{"id":"https://openalex.org/W4402742281","doi":"https://doi.org/10.1109/access.2024.3465789","title":"Non-Invasive, Memory Access-Triggered Near-Data Processing for DNN Training Acceleration on GPUs","display_name":"Non-Invasive, Memory Access-Triggered Near-Data Processing for DNN Training Acceleration on GPUs","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4402742281","doi":"https://doi.org/10.1109/access.2024.3465789"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3465789","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2024.3465789","pdf_url":null,"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":null,"license_id":null,"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":"http://dx.doi.org/10.1109/access.2024.3465789","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5074288663","display_name":"Hyungkyu Ham","orcid":"https://orcid.org/0000-0002-4989-2834"},"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":true,"raw_author_name":"Hyungkyu Ham","raw_affiliation_strings":["Department of Computer Science and Engineering, POSTECH, Pohang, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, POSTECH, Pohang, South Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057504898","display_name":"Hyunuk Cho","orcid":"https://orcid.org/0000-0002-1554-1884"},"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":"Hyunuk Cho","raw_affiliation_strings":["Department of Computer Science and Engineering, POSTECH, Pohang, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, POSTECH, Pohang, South Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100340264","display_name":"Minjae Kim","orcid":"https://orcid.org/0000-0002-6369-245X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Minjae Kim","raw_affiliation_strings":["Department of Computer Science and Engineering, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Seoul National University, Seoul, South Korea","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023909110","display_name":"Jueon Park","orcid":"https://orcid.org/0000-0003-4824-0698"},"institutions":[{"id":"https://openalex.org/I4210156097","display_name":"Rebellion (United Kingdom)","ror":"https://ror.org/04ppn0b98","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210156097"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jueon Park","raw_affiliation_strings":["Rebellions Inc., Seongnam, South Korea","Rebellions Inc, Seongnam, South Korea"],"affiliations":[{"raw_affiliation_string":"Rebellions Inc., Seongnam, South Korea","institution_ids":["https://openalex.org/I4210156097"]},{"raw_affiliation_string":"Rebellions Inc, Seongnam, South Korea","institution_ids":[]}]},{"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, POSTECH, Pohang, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, POSTECH, Pohang, South Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005051912","display_name":"Hyojin Sung","orcid":"https://orcid.org/0000-0002-3036-6180"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyojin Sung","raw_affiliation_strings":["Graduate School of Data Science, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Graduate School of Data Science, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064884832","display_name":"Eunhyeok Park","orcid":"https://orcid.org/0000-0002-7331-9819"},"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":"Eunhyeok Park","raw_affiliation_strings":["Department of Computer Science and Engineering, POSTECH, Pohang, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, POSTECH, Pohang, South Korea","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039338759","display_name":"Euicheol Lim","orcid":"https://orcid.org/0000-0002-8910-533X"},"institutions":[{"id":"https://openalex.org/I134353371","display_name":"SK Group (South Korea)","ror":"https://ror.org/03696td91","country_code":"KR","type":"company","lineage":["https://openalex.org/I134353371"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Euicheol Lim","raw_affiliation_strings":["SK Hynix, Incheon, South Korea","SK hynix, Icheon, South Korea"],"affiliations":[{"raw_affiliation_string":"SK Hynix, Incheon, South Korea","institution_ids":["https://openalex.org/I134353371"]},{"raw_affiliation_string":"SK hynix, Icheon, South Korea","institution_ids":["https://openalex.org/I134353371"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100334897","display_name":"Gwangsun Kim","orcid":"https://orcid.org/0000-0001-5749-5794"},"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":"Gwangsun Kim","raw_affiliation_strings":["Department of Computer Science and Engineering, POSTECH, Pohang, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, POSTECH, Pohang, South Korea","institution_ids":["https://openalex.org/I123900574"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":9,"corresponding_author_ids":["https://openalex.org/A5074288663"],"corresponding_institution_ids":["https://openalex.org/I123900574"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.6569,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.70006158,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"12","issue":null,"first_page":"142651","last_page":"142667"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13382","display_name":"Robotics and Automated Systems","score":0.8902000188827515,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T13382","display_name":"Robotics and Automated Systems","score":0.8902000188827515,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T10320","display_name":"Neural Networks and Applications","score":0.826200008392334,"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"}},{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.763700008392334,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7853662967681885},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.7684348225593567},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.6027070879936218},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5784839987754822},{"id":"https://openalex.org/keywords/random-access-memory","display_name":"Random access memory","score":0.48140406608581543},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.37342342734336853},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3260444402694702},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.20804914832115173}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7853662967681885},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.7684348225593567},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.6027070879936218},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5784839987754822},{"id":"https://openalex.org/C2994168587","wikidata":"https://www.wikidata.org/wiki/Q5295","display_name":"Random access memory","level":2,"score":0.48140406608581543},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.37342342734336853},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3260444402694702},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.20804914832115173},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3465789","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2024.3465789","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:5e0733ab887241b48181918dc53d2a04","is_oa":true,"landing_page_url":"https://doaj.org/article/5e0733ab887241b48181918dc53d2a04","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 12, Pp 142651-142667 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3465789","is_oa":true,"landing_page_url":"http://dx.doi.org/10.1109/access.2024.3465789","pdf_url":null,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6399999856948853,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G3370319402","display_name":null,"funder_award_id":"RS-2023-00277080","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G7123502832","display_name":null,"funder_award_id":"RS-2024-00415602","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2565094479","https://openalex.org/W2390829436","https://openalex.org/W1989791859","https://openalex.org/W602859758","https://openalex.org/W2006439817","https://openalex.org/W1971289376","https://openalex.org/W2379101322","https://openalex.org/W1992553864","https://openalex.org/W2776207444","https://openalex.org/W2726447019"],"abstract_inverted_index":{"Currently,":[0],"GPUs":[1,153,210],"face":[2],"significant":[3],"challenges":[4],"due":[5],"to":[6,47,111,126,151,154,239,252],"limited":[7],"off-chip":[8],"bandwidth":[9,99],"(BW)":[10,100],"and":[11,33,168,182,201,206,247],"memory":[12,24,39,72,92,98,118,128,139,148,158,180],"capacity":[13],"during":[14],"DNN":[15,212],"training.":[16,213],"To":[17],"address":[18],"these":[19],"bottlenecks,":[20],"we":[21,134,186],"propose":[22],"a":[23,51,131],"access-triggered":[25],"near-data":[26],"processing":[27],"matNDP":[28,61,83,121,232],"architecture":[29],"that":[30],"offloads":[31],"memory-":[32,205],"communication-bound":[34,207],"operations.":[35],"With":[36],"matNDP,":[37],"normal":[38,71],"accesses":[40],"also":[41,78,90],"serve":[42],"as":[43],"implicit":[44],"NDP":[45,49,64,109,143,189,220],"requests":[46,73],"enable":[48,188],"in":[50,70,130,147,170,179,211],"non-invasive":[52],"manner":[53],"without":[54,190,226],"modifying":[55],"core-side":[56],"ISA/microarchitecture/SW,":[57],"for":[58,74,80],"practicality.":[59],"Additionally,":[60],"enables":[62],"on-the-fly":[63],"where":[65],"the":[66,96,115,196],"data":[67],"already":[68],"supplied":[69],"compute-bound":[75],"operations":[76,208],"are":[77,145],"used":[79,107],"NDP;":[81],"thus,":[82],"can":[84,105,123,163,222,233],"overlap":[85,195],"even":[86],"dependent":[87,199],"kernels":[88,221],"while":[89,176],"reducing":[91],"traffic.":[93],"Moreover,":[94],"with":[95],"overlap,":[97],"underutilized":[101],"by":[102,108,237,250],"GPU":[103],"cores":[104],"be":[106,124,223],"units":[110,122,144],"improve":[112,234],"performance":[113],"under":[114],"same":[116],"total":[117],"BW.":[119],"The":[120],"deployed":[125,146],"heterogeneous":[127],"devices":[129],"system.":[132],"First,":[133],"deploy":[135],"them":[136],"near":[137],"GPU\u2019s":[138],"controllers.":[140],"Secondly,":[141],"our":[142,215],"expanders":[149],"connected":[150],"multiple":[152],"create":[155],"an":[156],"NDP-enabled":[157],"eXpander":[159],"Network":[160],"(NDPXNet).":[161],"It":[162],"entirely":[164],"offload":[165,203],"gradient":[166],"reduction":[167],"optimizer":[169,183],"data-parallel":[171],"training,":[172],"achieving":[173],"additional":[174],"speedups":[175],"eliminating":[177],"redundancy":[178],"usage":[181],"execution.":[184],"Thus,":[185],"1)":[187],"core":[191],"HW/SW":[192],"changes,":[193],"2)":[194],"execution":[197],"of":[198],"layers,":[200],"3)":[202],"both":[204],"from":[209],"Through":[214],"deep":[216],"learning":[217],"compiler":[218],"support,":[219],"generated":[224],"automatically":[225],"any":[227],"model":[228],"code":[229],"modification.":[230],"Consequently,":[231],"training":[235],"throughput":[236],"up":[238,251],"<inline-formula":[240],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[241],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[242],"<tex-math":[243],"notation=\"LaTeX\">$2.73\\times":[244],"$":[245],"</tex-math></inline-formula>":[246],"reduce":[248],"energy":[249],"41.4%.":[253]},"counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}
