{"id":"https://openalex.org/W2008216781","doi":"https://doi.org/10.1145/2807591.2807617","title":"Fault tolerant MapReduce-MPI for HPC clusters","display_name":"Fault tolerant MapReduce-MPI for HPC clusters","publication_year":2015,"publication_date":"2015-10-27","ids":{"openalex":"https://openalex.org/W2008216781","doi":"https://doi.org/10.1145/2807591.2807617","mag":"2008216781"},"language":"en","primary_location":{"id":"doi:10.1145/2807591.2807617","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2807591.2807617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"type":"conference-paper","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/A5024620270","display_name":"Yanfei Guo","orcid":"https://orcid.org/0000-0002-3731-5423"},"institutions":[{"id":"https://openalex.org/I888729015","display_name":"University of Colorado Colorado Springs","ror":"https://ror.org/054spjc55","country_code":"US","type":"education","lineage":["https://openalex.org/I888729015"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanfei Guo","raw_affiliation_strings":["University of Colorado, Colorado Springs",", University of Colorado Colorado Springs#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Colorado, Colorado Springs","institution_ids":["https://openalex.org/I888729015"]},{"raw_affiliation_string":", University of Colorado Colorado Springs#TAB#","institution_ids":["https://openalex.org/I888729015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031869683","display_name":"Wesley Bland","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":"Wesley Bland","raw_affiliation_strings":["Argonne National Laboratory","argonne national laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"argonne national laboratory","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050531633","display_name":"Pavan Balaji","orcid":"https://orcid.org/0000-0002-9785-4461"},"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":"Pavan Balaji","raw_affiliation_strings":["Argonne National Laboratory","argonne national laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Argonne National Laboratory","institution_ids":["https://openalex.org/I1282105669"]},{"raw_affiliation_string":"argonne national laboratory","institution_ids":["https://openalex.org/I1282105669"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078528016","display_name":"Xiaobo Zhou","orcid":"https://orcid.org/0000-0002-0466-7609"},"institutions":[{"id":"https://openalex.org/I888729015","display_name":"University of Colorado Colorado Springs","ror":"https://ror.org/054spjc55","country_code":"US","type":"education","lineage":["https://openalex.org/I888729015"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaobo Zhou","raw_affiliation_strings":["University of Colorado, Colorado Springs",", University of Colorado Colorado Springs#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Colorado, Colorado Springs","institution_ids":["https://openalex.org/I888729015"]},{"raw_affiliation_string":", University of Colorado Colorado Springs#TAB#","institution_ids":["https://openalex.org/I888729015"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.0542,"has_fulltext":false,"cited_by_count":32,"citation_normalized_percentile":{"value":0.94832055,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9991999864578247,"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/T11181","display_name":"Advanced Data Storage Technologies","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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8817782402038574},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.8016914129257202},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.6253596544265747},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5975319743156433},{"id":"https://openalex.org/keywords/message-passing-interface","display_name":"Message Passing Interface","score":0.5879352688789368},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5615581274032593},{"id":"https://openalex.org/keywords/message-passing","display_name":"Message passing","score":0.5186131000518799},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5026171207427979},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.46411022543907166},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4577230215072632},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.39812374114990234}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8817782402038574},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.8016914129257202},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.6253596544265747},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5975319743156433},{"id":"https://openalex.org/C166782233","wikidata":"https://www.wikidata.org/wiki/Q127879","display_name":"Message Passing Interface","level":3,"score":0.5879352688789368},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5615581274032593},{"id":"https://openalex.org/C854659","wikidata":"https://www.wikidata.org/wiki/Q1859284","display_name":"Message passing","level":2,"score":0.5186131000518799},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5026171207427979},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.46411022543907166},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4577230215072632},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.39812374114990234},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2807591.2807617","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2807591.2807617","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.4399999976158142}],"awards":[{"id":"https://openalex.org/G102163711","display_name":null,"funder_award_id":"DE\u2010 AC02\u201006CH11357","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4450889261","display_name":null,"funder_award_id":"CNS-0844983, CNS-1217979, CNS-1422119","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"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":35,"referenced_works":["https://openalex.org/W167093911","https://openalex.org/W1420267637","https://openalex.org/W1471136644","https://openalex.org/W1575350781","https://openalex.org/W1576341769","https://openalex.org/W1582448188","https://openalex.org/W1590405911","https://openalex.org/W1884594015","https://openalex.org/W1939822385","https://openalex.org/W1981432246","https://openalex.org/W1984564341","https://openalex.org/W1997021720","https://openalex.org/W2001495258","https://openalex.org/W2002472616","https://openalex.org/W2025024269","https://openalex.org/W2029804882","https://openalex.org/W2038912880","https://openalex.org/W2049400253","https://openalex.org/W2082659044","https://openalex.org/W2089536264","https://openalex.org/W2094359896","https://openalex.org/W2096504919","https://openalex.org/W2100830825","https://openalex.org/W2105039796","https://openalex.org/W2107098536","https://openalex.org/W2131043098","https://openalex.org/W2140509629","https://openalex.org/W2147470852","https://openalex.org/W2151713271","https://openalex.org/W2155662278","https://openalex.org/W2166837162","https://openalex.org/W2173213060","https://openalex.org/W2205436351","https://openalex.org/W2396433687","https://openalex.org/W2730779250"],"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/W2082659044","https://openalex.org/W2411226825"],"abstract_inverted_index":{"Building":[0],"MapReduce":[1,39,55,69,111],"applications":[2],"using":[3],"the":[4,12,25,35,38,65,89,94,105,117,144],"Message-Passing":[5],"Interface":[6],"(MPI)":[7],"enables":[8],"us":[9],"to":[10,24,50,81,120],"exploit":[11],"performance":[13],"of":[14,27,97],"large":[15],"HPC":[16,44,58,74,134],"clusters":[17],"for":[18,57,73,108,123],"big":[19],"data":[20],"analytics.":[21],"However,":[22],"due":[23],"lacking":[26],"native":[28],"fault":[29,40,53,67,109,126],"tolerance":[30,41],"support":[31],"in":[32,112],"MPI":[33,72,91],"and":[34,43,62,85,93,103,142],"incompatibility":[36],"between":[37],"model":[42,107,119],"schedulers,":[45],"it":[46],"is":[47],"very":[48],"hard":[49],"provide":[51],"a":[52,78,132],"tolerant":[54,68,110],"runtime":[56],"clusters.":[59,75],"We":[60,76,101,114],"propose":[61],"develop":[63,104],"FT-MRMPI,":[64],"first":[66],"framework":[70],"on":[71,131],"discover":[77],"unique":[79],"way":[80],"perform":[82],"failure":[83,99],"detection":[84],"recovery":[86],"by":[87,148],"exploiting":[88],"current":[90],"semantics":[92],"new":[95],"proposal":[96],"user-level":[98],"mitigation.":[100],"design":[102],"checkpoint/restart":[106],"MPI.":[113],"further":[115],"tailor":[116],"detect/resume":[118],"conserve":[121],"work":[122],"more":[124],"efficient":[125],"tolerance.":[127],"The":[128],"experimental":[129],"results":[130],"256-node":[133],"cluster":[135],"show":[136],"that":[137],"FT-MRMPI":[138],"effectively":[139],"masks":[140],"failures":[141],"reduces":[143],"job":[145],"completion":[146],"time":[147],"39%.":[149]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1}],"updated_date":"2026-08-01T09:00:35.917206","created_date":"2025-10-10T00:00:00"}
