{"id":"https://openalex.org/W2040661203","doi":"https://doi.org/10.1145/2642769.2642776","title":"Comparing, Contrasting, Generalizing, and Integrating Two Current Designs for Fault-Tolerant MPI","display_name":"Comparing, Contrasting, Generalizing, and Integrating Two Current Designs for Fault-Tolerant MPI","publication_year":2014,"publication_date":"2014-08-29","ids":{"openalex":"https://openalex.org/W2040661203","doi":"https://doi.org/10.1145/2642769.2642776","mag":"2040661203"},"language":"en","primary_location":{"id":"doi:10.1145/2642769.2642776","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2642769.2642776","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/A5010796044","display_name":"Amin Hassani","orcid":null},"institutions":[{"id":"https://openalex.org/I32389192","display_name":"University of Alabama at Birmingham","ror":"https://ror.org/008s83205","country_code":"US","type":"education","lineage":["https://openalex.org/I32389192"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Amin Hassani","raw_affiliation_strings":["University of Alabama at Birmingham, CH 115, 1300 University Blvd Birmingham, AL, 35294"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alabama at Birmingham, CH 115, 1300 University Blvd Birmingham, AL, 35294","institution_ids":["https://openalex.org/I32389192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026440046","display_name":"Anthony Skjellum","orcid":"https://orcid.org/0000-0001-5252-6600"},"institutions":[{"id":"https://openalex.org/I82497590","display_name":"Auburn University","ror":"https://ror.org/02v80fc35","country_code":"US","type":"education","lineage":["https://openalex.org/I82497590"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anthony Skjellum","raw_affiliation_strings":["Auburn University, 3101 Shelby Center, Auburn, AL 36849","Auburn University, 3101 Shelby Center, Auburn, AL 36849#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Auburn University, 3101 Shelby Center, Auburn, AL 36849","institution_ids":["https://openalex.org/I82497590"]},{"raw_affiliation_string":"Auburn University, 3101 Shelby Center, Auburn, AL 36849#TAB#","institution_ids":["https://openalex.org/I82497590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036922303","display_name":"Ron Brightwell","orcid":"https://orcid.org/0009-0009-8186-222X"},"institutions":[{"id":"https://openalex.org/I192454743","display_name":"Sandia National Laboratories California","ror":"https://ror.org/058m7ey48","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1330989302","https://openalex.org/I192454743","https://openalex.org/I198811213","https://openalex.org/I198811213","https://openalex.org/I4210104735"]},{"id":"https://openalex.org/I4210104735","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210104735"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ron Brightwell","raw_affiliation_strings":["Sandia National Laboratories, PO Box 5800, Albuquerque, NM 87185-1319","Sandia National Laboratories, PO Box 5800, Albuquerque, NM 87185-1319#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sandia National Laboratories, PO Box 5800, Albuquerque, NM 87185-1319","institution_ids":["https://openalex.org/I4210104735"]},{"raw_affiliation_string":"Sandia National Laboratories, PO Box 5800, Albuquerque, NM 87185-1319#TAB#","institution_ids":["https://openalex.org/I192454743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084732782","display_name":"Purushotham Bangalore","orcid":"https://orcid.org/0000-0002-1098-9997"},"institutions":[{"id":"https://openalex.org/I32389192","display_name":"University of Alabama at Birmingham","ror":"https://ror.org/008s83205","country_code":"US","type":"education","lineage":["https://openalex.org/I32389192"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Purushotham V. Bangalore","raw_affiliation_strings":["University of Alabama at Birmingham, CH 130, 1300 University Blvd Birmingham, AL, 35294","University of Alabama at Birmingham, CH 130, 1300 University Blvd Birmingham, AL, 35294#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Alabama at Birmingham, CH 130, 1300 University Blvd Birmingham, AL, 35294","institution_ids":["https://openalex.org/I32389192"]},{"raw_affiliation_string":"University of Alabama at Birmingham, CH 130, 1300 University Blvd Birmingham, AL, 35294#TAB#","institution_ids":["https://openalex.org/I32389192"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3599,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66926103,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"63","last_page":"68"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.989300012588501,"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/T13471","display_name":"Cognitive Functions and Memory","score":0.989300012588501,"subfield":{"id":"https://openalex.org/subfields/3205","display_name":"Experimental and Cognitive Psychology"},"field":{"id":"https://openalex.org/fields/32","display_name":"Psychology"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8219190835952759},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.7748333811759949},{"id":"https://openalex.org/keywords/corollary","display_name":"Corollary","score":0.7533153295516968},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.727466344833374},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5501794815063477},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.492125928401947},{"id":"https://openalex.org/keywords/standardization","display_name":"Standardization","score":0.4827541708946228},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.44573286175727844},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15590384602546692},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.09851774573326111},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06334412097930908}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8219190835952759},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7748333811759949},{"id":"https://openalex.org/C2780012671","wikidata":"https://www.wikidata.org/wiki/Q1343870","display_name":"Corollary","level":2,"score":0.7533153295516968},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.727466344833374},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5501794815063477},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.492125928401947},{"id":"https://openalex.org/C188087704","wikidata":"https://www.wikidata.org/wiki/Q369577","display_name":"Standardization","level":2,"score":0.4827541708946228},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.44573286175727844},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15590384602546692},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.09851774573326111},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06334412097930908},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2642769.2642776","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2642769.2642776","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"},{"id":"https://openalex.org/F4320338291","display_name":"Sandia National Laboratories","ror":"https://ror.org/01apwpt12"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1551972236","https://openalex.org/W1878988619","https://openalex.org/W2023324599","https://openalex.org/W2035362408","https://openalex.org/W2037208432","https://openalex.org/W2068020713","https://openalex.org/W2128577831","https://openalex.org/W2133943294","https://openalex.org/W2142812297","https://openalex.org/W2730779250"],"related_works":["https://openalex.org/W2376029318","https://openalex.org/W2388301251","https://openalex.org/W2013770701","https://openalex.org/W3013941779","https://openalex.org/W1998659141","https://openalex.org/W3195376785","https://openalex.org/W2378767206","https://openalex.org/W1540871478","https://openalex.org/W328308450","https://openalex.org/W282641168"],"abstract_inverted_index":{"We":[0,23,41],"compare":[1],"and":[2,6,19,29,46],"contrast":[3],"the":[4,67],"approaches":[5],"key":[7],"features":[8],"of":[9,58,61,64,76],"two":[10],"proposals":[11],"for":[12,81],"fault-tolerant":[13],"MPI:":[14],"User-Level":[15],"Failure":[16],"Mitigation":[17],"(UFLM)":[18],"Fault-Aware":[20],"MPI":[21,88],"(FA-MPI).":[22],"show":[24,42],"how":[25,31,43],"they":[26,32],"are":[27,78],"complementary":[28],"also":[30],"could":[33],"leverage":[34],"each":[35,65,77],"other":[36,68],"through":[37],"modifications":[38],"and/or":[39],"extensions.":[40],"to":[44,49,66],"\"weaken\"":[45],"extend":[47],"ULFM":[48],"help":[50],"integrate":[51],"it":[52],"with":[53,55],"FA-MPI,":[54],"corollary":[56],"benefits":[57],"broadening":[59],"applicability":[60],"ULFM.":[62],"Reducibility":[63],"is":[69],"considered.":[70],"This":[71],"helps":[72],"identify":[73],"which":[74],"components":[75],"minimally":[79],"\"required\"":[80],"standardization,":[82],"versus":[83],"layerable":[84],"on":[85],"a":[86],"future":[87],"specification.":[89]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
