{"id":"https://openalex.org/W3081748035","doi":"https://doi.org/10.1109/tcad.2020.3021336","title":"DLUX: A LUT-Based Near-Bank Accelerator for Data Center Deep Learning Training Workloads","display_name":"DLUX: A LUT-Based Near-Bank Accelerator for Data Center Deep Learning Training Workloads","publication_year":2020,"publication_date":"2020-09-02","ids":{"openalex":"https://openalex.org/W3081748035","doi":"https://doi.org/10.1109/tcad.2020.3021336","mag":"3081748035"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2020.3021336","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2020.3021336","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/A5078298822","display_name":"Peng Gu","orcid":"https://orcid.org/0000-0002-2663-4568"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peng Gu","raw_affiliation_strings":["University of California at Santa Barbara, Santa Barbara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2663-4568","affiliations":[{"raw_affiliation_string":"University of California at Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047767267","display_name":"Xinfeng Xie","orcid":"https://orcid.org/0000-0001-7285-6682"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xinfeng Xie","raw_affiliation_strings":["University of California at Santa Barbara, Santa Barbara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0001-7285-6682","affiliations":[{"raw_affiliation_string":"University of California at Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102837743","display_name":"Shuangchen Li","orcid":"https://orcid.org/0009-0003-6986-0463"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuangchen Li","raw_affiliation_strings":["University of California at Santa Barbara, Santa Barbara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of California at Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068606980","display_name":"Dimin Niu","orcid":"https://orcid.org/0000-0001-8440-3875"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimin Niu","raw_affiliation_strings":["Alibaba DAMO Academy, Sunnyvale, CA, USA","Samsung Semiconductor, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"Samsung Semiconductor, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046896624","display_name":"Hongzhong Zheng","orcid":"https://orcid.org/0000-0001-7696-9799"},"institutions":[{"id":"https://openalex.org/I4210095624","display_name":"Alibaba Group (United States)","ror":"https://ror.org/00rn0m335","country_code":"US","type":"company","lineage":["https://openalex.org/I4210095624","https://openalex.org/I45928872"]},{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongzhong Zheng","raw_affiliation_strings":["Alibaba DAMO Academy, Sunnyvale, CA, USA","Samsung Semiconductor, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba DAMO Academy, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210095624"]},{"raw_affiliation_string":"Samsung Semiconductor, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032065701","display_name":"Krishna T. Malladi","orcid":"https://orcid.org/0000-0002-3789-2255"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Krishna T. Malladi","raw_affiliation_strings":["Samsung Semiconductor, San Jose, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung Semiconductor, San Jose, CA, USA","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100385336","display_name":"Yuan Xie","orcid":"https://orcid.org/0000-0003-2093-1788"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Xie","raw_affiliation_strings":["University of California at Santa Barbara, Santa Barbara, CA, USA"],"raw_orcid":"https://orcid.org/0000-0003-2093-1788","affiliations":[{"raw_affiliation_string":"University of California at Santa Barbara, Santa Barbara, CA, USA","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.817,"has_fulltext":false,"cited_by_count":28,"citation_normalized_percentile":{"value":0.85536943,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"40","issue":"8","first_page":"1586","last_page":"1599"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9998999834060669,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9998999834060669,"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":0.9998000264167786,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9995999932289124,"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":0.8563175201416016},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5419039130210876},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4978799819946289},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.43613603711128235},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.41260457038879395},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.39213496446609497},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.34649208188056946}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8563175201416016},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5419039130210876},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4978799819946289},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.43613603711128235},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.41260457038879395},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.39213496446609497},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.34649208188056946},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tcad.2020.3021336","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2020.3021336","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"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-132939","is_oa":false,"landing_page_url":"http://www.scopus.com/record/display.url?eid=2-s2.0-85090440162&origin=inward","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8999999761581421,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G1003572525","display_name":"II-New: RICARDO:  Research Infrastructure for Circuit and Architecture Design with Emerging Technologies","funder_award_id":"1730309","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3069263526","display_name":"SHF:SMALL: MECAR: Memory-Centric Architecture to Bridge the Gap Between Computing and Memory","funder_award_id":"1719160","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7396753823","display_name":"SPX: Collaborative Research: Ula! - An Integrated Deep Neural Network (DNN) Acceleration Framework with Enhanced Unsupervised Learning Capability","funder_award_id":"1725447","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"},{"id":"https://openalex.org/F4320332195","display_name":"Samsung","ror":"https://ror.org/04w3jy968"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":68,"referenced_works":["https://openalex.org/W1486649854","https://openalex.org/W1606129576","https://openalex.org/W1667652561","https://openalex.org/W1686810756","https://openalex.org/W1922655562","https://openalex.org/W1982685588","https://openalex.org/W1999085092","https://openalex.org/W2002555321","https://openalex.org/W2030898836","https://openalex.org/W2034861439","https://openalex.org/W2048266589","https://openalex.org/W2092324191","https://openalex.org/W2112980698","https://openalex.org/W2129991978","https://openalex.org/W2270723299","https://openalex.org/W2341349540","https://openalex.org/W2402144811","https://openalex.org/W2442974303","https://openalex.org/W2466675884","https://openalex.org/W2474451066","https://openalex.org/W2508602506","https://openalex.org/W2515080096","https://openalex.org/W2516141709","https://openalex.org/W2518511512","https://openalex.org/W2520782513","https://openalex.org/W2562773490","https://openalex.org/W2582737986","https://openalex.org/W2605347906","https://openalex.org/W2605350416","https://openalex.org/W2606722458","https://openalex.org/W2613989746","https://openalex.org/W2626991402","https://openalex.org/W2657126969","https://openalex.org/W2761132374","https://openalex.org/W2765234579","https://openalex.org/W2790501674","https://openalex.org/W2794670651","https://openalex.org/W2796649226","https://openalex.org/W2809533219","https://openalex.org/W2884360532","https://openalex.org/W2888727064","https://openalex.org/W2896090304","https://openalex.org/W2897709121","https://openalex.org/W2904295992","https://openalex.org/W2911283150","https://openalex.org/W2939504873","https://openalex.org/W2949989598","https://openalex.org/W2953384591","https://openalex.org/W2962835968","https://openalex.org/W2963149687","https://openalex.org/W2963403868","https://openalex.org/W2963566954","https://openalex.org/W2964330541","https://openalex.org/W2985229340","https://openalex.org/W3042598257","https://openalex.org/W3099365437","https://openalex.org/W3105314253","https://openalex.org/W3105753409","https://openalex.org/W3146763006","https://openalex.org/W4242577057","https://openalex.org/W4302296459","https://openalex.org/W4385245566","https://openalex.org/W6629028937","https://openalex.org/W6682164510","https://openalex.org/W6693960836","https://openalex.org/W6704329389","https://openalex.org/W6713134421","https://openalex.org/W6739901393"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"The":[0],"frequent":[1],"data":[2,24,163,192,207,231],"movement":[3,208],"between":[4],"the":[5,8,33,52,57,66,83,88,91,117,121,126,158,166,170,175,187,195,199,220,229,236,254],"processor":[6],"and":[7,87,109,160,183,198,205,234,274],"memory":[9,30,54,72,92],"has":[10],"become":[11],"a":[12,40,75,95,106,146,152,211,259],"severe":[13],"performance":[14,108],"bottleneck":[15],"for":[16,47,113],"deep":[17],"neural":[18],"network":[19],"(DNN)":[20],"training":[21,49,115,180],"workloads":[22],"in":[23,56,90,194],"centers.":[25],"To":[26,61,99],"solve":[27],"this":[28,63],"off-chip":[29],"access":[31],"challenge,":[32],"3-D":[34],"stacking":[35],"processing-in-memory":[36],"(3D-PIM)":[37],"architecture":[38],"provides":[39],"viable":[41],"solution.":[42],"However,":[43],"existing":[44],"3D-PIM":[45,111,212],"designs":[46],"DNN":[48,67,114,179],"suffer":[50],"from":[51],"limited":[53],"bandwidth":[55],"base":[58],"logic":[59,69],"die.":[60],"overcome":[62],"obstacle,":[64],"integrating":[65],"related":[68],"near":[70],"each":[71],"bank":[73],"becomes":[74],"promising":[76],"yet":[77],"challenging":[78],"solution,":[79],"since":[80],"naively":[81],"implementing":[82],"floating-point":[84],"(FP)":[85],"unit":[86],"cache":[89],"die":[93],"incurs":[94],"large":[96],"area":[97,131,249],"overhead.":[98],"address":[100],"these":[101],"problems,":[102],"we":[103,142,173],"propose":[104,143],"DLUX,":[105],"high":[107,203],"energy-efficient":[110],"accelerator":[112],"using":[116],"near-bank":[118],"architecture.":[119],"From":[120,169],"hardware":[122],"perspective,":[123],"to":[124,144,156,190,227],"support":[125],"FP":[127],"multiplier":[128,248],"with":[129,151,258],"low":[130],"overhead,":[132],"an":[133],"in-DRAM":[134],"lookup":[135],"table":[136],"(LUT)":[137],"mechanism":[138],"is":[139,217],"invented.":[140],"Then,":[141],"use":[145],"small":[147],"scratchpad":[148,200],"buffer":[149,197],"together":[150],"lightweight":[153],"transformation":[154],"engine":[155],"exploit":[157],"locality":[159],"enable":[161],"flexible":[162],"layout":[164,232,238],"without":[165],"expensive":[167],"cache.":[168],"software":[171],"aspect,":[172],"split":[174],"mapping/scheduling":[176],"tasks":[177],"during":[178],"into":[181],"intralayer":[182,188],"interlayer":[184,221],"phases.":[185],"During":[186,219],"phase,":[189,222],"maximize":[191],"reuse":[193],"LUT":[196],"buffer,":[201],"achieve":[202],"concurrency,":[204],"reduce":[206,246],"among":[209],"banks,":[210],"customized":[213],"loop":[214],"tiling":[215],"technique":[216],"adopted.":[218],"efficient":[223],"techniques":[224],"are":[225],"invented":[226],"ensure":[228],"input-output":[230],"consistency":[233],"realize":[235],"forward-backward":[237],"transposition.":[239],"Experiment":[240],"results":[241],"show":[242,265],"that":[243,266],"DLUX":[244,267],"can":[245,268],"FP32":[247],"overhead":[250],"by":[251],"60%":[252],"against":[253],"direct":[255],"implementation.":[256],"Compared":[257],"Tesla":[260],"V100":[261],"GPU,":[262],"end-to-end":[263],"evaluations":[264],"provide":[269],"on":[270],"average":[271],"6.3\u00d7":[272],"speedup":[273],"42\u00d7":[275],"energy":[276],"efficiency":[277],"improvement.":[278]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}