{"id":"https://openalex.org/W4388894005","doi":"https://doi.org/10.1109/vlsi-soc57769.2023.10321918","title":"An Energy-Efficient and Area-Efficient Depthwise Separable Convolution Accelerator with Minimal On-Chip Memory Access","display_name":"An Energy-Efficient and Area-Efficient Depthwise Separable Convolution Accelerator with Minimal On-Chip Memory Access","publication_year":2023,"publication_date":"2023-10-16","ids":{"openalex":"https://openalex.org/W4388894005","doi":"https://doi.org/10.1109/vlsi-soc57769.2023.10321918"},"language":"en","primary_location":{"id":"doi:10.1109/vlsi-soc57769.2023.10321918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vlsi-soc57769.2023.10321918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IFIP/IEEE 31st International Conference on Very Large Scale Integration (VLSI-SoC)","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/A5100419293","display_name":"Yi Chen","orcid":"https://orcid.org/0000-0003-3669-1643"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Yi Chen","raw_affiliation_strings":["RWTH Aachen University,Chair of Integrated Digital Systems and Circuit Design,Germany","Chair of Integrated Digital Systems and Circuit Design, RWTH Aachen University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Chair of Integrated Digital Systems and Circuit Design,Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Chair of Integrated Digital Systems and Circuit Design, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043984277","display_name":"Jie Lou","orcid":"https://orcid.org/0000-0003-0380-8585"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Jie Lou","raw_affiliation_strings":["RWTH Aachen University,Chair of Integrated Digital Systems and Circuit Design,Germany","Chair of Integrated Digital Systems and Circuit Design, RWTH Aachen University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Chair of Integrated Digital Systems and Circuit Design,Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Chair of Integrated Digital Systems and Circuit Design, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024548698","display_name":"Christian Lanius","orcid":"https://orcid.org/0000-0001-7107-3782"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Christian Lanius","raw_affiliation_strings":["RWTH Aachen University,Chair of Integrated Digital Systems and Circuit Design,Germany","Chair of Integrated Digital Systems and Circuit Design, RWTH Aachen University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Chair of Integrated Digital Systems and Circuit Design,Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Chair of Integrated Digital Systems and Circuit Design, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5029479465","display_name":"Florian Freye","orcid":"https://orcid.org/0000-0003-3025-8910"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Florian Freye","raw_affiliation_strings":["RWTH Aachen University,Chair of Integrated Digital Systems and Circuit Design,Germany","Chair of Integrated Digital Systems and Circuit Design, RWTH Aachen University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Chair of Integrated Digital Systems and Circuit Design,Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Chair of Integrated Digital Systems and Circuit Design, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014668111","display_name":"Johnson Loh","orcid":"https://orcid.org/0009-0001-2659-5255"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Johnson Loh","raw_affiliation_strings":["RWTH Aachen University,Chair of Integrated Digital Systems and Circuit Design,Germany","Chair of Integrated Digital Systems and Circuit Design, RWTH Aachen University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Chair of Integrated Digital Systems and Circuit Design,Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Chair of Integrated Digital Systems and Circuit Design, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023628905","display_name":"Tobias Gemmeke","orcid":"https://orcid.org/0000-0003-1583-3411"},"institutions":[{"id":"https://openalex.org/I887968799","display_name":"RWTH Aachen University","ror":"https://ror.org/04xfq0f34","country_code":"DE","type":"education","lineage":["https://openalex.org/I887968799"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Tobias Gemmeke","raw_affiliation_strings":["RWTH Aachen University,Chair of Integrated Digital Systems and Circuit Design,Germany","Chair of Integrated Digital Systems and Circuit Design, RWTH Aachen University, Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RWTH Aachen University,Chair of Integrated Digital Systems and Circuit Design,Germany","institution_ids":["https://openalex.org/I887968799"]},{"raw_affiliation_string":"Chair of Integrated Digital Systems and Circuit Design, RWTH Aachen University, Germany","institution_ids":["https://openalex.org/I887968799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100419293"],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":0.5688,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.69154663,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9990000128746033,"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":0.9990000128746033,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9771999716758728,"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/T10860","display_name":"Speech and Audio Processing","score":0.9732000231742859,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.6753464937210083},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6493773460388184},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6190418004989624},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.6094260811805725},{"id":"https://openalex.org/keywords/static-random-access-memory","display_name":"Static random-access memory","score":0.5578742027282715},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.47135868668556213},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4466205835342407},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.4455801844596863},{"id":"https://openalex.org/keywords/tops","display_name":"TOPS","score":0.44032588601112366},{"id":"https://openalex.org/keywords/cmos","display_name":"CMOS","score":0.42039069533348083},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.4132877588272095},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3925319314002991},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.34929972887039185},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.29887855052948},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.29757457971572876},{"id":"https://openalex.org/keywords/electronic-engineering","display_name":"Electronic engineering","score":0.2159762978553772},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.2056826651096344},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17789119482040405},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.157159686088562},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.13078123331069946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6753464937210083},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6493773460388184},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6190418004989624},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.6094260811805725},{"id":"https://openalex.org/C68043766","wikidata":"https://www.wikidata.org/wiki/Q267416","display_name":"Static random-access memory","level":2,"score":0.5578742027282715},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.47135868668556213},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4466205835342407},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.4455801844596863},{"id":"https://openalex.org/C2777675136","wikidata":"https://www.wikidata.org/wiki/Q835642","display_name":"TOPS","level":3,"score":0.44032588601112366},{"id":"https://openalex.org/C46362747","wikidata":"https://www.wikidata.org/wiki/Q173431","display_name":"CMOS","level":2,"score":0.42039069533348083},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.4132877588272095},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3925319314002991},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.34929972887039185},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.29887855052948},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.29757457971572876},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.2159762978553772},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.2056826651096344},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17789119482040405},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.157159686088562},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.13078123331069946},{"id":"https://openalex.org/C548081761","wikidata":"https://www.wikidata.org/wiki/Q180388","display_name":"Waste management","level":1,"score":0.0},{"id":"https://openalex.org/C159737794","wikidata":"https://www.wikidata.org/wiki/Q124274","display_name":"Azimuth","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/vlsi-soc57769.2023.10321918","is_oa":false,"landing_page_url":"https://doi.org/10.1109/vlsi-soc57769.2023.10321918","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IFIP/IEEE 31st International Conference on Very Large Scale Integration (VLSI-SoC)","raw_type":"proceedings-article"},{"id":"pmh:oai:publications.rwth-aachen.de:980025","is_oa":false,"landing_page_url":"https://publications.rwth-aachen.de/record/980025","pdf_url":null,"source":{"id":"https://openalex.org/S4306401033","display_name":"RWTH Publications (RWTH Aachen)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I887968799","host_organization_name":"RWTH Aachen University","host_organization_lineage":["https://openalex.org/I887968799"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"2023 IFIP/IEEE 31st International Conference on Very Large Scale Integration (VLSI-SoC) : 16-18 Oct. 2023 : conference location: Dubai, United Arab Emirates / IFIP VLSI-SoC ; publisher: IEEE<br/>IFIP/IEEE 31. International Conference on Very Large Scale Integration, VLSI-SoC, Dubai, Stadt, U Arab Emirates, 2023-10-16 - 2023-10-18","raw_type":"info:eu-repo/semantics/publishedVersion"}],"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/F4320321408","display_name":"Ministry of Education","ror":"https://ror.org/01p262204"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W2017369466","https://openalex.org/W2289252105","https://openalex.org/W2591982329","https://openalex.org/W2605487586","https://openalex.org/W2808463410","https://openalex.org/W2899176839","https://openalex.org/W2916954108","https://openalex.org/W2973980443","https://openalex.org/W2979042679","https://openalex.org/W2989331028","https://openalex.org/W3120770213","https://openalex.org/W3123687588","https://openalex.org/W3159730268","https://openalex.org/W3162993841","https://openalex.org/W3177397229","https://openalex.org/W3210597831","https://openalex.org/W3215511279","https://openalex.org/W4200404774","https://openalex.org/W4200486959","https://openalex.org/W4297775537","https://openalex.org/W6737664043","https://openalex.org/W6760069825"],"related_works":["https://openalex.org/W2811109569","https://openalex.org/W2385933648","https://openalex.org/W2381557761","https://openalex.org/W4231398535","https://openalex.org/W2067978743","https://openalex.org/W4245680303","https://openalex.org/W1996292569","https://openalex.org/W4210522299","https://openalex.org/W2043153436","https://openalex.org/W4251921734"],"abstract_inverted_index":{"Depthwise":[0],"separable":[1],"convolution":[2,40,50],"(DSC)":[3],"has":[4],"emerged":[5],"as":[6],"a":[7,23,108],"crucial":[8],"building":[9],"block":[10],"for":[11,26,38,48,93,162,178,186,191],"developing":[12],"lightweight":[13],"convolutional":[14],"neural":[15],"networks":[16],"(CNNs).":[17],"In":[18],"this":[19],"paper,":[20],"we":[21,70,106],"present":[22,107],"hardware":[24],"accelerator":[25,115,137,181],"DSC":[27,114],"that":[28,134],"enables":[29],"100%":[30],"utilization":[31,47],"of":[32,64,147,155],"the":[33,58,65,127,135,169,175,179],"processing":[34],"element":[35],"(PE)":[36],"array":[37],"depthwise":[39],"(DWC)":[41],"and":[42,74,81,96,122,142,151,188],"achieves":[43],"up":[44],"to":[45,85,91,99,173,183],"98%":[46],"pointwise":[49],"(PWC),":[51],"while":[52],"also":[53],"reducing":[54],"latency.":[55],"By":[56],"partitioning":[57],"input":[59,79],"feature":[60],"map":[61],"(ifmap)":[62],"SRAM":[63,90],"DWC":[66,95,163,187],"into":[67],"three":[68],"banks,":[69],"minimize":[71],"memory":[72],"access":[73],"maximize":[75],"data":[76],"reuse.":[77],"The":[78,112,130],"activations":[80],"weights":[82],"only":[83],"need":[84],"be":[86],"loaded":[87],"once":[88],"from":[89],"PE":[92],"both":[94],"PWC.":[97],"Additionally,":[98],"support":[100],"efficient":[101],"operations":[102],"across":[103],"different":[104],"layers,":[105],"layerwise":[109],"matching":[110],"method.":[111],"proposed":[113,136,180],"is":[116],"implemented":[117],"in":[118],"22nm":[119],"FDSOI":[120],"technology":[121],"validated":[123],"using":[124],"MobileNetV1":[125],"on":[126],"CIFAR10":[128],"dataset.":[129],"post-layout":[131],"results":[132],"demonstrate":[133],"can":[138],"operate":[139],"at":[140,165],"1GHz":[141],"achieve":[143],"an":[144,152],"energy":[145,176],"efficiency":[146,154,177],"5.07":[148],"(3.96)":[149],"TOPS/W":[150,185,190],"area":[153],"519.2":[156],"(461.52)":[157],"GOPS/mm":[158],"<sup":[159],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[160],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">2</sup>":[161],"(PWC)":[164],"0.8V.":[166],"After":[167],"scaling":[168],"supply":[170],"voltage":[171],"down":[172],"0.5V,":[174],"increases":[182],"13.64":[184],"10.64":[189],"PWC,":[192],"respectively.":[193]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-05-24T08:33:08.758527","created_date":"2025-10-10T00:00:00"}