{"id":"https://openalex.org/W4286371336","doi":"https://doi.org/10.1109/access.2022.3192618","title":"On-the-Fly Lowering Engine: Offloading Data Layout Conversion for Convolutional Neural Networks","display_name":"On-the-Fly Lowering Engine: Offloading Data Layout Conversion for Convolutional Neural Networks","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4286371336","doi":"https://doi.org/10.1109/access.2022.3192618"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3192618","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3192618","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09833499.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09833499.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006712350","display_name":"Mingu Kang","orcid":"https://orcid.org/0000-0001-8104-5136"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Mingu Kang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon-si, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon-si, South Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009621669","display_name":"Sangmin Hyun","orcid":null},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sangmin Hyun","raw_affiliation_strings":["Department of Artificial Intelligence, Sungkyunkwan University, Suwon-si, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Sungkyunkwan University, Suwon-si, South Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084741187","display_name":"Tae Hee Han","orcid":"https://orcid.org/0000-0001-8508-7536"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tae Hee Han","raw_affiliation_strings":["Department of Semiconductor Systems Engineering, Sungkyunkwan University, Suwon-si, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Semiconductor Systems Engineering, Sungkyunkwan University, Suwon-si, South Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084281731","display_name":"Jungrae Kim","orcid":"https://orcid.org/0000-0003-1587-0677"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jungrae Kim","raw_affiliation_strings":["Department of Semiconductor Systems Engineering, Sungkyunkwan University, Suwon-si, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Semiconductor Systems Engineering, Sungkyunkwan University, Suwon-si, South Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5062176509","display_name":"Seokin Hong","orcid":"https://orcid.org/0000-0001-7842-125X"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seokin Hong","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon-si, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon-si, South Korea","institution_ids":["https://openalex.org/I848706"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5006712350"],"corresponding_institution_ids":["https://openalex.org/I848706"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.3058,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.54043006,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"10","issue":null,"first_page":"79730","last_page":"79746"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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":0.9958000183105469,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.875893235206604},{"id":"https://openalex.org/keywords/memory-footprint","display_name":"Memory footprint","score":0.7416887879371643},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.726798415184021},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6710385084152222},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5995932221412659},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5992780923843384},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4849705696105957},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.47146302461624146},{"id":"https://openalex.org/keywords/on-the-fly","display_name":"On the fly","score":0.4626973271369934},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4568099081516266},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.42135465145111084},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3893631100654602},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3713730573654175},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.22550803422927856},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.22346097230911255},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1882346272468567},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.12825936079025269},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.07257801294326782}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.875893235206604},{"id":"https://openalex.org/C74912251","wikidata":"https://www.wikidata.org/wiki/Q6815727","display_name":"Memory footprint","level":2,"score":0.7416887879371643},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.726798415184021},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6710385084152222},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5995932221412659},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5992780923843384},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4849705696105957},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.47146302461624146},{"id":"https://openalex.org/C2781020372","wikidata":"https://www.wikidata.org/wiki/Q533093","display_name":"On the fly","level":2,"score":0.4626973271369934},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4568099081516266},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.42135465145111084},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3893631100654602},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3713730573654175},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.22550803422927856},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.22346097230911255},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1882346272468567},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.12825936079025269},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.07257801294326782},{"id":"https://openalex.org/C84114770","wikidata":"https://www.wikidata.org/wiki/Q46344","display_name":"Quantum","level":2,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2022.3192618","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3192618","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09833499.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:c6819212e95b42548aceacaa7c72d720","is_oa":true,"landing_page_url":"https://doaj.org/article/c6819212e95b42548aceacaa7c72d720","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 10, Pp 79730-79746 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3192618","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3192618","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09833499.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4699999988079071,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1465815701","display_name":null,"funder_award_id":"20011074","funder_id":"https://openalex.org/F4320321681","funder_display_name":"Ministry of Trade, Industry and Energy"},{"id":"https://openalex.org/G1975815571","display_name":null,"funder_award_id":"020R1C1C1011419","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G342704958","display_name":null,"funder_award_id":"funded","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G3942910960","display_name":null,"funder_award_id":"(NRF) grant","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G4545665711","display_name":null,"funder_award_id":"2020M3H2A1076786","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G5734796203","display_name":null,"funder_award_id":"2020M3H","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G704248026","display_name":null,"funder_award_id":"2020R1C1C1011419","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G992484961","display_name":null,"funder_award_id":"Korea","funder_id":"https://openalex.org/F4320321681","funder_display_name":"Ministry of Trade, Industry and Energy"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320321378","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20"},{"id":"https://openalex.org/F4320321681","display_name":"Ministry of Trade, Industry and Energy","ror":"https://ror.org/008nkqk13"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"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":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4286371336.pdf","grobid_xml":"https://content.openalex.org/works/W4286371336.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W182691100","https://openalex.org/W1884620995","https://openalex.org/W1903029394","https://openalex.org/W1951742130","https://openalex.org/W1990315422","https://openalex.org/W2048266589","https://openalex.org/W2072730350","https://openalex.org/W2094756095","https://openalex.org/W2097117768","https://openalex.org/W2108598243","https://openalex.org/W2154001575","https://openalex.org/W2172654076","https://openalex.org/W2271177914","https://openalex.org/W2276486856","https://openalex.org/W2289252105","https://openalex.org/W2605739168","https://openalex.org/W2736230459","https://openalex.org/W2794952988","https://openalex.org/W2951894856","https://openalex.org/W2979545880","https://openalex.org/W3010639757","https://openalex.org/W3016832937","https://openalex.org/W3042416028","https://openalex.org/W3102337469","https://openalex.org/W3131607724","https://openalex.org/W3184382748","https://openalex.org/W3205727737","https://openalex.org/W4237812669","https://openalex.org/W4244254628","https://openalex.org/W4288079690","https://openalex.org/W4295312788","https://openalex.org/W6620707391","https://openalex.org/W6637151318","https://openalex.org/W6637373629","https://openalex.org/W6640442106","https://openalex.org/W6687483927","https://openalex.org/W6713134421","https://openalex.org/W6740373327","https://openalex.org/W6744651773","https://openalex.org/W6752390237","https://openalex.org/W6753585227","https://openalex.org/W6754777574","https://openalex.org/W6757703747","https://openalex.org/W6763412433","https://openalex.org/W6765129128"],"related_works":["https://openalex.org/W4221139464","https://openalex.org/W4289827464","https://openalex.org/W2125264433","https://openalex.org/W4237401226","https://openalex.org/W2038054897","https://openalex.org/W4236777984","https://openalex.org/W2112457107","https://openalex.org/W2159716314","https://openalex.org/W2244179743","https://openalex.org/W2293728877"],"abstract_inverted_index":{"Many":[0],"deep":[1],"learning":[2],"frameworks":[3],"utilize":[4],"GEneral":[5],"Matrix":[6],"Multiplication":[7],"(GEMM)-based":[8],"convolution":[9,15,18],"to":[10,49,57,93,115,134,143],"accelerate":[11],"CNN":[12,168],"execution.":[13],"GEMM-based":[14,64],"provides":[16],"faster":[17],"yet":[19],"requires":[20],"a":[21,40,81],"data":[22],"conversion":[23],"process":[24],"called":[25,44],"lowering":[26,52,60,108,114],"(i.e.,":[27],"im2col),":[28],"which":[29],"incurs":[30],"significant":[31],"memory":[32,95,127,139],"overhead":[33],"and":[34,97,110,136],"diminishes":[35],"performance.":[36],"This":[37],"paper":[38],"proposes":[39],"novel":[41],"hardware":[42,82,102],"mechanism,":[43],"<i>On-the-fly":[45],"Lowering":[46],"Engine</i>":[47],"(<i>OLE</i>),":[48],"eliminate":[50],"the":[51,59,63,68,77,89,101,117,137,149],"overheads.":[53],"Our":[54,120],"goal":[55],"is":[56,71],"offload":[58],"overheads":[61],"from":[62,88],"convolution.":[65],"With":[66],"OLE,":[67],"lowered":[69,85],"matrix":[70,86,92],"neither":[72],"pre-calculated":[73],"nor":[74],"stored":[75],"in":[76,160],"main":[78],"memory.":[79],"Instead,":[80],"engine":[83],"generates":[84],"on-the-fly":[87],"original":[90],"input":[91],"reduce":[94,126,148],"footprint":[96,128,140],"bandwidth":[98],"requirements.":[99],"Furthermore,":[100],"offloading":[103],"eliminates":[104],"CPU":[105],"cycles":[106],"for":[107,166],"operation":[109],"overlaps":[111],"computation":[112],"with":[113],"hide":[116],"performance":[118],"overhead.":[119],"evaluation":[121],"shows":[122],"that":[123],"OLE":[124,146],"can":[125,147],"of":[129,152,164],"convolutional":[130,153],"layer":[131],"inputs":[132],"down":[133],"1/12.5&#x00D7;":[135],"overall":[138],"by":[141,155],"up":[142],"33.5%.":[144],"Moreover,":[145],"execution":[150],"time":[151],"layers":[154],"57.7%":[156],"on":[157],"average,":[158],"resulting":[159],"an":[161],"average":[162],"speedup":[163],"2.3&#x00D7;":[165],"representative":[167],"models.":[169]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1}],"updated_date":"2026-03-13T16:22:10.518609","created_date":"2025-10-10T00:00:00"}