{"id":"https://openalex.org/W2158344138","doi":"https://doi.org/10.1109/ipdps.2010.5470436","title":"Algorithmic Cholesky factorization fault recovery","display_name":"Algorithmic Cholesky factorization fault recovery","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2158344138","doi":"https://doi.org/10.1109/ipdps.2010.5470436","mag":"2158344138"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2010.5470436","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2010.5470436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel &amp; Distributed Processing (IPDPS)","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/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 Mathematical and Computer Science, Colorado Schml of Mines, Golden, CO, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mathematical and Computer Science, Colorado Schml of Mines, Golden, CO, USA","institution_ids":["https://openalex.org/I167576493"]}]},{"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/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":false,"raw_author_name":"Zizhong Chen","raw_affiliation_strings":["Department of Mathematical and Computer Science, Colorado Schml of Mines, Golden, CO, USA"],"affiliations":[{"raw_affiliation_string":"Department of Mathematical and Computer Science, Colorado Schml of Mines, Golden, CO, USA","institution_ids":["https://openalex.org/I167576493"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5078501431"],"corresponding_institution_ids":["https://openalex.org/I167576493"],"apc_list":null,"apc_paid":null,"fwci":7.0664,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.97288618,"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":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10772","display_name":"Distributed systems and fault tolerance","score":0.994700014591217,"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":0.994700014591217,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9718000292778015,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T11303","display_name":"Bayesian Modeling and Causal Inference","score":0.9611999988555908,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.9844915866851807},{"id":"https://openalex.org/keywords/incomplete-cholesky-factorization","display_name":"Incomplete Cholesky factorization","score":0.8292473554611206},{"id":"https://openalex.org/keywords/minimum-degree-algorithm","display_name":"Minimum degree algorithm","score":0.8175660967826843},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8021776676177979},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6072938442230225},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5867874026298523},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.5687313675880432},{"id":"https://openalex.org/keywords/fault-detection-and-isolation","display_name":"Fault detection and isolation","score":0.5000495910644531},{"id":"https://openalex.org/keywords/fault-tolerance","display_name":"Fault tolerance","score":0.45933592319488525},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.44048476219177246},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4153318405151367},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.41090887784957886},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.194843590259552},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06737825274467468}],"concepts":[{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.9844915866851807},{"id":"https://openalex.org/C44363057","wikidata":"https://www.wikidata.org/wiki/Q6015160","display_name":"Incomplete Cholesky factorization","level":4,"score":0.8292473554611206},{"id":"https://openalex.org/C46085209","wikidata":"https://www.wikidata.org/wiki/Q17098969","display_name":"Minimum degree algorithm","level":5,"score":0.8175660967826843},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8021776676177979},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6072938442230225},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5867874026298523},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.5687313675880432},{"id":"https://openalex.org/C152745839","wikidata":"https://www.wikidata.org/wiki/Q5438153","display_name":"Fault detection and isolation","level":3,"score":0.5000495910644531},{"id":"https://openalex.org/C63540848","wikidata":"https://www.wikidata.org/wiki/Q3140932","display_name":"Fault tolerance","level":2,"score":0.45933592319488525},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.44048476219177246},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4153318405151367},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.41090887784957886},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.194843590259552},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06737825274467468},{"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/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0},{"id":"https://openalex.org/C172707124","wikidata":"https://www.wikidata.org/wiki/Q423488","display_name":"Actuator","level":2,"score":0.0},{"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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ipdps.2010.5470436","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2010.5470436","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE International Symposium on Parallel &amp; Distributed Processing (IPDPS)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1026.4514","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1026.4514","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.ucr.edu/%7Echen/papers/ipdps2010.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W133812513","https://openalex.org/W1576347883","https://openalex.org/W1825216778","https://openalex.org/W1826883764","https://openalex.org/W2008289885","https://openalex.org/W2030167104","https://openalex.org/W2037730929","https://openalex.org/W2072072075","https://openalex.org/W2083613288","https://openalex.org/W2097946733","https://openalex.org/W2107209346","https://openalex.org/W2119018856","https://openalex.org/W2128564847","https://openalex.org/W2138166684","https://openalex.org/W2139766632","https://openalex.org/W2142255879","https://openalex.org/W2150679822","https://openalex.org/W2151984682","https://openalex.org/W2152212524","https://openalex.org/W2162739943","https://openalex.org/W2165863720","https://openalex.org/W2296772319","https://openalex.org/W2952351386","https://openalex.org/W3198669718","https://openalex.org/W4232281662","https://openalex.org/W4285719527","https://openalex.org/W4320800818","https://openalex.org/W6605601114","https://openalex.org/W6638601623","https://openalex.org/W6684083097","https://openalex.org/W6684368920"],"related_works":["https://openalex.org/W2039814159","https://openalex.org/W898189783","https://openalex.org/W2049943687","https://openalex.org/W2381435995","https://openalex.org/W2104481679","https://openalex.org/W2041033288","https://openalex.org/W2028693659","https://openalex.org/W3046276560","https://openalex.org/W2053627399","https://openalex.org/W2079508979"],"abstract_inverted_index":{"Modeling":[0],"and":[1,82,133,154],"analysis":[2,81],"of":[3,23,50,84,112],"large":[4,27,168],"scale":[5],"scientific":[6],"systems":[7],"often":[8,30],"use":[9],"linear":[10,24],"least":[11],"squares":[12],"regression,":[13],"frequently":[14],"employing":[15],"Cholesky":[16,88,164],"factorization":[17,89],"to":[18,66,146,158],"solve":[19],"the":[20,48,55,68,150,160],"resulting":[21],"set":[22,111],"equations.":[25],"With":[26],"matrices,":[28],"this":[29,102,139],"will":[31],"be":[32],"performed":[33],"in":[34,108,144],"high":[35],"performance":[36],"clusters":[37],"containing":[38],"many":[39],"processors.":[40,61,113],"Assuming":[41],"a":[42,51,85],"constant":[43],"failure":[44,52],"rate":[45],"per":[46],"processor,":[47],"probability":[49],"occurring":[53],"during":[54],"execution":[56,70],"increases":[57],"linearly":[58],"with":[59,119],"additional":[60,110],"Fault":[62],"tolerant":[63,87],"methods":[64,121],"attempt":[65],"reduce":[67,159],"expected":[69,161],"time":[71],"by":[72],"allowing":[73],"recovery":[74,97],"from":[75,98,116],"failure.":[76],"This":[77,114],"paper":[78],"presents":[79],"an":[80,109],"implementation":[83,132],"fault":[86],"algorithm":[90,103],"that":[91,138],"does":[92],"not":[93],"require":[94],"checkpointing":[95],"for":[96,163],"fail-stop":[99,125],"failures.":[100],"Rather,":[101],"uses":[104],"redundant":[105],"data":[106],"added":[107],"differs":[115],"previous":[117],"works":[118],"algorithmic":[120],"as":[122,149],"it":[123],"addresses":[124],"failures":[126],"rather":[127],"than":[128],"fail-continue":[129],"cases.":[130],"The":[131],"experimentation":[134],"using":[135],"ScaLAPACK":[136],"demonstrates":[137],"method":[140],"has":[141],"decreasing":[142],"overhead":[143],"relation":[145],"overall":[147],"runtime":[148,162],"matrix":[151],"size":[152],"increases,":[153],"thus":[155],"shows":[156],"promise":[157],"factorizations":[165],"on":[166],"very":[167],"matrices.":[169]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":6},{"year":2012,"cited_by_count":6}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}
