{"id":"https://openalex.org/W4385253073","doi":"https://doi.org/10.1109/eit57321.2023.10187228","title":"Reconfigurable Distributed FPGA Cluster Design for Deep Learning Accelerators","display_name":"Reconfigurable Distributed FPGA Cluster Design for Deep Learning Accelerators","publication_year":2023,"publication_date":"2023-05-18","ids":{"openalex":"https://openalex.org/W4385253073","doi":"https://doi.org/10.1109/eit57321.2023.10187228"},"language":"en","primary_location":{"id":"doi:10.1109/eit57321.2023.10187228","is_oa":false,"landing_page_url":"https://doi.org/10.1109/eit57321.2023.10187228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Electro Information Technology (eIT)","raw_type":"proceedings-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/A5103236546","display_name":"Hans Johnson","orcid":"https://orcid.org/0000-0001-9153-921X"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hans Johnson","raw_affiliation_strings":["Illinois Institute of Technology,Embedded Computing and Signal Processing (ECASP) Research Laboratory,Department of Electrical and Computer Engineering,Chicago,IL,U.S.A","Department of Electrical and Computer Engineering, Embedded Computing and Signal Processing (ECASP) Research Laboratory, Illinois Institute of Technology, Chicago, IL, U.S.A"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology,Embedded Computing and Signal Processing (ECASP) Research Laboratory,Department of Electrical and Computer Engineering,Chicago,IL,U.S.A","institution_ids":["https://openalex.org/I180949307"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Embedded Computing and Signal Processing (ECASP) Research Laboratory, Illinois Institute of Technology, Chicago, IL, U.S.A","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074654866","display_name":"Tianyang Fang","orcid":"https://orcid.org/0009-0007-8741-0473"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tianyang Fang","raw_affiliation_strings":["Illinois Institute of Technology,Embedded Computing and Signal Processing (ECASP) Research Laboratory,Department of Electrical and Computer Engineering,Chicago,IL,U.S.A","Department of Electrical and Computer Engineering, Embedded Computing and Signal Processing (ECASP) Research Laboratory, Illinois Institute of Technology, Chicago, IL, U.S.A"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology,Embedded Computing and Signal Processing (ECASP) Research Laboratory,Department of Electrical and Computer Engineering,Chicago,IL,U.S.A","institution_ids":["https://openalex.org/I180949307"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Embedded Computing and Signal Processing (ECASP) Research Laboratory, Illinois Institute of Technology, Chicago, IL, U.S.A","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019306238","display_name":"Alejandro Perez-Vicente","orcid":null},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alejandro Perez-Vicente","raw_affiliation_strings":["Illinois Institute of Technology,Embedded Computing and Signal Processing (ECASP) Research Laboratory,Department of Electrical and Computer Engineering,Chicago,IL,U.S.A","Department of Electrical and Computer Engineering, Embedded Computing and Signal Processing (ECASP) Research Laboratory, Illinois Institute of Technology, Chicago, IL, U.S.A"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology,Embedded Computing and Signal Processing (ECASP) Research Laboratory,Department of Electrical and Computer Engineering,Chicago,IL,U.S.A","institution_ids":["https://openalex.org/I180949307"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Embedded Computing and Signal Processing (ECASP) Research Laboratory, Illinois Institute of Technology, Chicago, IL, U.S.A","institution_ids":["https://openalex.org/I180949307"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018536803","display_name":"Jafar Saniie","orcid":"https://orcid.org/0000-0002-2655-6950"},"institutions":[{"id":"https://openalex.org/I180949307","display_name":"Illinois Institute of Technology","ror":"https://ror.org/037t3ry66","country_code":"US","type":"education","lineage":["https://openalex.org/I180949307"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jafar Saniie","raw_affiliation_strings":["Illinois Institute of Technology,Embedded Computing and Signal Processing (ECASP) Research Laboratory,Department of Electrical and Computer Engineering,Chicago,IL,U.S.A","Department of Electrical and Computer Engineering, Embedded Computing and Signal Processing (ECASP) Research Laboratory, Illinois Institute of Technology, Chicago, IL, U.S.A"],"affiliations":[{"raw_affiliation_string":"Illinois Institute of Technology,Embedded Computing and Signal Processing (ECASP) Research Laboratory,Department of Electrical and Computer Engineering,Chicago,IL,U.S.A","institution_ids":["https://openalex.org/I180949307"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Embedded Computing and Signal Processing (ECASP) Research Laboratory, Illinois Institute of Technology, Chicago, IL, U.S.A","institution_ids":["https://openalex.org/I180949307"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103236546"],"corresponding_institution_ids":["https://openalex.org/I180949307"],"apc_list":null,"apc_paid":null,"fwci":0.616,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61667714,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9970999956130981,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.8173205852508545},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7186805605888367},{"id":"https://openalex.org/keywords/mpsoc","display_name":"MPSoC","score":0.6988842487335205},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6479735374450684},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.6352498531341553},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.5265917181968689},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5168122053146362},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4909975826740265},{"id":"https://openalex.org/keywords/ethernet","display_name":"Ethernet","score":0.4901886582374573},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.47377943992614746},{"id":"https://openalex.org/keywords/reconfigurability","display_name":"Reconfigurability","score":0.45087337493896484},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4151664972305298},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.4103900194168091},{"id":"https://openalex.org/keywords/system-on-a-chip","display_name":"System on a chip","score":0.30805182456970215},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.260356068611145},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.19941914081573486}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8173205852508545},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7186805605888367},{"id":"https://openalex.org/C2777187653","wikidata":"https://www.wikidata.org/wiki/Q975106","display_name":"MPSoC","level":3,"score":0.6988842487335205},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6479735374450684},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.6352498531341553},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.5265917181968689},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5168122053146362},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4909975826740265},{"id":"https://openalex.org/C172173386","wikidata":"https://www.wikidata.org/wiki/Q79984","display_name":"Ethernet","level":2,"score":0.4901886582374573},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.47377943992614746},{"id":"https://openalex.org/C2780149590","wikidata":"https://www.wikidata.org/wiki/Q7302742","display_name":"Reconfigurability","level":2,"score":0.45087337493896484},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4151664972305298},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4103900194168091},{"id":"https://openalex.org/C118021083","wikidata":"https://www.wikidata.org/wiki/Q610398","display_name":"System on a chip","level":2,"score":0.30805182456970215},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.260356068611145},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.19941914081573486},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/eit57321.2023.10187228","is_oa":false,"landing_page_url":"https://doi.org/10.1109/eit57321.2023.10187228","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Electro Information Technology (eIT)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.5699999928474426}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2132154112","https://openalex.org/W2537589430","https://openalex.org/W2903688003","https://openalex.org/W2963114857","https://openalex.org/W3038988173","https://openalex.org/W3128475717","https://openalex.org/W4205928000","https://openalex.org/W4210801615","https://openalex.org/W4285391846","https://openalex.org/W4307264545","https://openalex.org/W4312705522","https://openalex.org/W6839488046"],"related_works":["https://openalex.org/W2159103767","https://openalex.org/W1976012348","https://openalex.org/W2614713859","https://openalex.org/W2002682434","https://openalex.org/W4387782849","https://openalex.org/W2137671689","https://openalex.org/W2092587530","https://openalex.org/W2113449380","https://openalex.org/W3146394219","https://openalex.org/W2012131147"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,131],"distributed":[3,85],"system":[4,117],"based":[5],"on":[6,16],"low-power":[7],"embedded":[8],"FPGAs":[9],"designed":[10],"for":[11,21],"edge":[12],"computing":[13],"applications":[14],"focused":[15],"exploring":[17],"distributing":[18],"scheduling":[19],"optimizations":[20],"Deep":[22,75],"Learning":[23,76],"(DL)":[24],"workloads":[25,98],"to":[26,51,92,105,110,139],"obtain":[27],"the":[28,41,70,127,140,146],"best":[29],"performance":[30],"regarding":[31],"latency":[32],"and":[33,43,69,94,134],"power":[34],"efficiency.":[35],"Our":[36],"cluster":[37,71],"was":[38],"modular":[39],"throughout":[40],"experiment,":[42],"we":[44],"have":[45],"implementations":[46],"that":[47],"consist":[48],"of":[49,145],"up":[50],"12":[52],"Zynq-7020":[53],"chip-based":[54],"boards":[55,63],"as":[56,58],"well":[57],"5":[59],"UltraScale+":[60],"MPSoC":[61],"FPGA":[62],"connected":[64],"through":[65],"an":[66],"ethernet":[67],"switch,":[68],"will":[72],"evaluate":[73,93],"configurable":[74],"Accelerator":[77,81],"(DLA)":[78],"Versatile":[79],"Tensor":[80],"(VTA).":[82],"This":[83],"adaptable":[84],"architecture":[86],"is":[87],"distinguished":[88],"by":[89],"its":[90],"capacity":[91],"manage":[95],"neural":[96],"network":[97],"in":[99,130],"numerous":[100],"configurations":[101],"which":[102],"enables":[103],"users":[104],"conduct":[106],"multiple":[107],"experiments":[108],"tailored":[109],"their":[111],"specific":[112],"application":[113],"needs.":[114],"The":[115],"proposed":[116],"can":[118],"simultaneously":[119],"execute":[120],"diverse":[121],"Neural":[122],"Network":[123],"(NN)":[124],"models,":[125],"arrange":[126],"computation":[128],"graph":[129],"pipeline":[132],"structure,":[133],"manually":[135],"allocate":[136],"greater":[137],"resources":[138],"most":[141],"computationally":[142],"intensive":[143],"layers":[144],"NN":[147],"graph.":[148]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}