{"id":"https://openalex.org/W4404035520","doi":"https://doi.org/10.1109/tcad.2024.3490173","title":"HyCTor: A Hybrid CNN-Transformer Network Accelerator With Flexible Weight/Output Stationary Dataflow and Multicore Extension","display_name":"HyCTor: A Hybrid CNN-Transformer Network Accelerator With Flexible Weight/Output Stationary Dataflow and Multicore Extension","publication_year":2024,"publication_date":"2024-11-04","ids":{"openalex":"https://openalex.org/W4404035520","doi":"https://doi.org/10.1109/tcad.2024.3490173"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2024.3490173","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2024.3490173","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":["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/A5032210663","display_name":"Shuai Yuan","orcid":"https://orcid.org/0000-0002-2490-8027"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shuai Yuan","raw_affiliation_strings":["Department of Micro-Nano Electronics, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-2490-8027","affiliations":[{"raw_affiliation_string":"Department of Micro-Nano Electronics, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101583945","display_name":"Weifeng He","orcid":"https://orcid.org/0000-0002-7753-644X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weifeng He","raw_affiliation_strings":["Department of Micro-Nano Electronics, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-7753-644X","affiliations":[{"raw_affiliation_string":"Department of Micro-Nano Electronics, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103138440","display_name":"Zhenhua Zhu","orcid":"https://orcid.org/0009-0007-9259-7180"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenhua Zhu","raw_affiliation_strings":["Department of Electronic Engineering, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0007-9259-7180","affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017670541","display_name":"Fangxin Liu","orcid":"https://orcid.org/0000-0002-8769-293X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangxin Liu","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8769-293X","affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067161373","display_name":"Zhuoran Song","orcid":"https://orcid.org/0000-0002-6494-4786"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuoran Song","raw_affiliation_strings":["School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6494-4786","affiliations":[{"raw_affiliation_string":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102805465","display_name":"Guohao Dai","orcid":"https://orcid.org/0000-0002-8464-0130"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guohao Dai","raw_affiliation_strings":["Qing Yuan Research Institute, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-8464-0130","affiliations":[{"raw_affiliation_string":"Qing Yuan Research Institute, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054897331","display_name":"Guanghui He","orcid":"https://orcid.org/0000-0002-0486-6421"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guanghui He","raw_affiliation_strings":["Department of Micro-Nano Electronics and the MoE Key Laboratory of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0486-6421","affiliations":[{"raw_affiliation_string":"Department of Micro-Nano Electronics and the MoE Key Laboratory of Artificial Intelligence, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5102022581","display_name":"Yanan Sun","orcid":"https://orcid.org/0000-0001-8281-9121"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanan Sun","raw_affiliation_strings":["Department of Micro-Nano Electronics, Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-8281-9121","affiliations":[{"raw_affiliation_string":"Department of Micro-Nano Electronics, Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1868,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.78830657,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"44","issue":"5","first_page":"1819","last_page":"1832"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9659000039100647,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9659000039100647,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9470999836921692,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9437999725341797,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.784170925617218},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.6257568597793579},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.624956488609314},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.6125351190567017},{"id":"https://openalex.org/keywords/many-core","display_name":"Many core","score":0.5151301622390747},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.40935224294662476},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.19638755917549133},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14441460371017456},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10820767283439636},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.06293606758117676}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.784170925617218},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.6257568597793579},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.624956488609314},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.6125351190567017},{"id":"https://openalex.org/C3020431745","wikidata":"https://www.wikidata.org/wiki/Q25325220","display_name":"Many core","level":2,"score":0.5151301622390747},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.40935224294662476},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.19638755917549133},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14441460371017456},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10820767283439636},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.06293606758117676}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcad.2024.3490173","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2024.3490173","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"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.7599999904632568,"display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G3026348358","display_name":null,"funder_award_id":"2021YFA0717400","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G433992202","display_name":null,"funder_award_id":"#2024ZD0802100","funder_id":"https://openalex.org/F4320329860","funder_display_name":"National Science and Technology Major Project"},{"id":"https://openalex.org/G456948762","display_name":null,"funder_award_id":"62174110","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G616102654","display_name":null,"funder_award_id":"2023YFB4502200","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G625051844","display_name":null,"funder_award_id":"#62174110","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320309594","display_name":"Utah Science Technology and Research","ror":"https://ror.org/00h6set76"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1983394510","https://openalex.org/W2064675550","https://openalex.org/W2067523571","https://openalex.org/W2150633168","https://openalex.org/W2194775991","https://openalex.org/W2606722458","https://openalex.org/W2725159389","https://openalex.org/W3094502228","https://openalex.org/W3138516171","https://openalex.org/W3187908937","https://openalex.org/W3206453033","https://openalex.org/W3208788005","https://openalex.org/W4226512186","https://openalex.org/W4311088269","https://openalex.org/W4313251083","https://openalex.org/W4328088937","https://openalex.org/W4360831795","https://openalex.org/W4362602094","https://openalex.org/W4380881077","https://openalex.org/W4381050415","https://openalex.org/W4385245566","https://openalex.org/W4386763770","https://openalex.org/W4388692462","https://openalex.org/W4393592481","https://openalex.org/W6637373629","https://openalex.org/W6838322825"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W2171015181","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W2186985820","https://openalex.org/W4241012199","https://openalex.org/W2808785632","https://openalex.org/W170123544"],"abstract_inverted_index":{"Hybrid":[0],"convolutional":[1,44],"neural":[2],"network":[3],"(CNN)":[4],"and":[5,16,45,77,89,104,124,134,140,158,198,212,235,255,319,348],"Transformer":[6],"networks":[7,32,197],"are":[8,60],"emerging":[9],"in":[10,43,53,69,148,155,161,195,203,252],"computer":[11],"vision,":[12],"combining":[13],"convolutional,":[14],"linear,":[15],"attention":[17,54],"layers":[18],"to":[19,35,73,127,143,189,357],"achieve":[20],"high":[21],"accuracies":[22],"with":[23,109,248,295],"moderate":[24],"model":[25],"sizes.":[26],"Developing":[27],"the":[28,38,57,129,145,164,179,191,204,216,299,328],"accelerators":[29,59,247],"for":[30,63,82,92,113,131,170],"hybrid":[31,93,196],"is":[33,167,187,278],"pivotal":[34],"simultaneously":[36],"optimize":[37],"static":[39,83,132],"matrix":[40],"multiplication":[41],"(MM)":[42],"linear":[46],"layers,":[47,254],"as":[48,50],"well":[49],"dynamic":[51,75,149],"MM":[52,76],"layers.":[55],"However,":[56],"existing":[58],"primarily":[61],"designed":[62],"either":[64],"CNNs":[65],"or":[66],"Transformers,":[67],"resulting":[68],"increased":[70],"data":[71,146,193,200],"movement":[72,147],"support":[74],"potential":[78],"under-utilization":[79],"of":[80,119,276,304,333],"hardware":[81],"MM.":[84,150],"To":[85],"enhance":[86],"computational":[87,165],"performance":[88],"energy":[90,274],"efficiency":[91,166,275],"networks,":[94],"we":[95],"propose":[96],"HyCTor,":[97],"an":[98],"accelerator":[99],"featuring":[100],"flexible":[101,174],"output-stationary":[102],"(OS)":[103],"weight-stationary":[105],"(WS)":[106],"dataflows,":[107],"along":[108],"a":[110,183],"multicore":[111,205],"extension":[112],"higher":[114],"throughput.":[115],"The":[116,273],"parallel":[117],"array":[118],"HyCTor":[120,219,277,301,330,359],"supports":[121],"interlayer":[122],"slicing":[123],"intralayer":[125],"splicing":[126],"improve":[128],"utilization":[130,250],"MM,":[133],"enables":[135],"seamless":[136],"switching":[137],"between":[138],"OS":[139,156],"WS":[141,162],"dataflow":[142,157,175],"minimize":[144,199],"By":[151],"leveraging":[152],"structured":[153],"sparsity":[154,160,180],"unstructured":[159],"dataflow,":[163],"further":[168],"boosted":[169],"each":[171],"layer":[172],"through":[173],"selection":[176],"based":[177],"on":[178,209,360],"ratio.":[181],"Besides,":[182],"novel":[184],"QuadLoop-mesh":[185],"topology":[186],"proposed":[188,217],"address":[190],"complex":[192],"dependencies":[194],"transmission":[201],"distances":[202],"HyCTor.":[206],"Experimental":[207],"results":[208],"ResNet-18,":[210],"ViT-B,":[211],"TransIAR-AF":[213],"show":[214],"that":[215],"single-core":[218],"achieves":[220,302,331],"<inline-formula":[221,228,236,256,281,305,312,320,334,341,349],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[222,229,237,257,263,282,288,306,313,321,335,342,350],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[223,230,238,258,264,283,289,307,314,322,336,343,351],"<tex-math":[224,231,239,259,265,284,290,308,315,323,337,344,352],"notation=\"LaTeX\">$1.83\\times":[225],"$":[226,233,241,261,267,286,292,310,317,325,339,346,354],"</tex-math></inline-formula>,":[227,234,311,318,326,340,347],"notation=\"LaTeX\">$1.65\\times":[232],"notation=\"LaTeX\">$2.41\\times":[240],"</tex-math></inline-formula>":[242,268,293,355],"speedup":[243,269],"than":[244,270],"state-of-the-art":[245],"(SOTA)":[246],"100%":[249],"rate":[251],"most":[253],"notation=\"LaTeX\">$3.82\\times":[260],"</tex-math></inline-formula>\u2013<inline-formula":[262,287],"notation=\"LaTeX\">$38.5\\times":[266],"RTX4090":[271],"GPU.":[272],"improved":[279],"by":[280],"notation=\"LaTeX\">$1.81\\times":[285],"notation=\"LaTeX\">$8.77\\times":[291],"compared":[294,356],"SOTA":[296],"accelerators.":[297],"Moreover,":[298],"4-core":[300],"speedups":[303,332],"notation=\"LaTeX\">$3.32\\times":[309],"notation=\"LaTeX\">$2.58\\times":[316],"notation=\"LaTeX\">$2.91\\times":[324],"while":[327],"16-core":[329],"notation=\"LaTeX\">$7.05\\times":[338],"notation=\"LaTeX\">$4.05\\times":[345],"notation=\"LaTeX\">$9.64\\times":[353],"1-core":[358],"three":[361],"networks.":[362]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-20T07:56:41.581041","created_date":"2025-10-10T00:00:00"}