{"id":"https://openalex.org/W2773919090","doi":"https://doi.org/10.1109/tc.2017.2780237","title":"StaleLearn: Learning Acceleration with Asynchronous Synchronization Between Model Replicas on PIM","display_name":"StaleLearn: Learning Acceleration with Asynchronous Synchronization Between Model Replicas on PIM","publication_year":2017,"publication_date":"2017-12-06","ids":{"openalex":"https://openalex.org/W2773919090","doi":"https://doi.org/10.1109/tc.2017.2780237","mag":"2773919090"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2017.2780237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2017.2780237","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","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/A5041684303","display_name":"Joo Hwan Lee","orcid":"https://orcid.org/0000-0003-3989-2109"},"institutions":[{"id":"https://openalex.org/I4210101778","display_name":"Samsung (United States)","ror":"https://ror.org/01bfbvm65","country_code":"US","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210101778"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Joo Hwan Lee","raw_affiliation_strings":["Samsung Semiconductor, Inc., San Jose, CA"],"raw_orcid":"https://orcid.org/0000-0003-3989-2109","affiliations":[{"raw_affiliation_string":"Samsung Semiconductor, Inc., San Jose, CA","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000822269","display_name":"Hyesoon Kim","orcid":"https://orcid.org/0000-0002-6061-7825"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hyesoon Kim","raw_affiliation_strings":["School of Computer Science, Georgia Institute of Technology, Atlanta, GA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Georgia Institute of Technology, Atlanta, GA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1185,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.80170858,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"67","issue":"6","first_page":"861","last_page":"873"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9980000257492065,"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":0.9972000122070312,"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/computer-science","display_name":"Computer science","score":0.8800262212753296},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.697616696357727},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6449447870254517},{"id":"https://openalex.org/keywords/asynchronous-communication","display_name":"Asynchronous communication","score":0.5979488492012024},{"id":"https://openalex.org/keywords/synchronization","display_name":"Synchronization (alternating current)","score":0.5584962964057922},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4329336881637573}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8800262212753296},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.697616696357727},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6449447870254517},{"id":"https://openalex.org/C151319957","wikidata":"https://www.wikidata.org/wiki/Q752739","display_name":"Asynchronous communication","level":2,"score":0.5979488492012024},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.5584962964057922},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4329336881637573},{"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/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2017.2780237","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2017.2780237","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","0016-9340","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":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":48,"referenced_works":["https://openalex.org/W1844274058","https://openalex.org/W1975274780","https://openalex.org/W1979830285","https://openalex.org/W1980136882","https://openalex.org/W1981220134","https://openalex.org/W1981943579","https://openalex.org/W1988720110","https://openalex.org/W1989061323","https://openalex.org/W2007067737","https://openalex.org/W2009946006","https://openalex.org/W2034861439","https://openalex.org/W2039696740","https://openalex.org/W2049469158","https://openalex.org/W2078141470","https://openalex.org/W2088253639","https://openalex.org/W2097998348","https://openalex.org/W2098314020","https://openalex.org/W2113207845","https://openalex.org/W2131071574","https://openalex.org/W2132737349","https://openalex.org/W2132984949","https://openalex.org/W2133233009","https://openalex.org/W2135947393","https://openalex.org/W2138243089","https://openalex.org/W2138996412","https://openalex.org/W2142972517","https://openalex.org/W2145866640","https://openalex.org/W2153635508","https://openalex.org/W2156831150","https://openalex.org/W2163605009","https://openalex.org/W2168921806","https://openalex.org/W2295138987","https://openalex.org/W2474824677","https://openalex.org/W2569020760","https://openalex.org/W2898422183","https://openalex.org/W2963792515","https://openalex.org/W3120740533","https://openalex.org/W3148394109","https://openalex.org/W6662929504","https://openalex.org/W6674385629","https://openalex.org/W6677088747","https://openalex.org/W6679390333","https://openalex.org/W6679393576","https://openalex.org/W6679660245","https://openalex.org/W6680402377","https://openalex.org/W6684191040","https://openalex.org/W6720877245","https://openalex.org/W6755681954"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W3213381848","https://openalex.org/W2017587301","https://openalex.org/W2012954338","https://openalex.org/W2005148983","https://openalex.org/W2096672917","https://openalex.org/W2392023973","https://openalex.org/W2939411666"],"abstract_inverted_index":{"GPU":[0,15,25,112,168,186],"has":[1,16,63],"become":[2],"popular":[3],"with":[4,42,192],"a":[5,47,60,74,101,162],"large":[6,48],"amount":[7],"of":[8,50,111,120,134],"parallelism":[9,175],"found":[10],"in":[11,81],"learning.":[12,123],"While":[13],"the":[14,56,68,107,116,121,126,132,139,144,148,167],"been":[17,64],"effective":[18],"for":[19],"many":[20,24],"learning":[21,26,72,102,113,187],"tasks,":[22],"still":[23],"applications":[27,188],"have":[28],"low":[29,43],"execution":[30,51],"efficiency":[31],"due":[32],"to":[33,66,77,89,105],"sparse":[34],"data.":[35],"Sparse":[36],"data":[37,54],"induces":[38],"divergent":[39,135],"memory":[40,57,69,108,136],"accesses":[41,137],"locality,":[44],"thereby":[45],"consuming":[46],"fraction":[49],"time":[52],"transferring":[53],"across":[55],"hierarchy.":[58],"Although":[59],"considerable":[61],"effort":[62],"devoted":[65],"reducing":[67],"divergence,":[70],"iterative-convergent":[71,122],"provides":[73],"unique":[75],"opportunity":[76],"achieve":[78],"full":[79],"potential":[80],"modern":[82],"GPUs":[83],"that":[84],"it":[85],"allows":[86],"different":[87],"threads":[88],"continue":[90],"computation":[91],"using":[92],"stale":[93,117,127,158],"values.":[94],"In":[95],"this":[96],"paper,":[97],"we":[98],"propose":[99],"StaleLearn,":[100],"acceleration":[103],"mechanism":[104],"reduce":[106],"divergence":[109],"overhead":[110,150],"by":[114,142,151,189],"utilizing":[115],"value":[118,128,159],"tolerance":[119,160],"Based":[124],"on":[125,154],"tolerance,":[129],"StaleLearn":[130],"transforms":[131],"problem":[133,141],"into":[138],"synchronization":[140,149,153],"replicating":[143],"model":[145],"and":[146,169,178],"reduces":[147],"asynchronous":[152],"Processor-in-Memory":[155],"(PIM).":[156],"The":[157],"enables":[161],"clear":[163],"task":[164],"decomposition":[165],"between":[166,176],"PIM,":[170],"which":[171],"can":[172],"effectively":[173],"exploit":[174],"PIM":[177,194],"GPU.":[179],"On":[180],"average,":[181],"our":[182],"approach":[183],"accelerates":[184],"representative":[185],"3.17":[190],"times":[191],"existing":[193],"proposals.":[195]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}