{"id":"https://openalex.org/W2130886743","doi":"https://doi.org/10.1145/2228360.2228565","title":"Sparse LU factorization for parallel circuit simulation on GPU","display_name":"Sparse LU factorization for parallel circuit simulation on GPU","publication_year":2012,"publication_date":"2012-05-31","ids":{"openalex":"https://openalex.org/W2130886743","doi":"https://doi.org/10.1145/2228360.2228565","mag":"2130886743"},"language":"en","primary_location":{"id":"doi:10.1145/2228360.2228565","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2228360.2228565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th Annual Design Automation Conference","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/A5002519367","display_name":"Ling Ren","orcid":"https://orcid.org/0000-0003-3437-7570"},"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":"Ling Ren","raw_affiliation_strings":["Tsinghua University, Beijing, China","Department of Electronic Engineering, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"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/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":false,"raw_author_name":"Xiaoming Chen","raw_affiliation_strings":["Tsinghua University, Beijing, China","Department of Electronic Engineering, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"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/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":["Tsinghua University, Beijing, China","Department of Electronic Engineering, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"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/A5100361488","display_name":"Chenxi Zhang","orcid":"https://orcid.org/0000-0002-5736-9285"},"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":"Chenxi Zhang","raw_affiliation_strings":["Tsinghua University, Beijing, China","Department of Electronic Engineering, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"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":["Tsinghua University, Beijing, China","Department of Electronic Engineering, Tsinghua National Laboratory for Information Science and Technology, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"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":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5002519367"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":4.3817,"has_fulltext":false,"cited_by_count":41,"citation_normalized_percentile":{"value":0.9474826,"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":"1125","last_page":"1130"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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":0.9970999956130981,"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/parallel-computing","display_name":"Parallel computing","score":0.8781127333641052},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8630677461624146},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7935900688171387},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5976672768592834},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5722412467002869},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.568804144859314},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.535847544670105},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.5179692506790161},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.47866305708885193},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.46818745136260986},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.4624932110309601},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.44660454988479614},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3709040880203247},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.23826083540916443},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.23765504360198975},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.10672077536582947},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.070609450340271}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8781127333641052},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8630677461624146},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7935900688171387},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5976672768592834},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5722412467002869},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.568804144859314},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.535847544670105},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.5179692506790161},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.47866305708885193},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.46818745136260986},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.4624932110309601},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.44660454988479614},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3709040880203247},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.23826083540916443},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.23765504360198975},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.10672077536582947},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.070609450340271},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2228360.2228565","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2228360.2228565","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 49th Annual Design Automation Conference","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.717.9340","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.717.9340","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://nics.ee.tsinghua.edu.cn/people/chenxm/papers/dac12.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5699999928474426,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G2459280394","display_name":null,"funder_award_id":"6.09E+15","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1543500414","https://openalex.org/W1550780731","https://openalex.org/W1819329817","https://openalex.org/W1969033192","https://openalex.org/W2017431061","https://openalex.org/W2017509788","https://openalex.org/W2020561008","https://openalex.org/W2035080386","https://openalex.org/W2038205735","https://openalex.org/W2055094346","https://openalex.org/W2074093855","https://openalex.org/W2106969188","https://openalex.org/W2118076222","https://openalex.org/W2141331848","https://openalex.org/W2147753626","https://openalex.org/W2162322364","https://openalex.org/W2167078995","https://openalex.org/W2168033396","https://openalex.org/W2169150754","https://openalex.org/W2187691968","https://openalex.org/W2399715892","https://openalex.org/W4234460625"],"related_works":["https://openalex.org/W2052993554","https://openalex.org/W2046125858","https://openalex.org/W4205439893","https://openalex.org/W2030992542","https://openalex.org/W2344713096","https://openalex.org/W4318969829","https://openalex.org/W4386259950","https://openalex.org/W2002443693","https://openalex.org/W2041987899","https://openalex.org/W2358458784"],"abstract_inverted_index":{"Sparse":[0],"solver":[1,17,85],"has":[2,10],"become":[3],"the":[4,20,39,45,54,65,74,91,94,101,138,147,156],"bottleneck":[5],"of":[6,19,41,53,96,140],"SPICE":[7],"simulators.":[8],"There":[9],"been":[11],"few":[12],"work":[13,92],"on":[14,34,106,149],"GPU-based":[15,82,118],"sparse":[16,29,83,119,142],"because":[18],"high":[21],"data-dependency.":[22],"The":[23,51],"strong":[24],"data-dependency":[25],"de-termines":[26],"that":[27,153],"parallel":[28],"LU":[30,84,120,143],"factorization":[31,112,121,144],"runs":[32],"efficiently":[33],"shared-memory":[35],"computing":[36],"devices.":[37],"But":[38],"number":[40,95],"CPU":[42,128],"cores":[43,63],"sharing":[44,64],"same":[46],"memory":[47,102],"is":[48],"often":[49],"limited.":[50],"state":[52],"art":[55],"Graphic":[56],"Processing":[57],"Units":[58],"(GPU)":[59],"naturally":[60],"have":[61],"numerous":[62],"device":[66],"memory,":[67],"and":[68,100,129,145,151],"provide":[69],"a":[70,81],"possible":[71],"solution":[72],"to":[73],"problem.":[75],"In":[76],"this":[77],"paper,":[78],"we":[79],"propose":[80],"for":[86],"circuit":[87],"simulation.":[88],"We":[89,135],"optimize":[90],"partitioning,":[93],"active":[97],"thread":[98],"groups,":[99],"access":[103],"pattern,":[104],"based":[105],"GPU":[107],"architecture.":[108],"On":[109],"matrices":[110],"whose":[111],"in-volves":[113],"many":[114],"floating-point":[115],"operations,":[116],"our":[117],"achieves":[122],"7.90":[123],"\u00d7":[124],"speedup":[125,131],"over":[126,132],"1-core":[127],"1.49\u00d7":[130],"8-core":[133],"CPU.":[134],"also":[136],"analyze":[137],"scalability":[139],"par-allel":[141],"investigate":[146],"specifications":[148],"CPUs":[150],"GPUs":[152],"most":[154],"influence":[155],"performance.":[157]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}