{"id":"https://openalex.org/W2788362789","doi":"https://doi.org/10.1145/3176364.3176373","title":"Scaling collectives on large clusters using Intel(R) architecture processors and fabric","display_name":"Scaling collectives on large clusters using Intel(R) architecture processors and fabric","publication_year":2018,"publication_date":"2018-01-31","ids":{"openalex":"https://openalex.org/W2788362789","doi":"https://doi.org/10.1145/3176364.3176373","mag":"2788362789"},"language":"en","primary_location":{"id":"doi:10.1145/3176364.3176373","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3176364.3176373","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3176364.3176373?download=true","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":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3176364.3176373?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5073314426","display_name":"Masashi Horikoshi","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Masashi Horikoshi","raw_affiliation_strings":["Intel, K.K"],"affiliations":[{"raw_affiliation_string":"Intel, K.K","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075276415","display_name":"Larry Meadows","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Larry Meadows","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083825955","display_name":"Tom Elken","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tom Elken","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088373733","display_name":"Pradeep Sivakumar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Pradeep Sivakumar","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071557199","display_name":"Edward Mascarenhas","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Edward Mascarenhas","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041942029","display_name":"James Erwin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210158342","display_name":"Intel (United Kingdom)","ror":"https://ror.org/058cxws58","country_code":"GB","type":"company","lineage":["https://openalex.org/I1343180700","https://openalex.org/I4210158342"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James Erwin","raw_affiliation_strings":["Intel Corporation"],"affiliations":[{"raw_affiliation_string":"Intel Corporation","institution_ids":["https://openalex.org/I4210158342"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069758554","display_name":"Dmitry Durnov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dmitry Durnov","raw_affiliation_strings":["Intel, Russia"],"affiliations":[{"raw_affiliation_string":"Intel, Russia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090576680","display_name":"Alexander Sannikov","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexander Sannikov","raw_affiliation_strings":["Intel, Russia"],"affiliations":[{"raw_affiliation_string":"Intel, Russia","institution_ids":[]}]},{"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":["The University of Tokyo"],"affiliations":[{"raw_affiliation_string":"The University of Tokyo","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","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"],"affiliations":[{"raw_affiliation_string":"University of Tsukuba","institution_ids":["https://openalex.org/I146399215"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":10,"corresponding_author_ids":["https://openalex.org/A5073314426"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5049,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.58384258,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"59","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9944999814033508,"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":0.9944999814033508,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9779000282287598,"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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.972000002861023,"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/speedup","display_name":"Speedup","score":0.912731945514679},{"id":"https://openalex.org/keywords/xeon-phi","display_name":"Xeon Phi","score":0.7405626177787781},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7219957113265991},{"id":"https://openalex.org/keywords/xeon","display_name":"Xeon","score":0.7114289402961731},{"id":"https://openalex.org/keywords/scaling","display_name":"Scaling","score":0.6942680478096008},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6935358047485352},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5162451267242432},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.49798583984375},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.432212233543396},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.4264158308506012},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.32437166571617126},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.13711419701576233},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.10023757815361023}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.912731945514679},{"id":"https://openalex.org/C96972482","wikidata":"https://www.wikidata.org/wiki/Q1049168","display_name":"Xeon Phi","level":2,"score":0.7405626177787781},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7219957113265991},{"id":"https://openalex.org/C145108525","wikidata":"https://www.wikidata.org/wiki/Q656154","display_name":"Xeon","level":2,"score":0.7114289402961731},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.6942680478096008},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6935358047485352},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5162451267242432},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.49798583984375},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.432212233543396},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.4264158308506012},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.32437166571617126},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.13711419701576233},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.10023757815361023},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3176364.3176373","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3176364.3176373","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3176364.3176373?download=true","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":{"id":"doi:10.1145/3176364.3176373","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3176364.3176373","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3176364.3176373?download=true","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"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320322832","display_name":"University of Tokyo","ror":"https://ror.org/057zh3y96"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2788362789.pdf","grobid_xml":"https://content.openalex.org/works/W2788362789.grobid-xml"},"referenced_works_count":4,"referenced_works":["https://openalex.org/W1547956788","https://openalex.org/W1558115001","https://openalex.org/W2062011830","https://openalex.org/W2068975988"],"related_works":["https://openalex.org/W1974923383","https://openalex.org/W2475524688","https://openalex.org/W2739740241","https://openalex.org/W947442053","https://openalex.org/W2085105049","https://openalex.org/W2592417500","https://openalex.org/W2526069705","https://openalex.org/W2024016913","https://openalex.org/W2019153376","https://openalex.org/W2981664121"],"abstract_inverted_index":{"This":[0],"paper":[1],"provides":[2],"results":[3,65],"on":[4,12,41],"scaling":[5],"Barrier":[6,68,96],"and":[7,26,38,47,69,97],"Allreduce":[8,70,103],"to":[9,50,59,80],"8192":[10],"nodes":[11],"a":[13,82],"cluster":[14],"of":[15,24,29,36,44,84],"Intel\u00ae":[16],"Xeon":[17],"Phi\u2122":[18],"processors":[19],"installed":[20],"at":[21,104,111],"the":[22,27,34,42,52,105],"University":[23,28],"Tokyo":[25],"Tsukuba.":[30],"We":[31,62,77],"will":[32,63],"describe":[33],"effects":[35],"OS":[37],"platform":[39],"noise":[40,53,74],"performance":[43],"these":[45],"collectives,":[46],"provide":[48,64],"ways":[49],"minimize":[51],"as":[54,56],"well":[55,72],"isolate":[57],"it":[58],"specific":[60],"cores.":[61],"showing":[66],"that":[67],"scale":[71],"when":[73],"is":[75],"reduced.":[76],"were":[78],"able":[79],"achieve":[81],"latency":[83],"94":[85],"usec":[86,99],"(7.1x":[87],"speedup":[88],"from":[89],"baseline)":[90],"or":[91],"1":[92],"rank":[93],"per":[94],"node":[95],"145":[98],"(3.3x":[100],"speedup)":[101],"for":[102],"16":[106],"byte":[107],"(16B)":[108],"message":[109],"size":[110],"4096":[112],"nodes.":[113]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
