{"id":"https://openalex.org/W4399487612","doi":"https://doi.org/10.1145/3649476.3658752","title":"Communication Minimized Model-Architecture Co-design for Efficient Convolution Acceleration","display_name":"Communication Minimized Model-Architecture Co-design for Efficient Convolution Acceleration","publication_year":2024,"publication_date":"2024-06-10","ids":{"openalex":"https://openalex.org/W4399487612","doi":"https://doi.org/10.1145/3649476.3658752"},"language":"en","primary_location":{"id":"doi:10.1145/3649476.3658752","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649476.3658752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2024","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/A5101669107","display_name":"Wendi Sun","orcid":"https://orcid.org/0009-0002-3198-2345"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wendi Sun","raw_affiliation_strings":["School of Microelectronics, University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0009-0002-3198-2345","affiliations":[{"raw_affiliation_string":"School of Microelectronics, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100764841","display_name":"Wenhao Sun","orcid":"https://orcid.org/0009-0003-6118-8174"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenhao Sun","raw_affiliation_strings":["School of Microelectronics, University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0009-0003-6118-8174","affiliations":[{"raw_affiliation_string":"School of Microelectronics, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048328562","display_name":"Y Wang","orcid":"https://orcid.org/0009-0006-4017-8913"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Wang","raw_affiliation_strings":["School of Microelectronics, University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0009-0006-4017-8913","affiliations":[{"raw_affiliation_string":"School of Microelectronics, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033886915","display_name":"Yi Kang","orcid":"https://orcid.org/0000-0002-5487-6855"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yi Kang","raw_affiliation_strings":["School of Microelectronics, University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0002-5487-6855","affiliations":[{"raw_affiliation_string":"School of Microelectronics, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100423614","display_name":"Song Chen","orcid":"https://orcid.org/0000-0003-0341-3428"},"institutions":[{"id":"https://openalex.org/I126520041","display_name":"University of Science and Technology of China","ror":"https://ror.org/04c4dkn09","country_code":"CN","type":"education","lineage":["https://openalex.org/I126520041","https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Chen","raw_affiliation_strings":["School of Microelectronics, University of Science and Technology of China, China"],"raw_orcid":"https://orcid.org/0000-0003-0341-3428","affiliations":[{"raw_affiliation_string":"School of Microelectronics, University of Science and Technology of China, China","institution_ids":["https://openalex.org/I126520041"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.443,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.56458023,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"144","last_page":"150"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.9993000030517578,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9993000030517578,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9965999722480774,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9833999872207642,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/acceleration","display_name":"Acceleration","score":0.7481726408004761},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6965429782867432},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.6529075503349304},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5964087843894958},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.410773366689682},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13249588012695312},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.08970886468887329}],"concepts":[{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.7481726408004761},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6965429782867432},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.6529075503349304},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5964087843894958},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.410773366689682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13249588012695312},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08970886468887329},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"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},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3649476.3658752","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3649476.3658752","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Great Lakes Symposium on VLSI 2024","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2015861736","https://openalex.org/W2442974303","https://openalex.org/W2606722458","https://openalex.org/W2807091852","https://openalex.org/W3017059173","https://openalex.org/W3136346557","https://openalex.org/W4214493665","https://openalex.org/W4220972538","https://openalex.org/W4240168186"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W2038503502"],"abstract_inverted_index":{"CNN":[0,118],"is":[1,85,93],"indispensable":[2],"for":[3,64,100],"today\u2019s":[4],"Artificial":[5],"Intelligence":[6],"(AI)":[7],"applications,":[8],"but":[9,29],"brings":[10],"dominantly":[11],"large":[12],"overhead":[13],"of":[14,33],"data":[15,79],"communication.":[16],"Current":[17],"works":[18],"mainly":[19],"focus":[20],"on":[21,77,121],"prior":[22],"off-chip":[23,71],"or":[24],"intuitive/heuristic":[25],"on-chip":[26,83,101,136],"access":[27,39,46,161],"optimization,":[28],"with":[30,140,152,164],"the":[31,69],"development":[32],"Near":[34],"Memory":[35],"Processing":[36],"(NMP),":[37],"DRAM":[38],"cost":[40],"has":[41],"greatly":[42],"dropped":[43],"and":[44,87,105,114,142],"on&off-chip":[45,59,89],"optimization":[47],"needs":[48],"rethinking":[49],"as":[50],"a":[51,57,97,115],"whole.":[52],"Thus,":[53],"this":[54],"paper":[55],"proposes":[56],"holistic":[58],"communication-minimized":[60],"model-architecture":[61],"acceleration":[62],"scheme":[63],"CNN.":[65],"First,":[66],"we":[67,109,156],"derive":[68],"layer-wise":[70],"communication":[72,90],"Lower":[73],"Bound":[74],"(LB)":[75],"based":[76,120],"different":[78],"reuse":[80],"strategies.":[81],"Second,":[82],"LB":[84],"derived":[86],"overall":[88],"analysis":[91],"model":[92],"presented":[94],"to":[95],"provide":[96],"solid":[98],"guidance":[99],"storage":[102,137],"allocation,":[103],"dataflow":[104,113],"architecture":[106],"design.":[107],"Finally,":[108],"design":[110],"Window-Primitive":[111],"(WP)":[112],"Systolic-Cross-Line":[116],"(SCL)":[117],"accelerator":[119],"proposed":[122],"theoretical":[123],"model.":[124],"SCL":[125],"achieves":[126],"3.8":[127],"\u00d7":[128,134,144,148,160],"pJ/MAC":[129],"energy":[130,162],"reduction":[131,145],"at":[132,146],"1.4":[133],"less":[135,149],"area":[138,150],"compared":[139,151,163],"Eyeriss":[141],"1.3~1.8":[143],"3~4":[147],"CLB.":[153],"For":[154],"NMP,":[155],"reduce":[157],"around":[158],"2":[159],"previous":[165],"systolic":[166],"NMP":[167],"architecture.":[168]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}