{"id":"https://openalex.org/W4412623560","doi":"https://doi.org/10.1109/tnnls.2025.3587694","title":"HCG: Streaming DCNN Accelerator With a Hybrid Computational Granularity Scheme on FPGA","display_name":"HCG: Streaming DCNN Accelerator With a Hybrid Computational Granularity Scheme on FPGA","publication_year":2025,"publication_date":"2025-07-24","ids":{"openalex":"https://openalex.org/W4412623560","doi":"https://doi.org/10.1109/tnnls.2025.3587694","pmid":"https://pubmed.ncbi.nlm.nih.gov/40705585"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2025.3587694","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3587694","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5048231607","display_name":"Wenjin Huang","orcid":"https://orcid.org/0000-0002-8861-4263"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenjin Huang","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-8861-4263","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008878143","display_name":"Conghui Luo","orcid":"https://orcid.org/0000-0002-0525-1840"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Conghui Luo","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0525-1840","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022180506","display_name":"Baoze Zhao","orcid":"https://orcid.org/0000-0002-0050-4925"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baoze Zhao","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-0050-4925","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109573014","display_name":"Han Yi Jiao","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Han Jiao","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0003-2021-8015","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101448401","display_name":"Yihua Huang","orcid":"https://orcid.org/0000-0001-6736-7913"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihua Huang","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-6736-7913","affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5953,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82289658,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"36","issue":"10","first_page":"18681","last_page":"18695"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8565999865531921,"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":0.8565999865531921,"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/granularity","display_name":"Granularity","score":0.9020466804504395},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7897648215293884},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.7655183672904968},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6362215280532837},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3629542291164398},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3579637408256531},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.349327027797699},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2840687334537506},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16078752279281616},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15552273392677307}],"concepts":[{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.9020466804504395},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7897648215293884},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.7655183672904968},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6362215280532837},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3629542291164398},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3579637408256531},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.349327027797699},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2840687334537506},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16078752279281616},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15552273392677307},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2025.3587694","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2025.3587694","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:40705585","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40705585","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.5400000214576721}],"awards":[{"id":"https://openalex.org/G2810662379","display_name":null,"funder_award_id":"2024A1515011259","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G6552663724","display_name":null,"funder_award_id":"2022A1515110006","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G6701825051","display_name":null,"funder_award_id":"62276278","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G709943964","display_name":null,"funder_award_id":"2024A1515011259","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"},{"id":"https://openalex.org/G8204698780","display_name":null,"funder_award_id":"2022A1515110006","funder_id":"https://openalex.org/F4320337111","funder_display_name":"Basic and Applied Basic Research Foundation of Guangdong Province"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320337111","display_name":"Basic and Applied Basic Research Foundation of Guangdong Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W2294282016","https://openalex.org/W2525740295","https://openalex.org/W2565125333","https://openalex.org/W2810861508","https://openalex.org/W2891946740","https://openalex.org/W2899915146","https://openalex.org/W2902895686","https://openalex.org/W2912949188","https://openalex.org/W3082058622","https://openalex.org/W3118709344","https://openalex.org/W3131926233","https://openalex.org/W3132745255","https://openalex.org/W3159911742","https://openalex.org/W3164217046","https://openalex.org/W4211090839","https://openalex.org/W4280651189","https://openalex.org/W4291910419","https://openalex.org/W4312037452","https://openalex.org/W4312998584","https://openalex.org/W4379115810","https://openalex.org/W4379115892","https://openalex.org/W4379115905","https://openalex.org/W4384947633","https://openalex.org/W4387502592","https://openalex.org/W4388505151","https://openalex.org/W4391429093","https://openalex.org/W4391429613","https://openalex.org/W4400579168","https://openalex.org/W4401386645","https://openalex.org/W4409560185"],"related_works":["https://openalex.org/W2931688134","https://openalex.org/W2377919138","https://openalex.org/W2378857091","https://openalex.org/W103652678","https://openalex.org/W4226090359","https://openalex.org/W2059697060","https://openalex.org/W1967938402","https://openalex.org/W2386041993","https://openalex.org/W1608572506","https://openalex.org/W2352941988"],"abstract_inverted_index":{"With":[0],"the":[1,33,46,50,67,101,163,173,191,219,222,231,239,272],"growth":[2],"of":[3,49,72,93,136,165,221,233,247,274],"field-programmable":[4],"gate":[5],"array":[6],"(FPGA)":[7],"hardware":[8,195],"resources,":[9],"streaming":[10,21,109],"DCNN":[11],"accelerators":[12,254],"leverage":[13],"interconvolutional-layer":[14],"parallelism":[15],"to":[16,177,203],"enhance":[17],"throughput.":[18,217],"In":[19],"existing":[20,276],"accelerators,":[22],"convolution":[23],"nodes":[24,98,171],"typically":[25],"adopt":[26],"layer-":[27],"or":[28,70],"column-based":[29],"tiling":[30],"methods,":[31],"where":[32],"tiled":[34,77],"input":[35,41],"feature":[36,52],"map":[37,53],"(Ifmap)":[38],"encompasses":[39],"all":[40,97],"channels.":[42],"This":[43,104],"approach":[44],"facilitates":[45],"comprehensive":[47],"calculation":[48],"output":[51],"(Ofmap)":[54],"and":[55,85,132,147,152,172,186,198,215,225,250,266],"maximizes":[56],"interlayer":[57],"parallelism.":[58],"The":[59,90],"computational":[60,94,114,124,166,205],"granularity,":[61,125],"defined":[62],"in":[63],"this":[64,140,159],"study":[65],"as":[66],"calculated":[68],"rows":[69],"columns":[71],"Ofmap":[73],"based":[74],"on":[75,168,238],"each":[76,208],"Ifmap":[78,83],"data,":[79],"significantly":[80],"influences":[81],"on-chip":[82],"storage":[84],"off-chip":[86],"weight":[87],"bandwidth":[88],"(BW).":[89],"uniform":[91],"application":[92],"granularity":[95,115,167,206],"across":[96],"inevitably":[99],"impacts":[100],"memory-BW":[102,130,213],"tradeoff.":[103],"article":[105,160,192],"introduces":[106],"a":[107,112,127,179,194,200,234],"novel":[108],"accelerator":[110,237],"with":[111],"hybrid":[113,141],"(HCG)":[116],"scheme.":[117],"Each":[118],"node":[119],"employs":[120,199],"an":[121],"independently":[122],"optimized":[123],"enabling":[126],"more":[128,133],"flexible":[129],"tradeoff":[131,214],"effective":[134],"utilization":[135],"FPGA":[137],"resources.":[138],"However,":[139],"scheme":[142],"can":[143],"introduce":[144],"pipeline":[145,150,182,184],"bubbles":[146,185],"increase":[148],"system":[149,181,188],"complexity":[151],"control":[153],"logic.":[154],"To":[155],"address":[156],"these":[157],"challenges,":[158],"theoretically":[161],"analyzes":[162],"impact":[164],"individual":[169],"computing":[170,209],"overall":[174],"system,":[175],"aiming":[176],"establish":[178],"seamless":[180],"without":[183],"simplify":[187],"design.":[189],"Furthermore,":[190],"develops":[193],"overhead":[196],"model":[197],"heuristic":[201],"algorithm":[202],"optimize":[204],"for":[207,255],"node,":[210],"achieving":[211],"optimal":[212],"higher":[216],"Finally,":[218],"effectiveness":[220],"proposed":[223],"design":[224],"optimization":[226],"methodology":[227],"is":[228],"validated":[229],"through":[230],"implementation":[232],"3-TOPS":[235,262],"ResNet-18":[236],"Alveo":[240],"U250":[241],"development":[242],"board":[243],"under":[244],"BW":[245],"constraints":[246],"25,":[248],"20,":[249],"15":[251],"GB/s.":[252],"Additionally,":[253],"4-TOPS":[256,258,264,267],"VGG-16,":[257],"ResNet-34,":[259],"5-TOPS":[260],"ResNet-50,":[261],"MobileNetV1,":[263],"ConvNeXt-T,":[265],"ResNeXt-50":[268],"are":[269],"implemented,":[270],"surpassing":[271],"performance":[273],"most":[275],"works.":[277]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-24T13:16:06.693445","created_date":"2025-10-10T00:00:00"}