{"id":"https://openalex.org/W4403918491","doi":"https://doi.org/10.1109/access.2024.3488004","title":"Accelerating CNN Training With Concurrent Execution of GPU and Processing-in-Memory","display_name":"Accelerating CNN Training With Concurrent Execution of GPU and Processing-in-Memory","publication_year":2024,"publication_date":"2024-01-01","ids":{"openalex":"https://openalex.org/W4403918491","doi":"https://doi.org/10.1109/access.2024.3488004"},"language":"en","primary_location":{"id":"doi:10.1109/access.2024.3488004","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3488004","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":"https://doi.org/10.1109/access.2024.3488004","any_repository_has_fulltext":true},"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 Engineering and Computer Science, Inter-University Semiconductor Research Center (ISRC), Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Inter-University Semiconductor Research Center (ISRC), Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102861073","display_name":"Hyuk-Jae Lee","orcid":"https://orcid.org/0000-0001-8895-9117"},"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 Engineering and Computer Science, Inter-University Semiconductor Research Center (ISRC), Seoul National University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering and Computer Science, Inter-University Semiconductor Research Center (ISRC), Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050861404","display_name":"Kyomin Sohn","orcid":"https://orcid.org/0000-0002-8094-9843"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Kyomin Sohn","raw_affiliation_strings":["Samsung Electronics, Hwaseong-si, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics, Hwaseong-si, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111875390","display_name":"Hak-soo Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hak-Soo Yu","raw_affiliation_strings":["Samsung Electronics, Hwaseong-si, South Korea"],"affiliations":[{"raw_affiliation_string":"Samsung Electronics, Hwaseong-si, South Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"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/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Chae Eun Rhee","raw_affiliation_strings":["Department of Electronic Engineering, Hanyang University, Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electronic Engineering, Hanyang University, Seoul, South Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103127615"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.2631,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58565525,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":"12","issue":null,"first_page":"160190","last_page":"160204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9811999797821045,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9811999797821045,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9789999723434448,"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/T10320","display_name":"Neural Networks and Applications","score":0.9740999937057495,"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":0.8730154633522034},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6334142684936523},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.4518416225910187},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.37646305561065674},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3537274897098541},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.12183085083961487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8730154633522034},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6334142684936523},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.4518416225910187},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.37646305561065674},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3537274897098541},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.12183085083961487}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2024.3488004","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3488004","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:25b659e0974b47cab0202f7a4c608ae7","is_oa":true,"landing_page_url":"https://doaj.org/article/25b659e0974b47cab0202f7a4c608ae7","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 160190-160204 (2024)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2024.3488004","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2024.3488004","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":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1973573211","https://openalex.org/W1975381618","https://openalex.org/W1980287119","https://openalex.org/W2045431893","https://openalex.org/W2108598243","https://openalex.org/W2159908132","https://openalex.org/W2172654076","https://openalex.org/W2194775991","https://openalex.org/W2513721464","https://openalex.org/W2517869808","https://openalex.org/W2618530766","https://openalex.org/W2622263826","https://openalex.org/W2790546557","https://openalex.org/W2796649226","https://openalex.org/W2798724095","https://openalex.org/W2891017939","https://openalex.org/W2904295992","https://openalex.org/W2911173308","https://openalex.org/W2931092525","https://openalex.org/W2931633209","https://openalex.org/W2946749059","https://openalex.org/W2963073398","https://openalex.org/W2963340555","https://openalex.org/W2963446712","https://openalex.org/W2963989532","https://openalex.org/W2985229340","https://openalex.org/W2991040477","https://openalex.org/W2998993395","https://openalex.org/W3007895486","https://openalex.org/W3008805724","https://openalex.org/W3014934202","https://openalex.org/W3043140114","https://openalex.org/W3084623993","https://openalex.org/W3100710793","https://openalex.org/W3145545382","https://openalex.org/W3156313549","https://openalex.org/W3157174059","https://openalex.org/W3158634533","https://openalex.org/W3189166979","https://openalex.org/W3205265826","https://openalex.org/W3215253865","https://openalex.org/W4211165432","https://openalex.org/W4226148550","https://openalex.org/W4282970339","https://openalex.org/W4297775537","https://openalex.org/W4385245566","https://openalex.org/W4388297464","https://openalex.org/W4392427708","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6640442106","https://openalex.org/W6737664043","https://openalex.org/W6739622702","https://openalex.org/W6750448596","https://openalex.org/W6752784787","https://openalex.org/W6754222578","https://openalex.org/W6755130838","https://openalex.org/W6786965630"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"Training":[0],"of":[1,9,27,68,91,166,179,198,233,250,263,300,311],"convolutional":[2,22],"neural":[3],"networks":[4],"(CNN)":[5],"consumes":[6],"a":[7,155,191],"lot":[8],"time":[10],"and":[11,46,85,115,147,158,172,185,204,218,230,243,270,314],"resources.":[12],"While":[13],"most":[14],"previous":[15],"works":[16],"have":[17,42],"focused":[18],"on":[19,82,95,169,175],"accelerating":[20],"the":[21,25,77,83,87,92,96,113,118,163,170,183,196,211,216,231,239,257,260,264,271,292,303,308,312],"(CONV)":[23],"layer,":[24,223],"proportion":[26],"non-convolutional":[28],"(non-CONV)":[29],"layers,":[30],"such":[31],"as":[32],"batch":[33],"normalization,":[34],"is":[35,51,135],"gradually":[36],"increasing":[37],"during":[38],"training.":[39],"Non-CONV":[40],"layers":[41,168,174,245],"low":[43],"cache":[44],"reuse":[45],"arithmetic":[47],"intensity,":[48],"thereby":[49],"performance":[50,100,122],"limited":[52],"by":[53],"memory":[54,61,88,109,131,156,189,203,212,227,235],"bandwidth.":[55],"Processing-in-memory":[56],"(PIM)":[57],"can":[58,101,281],"utilize":[59],"wide":[60],"bandwidth,":[62],"making":[63],"it":[64,72,134],"suitable":[65],"for":[66,162,190,209,256],"acceleration":[67],"non-CONV":[69,93,148,173,244,261],"layers.":[70,149,287],"Therefore,":[71],"makes":[73],"sense":[74],"to":[75,129,194,307],"perform":[76],"computationally":[78],"complex":[79],"CONV":[80,146,167,242,286],"layer":[81,94],"host":[84,114,171,184,202,217,313],"handle":[86],"bottleneck":[89],"challenges":[90],"PIM.":[97,176,315],"Further":[98],"improved":[99],"be":[102,282],"expected":[103],"if":[104],"they":[105,280],"run":[106],"simultaneously.":[107],"However,":[108],"access":[110,188,213,228],"conflicts":[111],"between":[112,145,201,215],"PIM":[116,186,205,219],"are":[117,220,246,276],"biggest":[119],"factors":[120],"hindering":[121],"improvement.":[123],"Prior":[124],"studies":[125],"proposed":[126,293],"bank":[127,181],"partitioning":[128],"alleviate":[130],"conflicts,":[132],"but":[133],"not":[136],"effective":[137],"because":[138],"CNN":[139,159],"training":[140,160,240],"involves":[141],"significant":[142],"data":[143,200],"sharing":[144],"In":[150],"this":[151],"paper,":[152],"we":[153],"propose":[154],"scheduling":[157],"flow":[161],"pipelined":[164,247,294],"execution":[165,295],"First,":[177],"instead":[178],"applying":[180],"partitioning,":[182],"exclusively":[187],"certain":[192],"period":[193],"avoid":[195],"movement":[197],"shared":[199],"memory.":[206],"The":[207],"conditions":[208],"switching":[210],"authority":[214],"set":[221],"per":[222],"taking":[224],"into":[225],"account":[226],"characteristics":[229],"number":[232],"queued":[234],"requests.":[236],"Second,":[237],"in":[238,248],"flow,":[241],"units":[249],"output":[251],"feature":[252,265],"map":[253,266],"channels.":[254],"Specifically,":[255],"backward":[258],"pass,":[259],"tasks":[262],"gradient":[267,273],"calculation":[268],"phase":[269,275],"weight":[272],"update":[274],"rearranged":[277],"so":[278],"that":[279,291],"easily":[283],"performed":[284],"within":[285],"Experimental":[288],"results":[289],"show":[290],"achieves":[296],"an":[297],"average":[298],"speedup":[299],"18.1%":[301],"at":[302],"network":[304],"level":[305],"compared":[306],"serial":[309],"operation":[310]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}
