{"id":"https://openalex.org/W4395680644","doi":"https://doi.org/10.1109/tvlsi.2024.3383871","title":"Amoeba: An Efficient and Flexible FPGA-Based Accelerator for Arbitrary-Kernel CNNs","display_name":"Amoeba: An Efficient and Flexible FPGA-Based Accelerator for Arbitrary-Kernel CNNs","publication_year":2024,"publication_date":"2024-04-26","ids":{"openalex":"https://openalex.org/W4395680644","doi":"https://doi.org/10.1109/tvlsi.2024.3383871"},"language":"en","primary_location":{"id":"doi:10.1109/tvlsi.2024.3383871","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2024.3383871","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"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 Very Large Scale Integration (VLSI) 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/A5091293910","display_name":"Xiao Wu","orcid":"https://orcid.org/0000-0001-8306-6889"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiao Wu","raw_affiliation_strings":["School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0001-8306-6889","affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114309947","display_name":"Miaoxin Wang","orcid":"https://orcid.org/0009-0004-7336-1365"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Miaoxin Wang","raw_affiliation_strings":["School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"raw_orcid":"https://orcid.org/0009-0004-7336-1365","affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101534216","display_name":"Jun Lin","orcid":"https://orcid.org/0000-0003-2291-309X"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Lin","raw_affiliation_strings":["School of Electronic Science and Engineering and the Interdisciplinary Research Center for Future Intelligent Chips (Chip-X), Nanjing University, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering and the Interdisciplinary Research Center for Future Intelligent Chips (Chip-X), Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100696999","display_name":"Zhongfeng Wang","orcid":"https://orcid.org/0000-0002-7227-4786"},"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"]},{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongfeng Wang","raw_affiliation_strings":["School of Electronic Science and Engineering, Nanjing University, Nanjing, China","School of Integrated Circuits, Sun Yat-sen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-7227-4786","affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]},{"raw_affiliation_string":"School of Integrated Circuits, Sun Yat-sen University, Shenzhen, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5957,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.90946383,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"32","issue":"6","first_page":"1086","last_page":"1099"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9951000213623047,"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":0.9951000213623047,"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/T12859","display_name":"Cell Image Analysis Techniques","score":0.9932000041007996,"subfield":{"id":"https://openalex.org/subfields/1304","display_name":"Biophysics"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9921000003814697,"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":0.7214786410331726},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6924872398376465},{"id":"https://openalex.org/keywords/amoeba","display_name":"Amoeba (genus)","score":0.6118060350418091},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.49322742223739624},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.340628057718277},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.33223721385002136},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21415278315544128},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.08833801746368408},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.0856868326663971}],"concepts":[{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7214786410331726},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6924872398376465},{"id":"https://openalex.org/C2776172558","wikidata":"https://www.wikidata.org/wiki/Q46729","display_name":"Amoeba (genus)","level":2,"score":0.6118060350418091},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.49322742223739624},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.340628057718277},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.33223721385002136},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21415278315544128},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.08833801746368408},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0856868326663971},{"id":"https://openalex.org/C89423630","wikidata":"https://www.wikidata.org/wiki/Q7193","display_name":"Microbiology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tvlsi.2024.3383871","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tvlsi.2024.3383871","pdf_url":null,"source":{"id":"https://openalex.org/S37538908","display_name":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","issn_l":"1063-8210","issn":["1063-8210","1557-9999"],"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 Very Large Scale Integration (VLSI) Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2250357272","display_name":null,"funder_award_id":"62174084","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4187776313","display_name":null,"funder_award_id":"2022YFB4400604","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5354445887","display_name":null,"funder_award_id":"62341408","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W1899185266","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2598666589","https://openalex.org/W2795915628","https://openalex.org/W2887453575","https://openalex.org/W2963163009","https://openalex.org/W2982083293","https://openalex.org/W3008408165","https://openalex.org/W3036289652","https://openalex.org/W3082366738","https://openalex.org/W3125832420","https://openalex.org/W3138516171","https://openalex.org/W3149224530","https://openalex.org/W3172509117","https://openalex.org/W3178956316","https://openalex.org/W3194133609","https://openalex.org/W3206196385","https://openalex.org/W3217077065","https://openalex.org/W4205146836","https://openalex.org/W4205884968","https://openalex.org/W4214870144","https://openalex.org/W4226334005","https://openalex.org/W4246193833","https://openalex.org/W4285235315","https://openalex.org/W4293584584","https://openalex.org/W4297094636","https://openalex.org/W4297775537","https://openalex.org/W4312247188","https://openalex.org/W4312312779","https://openalex.org/W4317727911","https://openalex.org/W4318767343","https://openalex.org/W4324290984","https://openalex.org/W4360770687","https://openalex.org/W4384788057","https://openalex.org/W4384947633","https://openalex.org/W4390678688","https://openalex.org/W6638667902","https://openalex.org/W6639927594","https://openalex.org/W6737664043","https://openalex.org/W6750227808"],"related_works":["https://openalex.org/W2384623286","https://openalex.org/W194862172","https://openalex.org/W2212588251","https://openalex.org/W1995882302","https://openalex.org/W2799513399","https://openalex.org/W2076406583","https://openalex.org/W2096844293","https://openalex.org/W2363944576","https://openalex.org/W2351041855","https://openalex.org/W2570254841"],"abstract_inverted_index":{"Inspired":[0],"by":[1,141],"the":[2,85,112,118,127,133,147,193],"key":[3],"operation":[4],"of":[5,38,41,177,200],"vision":[6],"transformers":[7],"(ViTs),":[8],"convolutional":[9],"neural":[10],"networks":[11],"(CNNs)":[12],"have":[13],"widely":[14],"adopted":[15],"arbitrary-kernel":[16,97],"convolutions":[17,98],"to":[18,116,179,189],"achieve":[19],"high":[20],"performance":[21,144,168],"in":[22,47,82],"diverse":[23],"vision-based":[24],"tasks.":[25,206],"However,":[26],"existing":[27],"hardware":[28,201],"efforts":[29],"primarily":[30],"focus":[31],"on":[32,157,169,192],"implementing":[33],"CNN":[34,128,204],"models":[35],"that":[36],"consist":[37],"a":[39,58,142,175],"stack":[40],"small":[42],"kernels,":[43],"which":[44,92],"poses":[45],"challenges":[46],"supporting":[48,69],"large-kernel":[49],"convolutions.":[50],"To":[51,124],"address":[52],"this":[53],"limitation,":[54],"we":[55,76,103,131],"propose":[56],"Amoeba,":[57],"flexible":[59,94],"field-programmable":[60],"gate":[61],"array":[62],"(FPGA)-based":[63],"inference":[64,205],"accelerator":[65,154],"designed":[66],"for":[67,96,203],"efficiently":[68],"CNNs":[70],"with":[71,84],"arbitrary":[72],"kernel":[73],"sizes.":[74],"Specifically,":[75],"present":[77],"an":[78],"optimized":[79],"dataflow":[80],"approach":[81],"collaboration":[83],"Z-flow":[86],"method":[87],"and":[88,107,120,171],"kernel-segmentation":[89],"(Kseg)":[90],"scheme,":[91],"enables":[93],"support":[95],"without":[99],"sacrificing":[100],"efficiency.":[101],"Additionally,":[102],"incorporate":[104],"vertical-fused":[105],"(VF)":[106],"horizontal-fused":[108],"(HF)":[109],"methods":[110],"into":[111],"layer":[113],"execution":[114],"schedule":[115],"optimize":[117],"computation":[119],"data":[121],"transfer":[122],"process.":[123],"further":[125],"enhance":[126],"deployment":[129],"performance,":[130],"employ":[132],"loop":[134],"tiling":[135],"scheme":[136],"search":[137],"(LTSS)":[138],"method,":[139],"guided":[140],"fine-grained":[143],"model,":[145],"during":[146],"early":[148],"design":[149],"phase.":[150],"The":[151,163],"proposed":[152],"Amoeba":[153,183],"is":[155],"evaluated":[156],"Intel":[158],"Arria":[159],"10":[160],"SoC":[161],"FPGA.":[162],"experimental":[164],"results":[165],"demonstrate":[166],"excellent":[167],"prevalent":[170],"emerging":[172],"CNNs,":[173],"achieving":[174],"throughput":[176],"up":[178],"286.2":[180],"GOPs.":[181],"Notably,":[182],"achieves":[184],"4.36$\\times$better":[185],"DSP":[186],"efficiency":[187],"compared":[188],"prior":[190],"works":[191],"same":[194],"network,":[195],"highlighting":[196],"its":[197],"superior":[198],"utilization":[199],"resources":[202]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}