{"id":"https://openalex.org/W3159273459","doi":"https://doi.org/10.1145/3432816","title":"Toward Multi-FPGA Acceleration of the Neural Networks","display_name":"Toward Multi-FPGA Acceleration of the Neural Networks","publication_year":2021,"publication_date":"2021-04-29","ids":{"openalex":"https://openalex.org/W3159273459","doi":"https://doi.org/10.1145/3432816","mag":"3159273459"},"language":"en","primary_location":{"id":"doi:10.1145/3432816","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3432816","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3432816","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":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3432816","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5012323110","display_name":"Saman Biookaghazadeh","orcid":null},"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":"Saman Biookaghazadeh","raw_affiliation_strings":["Arizona State University, Tempe, AZ"],"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, AZ","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078038797","display_name":"Pravin Kumar Ravi","orcid":null},"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":"Pravin Kumar Ravi","raw_affiliation_strings":["Arizona State University, Tempe, AZ"],"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, AZ","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103197618","display_name":"Ming Zhao","orcid":"https://orcid.org/0000-0003-4126-3678"},"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":"Ming Zhao","raw_affiliation_strings":["Arizona State University, Tempe, AZ"],"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, AZ","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5012323110"],"corresponding_institution_ids":["https://openalex.org/I55732556"],"apc_list":null,"apc_paid":null,"fwci":2.7188,"has_fulltext":true,"cited_by_count":35,"citation_normalized_percentile":{"value":0.91811278,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"17","issue":"2","first_page":"1","last_page":"23"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9983000159263611,"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"}},{"id":"https://openalex.org/T10812","display_name":"Human Pose and Action Recognition","score":0.9975000023841858,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.9141085743904114},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8398721218109131},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7554807662963867},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6540810465812683},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6479653120040894},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5935425758361816},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5849143266677856},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5795688629150391},{"id":"https://openalex.org/keywords/low-latency","display_name":"Low latency (capital markets)","score":0.4583856463432312},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.453996479511261},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.44428855180740356},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.43406134843826294},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.4139418601989746},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4132470488548279},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.38511043787002563},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.37148305773735046},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.35461050271987915},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2685126066207886},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.12160128355026245},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.07896947860717773}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.9141085743904114},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8398721218109131},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7554807662963867},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6540810465812683},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6479653120040894},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5935425758361816},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5849143266677856},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5795688629150391},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.4583856463432312},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.453996479511261},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.44428855180740356},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.43406134843826294},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.4139418601989746},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4132470488548279},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.38511043787002563},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.37148305773735046},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.35461050271987915},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2685126066207886},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.12160128355026245},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.07896947860717773},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3432816","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3432816","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3432816","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":{"id":"doi:10.1145/3432816","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3432816","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3432816","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"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1371732599","display_name":null,"funder_award_id":"CNS-1619653","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2622782994","display_name":"II-NEW: GEARS - An Infrastructure for Energy-Efficient Big Data Research on Heterogeneous and Dynamic Data","funder_award_id":"1629888","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2652442311","display_name":"CSR: Medium: Collaborative Research: NVM-enabled Host-side Caches","funder_award_id":"1562837","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3443568","display_name":null,"funder_award_id":"CNS-1562837","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4180941946","display_name":null,"funder_award_id":"CNS-1629888","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G714929177","display_name":null,"funder_award_id":"1955593","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8563466892","display_name":"CAREER: Coordinated QoS-Driven Management of Cloud Computing and Storage Resources","funder_award_id":"1619653","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3159273459.pdf","grobid_xml":"https://content.openalex.org/works/W3159273459.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1522734439","https://openalex.org/W1983364832","https://openalex.org/W2090210354","https://openalex.org/W2094756095","https://openalex.org/W2155893237","https://openalex.org/W2172654076","https://openalex.org/W2211722331","https://openalex.org/W2294282016","https://openalex.org/W2475840367","https://openalex.org/W2526468814","https://openalex.org/W2592929672","https://openalex.org/W2606722458","https://openalex.org/W2745868649","https://openalex.org/W2756829667","https://openalex.org/W2785456876","https://openalex.org/W2789246071","https://openalex.org/W2795915628","https://openalex.org/W2883929540","https://openalex.org/W2896983500","https://openalex.org/W2903688003","https://openalex.org/W2907812233","https://openalex.org/W2962953210","https://openalex.org/W2979569264","https://openalex.org/W3100789280","https://openalex.org/W3121413886"],"related_works":["https://openalex.org/W2218038495","https://openalex.org/W2532502681","https://openalex.org/W2115380918","https://openalex.org/W3205411230","https://openalex.org/W4286899009","https://openalex.org/W3163341049","https://openalex.org/W9168048","https://openalex.org/W4300849822","https://openalex.org/W4376480820","https://openalex.org/W3155891479"],"abstract_inverted_index":{"High-throughput":[0],"and":[1,14,87,125,187],"low-latency":[2],"Convolutional":[3],"Neural":[4],"Network":[5],"(CNN)":[6],"inference":[7,21,151],"is":[8,102],"increasingly":[9],"important":[10],"for":[11,118,136,149],"many":[12],"cloud-":[13],"edge-computing":[15],"applications.":[16],"FPGA-based":[17],"acceleration":[18],"of":[19],"CNN":[20],"has":[22],"demonstrated":[23],"various":[24],"benefits":[25],"compared":[26],"to":[27,95,123,129,184,192],"other":[28,178],"high-performance":[29],"devices":[30],"such":[31,140],"as":[32,141],"GPGPUs.":[33],"Current":[34],"FPGA":[35,43,179],"CNN-acceleration":[36],"solutions":[37],"are":[38,46],"based":[39],"on":[40,52],"a":[41,71,89],"single":[42],"design,":[44],"which":[45,78],"limited":[47],"by":[48,182,190],"the":[49,96,105,163,168,174],"available":[50,97],"resources":[51],"an":[53],"FPGA.":[54],"In":[55,172],"addition,":[56,173],"they":[57],"can":[58,79,160,176],"only":[59],"accelerate":[60,80],"conventional":[61],"2D":[62,180],"neural":[63],"networks.":[64],"To":[65],"address":[66],"these":[67],"limitations,":[68],"we":[69],"present":[70],"generic":[72],"multi-FPGA":[73,147],"solution,":[74],"written":[75],"in":[76],"OpenCL,":[77],"more":[81,137],"complex":[82],"CNNs":[83],"(e.g.,":[84],"C3D":[85],"CNN)":[86],"achieve":[88],"near":[90],"linear":[91],"speedup":[92],"with":[93,111],"respect":[94],"single-FPGA":[98],"solutions.":[99],"The":[100,153],"design":[101,175],"built":[103],"upon":[104],"Intel":[106],"Deep":[107],"Learning":[108],"Accelerator":[109],"architecture,":[110],"three":[112],"extensions.":[113],"First,":[114],"it":[115,132,145],"includes":[116],"updates":[117],"better":[119],"area":[120],"efficiency":[121],"(up":[122,128],"25%)":[124],"higher":[126,150],"performance":[127],"24%).":[130],"Second,":[131],"supports":[133,146],"3D":[134,188],"convolutions":[135],"challenging":[138],"applications":[139],"video":[142],"learning.":[143],"Third,":[144],"communication":[148],"throughput.":[152],"results":[154],"show":[155],"that":[156],"utilizing":[157],"multiple":[158],"FPGAs":[159],"linearly":[161],"increase":[162],"overall":[164],"bandwidth":[165],"while":[166],"maintaining":[167],"same":[169],"end-to-end":[170],"latency.":[171],"outperform":[177],"accelerators":[181,189],"up":[183,191],"8.4":[185],"times":[186],"1.7":[193],"times.":[194]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":10}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}