{"id":"https://openalex.org/W1989653583","doi":"https://doi.org/10.1109/dsn.2013.6575309","title":"An algorithmic approach to error localization and partial recomputation for low-overhead fault tolerance","display_name":"An algorithmic approach to error localization and partial recomputation for low-overhead fault tolerance","publication_year":2013,"publication_date":"2013-06-01","ids":{"openalex":"https://openalex.org/W1989653583","doi":"https://doi.org/10.1109/dsn.2013.6575309","mag":"1989653583"},"language":"en","primary_location":{"id":"doi:10.1109/dsn.2013.6575309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsn.2013.6575309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 43rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN)","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/A5112214609","display_name":"Joseph Sloan","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Joseph Sloan","raw_affiliation_strings":["University of Illinois, Urbana-Champaign, USA","University of Illinois Urbana-Champaign, Urbana, Il, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, Il, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067547869","display_name":"Rakesh Kumar","orcid":"https://orcid.org/0000-0002-3290-2629"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rakesh Kumar","raw_affiliation_strings":["University of Illinois, Urbana-Champaign, USA","University of Illinois Urbana-Champaign, Urbana, Il, USA"],"affiliations":[{"raw_affiliation_string":"University of Illinois, Urbana-Champaign, USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois Urbana-Champaign, Urbana, Il, USA","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111681485","display_name":"Greg Bronevetsky","orcid":null},"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":"Greg Bronevetsky","raw_affiliation_strings":["Lawrence Livermore National Laboratory, Livermore, CA, USA","Lawrence Livermore National Lab, Livermore, CA, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, CA, USA","institution_ids":["https://openalex.org/I1282311441"]},{"raw_affiliation_string":"Lawrence Livermore National Lab, Livermore, CA, USA#TAB#","institution_ids":["https://openalex.org/I1282311441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5112214609"],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":8.6709,"has_fulltext":false,"cited_by_count":45,"citation_normalized_percentile":{"value":0.97854951,"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":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9991999864578247,"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"}},"topics":[{"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9980999827384949,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9976999759674072,"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":0.8348746299743652},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6972028017044067},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6549223065376282},{"id":"https://openalex.org/keywords/rollback","display_name":"Rollback","score":0.6399855017662048},{"id":"https://openalex.org/keywords/error-detection-and-correction","display_name":"Error detection and correction","score":0.4884189963340759},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.46262145042419434},{"id":"https://openalex.org/keywords/massively-parallel","display_name":"Massively parallel","score":0.45824286341667175},{"id":"https://openalex.org/keywords/resilience","display_name":"Resilience (materials science)","score":0.45451661944389343},{"id":"https://openalex.org/keywords/mpsoc","display_name":"MPSoC","score":0.4542161226272583},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4343671202659607},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3516739010810852},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3359013795852661},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3077138364315033}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8348746299743652},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6972028017044067},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6549223065376282},{"id":"https://openalex.org/C174220543","wikidata":"https://www.wikidata.org/wiki/Q395307","display_name":"Rollback","level":3,"score":0.6399855017662048},{"id":"https://openalex.org/C103088060","wikidata":"https://www.wikidata.org/wiki/Q1062839","display_name":"Error detection and correction","level":2,"score":0.4884189963340759},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.46262145042419434},{"id":"https://openalex.org/C190475519","wikidata":"https://www.wikidata.org/wiki/Q544384","display_name":"Massively parallel","level":2,"score":0.45824286341667175},{"id":"https://openalex.org/C2779585090","wikidata":"https://www.wikidata.org/wiki/Q3457762","display_name":"Resilience (materials science)","level":2,"score":0.45451661944389343},{"id":"https://openalex.org/C2777187653","wikidata":"https://www.wikidata.org/wiki/Q975106","display_name":"MPSoC","level":3,"score":0.4542161226272583},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4343671202659607},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3516739010810852},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3359013795852661},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3077138364315033},{"id":"https://openalex.org/C4822641","wikidata":"https://www.wikidata.org/wiki/Q846651","display_name":"Multiprocessing","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C75949130","wikidata":"https://www.wikidata.org/wiki/Q848010","display_name":"Database transaction","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/dsn.2013.6575309","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dsn.2013.6575309","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 43rd Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.380.6410","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.380.6410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://passat.crhc.illinois.edu/rakeshk/dsn_13_cam.pdf","raw_type":"text"}],"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/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320338286","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1587026990","https://openalex.org/W1592673641","https://openalex.org/W1768849904","https://openalex.org/W1974635992","https://openalex.org/W1984564341","https://openalex.org/W1984840642","https://openalex.org/W1997021720","https://openalex.org/W2004675401","https://openalex.org/W2035080386","https://openalex.org/W2037523067","https://openalex.org/W2054141820","https://openalex.org/W2083613288","https://openalex.org/W2114035455","https://openalex.org/W2118582701","https://openalex.org/W2123475473","https://openalex.org/W2123728588","https://openalex.org/W2134864637","https://openalex.org/W2142843905","https://openalex.org/W2147078347","https://openalex.org/W2150679822","https://openalex.org/W2157593310","https://openalex.org/W2159161022","https://openalex.org/W2161551433","https://openalex.org/W2169596872","https://openalex.org/W2344962204","https://openalex.org/W2471965769","https://openalex.org/W3022806736","https://openalex.org/W3145311561","https://openalex.org/W4295109456"],"related_works":["https://openalex.org/W2075454349","https://openalex.org/W2145855242","https://openalex.org/W2010356481","https://openalex.org/W2016184125","https://openalex.org/W4236084769","https://openalex.org/W2621536082","https://openalex.org/W2152640076","https://openalex.org/W2103295733","https://openalex.org/W2536664151","https://openalex.org/W2116314988"],"abstract_inverted_index":{"The":[0,82],"increasing":[1],"size":[2],"and":[3,119,134,161,175,185,205],"complexity":[4],"of":[5,58,78,99,105,110,124,152,194],"massively":[6],"parallel":[7,218],"systems":[8],"(e.g.":[9],"HPC":[10],"systems)":[11],"is":[12,88,102,107],"making":[13],"it":[14,106,210],"increasingly":[15,32],"likely":[16],"that":[17,89,187,209],"individual":[18],"circuits":[19],"will":[20],"produce":[21],"erroneous":[22],"results.":[23,142],"For":[24],"this":[25,68,86,183,188],"reason,":[26],"novel":[27,73,127,168],"fault":[28,35],"tolerance":[29,36],"approaches":[30,37],"are":[31,47,65],"needed.":[33],"Prior":[34],"often":[38],"rely":[39],"on":[40,157],"checkpoint-rollback":[41],"based":[42],"schemes.":[43],"Unfortunately,":[44],"such":[45,59],"schemes":[46,60],"primarily":[48],"limited":[49],"to":[50,114,137,178,215,221],"rare":[51],"error":[52,93,132,201],"event":[53],"scenarios":[54,202],"as":[55],"the":[56,97,115,121,140,148,192,195,207],"overheads":[57],"become":[61],"prohibitive":[62],"if":[63,96],"faults":[64],"common.":[66],"In":[67],"paper,":[69],"we":[70],"propose":[71],"a":[72,167],"approach":[74,87,129,146,189],"for":[75,85,170],"algorithmic":[76,131,150],"correction":[77],"faulty":[79],"application":[80],"outputs.":[81],"key":[83],"insight":[84],"even":[90,95],"under":[91],"high":[92,200],"scenarios,":[94],"result":[98],"an":[100],"algorithm":[101],"erroneous,":[103],"most":[104,116],"correct.":[108],"Instead":[109],"simply":[111],"rolling":[112],"back":[113],"recent":[117],"checkpoint":[118],"repeating":[120],"entire":[122],"segment":[123],"computation,":[125],"our":[126,145],"resilience":[128],"uses":[130],"localization":[133],"partial":[135,180],"recomputation":[136,181],"efficiently":[138],"correct":[139],"corrupted":[141],"We":[143,165],"evaluate":[144],"in":[147,173,199],"specific":[149],"scenario":[151],"linear":[153,163],"algebra":[154],"operations,":[155],"focusing":[156],"matrix-vector":[158],"multiplication":[159],"(MVM)":[160],"iterative":[162],"solvers.":[164],"develop":[166],"technique":[169],"localizing":[171],"errors":[172],"MVM":[174],"show":[176],"how":[177],"achieve":[179],"within":[182],"algorithm,":[184],"demonstrate":[186],"both":[190],"improves":[191],"performance":[193],"Conjugate":[196],"Gradient":[197],"solver":[198],"by":[203,213],"3x-4x":[204],"increases":[206],"probability":[208],"completes":[211],"successfully":[212],"up":[214,220],"60%":[216],"with":[217],"experiments":[219],"100":[222],"nodes.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":11},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
