{"id":"https://openalex.org/W2081325203","doi":"https://doi.org/10.1109/cluster.2014.6968739","title":"Scalable replay with partial-order dependencies for message-logging fault tolerance","display_name":"Scalable replay with partial-order dependencies for message-logging fault tolerance","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W2081325203","doi":"https://doi.org/10.1109/cluster.2014.6968739","mag":"2081325203"},"language":"en","primary_location":{"id":"doi:10.1109/cluster.2014.6968739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2014.6968739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Cluster Computing (CLUSTER)","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/A5053556996","display_name":"Jonathan Lifflander","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":"Jonathan Lifflander","raw_affiliation_strings":["Department of Computer Science, University of Illinois Urbana-Champaign","Dept. of Computer Science, University of Illinois Urbana-Champaign, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"Dept. of Computer Science, University of Illinois Urbana-Champaign, USA#TAB#","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046704108","display_name":"Esteban Meneses","orcid":"https://orcid.org/0000-0002-4307-6000"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Esteban Meneses","raw_affiliation_strings":["Center for Simulation and Modeling, University of Pittsburgh","Center for Simulation and Modeling, University of Pittsburgh, USA"],"affiliations":[{"raw_affiliation_string":"Center for Simulation and Modeling, University of Pittsburgh","institution_ids":["https://openalex.org/I170201317"]},{"raw_affiliation_string":"Center for Simulation and Modeling, University of Pittsburgh, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038754571","display_name":"Harshitha Menon","orcid":"https://orcid.org/0000-0003-4707-9580"},"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":"Harshitha Menon","raw_affiliation_strings":["Department of Computer Science, University of Illinois at Urbana-Champaign","[Dept. of Computer Science, Univ. of Illinois at Urbana, Champaign, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"[Dept. of Computer Science, Univ. of Illinois at Urbana, Champaign, USA]","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022632017","display_name":"Phil Miller","orcid":"https://orcid.org/0000-0001-5772-3654"},"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":"Phil Miller","raw_affiliation_strings":["Department of Computer Science, University of Illinois at Urbana-Champaign","[Dept. of Computer Science, Univ. of Illinois at Urbana, Champaign, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"[Dept. of Computer Science, Univ. of Illinois at Urbana, Champaign, USA]","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006650430","display_name":"Sriram Krishnamoorthy","orcid":"https://orcid.org/0000-0002-4682-1002"},"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":"Sriram Krishnamoorthy","raw_affiliation_strings":["Advanced Computing Mathematics, and Data Division, Pacific Northwest National Laboratory","Advanced Computing, Mathematics, and Data Division, Pacific Northwest National Laboratory, USA"],"affiliations":[{"raw_affiliation_string":"Advanced Computing Mathematics, and Data Division, Pacific Northwest National Laboratory","institution_ids":["https://openalex.org/I142606810"]},{"raw_affiliation_string":"Advanced Computing, Mathematics, and Data Division, Pacific Northwest National Laboratory, USA","institution_ids":["https://openalex.org/I142606810"]}]},{"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":"Laxmikant V. Kale","raw_affiliation_strings":["Department of Computer Science, University of Illinois at Urbana-Champaign","[Dept. of Computer Science, Univ. of Illinois at Urbana, Champaign, USA]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"[Dept. of Computer Science, Univ. of Illinois at Urbana, Champaign, USA]","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5053556996"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":3.5971,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.93598271,"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":"19","last_page":"28"},"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":0.9994000196456909,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9986000061035156,"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/computer-science","display_name":"Computer science","score":0.8791249990463257},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7543928623199463},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7464520931243896},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6590501666069031},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.464275062084198},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.4575352966785431},{"id":"https://openalex.org/keywords/ibm","display_name":"IBM","score":0.44784560799598694},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4438537061214447},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.42235201597213745},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.35515832901000977},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1700230836868286}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8791249990463257},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7543928623199463},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7464520931243896},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6590501666069031},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.464275062084198},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.4575352966785431},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.44784560799598694},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4438537061214447},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.42235201597213745},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.35515832901000977},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1700230836868286},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","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},{"id":"https://openalex.org/C171250308","wikidata":"https://www.wikidata.org/wiki/Q11468","display_name":"Nanotechnology","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cluster.2014.6968739","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cluster.2014.6968739","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE International Conference on Cluster Computing (CLUSTER)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.645.2313","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.645.2313","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://charm.cs.illinois.edu/newPapers/14-21/paper.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7400000095367432,"id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1501526905","https://openalex.org/W1504603681","https://openalex.org/W1527754331","https://openalex.org/W1557738209","https://openalex.org/W1571225045","https://openalex.org/W1856717456","https://openalex.org/W1877496576","https://openalex.org/W1923313248","https://openalex.org/W2007840840","https://openalex.org/W2031260715","https://openalex.org/W2032493687","https://openalex.org/W2035137413","https://openalex.org/W2035726034","https://openalex.org/W2043013658","https://openalex.org/W2073720444","https://openalex.org/W2079577430","https://openalex.org/W2097891567","https://openalex.org/W2108078705","https://openalex.org/W2119530254","https://openalex.org/W2123500455","https://openalex.org/W2127747666","https://openalex.org/W2134533588","https://openalex.org/W2155204206","https://openalex.org/W2159949231","https://openalex.org/W2160779498","https://openalex.org/W2171483507","https://openalex.org/W2172139828","https://openalex.org/W3006359531","https://openalex.org/W3147005146","https://openalex.org/W4231805343"],"related_works":["https://openalex.org/W3126131865","https://openalex.org/W4253186488","https://openalex.org/W2064720525","https://openalex.org/W2111125783","https://openalex.org/W1862835629","https://openalex.org/W2136799148","https://openalex.org/W2897533804","https://openalex.org/W2890506991","https://openalex.org/W2082659044","https://openalex.org/W2811255748"],"abstract_inverted_index":{"Deterministic":[0],"replay":[1,61,111],"of":[2,30],"a":[3,16,27,81,124,161],"parallel":[4],"application":[5,72],"is":[6,35],"commonly":[7],"used":[8,52],"for":[9,128,140],"discovering":[10],"bugs":[11],"or":[12],"to":[13,53,73,88,115,135,168,177],"recover":[14],"from":[15],"hard":[17],"fault":[18,21,156],"with":[19,175],"message-logging":[20,155],"tolerance.":[22],"For":[23],"message":[24],"passing":[25],"programs,":[26],"major":[28],"source":[29],"overhead":[31],"during":[32,110],"forward":[33],"execution":[34,99,108],"recording":[36],"the":[37,56,68,92,98,131,137],"order":[38,83,109,139],"in":[39,60,77,91],"which":[40],"messages":[41],"are":[42,104],"sent":[43],"and":[44,71,101,143],"received.":[45],"During":[46],"replay,":[47],"this":[48,120,147],"ordering":[49,94],"must":[50,84],"be":[51,85,116],"deterministically":[54],"reproduce":[55],"execution.":[57],"Previous":[58],"work":[59],"algorithms":[62],"often":[63],"makes":[64],"minimal":[65],"assumptions":[66],"about":[67,130],"programming":[69],"model":[70],"maintain":[74],"generality.":[75],"However,":[76],"many":[78],"applications,":[79],"only":[80],"partial":[82,138],"recorded":[86],"due":[87],"determinism":[89],"intrinsic":[90],"program,":[93],"constraints":[95],"imposed":[96],"by":[97],"model,":[100],"events":[102],"that":[103,159],"commutative":[105],"(their":[106],"relative":[107],"does":[112],"not":[113],"need":[114],"reproduced":[117],"exactly).":[118],"In":[119],"paper,":[121],"we":[122,149],"present":[123],"novel":[125],"algebraic":[126],"framework":[127],"reasoning":[129],"minimum":[132],"dependencies":[133],"required":[134],"represent":[136],"different":[141],"orderings":[142],"interleavings.":[144],"By":[145],"exploiting":[146],"framework,":[148],"improve":[150],"on":[151,171],"an":[152,172],"existing":[153],"scalable":[154],"tolerance":[157],"scheme":[158,166],"uses":[160],"total":[162],"order.":[163],"The":[164],"improved":[165],"scales":[167],"131,072":[169],"cores":[170],"IBM":[173],"BlueGene/P":[174],"up":[176],"2\u00d7":[178],"lower":[179],"overhead.":[180]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
