{"id":"https://openalex.org/W2340533753","doi":"https://doi.org/10.1177/1094342015623623","title":"Evaluating and extending user-level fault tolerance in MPI applications","display_name":"Evaluating and extending user-level fault tolerance in MPI applications","publication_year":2016,"publication_date":"2016-01-13","ids":{"openalex":"https://openalex.org/W2340533753","doi":"https://doi.org/10.1177/1094342015623623","mag":"2340533753"},"language":"en","primary_location":{"id":"doi:10.1177/1094342015623623","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342015623623","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":"https://www.osti.gov/biblio/1342070","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5033868370","display_name":"Ignacio Laguna","orcid":"https://orcid.org/0000-0002-9374-4433"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Ignacio Laguna","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103099268","display_name":"David F. Richards","orcid":"https://orcid.org/0000-0003-2047-3780"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David F Richards","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007709486","display_name":"Todd Gamblin","orcid":"https://orcid.org/0000-0002-7857-2805"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Todd Gamblin","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045289712","display_name":"Martin Schulz","orcid":"https://orcid.org/0000-0001-9013-435X"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Martin Schulz","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058719424","display_name":"Bronis R. de Supinski","orcid":"https://orcid.org/0000-0002-0339-1006"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bronis R de Supinski","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080122988","display_name":"Kathryn Mohror","orcid":"https://orcid.org/0000-0002-1366-1655"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kathryn Mohror","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044867580","display_name":"Howard Pritchard","orcid":"https://orcid.org/0000-0003-1969-0403"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Howard Pritchard","raw_affiliation_strings":["Los Alamos National Laboratory, NM, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5033868370"],"corresponding_institution_ids":["https://openalex.org/I1282311441"],"apc_list":null,"apc_paid":null,"fwci":3.8389,"has_fulltext":false,"cited_by_count":43,"citation_normalized_percentile":{"value":0.93842674,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"30","issue":"3","first_page":"305","last_page":"319"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9998000264167786,"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/T10772","display_name":"Distributed systems and fault tolerance","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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9987000226974487,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9980000257492065,"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":0.8516995310783386},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.8009305000305176},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.7412429451942444},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7324255108833313},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.6199328899383545},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5646668076515198},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.5153002738952637},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.486189067363739},{"id":"https://openalex.org/keywords/rollback","display_name":"Rollback","score":0.4187275469303131},{"id":"https://openalex.org/keywords/software-fault-tolerance","display_name":"Software fault tolerance","score":0.41344618797302246},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.36408573389053345},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2051607370376587},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1367252767086029},{"id":"https://openalex.org/keywords/database-transaction","display_name":"Database transaction","score":0.06467601656913757}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8516995310783386},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.8009305000305176},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.7412429451942444},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7324255108833313},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.6199328899383545},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5646668076515198},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.5153002738952637},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.486189067363739},{"id":"https://openalex.org/C174220543","wikidata":"https://www.wikidata.org/wiki/Q395307","display_name":"Rollback","level":3,"score":0.4187275469303131},{"id":"https://openalex.org/C50712370","wikidata":"https://www.wikidata.org/wiki/Q4269346","display_name":"Software fault tolerance","level":3,"score":0.41344618797302246},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.36408573389053345},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2051607370376587},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1367252767086029},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.06467601656913757},{"id":"https://openalex.org/C129307140","wikidata":"https://www.wikidata.org/wiki/Q6795880","display_name":"Maximum bubble pressure method","level":3,"score":0.0},{"id":"https://openalex.org/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1177/1094342015623623","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342015623623","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:osti.gov:1342070","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1342070","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1342070","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1342070","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W63848143","https://openalex.org/W163470805","https://openalex.org/W1576341769","https://openalex.org/W1661930086","https://openalex.org/W1837653564","https://openalex.org/W1939822385","https://openalex.org/W1967324265","https://openalex.org/W2014780580","https://openalex.org/W2017060126","https://openalex.org/W2021234574","https://openalex.org/W2036641664","https://openalex.org/W2045879521","https://openalex.org/W2062900651","https://openalex.org/W2066533186","https://openalex.org/W2079577430","https://openalex.org/W2082659044","https://openalex.org/W2084293824","https://openalex.org/W2105524676","https://openalex.org/W2116115793","https://openalex.org/W2126071114","https://openalex.org/W2132860930","https://openalex.org/W2140303949","https://openalex.org/W2145734880","https://openalex.org/W2155662278","https://openalex.org/W2159161022"],"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/W2082659044","https://openalex.org/W91323585"],"abstract_inverted_index":{"The":[0],"user-level":[1],"failure":[2],"mitigation":[3],"(ULFM)":[4],"interface":[5,76,113],"has":[6],"been":[7],"proposed":[8],"to":[9,29,35,66,77],"provide":[10],"fault-tolerant":[11,79,112],"semantics":[12],"in":[13,52],"the":[14,70],"Message":[15],"Passing":[16],"Interface":[17],"(MPI).":[18],"Previous":[19],"work":[20],"presented":[21],"performance":[22],"evaluations":[23],"of":[24,74],"ULFM;":[25],"yet":[26],"questions":[27],"related":[28],"its":[30],"programability":[31],"and":[32,72,123],"applicability,":[33],"especially":[34],"non-trivial,":[36],"bulk":[37,61,99,116],"synchronous":[38,62,100,117],"applications,":[39,91],"remain":[40],"unanswered.":[41],"In":[42],"this":[43,75],"article,":[44],"we":[45,107],"present":[46],"our":[47],"experiences":[48],"on":[49,69],"using":[50],"ULFM":[51,86,126],"a":[53,57,109],"case":[54],"study":[55],"with":[56,120],"large,":[58],"highly":[59],"scalable,":[60],"molecular":[63],"dynamics":[64],"application":[65],"shed":[67],"light":[68],"advantages":[71],"difficulties":[73],"program":[78],"MPI":[80,101,118],"applications.":[81,102],"We":[82],"found":[83],"that,":[84],"although":[85],"is":[87],"suitable":[88],"for":[89,96,114,127],"master\u2013worker":[90],"it":[92],"provides":[93],"few":[94],"benefits":[95],"more":[97],"common":[98],"To":[103],"address":[104],"these":[105],"limitations,":[106],"introduce":[108],"new,":[110],"simpler":[111],"complex,":[115],"programs":[119],"better":[121],"applicability":[122],"support":[124],"than":[125],"application-level":[128],"recovery":[129],"mechanisms,":[130],"such":[131],"as":[132],"global":[133],"rollback.":[134]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
