{"id":"https://openalex.org/W3096221800","doi":"https://doi.org/10.1109/tc.2020.3035826","title":"A Lightweight and Efficient GPU for NDP Utilizing Data Access Pattern of Image Processing","display_name":"A Lightweight and Efficient GPU for NDP Utilizing Data Access Pattern of Image Processing","publication_year":2020,"publication_date":"2020-11-04","ids":{"openalex":"https://openalex.org/W3096221800","doi":"https://doi.org/10.1109/tc.2020.3035826","mag":"3096221800"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2020.3035826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2020.3035826","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"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 Computers","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/A5103127615","display_name":"Jung\u2010Woo Choi","orcid":"https://orcid.org/0000-0003-4259-0566"},"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":true,"raw_author_name":"Jungwoo Choi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018573573","display_name":"Boyeal Kim","orcid":"https://orcid.org/0000-0003-4855-3600"},"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":"Boyeal Kim","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044746143","display_name":"Ji-Ye Jeon","orcid":null},"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":"Ji-Ye Jeon","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024723558","display_name":"Hyuk\u2010Jae Lee","orcid":"https://orcid.org/0000-0001-6811-9647"},"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":"Hyuk-Jae Lee","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"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 Inc., Icheon, Gyeonggi-do, South Korea"],"affiliations":[{"raw_affiliation_string":"SK Hynix Inc., Icheon, Gyeonggi-do, South Korea","institution_ids":["https://openalex.org/I134353371"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066755055","display_name":"Chae Eun Rhee","orcid":"https://orcid.org/0000-0002-7851-1703"},"institutions":[{"id":"https://openalex.org/I191879574","display_name":"Inha University","ror":"https://ror.org/01easw929","country_code":"KR","type":"education","lineage":["https://openalex.org/I191879574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chae Eun Rhee","raw_affiliation_strings":["Department of Information and Communication Engineering, Inha University, Incheon, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Information and Communication Engineering, Inha University, Incheon, South Korea","institution_ids":["https://openalex.org/I191879574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5103127615"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.9369,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.74073548,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"71","issue":"1","first_page":"13","last_page":"26"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9994000196456909,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9984999895095825,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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":0.8153678178787231},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.5373505353927612},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5249459743499756},{"id":"https://openalex.org/keywords/image-processing","display_name":"Image processing","score":0.5249450206756592},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5175942182540894},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.4831830561161041},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.4556657373905182},{"id":"https://openalex.org/keywords/graphics-processing-unit","display_name":"Graphics processing unit","score":0.45485997200012207},{"id":"https://openalex.org/keywords/static-random-access-memory","display_name":"Static random-access memory","score":0.43570995330810547},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3477436900138855},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.33625292778015137},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2560306191444397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.13883262872695923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8153678178787231},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.5373505353927612},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5249459743499756},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.5249450206756592},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5175942182540894},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.4831830561161041},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.4556657373905182},{"id":"https://openalex.org/C2779851693","wikidata":"https://www.wikidata.org/wiki/Q183484","display_name":"Graphics processing unit","level":2,"score":0.45485997200012207},{"id":"https://openalex.org/C68043766","wikidata":"https://www.wikidata.org/wiki/Q267416","display_name":"Static random-access memory","level":2,"score":0.43570995330810547},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3477436900138855},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.33625292778015137},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2560306191444397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.13883262872695923},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2020.3035826","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2020.3035826","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"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 Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.8700000047683716,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320317879","display_name":"SK Hynix","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1964826176","https://openalex.org/W1975237352","https://openalex.org/W1979527452","https://openalex.org/W2023925637","https://openalex.org/W2043083835","https://openalex.org/W2045525968","https://openalex.org/W2048441570","https://openalex.org/W2079038734","https://openalex.org/W2094332102","https://openalex.org/W2096661534","https://openalex.org/W2112547256","https://openalex.org/W2124969960","https://openalex.org/W2128120785","https://openalex.org/W2150947797","https://openalex.org/W2166918318","https://openalex.org/W2289175783","https://openalex.org/W2409197925","https://openalex.org/W2471077310","https://openalex.org/W2474451066","https://openalex.org/W2509155819","https://openalex.org/W2513721464","https://openalex.org/W2517869808","https://openalex.org/W2545376626","https://openalex.org/W2612654866","https://openalex.org/W2612735730","https://openalex.org/W2761132374","https://openalex.org/W2886589913","https://openalex.org/W3005783121","https://openalex.org/W3128982134","https://openalex.org/W3137551601","https://openalex.org/W3148444620","https://openalex.org/W4234833047","https://openalex.org/W4235870392","https://openalex.org/W4246587277","https://openalex.org/W4249082578","https://openalex.org/W6675244200","https://openalex.org/W6696699156","https://openalex.org/W6720284283","https://openalex.org/W6792253866"],"related_works":["https://openalex.org/W3151633427","https://openalex.org/W2012045996","https://openalex.org/W2212894501","https://openalex.org/W2793465010","https://openalex.org/W3024050170","https://openalex.org/W4293253840","https://openalex.org/W4378977321","https://openalex.org/W2967161359","https://openalex.org/W4308090481","https://openalex.org/W3211992815"],"abstract_inverted_index":{"As":[0],"the":[1,10,13,45,61,72,101,113,120,143,147,153,158,165,190,195,206],"demand":[2],"for":[3,15],"image":[4,16,81,104],"applications":[5,105],"with":[6,28],"high":[7],"resolution":[8],"increases,":[9],"importance":[11],"of":[12,54,64,74,103,149,157,175],"system":[14],"processing":[17,21,82,114,176],"is":[18,41,116,135],"growing.":[19],"Graphics":[20],"units":[22,177],"(GPUs)":[23],"can":[24],"increase":[25],"computational":[26],"capacity":[27],"massive":[29],"parallelism,":[30],"but":[31],"are":[32,160],"still":[33],"subject":[34],"to":[35,43,112,118,168,178,205],"limited":[36],"memory":[37],"bandwidth.":[38],"Near-data-processing":[39],"(NDP)":[40],"expected":[42],"mitigate":[44],"performance":[46,196],"and":[47,95,106,123,152,171,199],"energy":[48,203],"overhead":[49],"caused":[50],"as":[51],"a":[52,76,91,128,139,172,182],"result":[53],"data":[55,110,121,124,145],"transfer":[56],"by":[57,197],"performing":[58],"computations":[59],"on":[60,80,181],"logic":[62,183],"die":[63],"3D-stacked":[65],"memory.":[66],"Although":[67],"prior":[68],"studies":[69],"have":[70],"demonstrated":[71],"advantages":[73],"NDP,":[75],"NDP":[77,93,107,132,159,166,192,208],"solution":[78],"focused":[79],"has":[83],"not":[84],"yet":[85,130],"been":[86],"developed.":[87],"This":[88,163],"article":[89],"proposes":[90],"GPU-based":[92],"architecture":[94,134],"well-matched":[96],"optimization":[97],"strategies":[98],"considering":[99],"both":[100],"characteristics":[102],"constraints.":[108],"First,":[109],"allocation":[111],"unit":[115],"addressed":[117],"maintain":[119],"locality":[122],"access":[125],"pattern.":[126],"Second,":[127],"lightweight":[129],"efficient":[131],"GPU":[133,193],"proposed.":[136],"By":[137],"applying":[138],"prefetcher":[140],"that":[141,189],"leverages":[142],"pattern-aware":[144],"allocation,":[146],"number":[148,174],"active":[150],"warps":[151],"on-chip":[154],"SRAM":[155],"size":[156],"significantly":[161],"reduced.":[162],"enables":[164],"constraints":[167],"be":[169,179],"satisfied":[170],"greater":[173],"integrated":[180],"die.":[184],"The":[185],"evaluation":[186],"results":[187],"show":[188],"proposed":[191],"improves":[194],"1.85\u00d7":[198],"consumes":[200],"82.7":[201],"percent":[202],"compared":[204],"baseline":[207],"GPU.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}