{"id":"https://openalex.org/W4404057199","doi":"https://doi.org/10.1109/socc62300.2024.10737823","title":"EDEA: Efficient Dual-Engine Accelerator for Depthwise Separable Convolution with Direct Data Transfer","display_name":"EDEA: Efficient Dual-Engine Accelerator for Depthwise Separable Convolution with Direct Data Transfer","publication_year":2024,"publication_date":"2024-09-16","ids":{"openalex":"https://openalex.org/W4404057199","doi":"https://doi.org/10.1109/socc62300.2024.10737823"},"language":"en","primary_location":{"id":"doi:10.1109/socc62300.2024.10737823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/socc62300.2024.10737823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 37th International System-on-Chip Conference (SOCC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2503.11707","any_repository_has_fulltext":true},"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":false,"raw_author_name":"Yi Chen","raw_affiliation_strings":["RWTH Aachen University,Chair of Integrated Digital Systems and Circuit Design,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"]}]},{"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"],"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"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092378557","display_name":"Malte Wabnitz","orcid":"https://orcid.org/0009-0000-9122-3610"},"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":"Malte Wabnitz","raw_affiliation_strings":["RWTH Aachen University,Chair of Integrated Digital Systems and Circuit Design,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"]}]},{"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"],"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"]}]},{"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"],"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"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I887968799"],"apc_list":null,"apc_paid":null,"fwci":1.7046,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.84879545,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"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/T12810","display_name":"Real-time simulation and control systems","score":0.9506999850273132,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12810","display_name":"Real-time simulation and control systems","score":0.9506999850273132,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9366999864578247,"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/convolution","display_name":"Convolution (computer science)","score":0.7338033318519592},{"id":"https://openalex.org/keywords/separable-space","display_name":"Separable space","score":0.6971133947372437},{"id":"https://openalex.org/keywords/dual","display_name":"Dual (grammatical number)","score":0.6949970722198486},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6515703201293945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2105102241039276},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20312833786010742},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.07538062334060669}],"concepts":[{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.7338033318519592},{"id":"https://openalex.org/C70710897","wikidata":"https://www.wikidata.org/wiki/Q680081","display_name":"Separable space","level":2,"score":0.6971133947372437},{"id":"https://openalex.org/C2780980858","wikidata":"https://www.wikidata.org/wiki/Q110022","display_name":"Dual (grammatical number)","level":2,"score":0.6949970722198486},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6515703201293945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2105102241039276},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20312833786010742},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.07538062334060669},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/socc62300.2024.10737823","is_oa":false,"landing_page_url":"https://doi.org/10.1109/socc62300.2024.10737823","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE 37th International System-on-Chip Conference (SOCC)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2503.11707","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.11707","pdf_url":"https://arxiv.org/pdf/2503.11707","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2503.11707","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.11707","pdf_url":"https://arxiv.org/pdf/2503.11707","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.5400000214576721}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311649","display_name":"Ministry of Education","ror":"https://ror.org/036nq5137"},{"id":"https://openalex.org/F4320330944","display_name":"Nature","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2289252105","https://openalex.org/W2973980443","https://openalex.org/W2989331028","https://openalex.org/W3048234025","https://openalex.org/W3093796669","https://openalex.org/W3120770213","https://openalex.org/W3162993841","https://openalex.org/W3206196385","https://openalex.org/W3215511279","https://openalex.org/W4285146087","https://openalex.org/W4291910419","https://openalex.org/W4307927141","https://openalex.org/W4382814440","https://openalex.org/W4388894005","https://openalex.org/W4388976448","https://openalex.org/W4390776943","https://openalex.org/W4393034313","https://openalex.org/W6737664043","https://openalex.org/W6760069825"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2530952058","https://openalex.org/W2582836483","https://openalex.org/W4299366318","https://openalex.org/W3158431807","https://openalex.org/W4297580547","https://openalex.org/W2951583185","https://openalex.org/W2531409750","https://openalex.org/W4308155352"],"abstract_inverted_index":{"Depthwise":[0],"separable":[1],"convolution":[2,33,37],"(DSC)":[3],"has":[4],"emerged":[5],"as":[6],"a":[7,19,61,95,154,162],"crucial":[8],"technique,":[9],"especially":[10],"for":[11,21,188],"resource-constrained":[12],"devices.":[13],"In":[14,71],"this":[15],"paper,":[16],"we":[17,59,74],"propose":[18],"dual-engine":[20,123],"the":[22,28,48,56,68,72,82,105,110,128],"DSC":[23,44,122,176],"hardware":[24,185],"accelerator,":[25],"which":[26,80],"enables":[27],"full":[29],"utilization":[30],"of":[31,55,137,158,164,174],"depthwise":[32],"(DWC)":[34],"and":[35,53,88,92,99,112,117],"pointwise":[36],"(PWC)":[38],"processing":[39],"elements":[40],"(PEs)":[41],"in":[42],"all":[43,175],"layers.":[45],"To":[46],"determine":[47],"optimal":[49],"dataflow,":[50],"data":[51,107],"reuse,":[52],"configuration":[54],"target":[57],"architecture,":[58,73],"conduct":[60],"design":[62],"space":[63],"exploration":[64],"using":[65,127],"MobileNetV1":[66,179],"with":[67,161,167],"CIFAR10":[69],"dataset.":[70],"introduce":[75],"an":[76,135],"additional":[77],"non-convolutional":[78],"unit,":[79],"merges":[81],"dequantization,":[83],"batch":[84],"normalization":[85],"(BN),":[86],"ReLU,":[87],"quantization":[89],"between":[90,109],"DWC":[91,111],"PWC":[93],"into":[94],"simple":[96],"fixed-point":[97],"multiplication":[98],"addition":[100],"operation.":[101],"This":[102],"also":[103],"reduces":[104],"intermediate":[106],"access":[108],"PWC,":[113],"enabling":[114],"streaming":[115],"operation":[116],"reducing":[118],"latency.":[119],"The":[120,170],"proposed":[121],"accelerator":[124],"is":[125,180],"implemented":[126],"22nm":[129],"FDSOI":[130],"technology":[131],"from":[132],"GlobalFoundries,":[133],"occupying":[134],"area":[136],"$0.58":[138],"\\mathbf{~":[139],"m":[140],"m}^{2}$.":[141],"After":[142],"signoff,":[143],"it":[144],"can":[145],"operate":[146],"at":[147,150],"1":[148],"GHz":[149],"TT":[151],"corner,":[152],"achieving":[153],"peak":[155],"energy":[156,172],"efficiency":[157,173,186],"13.43":[159],"TOPS/W":[160],"throughput":[163],"973.55":[165],"GOPS":[166],"8-bit":[168],"precision.":[169],"average":[171],"layers":[177],"on":[178],"11.13":[181],"TOPS/W,":[182],"demonstrating":[183],"substantial":[184],"improvements":[187],"DSC-based":[189],"applications.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-10T00:00:00"}
