{"id":"https://openalex.org/W4320067983","doi":"https://doi.org/10.1145/3545008.3545054","title":"Exploiting CXL-based Memory for Distributed Deep Learning","display_name":"Exploiting CXL-based Memory for Distributed Deep Learning","publication_year":2022,"publication_date":"2022-08-29","ids":{"openalex":"https://openalex.org/W4320067983","doi":"https://doi.org/10.1145/3545008.3545054"},"language":"en","primary_location":{"id":"doi:10.1145/3545008.3545054","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3545008.3545054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 51st International Conference on Parallel Processing","raw_type":"proceedings-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/A5017707472","display_name":"Moiz Arif","orcid":"https://orcid.org/0000-0002-8823-5562"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Moiz Arif","raw_affiliation_strings":["Computer Science, Rochester Institute of Technology, United States of America"],"affiliations":[{"raw_affiliation_string":"Computer Science, Rochester Institute of Technology, United States of America","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017256448","display_name":"Kevin Assogba","orcid":"https://orcid.org/0000-0002-0377-4576"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kevin Assogba","raw_affiliation_strings":["Computer Science, Rochester Institute of Technology, United States of America"],"affiliations":[{"raw_affiliation_string":"Computer Science, Rochester Institute of Technology, United States of America","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054011637","display_name":"M. Mustafa Rafique","orcid":"https://orcid.org/0000-0002-5034-2880"},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"M. Mustafa Rafique","raw_affiliation_strings":["Computer Science, Rochester Institute of Technology, United States of America"],"affiliations":[{"raw_affiliation_string":"Computer Science, Rochester Institute of Technology, United States of America","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000418371","display_name":"Sudharshan S. Vazhkudai","orcid":"https://orcid.org/0000-0002-8596-5033"},"institutions":[{"id":"https://openalex.org/I11912373","display_name":"Micron (United States)","ror":"https://ror.org/02fv52296","country_code":"US","type":"company","lineage":["https://openalex.org/I11912373"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sudharshan Vazhkudai","raw_affiliation_strings":["Micron Technology, Inc., United States of America"],"affiliations":[{"raw_affiliation_string":"Micron Technology, Inc., United States of America","institution_ids":["https://openalex.org/I11912373"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5017707472"],"corresponding_institution_ids":["https://openalex.org/I155173764"],"apc_list":null,"apc_paid":null,"fwci":2.9811,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.91575686,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"11"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.9944000244140625,"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":0.8676939606666565},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6065696477890015},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5978356003761292},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5332913398742676},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.44896674156188965},{"id":"https://openalex.org/keywords/computer-data-storage","display_name":"Computer data storage","score":0.411642462015152},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.3969348967075348},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37561073899269104},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3702085018157959},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.16926893591880798},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16791296005249023},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.1519501507282257},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.08336490392684937}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8676939606666565},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6065696477890015},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5978356003761292},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5332913398742676},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.44896674156188965},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.411642462015152},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3969348967075348},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37561073899269104},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3702085018157959},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.16926893591880798},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16791296005249023},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.1519501507282257},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.08336490392684937}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3545008.3545054","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3545008.3545054","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 51st International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4300000071525574,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G2131453672","display_name":null,"funder_award_id":"2106635","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320307112","display_name":"Micron Technology","ror":"https://ror.org/02fv52296"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W2074881976","https://openalex.org/W2108598243","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2312694346","https://openalex.org/W2525739395","https://openalex.org/W2612026221","https://openalex.org/W2616570824","https://openalex.org/W2906257585","https://openalex.org/W2951947775","https://openalex.org/W2963304552","https://openalex.org/W2983617330","https://openalex.org/W2985313082","https://openalex.org/W2992429266","https://openalex.org/W2999044305","https://openalex.org/W3004495293","https://openalex.org/W3018396836","https://openalex.org/W3041188508","https://openalex.org/W3090843841","https://openalex.org/W3095915013","https://openalex.org/W3102254513","https://openalex.org/W3114711045","https://openalex.org/W3138770260","https://openalex.org/W3173453991","https://openalex.org/W3206416201","https://openalex.org/W3206418153","https://openalex.org/W3216116694","https://openalex.org/W4205871220","https://openalex.org/W4205947740","https://openalex.org/W4226379841","https://openalex.org/W4286307988","https://openalex.org/W6713134421"],"related_works":["https://openalex.org/W4375867731","https://openalex.org/W2136583354","https://openalex.org/W2111238207","https://openalex.org/W2611989081","https://openalex.org/W2760721665","https://openalex.org/W4230611425","https://openalex.org/W2731899572","https://openalex.org/W330130819","https://openalex.org/W2288610023","https://openalex.org/W4304166257"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"(DL)":[2],"is":[3,140],"being":[4],"widely":[5],"used":[6],"to":[7,41,87,112,123,133,189,217,222],"solve":[8],"complex":[9],"problems":[10],"in":[11,103],"scientific":[12],"applications":[13,28],"from":[14],"diverse":[15],"domains,":[16],"such":[17],"as":[18,76],"weather":[19],"forecasting,":[20],"medical":[21],"diagnostics,":[22],"and":[23,51,81,116,168,172,180,196,204,219,227],"fluid":[24],"dynamics":[25],"simulation.":[26],"DL":[27,121,131,176,186],"consume":[29],"a":[30,43,150,163,184,212],"large":[31,49],"amount":[32,60],"of":[33,61,158,215],"data":[34,80,138],"using":[35,137],"large-scale":[36],"high-performance":[37],"computing":[38],"(HPC)":[39],"systems":[40],"train":[42,135],"given":[44],"model.":[45],"These":[46],"workloads":[47,122],"have":[48],"memory":[50,63,105,115,229],"storage":[52,89,166],"requirements":[53],"that":[54,139,154,191],"typically":[55],"go":[56],"beyond":[57],"the":[58,72,77,92,100,104,125,144,156,200,206,223],"limited":[59],"main":[62],"available":[64],"on":[65],"an":[66],"HPC":[67],"server.":[68],"This":[69],"significantly":[70],"increases":[71],"overall":[73,126,201],"training":[74,79,93,127,207],"time":[75,128],"input":[78],"model":[82],"parameters":[83],"are":[84],"frequently":[85],"swapped":[86],"slower":[88],"tiers":[90],"during":[91],"process.":[94],"In":[95],"this":[96],"paper,":[97],"we":[98],"use":[99],"latest":[101],"advancements":[102],"subsystem,":[106],"specifically":[107],"Compute":[108],"Express":[109],"Link":[110],"(CXL),":[111],"provide":[113],"additional":[114,159],"fast":[117,164],"scratch":[118],"space":[119],"for":[120,175],"reduce":[124],"while":[129],"enabling":[130],"jobs":[132],"efficiently":[134],"models":[136],"much":[141],"larger":[142],"than":[143],"installed":[145],"system":[146],"memory.":[147],"We":[148,178],"propose":[149],"framework,":[151],"called":[152],"DeepMemoryDL,":[153],"manages":[155],"allocation":[157],"CXL-based":[160,228],"memory,":[161],"introduces":[162],"intermediate":[165],"tier,":[167],"provides":[169],"intelligent":[170],"prefetching":[171],"caching":[173],"mechanisms":[174],"workloads.":[177],"implement":[179],"integrate":[181],"DeepMemoryDL":[182],"with":[183],"popular":[185],"platform,":[187],"TensorFlow,":[188],"show":[190],"our":[192],"approach":[193],"reduces":[194,205],"read":[195],"write":[197],"latencies,":[198],"improves":[199],"I/O":[202],"throughput,":[203],"time.":[208],"Our":[209],"evaluation":[210],"shows":[211],"performance":[213],"improvement":[214],"up":[216],"34%":[218],"27%":[220],"compared":[221],"default":[224],"TensorFlow":[225],"platform":[226],"expansion":[230],"approaches,":[231],"respectively.":[232]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}