{"id":"https://openalex.org/W2909419460","doi":"https://doi.org/10.1145/3287624.3287638","title":"Addressing the issue of processing element under-utilization in general-purpose systolic deep learning accelerators","display_name":"Addressing the issue of processing element under-utilization in general-purpose systolic deep learning accelerators","publication_year":2019,"publication_date":"2019-01-18","ids":{"openalex":"https://openalex.org/W2909419460","doi":"https://doi.org/10.1145/3287624.3287638","mag":"2909419460"},"language":"en","primary_location":{"id":"doi:10.1145/3287624.3287638","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3287624.3287638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th Asia and South Pacific Design Automation Conference","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/A5068283310","display_name":"Bosheng Liu","orcid":"https://orcid.org/0000-0001-7123-7425"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bosheng Liu","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Xiaoming Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoming Chen","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100346965","display_name":"Ying Wang","orcid":"https://orcid.org/0000-0001-5172-4736"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ying Wang","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016864694","display_name":"Yinhe Han","orcid":"https://orcid.org/0000-0003-0904-6681"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yinhe Han","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100352041","display_name":"Jiajun Li","orcid":"https://orcid.org/0000-0002-7208-9345"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiajun Li","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044810210","display_name":"Haobo Xu","orcid":"https://orcid.org/0000-0002-0243-6516"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haobo Xu","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023380073","display_name":"Xiaowei Li","orcid":"https://orcid.org/0000-0002-0874-814X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaowei Li","raw_affiliation_strings":["University of Chinese Academy of Sciences"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"733","last_page":"738"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9965999722480774,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.8302991390228271},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7661263942718506},{"id":"https://openalex.org/keywords/systolic-array","display_name":"Systolic array","score":0.6949823498725891},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.5557317137718201},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5307683348655701},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5036599040031433},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4961753785610199},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4682019352912903},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45998117327690125},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.44326597452163696},{"id":"https://openalex.org/keywords/energy","display_name":"Energy (signal processing)","score":0.442592978477478},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.4401402473449707},{"id":"https://openalex.org/keywords/range","display_name":"Range (aeronautics)","score":0.4114602506160736},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3911231458187103},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3607058525085449},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3311442732810974},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.21798905730247498},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.11400812864303589}],"concepts":[{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.8302991390228271},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7661263942718506},{"id":"https://openalex.org/C150741067","wikidata":"https://www.wikidata.org/wiki/Q2377218","display_name":"Systolic array","level":3,"score":0.6949823498725891},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.5557317137718201},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5307683348655701},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5036599040031433},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4961753785610199},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4682019352912903},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45998117327690125},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.44326597452163696},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.442592978477478},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.4401402473449707},{"id":"https://openalex.org/C204323151","wikidata":"https://www.wikidata.org/wiki/Q905424","display_name":"Range (aeronautics)","level":2,"score":0.4114602506160736},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3911231458187103},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3607058525085449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3311442732810974},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.21798905730247498},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11400812864303589},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C14580979","wikidata":"https://www.wikidata.org/wiki/Q876049","display_name":"Very-large-scale integration","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3287624.3287638","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3287624.3287638","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th Asia and South Pacific Design Automation Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8899999856948853,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G5612089305","display_name":null,"funder_award_id":"Z171100000117019,Z181100008918006","funder_id":"https://openalex.org/F4320325902","funder_display_name":"Beijing Municipal Science and Technology Commission"},{"id":"https://openalex.org/G8074148872","display_name":null,"funder_award_id":"61804155, 61522406,61834006, 61532017, 61521092","funder_id":"https://openalex.org/F4320335595","funder_display_name":"National Natural Science Foundation of China-Yunnan Joint Fund"}],"funders":[{"id":"https://openalex.org/F4320325902","display_name":"Beijing Municipal Science and Technology Commission","ror":null},{"id":"https://openalex.org/F4320335595","display_name":"National Natural Science Foundation of China-Yunnan Joint Fund","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2062164080","https://openalex.org/W2067523571","https://openalex.org/W2095705004","https://openalex.org/W2097117768","https://openalex.org/W2136922672","https://openalex.org/W2152839228","https://openalex.org/W2160428323","https://openalex.org/W2163605009","https://openalex.org/W2170240176","https://openalex.org/W2194775991","https://openalex.org/W2279098554","https://openalex.org/W2420699360","https://openalex.org/W2442974303","https://openalex.org/W2605347906","https://openalex.org/W2606722458","https://openalex.org/W2618530766","https://openalex.org/W2625954420","https://openalex.org/W2906043559","https://openalex.org/W2963012544","https://openalex.org/W2963893493","https://openalex.org/W4394670654","https://openalex.org/W6674914833","https://openalex.org/W6687483927"],"related_works":["https://openalex.org/W2293118914","https://openalex.org/W2998381397","https://openalex.org/W4236419692","https://openalex.org/W2171015181","https://openalex.org/W3167919718","https://openalex.org/W4251718783","https://openalex.org/W4239447582","https://openalex.org/W2357124094","https://openalex.org/W3013241373","https://openalex.org/W4283703276"],"abstract_inverted_index":{"As":[0],"an":[1],"energy-efficient":[2],"hardware":[3,71,142],"solution":[4],"for":[5,154],"deep":[6],"neural":[7],"network":[8],"(DNN)":[9],"inference,":[10],"systolic":[11,31,56,101],"accelerators":[12,33],"are":[13,34,73],"particularly":[14],"popular":[15],"in":[16,54],"both":[17],"embedded":[18],"and":[19,27,82,109,118,127,144,151,165],"datacenter":[20],"computing":[21],"scenarios.":[22],"Despite":[23],"their":[24],"excellent":[25],"performance":[26,81,164],"energy":[28,83,166],"efficiency,":[29],"however,":[30],"DNN":[32,44,61,102,137,159],"naturally":[35],"facing":[36],"a":[37,55,99,105,155],"resource":[38,89],"under-utilization":[39],"problem":[40],"-":[41],"not":[42,74],"all":[43],"models":[45,62,138,160],"can":[46],"well":[47],"match":[48,135],"the":[49,78,132,140],"fixed":[50,141],"processing":[51],"elements":[52],"(PEs)":[53],"array":[57],"implementation,":[58],"because":[59,87],"typical":[60],"vary":[63],"significantly":[64],"from":[65],"applications":[66],"to":[67,76,134,139,161],"applications.":[68],"Consequently,":[69],"state-of-the-art":[70],"solutions":[72],"expected":[75],"deliver":[77],"nominal":[79],"(peak)":[80],"efficiency":[84],"as":[85],"claimed":[86],"of":[88,116,158],"under-utilization.":[90],"To":[91],"deal":[92],"with":[93,104],"this":[94,96],"dilemma,":[95],"study":[97],"proposes":[98],"novel":[100],"accelerator":[103,130],"flexible":[106],"computation":[107],"mapping":[108],"dataflow":[110],"scheme.":[111],"By":[112],"providing":[113],"three":[114],"types":[115],"parallelism":[117],"dynamically":[119],"switching":[120],"among":[121],"them:":[122],"channel-direction":[123],"mapping,":[124,126],"planar":[125],"hybrid,":[128],"our":[129],"offers":[131],"adaptability":[133],"various":[136],"resources,":[143],"thus,":[145],"enables":[146],"flexibly":[147],"exploiting":[148],"PE":[149],"provision":[150],"data":[152],"reuse":[153],"wide":[156],"range":[157],"achieve":[162],"optimal":[163],"efficiency.":[167]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}