{"id":"https://openalex.org/W3093682587","doi":"https://doi.org/10.1109/tcad.2020.3032626","title":"Sparse Tucker Tensor Decomposition on a Hybrid FPGA\u2013CPU Platform","display_name":"Sparse Tucker Tensor Decomposition on a Hybrid FPGA\u2013CPU Platform","publication_year":2020,"publication_date":"2020-10-21","ids":{"openalex":"https://openalex.org/W3093682587","doi":"https://doi.org/10.1109/tcad.2020.3032626","mag":"3093682587"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2020.3032626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2020.3032626","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"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 Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2010.10638","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103126544","display_name":"Weiyun Jiang","orcid":"https://orcid.org/0000-0002-4078-8133"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weiyun Jiang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California at Santa Barbara, Santa Barbara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-4078-8133","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California at Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072440587","display_name":"Kaiqi Zhang","orcid":"https://orcid.org/0000-0002-7923-1594"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaiqi Zhang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California at Santa Barbara, Santa Barbara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California at Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007933442","display_name":"Colin Yu Lin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Colin Yu Lin","raw_affiliation_strings":["Data Center Group, Xilinx, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Data Center Group, Xilinx, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100432889","display_name":"Feng Xing","orcid":"https://orcid.org/0000-0001-7126-057X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Feng Xing","raw_affiliation_strings":["Data Center Group, Xilinx, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7126-057X","affiliations":[{"raw_affiliation_string":"Data Center Group, Xilinx, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100459107","display_name":"Zheng Zhang","orcid":"https://orcid.org/0000-0002-2292-0030"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zheng Zhang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of California at Santa Barbara, Santa Barbara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2292-0030","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of California at Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3594,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.50501672,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"40","issue":"9","first_page":"1864","last_page":"1873"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2605","display_name":"Computational Mathematics"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10575","display_name":"Wireless Communication Networks Research","score":0.9627000093460083,"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/computer-science","display_name":"Computer science","score":0.6772370338439941},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6355847120285034},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.607614278793335},{"id":"https://openalex.org/keywords/sparse-matrix","display_name":"Sparse matrix","score":0.5890139937400818},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.573248028755188},{"id":"https://openalex.org/keywords/matrix-decomposition","display_name":"Matrix decomposition","score":0.5583810806274414},{"id":"https://openalex.org/keywords/kronecker-delta","display_name":"Kronecker delta","score":0.5102639198303223},{"id":"https://openalex.org/keywords/tensor-decomposition","display_name":"Tensor decomposition","score":0.5014307498931885},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.47375422716140747},{"id":"https://openalex.org/keywords/qr-decomposition","display_name":"QR decomposition","score":0.46635404229164124},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.46526387333869934},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3716770112514496},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36003559827804565},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.21322259306907654},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1789841651916504},{"id":"https://openalex.org/keywords/eigenvalues-and-eigenvectors","display_name":"Eigenvalues and eigenvectors","score":0.10317298769950867}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6772370338439941},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6355847120285034},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.607614278793335},{"id":"https://openalex.org/C56372850","wikidata":"https://www.wikidata.org/wiki/Q1050404","display_name":"Sparse matrix","level":3,"score":0.5890139937400818},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.573248028755188},{"id":"https://openalex.org/C42355184","wikidata":"https://www.wikidata.org/wiki/Q1361088","display_name":"Matrix decomposition","level":3,"score":0.5583810806274414},{"id":"https://openalex.org/C39482219","wikidata":"https://www.wikidata.org/wiki/Q192826","display_name":"Kronecker delta","level":2,"score":0.5102639198303223},{"id":"https://openalex.org/C2986737658","wikidata":"https://www.wikidata.org/wiki/Q30103009","display_name":"Tensor decomposition","level":3,"score":0.5014307498931885},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.47375422716140747},{"id":"https://openalex.org/C188060507","wikidata":"https://www.wikidata.org/wiki/Q653242","display_name":"QR decomposition","level":3,"score":0.46635404229164124},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.46526387333869934},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3716770112514496},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36003559827804565},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.21322259306907654},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1789841651916504},{"id":"https://openalex.org/C158693339","wikidata":"https://www.wikidata.org/wiki/Q190524","display_name":"Eigenvalues and eigenvectors","level":2,"score":0.10317298769950867},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","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/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcad.2020.3032626","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2020.3032626","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"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 Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2010.10638","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.10638","pdf_url":"https://arxiv.org/pdf/2010.10638","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2010.10638","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2010.10638","pdf_url":"https://arxiv.org/pdf/2010.10638","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.8100000023841858,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G8116395671","display_name":"SHF:Small: Tensor-Based Algorithm and Hardware Co-Optimization for Neural Network Architecture","funder_award_id":"1817037","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W112411653","https://openalex.org/W127396337","https://openalex.org/W1484523725","https://openalex.org/W1512387364","https://openalex.org/W1601946875","https://openalex.org/W1798945469","https://openalex.org/W1847900072","https://openalex.org/W1981745143","https://openalex.org/W2000215628","https://openalex.org/W2001518794","https://openalex.org/W2004642969","https://openalex.org/W2013912476","https://openalex.org/W2018282388","https://openalex.org/W2024165284","https://openalex.org/W2028087580","https://openalex.org/W2061873838","https://openalex.org/W2073389244","https://openalex.org/W2078841894","https://openalex.org/W2081023708","https://openalex.org/W2100779717","https://openalex.org/W2113055885","https://openalex.org/W2119511382","https://openalex.org/W2121739212","https://openalex.org/W2145305441","https://openalex.org/W2160551639","https://openalex.org/W2507398220","https://openalex.org/W2523567745","https://openalex.org/W2532981702","https://openalex.org/W2560517525","https://openalex.org/W2724545582","https://openalex.org/W2886961401","https://openalex.org/W2896429983","https://openalex.org/W2946624195","https://openalex.org/W2950001020","https://openalex.org/W2950034300","https://openalex.org/W2962881293","https://openalex.org/W2962988160","https://openalex.org/W2963704562","https://openalex.org/W2998487545","https://openalex.org/W3016735325","https://openalex.org/W4299823361","https://openalex.org/W6630579473","https://openalex.org/W6638060716","https://openalex.org/W6741042017","https://openalex.org/W6754114952"],"related_works":["https://openalex.org/W2078349096","https://openalex.org/W2002598339","https://openalex.org/W2150953077","https://openalex.org/W1599936522","https://openalex.org/W1558774265","https://openalex.org/W2006707200","https://openalex.org/W2015045768","https://openalex.org/W1802235332","https://openalex.org/W2398628089","https://openalex.org/W3200716635"],"abstract_inverted_index":{"Recommendation":[0],"systems,":[1],"social":[2],"network":[3],"analysis,":[4],"medical":[5],"imaging,":[6],"and":[7,24,45,54,84,103,123,138,151],"data":[8,18,55],"mining":[9],"often":[10],"involve":[11],"processing":[12],"sparse":[13,48,88],"high-dimensional":[14,17,49],"data.":[15],"Such":[16],"are":[19,57],"naturally":[20],"represented":[21],"as":[22],"tensors,":[23],"they":[25],"cannot":[26],"be":[27],"efficiently":[28],"processed":[29],"by":[30],"conventional":[31],"matrix":[32],"or":[33],"vector":[34],"computations.":[35],"Sparse":[36],"Tucker":[37,89],"decomposition":[38,106],"is":[39],"an":[40],"important":[41],"algorithm":[42,92],"for":[43,67],"compressing":[44],"analyzing":[46],"these":[47],"datasets.":[50,153],"When":[51],"energy":[52,143],"efficiency":[53],"privacy":[56],"major":[58],"concerns,":[59],"hardware":[60],"accelerators":[61],"on":[62,119,127,148],"resource-constraint":[63],"platforms":[64],"become":[65],"crucial":[66],"the":[68,115,124,149],"deployment":[69],"of":[70],"tensor":[71],"algorithms.":[72],"In":[73,111],"this":[74],"work,":[75],"we":[76,113],"propose":[77],"a":[78,120,128],"hybrid":[79,131],"computing":[80],"framework":[81],"containing":[82],"CPU":[83,147],"FPGA":[85,122],"to":[86],"accelerate":[87,114],"factorization.":[90],"This":[91],"has":[93],"three":[94],"main":[95],"modules:":[96],"1)":[97],"tensor-times-matrix":[98],"(TTM);":[99],"2)":[100],"Kronecker":[101],"products;":[102],"3)":[104],"QR":[105],"with":[107,146],"column":[108],"pivoting":[109],"(QRP).":[110],"addition,":[112],"former":[116],"two":[117],"modules":[118],"Xilinx":[121],"latter":[125],"one":[126],"CPU.":[129],"Our":[130],"platform":[132],"achieves$23.6":[133],"\\times":[134],"\\sim":[135],"1091\\times":[136],"$speedup":[137],"over":[139],"93.519%":[140],"~":[141],"99.514%":[142],"savings":[144],"compared":[145],"synthetic":[150],"real-world":[152]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}