{"id":"https://openalex.org/W2132450860","doi":"https://doi.org/10.1109/tpds.2014.2312199","title":"GPU-Accelerated Sparse LU Factorization for Circuit Simulation with Performance Modeling","display_name":"GPU-Accelerated Sparse LU Factorization for Circuit Simulation with Performance Modeling","publication_year":2014,"publication_date":"2014-03-18","ids":{"openalex":"https://openalex.org/W2132450860","doi":"https://doi.org/10.1109/tpds.2014.2312199","mag":"2132450860"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2014.2312199","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2014.2312199","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/A5100373745","display_name":"Xiaohong Chen","orcid":"https://orcid.org/0000-0002-9797-8384"},"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":true,"raw_author_name":"Xiaoming Chen","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China","Department of Electronic Engineering, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002519367","display_name":"Ling Ren","orcid":"https://orcid.org/0000-0003-3437-7570"},"institutions":[{"id":"https://openalex.org/I63966007","display_name":"Massachusetts Institute of Technology","ror":"https://ror.org/042nb2s44","country_code":"US","type":"education","lineage":["https://openalex.org/I63966007"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ling Ren","raw_affiliation_strings":["Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA","Department of Electrical Engineering & Computer Science, Massachusetts Institute of Technology, Cambridge,"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Massachusetts Institute of Technology, Cambridge, MA","institution_ids":["https://openalex.org/I63966007"]},{"raw_affiliation_string":"Department of Electrical Engineering & Computer Science, Massachusetts Institute of Technology, Cambridge,","institution_ids":["https://openalex.org/I63966007"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100445061","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0001-6108-5157"},"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":"Yu Wang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China","Department of Electronic Engineering, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103867707","display_name":"Huazhong 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":"Huazhong Yang","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China","Department of Electronic Engineering, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5100373745"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":6.7425,"has_fulltext":false,"cited_by_count":74,"citation_normalized_percentile":{"value":0.97205961,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"26","issue":"3","first_page":"786","last_page":"795"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9991999864578247,"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/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.9968000054359436,"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/computer-science","display_name":"Computer science","score":0.8317596912384033},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.805915355682373},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.5482944250106812},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5430620908737183},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.48384538292884827},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.4699345529079437},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.46807822585105896},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.443136066198349},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.32121002674102783},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.3149990439414978},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27509304881095886},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.11658591032028198},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08783835172653198}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8317596912384033},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.805915355682373},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.5482944250106812},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5430620908737183},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.48384538292884827},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.4699345529079437},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.46807822585105896},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.443136066198349},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.32121002674102783},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.3149990439414978},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27509304881095886},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.11658591032028198},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08783835172653198},{"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/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"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":1,"locations":[{"id":"doi:10.1109/tpds.2014.2312199","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2014.2312199","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":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W244652688","https://openalex.org/W1509453182","https://openalex.org/W1964704819","https://openalex.org/W1986822694","https://openalex.org/W2003105834","https://openalex.org/W2006384005","https://openalex.org/W2017431061","https://openalex.org/W2017509788","https://openalex.org/W2020561008","https://openalex.org/W2023354763","https://openalex.org/W2031990962","https://openalex.org/W2033614580","https://openalex.org/W2035080386","https://openalex.org/W2041999884","https://openalex.org/W2047650874","https://openalex.org/W2051917325","https://openalex.org/W2055094346","https://openalex.org/W2058569192","https://openalex.org/W2063186542","https://openalex.org/W2069849438","https://openalex.org/W2089024363","https://openalex.org/W2106969188","https://openalex.org/W2118076222","https://openalex.org/W2130886743","https://openalex.org/W2140153041","https://openalex.org/W2147753626","https://openalex.org/W2162322364","https://openalex.org/W2167078995","https://openalex.org/W2167334577","https://openalex.org/W2169150754","https://openalex.org/W2170802276","https://openalex.org/W2208934446","https://openalex.org/W2271439649","https://openalex.org/W2603505620","https://openalex.org/W3141650078","https://openalex.org/W3147150317","https://openalex.org/W4285719527","https://openalex.org/W6609470788","https://openalex.org/W6694169113"],"related_works":["https://openalex.org/W1561683466","https://openalex.org/W4318685353","https://openalex.org/W3113209370","https://openalex.org/W2009002108","https://openalex.org/W2947459586","https://openalex.org/W4301025548","https://openalex.org/W4205508326","https://openalex.org/W2582864838","https://openalex.org/W2791534362","https://openalex.org/W2276173551"],"abstract_inverted_index":{"The":[0,21,161],"sparse":[1,52,63,165],"matrix":[2],"solver":[3,53,64],"by":[4,156,172,184],"LU":[5,75,108,166],"factorization":[6,76,109,167],"is":[7,68,170],"a":[8,72,157],"serious":[9],"bottleneck":[10],"in":[11,54],"Simulation":[12],"Program":[13],"with":[14,131,145,187],"Integrated":[15],"Circuit":[16],"Emphasis":[17],"(SPICE)-based":[18],"circuit":[19,55,66],"simulators.":[20,56],"state-of-the-art":[22],"Graphics":[23],"Processing":[24],"Units":[25],"(GPU)":[26],"have":[27],"numerous":[28],"cores":[29],"sharing":[30],"the":[31,51,100,106,153,164,173,178],"same":[32],"memory,":[33],"provide":[34],"attractive":[35],"memory":[36,93,175,189],"bandwidth":[37],"and":[38,41,80,92,134],"compute":[39],"capability,":[40],"support":[42],"massive":[43],"thread-level":[44],"parallelism,":[45],"so":[46,177],"GPUs":[47,169,186],"can":[48,180],"potentially":[49],"accelerate":[50],"In":[57],"this":[58],"paper,":[59],"an":[60,115],"efficient":[61],"GPU-based":[62],"for":[65],"problems":[67],"proposed.":[69],"We":[70,148],"develop":[71],"hybrid":[73],"parallel":[74],"approach":[77,110,155],"combining":[78],"task-level":[79],"data-level":[81],"parallelism":[82],"on":[83,99,111,168],"GPUs.":[84],"Work":[85],"partitioning,":[86],"number":[87],"of":[88,118,152,163],"active":[89],"thread":[90],"groups,":[91],"access":[94],"patterns":[95],"are":[96],"optimized":[97],"based":[98],"GPU":[101],"architecture.":[102],"Experiments":[103],"show":[104],"that":[105],"proposed":[107,154],"NVIDIA":[112],"GTX580":[113],"attains":[114],"average":[116],"speedup":[117],"7.02":[119],"<formula":[120,136],"formulatype=\"inline\"":[121,137],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[122,138],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[123],"<tex":[124],"Notation=\"TeX\">$\\times$</tex><mathgraphic":[125],"fileref=\"chen-ieq1-2312199.gif\"":[126],"graphicformat=\"GIF\"/></formula>":[127,143],"(geometric":[128],"mean)":[129],"compared":[130,144],"sequential":[132],"PARDISO,":[133],"1.55":[135],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex":[139],"Notation=\"TeX\">$\\times$</tex>":[140],"<mathgraphic":[141],"fileref=\"chen-ieq2-2312199.gif\"":[142],"16-threaded":[146],"PARDISO.":[147],"also":[149],"investigate":[150],"bottlenecks":[151],"parametric":[158],"performance":[159,162,179],"model.":[160],"constrained":[171],"global":[174],"bandwidth,":[176],"be":[181],"further":[182],"improved":[183],"future":[185],"larger":[188],"bandwidth.":[190]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":10},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}