{"id":"https://openalex.org/W2990029213","doi":"https://doi.org/10.1109/tpds.2019.2953852","title":"Accelerating Sparse Cholesky Factorization on Sunway Manycore Architecture","display_name":"Accelerating Sparse Cholesky Factorization on Sunway Manycore Architecture","publication_year":2019,"publication_date":"2019-11-25","ids":{"openalex":"https://openalex.org/W2990029213","doi":"https://doi.org/10.1109/tpds.2019.2953852","mag":"2990029213"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2019.2953852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2019.2953852","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/A5046708261","display_name":"Mingzhen Li","orcid":"https://orcid.org/0000-0002-4115-9072"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Mingzhen Li","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100330624","display_name":"Yi Liu","orcid":"https://orcid.org/0000-0003-1829-2817"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Liu","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018705589","display_name":"Hailong Yang","orcid":"https://orcid.org/0000-0003-1101-7927"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hailong Yang","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074183877","display_name":"Zhongzhi Luan","orcid":"https://orcid.org/0000-0002-7186-0556"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongzhi Luan","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038750675","display_name":"Lin Gan","orcid":"https://orcid.org/0000-0003-1297-4462"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lin Gan","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115591592","display_name":"Guangwen Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangwen Yang","raw_affiliation_strings":["Department of Computer Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079362609","display_name":"Depei Qian","orcid":"https://orcid.org/0000-0002-5382-1473"},"institutions":[{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Depei Qian","raw_affiliation_strings":["Beihang University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Beihang University, Beijing, China","institution_ids":["https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5046708261"],"corresponding_institution_ids":["https://openalex.org/I82880672"],"apc_list":null,"apc_paid":null,"fwci":1.9261,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.86224889,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"31","issue":"7","first_page":"1636","last_page":"1650"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9943000078201294,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9943000078201294,"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":0.7878055572509766},{"id":"https://openalex.org/keywords/cholesky-decomposition","display_name":"Cholesky decomposition","score":0.7864489555358887},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6629552245140076},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5134507417678833},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.5067048668861389},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.4538399875164032},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.368685781955719},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.334686279296875},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19035542011260986},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.11062565445899963},{"id":"https://openalex.org/keywords/computational-chemistry","display_name":"Computational chemistry","score":0.08734041452407837},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0860956609249115}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7878055572509766},{"id":"https://openalex.org/C34727166","wikidata":"https://www.wikidata.org/wiki/Q515375","display_name":"Cholesky decomposition","level":3,"score":0.7864489555358887},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6629552245140076},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5134507417678833},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.5067048668861389},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.4538399875164032},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.368685781955719},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.334686279296875},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19035542011260986},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.11062565445899963},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.08734041452407837},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0860956609249115},{"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/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2019.2953852","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2019.2953852","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":[{"score":0.550000011920929,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G4727018227","display_name":null,"funder_award_id":"2016YFB0200100","funder_id":"https://openalex.org/F4320336026","funder_display_name":"National Key Research and Development Program of China Stem Cell and Translational Research"},{"id":"https://openalex.org/G4779907915","display_name":null,"funder_award_id":"61502019","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6322973505","display_name":null,"funder_award_id":"61732002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6408341383","display_name":null,"funder_award_id":"2016YFB1000503","funder_id":"https://openalex.org/F4320336026","funder_display_name":"National Key Research and Development Program of China Stem Cell and Translational Research"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320336026","display_name":"National Key Research and Development Program of China Stem Cell and Translational Research","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W182691100","https://openalex.org/W1028753842","https://openalex.org/W1506342804","https://openalex.org/W1520511539","https://openalex.org/W1558138778","https://openalex.org/W1585892185","https://openalex.org/W1982355466","https://openalex.org/W2003249877","https://openalex.org/W2011832776","https://openalex.org/W2013424510","https://openalex.org/W2013459285","https://openalex.org/W2016279572","https://openalex.org/W2035080386","https://openalex.org/W2062897230","https://openalex.org/W2063675347","https://openalex.org/W2064872546","https://openalex.org/W2070232376","https://openalex.org/W2089024363","https://openalex.org/W2118341515","https://openalex.org/W2121893797","https://openalex.org/W2122747952","https://openalex.org/W2127882405","https://openalex.org/W2130289795","https://openalex.org/W2142677441","https://openalex.org/W2153625108","https://openalex.org/W2155893237","https://openalex.org/W2156426360","https://openalex.org/W2171226522","https://openalex.org/W2187691968","https://openalex.org/W2206856102","https://openalex.org/W2208934446","https://openalex.org/W2410272182","https://openalex.org/W2598689602","https://openalex.org/W2614185560","https://openalex.org/W2622428623","https://openalex.org/W2728256789","https://openalex.org/W2767497803","https://openalex.org/W2767612671","https://openalex.org/W2775348209","https://openalex.org/W2781998146","https://openalex.org/W2805108849","https://openalex.org/W2887666076","https://openalex.org/W2891832717","https://openalex.org/W2899133614","https://openalex.org/W2901423583","https://openalex.org/W2902659137","https://openalex.org/W2902699695","https://openalex.org/W2914505133","https://openalex.org/W2963080259","https://openalex.org/W4235810972","https://openalex.org/W4244567449","https://openalex.org/W4248080568","https://openalex.org/W4252721932","https://openalex.org/W4401247571","https://openalex.org/W6633456370","https://openalex.org/W6656654805","https://openalex.org/W6687000134","https://openalex.org/W6735205816"],"related_works":["https://openalex.org/W2526784484","https://openalex.org/W1509943448","https://openalex.org/W2074431240","https://openalex.org/W2061572227","https://openalex.org/W2100843445","https://openalex.org/W3149476094","https://openalex.org/W1987177655","https://openalex.org/W1545561241","https://openalex.org/W2025695688","https://openalex.org/W162008856"],"abstract_inverted_index":{"To":[0],"improve":[1],"the":[2,11,15,19,30,36,39,64,112,128,132],"performance":[3,144],"of":[4,14,33,38,89,131],"sparse":[5,16,34,60,90],"Cholesky":[6,91],"factorization,":[7],"existing":[8],"research":[9,75],"divides":[10],"adjacent":[12],"columns":[13],"matrix":[17,53,106],"with":[18],"same":[20],"nonzero":[21],"patterns":[22],"into":[23],"supernodes":[24,41],"for":[25,127],"parallelization.":[26],"However,":[27],"due":[28],"to":[29,47,57,63,108,111,125],"various":[31],"structures":[32],"matrices,":[35],"computation":[37],"generated":[40],"varies":[42],"significantly,":[43],"and":[44,103,115],"thus":[45],"hard":[46],"optimize":[48],"when":[49],"computed":[50],"by":[51],"dense":[52,105],"kernels.":[54],"Therefore,":[55],"how":[56],"efficiently":[58],"map":[59],"Choleksy":[61],"factorization":[62,92],"emerging":[65],"architectures,":[66],"such":[67],"as":[68],"Sunway":[69,94],"many-core":[70],"processor,":[71],"remains":[72],"an":[73,122],"active":[74],"direction.":[76],"In":[77,118],"this":[78],"article,":[79],"we":[80,97,120],"propose":[81,121],"swCholesky,":[82],"which":[83],"is":[84],"a":[85,104],"highly":[86],"optimized":[87],"implementation":[88],"on":[93],"processor.":[95],"Specifically,":[96],"design":[98],"three":[99],"kernel":[100,113],"task":[101],"queues":[102],"library":[107],"dynamically":[109],"adapt":[110],"characteristics":[114],"architecture":[116],"features.":[117],"addition,":[119],"auto-tuning":[123],"mechanism":[124],"search":[126],"optimal":[129],"settings":[130],"important":[133],"parameters":[134],"in":[135],"swCholesky.":[136],"Our":[137],"experiments":[138],"show":[139],"that":[140],"swCholesky":[141],"achieves":[142],"better":[143],"than":[145],"state-of-the-art":[146],"implementations.":[147]},"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":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}