{"id":"https://openalex.org/W2270723299","doi":null,"title":"Scaling Deep Learning on Multiple In-Memory Processors","display_name":"Scaling Deep Learning on Multiple In-Memory Processors","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2270723299","mag":"2270723299"},"language":"en","primary_location":{"id":"mag:2270723299","doi":null,"is_oa":false,"landing_page_url":"https://www.eecis.udel.edu/~lxu/resources/Scaling%20Deep%20Learning%20on%20Multiple%20In-Memory%20Processors.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5039304555","display_name":"Lifan Xu","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lifan Xu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005899835","display_name":"Dong Ping Zhang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dong Ping Zhang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5060736283","display_name":"Nuwan Jayasena","orcid":"https://orcid.org/0009-0005-2973-9479","observed_orcids":["https://orcid.org/0009-0005-2973-9479"]},"institutions":[{"id":"https://openalex.org/I4210137977","display_name":"Advanced Micro Devices (United States)","ror":"https://ror.org/04kd6c783","country_code":"US","type":"company","lineage":["https://openalex.org/I4210137977"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nuwan Jayasena","raw_affiliation_strings":["Advanced Micro Devices"],"raw_orcid":"https://orcid.org/0009-0005-2973-9479","affiliations":[{"raw_affiliation_string":"Advanced Micro Devices","institution_ids":["https://openalex.org/I4210137977"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.5571,"has_fulltext":false,"cited_by_count":17,"citation_normalized_percentile":{"value":0.88433831,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":98},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9520999789237976,"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":0.9520999789237976,"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/T11527","display_name":"3D IC and TSV technologies","score":0.033799998462200165,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.00419999985024333,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/in-memory-computing","display_name":"in-memory computing","score":0.9490000009536743},{"id":"https://openalex.org/keywords/3d-die-stacking","display_name":"3D die stacking","score":0.8889999985694885},{"id":"https://openalex.org/keywords/deep-learning-acceleration","display_name":"deep learning acceleration","score":0.8130000233650208},{"id":"https://openalex.org/keywords/parallelization","display_name":"parallelization","score":0.6800000071525574},{"id":"https://openalex.org/keywords/convolutional-layers","display_name":"convolutional layers","score":0.8730000257492065},{"id":"https://openalex.org/keywords/pooling-layers","display_name":"pooling layers","score":0.9380000233650208},{"id":"https://openalex.org/keywords/fully-connected-layers","display_name":"fully connected layers","score":0.9959999918937683},{"id":"https://openalex.org/keywords/energy-efficiency","display_name":"energy efficiency","score":0.7390000224113464},{"id":"https://openalex.org/keywords/data-movement-overhead","display_name":"data movement overhead","score":0.6859999895095825},{"id":"https://openalex.org/keywords/gpu-comparison","display_name":"GPU comparison","score":0.906000018119812}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.833424985408783},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.8272390961647034},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.6490313410758972},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5656474232673645},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5591849684715271},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.5442535877227783},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.4907172918319702},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.44975724816322327},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4259762167930603},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3727542459964752},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3281365633010864},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.11292484402656555},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2270723299","doi":null,"is_oa":false,"landing_page_url":"https://www.eecis.udel.edu/~lxu/resources/Scaling%20Deep%20Learning%20on%20Multiple%20In-Memory%20Processors.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W1598866093","https://openalex.org/W1686810756","https://openalex.org/W1975237352","https://openalex.org/W1998399571","https://openalex.org/W2038666141","https://openalex.org/W2072128103","https://openalex.org/W2076063813","https://openalex.org/W2136922672","https://openalex.org/W2162390675","https://openalex.org/W2163605009","https://openalex.org/W2168231600"],"related_works":["https://openalex.org/W4405778679","https://openalex.org/W2625998576","https://openalex.org/W3209676039","https://openalex.org/W4285815043","https://openalex.org/W3163905326","https://openalex.org/W4401568752","https://openalex.org/W4407694321","https://openalex.org/W3138893848","https://openalex.org/W4226407946","https://openalex.org/W3138708228"],"abstract_inverted_index":{"Deep":[0],"learning":[1,14,46,84,108],"methods":[2,85],"are":[3,120],"proven":[4],"to":[5,42,63,67,122],"be":[6],"state-of-theart":[7],"in":[8,12],"addressing":[9],"many":[10],"challenges":[11],"machine":[13],"domains.":[15],"However,":[16],"it":[17],"comes":[18],"at":[19],"the":[20,80,98],"cost":[21],"of":[22,31,82],"high":[23],"computational":[24],"requirements":[25],"and":[26,48,69,101,110],"energy":[27,50],"consumption.":[28],"The":[29],"emergence":[30],"Processing":[32],"In":[33,75],"Memory":[34],"(PIM)":[35],"with":[36,89,135],"diestacking":[37],"technology":[38],"presents":[39],"an":[40],"opportunity":[41],"speed":[43],"up":[44],"deep":[45,83,107],"computation":[47],"reduce":[49,71],"consumption":[51],"by":[52],"providing":[53],"low-cost":[54],"high-bandwidth":[55],"memory":[56,68],"accesses.":[57],"PIM":[58,91,131],"uses":[59],"3D":[60],"die":[61],"stacking":[62],"move":[64],"computations":[65],"closer":[66],"therefore":[70],"data":[72],"movement":[73],"overheads.":[74],"this":[76],"paper,":[77],"we":[78,119],"study":[79],"parallelization":[81],"on":[86],"a":[87],"system":[88],"multiple":[90,130],"devices.":[92],"We":[93],"select":[94],"three":[95],"typical":[96],"layers:":[97],"convolutional,":[99],"pooling,":[100],"fully":[102],"connected":[103],"layers":[104],"from":[105],"common":[106],"models":[109],"parallelize":[111],"them":[112],"using":[113,129],"different":[114],"schemes.":[115],"Preliminary":[116],"results":[117],"show":[118],"able":[121],"reach":[123],"competitive":[124],"or":[125],"even":[126],"better":[127],"performance":[128],"devices":[132],"when":[133],"comparing":[134],"traditional":[136],"GPU":[137],"parallelization.":[138]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1}],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2016-06-24T00:00:00"}