{"id":"https://openalex.org/W4249932213","doi":"https://doi.org/10.1109/micro.2016.7783725","title":"Fused-layer CNN accelerators","display_name":"Fused-layer CNN accelerators","publication_year":2016,"publication_date":"2016-10-01","ids":{"openalex":"https://openalex.org/W4249932213","doi":"https://doi.org/10.1109/micro.2016.7783725"},"language":"en","primary_location":{"id":"doi:10.1109/micro.2016.7783725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/micro.2016.7783725","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 49th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5012860782","display_name":"Manoj Alwani","orcid":null},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Manoj Alwani","raw_affiliation_strings":["Stony Brook University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100325120","display_name":"Han Chen","orcid":"https://orcid.org/0000-0002-6315-802X"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Chen","raw_affiliation_strings":["Stony Brook University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010051312","display_name":"Michael Ferdman","orcid":"https://orcid.org/0000-0001-5808-1040"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Michael Ferdman","raw_affiliation_strings":["Stony Brook University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061612911","display_name":"Peter Milder","orcid":"https://orcid.org/0000-0003-1146-3011"},"institutions":[{"id":"https://openalex.org/I59553526","display_name":"Stony Brook University","ror":"https://ror.org/05qghxh33","country_code":"US","type":"education","lineage":["https://openalex.org/I59553526"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Milder","raw_affiliation_strings":["Stony Brook University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stony Brook University","institution_ids":["https://openalex.org/I59553526"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I59553526"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":534,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9991999864578247,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9987000226974487,"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":0.841754138469696},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7709838151931763},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6080243587493896},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.538332462310791},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.516841471195221},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.48489052057266235},{"id":"https://openalex.org/keywords/virtex","display_name":"Virtex","score":0.48367032408714294},{"id":"https://openalex.org/keywords/chip","display_name":"Chip","score":0.4725636839866638},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.47176483273506165},{"id":"https://openalex.org/keywords/fuse","display_name":"Fuse (electrical)","score":0.46812546253204346},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4303589463233948},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4200502932071686},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3950656056404114},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37818410992622375},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.36114799976348877},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.2394382357597351},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09739217162132263},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08501619100570679}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.841754138469696},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7709838151931763},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6080243587493896},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.538332462310791},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.516841471195221},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.48489052057266235},{"id":"https://openalex.org/C2777674469","wikidata":"https://www.wikidata.org/wiki/Q20741011","display_name":"Virtex","level":3,"score":0.48367032408714294},{"id":"https://openalex.org/C165005293","wikidata":"https://www.wikidata.org/wiki/Q1074500","display_name":"Chip","level":2,"score":0.4725636839866638},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.47176483273506165},{"id":"https://openalex.org/C141353440","wikidata":"https://www.wikidata.org/wiki/Q182221","display_name":"Fuse (electrical)","level":2,"score":0.46812546253204346},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4303589463233948},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4200502932071686},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3950656056404114},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37818410992622375},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.36114799976348877},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.2394382357597351},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09739217162132263},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08501619100570679},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/micro.2016.7783725","is_oa":false,"landing_page_url":"https://doi.org/10.1109/micro.2016.7783725","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 49th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W77656806","https://openalex.org/W753012316","https://openalex.org/W1686810756","https://openalex.org/W1990315422","https://openalex.org/W2000967104","https://openalex.org/W2048266589","https://openalex.org/W2094756095","https://openalex.org/W2096645269","https://openalex.org/W2097117768","https://openalex.org/W2102543317","https://openalex.org/W2117539524","https://openalex.org/W2117696986","https://openalex.org/W2125203716","https://openalex.org/W2142801765","https://openalex.org/W2163605009","https://openalex.org/W3004171485","https://openalex.org/W4232383452","https://openalex.org/W4256629673","https://openalex.org/W4302296459","https://openalex.org/W6622239757","https://openalex.org/W6637151318","https://openalex.org/W6637373629","https://openalex.org/W6662587704","https://openalex.org/W6678493590","https://openalex.org/W6684191040"],"related_works":["https://openalex.org/W2999668243","https://openalex.org/W2544043553","https://openalex.org/W2546284597","https://openalex.org/W2348562861","https://openalex.org/W2170552397","https://openalex.org/W2540393334","https://openalex.org/W2390042878","https://openalex.org/W2062932566","https://openalex.org/W2085828379","https://openalex.org/W2271847574"],"abstract_inverted_index":{"Deep":[0],"convolutional":[1,123,181],"neural":[2],"networks":[3],"(CNNs)":[4],"are":[5,43,92,129,148],"rapidly":[6,44],"becoming":[7],"the":[8,65,75,89,111,120,133,141,145,158,166,178,184,191,219],"dominant":[9],"approach":[10,170],"to":[11,51,57,62,73,82,95,131,190,227],"computer":[12],"vision":[13],"and":[14,32,187],"a":[15,36,105,173,196],"major":[16],"component":[17],"of":[18,114,135,154,160,168,183,206],"many":[19],"other":[20],"pervasive":[21],"machine":[22],"learning":[23],"tasks,":[24],"such":[25,53],"as":[26],"speech":[27],"recognition,":[28],"natural":[29],"language":[30],"processing,":[31],"fraud":[33],"detection.":[34],"As":[35],"result,":[37],"accelerators":[38,55,61,116],"for":[39,177],"efficiently":[40],"evaluating":[41],"CNNs":[42],"growing":[45],"in":[46,110,143],"popularity.":[47],"The":[48],"conventional":[49],"approaches":[50],"designing":[52],"CNN":[54,66,115,137,162,175],"is":[56],"focus":[58],"on":[59,97,119,150,195],"creating":[60],"iteratively":[63],"process":[64],"layers.":[67,124,163],"However,":[68],"by":[69,139,171,203,222],"processing":[70,134],"each":[71],"layer":[72],"completion,":[74],"accelerator":[76,176,193,211],"designs":[77],"must":[78],"use":[79],"off-chip":[80,213],"memory":[81],"store":[83],"intermediate":[84,90,155],"data":[85,91,147,156,216],"between":[86,157],"layers,":[87],"because":[88],"too":[93],"large":[94],"fit":[96],"chip.":[98],"In":[99],"this":[100],"work,":[101],"we":[102,128],"observe":[103],"that":[104,117,127],"previously":[106],"unexplored":[107],"dimension":[108],"exists":[109],"design":[112],"space":[113],"focuses":[118],"dataflow":[121],"across":[122],"We":[125,164,200],"find":[126,201],"able":[130],"fuse":[132],"multiple":[136],"layers":[138,182],"modifying":[140],"order":[142],"which":[144],"input":[146],"brought":[149],"chip,":[151],"enabling":[152],"caching":[153],"evaluation":[159],"adjacent":[161],"demonstrate":[165],"effectiveness":[167],"our":[169,209],"constructing":[172],"fused-layer":[174,210],"first":[179],"five":[180],"VGGNet-E":[185],"network":[186],"comparing":[188],"it":[189],"state-of-the-art":[192],"implemented":[194],"Xilinx":[197],"Virtex-7":[198],"FPGA.":[199],"that,":[202],"using":[204],"362KB":[205],"on-chip":[207],"storage,":[208],"minimizes":[212],"feature":[214],"map":[215],"transfer,":[217],"reducing":[218],"total":[220],"transfer":[221],"95%,":[223],"from":[224],"77MB":[225],"down":[226],"3.6MB":[228],"per":[229],"image.":[230]},"counts_by_year":[{"year":2026,"cited_by_count":11},{"year":2025,"cited_by_count":43},{"year":2024,"cited_by_count":65},{"year":2023,"cited_by_count":66},{"year":2022,"cited_by_count":76},{"year":2021,"cited_by_count":84},{"year":2020,"cited_by_count":56},{"year":2019,"cited_by_count":57},{"year":2018,"cited_by_count":60},{"year":2017,"cited_by_count":16}],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2025-10-10T00:00:00"}