{"id":"https://openalex.org/W4285261840","doi":"https://doi.org/10.1109/lca.2022.3182363","title":"Runtime Support for Accelerating CNN Models on Digital DRAM Processing-in-Memory Hardware","display_name":"Runtime Support for Accelerating CNN Models on Digital DRAM Processing-in-Memory Hardware","publication_year":2022,"publication_date":"2022-06-13","ids":{"openalex":"https://openalex.org/W4285261840","doi":"https://doi.org/10.1109/lca.2022.3182363"},"language":"en","primary_location":{"id":"doi:10.1109/lca.2022.3182363","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2022.3182363","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"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 Computer Architecture Letters","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/A5042560026","display_name":"Yongwon Shin","orcid":"https://orcid.org/0000-0002-0481-172X"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yongwon Shin","raw_affiliation_strings":["Department of Computer Science and Engineering, Graduate School of Artificial Intelligence, Pohang University of Science and Technology, Pohang, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-0481-172X","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Graduate School of Artificial Intelligence, Pohang University of Science and Technology, Pohang, South Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060009407","display_name":"Juseong Park","orcid":"https://orcid.org/0000-0003-0283-5186"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Juseong Park","raw_affiliation_strings":["Department of Computer Science and Engineering, Graduate School of Artificial Intelligence, Pohang University of Science and Technology, Pohang, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-0283-5186","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Graduate School of Artificial Intelligence, Pohang University of Science and Technology, Pohang, South Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062791122","display_name":"Jeongmin Hong","orcid":"https://orcid.org/0000-0002-5492-5346"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jeongmin Hong","raw_affiliation_strings":["Department of Computer Science and Engineering, Graduate School of Artificial Intelligence, Pohang University of Science and Technology, Pohang, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-5492-5346","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Graduate School of Artificial Intelligence, Pohang University of Science and Technology, Pohang, South Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005051912","display_name":"Hyojin Sung","orcid":"https://orcid.org/0000-0002-3036-6180"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyojin Sung","raw_affiliation_strings":["Department of Computer Science and Engineering, Graduate School of Artificial Intelligence, Pohang University of Science and Technology, Pohang, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-3036-6180","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Graduate School of Artificial Intelligence, Pohang University of Science and Technology, Pohang, South Korea","institution_ids":["https://openalex.org/I123900574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I123900574"],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.1635,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.40508038,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"21","issue":"2","first_page":"33","last_page":"36"},"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":0.9998999834060669,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","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"}}],"keywords":[{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8870223164558411},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8734911680221558},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.7248713970184326},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6666235327720642},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6202548742294312},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5900914669036865},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.48574477434158325},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4118838608264923},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3469778895378113},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3414793610572815},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.303219199180603},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.17866754531860352},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16494736075401306}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8870223164558411},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8734911680221558},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.7248713970184326},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6666235327720642},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6202548742294312},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5900914669036865},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.48574477434158325},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4118838608264923},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3469778895378113},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3414793610572815},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.303219199180603},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.17866754531860352},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16494736075401306}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lca.2022.3182363","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lca.2022.3182363","pdf_url":null,"source":{"id":"https://openalex.org/S17643076","display_name":"IEEE Computer Architecture Letters","issn_l":"1556-6056","issn":["1556-6056","1556-6064","2473-2575"],"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 Computer Architecture Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6800000071525574,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G2702555917","display_name":null,"funder_award_id":"2019-0-01906","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G5711625785","display_name":null,"funder_award_id":"2021-0-00871","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"},{"id":"https://openalex.org/G8817798873","display_name":null,"funder_award_id":"2021-0-00310","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2034861439","https://openalex.org/W2064675550","https://openalex.org/W2094332102","https://openalex.org/W2112547256","https://openalex.org/W2194775991","https://openalex.org/W2953212265","https://openalex.org/W2963163009","https://openalex.org/W2963918968","https://openalex.org/W3043023836","https://openalex.org/W3044083334","https://openalex.org/W3100710793","https://openalex.org/W3102510044","https://openalex.org/W3189166979","https://openalex.org/W4221001402","https://openalex.org/W6631660994","https://openalex.org/W6755207826","https://openalex.org/W6762718338","https://openalex.org/W6763737044"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2891987081","https://openalex.org/W4376647684","https://openalex.org/W2532502681","https://openalex.org/W4221139464"],"abstract_inverted_index":{"Processing-in-memory":[0],"(PIM)":[1],"provides":[2],"promising":[3],"solutions":[4],"to":[5,19,73,122,173],"the":[6,48,69,83],"main":[7,66],"memory":[8,17,89],"bottleneck":[9],"by":[10],"placing":[11],"computational":[12],"logic":[13,34],"in":[14,47,100],"or":[15,151],"near":[16],"devices":[18],"reduce":[20,123],"data":[21],"movement":[22],"overheads.":[23],"Recent":[24],"work":[25],"explored":[26],"how":[27],"commercial":[28,70],"DRAM":[29],"can":[30,137],"feature":[31],"digital":[32],"PIM":[33,141],"while":[35],"meeting":[36],"fab-level":[37],"energy":[38],"and":[39,42,85,97,114,147,163,165],"area":[40,84],"constraints,":[41],"showed":[43],"a":[44,110],"significant":[45],"speedup":[46,157,178],"inference":[49],"time":[50],"of":[51,112,118],"data-intensive":[52],"deep":[53],"learning":[54],"models.":[55],"However,":[56],"convolutional":[57],"neural":[58],"network":[59],"(CNN)":[60],"models":[61,106,186],"were":[62],"not":[63],"considered":[64],"as":[65],"targets":[67],"for":[68,140,179,183],"DRAM-PIM":[71,92,164],"due":[72],"their":[74],"compute-intensive":[75,120],"convolution":[76,136],"layers.":[77],"Moreover,":[78],"recent":[79],"studies":[80],"revealed":[81],"that":[82,134],"power":[86],"constraints":[87],"on":[88,161,176],"die":[90],"prevent":[91],"from":[93],"competing":[94],"with":[95,143,158],"GPUs":[96],"specialized":[98],"accelerators":[99],"accelerating":[101],"them.":[102],"Recently,":[103],"mobile":[104,184],"CNN":[105,185],"have":[107],"increasingly":[108],"adopted":[109],"composition":[111],"depthwise":[113],"pointwise":[115],"convolutions":[116,121,182],"instead":[117],"such":[119],"computation":[124],"cost":[125],"without":[126,148],"accuracy":[127],"drop.":[128],"In":[129],"this":[130],"paper,":[131],"we":[132],"show":[133],"1x1":[135,181],"be":[138],"offloaded":[139],"acceleration":[142],"integrated":[144],"runtime":[145],"support":[146],"any":[149],"hardware":[150],"algorithm":[152],"changes.":[153],"We":[154],"provide":[155],"further":[156],"parallel":[159],"execution":[160],"GPU":[162],"code":[166],"generation":[167],"optimizations.":[168],"Our":[169],"solution":[170],"achieves":[171],"up":[172],"35.2%":[174],"(31.6%":[175],"average)":[177],"all":[180],"against":[187],"GPU.":[188]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}