{"id":"https://openalex.org/W2008505510","doi":"https://doi.org/10.1145/1183401.1183433","title":"Scalable, fault tolerant membership for MPI tasks on HPC systems","display_name":"Scalable, fault tolerant membership for MPI tasks on HPC systems","publication_year":2006,"publication_date":"2006-06-28","ids":{"openalex":"https://openalex.org/W2008505510","doi":"https://doi.org/10.1145/1183401.1183433","mag":"2008505510"},"language":"en","primary_location":{"id":"doi:10.1145/1183401.1183433","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1183401.1183433","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th annual international conference on Supercomputing","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/A5069911834","display_name":"Jyothish Varma","orcid":null},"institutions":[{"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":"Jyothish Varma","raw_affiliation_strings":["North Carolina State University, Raleigh, NC","North Carolina State University, Raleigh, NC;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"North Carolina State University, Raleigh, NC;","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100407048","display_name":"Chao Wang","orcid":"https://orcid.org/0000-0002-8054-3472"},"institutions":[{"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":"Chao Wang","raw_affiliation_strings":["North Carolina State University, Raleigh, NC","North Carolina State University, Raleigh, NC;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"North Carolina State University, Raleigh, NC;","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031749427","display_name":"Frank Mueller","orcid":"https://orcid.org/0000-0002-0258-0294"},"institutions":[{"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":"Frank Mueller","raw_affiliation_strings":["North Carolina State University, Raleigh, NC","North Carolina State University, Raleigh, NC;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC","institution_ids":["https://openalex.org/I137902535"]},{"raw_affiliation_string":"North Carolina State University, Raleigh, NC;","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019453159","display_name":"Christian Engelmann","orcid":"https://orcid.org/0000-0003-4365-6416"},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christian Engelmann","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN","Oak Ridge National Laboratory, Oak Ridge, TN#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN#TAB#","institution_ids":["https://openalex.org/I1289243028"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109843869","display_name":"Stephen L. Scott","orcid":null},"institutions":[{"id":"https://openalex.org/I1289243028","display_name":"Oak Ridge National Laboratory","ror":"https://ror.org/01qz5mb56","country_code":"US","type":"facility","lineage":["https://openalex.org/I1289243028","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I4210159294"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen L. Scott","raw_affiliation_strings":["Oak Ridge National Laboratory, Oak Ridge, TN","Oak Ridge National Laboratory, Oak Ridge, TN#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN","institution_ids":["https://openalex.org/I1289243028"]},{"raw_affiliation_string":"Oak Ridge National Laboratory, Oak Ridge, TN#TAB#","institution_ids":["https://openalex.org/I1289243028"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9401,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.71997453,"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":"219","last_page":"228"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T10715","display_name":"Distributed and Parallel Computing Systems","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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9991999864578247,"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/computer-science","display_name":"Computer science","score":0.8773031234741211},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8218679428100586},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.744750440120697},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.607803463935852},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5967186689376831},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.5829891562461853},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5780755877494812},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.5656085014343262},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4555850923061371},{"id":"https://openalex.org/keywords/reliability","display_name":"Reliability (semiconductor)","score":0.4390066862106323},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.4309470057487488},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.2737017869949341},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.21348735690116882}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8773031234741211},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8218679428100586},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.744750440120697},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.607803463935852},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5967186689376831},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.5829891562461853},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5780755877494812},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.5656085014343262},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4555850923061371},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.4390066862106323},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.4309470057487488},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2737017869949341},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.21348735690116882},{"id":"https://openalex.org/C204787440","wikidata":"https://www.wikidata.org/wiki/Q188504","display_name":"Alternative medicine","level":2,"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/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","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},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/1183401.1183433","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1183401.1183433","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th annual international conference on Supercomputing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.422.2346","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.422.2346","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://moss.csc.ncsu.edu/~mueller/ftp/pub/mueller/papers/ipdps06.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.67.4456","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.67.4456","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://moss.csc.ncsu.edu/~mueller/ftp/pub/mueller/papers/ics06.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6100000143051147,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W4013337","https://openalex.org/W1482022028","https://openalex.org/W1498659283","https://openalex.org/W1500828634","https://openalex.org/W1576341769","https://openalex.org/W1577580543","https://openalex.org/W1579775238","https://openalex.org/W1825216778","https://openalex.org/W1869643030","https://openalex.org/W1963341458","https://openalex.org/W1971952282","https://openalex.org/W1986474696","https://openalex.org/W1993383198","https://openalex.org/W1997021720","https://openalex.org/W1997662655","https://openalex.org/W2045450417","https://openalex.org/W2045879521","https://openalex.org/W2046136445","https://openalex.org/W2046980086","https://openalex.org/W2047686393","https://openalex.org/W2064757275","https://openalex.org/W2077671984","https://openalex.org/W2081612620","https://openalex.org/W2091876663","https://openalex.org/W2102061396","https://openalex.org/W2105039796","https://openalex.org/W2108095339","https://openalex.org/W2110966151","https://openalex.org/W2114035455","https://openalex.org/W2130264930","https://openalex.org/W2133943294","https://openalex.org/W2141266148","https://openalex.org/W2145325071","https://openalex.org/W2164333096","https://openalex.org/W2165900899","https://openalex.org/W2166313409","https://openalex.org/W2168380557","https://openalex.org/W2171371822","https://openalex.org/W2171453084","https://openalex.org/W4285719527","https://openalex.org/W4300056088","https://openalex.org/W6600150046","https://openalex.org/W6643050054"],"related_works":["https://openalex.org/W3126131865","https://openalex.org/W2384867379","https://openalex.org/W4400094300","https://openalex.org/W2329539859","https://openalex.org/W4253186488","https://openalex.org/W2251285835","https://openalex.org/W1862835629","https://openalex.org/W2136799148","https://openalex.org/W2897533804","https://openalex.org/W2890506991"],"abstract_inverted_index":{"Reliability":[0],"is":[1,153],"increasingly":[2],"becoming":[3],"a":[4,61,75,81,139],"challenge":[5],"for":[6,107,155],"high-performance":[7],"computing":[8],"(HPC)":[9],"systems":[10],"with":[11],"thousands":[12],"of":[13,84,90,100,102,146,161],"nodes,":[14],"such":[15],"as":[16],"IBM's":[17],"Blue":[18],"Gene/L.":[19],"A":[20],"shorter":[21],"mean-time-to-failure":[22],"can":[23,40,121],"be":[24,122],"addressed":[25],"by":[26],"adding":[27],"fault":[28],"tolerance":[29],"to":[30,34,64,124,129],"reconfigure":[31],"working":[32],"nodes":[33,86],"ensure":[35],"that":[36,79],"communication":[37,68,159],"and":[38,50,104,114,165],"computation":[39],"progress.":[41],"However,":[42],"existing":[43],"approaches":[44],"fall":[45],"short":[46],"in":[47,87,97,157],"providing":[48],"scalability":[49,145],"small":[51],"recon":[52,65,108],"guration":[53,109],"overhead":[54],"within":[55],"the":[56,67,88,98,126,144,147,150,158],"fault-tolerant":[57],"layer.This":[58],"paper":[59],"contributes":[60],"scalable":[62],"approach":[63],"gure":[66],"infrastructure":[69],"after":[70],"node":[71],"failures.":[72],"We":[73,133],"propose":[74],"decentralized":[76],"(peer-to-peer)":[77],"protocol":[78,93,120],"maintains":[80],"consistent":[82],"view":[83],"active":[85],"presence":[89],"faults.":[91],"Our":[92],"shows":[94],"response":[95],"times":[96],"order":[99],"hundreds":[101],"microseconds":[103],"single-digit":[105],"milliseconds":[106],"using":[110],"MPI":[111,162],"over":[112,116],"BlueGene/L":[113],"TCP":[115],"Gigabit,":[117],"respectively.":[118],"The":[119],"adapted":[123],"match":[125],"network":[127],"topology":[128],"further":[130],"increase":[131],"performance.":[132],"also":[134],"verify":[135],"experimental":[136],"results":[137],"against":[138],"performance":[140],"model,":[141],"which":[142],"demonstrates":[143],"approach.":[148],"Hence,":[149],"membership":[151],"service":[152],"suitable":[154],"deployment":[156],"layer":[160],"runtime":[163],"systems,":[164],"we":[166],"have":[167],"integrated":[168],"an":[169],"early":[170],"version":[171],"into":[172],"LAM/MPI.":[173]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}
