{"id":"https://openalex.org/W1591652341","doi":"https://doi.org/10.1109/ccgrid.2004.1336706","title":"An simple and efficient fault tolerance mechanism for divide-and-conquer systems","display_name":"An simple and efficient fault tolerance mechanism for divide-and-conquer systems","publication_year":2004,"publication_date":"2004-11-08","ids":{"openalex":"https://openalex.org/W1591652341","doi":"https://doi.org/10.1109/ccgrid.2004.1336706","mag":"1591652341"},"language":"en","primary_location":{"id":"doi:10.1109/ccgrid.2004.1336706","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccgrid.2004.1336706","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Symposium on Cluster Computing and the Grid, 2004. CCGrid 2004.","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/A5034343479","display_name":"Gosia Wrzesi\u00f1ska","orcid":null},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"G. Wrzesinska","raw_affiliation_strings":["Department of Mathematics and Computer Science, Vrije Universiteit Amsterdam, Amsterdam, Netherlands","Dept. of Math. & Comput. Sci., Vrije Universiteit Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, Vrije Universiteit Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I865915315"]},{"raw_affiliation_string":"Dept. of Math. & Comput. Sci., Vrije Universiteit Amsterdam, Netherlands","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063310768","display_name":"Rob V. van Nieuwpoort","orcid":"https://orcid.org/0000-0002-2947-9444"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"R.V. van Nieuwpoort","raw_affiliation_strings":["Department of Mathematics and Computer Science, Vrije Universiteit Amsterdam, Amsterdam, Netherlands","Dept. of Math. & Comput. Sci., Vrije Universiteit Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, Vrije Universiteit Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I865915315"]},{"raw_affiliation_string":"Dept. of Math. & Comput. Sci., Vrije Universiteit Amsterdam, Netherlands","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049957239","display_name":"Jason Maassen","orcid":"https://orcid.org/0000-0002-8172-4865"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"J. Maassen","raw_affiliation_strings":["Department of Mathematics and Computer Science, Vrije Universiteit Amsterdam, Amsterdam, Netherlands","Dept. of Math. & Comput. Sci., Vrije Universiteit Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, Vrije Universiteit Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I865915315"]},{"raw_affiliation_string":"Dept. of Math. & Comput. Sci., Vrije Universiteit Amsterdam, Netherlands","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5055231636","display_name":"Henri E. Bal","orcid":"https://orcid.org/0000-0001-9827-4461"},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"H.E. Bal","raw_affiliation_strings":["Department of Mathematics and Computer Science, Vrije Universiteit Amsterdam, Amsterdam, Netherlands","Dept. of Math. & Comput. Sci., Vrije Universiteit Amsterdam, Netherlands"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics and Computer Science, Vrije Universiteit Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I865915315"]},{"raw_affiliation_string":"Dept. of Math. & Comput. Sci., Vrije Universiteit Amsterdam, Netherlands","institution_ids":["https://openalex.org/I865915315"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5034343479"],"corresponding_institution_ids":["https://openalex.org/I865915315"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.11153982,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"735","last_page":"735"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing 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"}},"topics":[{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing 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":0.9958000183105469,"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":0.9940000176429749,"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":0.853459894657135},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6669803857803345},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6413363814353943},{"id":"https://openalex.org/keywords/divide-and-conquer-algorithms","display_name":"Divide and conquer algorithms","score":0.6127917766571045},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5523895025253296},{"id":"https://openalex.org/keywords/java","display_name":"Java","score":0.5234493613243103},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.47037047147750854},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.43564170598983765},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.4142690598964691},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2639888823032379},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11683964729309082}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.853459894657135},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6669803857803345},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6413363814353943},{"id":"https://openalex.org/C71559656","wikidata":"https://www.wikidata.org/wiki/Q671298","display_name":"Divide and conquer algorithms","level":2,"score":0.6127917766571045},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5523895025253296},{"id":"https://openalex.org/C548217200","wikidata":"https://www.wikidata.org/wiki/Q251","display_name":"Java","level":2,"score":0.5234493613243103},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.47037047147750854},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.43564170598983765},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.4142690598964691},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2639888823032379},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11683964729309082},{"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":1,"locations":[{"id":"doi:10.1109/ccgrid.2004.1336706","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccgrid.2004.1336706","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE International Symposium on Cluster Computing and the Grid, 2004. CCGrid 2004.","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":0,"referenced_works":[],"related_works":["https://openalex.org/W4247094814","https://openalex.org/W2384867379","https://openalex.org/W3214280620","https://openalex.org/W2329539859","https://openalex.org/W3191490922","https://openalex.org/W1862835629","https://openalex.org/W2099111379","https://openalex.org/W2136799148","https://openalex.org/W2897533804","https://openalex.org/W2890506991"],"abstract_inverted_index":{"Summary":[0],"form":[1],"only":[2],"given.":[3],"We":[4,41,130,201,273],"study":[5,26],"if":[6],"fault":[7,46,134,175,207],"tolerance":[8,47,135,176,208],"can":[9,72,102,116],"be":[10,74],"made":[11],"simpler":[12],"and":[13,33,173,310],"more":[14],"efficient":[15],"by":[16,59,260],"exploiting":[17],"the":[18,21,54,63,78,112,121,127,151,192,203,214,221,230,244,257,269,305,307],"structure":[19],"of":[20,56,62,80,86,93,105,120,150,157,205,213,224,234,243,247,256,276,282,304],"application.":[22],"More":[23],"specifically,":[24],"we":[25,227,264],"divide-and-conquer":[27,50,143],"parallelism,":[28],"which":[29,139],"is":[30,96,140,146,159,188,237],"a":[31,44,66,84,87,141,198,211,280],"popular":[32],"effective":[34],"paradigm":[35],"for":[36,49],"writing":[37],"parallel":[38,128,285],"Grid":[39],"applications.":[40],"have":[42,131],"designed":[43],"novel":[45],"mechanism":[48,95,101,136,236],"applications":[51,278],"that":[52,124,229,251],"reduces":[53],"amount":[55,79],"redundant":[57],"computation":[58],"storing":[60],"results":[61,71,242],"discarded":[64],"in":[65,137,161,182,295],"global":[67],"(replicated)":[68],"table.":[69],"These":[70],"later":[73],"reused,":[75],"thereby":[76],"minimizing":[77],"work":[81,258],"lost":[82],"as":[83],"result":[85],"crash.":[88],"The":[89,155,169,184,241],"execution":[90,231],"time":[91,232],"overhead":[92,233],"our":[94,133,174,206,225,235,248,252,277],"close":[97,238],"to":[98,194,239],"zero.":[99,240],"Our":[100],"handle":[103,118],"crashes":[104,119],"multiple":[106],"processors":[107],"or":[108],"entire":[109],"clusters":[110],"at":[111],"same":[113],"time..":[114],"It":[115],"also":[117,178],"root":[122],"node":[123],"initially":[125],"started":[126],"computation.":[129],"incorporated":[132],"Satin,":[138],"Java-based":[142],"system.":[144],"Satin":[145,170],"implemented":[147,160],"on":[148,197,210,268,279],"top":[149],"Ibis":[152,158],"communication":[153],"library.":[154],"core":[156],"pure":[162],"Java,":[163],"without":[164],"using":[165],"any":[166],"native":[167],"libraries.":[168],"runtime":[171],"system":[172,186],"extension":[177],"are":[179],"written":[180],"entirely":[181],"Java.":[183],"resulting":[185],"therefore":[187],"highly":[189],"portable":[190],"allowing":[191],"software":[193],"run":[195],"unmodified":[196],"heterogeneous":[199,284],"Grid.":[200],"evaluated":[202],"performance":[204],"scheme":[209],"cluster":[212],"Distributed":[215],"ASCI":[216],"Supercomputer":[217],"2":[218],"(DAS-2).":[219],"In":[220],"first":[222],"part":[223,246],"tests,":[226],"show":[228,250],"second":[245],"tests":[249,267],"algorithm":[253],"salvages":[254],"most":[255],"done":[259],"alive":[261],"processors.":[262],"Finally,":[263],"carried":[265],"out":[266],"European":[270,298],"GridLab":[271],"testbed.":[272],"ran":[274],"one":[275,303],"set":[281],"six":[283],"machines":[286],"(four":[287],"different":[288,292,297],"operating":[289],"systems,":[290],"four":[291,296],"architectures)":[293],"located":[294],"countries.":[299],"After":[300],"manually":[301],"killing":[302],"sites,":[306],"program":[308],"recovered":[309],"finished":[311],"normally.":[312]},"counts_by_year":[{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
