{"id":"https://openalex.org/W1591363587","doi":"https://doi.org/10.1109/ipdps.2003.1213135","title":"Efficient collective operations using remote memory operations on VIA-based clusters","display_name":"Efficient collective operations using remote memory operations on VIA-based clusters","publication_year":2004,"publication_date":"2004-03-22","ids":{"openalex":"https://openalex.org/W1591363587","doi":"https://doi.org/10.1109/ipdps.2003.1213135","mag":"1591363587"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2003.1213135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2003.1213135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings International Parallel and Distributed Processing Symposium","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/A5064308482","display_name":"Rakesh Gupta","orcid":"https://orcid.org/0000-0002-8134-2576"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"R. Gupta","raw_affiliation_strings":["Ohio State Uinversity, USA"],"affiliations":[{"raw_affiliation_string":"Ohio State Uinversity, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050531633","display_name":"Pavan Balaji","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"P. Balaji","raw_affiliation_strings":["Ohio State Uinversity, USA"],"affiliations":[{"raw_affiliation_string":"Ohio State Uinversity, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024879682","display_name":"Dhabaleswar K. Panda","orcid":"https://orcid.org/0000-0002-0356-1781"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"D.K. Panda","raw_affiliation_strings":["Ohio State Uinversity, USA"],"affiliations":[{"raw_affiliation_string":"Ohio State Uinversity, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047131679","display_name":"Jarek Nieplocha","orcid":null},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"J. Nieplocha","raw_affiliation_strings":["Pacific Northwest National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Laboratory, USA","institution_ids":["https://openalex.org/I142606810"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5064308482"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6409,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.88728958,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"9","last_page":"9"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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":0.9997000098228455,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9988999962806702,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/remote-direct-memory-access","display_name":"Remote direct memory access","score":0.9861202239990234},{"id":"https://openalex.org/keywords/infiniband","display_name":"InfiniBand","score":0.8834629058837891},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8593465089797974},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7028239369392395},{"id":"https://openalex.org/keywords/byte","display_name":"Byte","score":0.5665397047996521},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5590350031852722},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.49561989307403564},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.4953221380710602},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4546211361885071},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3927227556705475}],"concepts":[{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.9861202239990234},{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.8834629058837891},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8593465089797974},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7028239369392395},{"id":"https://openalex.org/C43364308","wikidata":"https://www.wikidata.org/wiki/Q8799","display_name":"Byte","level":2,"score":0.5665397047996521},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5590350031852722},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.49561989307403564},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4953221380710602},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4546211361885071},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3927227556705475},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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":4,"locations":[{"id":"doi:10.1109/ipdps.2003.1213135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2003.1213135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings International Parallel and Distributed Processing Symposium","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.75.27","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.75.27","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/~balaji/pubs/2003/ipdps/ipdps03.rdma_collectives.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.76.6488","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.76.6488","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nowlab.cse.ohio-state.edu/publications/conf-papers/2003/guptar-ipdps03.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.8.4834","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.8.4834","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ftp://ftp.cis.ohio-state.edu/pub/communication/papers/ipdps03-rdmacoll.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320306250","display_name":"Battelle","ror":"https://ror.org/01h5tnr73"},{"id":"https://openalex.org/F4320337380","display_name":"Division of Mathematical Sciences","ror":"https://ror.org/051fftw81"},{"id":"https://openalex.org/F4320338354","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1578322035","https://openalex.org/W2098246574","https://openalex.org/W2120110223","https://openalex.org/W6674699788"],"related_works":["https://openalex.org/W1978254186","https://openalex.org/W4245217724","https://openalex.org/W4390917331","https://openalex.org/W1984788566","https://openalex.org/W4253931064","https://openalex.org/W3166154920","https://openalex.org/W2154082760","https://openalex.org/W1964981582","https://openalex.org/W4282599985","https://openalex.org/W2139382794"],"abstract_inverted_index":{"High":[0],"performance":[1,79,204,216],"scientific":[2],"applications":[3],"require":[4],"efficient":[5],"and":[6,30,61,80,113,118,178,199,224,232],"fast":[7],"collective":[8,12,82,102],"communication":[9,13,103],"operations.":[10,38,83,122],"Most":[11],"operations":[14,40],"have":[15,111],"been":[16],"built":[17],"on":[18,141,183],"top":[19],"of":[20,98,108,130,172,205,218],"point-to-point":[21],"send/receive":[22],"primitives.":[23],"Modern":[24],"user-level":[25],"protocols":[26],"such":[27],"as":[28,154],"VIA":[29],"the":[31,49,57,70,89,96,115,119,155,161,165,189,203,237],"emerging":[32],"InfiniBand":[33],"architecture":[34],"support":[35],"remote":[36],"DMA":[37],"These":[39,211],"not":[41],"only":[42],"allow":[43,56],"data":[44,139],"to":[45,59,134,201],"be":[46,95],"moved":[47],"between":[48],"nodes":[50],"with":[51,164],"low":[52],"overhead":[53],"but":[54],"also":[55,147,193],"user":[58],"create":[60],"provide":[62],"a":[63,99,106,128,142,149,170,184,215],"logical":[64],"shared":[65],"memory":[66],"address":[67],"space":[68],"across":[69],"nodes.":[71],"This":[72],"feature":[73],"demonstrates":[74],"potential":[75],"for":[76,137,174,180,188,197,208,221,227,230,236],"designing":[77],"high":[78],"scalable":[81],"In":[84],"this":[85,206],"paper,":[86],"we":[87,110,126],"discuss":[88],"various":[90],"design":[91,207],"issues":[92],"that":[93],"may":[94],"basis":[97],"RDMA":[100,162],"supported":[101],"library.":[104],"As":[105],"proof":[107],"concept,":[109],"designed":[112],"implemented":[114],"RDMA-based":[116,120,124],"broadcast":[117,136,198],"allreduce":[121,190,200,238],"For":[123],"broadcast,":[125],"get":[127],"benefit":[129,171,217],"14%,":[131],"when":[132],"compared":[133],"send/receive-based":[135],"4KB":[138,181,228],"size":[140],"16":[143,185],"node":[144,186,234],"cluster.":[145],"We":[146,192],"introduce":[148,194],"new":[150,166],"reduce":[151,158,167],"algorithm":[152,168],"called":[153],"Degree-k":[156],"tree-based":[157],"algorithm.":[159],"Combining":[160],"mechanism":[163],"shows":[169],"38%":[173],"4":[175,222],"byte":[176],"messages":[177,182,229],"9%":[179],"cluster":[187],"operation.":[191,239],"analytical":[195,212],"models":[196,213],"predict":[202],"large-scale":[209],"clusters.":[210],"yield":[214],"about":[219],"35-40%":[220],"bytes":[223],"around":[225],"14%":[226],"512":[231],"1024":[233],"clusters":[235]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}