{"id":"https://openalex.org/W4280594985","doi":"https://doi.org/10.23919/date54114.2022.9774626","title":"TCX: A Programmable Tensor Processor","display_name":"TCX: A Programmable Tensor Processor","publication_year":2022,"publication_date":"2022-03-14","ids":{"openalex":"https://openalex.org/W4280594985","doi":"https://doi.org/10.23919/date54114.2022.9774626"},"language":"en","primary_location":{"id":"doi:10.23919/date54114.2022.9774626","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date54114.2022.9774626","pdf_url":null,"source":{"id":"https://openalex.org/S4363607924","display_name":"2022 Design, Automation & Test in Europe Conference & Exhibition (DATE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 Design, Automation & Test in Europe Conference & Exhibition (DATE)","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/A5053458110","display_name":"Tailin Liang","orcid":"https://orcid.org/0000-0002-7643-912X"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Tailin Liang","raw_affiliation_strings":["School of Computer Science and Communication Engineering, University of Science and Technology,Beijing,China,100083","Hua Xia General Processor Technologies, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Communication Engineering, University of Science and Technology,Beijing,China,100083","institution_ids":["https://openalex.org/I92403157"]},{"raw_affiliation_string":"Hua Xia General Processor Technologies, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100436101","display_name":"Lei Wang","orcid":"https://orcid.org/0000-0003-1865-8153"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Wang","raw_affiliation_strings":["School of Computer Science and Communication Engineering, University of Science and Technology,Beijing,China,100083"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Communication Engineering, University of Science and Technology,Beijing,China,100083","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101668556","display_name":"Shi Shao-bo","orcid":"https://orcid.org/0000-0003-4172-8906"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaobo Shi","raw_affiliation_strings":["School of Computer Science and Communication Engineering, University of Science and Technology,Beijing,China,100083","Hua Xia General Processor Technologies, Beijing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Communication Engineering, University of Science and Technology,Beijing,China,100083","institution_ids":["https://openalex.org/I92403157"]},{"raw_affiliation_string":"Hua Xia General Processor Technologies, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086798411","display_name":"John Glossner","orcid":"https://orcid.org/0000-0003-0713-2105"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"John Glossner","raw_affiliation_strings":["School of Computer Science and Communication Engineering, University of Science and Technology,Beijing,China,100083","General Processor Technologies, Tarrytown, NY, United States"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Communication Engineering, University of Science and Technology,Beijing,China,100083","institution_ids":["https://openalex.org/I92403157"]},{"raw_affiliation_string":"General Processor Technologies, Tarrytown, NY, United States","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100403817","display_name":"Xiaotong Zhang","orcid":"https://orcid.org/0000-0002-5122-3998"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaotong Zhang","raw_affiliation_strings":["School of Computer Science and Communication Engineering, University of Science and Technology,Beijing,China,100083"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Communication Engineering, University of Science and Technology,Beijing,China,100083","institution_ids":["https://openalex.org/I92403157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5053458110"],"corresponding_institution_ids":["https://openalex.org/I92403157"],"apc_list":null,"apc_paid":null,"fwci":0.2144,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.26895854,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1023","last_page":"1028"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9988999962806702,"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":0.9988999962806702,"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/T12303","display_name":"Tensor decomposition and applications","score":0.9930999875068665,"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/T13650","display_name":"Computational Physics and Python Applications","score":0.9782999753952026,"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/computer-science","display_name":"Computer science","score":0.8224392533302307},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.6163000464439392},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5793852806091309},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5332016348838806},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5329549908638},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4847869277000427},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.46501046419143677},{"id":"https://openalex.org/keywords/tensor-contraction","display_name":"Tensor contraction","score":0.43615081906318665},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.42715543508529663},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3539239168167114},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.32100772857666016},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25450068712234497},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11650702357292175},{"id":"https://openalex.org/keywords/tensor-product","display_name":"Tensor product","score":0.11409080028533936},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0967264473438263}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8224392533302307},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.6163000464439392},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5793852806091309},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5332016348838806},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5329549908638},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4847869277000427},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.46501046419143677},{"id":"https://openalex.org/C124007464","wikidata":"https://www.wikidata.org/wiki/Q428091","display_name":"Tensor contraction","level":3,"score":0.43615081906318665},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.42715543508529663},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3539239168167114},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.32100772857666016},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25450068712234497},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11650702357292175},{"id":"https://openalex.org/C51255310","wikidata":"https://www.wikidata.org/wiki/Q1163016","display_name":"Tensor product","level":2,"score":0.11409080028533936},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0967264473438263},{"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/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","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:10.23919/date54114.2022.9774626","is_oa":false,"landing_page_url":"https://doi.org/10.23919/date54114.2022.9774626","pdf_url":null,"source":{"id":"https://openalex.org/S4363607924","display_name":"2022 Design, Automation & Test in Europe Conference & Exhibition (DATE)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 Design, Automation & Test in Europe Conference & Exhibition (DATE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1998475350","display_name":null,"funder_award_id":"61671056,61971031","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4096362481","display_name":null,"funder_award_id":"2018YFB0704300","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2067523571","https://openalex.org/W2170585292","https://openalex.org/W2185454528","https://openalex.org/W2289252105","https://openalex.org/W2565960208","https://openalex.org/W2604177858","https://openalex.org/W2604319603","https://openalex.org/W2605487586","https://openalex.org/W2734572653","https://openalex.org/W2767864757","https://openalex.org/W2807127337","https://openalex.org/W2963114857","https://openalex.org/W2979042679","https://openalex.org/W3114688520","https://openalex.org/W3184606595"],"related_works":["https://openalex.org/W1887380982","https://openalex.org/W2385280846","https://openalex.org/W2140205332","https://openalex.org/W2060415987","https://openalex.org/W4319065663","https://openalex.org/W2519254393","https://openalex.org/W2588463123","https://openalex.org/W4390617408","https://openalex.org/W2550374317","https://openalex.org/W2159645853"],"abstract_inverted_index":{"Neural":[0],"network":[1],"processors":[2],"and":[3,34,47,61,127,143,156,170,185],"accelerators":[4],"are":[5],"domain-specific":[6],"architectures":[7],"deployed":[8],"to":[9,95,166,200],"solve":[10],"the":[11,74,160],"high":[12],"computational":[13],"requirements":[14,133],"of":[15,73,97,149,163],"deep":[16],"learning":[17],"algorithms.":[18],"This":[19],"paper":[20],"proposes":[21],"a":[22,41,193],"new":[23,124],"instruction":[24],"set":[25],"extension":[26],"for":[27,65,108,117,146,173],"tensor":[28,37,50,76,85,111,119,125,136,150,164],"computing,":[29],"TCX,":[30],"with":[31,198],"RISC-style":[32],"instructions":[33,129],"variable":[35],"length":[36],"extensions.":[38],"It":[39,52,204],"features":[40],"multidimensional":[42],"register":[43,101,120],"file,":[44],"dimension":[45],"registers,":[46],"fully":[48],"generic":[49],"instructions.":[51],"can":[53],"be":[54],"seamlessly":[55],"integrated":[56],"into":[57],"existing":[58],"RISC":[59],"ISAs":[60],"provides":[62],"software":[63],"compatibility":[64],"scalable":[66,88],"hardware":[67],"implementations.":[68],"We":[69,122,158],"present":[70],"an":[71,80],"implementation":[72],"TCX":[75,179],"computing":[77],"accelerator":[78,86],"using":[79,192],"out-of-order":[81],"microarchitecture":[82],"implementation.":[83],"The":[84,178],"is":[87,104],"in":[89,215],"computation":[90,144,161],"units":[91],"from":[92],"several":[93,174],"hundred":[94],"tens":[96],"thousands.":[98],"An":[99],"optimized":[100],"renaming":[102],"mechanism":[103],"described":[105],"which":[106],"allows":[107],"many":[109],"physical":[110],"registers":[112],"without":[113],"requiring":[114],"architectural":[115],"support":[116],"large":[118],"names.":[121],"describe":[123],"load":[126],"store":[128],"that":[130],"reduce":[131],"bandwidth":[132,142],"based":[134],"on":[135],"dimensions.":[137],"Implementations":[138],"may":[139],"balance":[140,167],"data":[141],"utilization":[145],"different":[147],"types":[148],"computations":[151],"such":[152],"as":[153],"element-wise,":[154],"depth-wise,":[155],"matrix-multiplication.":[157],"characterize":[159],"precision":[162],"operations":[165,189],"area,":[168],"generality,":[169],"accuracy":[171],"loss":[172],"well-known":[175],"neural":[176],"networks.":[177],"processor":[180],"runs":[181],"at":[182],"1":[183],"GHz":[184],"sustains":[186],"8.2":[187],"Tera":[188],"per":[190,213],"second":[191],"4096":[194],"multiplication-accumulation":[195],"compute":[196],"unit":[197],"up":[199],"98.83%":[201],"MAC":[202],"utilization.":[203],"consumes":[205],"12.8":[206],"square":[207],"millimeters":[208],"while":[209],"dissipating":[210],"0.46":[211],"Watts":[212],"TOP":[214],"TSMC":[216],"28nm":[217],"technology.":[218]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}