{"id":"https://openalex.org/W3104089758","doi":"https://doi.org/10.1145/3339186.3339199","title":"MPI Collectives for Multi-core Clusters","display_name":"MPI Collectives for Multi-core Clusters","publication_year":2019,"publication_date":"2019-07-22","ids":{"openalex":"https://openalex.org/W3104089758","doi":"https://doi.org/10.1145/3339186.3339199","mag":"3104089758"},"language":"en","primary_location":{"id":"doi:10.1145/3339186.3339199","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3339186.3339199","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 48th International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"preprint","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/A5101978404","display_name":"Huan Zhou","orcid":"https://orcid.org/0009-0008-2596-5198"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Huan Zhou","raw_affiliation_strings":["HLRS, University of Stuttgart, Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"HLRS, University of Stuttgart, Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064665553","display_name":"Jos\u00e9 Gracia","orcid":"https://orcid.org/0000-0002-8925-6592"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Gracia","raw_affiliation_strings":["HLRS, University of Stuttgart, Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"HLRS, University of Stuttgart, Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091813919","display_name":"Ralf Schneider","orcid":"https://orcid.org/0000-0001-6583-9016"},"institutions":[{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Ralf Schneider","raw_affiliation_strings":["HLRS, University of Stuttgart, Stuttgart, Germany"],"affiliations":[{"raw_affiliation_string":"HLRS, University of Stuttgart, Stuttgart, Germany","institution_ids":["https://openalex.org/I100066346"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101978404"],"corresponding_institution_ids":["https://openalex.org/I100066346"],"apc_list":null,"apc_paid":null,"fwci":1.03778028,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.75734238,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":93,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9990000128746033,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9987000226974487,"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/computer-science","display_name":"Computer science","score":0.9028189778327942},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7377362847328186},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.6856070756912231},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.6092803478240967},{"id":"https://openalex.org/keywords/spmd","display_name":"SPMD","score":0.6074990034103394},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.5738157629966736},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5354981422424316},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.5207653045654297},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.48277345299720764},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3213668167591095}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9028189778327942},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7377362847328186},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.6856070756912231},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.6092803478240967},{"id":"https://openalex.org/C7042729","wikidata":"https://www.wikidata.org/wiki/Q2289219","display_name":"SPMD","level":2,"score":0.6074990034103394},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.5738157629966736},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5354981422424316},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.5207653045654297},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.48277345299720764},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3213668167591095},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3339186.3339199","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3339186.3339199","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Workshop Proceedings of the 48th International Conference on Parallel Processing","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":30,"referenced_works":["https://openalex.org/W31923072","https://openalex.org/W1498011047","https://openalex.org/W1554378292","https://openalex.org/W1554398046","https://openalex.org/W1574750619","https://openalex.org/W1986445598","https://openalex.org/W1988888548","https://openalex.org/W2000531806","https://openalex.org/W2034714579","https://openalex.org/W2043143850","https://openalex.org/W2050120016","https://openalex.org/W2056999868","https://openalex.org/W2085040216","https://openalex.org/W2087157372","https://openalex.org/W2099030945","https://openalex.org/W2110035325","https://openalex.org/W2111144707","https://openalex.org/W2121207198","https://openalex.org/W2131613942","https://openalex.org/W2138782497","https://openalex.org/W2139702875","https://openalex.org/W2146375161","https://openalex.org/W2166834428","https://openalex.org/W2171418771","https://openalex.org/W2261799817","https://openalex.org/W2294782168","https://openalex.org/W3100190457","https://openalex.org/W3104493324","https://openalex.org/W4252163020","https://openalex.org/W4300402905"],"related_works":["https://openalex.org/W303598914","https://openalex.org/W2110637160","https://openalex.org/W2072996874","https://openalex.org/W2366325093","https://openalex.org/W1987227219","https://openalex.org/W3132387974","https://openalex.org/W2244707588","https://openalex.org/W2498758832","https://openalex.org/W2154020360","https://openalex.org/W2133825528"],"abstract_inverted_index":{"The":[0,157],"advent":[1],"of":[2,34,44,72,102,106,123,130,159],"multi-/many-core":[3],"processors":[4],"in":[5,69,120],"clusters":[6],"advocates":[7],"hybrid":[8,32,42,73,133],"parallel":[9],"programming,":[10],"which":[11],"combines":[12],"Message":[13],"Passing":[14],"Interface":[15],"(MPI)":[16],"for":[17,25,59,132,139,184],"inter-node":[18],"parallelism":[19],"with":[20,193],"a":[21,38,145,166,194,203],"shared":[22,94],"memory":[23,79,82,89],"model":[24],"on-node":[26,96,104],"parallelism.":[27],"Compared":[28],"to":[29,77,153],"the":[30,70,100,116,121,136,148],"traditional":[31,137],"approach":[33,43,58,129,161,192],"MPI":[35,45,113],"plus":[36,46],"OpenMP,":[37],"new,":[39],"but":[40],"promising":[41],"MPI-3":[47],"shared-memory":[48],"extensions":[49],"(MPI+MPI)":[50],"is":[51,91,151],"gaining":[52],"attraction.":[53],"We":[54,126,187],"describe":[55],"an":[56],"algorithmic":[57],"collective":[60],"operations":[61],"(with":[62],"allgather":[63,185],"and":[64,81,93,135,142,172,202],"broadcast":[65],"as":[66,76],"concrete":[67],"examples)":[68],"context":[71,122],"MPI+MPI,":[74],"so":[75],"minimize":[78],"consumption":[80],"copies.":[83],"With":[84],"this":[85],"approach,":[86],"only":[87],"one":[88,138],"copy":[90],"maintained":[92],"by":[95],"processes.":[97],"This":[98],"allows":[99],"removal":[101],"unnecessary":[103],"copies":[105],"replicated":[107],"data":[108,155],"that":[109,150,177],"are":[110,118],"required":[111,152],"between":[112],"processes":[114],"when":[115],"collectives":[117,131],"invoked":[119],"pure":[124,140],"MPI.":[125],"compare":[127],"our":[128,160,191],"MPI+MPI":[134],"MPI,":[141],"also":[143],"have":[144,188],"discussion":[146],"on":[147,165],"synchronization":[149],"guarantee":[154],"integrity.":[156],"performance":[158,183],"has":[162],"been":[163],"validated":[164,190],"Cray":[167],"XC40":[168],"system":[169],"(Cray":[170],"MPI)":[171],"NEC":[173],"cluster":[174],"(OpenMPI),":[175],"showing":[176],"it":[178],"achieves":[179],"comparable":[180],"or":[181],"better":[182],"operations.":[186],"further":[189],"standard":[195],"computational":[196],"kernel,":[197],"namely":[198],"distributed":[199],"matrix":[200],"multiplication,":[201],"Bayesian":[204],"Probabilistic":[205],"Matrix":[206],"Factorization":[207],"code.":[208]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2020-11-23T00:00:00"}