{"id":"https://openalex.org/W2155779395","doi":"https://doi.org/10.1109/ipdpsw.2010.5470849","title":"Optimizing MPI communication within large multicore nodes with kernel assistance","display_name":"Optimizing MPI communication within large multicore nodes with kernel assistance","publication_year":2010,"publication_date":"2010-04-01","ids":{"openalex":"https://openalex.org/W2155779395","doi":"https://doi.org/10.1109/ipdpsw.2010.5470849","mag":"2155779395"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw.2010.5470849","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2010.5470849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel &amp; Distributed Processing, Workshops and Phd Forum (IPDPSW)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://inria.hal.science/inria-00451471","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5021481541","display_name":"St\u00e9phanie Moreaud","orcid":null},"institutions":[{"id":"https://openalex.org/I4210142254","display_name":"Laboratoire Bordelais de Recherche en Informatique","ror":"https://ror.org/03adqg323","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I15057530","https://openalex.org/I4210142254","https://openalex.org/I4210159245","https://openalex.org/I4210160189"]},{"id":"https://openalex.org/I15057530","display_name":"Universit\u00e9 de Bordeaux","ror":"https://ror.org/057qpr032","country_code":"FR","type":"education","lineage":["https://openalex.org/I15057530"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Stephanie Moreaud","raw_affiliation_strings":["INRIA, LaBRI, Universit\u00e9 Bordeaux, Talence, France"],"affiliations":[{"raw_affiliation_string":"INRIA, LaBRI, Universit\u00e9 Bordeaux, Talence, France","institution_ids":["https://openalex.org/I15057530","https://openalex.org/I4210142254","https://openalex.org/I1326498283","https://openalex.org/I4210160189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008381628","display_name":"Brice Goglin","orcid":"https://orcid.org/0000-0002-8671-4615"},"institutions":[{"id":"https://openalex.org/I15057530","display_name":"Universit\u00e9 de Bordeaux","ror":"https://ror.org/057qpr032","country_code":"FR","type":"education","lineage":["https://openalex.org/I15057530"]},{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]},{"id":"https://openalex.org/I4210142254","display_name":"Laboratoire Bordelais de Recherche en Informatique","ror":"https://ror.org/03adqg323","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I15057530","https://openalex.org/I4210142254","https://openalex.org/I4210159245","https://openalex.org/I4210160189"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Brice Goglin","raw_affiliation_strings":["INRIA, LaBRI, Universit\u00e9 Bordeaux, Talence, France"],"affiliations":[{"raw_affiliation_string":"INRIA, LaBRI, Universit\u00e9 Bordeaux, Talence, France","institution_ids":["https://openalex.org/I15057530","https://openalex.org/I4210142254","https://openalex.org/I1326498283","https://openalex.org/I4210160189"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037063480","display_name":"Raymond Namyst","orcid":"https://orcid.org/0000-0001-7734-1258"},"institutions":[{"id":"https://openalex.org/I4210160189","display_name":"Institut Polytechnique de Bordeaux","ror":"https://ror.org/054qv7y42","country_code":"FR","type":"education","lineage":["https://openalex.org/I4210160189"]},{"id":"https://openalex.org/I4210142254","display_name":"Laboratoire Bordelais de Recherche en Informatique","ror":"https://ror.org/03adqg323","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I15057530","https://openalex.org/I4210142254","https://openalex.org/I4210159245","https://openalex.org/I4210160189"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]},{"id":"https://openalex.org/I15057530","display_name":"Universit\u00e9 de Bordeaux","ror":"https://ror.org/057qpr032","country_code":"FR","type":"education","lineage":["https://openalex.org/I15057530"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Raymond Namyst","raw_affiliation_strings":["INRIA, LaBRI, Universit\u00e9 Bordeaux, Talence, France"],"affiliations":[{"raw_affiliation_string":"INRIA, LaBRI, Universit\u00e9 Bordeaux, Talence, France","institution_ids":["https://openalex.org/I15057530","https://openalex.org/I4210142254","https://openalex.org/I1326498283","https://openalex.org/I4210160189"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089400383","display_name":"David Goodell","orcid":null},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Goodell","raw_affiliation_strings":["Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, IL, USA"],"affiliations":[{"raw_affiliation_string":"Mathematics and Computer Science Division, Argonne National Laboratory, Argonne, IL, USA","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5021481541"],"corresponding_institution_ids":["https://openalex.org/I1326498283","https://openalex.org/I15057530","https://openalex.org/I4210142254","https://openalex.org/I4210160189"],"apc_list":null,"apc_paid":null,"fwci":3.0298,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.92041651,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998999834060669,"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":0.9991999864578247,"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":0.8462393283843994},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.706632673740387},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.64352947473526},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6395494341850281},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6167399287223816},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5931847095489502},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4622587561607361},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.44921496510505676},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.38556715846061707},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.25787076354026794}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8462393283843994},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.706632673740387},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.64352947473526},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6395494341850281},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6167399287223816},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5931847095489502},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4622587561607361},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.44921496510505676},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.38556715846061707},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.25787076354026794},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0}],"mesh":[],"locations_count":6,"locations":[{"id":"doi:10.1109/ipdpsw.2010.5470849","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2010.5470849","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel &amp; Distributed Processing, Workshops and Phd Forum (IPDPSW)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1026.9603","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1026.9603","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://hal.archives-ouvertes.fr/file/index/docid/452557/filename/CAC10.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.386.7986","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.386.7986","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hal.archives-ouvertes.fr/docs/00/45/25/57/PDF/CAC10.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.617.12","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.617.12","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.mcs.anl.gov/uploads/cels/papers/P1731.pdf","raw_type":"text"},{"id":"pmh:oai:HAL:inria-00451471v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00451471","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Workshop on Communication Architecture for Clusters, held in conjunction with IPDPS 2010, Apr 2010, Atlanta, United States. 7 p., &#x27E8;10.1109/IPDPSW.2010.5470849&#x27E9;","raw_type":"Conference papers"},{"id":"pmh:oai:oskar-bordeaux.fr:20.500.12278/198279","is_oa":false,"landing_page_url":"https://oskar-bordeaux.fr/handle/20.500.12278/198279","pdf_url":null,"source":{"id":"https://openalex.org/S4306402569","display_name":"Oskar-Bordeaux (Universite de Bordeaux)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Communication dans un congr\u00e8s"}],"best_oa_location":{"id":"pmh:oai:HAL:inria-00451471v1","is_oa":true,"landing_page_url":"https://inria.hal.science/inria-00451471","pdf_url":null,"source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Workshop on Communication Architecture for Clusters, held in conjunction with IPDPS 2010, Apr 2010, Atlanta, United States. 7 p., &#x27E8;10.1109/IPDPSW.2010.5470849&#x27E9;","raw_type":"Conference papers"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1825216778","https://openalex.org/W2032654702","https://openalex.org/W2040819538","https://openalex.org/W2083655751","https://openalex.org/W2106103789","https://openalex.org/W2112121929","https://openalex.org/W2112184852","https://openalex.org/W2113290275","https://openalex.org/W2133352850","https://openalex.org/W2140050348","https://openalex.org/W2153644289","https://openalex.org/W2165808215","https://openalex.org/W2536939761","https://openalex.org/W3144982104","https://openalex.org/W4253621724","https://openalex.org/W6638601623","https://openalex.org/W6675595333"],"related_works":["https://openalex.org/W1993191611","https://openalex.org/W2023938924","https://openalex.org/W3136989197","https://openalex.org/W2918840249","https://openalex.org/W1991859582","https://openalex.org/W2110053126","https://openalex.org/W2079303253","https://openalex.org/W2104702637","https://openalex.org/W4248099758","https://openalex.org/W2979015021"],"abstract_inverted_index":{"As":[0],"the":[1,24,92,96],"number":[2],"of":[3,23,66],"cores":[4],"per":[5],"node":[6],"increases":[7],"in":[8,28],"modern":[9],"clusters,":[10],"intra-node":[11],"communication":[12,97],"efficiency":[13],"becomes":[14],"critical":[15],"to":[16,43,63,86,91,108],"application":[17],"performance.":[18],"We":[19,46,83],"present":[20],"a":[21,31,64],"study":[22],"traditional":[25],"double-copy":[26],"model":[27],"MPICH2":[29],"and":[30,74,77,99],"kernel-assisted":[32],"single-copy":[33],"strategy":[34,90],"with":[35,41],"KNEM":[36,49],"on":[37,55,95],"different":[38],"shared-memory":[39],"hosts":[40],"up":[42,62],"96":[44],"cores.":[45],"show":[47,101],"that":[48,102],"suffers":[50],"less":[51],"from":[52,88],"process":[53],"placement":[54],"these":[56],"complex":[57],"architectures.":[58,115],"It":[59],"improves":[60,79],"throughput":[61],"factor":[65],"2":[67],"for":[68,71,113],"large":[69],"messages":[70],"both":[72],"point-to-point":[73],"collective":[75],"operations,":[76],"significantly":[78],"NPB":[80],"execution":[81],"time.":[82],"detail":[84],"when":[85],"switch":[87],"one":[89],"other":[93],"depending":[94],"pattern":[98],"we":[100],"I/OAT":[103],"copy":[104],"offload":[105],"only":[106],"appears":[107],"be":[109],"an":[110],"interesting":[111],"solution":[112],"older":[114]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
