{"id":"https://openalex.org/W3171753205","doi":"https://doi.org/10.1109/tvlsi.2021.3080318","title":"An Efficient Parallel Processor for Dense Tensor Computation","display_name":"An Efficient Parallel Processor for Dense Tensor Computation","publication_year":2021,"publication_date":"2021-05-27","ids":{"openalex":"https://openalex.org/W3171753205","doi":"https://doi.org/10.1109/tvlsi.2021.3080318","mag":"3171753205"},"language":"en","primary_location":{"id":"doi:10.1109/tvlsi.2021.3080318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2021.3080318","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"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 Very Large Scale Integration (VLSI) Systems","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/A5031974682","display_name":"Wei-pei Huang","orcid":"https://orcid.org/0000-0002-9583-4811"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Wei-Pei Huang","raw_affiliation_strings":["City University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077847474","display_name":"Ray C. C. Cheung","orcid":"https://orcid.org/0000-0002-6764-0729"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Ray C. C. Cheung","raw_affiliation_strings":["City University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100644375","display_name":"Hong Yan","orcid":"https://orcid.org/0000-0001-9661-3095"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Hong Yan","raw_affiliation_strings":["City University of Hong Kong, Hong Kong"],"affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I168719708"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5031974682"],"corresponding_institution_ids":["https://openalex.org/I168719708"],"apc_list":null,"apc_paid":null,"fwci":0.4024,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.51874244,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"29","issue":"7","first_page":"1335","last_page":"1347"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12303","display_name":"Tensor decomposition and applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9969000220298767,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9635999798774719,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6921111941337585},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.654197096824646},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6425503492355347},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.621697723865509},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6009705066680908},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.5874199271202087},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5727642774581909},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.5264034271240234},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.4311806559562683},{"id":"https://openalex.org/keywords/chip","display_name":"Chip","score":0.4189434349536896},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3449048697948456},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3219149112701416},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3066657483577728},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.23132160305976868},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.11934778094291687},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11243724822998047},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.08862826228141785}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6921111941337585},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.654197096824646},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6425503492355347},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.621697723865509},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6009705066680908},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.5874199271202087},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5727642774581909},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.5264034271240234},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.4311806559562683},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.4189434349536896},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3449048697948456},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3219149112701416},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3066657483577728},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.23132160305976868},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.11934778094291687},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11243724822998047},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.08862826228141785},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tvlsi.2021.3080318","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2021.3080318","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"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 Very Large Scale Integration (VLSI) Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G4946508935","display_name":null,"funder_award_id":"9610460","funder_id":"https://openalex.org/F4320309893","funder_display_name":"City University of Hong Kong"}],"funders":[{"id":"https://openalex.org/F4320309893","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23"},{"id":"https://openalex.org/F4320321920","display_name":"Innovation and Technology Commission","ror":"https://ror.org/04vf9tr09"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1511885491","https://openalex.org/W2013506888","https://openalex.org/W2024165284","https://openalex.org/W2025603201","https://openalex.org/W2100247557","https://openalex.org/W2119412403","https://openalex.org/W2131316979","https://openalex.org/W2148507357","https://openalex.org/W2469230926","https://openalex.org/W2523567745","https://openalex.org/W2528907418","https://openalex.org/W2544822491","https://openalex.org/W2767946586","https://openalex.org/W2950001020","https://openalex.org/W2998487545","https://openalex.org/W3008772580","https://openalex.org/W4312258136","https://openalex.org/W6729203000"],"related_works":["https://openalex.org/W2067951144","https://openalex.org/W1572523360","https://openalex.org/W1543798151","https://openalex.org/W2622518229","https://openalex.org/W2747563384","https://openalex.org/W2273364576","https://openalex.org/W2791204867","https://openalex.org/W2153237593","https://openalex.org/W3101543398","https://openalex.org/W2125153270"],"abstract_inverted_index":{"Nowadays,":[0],"many":[1],"data":[2,100,133,160],"are":[3,6],"multidimensional,":[4],"which":[5,217],"called":[7],"tensors.":[8],"Tensor":[9],"computations":[10],"have":[11,21],"been":[12,22,29,141,204],"applied":[13],"in":[14,84],"different":[15],"fields":[16],"and":[17,46,66,70,88,98,108],"various":[18],"software":[19],"libraries":[20],"developed.":[23],"However,":[24],"not":[25],"much":[26],"attention":[27],"has":[28,140,203],"received":[30],"for":[31,52,64,169,198],"developing":[32],"a":[33,219],"hardware":[34],"architecture":[35],"to":[36,208],"accelerate":[37],"the":[38,53,91,103,124,129,132,147,151,172,176,201,212],"tensor":[39,55,74,164],"computations.":[40],"In":[41,195],"this":[42],"article,":[43],"an":[44],"efficient":[45],"unified":[47],"processing":[48],"element":[49],"(PE)":[50],"array":[51,61,106],"3-D":[54,158],"computation":[56,96],"is":[57,62,82,123,167,218],"demonstrated.":[58],"Our":[59,80],"PE":[60],"optimized":[63],"thin":[65],"tall":[67],"tensor-matrix":[68],"multiplication":[69],"two":[71,182],"types":[72],"of":[73,131],"times":[75,183],"matrices":[76],"chain":[77],"(TTMc)":[78],"operations.":[79],"design":[81],"evaluated":[83],"three":[85],"study":[86],"cases":[87],"compared":[89,145,189,210],"with":[90,146,190,211],"state-of-the-art":[92,148],"design.":[93],"By":[94],"using":[95],"partition":[97],"rearrangement,":[99],"movement":[101],"between":[102],"field-programmable":[104],"gate":[105],"(FPGA)":[107],"off-chip":[109],"DDR":[110],"memory":[111],"can":[112],"be":[113],"reduced":[114],"by":[115,143,163,179,206,215],"O(I":[116],"<sup":[117],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[118],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[119],"),":[120],"where":[121],"I":[122],"maximum":[125],"range":[126],"among":[127],"all":[128],"dimensions":[130],"tensor.":[134],"For":[135,171],"TTMc":[136],"implementation,":[137],"clock":[138],"frequency":[139],"increased":[142],"18%":[144],"implementation":[149,188],"on":[150,157,185,193],"same":[152],"FPGA":[153,187],"chip.":[154],"An":[155],"experiment":[156],"volumetric":[159],"set":[161],"rendering":[162],"approximation":[165],"method":[166],"conducted":[168],"demonstration.":[170],"bricks":[173],"reconstruction":[174],"process,":[175],"runtime":[177,202],"decreased":[178,205],"50%,":[180],"i.e.,":[181],"faster,":[184],"our":[186],"that":[191],"running":[192],"GPU.":[194],"CANDECOMP/PARAFAC":[196],"decomposition,":[197],"one":[199],"iteration,":[200],"up":[207],"93%":[209],"programs":[213],"implemented":[214],"Tensorly,":[216],"python":[220],"library.":[221]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}