{"id":"https://openalex.org/W3212893044","doi":"https://doi.org/10.1109/dac18074.2021.9586141","title":"SFLU: Synchronization-Free Sparse LU Factorization for Fast Circuit Simulation on GPUs","display_name":"SFLU: Synchronization-Free Sparse LU Factorization for Fast Circuit Simulation on GPUs","publication_year":2021,"publication_date":"2021-11-08","ids":{"openalex":"https://openalex.org/W3212893044","doi":"https://doi.org/10.1109/dac18074.2021.9586141","mag":"3212893044"},"language":"en","primary_location":{"id":"doi:10.1109/dac18074.2021.9586141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac18074.2021.9586141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 58th ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100709033","display_name":"Jianqi Zhao","orcid":"https://orcid.org/0009-0006-6647-282X"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianqi Zhao","raw_affiliation_strings":["Department of Computer Science and Technology, Super Scientific Software Laboratory, China University of Petroleum-Beijing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Super Scientific Software Laboratory, China University of Petroleum-Beijing, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112305832","display_name":"Yao Wen","orcid":null},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yao Wen","raw_affiliation_strings":["Department of Computer Science and Technology, Super Scientific Software Laboratory, China University of Petroleum-Beijing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Super Scientific Software Laboratory, China University of Petroleum-Beijing, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030675373","display_name":"Yuchen Luo","orcid":"https://orcid.org/0000-0003-0202-3727"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Luo","raw_affiliation_strings":["Department of Computer Science and Technology, Super Scientific Software Laboratory, China University of Petroleum-Beijing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Super Scientific Software Laboratory, China University of Petroleum-Beijing, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057257864","display_name":"Zhou Jin","orcid":"https://orcid.org/0000-0002-0632-9494"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhou Jin","raw_affiliation_strings":["Department of Computer Science and Technology, Super Scientific Software Laboratory, China University of Petroleum-Beijing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Super Scientific Software Laboratory, China University of Petroleum-Beijing, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100444152","display_name":"Weifeng Liu","orcid":"https://orcid.org/0000-0002-2150-5759"},"institutions":[{"id":"https://openalex.org/I204553293","display_name":"China University of Petroleum, Beijing","ror":"https://ror.org/041qf4r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I204553293"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weifeng Liu","raw_affiliation_strings":["Department of Computer Science and Technology, Super Scientific Software Laboratory, China University of Petroleum-Beijing, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Technology, Super Scientific Software Laboratory, China University of Petroleum-Beijing, Beijing, China","institution_ids":["https://openalex.org/I204553293"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069323283","display_name":"Zhenya Zhou","orcid":"https://orcid.org/0000-0002-2645-6386"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenya Zhou","raw_affiliation_strings":["Huada Empyrean Software Co. Ltd, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Huada Empyrean Software Co. Ltd, Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":30,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"42"},"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":0.9993000030517578,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9952999949455261,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.810705304145813},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7926622629165649},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.5799462199211121},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.573330819606781},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5574227571487427},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.5300031900405884},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.4839742183685303},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.47811976075172424},{"id":"https://openalex.org/keywords/titan","display_name":"Titan (rocket family)","score":0.4419199526309967},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.4277094900608063},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4144071936607361},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.41388243436813354},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3519861698150635}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.810705304145813},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7926622629165649},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.5799462199211121},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.573330819606781},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5574227571487427},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.5300031900405884},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.4839742183685303},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.47811976075172424},{"id":"https://openalex.org/C50805821","wikidata":"https://www.wikidata.org/wiki/Q1136670","display_name":"Titan (rocket family)","level":2,"score":0.4419199526309967},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.4277094900608063},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4144071936607361},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.41388243436813354},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3519861698150635},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"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/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","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":1,"locations":[{"id":"doi:10.1109/dac18074.2021.9586141","is_oa":false,"landing_page_url":"https://doi.org/10.1109/dac18074.2021.9586141","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 58th ACM/IEEE Design Automation Conference (DAC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":18,"referenced_works":["https://openalex.org/W1959955997","https://openalex.org/W1970009422","https://openalex.org/W1984429368","https://openalex.org/W1998894100","https://openalex.org/W2017509788","https://openalex.org/W2020561008","https://openalex.org/W2035080386","https://openalex.org/W2041999884","https://openalex.org/W2052602889","https://openalex.org/W2074140323","https://openalex.org/W2118076222","https://openalex.org/W2128131218","https://openalex.org/W2130886743","https://openalex.org/W2132450860","https://openalex.org/W2355089277","https://openalex.org/W2469975815","https://openalex.org/W2887698420","https://openalex.org/W3007849603"],"related_works":["https://openalex.org/W2070865675","https://openalex.org/W2170268965","https://openalex.org/W3165899388","https://openalex.org/W4288452443","https://openalex.org/W4236883517","https://openalex.org/W2057774067","https://openalex.org/W3007849603","https://openalex.org/W2523376728","https://openalex.org/W4384637869","https://openalex.org/W2006005151"],"abstract_inverted_index":{"Sparse":[0],"LU":[1,27,79],"factorization":[2,28,80],"is":[3],"one":[4],"of":[5,10,20,53,58,66,133,170],"the":[6,17,54,59,100,104,116,135],"key":[7],"building":[8],"blocks":[9,102,118],"sparse":[11,26,78,153],"direct":[12],"solvers":[13],"and":[14,97,145,165,174,179],"often":[15],"dominates":[16],"computing":[18],"time":[19],"circuit":[21],"simulation":[22],"programs.":[23],"Existing":[24],"GPU-accelerated":[25],"methods":[29,60],"either":[30,119],"offload":[31],"relatively":[32],"small":[33],"dense":[34],"matrix-matrix":[35],"multiplications":[36],"to":[37,44,122,177],"GPU":[38,86,147],"cores,":[39,87],"or":[40,124],"extract":[41],"level-set":[42],"information":[43,110],"parallelize":[45],"elimination":[46,132],"operations":[47],"in":[48,72],"each":[49,91],"level.":[50],"However,":[51],"because":[52],"insufficient":[55],"parallelism,":[56],"neither":[57],"can":[61],"saturate":[62,85],"a":[63,76,95,168],"large":[64],"amount":[65],"compute":[67],"units":[68],"on":[69,112,155,171],"modern":[70],"GPUs.We":[71],"this":[73],"paper":[74],"propose":[75],"synchronization-free":[77],"algorithm":[81],"called":[82],"SFLU.":[83],"To":[84],"our":[88,139,161],"method":[89,140],"lets":[90],"thread":[92,101,117],"block":[93],"eliminate":[94],"column":[96],"runs":[98],"all":[99,115,134],"at":[103],"same":[105],"time.":[106],"Through":[107],"communicating":[108],"dependency":[109],"stored":[111],"global":[113],"memory,":[114],"busy":[120],"wait":[121],"run":[123],"get":[125],"updated":[126],"by":[127,167],"their":[128],"previous":[129],"columns.":[130],"Because":[131],"columns":[136],"work":[137],"concurrently,":[138],"avoids":[141],"any":[142],"barrier":[143],"synchronization":[144],"saturates":[146],"resources.":[148],"By":[149],"benchmarking":[150],"over":[151],"1000":[152],"matrices":[154],"an":[156],"NVIDIA":[157],"Titan":[158],"RTX":[159],"GPU,":[160],"SFLU":[162],"outperforms":[163],"SuperLU":[164],"GLU":[166],"factor":[169],"average":[172],"155.71":[173],"8.21":[175],"(up":[176],"3585.62":[178],"252.66),":[180],"respectively.":[181]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}