{"id":"https://openalex.org/W2026036594","doi":"https://doi.org/10.1109/fpl.2009.5272560","title":"Hardware implementation of MPI_Barrier on an FPGA cluster","display_name":"Hardware implementation of MPI_Barrier on an FPGA cluster","publication_year":2009,"publication_date":"2009-08-01","ids":{"openalex":"https://openalex.org/W2026036594","doi":"https://doi.org/10.1109/fpl.2009.5272560","mag":"2026036594"},"language":"en","primary_location":{"id":"doi:10.1109/fpl.2009.5272560","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpl.2009.5272560","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 International Conference on Field Programmable Logic and Applications","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/A5046067082","display_name":"Shanyuan Gao","orcid":"https://orcid.org/0000-0001-7113-125X"},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]},{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shanyuan Gao","raw_affiliation_strings":["Reconfigurable Computing Systems Laboratory, Electrical & Computer Engineering Department, North Carolina State University, Charlotte, USA","Reconfigurable Computing Systems Lab, Electrical & Computer Engineering Department, University of North Carolina at Charlotte, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reconfigurable Computing Systems Laboratory, Electrical & Computer Engineering Department, North Carolina State University, Charlotte, USA","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"Reconfigurable Computing Systems Lab, Electrical & Computer Engineering Department, University of North Carolina at Charlotte, USA","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110900114","display_name":"Andrew G. Schmidt","orcid":null},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]},{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew G. Schmidt","raw_affiliation_strings":["Reconfigurable Computing Systems Laboratory, Electrical & Computer Engineering Department, North Carolina State University, Charlotte, USA","Reconfigurable Computing Systems Lab, Electrical & Computer Engineering Department, University of North Carolina at Charlotte, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reconfigurable Computing Systems Laboratory, Electrical & Computer Engineering Department, North Carolina State University, Charlotte, USA","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"Reconfigurable Computing Systems Lab, Electrical & Computer Engineering Department, University of North Carolina at Charlotte, USA","institution_ids":["https://openalex.org/I102149020"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5106082786","display_name":"Ron Sass","orcid":null},"institutions":[{"id":"https://openalex.org/I102149020","display_name":"University of North Carolina at Charlotte","ror":"https://ror.org/04dawnj30","country_code":"US","type":"education","lineage":["https://openalex.org/I102149020"]},{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ron Sass","raw_affiliation_strings":["Reconfigurable Computing Systems Laboratory, Electrical & Computer Engineering Department, North Carolina State University, Charlotte, USA","Reconfigurable Computing Systems Lab, Electrical & Computer Engineering Department, University of North Carolina at Charlotte, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Reconfigurable Computing Systems Laboratory, Electrical & Computer Engineering Department, North Carolina State University, Charlotte, USA","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"Reconfigurable Computing Systems Lab, Electrical & Computer Engineering Department, University of North Carolina at Charlotte, USA","institution_ids":["https://openalex.org/I102149020"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.217,"has_fulltext":false,"cited_by_count":21,"citation_normalized_percentile":{"value":0.92136639,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"12","last_page":"17"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9998000264167786,"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/T10772","display_name":"Distributed systems and fault tolerance","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8722243309020996},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.669830858707428},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6617969274520874},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.6391773223876953},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.44932490587234497},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4456145763397217},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.4401543438434601},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.43780121207237244},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.43106839060783386},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.41137343645095825},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.37597158551216125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8722243309020996},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.669830858707428},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6617969274520874},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.6391773223876953},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.44932490587234497},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4456145763397217},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.4401543438434601},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.43780121207237244},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.43106839060783386},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.41137343645095825},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.37597158551216125},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fpl.2009.5272560","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fpl.2009.5272560","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2009 International Conference on Field Programmable Logic and Applications","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1550062991","https://openalex.org/W1555178782","https://openalex.org/W1994691947","https://openalex.org/W2015065468","https://openalex.org/W2018899347","https://openalex.org/W2069942366","https://openalex.org/W2098246574","https://openalex.org/W2105908643","https://openalex.org/W2106982779","https://openalex.org/W2117006886","https://openalex.org/W2124150072","https://openalex.org/W2131613942","https://openalex.org/W2136058988","https://openalex.org/W2144998751","https://openalex.org/W2151333238","https://openalex.org/W2151952022","https://openalex.org/W2158087462","https://openalex.org/W2160098476","https://openalex.org/W2164945803","https://openalex.org/W3017969408","https://openalex.org/W4237651079","https://openalex.org/W4254253404","https://openalex.org/W6633054997","https://openalex.org/W6633308500","https://openalex.org/W6674699788"],"related_works":["https://openalex.org/W2362269215","https://openalex.org/W1971506073","https://openalex.org/W148823471","https://openalex.org/W1778016906","https://openalex.org/W1554606847","https://openalex.org/W1571147990","https://openalex.org/W1617499594","https://openalex.org/W2354106728","https://openalex.org/W1582405267","https://openalex.org/W2117014006"],"abstract_inverted_index":{"Message-Passing":[0,12],"is":[1,15,72,96,138,149],"the":[2,16,48,83,110,116,142,159,162],"dominant":[3],"programming":[4],"model":[5],"for":[6,81],"distributed":[7],"memory":[8],"parallel":[9],"computers":[10],"and":[11,22,39,76,137,164,188],"Interface":[13],"(MPI)":[14],"standard.":[17],"Along":[18],"with":[19,141,178],"point-to-point":[20],"send":[21],"receive":[23],"message":[24],"primitives,":[25],"MPI":[26,147,198],"includes":[27],"a":[28,58,67,73,134,152,179,189],"set":[29],"of":[30,42,47,60,69,92,112,170],"collective":[31,51,101,199],"communication":[32,102],"operations":[33,200],"that":[34,97,195],"are":[35,104],"used":[36],"to":[37,107,115],"synchronize":[38],"coordinate":[40],"groups":[41],"tasks.":[43],"The":[44,94,118,129,168],"MPI_Barrier,":[45],"one":[46],"most":[49],"important":[50],"procedures,":[52],"has":[53],"been":[54],"extensively":[55],"studied":[56],"on":[57,123,183],"variety":[59],"architectures":[61],"over":[62],"last":[63],"twenty":[64],"years.":[65],"However,":[66],"cluster":[68,187],"Platform":[70],"FPGAs":[71,124],"new":[74],"architecture":[75],"offers":[77],"interesting,":[78],"resource-efficient":[79],"options":[80],"implementing":[82],"barrier":[84,98],"operation.":[85],"This":[86,156],"paper":[87],"describes":[88],"an":[89,185],"FPGA":[90,130,186],"implementation":[91,182],"MPI_Barrier.":[93],"premise":[95],"(and":[99],"other":[100,197],"operations)":[103],"very":[105],"sensitive":[106],"latency":[108],"as":[109],"number":[111],"nodes":[113],"scales":[114],"tens-of-thousands.":[117],"relatively":[119],"slow":[120],"processors":[121],"found":[122],"will":[125],"significantly":[126],"cap":[127],"performance.":[128],"hardware":[131,202],"design":[132,172],"implements":[133],"tree-based":[135],"algorithm":[136],"tightly":[139],"integrated":[140],"custom":[143],"high-speed":[144],"on-chip/off-chip":[145],"network.":[146],"access":[148],"available":[150],"through":[151],"specially-designed":[153],"kernel":[154],"module.":[155],"effectively":[157],"offloads":[158],"work":[160],"from":[161],"CPU":[163],"OS":[165],"into":[166,201],"hardware.":[167],"evaluation":[169],"this":[171],"shows":[173],"significant":[174],"performance":[175],"gains":[176],"compared":[177],"conventional":[180],"software":[181],"both":[184],"commodity":[190],"cluster.":[191],"Further,":[192],"it":[193],"suggests":[194],"moving":[196],"would":[203],"be":[204],"beneficial.":[205]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":6}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}