{"id":"https://openalex.org/W4388229519","doi":"https://doi.org/10.1145/3628599","title":"Optimal Model Partitioning with Low-Overhead Profiling on the PIM-based Platform for Deep Learning Inference","display_name":"Optimal Model Partitioning with Low-Overhead Profiling on the PIM-based Platform for Deep Learning Inference","publication_year":2023,"publication_date":"2023-11-02","ids":{"openalex":"https://openalex.org/W4388229519","doi":"https://doi.org/10.1145/3628599"},"language":"en","primary_location":{"id":"doi:10.1145/3628599","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3628599","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3628599","source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3628599","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5009921737","display_name":"Seok Young Kim","orcid":"https://orcid.org/0000-0002-6259-9413"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seok Young Kim","raw_affiliation_strings":["Korea University, Korea"],"raw_orcid":"https://orcid.org/0000-0002-6259-9413","affiliations":[{"raw_affiliation_string":"Korea University, Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101853806","display_name":"Jae-Wook Lee","orcid":"https://orcid.org/0009-0007-1179-4730"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaewook Lee","raw_affiliation_strings":["Korea University, Korea"],"raw_orcid":"https://orcid.org/0009-0007-1179-4730","affiliations":[{"raw_affiliation_string":"Korea University, Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078505862","display_name":"Yoonah Paik","orcid":"https://orcid.org/0000-0002-8294-1079"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yoonah Paik","raw_affiliation_strings":["Korea University, Korea"],"raw_orcid":"https://orcid.org/0000-0002-8294-1079","affiliations":[{"raw_affiliation_string":"Korea University, Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100772338","display_name":"Chang Hyun Kim","orcid":"https://orcid.org/0000-0001-6224-7074"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chang Hyun Kim","raw_affiliation_strings":["Korea University, Korea"],"raw_orcid":"https://orcid.org/0000-0001-6224-7074","affiliations":[{"raw_affiliation_string":"Korea University, Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112018351","display_name":"Won Jun Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Won Jun Lee","raw_affiliation_strings":["Korea University, Korea"],"raw_orcid":"https://orcid.org/0000-0001-6555-1741","affiliations":[{"raw_affiliation_string":"Korea University, Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"last","author":{"id":null,"display_name":"Seon Wook Kim","orcid":"https://orcid.org/0000-0001-6161-0871"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seon Wook Kim","raw_affiliation_strings":["Korea University, Korea"],"raw_orcid":"https://orcid.org/0000-0001-6161-0871","affiliations":[{"raw_affiliation_string":"Korea University, Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I197347611"],"apc_list":null,"apc_paid":null,"fwci":0.7952,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69453428,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"29","issue":"2","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9976000189781189,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9976000189781189,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9879000186920166,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.984499990940094,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.9145879149436951},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.740532398223877},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7129164338111877},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4732554256916046},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.46484890580177307},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4420742392539978},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4384036064147949},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3520727753639221},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3322674632072449},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15442153811454773}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9145879149436951},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.740532398223877},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7129164338111877},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4732554256916046},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.46484890580177307},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4420742392539978},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4384036064147949},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3520727753639221},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3322674632072449},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15442153811454773}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3628599","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3628599","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3628599","source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3628599","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3628599","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3628599","source":{"id":"https://openalex.org/S105046310","display_name":"ACM Transactions on Design Automation of Electronic Systems","issn_l":"1084-4309","issn":["1084-4309","1557-7309"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Design Automation of Electronic Systems","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8999999761581421,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G4700831490","display_name":null,"funder_award_id":"2022-","funder_id":"https://openalex.org/F4320335489","funder_display_name":"Institute for Information and Communications Technology Promotion"}],"funders":[{"id":"https://openalex.org/F4320317879","display_name":"SK Hynix","ror":null},{"id":"https://openalex.org/F4320322202","display_name":"IC Design Education Center","ror":"https://ror.org/005v57z85"},{"id":"https://openalex.org/F4320324891","display_name":"Iran Telecommunication Research Center","ror":"https://ror.org/01a3g2z22"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"},{"id":"https://openalex.org/F4320335489","display_name":"Institute for Information and Communications Technology Promotion","ror":"https://ror.org/01g0hqq23"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388229519.pdf","grobid_xml":"https://content.openalex.org/works/W4388229519.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W73629738","https://openalex.org/W1720285298","https://openalex.org/W1805440014","https://openalex.org/W1971391208","https://openalex.org/W1984222112","https://openalex.org/W1993338334","https://openalex.org/W2012429438","https://openalex.org/W2014724071","https://openalex.org/W2023083159","https://openalex.org/W2026898864","https://openalex.org/W2064675550","https://openalex.org/W2122570236","https://openalex.org/W2126255765","https://openalex.org/W2133487610","https://openalex.org/W2150476673","https://openalex.org/W2157427457","https://openalex.org/W2270323267","https://openalex.org/W2295035104","https://openalex.org/W2342906597","https://openalex.org/W2926767350","https://openalex.org/W3100710793","https://openalex.org/W3101708369","https://openalex.org/W3138708228","https://openalex.org/W3139059822","https://openalex.org/W3177372937","https://openalex.org/W3189166979","https://openalex.org/W3191222816"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W2161444195","https://openalex.org/W2589019771","https://openalex.org/W2985540061","https://openalex.org/W2185012154","https://openalex.org/W4252521128","https://openalex.org/W2055243143","https://openalex.org/W4287867321","https://openalex.org/W2911183501","https://openalex.org/W2611230223"],"abstract_inverted_index":{"Recently":[0],"Processing-in-Memory":[1],"(PIM)":[2],"has":[3],"become":[4,57],"a":[5,29,33,79,128],"promising":[6],"solution":[7],"to":[8,68,72,99,118,131,138,157],"achieve":[9,73],"energy-efficient":[10],"computation":[11,17],"in":[12,202,218,240],"data-intensive":[13],"applications":[14],"by":[15,42,113,177],"placing":[16],"near":[18],"or":[19],"inside":[20],"the":[21,39,44,48,70,74,101,115,121,133,141,147,153,159,165,170,179,186,190,203,215,237,242,245,253],"memory.":[22],"In":[23],"most":[24],"Deep":[25,52],"Learning":[26],"(DL)":[27],"frameworks,":[28],"user":[30],"manually":[31,248],"partitions":[32],"model\u2019s":[34],"computational":[35],"graph":[36],"(CG)":[37],"onto":[38],"computing":[40,200],"devices":[41,201],"considering":[43,114],"devices\u2019":[45,116],"capability":[46,117],"and":[47,105,143,182,208,226,252],"data":[49],"transfer.":[50],"The":[51],"Neural":[53],"Network":[54],"(DNN)":[55],"models":[56,184],"increasingly":[58],"complex":[59],"for":[60,96,223,228],"improving":[61],"accuracy;":[62],"thus,":[63],"it":[64],"is":[65],"exceptionally":[66],"challenging":[67],"partition":[69],"execution":[71,162,246],"best":[75],"performance,":[76],"especially":[77],"on":[78,185],"PIM-based":[80],"platform":[81,193],"requiring":[82],"frequent":[83],"offloading":[84],"of":[85,88,146],"large":[86],"amounts":[87],"data.":[89,172],"This":[90],"article":[91],"proposes":[92],"two":[93],"novel":[94],"algorithms":[95],"DL":[97],"inference":[98],"resolve":[100],"challenge:":[102],"low-overhead":[103],"profiling":[104,129,136],"optimal":[106,160],"model":[107,154,233],"partitioning.":[108],"First,":[109],"we":[110,126,151,211],"reconstruct":[111],"CG":[112],"represent":[119],"all":[120,140,214,241],"possible":[122],"scheduling":[123],"paths.":[124],"Second,":[125],"develop":[127],"algorithm":[130,156,235],"find":[132,213],"required":[134],"minimum":[135,161],"paths":[137],"measure":[139],"node":[142,224],"edge":[144,229],"costs":[145,216,225],"reconstructed":[148],"CG.":[149],"Finally,":[150],"devise":[152],"partitioning":[155,234],"get":[158],"time":[163],"using":[164],"dynamic":[166],"programming":[167],"technique":[168],"with":[169,189,194,247],"profiled":[171],"We":[173],"evaluated":[174],"our":[175,232],"work":[176],"executing":[178],"BERT,":[180],"RoBERTa,":[181],"GPT-2":[183],"ARM":[187],"multicores":[188],"PIM-modeled":[191],"FPGA":[192],"various":[195],"sequence":[196],"lengths.":[197],"For":[198],"three":[199,222],"platform,":[204],"i.e.,":[205],"CPU":[206],"serial/parallel":[207],"PIM":[209],"executions,":[210],"could":[212],"only":[217],"four":[219],"profile":[220],"runs,":[221],"one":[227],"costs.":[230],"Also,":[231],"achieved":[236],"highest":[238],"performance":[239],"experiments":[243],"over":[244],"assigned":[249],"device":[250],"priority":[251],"state-of-the-art":[254],"greedy":[255],"approach.":[256]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}