{"id":"https://openalex.org/W4220782773","doi":"https://doi.org/10.1109/isscc42614.2022.9731757","title":"A 65nm Systolic Neural CPU Processor for Combined Deep Learning and General-Purpose Computing with 95% PE Utilization, High Data Locality and Enhanced End-to-End Performance","display_name":"A 65nm Systolic Neural CPU Processor for Combined Deep Learning and General-Purpose Computing with 95% PE Utilization, High Data Locality and Enhanced End-to-End Performance","publication_year":2022,"publication_date":"2022-02-20","ids":{"openalex":"https://openalex.org/W4220782773","doi":"https://doi.org/10.1109/isscc42614.2022.9731757"},"language":"en","primary_location":{"id":"doi:10.1109/isscc42614.2022.9731757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isscc42614.2022.9731757","pdf_url":null,"source":{"id":"https://openalex.org/S4363607897","display_name":"2022 IEEE International Solid- State Circuits Conference (ISSCC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Solid- State Circuits Conference (ISSCC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5041367243","display_name":"Yuhao Ju","orcid":"https://orcid.org/0000-0003-2509-400X"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuhao Ju","raw_affiliation_strings":["Northwestern University,Evanston,IL","Northwestern University, Evanston, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University,Evanston,IL","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Northwestern University, Evanston, IL","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005991726","display_name":"Jie Gu","orcid":"https://orcid.org/0000-0003-2912-7294"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jie Gu","raw_affiliation_strings":["Northwestern University,Evanston,IL","Northwestern University, Evanston, IL"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northwestern University,Evanston,IL","institution_ids":["https://openalex.org/I111979921"]},{"raw_affiliation_string":"Northwestern University, Evanston, IL","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I111979921"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"3"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9997000098228455,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994999766349792,"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/computer-science","display_name":"Computer science","score":0.8281947374343872},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.7075687050819397},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4799261689186096},{"id":"https://openalex.org/keywords/cpu-shielding","display_name":"CPU shielding","score":0.45779189467430115},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43790215253829956},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.4145176112651825},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3855985403060913},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.2907281219959259},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20199626684188843}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8281947374343872},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.7075687050819397},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4799261689186096},{"id":"https://openalex.org/C180613757","wikidata":"https://www.wikidata.org/wiki/Q5013757","display_name":"CPU shielding","level":3,"score":0.45779189467430115},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43790215253829956},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.4145176112651825},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3855985403060913},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.2907281219959259},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20199626684188843},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isscc42614.2022.9731757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isscc42614.2022.9731757","pdf_url":null,"source":{"id":"https://openalex.org/S4363607897","display_name":"2022 IEEE International Solid- State Circuits Conference (ISSCC)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Solid- State Circuits Conference (ISSCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[{"id":"https://openalex.org/G6842002372","display_name":null,"funder_award_id":"CCF-2008906","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2606722458","https://openalex.org/W3101856175","https://openalex.org/W3102175148","https://openalex.org/W3213528054","https://openalex.org/W6785458485"],"related_works":["https://openalex.org/W2387982802","https://openalex.org/W1896942098","https://openalex.org/W1991061790","https://openalex.org/W2088078730","https://openalex.org/W2400763249","https://openalex.org/W1482063109","https://openalex.org/W2043940072","https://openalex.org/W2249399447","https://openalex.org/W2745443495","https://openalex.org/W2904030423"],"abstract_inverted_index":{"Despite":[0],"recent":[1],"progress":[2],"on":[3,343],"building":[4],"highly":[5,57],"efficient":[6,58],"deep":[7,120],"neural":[8,211],"network":[9],"(DNN)":[10],"accelerators,":[11],"few":[12],"works":[13,151],"have":[14,152],"targeted":[15],"improving":[16],"the":[17,38,44,51,54,65,89,102,123,132,144,179,184,189,194,216,278,325],"end-to-end":[18,45,119,264,344],"performance":[19],"of":[20,91,94,134,157,162,183,187,196,218,233,260,270],"deep-learning":[21],"tasks,":[22],"where":[23],"inter-layer":[24,315],"pre/post-processing,":[25],"data":[26,29,59,79,106,141,154,158,176,197,312],"alignment":[27],"and":[28,33,53,75,97,105,140,146,222,302,339],"movement":[30,107,142,159,313],"across":[31,108,317],"memory":[32,163],"processing":[34,109,139],"units":[35],"often":[36,126],"dominate":[37],"execution":[39],"time.":[40],"An":[41],"improvement":[42,161,338],"to":[43,101,174,192,257,289],"computation":[46],"requires":[47],"cohesive":[48],"cooperation":[49],"between":[50,143],"accelerator":[52,77,124,147,168,226,280],"CPU":[55,73,103,138,145,185,212,221,250,288,301],"with":[56,78,131,267,294,306,332],"flow":[60],"management.":[61],"Figure":[62],"15.2.1":[63],"shows":[64],"most":[66],"commonly":[67],"used":[68],"heterogeneous":[69,297],"architecture,":[70,208],"containing":[71],"a":[72,83,206,209,219,223,228,247,252,285,295,300,307,328],"core":[74],"an":[76,118,167,268,303],"communication":[80],"managed":[81],"by":[82],"DMA":[84,190],"engine.":[85],"However,":[86],"there":[87],"remain":[88],"challenges":[90],"low":[92],"utilization":[93,259],"PE":[95,258],"cores":[96,110,318],"large":[98],"latency":[99,337],"due":[100],"workload":[104],"[1]\u2013[4].":[111],"As":[112],"shown":[113],"in":[114,117,227],"Fig.":[115],"15.2.1,":[116],"learning":[121],"task,":[122],"is":[125],"utilized":[127],"at":[128],"only":[129],"30-50%":[130],"rest":[133],"time":[135],"waiting":[136],"for":[137,263,314],"cores.":[148],"Some":[149],"prior":[150],"considered":[153],"compression,":[155],"reduction":[156],"or":[160,251],"bandwidth.":[164],"For":[165],"instance,":[166],"coherency":[169],"port":[170],"(ACP)":[171],"was":[172],"designed":[173],"request":[175],"directly":[177],"from":[178],"last":[180],"level":[181],"cache":[182],"instead":[186],"using":[188],"engine":[191],"improve":[193,290],"efficiency":[195,342],"transfer":[198],"[3],":[199],"[5].":[200],"In":[201],"this":[202,234],"work,":[203],"we":[204,323],"propose":[205],"new":[207],"systolic":[210,224,253],"(SNCPU),":[213],"which":[214],"fuses":[215],"operation":[217],"conventional":[220,296],"CNN":[225,254,279],"single":[229],"core.":[230],"The":[231,238],"contributions":[232],"work":[235],"include:":[236],"1)":[237],"proposed":[239],"SNCPU":[240,326],"architecture":[241,298],"can":[242,281,319],"be":[243,282,320],"flexibly":[244],"reconfigured":[245,283],"into":[246,284],"multi-core":[248],"RISC-V":[249,287],"accelerator,":[255],"leading":[256],"over":[261],"95%":[262],"operation;":[265],"2)":[266],"overhead":[269],"less":[271],"than":[272],"10":[273],"<sup":[274,334],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[275,335],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">%</sup>":[276,336],",":[277],"10-core":[286],"throughput":[291],"significantly":[292],"compared":[293],"having":[299],"accelerator;":[304],"3)":[305],"special":[308],"bi-directional":[309],"dataflow,":[310],"expensive":[311],"pre/post-processing":[316],"avoided;":[321],"4)":[322],"demonstrate":[324],"through":[327],"65nm":[329],"test":[330],"chip":[331],"39-to-64":[333],"0.65-to-1.8TOPS/W":[340],"energy":[341],"image-classification":[345],"tasks.":[346]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":9}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}