{"id":"https://openalex.org/W4414913085","doi":"https://doi.org/10.1145/3770756","title":"DA-VinCi: A Deep-Learning Accelerator Overlay Using In-Memory Computing","display_name":"DA-VinCi: A Deep-Learning Accelerator Overlay Using In-Memory Computing","publication_year":2025,"publication_date":"2025-10-07","ids":{"openalex":"https://openalex.org/W4414913085","doi":"https://doi.org/10.1145/3770756"},"language":"en","primary_location":{"id":"doi:10.1145/3770756","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3770756","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"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 Reconfigurable Technology 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/A5097656516","display_name":"MD Arafat Kabir","orcid":"https://orcid.org/0000-0002-9920-2985"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"MD Arafat Kabir","raw_affiliation_strings":["University of Arkansas, Fayetteville, Arkansas, USA","University of Arkansas, USA"],"raw_orcid":"https://orcid.org/0000-0002-9920-2985","affiliations":[{"raw_affiliation_string":"University of Arkansas, Fayetteville, Arkansas, USA","institution_ids":["https://openalex.org/I78715868"]},{"raw_affiliation_string":"University of Arkansas, USA","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106956812","display_name":"Nathaniel Fredricks","orcid":null},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nathaniel Fredricks","raw_affiliation_strings":["University of Arkansas, Fayetteville, Arkansas, USA","University of Arkansas, USA"],"raw_orcid":"https://orcid.org/0009-0007-5329-8233","affiliations":[{"raw_affiliation_string":"University of Arkansas, Fayetteville, Arkansas, USA","institution_ids":["https://openalex.org/I78715868"]},{"raw_affiliation_string":"University of Arkansas, USA","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033857478","display_name":"Tendayi Kamucheka","orcid":"https://orcid.org/0000-0002-7853-5780"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tendayi Kamucheka","raw_affiliation_strings":["University of Arkansas Fayetteville, Fayetteville, Arkansas, USA","University of Arkansas, USA"],"raw_orcid":"https://orcid.org/0000-0002-7853-5780","affiliations":[{"raw_affiliation_string":"University of Arkansas Fayetteville, Fayetteville, Arkansas, USA","institution_ids":["https://openalex.org/I78715868"]},{"raw_affiliation_string":"University of Arkansas, USA","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032279242","display_name":"Joel Mandebi Mbongue","orcid":"https://orcid.org/0000-0002-9277-5043"},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joel Mandebi","raw_affiliation_strings":["Advanced Micro Devices, Inc., (AMD), Santa Clara, California, USA","Advanced Micro Devices, Inc. (AMD), USA"],"raw_orcid":"https://orcid.org/0000-0002-9277-5043","affiliations":[{"raw_affiliation_string":"Advanced Micro Devices, Inc., (AMD), Santa Clara, California, USA","institution_ids":["https://openalex.org/I4210137977"]},{"raw_affiliation_string":"Advanced Micro Devices, Inc. (AMD), USA","institution_ids":["https://openalex.org/I4210137977"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069173833","display_name":"Miaoqing Huang","orcid":"https://orcid.org/0000-0001-7376-3744"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Miaoqing Huang","raw_affiliation_strings":["University of Arkansas, Fayetteville, Arkansas, USA","University of Arkansas, USA"],"raw_orcid":"https://orcid.org/0000-0001-7376-3744","affiliations":[{"raw_affiliation_string":"University of Arkansas, Fayetteville, Arkansas, USA","institution_ids":["https://openalex.org/I78715868"]},{"raw_affiliation_string":"University of Arkansas, USA","institution_ids":["https://openalex.org/I78715868"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001266986","display_name":"Jason D. Bakos","orcid":"https://orcid.org/0000-0002-0821-6258"},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jason D. Bakos","raw_affiliation_strings":["University of South Carolina, Columbia, South Carolina, USA","University of South Carolina, USA"],"raw_orcid":"https://orcid.org/0000-0002-0821-6258","affiliations":[{"raw_affiliation_string":"University of South Carolina, Columbia, South Carolina, USA","institution_ids":["https://openalex.org/I155781252"]},{"raw_affiliation_string":"University of South Carolina, USA","institution_ids":["https://openalex.org/I155781252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062434121","display_name":"David Andrews","orcid":"https://orcid.org/0000-0003-1464-7107"},"institutions":[{"id":"https://openalex.org/I78715868","display_name":"University of Arkansas at Fayetteville","ror":"https://ror.org/05jbt9m15","country_code":"US","type":"education","lineage":["https://openalex.org/I78715868"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Andrews","raw_affiliation_strings":["University of Arkansas, Fayetteville, Arkansas, USA","University of Arkansas, USA"],"raw_orcid":"https://orcid.org/0000-0003-1464-7107","affiliations":[{"raw_affiliation_string":"University of Arkansas, Fayetteville, Arkansas, USA","institution_ids":["https://openalex.org/I78715868"]},{"raw_affiliation_string":"University of Arkansas, USA","institution_ids":["https://openalex.org/I78715868"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5352,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.71487414,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"18","issue":"4","first_page":"1","last_page":"38"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9977999925613403,"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":0.9977999925613403,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9947999715805054,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.9878000020980835,"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":0.7142999768257141},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6880000233650208},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.4767000079154968},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.4733000099658966},{"id":"https://openalex.org/keywords/clock-rate","display_name":"Clock rate","score":0.4277999997138977},{"id":"https://openalex.org/keywords/simd","display_name":"SIMD","score":0.41440001130104065},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.37139999866485596}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8452000021934509},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7142999768257141},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6880000233650208},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.4767000079154968},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.4733000099658966},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4487999975681305},{"id":"https://openalex.org/C178693496","wikidata":"https://www.wikidata.org/wiki/Q911691","display_name":"Clock rate","level":3,"score":0.4277999997138977},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.42579999566078186},{"id":"https://openalex.org/C150552126","wikidata":"https://www.wikidata.org/wiki/Q339387","display_name":"SIMD","level":2,"score":0.41440001130104065},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.40630000829696655},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.39089998602867126},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.37139999866485596},{"id":"https://openalex.org/C114237110","wikidata":"https://www.wikidata.org/wiki/Q114901","display_name":"Gate array","level":3,"score":0.3490000069141388},{"id":"https://openalex.org/C68043766","wikidata":"https://www.wikidata.org/wiki/Q267416","display_name":"Static random-access memory","level":2,"score":0.31619998812675476},{"id":"https://openalex.org/C77390884","wikidata":"https://www.wikidata.org/wiki/Q217302","display_name":"Application-specific integrated circuit","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C37724790","wikidata":"https://www.wikidata.org/wiki/Q210813","display_name":"Direct memory access","level":3,"score":0.28859999775886536},{"id":"https://openalex.org/C91481028","wikidata":"https://www.wikidata.org/wiki/Q1054686","display_name":"Distributed memory","level":3,"score":0.27070000767707825},{"id":"https://openalex.org/C203864433","wikidata":"https://www.wikidata.org/wiki/Q5426992","display_name":"FPGA prototype","level":3,"score":0.26260000467300415},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3770756","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3770756","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"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 Reconfigurable Technology and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W1969911580","https://openalex.org/W2058490651","https://openalex.org/W2064675550","https://openalex.org/W2112547256","https://openalex.org/W2112980698","https://openalex.org/W2122060420","https://openalex.org/W2122364000","https://openalex.org/W2133131244","https://openalex.org/W2460300668","https://openalex.org/W2803426421","https://openalex.org/W2915041608","https://openalex.org/W2935524202","https://openalex.org/W2990714382","https://openalex.org/W2995684380","https://openalex.org/W2998986365","https://openalex.org/W3197665962","https://openalex.org/W4211096911","https://openalex.org/W4242149169","https://openalex.org/W4243575863","https://openalex.org/W4245287157","https://openalex.org/W4245299501","https://openalex.org/W4245550464","https://openalex.org/W4248032436","https://openalex.org/W4248980851","https://openalex.org/W4253118902","https://openalex.org/W4283219803","https://openalex.org/W4285121610","https://openalex.org/W4293731257","https://openalex.org/W4297097035","https://openalex.org/W4298883496","https://openalex.org/W4299617642","https://openalex.org/W4299937212","https://openalex.org/W4312951380","https://openalex.org/W4379388660","https://openalex.org/W4387042449","https://openalex.org/W4388215268","https://openalex.org/W4399657747","https://openalex.org/W4403322662","https://openalex.org/W4407953972","https://openalex.org/W4414913085"],"related_works":[],"abstract_inverted_index":{"The":[0,253,294],"matrix":[1],"operations":[2],"that":[3,34,45,145,162,263,364],"underpin":[4],"today\u2019s":[5],"deep":[6],"learning":[7],"models":[8,33,44],"are":[9,35,46,51],"routinely":[10],"implemented":[11],"in":[12,32],"Single":[13],"Instruction":[14,259],"Multiple":[15],"Data":[16],"(SIMD)":[17],"domain":[18],"specific":[19],"accelerators.":[20,102],"SIMD":[21],"accelerators":[22,399],"including":[23,280],"GPUs":[24],"and":[25,59,244,289,296,313,390],"array":[26],"processors":[27],"can":[28,40],"effectively":[29],"leverage":[30,112],"parallelism":[31],"compute-bound,":[36],"but":[37],"their":[38,171],"effectiveness":[39],"be":[41,168],"diminished":[42],"for":[43,62,96],"memory-bound.":[47],"Processing-in-Memory":[48],"(PIM)":[49,310],"architectures":[50,127,165],"being":[52],"explored":[53],"to":[54,111,120,232,236,269,332,369,381,392],"provide":[55,270,354],"better":[56],"energy":[57],"efficiency":[58],"scalable":[60,203,316],"performance":[61],"these":[63],"memory-bound":[64,277],"models.":[65],"Modern":[66],"Field":[67],"Programmable":[68],"Gate":[69],"Arrays":[70],"(FPGAs)":[71],"feature":[72],"hundreds":[73],"of":[74,76,149,211,217,224,229,240,250,273,276,300,328,334],"megabits":[75],"Static":[77],"Random":[78],"Access":[79],"Memory":[80,101,309],"(SRAM)":[81],"distributed":[82],"across":[83,360],"the":[84,123,146,150,201,214,222,227,237,246,251,265,326,335,349],"device":[85],"as":[86],"disaggregated":[87],"memory":[88],"resources.":[89],"This":[90],"makes":[91],"FPGAs":[92],"ideal":[93],"programmable":[94,258],"platforms":[95],"developing":[97],"custom":[98,172,397],"Processor":[99,307],"In/Near":[100],"Several":[103],"PIM":[104,126,164,206,377],"array-based":[105],"accelerator":[106,208],"designs":[107,151],"have":[108],"been":[109],"proposed":[110],"this":[113,179],"substantial":[114],"internal":[115],"bandwidth.":[116],"However,":[117],"results":[118,160,321],"reported":[119],"date":[121],"show":[122,144,365],"FPGA":[124,163,204,388],"based":[125,205],"operating":[128],"at":[129,213,245,346],"system":[130],"clock":[131,140,248],"frequencies":[132],"well":[133],"below":[134],"a":[135,184,218,241,257,274,305,314,370,375],"chips":[136,350],"Block-RAM":[137],"(BRAM)":[138],"Fmax":[139],"frequency.":[141],"Results":[142],"also":[143],"compute":[147,230],"densities":[148],"do":[152],"not":[153],"scale":[154,233],"linearly":[155,234,324],"with":[156,170],"BRAM":[157,336,351],"densities.":[158],"These":[159],"indicate":[161],"will":[166],"never":[167],"competitive":[169],"Application-Specific":[173],"Integrated":[174],"Circuit":[175],"(ASIC)":[176],"counterparts.":[177],"In":[178,193,308],"article,":[180],"we":[181],"introduce":[182],"DA-VinCi,":[183],"D":[185],"eep-Learning":[186],"A":[187],"ccelerator":[188],"O":[189],"v":[190],"erlay":[191],"using":[192],"-Memory":[194],"C":[195],"omput":[196],"i":[197],"ng.":[198],"DA-VinCi":[199,225,254,301,323,366],"is":[200,302],"first":[202],"deep-learning":[207,278,362,398],"overlay":[209,255,378],"capable":[210],"clocking":[212,298,345],"maximum":[215,238,247],"frequency":[216,249,299],"device\u2019s":[219],"BRAM.":[220,252],"Further,":[221],"architecture":[223,312],"allows":[226,264],"number":[228,327],"units":[231],"up":[235,368,380,391],"capacity":[239,337],"devices":[242],"BRAM,":[243],"has":[256],"Set":[260],"Architecture":[261],"(ISA)":[262],"same":[266],"synthesized":[267],"design":[268],"low-latency":[271],"inferencing":[272],"range":[275],"models,":[279],"Multilayer":[281],"Perceptrons,":[282],"Recurrent":[283,291],"Neural":[284],"Network,":[285],"Long":[286],"Short-Term":[287],"Memory,":[288],"Gated":[290],"Unit":[292],"networks.":[293],"scalability":[295],"high":[297],"achieved":[303],"through":[304],"new":[306],"tile":[311],"highly":[315],"system-level":[317],"framework.":[318],"We":[319,353],"present":[320],"showing":[322],"scaling":[325],"Processing":[329],"Elements":[330],"(PEs)":[331],"100%":[333],"(over":[338],"60K":[339],"PEs)":[340],"on":[341,357,400],"an":[342],"Alveo":[343],"U55":[344],"737":[347],"MHz,":[348],"Fmax.":[352],"comparative":[355],"studies":[356],"inference":[358],"latency":[359],"multiple":[361],"applications":[363],"achieves":[367],"201":[371],"\\(\\times\\)":[372,383,394],"improvement":[373,384,395],"over":[374,385,396],"state-of-the-art":[376],"accelerator,":[379],"87":[382],"existing":[386],"PIM-based":[387],"accelerators,":[389],"57":[393],"FPGAs.":[401]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}