{"id":"https://openalex.org/W2344713096","doi":"https://doi.org/10.1145/2927964.2927978","title":"A Configurable Architecture for Sparse LU Decomposition on Matrices with Arbitrary Patterns","display_name":"A Configurable Architecture for Sparse LU Decomposition on Matrices with Arbitrary Patterns","publication_year":2016,"publication_date":"2016-04-22","ids":{"openalex":"https://openalex.org/W2344713096","doi":"https://doi.org/10.1145/2927964.2927978","mag":"2344713096"},"language":"en","primary_location":{"id":"doi:10.1145/2927964.2927978","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2927964.2927978","pdf_url":null,"source":{"id":"https://openalex.org/S4210193905","display_name":"ACM SIGARCH Computer Architecture News","issn_l":"0163-5964","issn":["0163-5964","1943-5851"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320740","host_organization_name":"ACM SIGARCH","host_organization_lineage":["https://openalex.org/P4310320740"],"host_organization_lineage_names":["ACM SIGARCH"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGARCH Computer Architecture News","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/A5100740743","display_name":"Xinying Wang","orcid":"https://orcid.org/0000-0002-6663-9232"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinying Wang","raw_affiliation_strings":["Iowa State University, Ames, Iowa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iowa State University, Ames, Iowa","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026774201","display_name":"Phillip H. Jones","orcid":"https://orcid.org/0000-0002-8220-7552"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Phillip H. Jones","raw_affiliation_strings":["Iowa State University, Ames, Iowa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iowa State University, Ames, Iowa","institution_ids":["https://openalex.org/I173911158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081541206","display_name":"Joseph Zambreno","orcid":"https://orcid.org/0000-0002-0566-5744"},"institutions":[{"id":"https://openalex.org/I173911158","display_name":"Iowa State University","ror":"https://ror.org/04rswrd78","country_code":"US","type":"education","lineage":["https://openalex.org/I173911158"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joseph Zambreno","raw_affiliation_strings":["Iowa State University, Ames, Iowa"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Iowa State University, Ames, Iowa","institution_ids":["https://openalex.org/I173911158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.7209,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.74478647,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"43","issue":"4","first_page":"76","last_page":"81"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9990000128746033,"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/T10363","display_name":"Low-power high-performance VLSI design","score":0.9987000226974487,"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/sparse-matrix","display_name":"Sparse matrix","score":0.7645136117935181},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7089109420776367},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.7020869851112366},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6910001039505005},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6708064675331116},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5867293477058411},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5800521373748779},{"id":"https://openalex.org/keywords/sparse-approximation","display_name":"Sparse approximation","score":0.5739907026290894},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5388498306274414},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.4961183965206146},{"id":"https://openalex.org/keywords/factorization","display_name":"Factorization","score":0.48635321855545044},{"id":"https://openalex.org/keywords/domain-decomposition-methods","display_name":"Domain decomposition methods","score":0.4717503488063812},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4658278822898865},{"id":"https://openalex.org/keywords/incomplete-lu-factorization","display_name":"Incomplete LU factorization","score":0.45280104875564575},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3750649392604828},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.13875159621238708}],"concepts":[{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.7645136117935181},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7089109420776367},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.7020869851112366},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6910001039505005},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6708064675331116},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5867293477058411},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5800521373748779},{"id":"https://openalex.org/C124066611","wikidata":"https://www.wikidata.org/wiki/Q28684319","display_name":"Sparse approximation","level":2,"score":0.5739907026290894},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5388498306274414},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.4961183965206146},{"id":"https://openalex.org/C187834632","wikidata":"https://www.wikidata.org/wiki/Q188804","display_name":"Factorization","level":2,"score":0.48635321855545044},{"id":"https://openalex.org/C198880260","wikidata":"https://www.wikidata.org/wiki/Q5289813","display_name":"Domain decomposition methods","level":3,"score":0.4717503488063812},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4658278822898865},{"id":"https://openalex.org/C134978465","wikidata":"https://www.wikidata.org/wiki/Q1654069","display_name":"Incomplete LU factorization","level":4,"score":0.45280104875564575},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3750649392604828},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.13875159621238708},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","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},{"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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C135628077","wikidata":"https://www.wikidata.org/wiki/Q220184","display_name":"Finite element method","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2927964.2927978","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2927964.2927978","pdf_url":null,"source":{"id":"https://openalex.org/S4210193905","display_name":"ACM SIGARCH Computer Architecture News","issn_l":"0163-5964","issn":["0163-5964","1943-5851"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320740","host_organization_name":"ACM SIGARCH","host_organization_lineage":["https://openalex.org/P4310320740"],"host_organization_lineage_names":["ACM SIGARCH"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM SIGARCH Computer Architecture News","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":16,"referenced_works":["https://openalex.org/W1738124305","https://openalex.org/W1987414064","https://openalex.org/W2003105834","https://openalex.org/W2022304554","https://openalex.org/W2022842990","https://openalex.org/W2035080386","https://openalex.org/W2041999884","https://openalex.org/W2051917325","https://openalex.org/W2055094346","https://openalex.org/W2063675347","https://openalex.org/W2098012923","https://openalex.org/W2132450860","https://openalex.org/W2153189923","https://openalex.org/W2160106215","https://openalex.org/W2503125224","https://openalex.org/W2798909945"],"related_works":["https://openalex.org/W2964496048","https://openalex.org/W2904573237","https://openalex.org/W1997196200","https://openalex.org/W3014000538","https://openalex.org/W2386810910","https://openalex.org/W4246966070","https://openalex.org/W156354643","https://openalex.org/W2051917325","https://openalex.org/W2031938882","https://openalex.org/W1538827969"],"abstract_inverted_index":{"Sparse":[0],"LU":[1,49,83],"decomposition":[2,84],"has":[3],"been":[4,44,63],"widely":[5],"used":[6],"to":[7,46,65,128],"solve":[8],"sparse":[9,48,82,91],"linear":[10],"systems":[11],"of":[12,69,100,117,142],"equations":[13],"found":[14],"in":[15],"many":[16],"scientific":[17],"and":[18,28,89,105],"engineering":[19],"applications,":[20],"such":[21],"as":[22],"circuit":[23],"simulation,":[24],"power":[25],"system":[26],"modeling":[27],"computer":[29],"vision.":[30],"However,":[31],"it":[32],"is":[33,112],"considered":[34],"a":[35,126,139],"computationally":[36],"expensive":[37],"factorization":[38],"tool.":[39],"While":[40],"parallel":[41],"implementations":[42],"have":[43,62],"explored":[45],"accelerate":[47],"decomposition,":[50],"irregular":[51],"sparsity":[52,67,95,143],"patterns":[53,68],"often":[54],"limit":[55],"their":[56],"performance":[57],"gains.":[58],"Prior":[59],"FPGA-based":[60],"accelerators":[61],"customized":[64],"domain-specific":[66],"pre-ordered":[70],"symmetric":[71,88],"matrices.":[72],"In":[73],"this":[74],"paper,":[75],"we":[76],"present":[77],"an":[78,132],"efficient":[79],"architecture":[80,102],"for":[81,136],"that":[85],"supports":[86],"both":[87],"asymmetric":[90],"matrices":[92,119],"with":[93],"arbitrary":[94],"patterns.":[96,144],"The":[97],"control":[98],"structure":[99],"our":[101],"parallelizes":[103],"computation":[104],"pivoting":[106],"operations.":[107],"Also,":[108],"on-chip":[109],"resource":[110],"utilization":[111],"configured":[113],"based":[114],"on":[115],"properties":[116],"the":[118],"being":[120],"processed.":[121],"Our":[122],"experimental":[123],"results":[124],"show":[125],"1:6":[127],"14x":[129],"speedup":[130],"over":[131],"optimized":[133],"software":[134],"implementation":[135],"benchmarks":[137],"containing":[138],"wide":[140],"range":[141]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}