{"id":"https://openalex.org/W2084293824","doi":"https://doi.org/10.1145/2642769.2642775","title":"Evaluating User-Level Fault Tolerance for MPI Applications","display_name":"Evaluating User-Level Fault Tolerance for MPI Applications","publication_year":2014,"publication_date":"2014-08-29","ids":{"openalex":"https://openalex.org/W2084293824","doi":"https://doi.org/10.1145/2642769.2642775","mag":"2084293824"},"language":"en","primary_location":{"id":"doi:10.1145/2642769.2642775","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2642769.2642775","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st European MPI Users' Group Meeting","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/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":false,"raw_author_name":"Ignacio Laguna","raw_affiliation_strings":["Lawrence Livermore National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"last","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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory","institution_ids":["https://openalex.org/I1282311441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1282311441"],"apc_list":null,"apc_paid":null,"fwci":5.7591,"has_fulltext":false,"cited_by_count":37,"citation_normalized_percentile":{"value":0.96340492,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"57","last_page":"62"},"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":0.9968000054359436,"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":0.994700014591217,"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":0.8364229202270508},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.807811975479126},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.710552990436554},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5700873136520386},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5528481006622314},{"id":"https://openalex.org/keywords/user-interface","display_name":"User interface","score":0.5045372247695923},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.4893731474876404},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4696069657802582},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.3877267837524414},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.2678977847099304},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.221896231174469}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8364229202270508},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.807811975479126},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.710552990436554},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5700873136520386},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5528481006622314},{"id":"https://openalex.org/C89505385","wikidata":"https://www.wikidata.org/wiki/Q47146","display_name":"User interface","level":2,"score":0.5045372247695923},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.4893731474876404},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4696069657802582},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.3877267837524414},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2678977847099304},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.221896231174469},{"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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2642769.2642775","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2642769.2642775","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st European MPI Users' Group Meeting","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W163470805","https://openalex.org/W1576341769","https://openalex.org/W1661930086","https://openalex.org/W1939822385","https://openalex.org/W1967324265","https://openalex.org/W2021234574","https://openalex.org/W2079577430","https://openalex.org/W2082659044","https://openalex.org/W2132860930","https://openalex.org/W2140303949","https://openalex.org/W2145734880","https://openalex.org/W2159161022","https://openalex.org/W2990714382"],"related_works":["https://openalex.org/W2124048060","https://openalex.org/W1902983110","https://openalex.org/W2378910916","https://openalex.org/W4386915331","https://openalex.org/W2116006827","https://openalex.org/W2086666199","https://openalex.org/W1511717675","https://openalex.org/W2361929291","https://openalex.org/W1493716264","https://openalex.org/W2082659044"],"abstract_inverted_index":{"The":[0],"User":[1],"Level":[2],"Failure":[3],"Mitigation":[4],"(ULFM)":[5],"interface":[6,64],"has":[7,18],"been":[8],"proposed":[9],"to":[10,28,54,65],"provide":[11],"fault-tolerant":[12,67],"semantics":[13],"in":[14,45],"MPI.":[15],"Previous":[16],"work":[17],"presented":[19],"performance":[20],"evaluations":[21],"of":[22,62],"the":[23,58],"interface;":[24],"yet":[25],"questions":[26],"related":[27],"its":[29],"programability":[30],"and":[31,60],"applicability":[32],"remain":[33],"unanswered.":[34],"In":[35],"this":[36,63],"paper,":[37],"we":[38],"present":[39],"our":[40],"experiences":[41],"on":[42,57],"using":[43],"ULFM":[44,74],"a":[46],"case":[47],"study":[48],"(a":[49],"large":[50],"molecular":[51],"dynamics":[52],"application)":[53],"shed":[55],"light":[56],"advantages":[59],"difficulties":[61],"program":[66],"MPI":[68,94],"applications.":[69,95],"We":[70],"found":[71],"that,":[72],"although":[73],"is":[75],"suitable":[76],"for":[77,88],"applications":[78],"with":[79],"work-decomposition":[80],"flexibility":[81],"(e.g.,":[82,91],"master-slave),":[83],"it":[84],"provides":[85],"few":[86],"benefits":[87],"more":[89],"general":[90],"bulk":[92],"synchronous)":[93]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":6}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
