{"id":"https://openalex.org/W2745999522","doi":"https://doi.org/10.1145/3127024.3127037","title":"What does fault tolerant deep learning need from MPI?","display_name":"What does fault tolerant deep learning need from MPI?","publication_year":2017,"publication_date":"2017-08-24","ids":{"openalex":"https://openalex.org/W2745999522","doi":"https://doi.org/10.1145/3127024.3127037","mag":"2745999522"},"language":"en","primary_location":{"id":"doi:10.1145/3127024.3127037","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3127024.3127037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th 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/A5019702659","display_name":"Vinay Amatya","orcid":null},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vinay Amatya","raw_affiliation_strings":["Pacific Northwest National Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Lab","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009322871","display_name":"Abhinav Vishnu","orcid":"https://orcid.org/0000-0002-0593-4780"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abhinav Vishnu","raw_affiliation_strings":["Pacific Northwest National Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Lab","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058970517","display_name":"Charles Siegel","orcid":"https://orcid.org/0000-0001-6644-5764"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Charles Siegel","raw_affiliation_strings":["Pacific Northwest National Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Lab","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072118143","display_name":"Jeff Daily","orcid":"https://orcid.org/0000-0001-6212-5173"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeff Daily","raw_affiliation_strings":["Pacific Northwest National Lab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Lab","institution_ids":["https://openalex.org/I142606810"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5542,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.76191922,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9907000064849854,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9724000096321106,"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":0.8160771131515503},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.7741544842720032},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.7599215507507324},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5896028280258179},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5729082822799683},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5299402475357056},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5266349911689758},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5258303880691528},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4947225749492645},{"id":"https://openalex.org/keywords/software-fault-tolerance","display_name":"Software fault tolerance","score":0.4117283821105957},{"id":"https://openalex.org/keywords/software-engineering","display_name":"Software engineering","score":0.14837998151779175}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8160771131515503},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.7741544842720032},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.7599215507507324},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5896028280258179},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5729082822799683},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5299402475357056},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5266349911689758},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5258303880691528},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4947225749492645},{"id":"https://openalex.org/C50712370","wikidata":"https://www.wikidata.org/wiki/Q4269346","display_name":"Software fault tolerance","level":3,"score":0.4117283821105957},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.14837998151779175}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3127024.3127037","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3127024.3127037","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th European MPI Users' Group Meeting","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6499999761581421,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W778657980","https://openalex.org/W1442374986","https://openalex.org/W1493735863","https://openalex.org/W1548328233","https://openalex.org/W1549998098","https://openalex.org/W1598866093","https://openalex.org/W1606347560","https://openalex.org/W1867117070","https://openalex.org/W1906251618","https://openalex.org/W1934946603","https://openalex.org/W1983545421","https://openalex.org/W1997794724","https://openalex.org/W2008216781","https://openalex.org/W2063385859","https://openalex.org/W2082659044","https://openalex.org/W2097117768","https://openalex.org/W2112796928","https://openalex.org/W2116768598","https://openalex.org/W2117539524","https://openalex.org/W2119391823","https://openalex.org/W2125621954","https://openalex.org/W2130604611","https://openalex.org/W2132860930","https://openalex.org/W2133043855","https://openalex.org/W2139835701","https://openalex.org/W2142812297","https://openalex.org/W2155662278","https://openalex.org/W2155893237","https://openalex.org/W2161416813","https://openalex.org/W2163605009","https://openalex.org/W2168231600","https://openalex.org/W2170135819","https://openalex.org/W2181607856","https://openalex.org/W2186615578","https://openalex.org/W2198403777","https://openalex.org/W2204075824","https://openalex.org/W2287011250","https://openalex.org/W2339765813","https://openalex.org/W2340533753","https://openalex.org/W2345707736","https://openalex.org/W2477663446","https://openalex.org/W2521557683","https://openalex.org/W2526749411","https://openalex.org/W2527006803","https://openalex.org/W2528385196","https://openalex.org/W2538471976","https://openalex.org/W2580688187","https://openalex.org/W2582187633","https://openalex.org/W2618530766","https://openalex.org/W2622263826","https://openalex.org/W2724382637","https://openalex.org/W2950094539","https://openalex.org/W2962844195","https://openalex.org/W2962911728","https://openalex.org/W2963903325","https://openalex.org/W2964090591","https://openalex.org/W2964166868","https://openalex.org/W3118608800","https://openalex.org/W4302103866","https://openalex.org/W6636358008","https://openalex.org/W6674914833","https://openalex.org/W6684859321","https://openalex.org/W6687494587","https://openalex.org/W6696776605","https://openalex.org/W6704818120","https://openalex.org/W6727072144","https://openalex.org/W6728785192"],"related_works":["https://openalex.org/W2971479921","https://openalex.org/W3145923041","https://openalex.org/W2946906624","https://openalex.org/W841176518","https://openalex.org/W2101077206","https://openalex.org/W2157727563","https://openalex.org/W2470343202","https://openalex.org/W1978919910","https://openalex.org/W1488443159","https://openalex.org/W2343719514"],"abstract_inverted_index":{"Deep":[0],"Learning":[1,10,189],"(DL)":[2],"algorithms":[3,19,111],"have":[4],"become":[5,46],"the":[6,94,117,130,187,209,220,223],"de":[7],"facto":[8],"Machine":[9,188],"(ML)":[11],"algorithm":[12],"for":[13,76,89,96,119,145,156,191,202],"large":[14],"scale":[15],"data":[16,137,150],"analysis.":[17],"DL":[18,26,44,64,80,110,174,227],"are":[20],"computationally":[21],"expensive":[22],"--":[23,50],"even":[24],"distributed":[25,179],"implementations":[27],"which":[28,115],"use":[29],"MPI":[30,75,100,167],"require":[31],"days":[32],"of":[33,53,106,132,147,182,222],"training":[34],"(model":[35],"learning)":[36],"time":[37],"on":[38,129],"commonly":[39],"studied":[40],"datasets.":[41],"Long":[42],"running":[43],"applications":[45],"susceptible":[47],"to":[48,61,171],"faults":[49],"requiring":[51],"development":[52],"a":[54,97,140,178],"fault":[55,62,78,98,121,158,162,172,225],"tolerant":[56,63,79,99,173,226],"system":[57],"infrastructure,":[58],"in":[59,109,166],"addition":[60],"algorithms.":[65],"This":[66],"raises":[67],"an":[68,103,126],"important":[69],"question:":[70],"What":[71],"is":[72],"needed":[73],"from":[74],"designing":[77],"implementations?":[81],"In":[82],"this":[83,87],"paper,":[84],"we":[85],"address":[86],"problem":[88],"permanent":[90],"faults.":[91],"We":[92,124,176,195],"motivate":[93],"need":[95,118,141],"specification":[101],"by":[102,199],"in-depth":[104,127],"consideration":[105,155],"recent":[107],"innovations":[108],"and":[112,138,152,168,212,214],"their":[113,169],"properties,":[114],"drive":[116],"specific":[120],"tolerance":[122,159],"features.":[123],"present":[125],"discussion":[128],"suitability":[131],"different":[133],"parallelism":[134],"types":[135],"(model,":[136],"hybrid);":[139],"(or":[142],"lack":[143],"thereof)":[144],"check-pointing":[146],"any":[148],"critical":[149],"structures;":[151],"most":[153],"importantly,":[154],"several":[157],"proposals":[160],"(user-level":[161],"mitigation":[163],"(ULFM),":[164],"Reinit)":[165],"applicability":[170],"implementations.":[175],"leverage":[177],"memory":[180],"implementation":[181,228],"Caffe,":[183],"currently":[184],"available":[185],"under":[186],"Toolkit":[190],"Extreme":[192],"Scale":[193],"(MaTEx).":[194],"implement":[196],"our":[197],"approaches":[198],"extending":[200],"MaTEx-Caffe":[201],"using":[203,208,229],"ULFM-based":[204],"implementation.":[205],"Our":[206],"evaluation":[207],"ImageNet":[210],"dataset":[211],"AlexNet,":[213],"GoogLeNet":[215],"neural":[216],"network":[217],"topologies":[218],"demonstrates":[219],"effectiveness":[221],"proposed":[224],"OpenMPI":[230],"based":[231],"ULFM.":[232]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}