{"id":"https://openalex.org/W4401357692","doi":"https://doi.org/10.1109/tcsvt.2024.3439600","title":"A 109-GOPs/W FPGA-Based Vision Transformer Accelerator With Weight-Loop Dataflow Featuring Data Reusing and Resource Saving","display_name":"A 109-GOPs/W FPGA-Based Vision Transformer Accelerator With Weight-Loop Dataflow Featuring Data Reusing and Resource Saving","publication_year":2024,"publication_date":"2024-08-06","ids":{"openalex":"https://openalex.org/W4401357692","doi":"https://doi.org/10.1109/tcsvt.2024.3439600"},"language":"en","primary_location":{"id":"doi:10.1109/tcsvt.2024.3439600","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3439600","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5058277050","display_name":"Yueqi Zhang","orcid":"https://orcid.org/0000-0002-1956-766X"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yueqi Zhang","raw_affiliation_strings":["Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education), School of Integrated Circuits, Xidian University, Xi&#x2019;an, China","School of Integrated Circuits, Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education), Xidian University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0002-1956-766X","affiliations":[{"raw_affiliation_string":"Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education), School of Integrated Circuits, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Integrated Circuits, Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education), Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023015877","display_name":"Lichen Feng","orcid":"https://orcid.org/0000-0002-7685-2141"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lichen Feng","raw_affiliation_strings":["Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education), School of Integrated Circuits, Xidian University, Xi&#x2019;an, China","School of Integrated Circuits, Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education), Xidian University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0002-7685-2141","affiliations":[{"raw_affiliation_string":"Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education), School of Integrated Circuits, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Integrated Circuits, Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education), Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089503849","display_name":"Hongwei Shan","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongwei Shan","raw_affiliation_strings":["Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education), School of Integrated Circuits, Xidian University, Xi&#x2019;an, China","School of Integrated Circuits, Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education), Xidian University, Xi&#x2019;an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education), School of Integrated Circuits, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Integrated Circuits, Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education), Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039575274","display_name":"Zhangming Zhu","orcid":"https://orcid.org/0000-0002-7764-1928"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhangming Zhu","raw_affiliation_strings":["Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education), School of Integrated Circuits, Xidian University, Xi&#x2019;an, China","School of Integrated Circuits, Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education), Xidian University, Xi&#x2019;an, China"],"raw_orcid":"https://orcid.org/0000-0002-7764-1928","affiliations":[{"raw_affiliation_string":"Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education), School of Integrated Circuits, Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]},{"raw_affiliation_string":"School of Integrated Circuits, Key Laboratory of Analog Integrated Circuits and Systems (Ministry of Education), Xidian University, Xi&#x2019;an, China","institution_ids":["https://openalex.org/I149594827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I149594827"],"apc_list":null,"apc_paid":null,"fwci":2.3453,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.88855486,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"34","issue":"12","first_page":"13596","last_page":"13610"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9994000196456909,"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"}},"topics":[{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9994000196456909,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9814000129699707,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9578999876976013,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7413650751113892},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.6825278401374817},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.6589380502700806},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6439369320869446},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.5493365526199341},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.42929807305336},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.34987586736679077},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.30293071269989014},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.17553114891052246},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.0989815890789032}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7413650751113892},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6825278401374817},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.6589380502700806},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6439369320869446},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.5493365526199341},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.42929807305336},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.34987586736679077},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.30293071269989014},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.17553114891052246},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0989815890789032},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2024.3439600","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2024.3439600","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.550000011920929,"id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G5870840838","display_name":null,"funder_award_id":"62104175","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8921800214","display_name":null,"funder_award_id":"U22A2013","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2017369466","https://openalex.org/W2037227137","https://openalex.org/W2108598243","https://openalex.org/W2606722458","https://openalex.org/W2795961274","https://openalex.org/W3082058622","https://openalex.org/W3096609285","https://openalex.org/W3114514344","https://openalex.org/W3138516171","https://openalex.org/W3164543136","https://openalex.org/W3184454880","https://openalex.org/W3199934250","https://openalex.org/W4200400428","https://openalex.org/W4285250061","https://openalex.org/W4289656095","https://openalex.org/W4308479898","https://openalex.org/W4312335509","https://openalex.org/W4312671791","https://openalex.org/W4321608108","https://openalex.org/W4321637298","https://openalex.org/W4360831786","https://openalex.org/W4376455279","https://openalex.org/W4378194725","https://openalex.org/W4385245566","https://openalex.org/W4387789586","https://openalex.org/W4394627484","https://openalex.org/W6755207826","https://openalex.org/W6788135285","https://openalex.org/W6789753369","https://openalex.org/W6790690058","https://openalex.org/W6840088539"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W2171015181","https://openalex.org/W4239447582","https://openalex.org/W1484403103","https://openalex.org/W2521947294","https://openalex.org/W2999668243"],"abstract_inverted_index":{"The":[0,153],"Vision":[1],"Transformer":[2],"(ViT)":[3],"models":[4],"have":[5],"demonstrated":[6],"excellent":[7],"performance":[8,30],"in":[9,128],"computer":[10],"vision":[11],"tasks,":[12],"but":[13],"a":[14,42,46,96,105,172],"large":[15],"amount":[16],"of":[17,66,72,142,155,168],"computation":[18,84],"and":[19,50,62,69,77,145,150],"memory":[20,67],"access":[21],"for":[22,54,113,148],"massive":[23],"matrix":[24,56],"multiplications":[25],"lead":[26],"to":[27,32,94,118,161,176],"degraded":[28],"hardware":[29],"compared":[31,175],"convolutional":[33],"neural":[34],"network":[35],"(CNN).":[36],"In":[37],"this":[38],"paper,":[39],"we":[40],"propose":[41],"ViT":[43,135],"accelerator":[44,136,157],"with":[45,86,164],"novel":[47,106],"\u201cWeight-Loop\u201d":[48],"dataflow":[49,89],"its":[51],"computing":[52],"unit,":[53],"efficient":[55],"multiplication":[57],"computation.":[58],"By":[59],"data":[60],"partitioning":[61],"rearrangement,":[63],"the":[64,70,78,87,120,129,133,138,156,177],"number":[65,71],"accesses":[68],"registers":[73],"are":[74,81],"greatly":[75],"reduced,":[76],"adder":[79],"trees":[80],"eliminated.":[82],"A":[83],"pipeline":[85],"proposed":[88,134],"scheduling":[90],"method":[91,112],"is":[92,116],"constructed":[93],"maintain":[95],"high":[97],"utilization":[98],"rate":[99],"through":[100],"zero":[101],"bubble":[102],"switching.":[103],"Moreover,":[104],"accurate":[107],"dual":[108],"INT8":[109],"multiply-accumulate":[110],"(DI8MAC)":[111],"DSP":[114],"optimization":[115],"introduced":[117],"eliminate":[119],"additional":[121],"correction":[122],"circuits":[123],"by":[124],"weight":[125],"encoding.":[126],"Verified":[127],"Xilinx":[130],"XCZU9EG":[131],"FPGA,":[132],"achieves":[137],"lowest":[139],"inference":[140],"latencies":[141],"3.91":[143],"ms":[144,147],"13.98":[146],"ViT-S":[149],"ViT-B,":[151],"respectively.":[152],"throughput":[154],"can":[158],"reach":[159],"up":[160],"2330.2":[162],"GOPs":[163],"an":[165],"energy":[166],"efficiency":[167],"109":[169],"GOPs/W,":[170],"showing":[171],"significant":[173],"improvement":[174],"state-of-the-art":[178],"works.":[179]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":1}],"updated_date":"2026-06-30T13:55:48.251075","created_date":"2025-10-10T00:00:00"}
