{"id":"https://openalex.org/W2082659044","doi":"https://doi.org/10.1177/1094342004046045","title":"Fault Tolerance in Message Passing Interface Programs","display_name":"Fault Tolerance in Message Passing Interface Programs","publication_year":2004,"publication_date":"2004-08-01","ids":{"openalex":"https://openalex.org/W2082659044","doi":"https://doi.org/10.1177/1094342004046045","mag":"2082659044"},"language":"en","primary_location":{"id":"doi:10.1177/1094342004046045","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342004046045","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/A5017241944","display_name":"William Gropp","orcid":"https://orcid.org/0000-0003-2905-3029"},"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":true,"raw_author_name":"William Gropp","raw_affiliation_strings":["Mathematics and Computer Science Division Argonne National Laboratory\r                        Argonne, IL 60439, USA","Mathematics and Computer Science Division Argonne National Laboratory#R# Argonne, IL 60439, USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mathematics and Computer Science Division Argonne National Laboratory\r                        Argonne, IL 60439, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"Mathematics and Computer Science Division Argonne National Laboratory#R# Argonne, IL 60439, USA,","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078469358","display_name":"Ewing Lusk","orcid":null},"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":"Ewing Lusk","raw_affiliation_strings":["Mathematics and Computer Science Division Argonne National Laboratory\r                        Argonne, IL 60439, USA","Mathematics and Computer Science Division Argonne National Laboratory#R# Argonne, IL 60439, USA,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mathematics and Computer Science Division Argonne National Laboratory\r                        Argonne, IL 60439, USA","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"Mathematics and Computer Science Division Argonne National Laboratory#R# Argonne, IL 60439, USA,","institution_ids":["https://openalex.org/I1282105669"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5017241944"],"corresponding_institution_ids":["https://openalex.org/I1282105669"],"apc_list":null,"apc_paid":null,"fwci":3.9913,"has_fulltext":false,"cited_by_count":131,"citation_normalized_percentile":{"value":0.94247958,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"18","issue":"3","first_page":"363","last_page":"372"},"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":0.9993000030517578,"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":0.996399998664856,"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":0.8610378503799438},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.8332921862602234},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.7668095827102661},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.7250556945800781},{"id":"https://openalex.org/keywords/interface","display_name":"Interface (matter)","score":0.6007205247879028},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.5302286744117737},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4882962703704834},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.47635674476623535},{"id":"https://openalex.org/keywords/software-fault-tolerance","display_name":"Software fault tolerance","score":0.421223521232605},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4107837677001953},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3621678352355957}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8610378503799438},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.8332921862602234},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.7668095827102661},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.7250556945800781},{"id":"https://openalex.org/C113843644","wikidata":"https://www.wikidata.org/wiki/Q901882","display_name":"Interface (matter)","level":4,"score":0.6007205247879028},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.5302286744117737},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4882962703704834},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.47635674476623535},{"id":"https://openalex.org/C50712370","wikidata":"https://www.wikidata.org/wiki/Q4269346","display_name":"Software fault tolerance","level":3,"score":0.421223521232605},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4107837677001953},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3621678352355957},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C157915830","wikidata":"https://www.wikidata.org/wiki/Q2928001","display_name":"Bubble","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1177/1094342004046045","is_oa":false,"landing_page_url":"https://doi.org/10.1177/1094342004046045","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":[{"display_name":"Peace, Justice and strong institutions","id":"https://metadata.un.org/sdg/16","score":0.47999998927116394}],"awards":[],"funders":[{"id":"https://openalex.org/F4320308380","display_name":"Yale University","ror":"https://ror.org/03v76x132"},{"id":"https://openalex.org/F4320309626","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28"},{"id":"https://openalex.org/F4320310281","display_name":"Case Western Reserve University","ror":"https://ror.org/051fd9666"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"},{"id":"https://openalex.org/F4320338284","display_name":"Argonne National Laboratory","ror":"https://ror.org/05gvnxz63"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W31923072","https://openalex.org/W169659540","https://openalex.org/W1510543252","https://openalex.org/W1575350781","https://openalex.org/W1576341769","https://openalex.org/W1848988118","https://openalex.org/W2013639878","https://openalex.org/W2027938185","https://openalex.org/W2039765803","https://openalex.org/W2048894106","https://openalex.org/W2062377943","https://openalex.org/W2105039796","https://openalex.org/W2105227455","https://openalex.org/W2107581395","https://openalex.org/W2123669573","https://openalex.org/W2163755682","https://openalex.org/W2171453084","https://openalex.org/W2499905000","https://openalex.org/W2994762488","https://openalex.org/W4237868154","https://openalex.org/W4241975503","https://openalex.org/W4298266530"],"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/W91323585"],"abstract_inverted_index":{"In":[0],"this":[1,39],"paper":[2],"we":[3],"examine":[4],"the":[5,17,26,55],"topic":[6],"of":[7,19,46,78],"writing":[8,71],"fault-tolerant":[9],"Message":[10],"Passing":[11],"Interface":[12],"(MPI)":[13],"applications.":[14],"We":[15,34,58],"discuss":[16],"meaning":[18],"fault":[20,79],"tolerance":[21],"in":[22],"general":[23],"and":[24,53],"what":[25],"MPI":[27,48,51,56,64],"Standard":[28],"has":[29],"to":[30,38],"say":[31],"about":[32],"it.":[33],"survey":[35],"several":[36],"approaches":[37],"problem,":[40],"namely":[41],"checkpointing,":[42],"restructuring":[43],"a":[44,67],"class":[45],"standard":[47],"programs,":[49],"modifying":[50],"semantics,":[52],"extending":[54],"specification.":[57],"conclude":[59],"that,":[60],"within":[61],"certain":[62],"constraints,":[63],"can":[65],"provide":[66],"useful":[68],"context":[69],"for":[70],"application":[72],"programs":[73],"that":[74],"exhibit":[75],"significant":[76],"degrees":[77],"tolerance.":[80]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":11},{"year":2013,"cited_by_count":12},{"year":2012,"cited_by_count":12}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
