{"id":"https://openalex.org/W2783477199","doi":"https://doi.org/10.1109/asicon.2017.8252462","title":"Parallel sparse LU decomposition using FPGA with an efficient cache architecture","display_name":"Parallel sparse LU decomposition using FPGA with an efficient cache architecture","publication_year":2017,"publication_date":"2017-10-01","ids":{"openalex":"https://openalex.org/W2783477199","doi":"https://doi.org/10.1109/asicon.2017.8252462","mag":"2783477199"},"language":"en","primary_location":{"id":"doi:10.1109/asicon.2017.8252462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asicon.2017.8252462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 12th International Conference on ASIC (ASICON)","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/A5069736192","display_name":"Xiang Ge","orcid":"https://orcid.org/0000-0001-5975-8260"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Ge","raw_affiliation_strings":["State Key Lab of ASIC & System, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of ASIC & System, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020841047","display_name":"Hengliang Zhu","orcid":"https://orcid.org/0000-0002-0338-9256"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hengliang Zhu","raw_affiliation_strings":["State Key Lab of ASIC & System, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of ASIC & System, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045464812","display_name":"Fan Yang","orcid":"https://orcid.org/0000-0003-2164-8175"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fan Yang","raw_affiliation_strings":["State Key Lab of ASIC & System, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of ASIC & System, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002732486","display_name":"Lingli Wang","orcid":"https://orcid.org/0000-0002-0579-3527"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lingli Wang","raw_affiliation_strings":["State Key Lab of ASIC & System, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of ASIC & System, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064213921","display_name":"Xuan Zeng","orcid":"https://orcid.org/0000-0002-8097-4053"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuan Zeng","raw_affiliation_strings":["State Key Lab of ASIC & System, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"State Key Lab of ASIC & System, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4785,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.69344691,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"259","last_page":"262"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11697","display_name":"Numerical Methods and Algorithms","score":0.9995999932289124,"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/T11697","display_name":"Numerical Methods and Algorithms","score":0.9995999932289124,"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":0.9994000196456909,"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"}},{"id":"https://openalex.org/T10792","display_name":"Matrix Theory and Algorithms","score":0.9987999796867371,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8642324209213257},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8221977949142456},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.757918119430542},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.7233888506889343},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5981035828590393},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.5859847664833069},{"id":"https://openalex.org/keywords/cache-pollution","display_name":"Cache pollution","score":0.5763675570487976},{"id":"https://openalex.org/keywords/smart-cache","display_name":"Smart Cache","score":0.5530062913894653},{"id":"https://openalex.org/keywords/cache-invalidation","display_name":"Cache invalidation","score":0.551888108253479},{"id":"https://openalex.org/keywords/cache-oblivious-algorithm","display_name":"Cache-oblivious algorithm","score":0.48997560143470764},{"id":"https://openalex.org/keywords/page-cache","display_name":"Page cache","score":0.4854326844215393},{"id":"https://openalex.org/keywords/lu-decomposition","display_name":"LU decomposition","score":0.47840389609336853},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.4590607285499573},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.1634361743927002}],"concepts":[{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8642324209213257},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8221977949142456},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.757918119430542},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.7233888506889343},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5981035828590393},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.5859847664833069},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.5763675570487976},{"id":"https://openalex.org/C167713795","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"Smart Cache","level":5,"score":0.5530062913894653},{"id":"https://openalex.org/C25536678","wikidata":"https://www.wikidata.org/wiki/Q5015977","display_name":"Cache invalidation","level":5,"score":0.551888108253479},{"id":"https://openalex.org/C59687516","wikidata":"https://www.wikidata.org/wiki/Q5015938","display_name":"Cache-oblivious algorithm","level":5,"score":0.48997560143470764},{"id":"https://openalex.org/C36340418","wikidata":"https://www.wikidata.org/wiki/Q7124288","display_name":"Page cache","level":5,"score":0.4854326844215393},{"id":"https://openalex.org/C123213974","wikidata":"https://www.wikidata.org/wiki/Q833089","display_name":"LU decomposition","level":4,"score":0.47840389609336853},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.4590607285499573},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.1634361743927002},{"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/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/asicon.2017.8252462","is_oa":false,"landing_page_url":"https://doi.org/10.1109/asicon.2017.8252462","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE 12th International Conference on ASIC (ASICON)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1568811919","https://openalex.org/W1988420772","https://openalex.org/W2017431061","https://openalex.org/W2020561008","https://openalex.org/W2030909247","https://openalex.org/W2051917325","https://openalex.org/W2074093855","https://openalex.org/W2106969188","https://openalex.org/W2123969616","https://openalex.org/W2147542748","https://openalex.org/W2160106215","https://openalex.org/W2503125224"],"related_works":["https://openalex.org/W2098406302","https://openalex.org/W2535115842","https://openalex.org/W2546991807","https://openalex.org/W2734782074","https://openalex.org/W2076114130","https://openalex.org/W2020176098","https://openalex.org/W2121191383","https://openalex.org/W1584415117","https://openalex.org/W1967490696","https://openalex.org/W2500877097"],"abstract_inverted_index":{"LU":[0,29,43,71],"decomposition":[1,44],"is":[2,47,52,74],"widely":[3],"used":[4,111],"in":[5],"the":[6,28,55,61,66,70,79,102,107,115,150],"field":[7],"of":[8,69,109,129],"numerical":[9],"analysis":[10],"and":[11,91,105],"engineering":[12],"to":[13,26,77,112],"solve":[14],"large-scale":[15],"sparse":[16,42],"linear":[17],"equations.":[18],"The":[19,49,97,120,139],"complex":[20],"data":[21,117],"dependency":[22,68,83],"makes":[23],"it":[24],"difficult":[25],"parallelize":[27],"decomposition.":[30,72],"In":[31],"this":[32],"paper,":[33],"an":[34,37],"architecture":[35,51,94],"with":[36,132,149],"efficient":[38,88],"cache":[39,89,99,103,110,140,152],"for":[40],"parallel":[41],"using":[45,60],"FPGA":[46],"proposed.":[48,96],"proposed":[50,98,151],"based":[53],"on":[54,118,135,147],"Gilbert-Peierls":[56],"(G-P)":[57],"algorithm.":[58],"By":[59],"elimination":[62],"graph,":[63],"we":[64],"find":[65],"column":[67],"It":[73],"thus":[75],"possible":[76],"exploit":[78],"parallelism.":[80],"Through":[81],"a":[82,85],"table,":[84],"simple":[86],"but":[87],"strategy":[90,100],"its":[92],"corresponding":[93],"are":[95],"avoids":[101],"miss":[104],"reduces":[106],"size":[108,141],"store":[113],"all":[114],"intermediate":[116],"chip.":[119],"experiment":[121],"demonstrates":[122],"that,":[123],"our":[124],"design":[125],"can":[126,142],"achieve":[127],"speedup":[128],"2.85x-10.27x,":[130],"compared":[131],"UMFPACK":[133],"running":[134],"general":[136],"purpose":[137],"processors.":[138],"be":[143],"reduced":[144],"by":[145],"50.93%":[146],"average":[148],"strategy.":[153]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}