{"id":"https://openalex.org/W2699539367","doi":"https://doi.org/10.1145/3154839","title":"A GPU-Outperforming FPGA Accelerator Architecture for Binary Convolutional Neural Networks","display_name":"A GPU-Outperforming FPGA Accelerator Architecture for Binary Convolutional Neural Networks","publication_year":2018,"publication_date":"2018-04-30","ids":{"openalex":"https://openalex.org/W2699539367","doi":"https://doi.org/10.1145/3154839","mag":"2699539367"},"language":"en","primary_location":{"id":"doi:10.1145/3154839","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3154839","pdf_url":null,"source":{"id":"https://openalex.org/S96198239","display_name":"ACM Journal on Emerging Technologies in Computing Systems","issn_l":"1550-4832","issn":["1550-4832","1550-4840"],"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 Journal on Emerging Technologies in 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/A5101493770","display_name":"Yixing Li","orcid":"https://orcid.org/0000-0002-8190-9931"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yixing Li","raw_affiliation_strings":["Arizona State University, AZ, USA"],"affiliations":[{"raw_affiliation_string":"Arizona State University, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013941213","display_name":"Zichuan Liu","orcid":"https://orcid.org/0000-0002-5709-8497"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Zichuan Liu","raw_affiliation_strings":["Nanyang Technological University, Singapore"],"affiliations":[{"raw_affiliation_string":"Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5000248352","display_name":"Kai Xu","orcid":"https://orcid.org/0000-0002-9054-0216"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kai Xu","raw_affiliation_strings":["Arizona State University, AZ, USA"],"affiliations":[{"raw_affiliation_string":"Arizona State University, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034853402","display_name":"Hao Yu","orcid":"https://orcid.org/0000-0002-2674-4118"},"institutions":[{"id":"https://openalex.org/I3045169105","display_name":"Southern University of Science and Technology","ror":"https://ror.org/049tv2d57","country_code":"CN","type":"education","lineage":["https://openalex.org/I3045169105"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Yu","raw_affiliation_strings":["Southern University of Science and Technology"],"affiliations":[{"raw_affiliation_string":"Southern University of Science and Technology","institution_ids":["https://openalex.org/I3045169105"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083744126","display_name":"Fengbo Ren","orcid":"https://orcid.org/0000-0002-6509-8753"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fengbo Ren","raw_affiliation_strings":["Arizona State University, AZ, USA"],"affiliations":[{"raw_affiliation_string":"Arizona State University, AZ, USA","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101493770"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":3.4471,"has_fulltext":false,"cited_by_count":67,"citation_normalized_percentile":{"value":0.94634182,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":"14","issue":"2","first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.991599977016449,"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/T12676","display_name":"Machine Learning and ELM","score":0.989799976348877,"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":0.814702570438385},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7991495132446289},{"id":"https://openalex.org/keywords/titan","display_name":"Titan (rocket family)","score":0.7354193925857544},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.7115646004676819},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.640713095664978},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6136729717254639},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5186035633087158},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.5079644322395325},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4551600515842438},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.4491793215274811},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.35190874338150024},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3366481065750122},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3013458251953125},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1865641176700592},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07908272743225098}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.814702570438385},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7991495132446289},{"id":"https://openalex.org/C50805821","wikidata":"https://www.wikidata.org/wiki/Q1136670","display_name":"Titan (rocket family)","level":2,"score":0.7354193925857544},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.7115646004676819},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.640713095664978},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6136729717254639},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5186035633087158},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.5079644322395325},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4551600515842438},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.4491793215274811},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.35190874338150024},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3366481065750122},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3013458251953125},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1865641176700592},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07908272743225098},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"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/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3154839","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3154839","pdf_url":null,"source":{"id":"https://openalex.org/S96198239","display_name":"ACM Journal on Emerging Technologies in Computing Systems","issn_l":"1550-4832","issn":["1550-4832","1550-4840"],"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 Journal on Emerging Technologies in Computing Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8999999761581421,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307791","display_name":"Cisco Systems","ror":"https://ror.org/03yt1ez60"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W593092793","https://openalex.org/W1701967867","https://openalex.org/W1836465849","https://openalex.org/W1845051632","https://openalex.org/W1902934009","https://openalex.org/W2094756095","https://openalex.org/W2112796928","https://openalex.org/W2125203716","https://openalex.org/W2186222003","https://openalex.org/W2211629196","https://openalex.org/W2264905057","https://openalex.org/W2266701264","https://openalex.org/W2276486856","https://openalex.org/W2276892413","https://openalex.org/W2294282016","https://openalex.org/W2319920447","https://openalex.org/W2431931973","https://openalex.org/W2474119684","https://openalex.org/W2557283755","https://openalex.org/W2584311934","https://openalex.org/W2584616277","https://openalex.org/W2585560244","https://openalex.org/W2585774018","https://openalex.org/W2586565528","https://openalex.org/W2604700561","https://openalex.org/W2607662938","https://openalex.org/W2618530766","https://openalex.org/W2919115771","https://openalex.org/W2951978180","https://openalex.org/W2953212265","https://openalex.org/W2962835968","https://openalex.org/W4214745135"],"related_works":["https://openalex.org/W2408545863","https://openalex.org/W643179351","https://openalex.org/W2740469715","https://openalex.org/W2905265805","https://openalex.org/W2162805293","https://openalex.org/W2064207836","https://openalex.org/W2013629274","https://openalex.org/W2518118925","https://openalex.org/W3035662153","https://openalex.org/W3159273459"],"abstract_inverted_index":{"FPGA-based":[0,24],"hardware":[1],"accelerators":[2],"for":[3,23,78,133,153],"convolutional":[4],"neural":[5],"networks":[6],"(CNNs)":[7],"have":[8],"received":[9],"attention":[10],"due":[11],"to":[12,26,105],"their":[13],"higher":[14,29,189],"energy":[15,53,190],"efficiency":[16,54],"than":[17,31,148],"GPUs.":[18],"However,":[19],"it":[20],"is":[21,58,99,103,141,173],"challenging":[22],"solutions":[25],"achieve":[27],"a":[28,44,56,138,149,175,178],"throughput":[30,51,185],"GPU":[32,113,152,181],"counterparts.":[33],"In":[34],"this":[35],"article,":[36],"we":[37,68],"demonstrate":[38],"that":[39,83,100,128],"FPGA":[40,74,97,140],"acceleration":[41,114],"can":[42],"be":[43],"superior":[45],"solution":[46,172],"in":[47,158,166,182],"terms":[48,183],"of":[49,95,112,122,184],"both":[50],"and":[52,65,81,144],"when":[55],"CNN":[57],"trained":[59],"with":[60,88,177],"binary":[61,134],"constraints":[62],"on":[63,118,137,174],"weights":[64],"activations.":[66],"Specifically,":[67],"propose":[69],"an":[70],"optimized":[71],"fully":[72],"mapped":[73],"accelerator":[75,98,131],"architecture":[76,132],"tailored":[77],"bitwise":[79],"convolution":[80],"normalization":[82],"features":[84],"massive":[85],"spatial":[86],"parallelism":[87],"deep":[89],"pipelines":[90],"stages.":[91],"A":[92],"key":[93],"advantage":[94],"the":[96,110,119,123,129,170],"its":[101],"performance":[102,111],"insensitive":[104],"data":[106,165],"batch":[107,120,160,168],"size,":[108],"while":[109,186],"varies":[115],"largely":[116],"depending":[117],"size":[121],"data.":[124],"Experiment":[125],"results":[126],"show":[127],"proposed":[130,171],"CNNs":[135],"running":[136],"Virtex-7":[139],"8.3\u00d7":[142],"faster":[143],"75\u00d7":[145],"more":[146],"energy-efficient":[147],"Titan":[150,179],"X":[151,180],"processing":[154,163],"online":[155],"individual":[156],"requests":[157],"small":[159],"sizes.":[161],"For":[162],"static":[164],"large":[167],"sizes,":[169],"par":[176],"delivering":[187],"9.5\u00d7":[188],"efficiency.":[191]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":13},{"year":2018,"cited_by_count":4}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}