{"id":"https://openalex.org/W2072910106","doi":"https://doi.org/10.1109/hoti.2009.12","title":"MPI Collective Communications on The Blue Gene/P Supercomputer: Algorithms and Optimizations","display_name":"MPI Collective Communications on The Blue Gene/P Supercomputer: Algorithms and Optimizations","publication_year":2009,"publication_date":"2009-08-01","ids":{"openalex":"https://openalex.org/W2072910106","doi":"https://doi.org/10.1109/hoti.2009.12","mag":"2072910106"},"language":"en","primary_location":{"id":"doi:10.1109/hoti.2009.12","doi":"https://doi.org/10.1109/hoti.2009.12","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hoti.2009.12","pdf_url":null,"source":{"id":"https://openalex.org/S4210232710","display_name":"IEEE Symposium on High-Performance Interconnects (HOTI)","issn_l":"1550-4794","issn":["1550-4794","2332-5569"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 17th IEEE Symposium on High Performance Interconnects","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W2072910106"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"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/A5076794726","display_name":"Ahmad Faraj","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmad Faraj","raw_affiliation_strings":["IBM Systems and Technology Group, Rochester, MN, USA","Syst. & Technol. Group, IBM, Rochester, MN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Systems and Technology Group, Rochester, MN, USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"Syst. & Technol. Group, IBM, Rochester, MN, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070117771","display_name":"Sameer Kumar","orcid":"https://orcid.org/0000-0001-8697-7370","observed_orcids":["https://orcid.org/0000-0001-8697-7370"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sameer Kumar","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","T. J. Watson Res. Center, IBM, Yorktown Heights, NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"T. J. Watson Res. Center, IBM, Yorktown Heights, NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Brian Smith","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Brian Smith","raw_affiliation_strings":["IBM Systems and Technology Group, Rochester, MN, USA","Syst. & Technol. Group, IBM, Rochester, MN, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Systems and Technology Group, Rochester, MN, USA","institution_ids":["https://openalex.org/I1341412227"]},{"raw_affiliation_string":"Syst. & Technol. Group, IBM, Rochester, MN, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109965519","display_name":"Amith R. Mamidala","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amith Mamidala","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","T. J. Watson Res. Center, IBM, Yorktown Heights, NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"T. J. Watson Res. Center, IBM, Yorktown Heights, NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062279572","display_name":"John A. Gunnels","orcid":"https://orcid.org/0000-0001-5110-190X","observed_orcids":["https://orcid.org/0000-0001-5110-190X"]},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]},{"id":"https://openalex.org/I4210114115","display_name":"IBM Research - Thomas J. Watson Research Center","ror":"https://ror.org/0265w5591","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Gunnels","raw_affiliation_strings":["IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","T. J. Watson Res. Center, IBM, Yorktown Heights, NY, USA#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM Thomas J. Watson Research Center, Yorktown Heights, NY, USA","institution_ids":["https://openalex.org/I4210114115"]},{"raw_affiliation_string":"T. J. Watson Res. Center, IBM, Yorktown Heights, NY, USA#TAB#","institution_ids":["https://openalex.org/I1341412227","https://openalex.org/I4210114115"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6986,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.91180067,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"63","last_page":"72"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9800000190734863,"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":0.9800000190734863,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.010099999606609344,"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":0.006800000090152025,"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/mpi-collective-communication","display_name":"MPI collective communication","score":0.9800000190734863},{"id":"https://openalex.org/keywords/blue-gene-p","display_name":"Blue Gene/P","score":0.8809999823570251},{"id":"https://openalex.org/keywords/massively-parallel-computers","display_name":"massively parallel computers","score":0.8930000066757202},{"id":"https://openalex.org/keywords/global-algorithm","display_name":"global algorithm","score":0.7020000219345093},{"id":"https://openalex.org/keywords/torus-networks","display_name":"torus networks","score":0.8069999814033508},{"id":"https://openalex.org/keywords/direct-memory-access","display_name":"direct memory access","score":0.7900000214576721},{"id":"https://openalex.org/keywords/shared-memory","display_name":"shared memory","score":0.7620000243186951},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"asynchronous communication","score":0.8069999814033508},{"id":"https://openalex.org/keywords/scalability","display_name":"scalability","score":0.453000009059906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8287606239318848},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.7840245962142944},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.72914057970047},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6556667685508728},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.650292694568634},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.5324372053146362},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4881613850593567},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.4562155306339264},{"id":"https://openalex.org/C199845137","wikidata":"https://www.wikidata.org/wiki/Q145490","display_name":"Network topology","level":2,"score":0.4352855980396271},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.41619545221328735},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3817236125469208},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35167041420936584},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2755669951438904},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.21960115432739258},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hoti.2009.12","doi":"https://doi.org/10.1109/hoti.2009.12","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hoti.2009.12","pdf_url":null,"source":{"id":"https://openalex.org/S4210232710","display_name":"IEEE Symposium on High-Performance Interconnects (HOTI)","issn_l":"1550-4794","issn":["1550-4794","2332-5569"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 17th IEEE Symposium on High Performance Interconnects","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W112345847","https://openalex.org/W1944805600","https://openalex.org/W1980670496","https://openalex.org/W1991732708","https://openalex.org/W1993618856","https://openalex.org/W2032654702","https://openalex.org/W2037492572","https://openalex.org/W2057054012","https://openalex.org/W2081612620","https://openalex.org/W2138690674","https://openalex.org/W2164945803","https://openalex.org/W2198690661","https://openalex.org/W3144982104","https://openalex.org/W4231539410","https://openalex.org/W6660129092","https://openalex.org/W6665100429"],"related_works":["https://openalex.org/W2164352834","https://openalex.org/W2164945803","https://openalex.org/W2103366781","https://openalex.org/W2107406335","https://openalex.org/W7100646576","https://openalex.org/W2087124296","https://openalex.org/W7099970213","https://openalex.org/W7099720747","https://openalex.org/W4291908378","https://openalex.org/W1582429126"],"abstract_inverted_index":{"The":[0],"IBM":[1],"Blue":[2],"Gene/P":[3],"(BG/P)":[4],"system":[5],"is":[6],"a":[7],"massively":[8],"parallel":[9],"supercomputer":[10],"succeeding":[11],"BG/L,":[12],"and":[13,21,28,68,84,112,118,124,142,147],"it":[14],"comes":[15],"with":[16,133],"many":[17],"machine":[18],"design":[19],"enhancements":[20],"new":[22],"architectural":[23],"features":[24,37],"at":[25],"the":[26,81,91,104,140,145],"hardware":[27,55,132],"software":[29],"levels.":[30],"This":[31],"paper":[32],"presents":[33],"techniques":[34],"leveraging":[35],"such":[36],"to":[38,115,135],"deliver":[39],"high":[40],"performance":[41,125,128],"MPI":[42,72],"collective":[43,61,69,110],"communication":[44],"primitives.":[45],"In":[46],"particular,":[47],"we":[48],"exploit":[49],"BG/P":[50,131],"rich":[51],"set":[52],"of":[53,60,100,121,144],"network":[54],"in":[56],"exploring":[57],"three":[58],"classes":[59],"algorithms:":[62],"global":[63,66],"algorithms":[64,76,86,120,146],"on":[65,80,130],"interrupt":[67],"networks":[70],"for":[71,77,87],"COMM":[73],"WORLD;":[74],"rectangular":[75,78],"communicators":[79,89],"torus":[82,92],"network;":[83],"binomial":[85],"irregular":[88],"over":[90],"point-to-point":[93],"network.":[94],"We":[95],"also":[96],"utilize":[97],"various":[98],"forms":[99],"data":[101],"movements":[102],"including":[103],"direct":[105],"memory":[106],"access":[107],"(DMA)":[108],"engine,":[109],"network,":[111],"shared":[113],"memory,":[114],"implement":[116],"synchronous":[117],"asynchronous":[119],"different":[122],"objectives":[123],"characteristics.":[126],"Our":[127],"study":[129],"up":[134],"16":[136],"K":[137],"nodes":[138],"demonstrates":[139],"efficiency":[141],"scalability":[143],"optimizations.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-11-11T12:16:26.678958","created_date":"2016-06-24T00:00:00"}