{"id":"https://openalex.org/W2149480830","doi":"https://doi.org/10.1109/ipdps.2004.1303244","title":"A fault tolerant protocol for massively parallel systems","display_name":"A fault tolerant protocol for massively parallel systems","publication_year":2004,"publication_date":"2004-06-10","ids":{"openalex":"https://openalex.org/W2149480830","doi":"https://doi.org/10.1109/ipdps.2004.1303244","mag":"2149480830"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2004.1303244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2004.1303244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th International Parallel and Distributed Processing Symposium, 2004. Proceedings.","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/A5079269181","display_name":"Sayantan Chakravorty","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"S. Chakravorty","raw_affiliation_strings":["Department of Computer Science, University of Illinois, Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051465480","display_name":"Laxmikant V. Kal\u00e9","orcid":"https://orcid.org/0000-0001-9673-8445"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"L.V. Kale","raw_affiliation_strings":["Department of Computer Science, University of Illinois, Urbana-Champaign, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5079269181"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":5.0986,"has_fulltext":false,"cited_by_count":38,"citation_normalized_percentile":{"value":0.95828726,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"212","last_page":"219"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998999834060669,"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/T10772","display_name":"Distributed systems and fault tolerance","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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9983999729156494,"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":0.9977999925613403,"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":0.812080979347229},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7642824053764343},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6225906610488892},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5514013171195984},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5091091990470886},{"id":"https://openalex.org/keywords/virtual-machine","display_name":"Virtual machine","score":0.48920655250549316},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.47840437293052673},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.4581443965435028},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4272952079772949},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.39772093296051025},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.22834569215774536}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.812080979347229},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7642824053764343},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6225906610488892},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5514013171195984},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5091091990470886},{"id":"https://openalex.org/C25344961","wikidata":"https://www.wikidata.org/wiki/Q192726","display_name":"Virtual machine","level":2,"score":0.48920655250549316},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.47840437293052673},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.4581443965435028},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4272952079772949},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.39772093296051025},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.22834569215774536},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipdps.2004.1303244","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2004.1303244","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"18th International Parallel and Distributed Processing Symposium, 2004. Proceedings.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W34870269","https://openalex.org/W1493349449","https://openalex.org/W1506585574","https://openalex.org/W1576341769","https://openalex.org/W1675633711","https://openalex.org/W1923741182","https://openalex.org/W2052915895","https://openalex.org/W2081409107","https://openalex.org/W2081413727","https://openalex.org/W2100970777","https://openalex.org/W2105039796","https://openalex.org/W2109739361","https://openalex.org/W2114035455","https://openalex.org/W2118832215","https://openalex.org/W2126071114","https://openalex.org/W2131053137","https://openalex.org/W2133553843","https://openalex.org/W2150412589","https://openalex.org/W2160123909","https://openalex.org/W2170163131","https://openalex.org/W2171453084","https://openalex.org/W3022806736","https://openalex.org/W4237816542","https://openalex.org/W4239059712","https://openalex.org/W6601359364","https://openalex.org/W6634580932","https://openalex.org/W6637213917","https://openalex.org/W6681906569","https://openalex.org/W6818786110"],"related_works":["https://openalex.org/W1970433854","https://openalex.org/W2023867642","https://openalex.org/W1905852083","https://openalex.org/W113996306","https://openalex.org/W81589881","https://openalex.org/W4386582991","https://openalex.org/W1862835629","https://openalex.org/W2136799148","https://openalex.org/W2897533804","https://openalex.org/W2890506991"],"abstract_inverted_index":{"Summary":[0],"form":[1],"only":[2,69],"given.":[3],"As":[4],"parallel":[5],"machines":[6,18],"grow":[7],"larger,":[8],"the":[9,16,40,48,60,90,128,153,165],"mean":[10],"time":[11,161],"between":[12],"failure":[13],"shrinks.":[14],"With":[15],"planned":[17],"of":[19,33],"near":[20],"future,":[21],"therefore,":[22],"fault":[23,82,159],"tolerance":[24,83],"will":[25],"become":[26],"an":[27,65],"important":[28],"issue.":[29],"The":[30,115],"traditional":[31],"method":[32],"dealing":[34],"with":[35],"faults":[36],"is":[37,139],"to":[38,45,62,64,123,157],"checkpoint":[39],"entire":[41],"application":[42],"periodically":[43],"and":[44,99,131,143],"start":[46],"from":[47,103],"last":[49],"checkpoint.":[50],"However,":[51],"such":[52],"a":[53,79,100],"strategy":[54],"wastes":[55],"resources":[56],"by":[57,109,163],"requiring":[58],"all":[59],"processors":[61,110],"revert":[63],"earlier":[66],"state,":[67],"whereas":[68],"one":[70],"processor":[71,148],"has":[72,155],"lost":[73],"its":[74],"current":[75],"state.":[76],"We":[77,126],"present":[78,127],"scheme":[80,116,130,154],"for":[81],"that":[84,111],"aims":[85],"at":[86],"low":[87],"overhead":[88],"on":[89,134,141],"forward":[91],"path":[92],"(i.e.":[93],"when":[94],"there":[95],"are":[96],"no":[97],"failures)":[98],"fast":[101],"recovery":[102,160],"faults,":[104],"without":[105],"wasting":[106],"computation":[107],"done":[108],"have":[112],"not":[113,118],"faulted.":[114],"does":[117],"require":[119],"any":[120],"individual":[121],"component":[122],"be":[124],"fault-free.":[125],"basic":[129],"performance":[132],"data":[133],"small":[135],"clusters.":[136],"Since":[137],"it":[138],"based":[140],"Charm++":[142],"Adaptive":[144],"MPI,":[145],"where":[146],"each":[147],"houses":[149],"several":[150],"virtual":[151,167],"processors,":[152],"potential":[156],"reduce":[158],"significantly,":[162],"migrating":[164],"recovering":[166],"processors.":[168]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
