{"id":"https://openalex.org/W2525254981","doi":"https://doi.org/10.1177/1094342016669416","title":"Unified fault-tolerance framework for hybrid task-parallel message-passing applications","display_name":"Unified fault-tolerance framework for hybrid task-parallel message-passing applications","publication_year":2016,"publication_date":"2016-09-26","ids":{"openalex":"https://openalex.org/W2525254981","doi":"https://doi.org/10.1177/1094342016669416","mag":"2525254981"},"language":"en","primary_location":{"id":"doi:10.1177/1094342016669416","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342016669416","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2117/90874","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5034946156","display_name":"Omer Subasi","orcid":"https://orcid.org/0000-0002-5373-7570"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Omer Subasi","raw_affiliation_strings":["Barcelona Supercomputing Center, Spain","Universitat Politecnica de Catalunya, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Spain","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"raw_affiliation_string":"Universitat Politecnica de Catalunya, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109908229","display_name":"Tatiana Martsinkevich","orcid":null},"institutions":[{"id":"https://openalex.org/I102197404","display_name":"Universit\u00e9 Paris-Sud","ror":"https://ror.org/028rypz17","country_code":"FR","type":"education","lineage":["https://openalex.org/I102197404"]},{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en sciences et technologies du num\u00e9rique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"government","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Tatiana Martsinkevich","raw_affiliation_strings":["INRIA, University of Paris Sud, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"INRIA, University of Paris Sud, France","institution_ids":["https://openalex.org/I102197404","https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024878985","display_name":"Ferad Zyulkyarov","orcid":"https://orcid.org/0000-0003-3139-7349"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Ferad Zyulkyarov","raw_affiliation_strings":["Barcelona Supercomputing Center, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Spain","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075162875","display_name":"Osman \u00dcnsal","orcid":"https://orcid.org/0000-0002-0544-9697"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Osman Unsal","raw_affiliation_strings":["Barcelona Supercomputing Center, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Spain","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035035680","display_name":"Jes\u00fas Labarta","orcid":"https://orcid.org/0000-0002-7489-4727"},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Jesus Labarta","raw_affiliation_strings":["Barcelona Supercomputing Center, Spain","Universitat Politecnica de Catalunya, Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center, Spain","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"raw_affiliation_string":"Universitat Politecnica de Catalunya, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046613458","display_name":"Franck Cappello","orcid":"https://orcid.org/0000-0002-7890-3934"},"institutions":[{"id":"https://openalex.org/I1282105669","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282105669","https://openalex.org/I1330989302","https://openalex.org/I39565521","https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Franck Cappello","raw_affiliation_strings":["Argonne National Laboratory, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory, USA","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5034946156"],"corresponding_institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":1.1397,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.84501414,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"32","issue":"5","first_page":"641","last_page":"657"},"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.9969000220298767,"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":0.8613088130950928},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7788407206535339},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.7274852395057678},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6867932081222534},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.6124703884124756},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5932367444038391},{"id":"https://openalex.org/keywords/protocol","display_name":"Protocol (science)","score":0.5918752551078796},{"id":"https://openalex.org/keywords/transient","display_name":"Transient (computer programming)","score":0.5774590373039246},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.5505134463310242},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.482530802488327},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.448871910572052},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12967175245285034}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8613088130950928},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7788407206535339},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.7274852395057678},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6867932081222534},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.6124703884124756},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5932367444038391},{"id":"https://openalex.org/C2780385302","wikidata":"https://www.wikidata.org/wiki/Q367158","display_name":"Protocol (science)","level":3,"score":0.5918752551078796},{"id":"https://openalex.org/C2780799671","wikidata":"https://www.wikidata.org/wiki/Q17087362","display_name":"Transient (computer programming)","level":2,"score":0.5774590373039246},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.5505134463310242},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.482530802488327},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.448871910572052},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12967175245285034},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"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/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1177/1094342016669416","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342016669416","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},{"id":"pmh:oai:dnet:upcommonspor::13837b09637b24b84931173dad4b5085","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/90874","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/submittedVersion"},{"id":"pmh:oai:upcommons.upc.edu:2117/90874","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/90874","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:dnet:upcommonspor::13837b09637b24b84931173dad4b5085","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/90874","pdf_url":null,"source":{"id":"https://openalex.org/S4306402641","display_name":"LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Cient\u00edficas)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4383465926","host_organization_name":"LA Referencia","host_organization_lineage":["https://openalex.org/I4383465926"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/submittedVersion"},"sustainable_development_goals":[{"score":0.6700000166893005,"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W23377417","https://openalex.org/W132161408","https://openalex.org/W1570414964","https://openalex.org/W1695243693","https://openalex.org/W1967925433","https://openalex.org/W1981432246","https://openalex.org/W1983959114","https://openalex.org/W1984564341","https://openalex.org/W1985713815","https://openalex.org/W1986905947","https://openalex.org/W1999776923","https://openalex.org/W2018430781","https://openalex.org/W2033656974","https://openalex.org/W2035492130","https://openalex.org/W2036432007","https://openalex.org/W2070638479","https://openalex.org/W2074626480","https://openalex.org/W2098631346","https://openalex.org/W2105524676","https://openalex.org/W2121575774","https://openalex.org/W2132835375","https://openalex.org/W2133046454","https://openalex.org/W2142677441","https://openalex.org/W2152705922","https://openalex.org/W2161537327","https://openalex.org/W2486668382","https://openalex.org/W3137220996","https://openalex.org/W3143778233","https://openalex.org/W4229701516","https://openalex.org/W4234514454","https://openalex.org/W4237517739","https://openalex.org/W4244600229","https://openalex.org/W4246310005","https://openalex.org/W4250644124","https://openalex.org/W4401212500"],"related_works":["https://openalex.org/W2124048060","https://openalex.org/W4386915331","https://openalex.org/W2378910916","https://openalex.org/W2116006827","https://openalex.org/W2361929291","https://openalex.org/W2086666199","https://openalex.org/W1997862718","https://openalex.org/W1511717675","https://openalex.org/W2185992486","https://openalex.org/W2082659044"],"abstract_inverted_index":{"We":[0,64,110],"present":[1],"a":[2,17,54,58,90],"unified":[3,125,142],"fault-tolerance":[4],"framework":[5],"for":[6,72,114],"task-parallel":[7],"message-passing":[8],"applications":[9],"to":[10,77,93,105],"mitigate":[11],"transient":[12],"errors.":[13],"First,":[14],"we":[15,47,88],"propose":[16],"fault-tolerant":[18,51],"message-logging":[19],"protocol":[20,79,99],"that":[21,29,49,67,130],"only":[22],"requires":[23],"the":[24,27,31,42,74,78,83,115,120,124,131,141],"restart":[25],"of":[26,62,85,123],"task":[28],"experienced":[30],"error":[32],"and":[33,97,119],"transparently":[34],"handles":[35],"any":[36],"message":[37],"passing":[38],"interface":[39],"calls":[40],"inside":[41],"task.":[43],"In":[44],"our":[45,50,98],"experiments":[46],"demonstrate":[48],"solution":[52],"has":[53],"reasonable":[55],"overhead,":[56],"with":[57,100,140],"maximum":[59],"observed":[60],"overhead":[61],"4.5%.":[63],"also":[65],"show":[66,129],"fine-grained":[68],"parallelization":[69],"is":[70],"important":[71],"hiding":[73],"overheads":[75],"related":[76],"as":[80,82,136,138],"well":[81],"recovery":[84],"tasks.":[86],"Secondly,":[87],"develop":[89],"mathematical":[91],"model":[92],"unify":[94],"task-level":[95],"checkpointing":[96,102,117],"system-wide":[101],"in":[103],"order":[104],"provide":[106,111],"complete":[107],"failure":[108],"coverage.":[109],"closed":[112],"formulas":[113],"optimal":[116],"interval":[118],"performance":[121,132],"score":[122],"scheme.":[126,143],"Experimental":[127],"results":[128],"improvement":[133],"can":[134],"be":[135],"high":[137],"98%":[139]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}