{"id":"https://openalex.org/W2105227455","doi":"https://doi.org/10.1177/1094342004046052","title":"Building and Using a Fault-Tolerant MPI Implementation","display_name":"Building and Using a Fault-Tolerant MPI Implementation","publication_year":2004,"publication_date":"2004-08-01","ids":{"openalex":"https://openalex.org/W2105227455","doi":"https://doi.org/10.1177/1094342004046052","mag":"2105227455"},"language":"en","primary_location":{"id":"doi:10.1177/1094342004046052","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342004046052","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"]},{"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","US"],"is_corresponding":true,"raw_author_name":"Graham E. Fagg","raw_affiliation_strings":["High Performance Computing Center Stuttgart Allmandring 30, D-70550\r                        Stuttgart, Germany, Department of Computer Science, Suite 413, 1122\r                        Volunteer Blvd., University of Tennessee, Knoxville, TN 37996-3450, USA","High Performance Computing Center Stuttgart Allmandring 30, D-70550\r Stuttgart, Germany, Department of Computer Science, Suite 413, 1122\r Volunteer Blvd., University of Tennessee, Knoxville, TN 37996-3450, USA"],"affiliations":[{"raw_affiliation_string":"High Performance Computing Center Stuttgart Allmandring 30, D-70550\r                        Stuttgart, Germany, Department of Computer Science, Suite 413, 1122\r                        Volunteer Blvd., University of Tennessee, Knoxville, TN 37996-3450, USA","institution_ids":["https://openalex.org/I75027704","https://openalex.org/I100066346"]},{"raw_affiliation_string":"High Performance Computing Center Stuttgart Allmandring 30, D-70550\r Stuttgart, Germany, Department of Computer Science, Suite 413, 1122\r Volunteer Blvd., University of Tennessee, Knoxville, TN 37996-3450, USA","institution_ids":["https://openalex.org/I100066346","https://openalex.org/I75027704"]}]},{"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/I2802706902","display_name":"Knoxville College","ror":"https://ror.org/02bxrp522","country_code":"US","type":"education","lineage":["https://openalex.org/I2802706902"]},{"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":false,"raw_author_name":"Jack J. Dongarra","raw_affiliation_strings":["Department of Computer Science, Suite 413, 1122 Volunteer Blvd.,\r                        University of Tennessee, Knoxville, TN 37996-3450, USA","Department of Computer Science, Suite 413, 1122 Volunteer Blvd.,\r University of Tennessee, Knoxville, TN 37996-3450, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Suite 413, 1122 Volunteer Blvd.,\r                        University of Tennessee, Knoxville, TN 37996-3450, USA","institution_ids":["https://openalex.org/I75027704","https://openalex.org/I2802706902"]},{"raw_affiliation_string":"Department of Computer Science, Suite 413, 1122 Volunteer Blvd.,\r University of Tennessee, Knoxville, TN 37996-3450, USA","institution_ids":["https://openalex.org/I75027704"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5005256587"],"corresponding_institution_ids":["https://openalex.org/I100066346","https://openalex.org/I75027704"],"apc_list":null,"apc_paid":null,"fwci":4.2379,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.94615171,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"18","issue":"3","first_page":"353","last_page":"361"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9993000030517578,"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":0.9993000030517578,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9987999796867371,"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":0.9972000122070312,"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":0.8839312791824341},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7521562576293945},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.6042664051055908},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.490591436624527},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.46939462423324585},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.4271654486656189},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.40817540884017944},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3936882019042969}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8839312791824341},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7521562576293945},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.6042664051055908},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.490591436624527},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.46939462423324585},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.4271654486656189},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.40817540884017944},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3936882019042969}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1177/1094342004046052","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342004046052","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:CiteSeerX.psu:10.1.1.132.9090","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.132.9090","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://icl.cs.utk.edu/projectsfiles/sans/pubs/ft-semantics-lyon2002.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.137.2606","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.137.2606","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://hpc.sagepub.com/cgi/reprint/18/3/353.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.228.6596","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.228.6596","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.netlib.org/utk/people/JackDongarra/PAPERS/154_2004_building-and-using-a-fault-tolerant-mpi-implementation.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.421.8902","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.421.8902","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.netlib.org/utk/people/JackDongarra/PAPERS/ft-mpi-lyon-fagg.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W153115887","https://openalex.org/W1523826187","https://openalex.org/W1573548168","https://openalex.org/W1589918049","https://openalex.org/W1770291975","https://openalex.org/W2002452469","https://openalex.org/W2013639878","https://openalex.org/W2039088133","https://openalex.org/W2091257550","https://openalex.org/W2105039796","https://openalex.org/W2111374036","https://openalex.org/W2120211670","https://openalex.org/W2123669573","https://openalex.org/W2126071114","https://openalex.org/W2148979214","https://openalex.org/W2158479991","https://openalex.org/W2171453084","https://openalex.org/W2543535082","https://openalex.org/W4238260848","https://openalex.org/W4245503759"],"related_works":["https://openalex.org/W2978729728","https://openalex.org/W4288966080","https://openalex.org/W1530347314","https://openalex.org/W2510374584","https://openalex.org/W2098482419","https://openalex.org/W4254638342","https://openalex.org/W2054468904","https://openalex.org/W2082659044","https://openalex.org/W2811255748","https://openalex.org/W2171348457"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"discuss":[4],"the":[5,24,32,51,61,77,112],"design":[6],"and":[7,34,68],"use":[8,105],"of":[9,23,37,60,79,87],"a":[10,19,47,81],"fault-tolerant":[11,82],"MPI":[12,26,53,83,113],"(FT-MPI)":[13],"that":[14,22],"handles":[15,92],"process":[16,28],"failures":[17,38,93],"in":[18,85],"way":[20],"beyond":[21],"original":[25],"static":[27],"model.":[29],"FTMPI":[30],"allows":[31],"semantics":[33],"associated":[35],"modes":[36],"to":[39],"be":[40],"explicitly":[41],"controlled":[42],"by":[43],"an":[44,58,90],"application":[45],"via":[46],"modified":[48],"functionality":[49],"within":[50,111],"standard":[52],"1.2":[54],"API.":[55],"Given":[56],"is":[57,74],"overview":[59],"FT-MPI":[62],"semantics,":[63],"architecture":[64],"design,":[65],"example":[66],"usage":[67],"sample":[69],"applications.":[70],"A":[71],"short":[72],"discussion":[73],"given":[75],"on":[76],"consequences":[78],"designing":[80],"both":[84],"terms":[86],"how":[88,101],"such":[89],"implementation":[91],"at":[94],"multiple":[95],"levels":[96],"internally":[97],"as":[98,100],"well":[99],"existing":[102],"applications":[103],"can":[104],"new":[106],"features":[107],"while":[108],"still":[109],"remaining":[110],"standard.":[114]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
