Space":[12],"(PGAS)":[13],"languages":[14],"are":[15],"used.":[16],"We":[17,65],"have":[18],"designed":[19],"an":[20,118],"XcalableMP":[21],"(XMP)":[22],"PGAS":[23],"language":[24],"and":[25,58,78,113],"developed":[26],"Omni":[28,45,71,93,129],"XMP":[29,125,143],"compiler":[30,46,72,94],"(Omni":[31],"compiler)":[32],"for":[33,69],"XMP.":[34],"In":[35],"present":[37],"study,":[38],"we":[39,107],"evaluated":[40],"performance":[42,67,90,110,136],"of":[43,91,111,124,137,149],"Oakforest-PACS,":[48],"which":[49,116],"is":[50,117],"system":[53],"based":[54],"Knights":[56],"Landing,":[57],"general":[61],"Linux":[62],"system.":[64],"performed":[66],"tuning":[68,96,102],"using":[73,142],"Lattice":[75,139],"QCD":[76,140],"mini-application":[77,141],"some":[79],"mathematical":[80],"functions":[81],"appearing":[82],"in":[83,153],"that":[84,123,134],"application.":[85],"As":[86],"result,":[88],"after":[95],"was":[97,144],"improved":[98],"compared":[99,108],"to":[100,122],"before":[101],"both":[104],"systems.":[105],"Furthermore,":[106],"MPI":[112,154],"OpenMP":[114],"(MPI+OpenMP),":[115],"existing":[119],"model,":[121],"with":[126],"tuned":[128],"compiler.":[130],"The":[131],"results":[132],"showed":[133],"achieving":[145],"more":[146],"than":[147],"94%":[148],"implementation":[151],"written":[152],"+":[155],"OpenMP.":[156]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
