{"id":"https://openalex.org/W3179227704","doi":"https://doi.org/10.1109/tcad.2021.3096458","title":"CU.POKer: Placing DNNs on WSE With Optimal Kernel Sizing and Efficient Protocol Optimization","display_name":"CU.POKer: Placing DNNs on WSE With Optimal Kernel Sizing and Efficient Protocol Optimization","publication_year":2021,"publication_date":"2021-07-12","ids":{"openalex":"https://openalex.org/W3179227704","doi":"https://doi.org/10.1109/tcad.2021.3096458","mag":"3179227704"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2021.3096458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2021.3096458","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-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/A5003335238","display_name":"Bentian Jiang","orcid":"https://orcid.org/0000-0001-8163-3114"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bentian Jiang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-8163-3114","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101951915","display_name":"Jingsong Chen","orcid":"https://orcid.org/0000-0001-9867-9805"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jingsong Chen","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-9867-9805","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091445235","display_name":"Jinwei Liu","orcid":"https://orcid.org/0000-0001-8161-5004"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Jinwei Liu","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100399703","display_name":"Lixin Liu","orcid":"https://orcid.org/0000-0002-8451-8100"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Lixin Liu","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017118859","display_name":"Fangzhou Wang","orcid":"https://orcid.org/0000-0001-9960-2711"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Fangzhou Wang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-9960-2711","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614072","display_name":"Xiaopeng Zhang","orcid":"https://orcid.org/0000-0002-8423-5776"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaopeng Zhang","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070795253","display_name":"Evangeline F. Y. Young","orcid":"https://orcid.org/0000-0003-0623-1590"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Evangeline F. Y. Young","raw_affiliation_strings":["Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I177725633"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.06492024,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":"41","issue":"6","first_page":"1888","last_page":"1901"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11338","display_name":"Advancements in Photolithography Techniques","score":0.9993000030517578,"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"}},"topics":[{"id":"https://openalex.org/T11338","display_name":"Advancements in Photolithography Techniques","score":0.9993000030517578,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.998199999332428,"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/T11522","display_name":"VLSI and FPGA Design Techniques","score":0.9976999759674072,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7680989503860474},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5536580085754395},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.543618381023407},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.45474880933761597},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4501872956752777},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4392229914665222},{"id":"https://openalex.org/keywords/floorplan","display_name":"Floorplan","score":0.4262542128562927},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4214634597301483},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.4173371195793152},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3301982283592224}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7680989503860474},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5536580085754395},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.543618381023407},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.45474880933761597},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4501872956752777},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4392229914665222},{"id":"https://openalex.org/C130145326","wikidata":"https://www.wikidata.org/wiki/Q1553985","display_name":"Floorplan","level":2,"score":0.4262542128562927},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4214634597301483},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.4173371195793152},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3301982283592224},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcad.2021.3096458","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2021.3096458","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.550000011920929,"id":"https://metadata.un.org/sdg/9"}],"awards":[{"id":"https://openalex.org/G4601850100","display_name":null,"funder_award_id":"CUHK14209320","funder_id":"https://openalex.org/F4320321592","funder_display_name":"Research Grants Council, University Grants Committee"}],"funders":[{"id":"https://openalex.org/F4320321592","display_name":"Research Grants Council, University Grants Committee","ror":"https://ror.org/00djwmt25"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W1901129140","https://openalex.org/W2106366463","https://openalex.org/W2165891825","https://openalex.org/W2194775991","https://openalex.org/W2559581617","https://openalex.org/W2772709170","https://openalex.org/W3012493694","https://openalex.org/W3018195242","https://openalex.org/W3112683606","https://openalex.org/W4247390131","https://openalex.org/W4292779060","https://openalex.org/W6746177919"],"related_works":["https://openalex.org/W2055008360","https://openalex.org/W1500063550","https://openalex.org/W215057456","https://openalex.org/W2135118255","https://openalex.org/W2165891825","https://openalex.org/W2106366463","https://openalex.org/W1535718467","https://openalex.org/W4231092740","https://openalex.org/W3115480774","https://openalex.org/W2983230882"],"abstract_inverted_index":{"The":[0],"tremendous":[1],"growth":[2],"in":[3,62,173],"deep":[4,113],"learning":[5],"(DL)":[6],"applications":[7],"has":[8],"created":[9],"an":[10],"exponential":[11],"demand":[12],"for":[13,111],"computing":[14],"power,":[15],"which":[16],"leads":[17],"to":[18,36,135],"the":[19,64,83,91,137,142,155,164,169],"rise":[20],"of":[21,69,86,157],"AI-specific":[22],"hardware.":[23,72],"Targeted":[24],"toward":[25],"accelerating":[26],"computation-intensive":[27],"DL":[28,94],"applications,":[29],"AI":[30,71],"hardware,":[31],"including":[32],"but":[33,167],"not":[34,162],"limited":[35],"GPGPU,":[37],"TPU,":[38],"ASICs,":[39],"etc.,":[40],"have":[41,58],"been":[42,59],"adopted":[43],"ubiquitously.":[44],"As":[45],"a":[46,78,106,128],"result,":[47],"domain-specific":[48],"CAD":[49],"tools":[50],"play":[51],"more":[52,54],"and":[53,57,66,127],"important":[55],"roles":[56],"deeply":[60],"involved":[61],"both":[63],"design":[65],"compilation":[67],"stages":[68],"modern":[70],"Recently,":[73],"ISPD":[74,149],"2020":[75,150],"contest":[76,151],"introduced":[77],"special":[79],"challenge":[80],"targeting":[81],"at":[82],"physical":[84],"mapping":[85],"neural":[87,114],"network":[88,115],"workloads":[89],"onto":[90],"largest":[92],"commercial":[93],"accelerator,":[95],"CS-1":[96],"wafer-scale":[97],"engine":[98,108],"(WSE).":[99],"In":[100],"this":[101],"article,":[102],"we":[103],"proposed":[104,159],"CU.POKer,":[105],"high-performance":[107],"fully":[109],"customized":[110],"WSE\u2019s":[112],"workload":[116],"placement":[117,130],"challenge.":[118],"A":[119],"provably":[120],"optimal":[121],"placeable":[122],"kernel":[123],"candidate":[124],"searching":[125],"scheme":[126],"data-flow-aware":[129],"tool":[131],"are":[132],"developed":[133],"accordingly":[134],"ensure":[136],"state-of-the-art":[138],"(SOTA)":[139],"quality":[140],"on":[141,148],"real":[143],"industrial":[144],"benchmarks.":[145],"Experimental":[146],"results":[147],"evaluation":[152],"suites":[153],"demonstrated":[154],"superiority":[156],"our":[158],"framework":[160],"over":[161],"only":[163],"SOTA":[165],"placer":[166],"also":[168],"conventional":[170],"heuristics":[171],"used":[172],"general":[174],"floorplanning.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}