{"id":"https://openalex.org/W2165863720","doi":"https://doi.org/10.1177/1094342005056137","title":"Process Fault Tolerance: Semantics, Design and Applications for High Performance Computing","display_name":"Process Fault Tolerance: Semantics, Design and Applications for High Performance Computing","publication_year":2005,"publication_date":"2005-11-01","ids":{"openalex":"https://openalex.org/W2165863720","doi":"https://doi.org/10.1177/1094342005056137","mag":"2165863720"},"language":"en","primary_location":{"id":"doi:10.1177/1094342005056137","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342005056137","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":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005256587","display_name":"Graham E. Fagg","orcid":null},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Graham E. Fagg","raw_affiliation_strings":["INNOVATIVE COMPUTING LABORATORY, COMPUTER SCIENCE DEPARTMENT UNIVERSITY\r                        OF TENNESSEE, KNOXVILLE, TN 37996-3450, USA, ()"],"affiliations":[{"raw_affiliation_string":"INNOVATIVE COMPUTING LABORATORY, COMPUTER SCIENCE DEPARTMENT UNIVERSITY\r                        OF TENNESSEE, KNOXVILLE, TN 37996-3450, USA, ()","institution_ids":["https://openalex.org/I75027704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103111823","display_name":"Edgar Gabriel","orcid":"https://orcid.org/0000-0002-2541-1370"},"institutions":[{"id":"https://openalex.org/I31582689","display_name":"Stuttgart University of Applied Sciences","ror":"https://ror.org/039gdg280","country_code":"DE","type":"education","lineage":["https://openalex.org/I31582689"]},{"id":"https://openalex.org/I4210143490","display_name":"Computing Center","ror":"https://ror.org/0557kgc34","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210143490","https://openalex.org/I4210148470"]},{"id":"https://openalex.org/I100066346","display_name":"University of Stuttgart","ror":"https://ror.org/04vnq7t77","country_code":"DE","type":"education","lineage":["https://openalex.org/I100066346"]}],"countries":["DE","RU"],"is_corresponding":false,"raw_author_name":"Edgar Gabriel","raw_affiliation_strings":["HIGH PERFORMANCE COMPUTING CENTER STUTTGART, UNIVERSITY OF STUTTGART,\r                        D-70550 STUTTGART, GERMANY, AND INNOVATIVE COMPUTING LABORATORY, COMPUTER\r                        SCIENCE DEPARTMENT UNIVERSITY OF TENNESSEE, KNOXVILLE, TN 37996-3450, USA","HIGH PERFORMANCE COMPUTING CENTER STUTTGART, UNIVERSITY OF STUTTGART,\r D-70550 STUTTGART, GERMANY, AND INNOVATIVE COMPUTING LABORATORY, COMPUTER\r SCIENCE DEPARTMENT UNIVERSITY OF TENNESSEE, KNOXVILLE, TN 37996-3450, USA"],"affiliations":[{"raw_affiliation_string":"HIGH PERFORMANCE COMPUTING CENTER STUTTGART, UNIVERSITY OF STUTTGART,\r                        D-70550 STUTTGART, GERMANY, AND INNOVATIVE COMPUTING LABORATORY, COMPUTER\r                        SCIENCE DEPARTMENT UNIVERSITY OF TENNESSEE, KNOXVILLE, TN 37996-3450, USA","institution_ids":["https://openalex.org/I4210143490","https://openalex.org/I100066346","https://openalex.org/I31582689"]},{"raw_affiliation_string":"HIGH PERFORMANCE COMPUTING CENTER STUTTGART, UNIVERSITY OF STUTTGART,\r D-70550 STUTTGART, GERMANY, AND INNOVATIVE COMPUTING LABORATORY, COMPUTER\r SCIENCE DEPARTMENT UNIVERSITY OF TENNESSEE, KNOXVILLE, TN 37996-3450, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5061737717","display_name":"Zizhong Chen","orcid":"https://orcid.org/0000-0003-2578-4940"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zizhong Chen","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035177658","display_name":"Thara Angskun","orcid":"https://orcid.org/0000-0003-3677-8327"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thara Angskun","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010055736","display_name":"George Bosilca","orcid":"https://orcid.org/0000-0003-2411-8495"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"George Bosilca","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047741983","display_name":"Jelena Pje\u0161ivac\u2013Grbovi\u0107","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jelena Pjesivac-Grbovic","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5075517045","display_name":"Jack Dongarra","orcid":"https://orcid.org/0000-0003-3247-1782"},"institutions":[{"id":"https://openalex.org/I75027704","display_name":"University of Tennessee at Knoxville","ror":"https://ror.org/020f3ap87","country_code":"US","type":"education","lineage":["https://openalex.org/I75027704"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jack J. Dongarra","raw_affiliation_strings":["INNOVATIVE COMPUTING LABORATORY, COMPUTER SCIENCE DEPARTMENT UNIVERSITY\r                        OF TENNESSEE, KNOXVILLE, TN 37996-3450, USA, ()"],"affiliations":[{"raw_affiliation_string":"INNOVATIVE COMPUTING LABORATORY, COMPUTER SCIENCE DEPARTMENT UNIVERSITY\r                        OF TENNESSEE, KNOXVILLE, TN 37996-3450, USA, ()","institution_ids":["https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5005256587","https://openalex.org/A5075517045"],"corresponding_institution_ids":["https://openalex.org/I75027704"],"apc_list":null,"apc_paid":null,"fwci":6.2958,"has_fulltext":false,"cited_by_count":54,"citation_normalized_percentile":{"value":0.96825713,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"19","issue":"4","first_page":"465","last_page":"477"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":1.0,"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":1.0,"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":0.9998999834060669,"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/T10772","display_name":"Distributed systems and fault tolerance","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8538359999656677},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7970645427703857},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6555442810058594},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6015585660934448},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5958012342453003},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.5679349899291992},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5170936584472656},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5086823105812073},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.43316102027893066},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.43144404888153076},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.42828547954559326},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4249635338783264},{"id":"https://openalex.org/keywords/fault","display_name":"Fault (geology)","score":0.41301029920578003},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2884027361869812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8538359999656677},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7970645427703857},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6555442810058594},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6015585660934448},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5958012342453003},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.5679349899291992},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5170936584472656},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5086823105812073},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.43316102027893066},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.43144404888153076},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.42828547954559326},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4249635338783264},{"id":"https://openalex.org/C175551986","wikidata":"https://www.wikidata.org/wiki/Q47089","display_name":"Fault (geology)","level":2,"score":0.41301029920578003},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2884027361869812},{"id":"https://openalex.org/C165205528","wikidata":"https://www.wikidata.org/wiki/Q83371","display_name":"Seismology","level":1,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342005056137","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342005056137","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"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5400000214576721,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332169","display_name":"Directorate for Computer and Information Science and Engineering","ror":"https://ror.org/025kzpk63"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W21025594","https://openalex.org/W31923072","https://openalex.org/W80177976","https://openalex.org/W134816542","https://openalex.org/W169659540","https://openalex.org/W1492255554","https://openalex.org/W1575350781","https://openalex.org/W1825216778","https://openalex.org/W2013639878","https://openalex.org/W2039088133","https://openalex.org/W2045879521","https://openalex.org/W2081612620","https://openalex.org/W2105039796","https://openalex.org/W2123669573","https://openalex.org/W2126071114","https://openalex.org/W2158479991","https://openalex.org/W2163755682","https://openalex.org/W2171453084","https://openalex.org/W2994762488","https://openalex.org/W4233095313","https://openalex.org/W4245503759"],"related_works":["https://openalex.org/W1902983110","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/W2082659044"],"abstract_inverted_index":{"With":[0],"increasing":[1],"numbers":[2],"of":[3,25,45,49,87,92,109],"processors":[4],"on":[5],"current":[6],"machines,":[7],"the":[8,33,36,43,50,55,66,85,95,120],"probability":[9],"for":[10,29,58,122],"node":[11,72],"or":[12,73],"link":[13,74],"failures":[14],"is":[15,22],"also":[16],"increasing.":[17],"Therefore,":[18],"application-level":[19],"fault":[20],"tolerance":[21],"becoming":[23],"more":[24],"an":[26,90],"important":[27],"issue":[28],"both":[30],"end-users":[31],"and":[32,76],"institutions":[34],"running":[35],"machines.":[37],"In":[38],"this":[39],"paper":[40],"we":[41],"present":[42,84],"semantics":[44,96],"a":[46,71,80,110,125],"fault-tolerant":[47,88,111],"version":[48],"message":[51],"passing":[52],"interface":[53],"(MPI),":[54],"de-facto":[56],"standard":[57],"communication":[59],"in":[60,79],"scientific":[61],"applications,":[62],"which":[63],"gives":[64],"applications":[65],"possibility":[67],"to":[68],"recover":[69],"from":[70,124],"error":[75],"continue":[77],"execution":[78],"well-defined":[81],"way.":[82],"We":[83],"architecture":[86],"MPI,":[89],"implementation":[91],"MPI":[93],"using":[94],"presented":[97],"above":[98],"as":[99,101,117,119],"well":[100,118],"benchmark":[102],"results":[103,116],"with":[104],"various":[105],"applications.":[106],"An":[107],"example":[108],"parallel":[112],"equation":[113],"solver,":[114],"performance":[115],"time":[121],"recovering":[123],"process":[126],"failure":[127],"are":[128],"furthermore":[129],"detailed.":[130]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":3}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
