{"id":"https://openalex.org/W4306755820","doi":"https://doi.org/10.1145/3568310","title":"TCX: A RISC Style Tensor Computing Extension and a Programmable Tensor Processor","display_name":"TCX: A RISC Style Tensor Computing Extension and a Programmable Tensor Processor","publication_year":2022,"publication_date":"2022-10-19","ids":{"openalex":"https://openalex.org/W4306755820","doi":"https://doi.org/10.1145/3568310"},"language":"en","primary_location":{"id":"doi:10.1145/3568310","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3568310","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing 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/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":["University of Science and Technology Beijing, China and Hua Xia General Processor Technologies, Haidian Qu, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7643-912X","affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, China and Hua Xia General Processor Technologies, Haidian Qu, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"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":["University of Science and Technology Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1865-8153","affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, China","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":["University of Science and Technology Beijing, China and Hua Xia General Processor Technologies, Haidian Qu, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-4172-8906","affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, China and Hua Xia General Processor Technologies, Haidian Qu, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"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":["University of Science and Technology Beijing, China and General Processor Technologies, New York, USA"],"raw_orcid":"https://orcid.org/0000-0003-0713-2105","affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, China and General Processor Technologies, New York, USA","institution_ids":["https://openalex.org/I92403157"]}]},{"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":["University of Science and Technology Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5122-3998","affiliations":[{"raw_affiliation_string":"University of Science and Technology Beijing, Beijing, China","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":0.4669,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61044321,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":"22","issue":"3","first_page":"1","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9887999892234802,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9855999946594238,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.8569605946540833},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.5868139863014221},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.5277854800224304},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5093332529067993},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.48426005244255066},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.47327542304992676},{"id":"https://openalex.org/keywords/tensor-contraction","display_name":"Tensor contraction","score":0.4731220602989197},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4529508650302887},{"id":"https://openalex.org/keywords/floating-point","display_name":"Floating point","score":0.42459604144096375},{"id":"https://openalex.org/keywords/microarchitecture","display_name":"Microarchitecture","score":0.4100243151187897},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.28345954418182373},{"id":"https://openalex.org/keywords/tensor-product","display_name":"Tensor product","score":0.12116211652755737},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.10338062047958374},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08644673228263855}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8569605946540833},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.5868139863014221},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.5277854800224304},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5093332529067993},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.48426005244255066},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.47327542304992676},{"id":"https://openalex.org/C124007464","wikidata":"https://www.wikidata.org/wiki/Q428091","display_name":"Tensor contraction","level":3,"score":0.4731220602989197},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4529508650302887},{"id":"https://openalex.org/C84211073","wikidata":"https://www.wikidata.org/wiki/Q117879","display_name":"Floating point","level":2,"score":0.42459604144096375},{"id":"https://openalex.org/C107598950","wikidata":"https://www.wikidata.org/wiki/Q259864","display_name":"Microarchitecture","level":2,"score":0.4100243151187897},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.28345954418182373},{"id":"https://openalex.org/C51255310","wikidata":"https://www.wikidata.org/wiki/Q1163016","display_name":"Tensor product","level":2,"score":0.12116211652755737},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.10338062047958374},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08644673228263855},{"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/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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3568310","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3568310","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Embedded Computing Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6593575852","display_name":null,"funder_award_id":"FRF-GF-19-018B","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G8155631574","display_name":null,"funder_award_id":"61971031, 61671056","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation 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/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2000967104","https://openalex.org/W2048266589","https://openalex.org/W2067523571","https://openalex.org/W2152839228","https://openalex.org/W2170585292","https://openalex.org/W2185454528","https://openalex.org/W2233116163","https://openalex.org/W2283605469","https://openalex.org/W2289252105","https://openalex.org/W2540279855","https://openalex.org/W2604319603","https://openalex.org/W2605487586","https://openalex.org/W2611105550","https://openalex.org/W2613264175","https://openalex.org/W2734572653","https://openalex.org/W2766143712","https://openalex.org/W2767864757","https://openalex.org/W2807127337","https://openalex.org/W2945146780","https://openalex.org/W2963114857","https://openalex.org/W2963145956","https://openalex.org/W2979042679","https://openalex.org/W3004127905","https://openalex.org/W3015980402","https://openalex.org/W3034297393","https://openalex.org/W3082020764","https://openalex.org/W3114688520","https://openalex.org/W3117961507","https://openalex.org/W3123542955","https://openalex.org/W3184606595","https://openalex.org/W4220782773","https://openalex.org/W4230989867"],"related_works":["https://openalex.org/W4250432526","https://openalex.org/W2101536355","https://openalex.org/W2171175484","https://openalex.org/W2085872434","https://openalex.org/W2883183116","https://openalex.org/W2026084820","https://openalex.org/W2562747857","https://openalex.org/W4308095153","https://openalex.org/W4213087105","https://openalex.org/W4391013600"],"abstract_inverted_index":{"Neural":[0],"network":[1],"processors":[2],"and":[3,52,68,134,150,163,177,192],"accelerators":[4],"are":[5],"domain-specific":[6],"architectures":[7],"deployed":[8],"to":[9,102,173],"solve":[10],"the":[11,83,167],"high":[12],"computational":[13],"requirements":[14,140],"of":[15,82,104,156,170],"deep":[16],"learning":[17],"algorithms.":[18],"This":[19],"article":[20],"proposes":[21],"a":[22,46,78,200],"new":[23,131],"instruction":[24],"set":[25],"extension":[26],"for":[27,72,115,124,153,180],"tensor":[28,42,55,79,84,92,118,126,132,142,157,171],"computing,":[29],"TCX,":[30],"using":[31,86,141,199],"Reduced":[32],"Instruction":[33,65],"Set":[34,66],"Computer":[35],"(RISC)":[36],"instructions":[37,136],"enhanced":[38],"with":[39],"variable":[40],"length":[41],"extensions.":[43],"It":[44,57,205],"features":[45],"multi-dimensional":[47],"register":[48,108,127],"file,":[49],"dimension":[50,143],"registers,":[51],"fully":[53],"generic":[54],"instructions.":[56],"can":[58],"be":[59],"seamlessly":[60],"integrated":[61],"into":[62],"existing":[63],"RISC":[64,89],"Architectures":[67],"provides":[69],"software":[70],"compatibility":[71],"scalable":[73,95],"hardware":[74],"implementations.":[75],"We":[76,129,165],"present":[77],"accelerator":[80,93],"implementation":[81],"extensions":[85],"an":[87],"out-of-order":[88],"microarchitecture.":[90],"The":[91,185],"is":[94,111],"in":[96,213],"computation":[97,151,168],"units":[98],"from":[99],"several":[100,181],"hundred":[101],"tens":[103],"thousands.":[105],"An":[106],"optimized":[107],"renaming":[109],"mechanism":[110],"described":[112],"that":[113,137],"allows":[114],"many":[116],"physical":[117],"registers":[119],"without":[120],"requiring":[121],"architectural":[122],"support":[123],"large":[125],"names.":[128],"describe":[130],"load":[133],"store":[135],"reduce":[138],"bandwidth":[139,149],"registers.":[144],"Implementations":[145],"may":[146],"balance":[147,174],"data":[148],"utilization":[152],"different":[154],"types":[155],"computations":[158],"such":[159],"as":[160],"element-wise,":[161],"depthwise,":[162],"matrix-multiplication.":[164],"characterize":[166],"precision":[169],"operations":[172,196],"area,":[175],"generality,":[176],"accuracy":[178],"loss":[179],"well-known":[182],"neural":[183],"networks.":[184],"TCX":[186],"processor":[187],"runs":[188],"at":[189],"1":[190],"GHz":[191],"sustains":[193],"8.2":[194],"Tera":[195],"per":[197],"second":[198],"4,096":[201],"multiply-accumulate":[202],"compute":[203],"unit.":[204],"consumes":[206],"12.8":[207],"mm":[208],"2":[209],"while":[210],"dissipating":[211],"0.46W/TOPs":[212],"TSMC":[214],"28-nm":[215],"technology.":[216]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}