{"id":"https://openalex.org/W2052455844","doi":"https://doi.org/10.1109/tpds.2014.2320502","title":"Fail-Stop Failure Algorithm-Based Fault Tolerance for Cholesky Decomposition","display_name":"Fail-Stop Failure Algorithm-Based Fault Tolerance for Cholesky Decomposition","publication_year":2014,"publication_date":"2014-04-25","ids":{"openalex":"https://openalex.org/W2052455844","doi":"https://doi.org/10.1109/tpds.2014.2320502","mag":"2052455844"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2014.2320502","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2014.2320502","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","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/A5078501431","display_name":"Doug Hakkarinen","orcid":null},"institutions":[{"id":"https://openalex.org/I167576493","display_name":"Colorado School of Mines","ror":"https://ror.org/04raf6v53","country_code":"US","type":"education","lineage":["https://openalex.org/I167576493"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Doug Hakkarinen","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Colorado School of Mines, Golden, CO","[Dept. of Electrical Engineering and Computer Science, Colorado School of Mines, Golden, CO]"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Colorado School of Mines, Golden, CO","institution_ids":["https://openalex.org/I167576493"]},{"raw_affiliation_string":"[Dept. of Electrical Engineering and Computer Science, Colorado School of Mines, Golden, CO]","institution_ids":["https://openalex.org/I167576493"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020822198","display_name":"Panruo Wu","orcid":"https://orcid.org/0000-0003-1859-3580"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Panruo Wu","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California, Riverside, CA","Department of Computer Science and Engineering, University of California, Riverside, CA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California, Riverside, CA","institution_ids":["https://openalex.org/I103635307"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California, Riverside, CA#TAB#","institution_ids":["https://openalex.org/I103635307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061737717","display_name":"Zizhong Chen","orcid":"https://orcid.org/0000-0003-2578-4940"},"institutions":[{"id":"https://openalex.org/I103635307","display_name":"University of California, Riverside","ror":"https://ror.org/03nawhv43","country_code":"US","type":"education","lineage":["https://openalex.org/I103635307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zizhong Chen","raw_affiliation_strings":["Department of Computer Science and Engineering, University of California, Riverside, CA","Department of Computer Science and Engineering, University of California, Riverside, CA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California, Riverside, CA","institution_ids":["https://openalex.org/I103635307"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, University of California, Riverside, CA#TAB#","institution_ids":["https://openalex.org/I103635307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078501431"],"corresponding_institution_ids":["https://openalex.org/I167576493"],"apc_list":null,"apc_paid":null,"fwci":3.7929,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.93873462,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"26","issue":"5","first_page":"1323","last_page":"1335"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.9997000098228455,"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":0.9997000098228455,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9918000102043152,"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/T11005","display_name":"Radiation Effects in Electronics","score":0.9829999804496765,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.9879969358444214},{"id":"https://openalex.org/keywords/minimum-degree-algorithm","display_name":"Minimum degree algorithm","score":0.8625661730766296},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8468196392059326},{"id":"https://openalex.org/keywords/incomplete-cholesky-factorization","display_name":"Incomplete Cholesky factorization","score":0.7038095593452454},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.669845461845398},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.6519692540168762},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6498371362686157},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5749763250350952},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.571407675743103},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.544664204120636},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5028521418571472},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4296974241733551},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.42369508743286133},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.2460276186466217}],"concepts":[{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.9879969358444214},{"id":"https://openalex.org/C46085209","wikidata":"https://www.wikidata.org/wiki/Q17098969","display_name":"Minimum degree algorithm","level":5,"score":0.8625661730766296},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8468196392059326},{"id":"https://openalex.org/C44363057","wikidata":"https://www.wikidata.org/wiki/Q6015160","display_name":"Incomplete Cholesky factorization","level":4,"score":0.7038095593452454},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.669845461845398},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.6519692540168762},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6498371362686157},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5749763250350952},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.571407675743103},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.544664204120636},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5028521418571472},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4296974241733551},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.42369508743286133},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.2460276186466217},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2014.2320502","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2014.2320502","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G355070363","display_name":null,"funder_award_id":"#CCF-1305622","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4746431001","display_name":null,"funder_award_id":"#ACI-1305624","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W186443009","https://openalex.org/W1607259846","https://openalex.org/W1825216778","https://openalex.org/W1826883764","https://openalex.org/W1980321276","https://openalex.org/W1981493666","https://openalex.org/W1995746640","https://openalex.org/W2020804487","https://openalex.org/W2024966997","https://openalex.org/W2030167104","https://openalex.org/W2037523067","https://openalex.org/W2059300917","https://openalex.org/W2083613288","https://openalex.org/W2096504919","https://openalex.org/W2107209346","https://openalex.org/W2119018856","https://openalex.org/W2123500455","https://openalex.org/W2128511938","https://openalex.org/W2128564847","https://openalex.org/W2135966495","https://openalex.org/W2142255879","https://openalex.org/W2145670264","https://openalex.org/W2147573012","https://openalex.org/W2150679822","https://openalex.org/W2151984682","https://openalex.org/W2152212524","https://openalex.org/W2158344138","https://openalex.org/W2164303766","https://openalex.org/W2165863720","https://openalex.org/W2925006810","https://openalex.org/W4213043702","https://openalex.org/W6607608670","https://openalex.org/W6636392189","https://openalex.org/W6638601623","https://openalex.org/W6682626600"],"related_works":["https://openalex.org/W3046276560","https://openalex.org/W2053627399","https://openalex.org/W2026337412","https://openalex.org/W2113085198","https://openalex.org/W2381435995","https://openalex.org/W2020578791","https://openalex.org/W2074550915","https://openalex.org/W54819768","https://openalex.org/W2135765421","https://openalex.org/W2052455844"],"abstract_inverted_index":{"Cholesky":[0,83,170],"decomposition":[1],"is":[2,131],"a":[3,31,37,46,80],"widely":[4],"used":[5],"algorithm":[6,85,98],"to":[7,61,152,164],"solve":[8],"linear":[9],"equations":[10],"with":[11,30,54,114],"symmetric":[12],"and":[13,77,135,160],"positive":[14],"definite":[15],"coefficient":[16],"matrix.":[17],"With":[18],"large":[19,32,174],"matrices,":[20],"this":[21,97,145],"often":[22],"will":[23],"be":[24],"performed":[25],"on":[26,137,172],"high":[27],"performance":[28],"supercomputers":[29],"number":[33],"of":[34,45,79,107],"processors.":[35,56],"Assuming":[36],"constant":[38],"failure":[39,47],"rate":[40],"per":[41],"processor,":[42],"the":[43,50,63,138,156,166],"probability":[44],"occurring":[48],"during":[49],"execution":[51,65],"increases":[52],"linearly":[53],"additional":[55,105],"Fault":[57],"tolerant":[58,82],"methods":[59,116],"attempt":[60],"reduce":[62,165],"expected":[64,167],"time":[66],"by":[67],"allowing":[68],"recovery":[69,92],"from":[70,93,111],"failure.":[71],"This":[72,109],"paper":[73],"presents":[74],"an":[75,104],"analysis":[76],"implementation":[78],"fault":[81,128],"factorization":[84],"that":[86,144],"does":[87],"not":[88],"require":[89],"checkpointing":[90],"for":[91,169],"fail-stop":[94,120],"failures.":[95],"Rather,":[96],"uses":[99],"redundant":[100],"data":[101],"added":[102],"in":[103,150],"set":[106],"processes.":[108],"differs":[110],"previous":[112],"works":[113],"algorithmic":[115],"as":[117,155],"it":[118],"addresses":[119],"failures":[121],"rather":[122],"than":[123],"fail-continue":[124],"cases.":[125],"The":[126],"proposed":[127],"tolerance":[129],"scheme":[130],"incorporated":[132],"into":[133],"ScaLAPACK":[134],"validated":[136],"supercomputer":[139],"Kraken.":[140],"Experimental":[141],"results":[142],"demonstrate":[143],"method":[146],"has":[147],"decreasing":[148],"overhead":[149],"relation":[151],"overall":[153],"runtime":[154,168],"matrix":[157],"size":[158],"increases,":[159],"thus":[161],"shows":[162],"promise":[163],"factorizations":[171],"very":[173],"matrices.":[175]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
