{"id":"https://openalex.org/W3173589482","doi":"https://doi.org/10.1109/tpds.2021.3090316","title":"gSoFa: Scalable Sparse Symbolic LU Factorization on GPUs","display_name":"gSoFa: Scalable Sparse Symbolic LU Factorization on GPUs","publication_year":2021,"publication_date":"2021-06-17","ids":{"openalex":"https://openalex.org/W3173589482","doi":"https://doi.org/10.1109/tpds.2021.3090316","mag":"3173589482"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2021.3090316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3090316","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":true,"oa_status":"green","oa_url":"https://www.osti.gov/biblio/1960228","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5016461884","display_name":"Anil Gaihre","orcid":"https://orcid.org/0000-0002-4892-6799"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Anil Gaihre","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken, NJ, USA"],"raw_orcid":"https://orcid.org/0000-0002-4892-6799","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken, NJ, USA","institution_ids":["https://openalex.org/I108468826"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006873445","display_name":"Xiaoye Sherry Li","orcid":"https://orcid.org/0000-0002-0747-698X"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoye Sherry Li","raw_affiliation_strings":["Lawrence Berkeley National Laboratory, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory, Berkeley, CA, USA","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100338932","display_name":"Hang Liu","orcid":"https://orcid.org/0000-0002-1379-6314"},"institutions":[{"id":"https://openalex.org/I108468826","display_name":"Stevens Institute of Technology","ror":"https://ror.org/02z43xh36","country_code":"US","type":"education","lineage":["https://openalex.org/I108468826"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hang Liu","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken, NJ, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Stevens Institute of Technology, Hoboken, NJ, USA","institution_ids":["https://openalex.org/I108468826"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7927,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.75261957,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"33","issue":"4","first_page":"1015","last_page":"1026"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9983999729156494,"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":0.9983999729156494,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9961000084877014,"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":0.9926000237464905,"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/factorization","display_name":"Factorization","score":0.6594526767730713},{"id":"https://openalex.org/keywords/notation","display_name":"Notation","score":0.608797550201416},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.45001286268234253},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.4395403563976288},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.43303459882736206},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.4213992953300476},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4188781976699829},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3925856053829193},{"id":"https://openalex.org/keywords/algebra-over-a-field","display_name":"Algebra over a field","score":0.38403603434562683},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.3594508767127991},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.3340412378311157},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.29169952869415283},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.24781903624534607},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.23229417204856873},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1586591601371765},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11418858170509338},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.06716832518577576}],"concepts":[{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.6594526767730713},{"id":"https://openalex.org/C45357846","wikidata":"https://www.wikidata.org/wiki/Q2001982","display_name":"Notation","level":2,"score":0.608797550201416},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.45001286268234253},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.4395403563976288},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.43303459882736206},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.4213992953300476},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4188781976699829},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3925856053829193},{"id":"https://openalex.org/C136119220","wikidata":"https://www.wikidata.org/wiki/Q1000660","display_name":"Algebra over a field","level":2,"score":0.38403603434562683},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3594508767127991},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.3340412378311157},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.29169952869415283},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.24781903624534607},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.23229417204856873},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1586591601371765},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11418858170509338},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.06716832518577576},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpds.2021.3090316","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2021.3090316","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"},{"id":"pmh:oai:osti.gov:1960228","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1960228","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:1960228","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/1960228","pdf_url":null,"source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G422089240","display_name":"CRII: SHF: Expediting Subgraph Matching on GPUs","funder_award_id":"2000722","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"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W625657276","https://openalex.org/W1985291160","https://openalex.org/W1998894100","https://openalex.org/W2017431061","https://openalex.org/W2019092032","https://openalex.org/W2020561008","https://openalex.org/W2021108117","https://openalex.org/W2027851979","https://openalex.org/W2038205735","https://openalex.org/W2041470524","https://openalex.org/W2042545849","https://openalex.org/W2053266474","https://openalex.org/W2055791798","https://openalex.org/W2057112598","https://openalex.org/W2086119402","https://openalex.org/W2089341221","https://openalex.org/W2095420020","https://openalex.org/W2130886743","https://openalex.org/W2141331848","https://openalex.org/W2143131337","https://openalex.org/W2161455936","https://openalex.org/W2169528473","https://openalex.org/W2397636522","https://openalex.org/W2435994428","https://openalex.org/W2469975815","https://openalex.org/W2950537538","https://openalex.org/W2951135776","https://openalex.org/W2984365163","https://openalex.org/W3000173590","https://openalex.org/W3006582303","https://openalex.org/W3007849603","https://openalex.org/W6650020292"],"related_works":["https://openalex.org/W2766762530","https://openalex.org/W119752240","https://openalex.org/W2602301532","https://openalex.org/W1988437637","https://openalex.org/W1977700955","https://openalex.org/W4388311419","https://openalex.org/W2271643833","https://openalex.org/W1973739845","https://openalex.org/W2127054029","https://openalex.org/W2060455298"],"abstract_inverted_index":{"Decomposing":[0],"a":[1,4,28,120,145,170,224],"matrix$\\mathbf":[2,6,10],"{A}$into":[3],"lower":[5],"{L}$and":[7],"an":[8,20,70],"upper":[9],"{U}$,":[11],"which":[12],"is":[13,19,49,128],"also":[14],"known":[15],"as":[16],"LU":[17,31,79,109],"decomposition,":[18],"essential":[21],"operation":[22],"in":[23,38,43,227],"numerical":[24],"linear":[25],"algebra.":[26],"For":[27],"sparse":[29],"matrix,":[30],"decomposition":[32],"often":[33],"introduces":[34],"more":[35],"nonzero":[36,54],"entries":[37],"the$\\mathbf":[39],"{L}$and$\\mathbf":[40,57],"{U}$factors":[41],"than":[42],"the":[44,53,61,65,84,88,98,102,153,156,160,175,204,219,228],"original":[45],"matrix.":[46],"Asymbolic":[47],"factorizationstep":[48],"needed":[50],"to":[51,76,87,106,151,173,189,194,199,215],"identify":[52],"structures":[55],"of$\\mathbf":[56],"{U}$matrices.":[58],"Attracted":[59],"by":[60,181,210],"enormous":[62],"potentials":[63],"of":[64,72,90,137,218,223],"Graphics":[66],"Processing":[67],"Units":[68],"(GPUs),":[69],"array":[71],"efforts":[73],"have":[74],"surged":[75],"deploy":[77],"various":[78],"factorization":[80,111,125],"steps":[81],"except":[82],"for":[83,131],"symbolic":[85,110,124,184],"factorization,":[86],"best":[89],"our":[91],"knowledge,":[92],"on":[93,115,208],"GPUs.":[94,116,138],"This":[95],"article":[96],"introducesgSoFa,":[97],"firstGPU-basedsymbolicfactorization":[99],"design":[100],"with":[101],"following":[103],"three":[104],"optimizations":[105],"enable":[107],"scalable":[108],"fornonsymmetric":[112],"patternsparse":[113],"matrices":[114],"First,":[117],"we":[118,140,168],"introduce":[119,169],"novel":[121],"fine-grained":[122],"parallel":[123],"algorithm":[126],"that":[127],"well":[129],"suited":[130],"theSingle":[132],"Instruction":[133],"Multiple":[134],"Thread(SIMT)":[135],"architecture":[136],"Second,":[139],"tailor":[141],"supernode":[142,165],"detection":[143],"into":[144],"SIMT":[146],"friendly":[147],"process":[148],"and":[149,158,202],"strive":[150],"balance":[152],"workload,":[154],"minimize":[155],"communication":[157],"saturate":[159],"GPU":[161,226],"computing":[162],"resources":[163],"during":[164],"detection.":[166],"Third,":[167],"three-pronged":[171],"optimization":[172],"reduce":[174],"excessive":[176],"space":[177],"consumption":[178],"problem":[179],"faced":[180],"multi-source":[182],"concurrent":[183],"factorization.":[185],"Taken":[186],"together,gSoFaachieves":[187],"up":[188,214],"31\u00d7":[190],"speedup":[191],"from":[192],"1":[193],"44":[195],"Summit":[196,229],"nodes":[197],"(6":[198],"264":[200],"GPUs)":[201],"outperforms":[203],"state-of-the-art":[205],"CPU":[206],"project,":[207],"average,":[209],"5\u00d7.":[211],"Notably,gSoFaalso":[212],"achieves":[213],"47":[216],"percent":[217],"peak":[220],"memory":[221],"throughput":[222],"V100":[225],"Supercomputer.":[230]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}