{"id":"https://openalex.org/W2102291960","doi":"https://doi.org/10.1137/090760969","title":"Communication-optimal Parallel and Sequential Cholesky Decomposition","display_name":"Communication-optimal Parallel and Sequential Cholesky Decomposition","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2102291960","doi":"https://doi.org/10.1137/090760969","mag":"2102291960"},"language":"en","primary_location":{"id":"doi:10.1137/090760969","is_oa":false,"landing_page_url":"https://doi.org/10.1137/090760969","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Scientific Computing","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/0902.2537","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Grey Ballard","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Grey Ballard","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"James Demmel","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"James Demmel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Olga Holtz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Olga Holtz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"Oded Schwartz","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Oded Schwartz","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0612,"has_fulltext":true,"cited_by_count":28,"citation_normalized_percentile":{"value":0.87106674,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"32","issue":"6","first_page":"3495","last_page":"3523"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.28209999203681946,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.28209999203681946,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T11435","display_name":"Polynomial and algebraic computation","score":0.2605000138282776,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10963","display_name":"Advanced Optimization Algorithms Research","score":0.10700000077486038,"subfield":{"id":"https://openalex.org/subfields/2612","display_name":"Numerical Analysis"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.9534000158309937},{"id":"https://openalex.org/keywords/qr-decomposition","display_name":"QR decomposition","score":0.7480000257492065},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.6456000208854675},{"id":"https://openalex.org/keywords/incomplete-cholesky-factorization","display_name":"Incomplete Cholesky factorization","score":0.5633999705314636},{"id":"https://openalex.org/keywords/distributed-memory","display_name":"Distributed memory","score":0.5044000148773193},{"id":"https://openalex.org/keywords/gaussian-elimination","display_name":"Gaussian elimination","score":0.47760000824928284},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.41600000858306885},{"id":"https://openalex.org/keywords/parallel-algorithm","display_name":"Parallel algorithm","score":0.39649999141693115},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.38530001044273376},{"id":"https://openalex.org/keywords/multiplication","display_name":"Multiplication (music)","score":0.36730000376701355}],"concepts":[{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.9534000158309937},{"id":"https://openalex.org/C188060507","wikidata":"https://www.wikidata.org/wiki/Q653242","display_name":"QR decomposition","level":3,"score":0.7480000257492065},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.6456000208854675},{"id":"https://openalex.org/C44363057","wikidata":"https://www.wikidata.org/wiki/Q6015160","display_name":"Incomplete Cholesky factorization","level":4,"score":0.5633999705314636},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.536899983882904},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.5044000148773193},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.49399998784065247},{"id":"https://openalex.org/C126312332","wikidata":"https://www.wikidata.org/wiki/Q2658","display_name":"Gaussian elimination","level":3,"score":0.47760000824928284},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4487000107765198},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4307999908924103},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.41600000858306885},{"id":"https://openalex.org/C120373497","wikidata":"https://www.wikidata.org/wiki/Q1087987","display_name":"Parallel algorithm","level":2,"score":0.39649999141693115},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.38530001044273376},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.36660000681877136},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.3587999939918518},{"id":"https://openalex.org/C49712288","wikidata":"https://www.wikidata.org/wiki/Q77601250","display_name":"Positive-definite matrix","level":3,"score":0.35350000858306885},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.34220001101493835},{"id":"https://openalex.org/C163834973","wikidata":"https://www.wikidata.org/wiki/Q2004891","display_name":"Numerical linear algebra","level":3,"score":0.3264999985694885},{"id":"https://openalex.org/C6802819","wikidata":"https://www.wikidata.org/wiki/Q1072174","display_name":"Linear system","level":2,"score":0.3158999979496002},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.3149000108242035},{"id":"https://openalex.org/C134978465","wikidata":"https://www.wikidata.org/wiki/Q1654069","display_name":"Incomplete LU factorization","level":4,"score":0.31299999356269836},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.30979999899864197},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.3061999976634979},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.298799991607666},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.2971000075340271},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.2913999855518341},{"id":"https://openalex.org/C46085209","wikidata":"https://www.wikidata.org/wiki/Q17098969","display_name":"Minimum degree algorithm","level":5,"score":0.28929999470710754},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.2709999978542328},{"id":"https://openalex.org/C84507854","wikidata":"https://www.wikidata.org/wiki/Q952222","display_name":"Diagonally dominant matrix","level":3,"score":0.2694000005722046},{"id":"https://openalex.org/C139352143","wikidata":"https://www.wikidata.org/wiki/Q82571","display_name":"Linear algebra","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.26649999618530273},{"id":"https://openalex.org/C83581934","wikidata":"https://www.wikidata.org/wiki/Q527381","display_name":"Arbitrary-precision arithmetic","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C77553402","wikidata":"https://www.wikidata.org/wiki/Q13222579","display_name":"Upper and lower bounds","level":2,"score":0.2574000060558319}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1137/090760969","is_oa":false,"landing_page_url":"https://doi.org/10.1137/090760969","pdf_url":null,"source":{"id":"https://openalex.org/S165512578","display_name":"SIAM Journal on Scientific Computing","issn_l":"1064-8275","issn":["1064-8275","1095-7197"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320508","host_organization_name":"Society for Industrial and Applied Mathematics","host_organization_lineage":["https://openalex.org/P4310320508"],"host_organization_lineage_names":["Society for Industrial and Applied Mathematics"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"SIAM Journal on Scientific Computing","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:0902.2537","is_oa":true,"landing_page_url":"https://arxiv.org/abs/0902.2537","pdf_url":"https://arxiv.org/pdf/0902.2537","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:0902.2537","is_oa":true,"landing_page_url":"https://arxiv.org/abs/0902.2537","pdf_url":"https://arxiv.org/pdf/0902.2537","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2102291960.pdf","grobid_xml":"https://content.openalex.org/works/W2102291960.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W1986334759","https://openalex.org/W2007768252","https://openalex.org/W2010747199","https://openalex.org/W2026237859","https://openalex.org/W2038142281","https://openalex.org/W2048973547","https://openalex.org/W2166737459","https://openalex.org/W2677289244"],"related_works":[],"abstract_inverted_index":{"Numerical":[0],"algorithms":[1,50,108,198],"have":[2],"two":[3],"kinds":[4],"of":[5,19,46,72,96,149,184,196,202,207,233,235],"costs:":[6],"arithmetic":[7,41],"and":[8,69,105,109,124,139,142,161,164,172,177,215],"communication,":[9],"by":[10,227],"which":[11,80],"we":[12,56,92,119],"mean":[13],"either":[14],"moving":[15],"data":[16,110],"between":[17],"levels":[18,234],"a":[20,29,194],"memory":[21,126,236],"hierarchy":[22],"(in":[23,33],"the":[24,34,63,94,107,116,122,185,203],"sequential":[25,117,225],"case)":[26],"or":[27],"over":[28],"network":[30],"connecting":[31],"processors":[32],"parallel":[35],"case).":[36],"Communication":[37],"costs":[38,95],"often":[39],"dominate":[40],"costs,":[42],"so":[43],"it":[44,218],"is":[45,81],"interest":[47],"to":[48,77,101],"design":[49],"minimizing":[51],"communication.":[52],"In":[53,115],"this":[54,192,221],"paper":[55],"first":[57],"extend":[58],"known":[59],"lower":[60,103],"bounds":[61,104],"on":[62,189,224],"communication":[64,229],"cost":[65],"(both":[66],"for":[67,70,83,199,230],"bandwidth":[68],"latency)":[71],"conventional":[73],"($O(n^3)$)":[74],"matrix":[75],"multiplication":[76],"Cholesky":[78,98],"factorization,":[79],"used":[82],"solving":[84],"dense":[85,208],"symmetric":[86],"positive":[87],"definite":[88],"linear":[89,209],"systems.":[90],"Second,":[91],"compare":[93],"various":[97],"decomposition":[99],"implementations":[100,201],"these":[102],"identify":[106],"structures":[111],"that":[112],"attain":[113],"them.":[114],"case,":[118],"consider":[120],"both":[121],"two-level":[123],"hierarchical":[125],"models.":[127],"Combined":[128],"with":[129,212],"prior":[130,222],"results":[131],"in":[132],"[J.":[133,154,173],"Demmel":[134,155],"et":[135,156],"al.,":[136,157],"Communication-optimal":[137,159],"Parallel":[138,160],"Sequential":[140,162],"QR":[141,163],"LU":[143,165,211,226],"Factorizations,":[144,166],"Technical":[145],"report":[146],"EECS-2008-89,":[147],"University":[148],"California,":[150],"Berkeley,":[151],"CA,":[152],"2008],":[153],"Implementing":[158],"SIAM.":[167],"J.":[168],"Sci.":[169],"Comp.,":[170],"submitted],":[171],"Demmel,":[174],"L.":[175],"Grigori,":[176],"H.":[178],"Xiang,":[179],"Communication-avoiding":[180],"Gaussian":[181],"Elimination,":[182],"Proceedings":[183],"2008":[186],"ACM/IEEE":[187],"Conference":[188],"Supercomputing,":[190],"2008]":[191],"gives":[193],"set":[195],"communication-optimal":[197],"$O(n^3)$":[200],"three":[204],"basic":[205],"factorizations":[206],"algebra:":[210],"pivoting,":[213],"QR,":[214],"Cholesky.":[216],"But":[217],"goes":[219],"beyond":[220],"work":[223],"optimizing":[228],"any":[231],"number":[232],"hierarchy.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2016-06-24T00:00:00"}