{"id":"https://openalex.org/W2048431618","doi":"https://doi.org/10.1109/ipdpsw.2010.5470856","title":"Designing high-performance and resilient message passing on InfiniBand","display_name":"Designing high-performance and resilient message passing on InfiniBand","publication_year":2010,"publication_date":"2010-04-01","ids":{"openalex":"https://openalex.org/W2048431618","doi":"https://doi.org/10.1109/ipdpsw.2010.5470856","mag":"2048431618"},"language":"en","primary_location":{"id":"doi:10.1109/ipdpsw.2010.5470856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2010.5470856","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":"conference-paper","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/A5033901219","display_name":"Matthew J. Koop","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matthew J. Koop","raw_affiliation_strings":["High Performance Technologies, Inc., USA","High Performance Technologies, Inc (HPTi), USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"High Performance Technologies, Inc., USA","institution_ids":[]},{"raw_affiliation_string":"High Performance Technologies, Inc (HPTi), USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071927802","display_name":"Pavel Shamis","orcid":null},"institutions":[{"id":"https://openalex.org/I458620863","display_name":"Mellanox Technologies (Israel)","ror":"https://ror.org/00gym2132","country_code":"IL","type":"company","lineage":["https://openalex.org/I4210088690","https://openalex.org/I458620863"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Pavel Shamis","raw_affiliation_strings":["Mellanox Technologies, Inc., Israel","Mellanox Technologies (Israel)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mellanox Technologies, Inc., Israel","institution_ids":["https://openalex.org/I458620863"]},{"raw_affiliation_string":"Mellanox Technologies (Israel)","institution_ids":["https://openalex.org/I458620863"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023517763","display_name":"Ishai Rabinovitz","orcid":null},"institutions":[{"id":"https://openalex.org/I458620863","display_name":"Mellanox Technologies (Israel)","ror":"https://ror.org/00gym2132","country_code":"IL","type":"company","lineage":["https://openalex.org/I4210088690","https://openalex.org/I458620863"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Ishai Rabinovitz","raw_affiliation_strings":["Mellanox Technologies, Inc., Israel","Mellanox Technologies (Israel)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mellanox Technologies, Inc., Israel","institution_ids":["https://openalex.org/I458620863"]},{"raw_affiliation_string":"Mellanox Technologies (Israel)","institution_ids":["https://openalex.org/I458620863"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024879682","display_name":"Dhabaleswar K. Panda","orcid":"https://orcid.org/0000-0002-0356-1781"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dhabaleswar K. Panda","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, USA","Department of Computer Science and Engineering, The Ohio State University, USA;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, USA;","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T10829","display_name":"Interconnection Networks and Systems","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"}},"topics":[{"id":"https://openalex.org/T10829","display_name":"Interconnection Networks and Systems","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/T10772","display_name":"Distributed systems and fault tolerance","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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9993000030517578,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/infiniband","display_name":"InfiniBand","score":0.9951703548431396},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8120540380477905},{"id":"https://openalex.org/keywords/remote-direct-memory-access","display_name":"Remote direct memory access","score":0.7079582810401917},{"id":"https://openalex.org/keywords/mean-time-between-failures","display_name":"Mean time between failures","score":0.6658195853233337},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.6106802225112915},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5569326877593994},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5134530663490295},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.5084342360496521},{"id":"https://openalex.org/keywords/interconnection","display_name":"Interconnection","score":0.4719711244106293},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.4543728530406952},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.4440305233001709},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.271589457988739},{"id":"https://openalex.org/keywords/reliability-engineering","display_name":"Reliability engineering","score":0.253928005695343},{"id":"https://openalex.org/keywords/failure-rate","display_name":"Failure rate","score":0.22909194231033325},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08720332384109497}],"concepts":[{"id":"https://openalex.org/C2781030343","wikidata":"https://www.wikidata.org/wiki/Q922437","display_name":"InfiniBand","level":2,"score":0.9951703548431396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8120540380477905},{"id":"https://openalex.org/C130795937","wikidata":"https://www.wikidata.org/wiki/Q2561570","display_name":"Remote direct memory access","level":2,"score":0.7079582810401917},{"id":"https://openalex.org/C44154001","wikidata":"https://www.wikidata.org/wiki/Q754940","display_name":"Mean time between failures","level":3,"score":0.6658195853233337},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.6106802225112915},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5569326877593994},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5134530663490295},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.5084342360496521},{"id":"https://openalex.org/C123745756","wikidata":"https://www.wikidata.org/wiki/Q1665949","display_name":"Interconnection","level":2,"score":0.4719711244106293},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.4543728530406952},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.4440305233001709},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.271589457988739},{"id":"https://openalex.org/C200601418","wikidata":"https://www.wikidata.org/wiki/Q2193887","display_name":"Reliability engineering","level":1,"score":0.253928005695343},{"id":"https://openalex.org/C163164238","wikidata":"https://www.wikidata.org/wiki/Q2737027","display_name":"Failure rate","level":2,"score":0.22909194231033325},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08720332384109497},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdpsw.2010.5470856","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdpsw.2010.5470856","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"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W21025594","https://openalex.org/W1506581116","https://openalex.org/W1575350781","https://openalex.org/W1825216778","https://openalex.org/W1986669688","https://openalex.org/W2018501701","https://openalex.org/W2082490936","https://openalex.org/W2167890759","https://openalex.org/W4234395696","https://openalex.org/W6638601623","https://openalex.org/W6684721908"],"related_works":["https://openalex.org/W1978254186","https://openalex.org/W4245217724","https://openalex.org/W4390917331","https://openalex.org/W4253931064","https://openalex.org/W1984788566","https://openalex.org/W3166154920","https://openalex.org/W2154082760","https://openalex.org/W1964981582","https://openalex.org/W4282599985","https://openalex.org/W2751263050"],"abstract_inverted_index":{"Clusters":[0],"featuring":[1],"the":[2,12,16,43,51,61,73,80,92,111,121,124,172,175],"InfiniBand":[3,29,49,125],"interconnect":[4],"are":[5,46,104],"continuing":[6],"to":[7,59,72,106,159],"scale.":[8],"As":[9,55],"an":[10],"example,":[11],"\u00bfRanger\u00bf":[13],"system":[14],"at":[15],"Texas":[17],"Advanced":[18],"Computing":[19],"Center":[20],"(TACC)":[21],"includes":[22],"over":[23,40],"60,000":[24],"cores":[25],"with":[26],"nearly":[27],"4,000":[28],"ports.":[30],"The":[31],"latest":[32],"Top500":[33],"list":[34],"shows":[35,166],"30%":[36],"of":[37,42,76,95,101,113,150,161],"systems":[38,57],"and":[39,66,143,153,174],"50%":[41],"top":[44],"100":[45],"now":[47],"using":[48,137],"as":[50,116,118],"compute":[52],"node":[53],"interconnect.":[54],"these":[56],"continue":[58],"scale,":[60],"Mean-Time-Between-Failure":[62],"(MTBF)":[63],"is":[64,157],"reducing":[65],"additional":[67],"resiliency":[68],"must":[69],"be":[70],"provided":[71],"important":[74],"components":[75],"HPC":[77],"systems,":[78],"including":[79],"MPI":[81],"library.":[82],"In":[83],"this":[84],"paper":[85],"we":[86,168],"present":[87],"a":[88,99,148,162],"design":[89,152],"that":[90,155,160,167],"leverages":[91],"reliability":[93,132,177],"semantics":[94],"InfiniBand,":[96],"but":[97],"provides":[98],"higher-level":[100],"resiliency.":[102],"We":[103,130,146],"able":[105],"avoid":[107],"aborting":[108],"jobs":[109],"in":[110,123],"case":[112],"network":[114,176],"failures":[115,119],"well":[117],"on":[120],"endpoints":[122],"Host":[126],"Channel":[127],"Adapters":[128],"(HCA).":[129],"propose":[131],"designs":[133,136],"for":[134,179],"rendezvous":[135],"both":[138,171],"Remote":[139],"DMA":[140],"(RDMA)":[141],"read":[142],"write":[144],"operations.":[145],"implement":[147],"prototype":[149],"our":[151],"show":[154],"performance":[156,173],"near-identical":[158],"non-resilient":[163],"design.":[164],"This":[165],"can":[169],"have":[170],"needed":[178],"large-scale":[180],"systems.":[181]},"counts_by_year":[{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
