{"id":"https://openalex.org/W4401765190","doi":"https://doi.org/10.1145/3680546","title":"A Data-Loader Tunable Knob to Shorten GPU Idleness for Distributed Deep Learning","display_name":"A Data-Loader Tunable Knob to Shorten GPU Idleness for Distributed Deep Learning","publication_year":2024,"publication_date":"2024-08-22","ids":{"openalex":"https://openalex.org/W4401765190","doi":"https://doi.org/10.1145/3680546"},"language":"en","primary_location":{"id":"doi:10.1145/3680546","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3680546","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1145/3680546","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5013649821","display_name":"Danlin Jia","orcid":"https://orcid.org/0000-0003-2858-0505"},"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":"Danlin Jia","raw_affiliation_strings":["Samsung Semiconductor Inc USA, San Jose, United States"],"raw_orcid":"https://orcid.org/0000-0003-2858-0505","affiliations":[{"raw_affiliation_string":"Samsung Semiconductor Inc USA, San Jose, United States","institution_ids":["https://openalex.org/I4210101778"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5007300551","display_name":"Geng Yuan","orcid":"https://orcid.org/0000-0001-9844-992X"},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Geng Yuan","raw_affiliation_strings":["University of Georgia School of Computing, Athens, United States"],"raw_orcid":"https://orcid.org/0000-0001-9844-992X","affiliations":[{"raw_affiliation_string":"University of Georgia School of Computing, Athens, United States","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102716914","display_name":"Yiming Xie","orcid":"https://orcid.org/0009-0007-8841-9699"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]},{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiming Xie","raw_affiliation_strings":["Northeastern University College of Engineering, Boston, United States"],"raw_orcid":"https://orcid.org/0009-0007-8841-9699","affiliations":[{"raw_affiliation_string":"Northeastern University College of Engineering, Boston, United States","institution_ids":["https://openalex.org/I111088046","https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043582832","display_name":"Xue Lin","orcid":"https://orcid.org/0000-0001-6210-8883"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]},{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xue Lin","raw_affiliation_strings":["Northeastern University College of Engineering, Boston, United States"],"raw_orcid":"https://orcid.org/0000-0001-6210-8883","affiliations":[{"raw_affiliation_string":"Northeastern University College of Engineering, Boston, United States","institution_ids":["https://openalex.org/I111088046","https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091825452","display_name":"Ningfang Mi","orcid":"https://orcid.org/0009-0005-0934-1287"},"institutions":[{"id":"https://openalex.org/I111088046","display_name":"Boston University","ror":"https://ror.org/05qwgg493","country_code":"US","type":"education","lineage":["https://openalex.org/I111088046"]},{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ningfang Mi","raw_affiliation_strings":["Northeastern University College of Engineering, Boston, United States"],"raw_orcid":"https://orcid.org/0009-0005-0934-1287","affiliations":[{"raw_affiliation_string":"Northeastern University College of Engineering, Boston, United States","institution_ids":["https://openalex.org/I111088046","https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1645,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.42663032,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"21","issue":"4","first_page":"1","last_page":"25"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9929999709129333,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9861000180244446,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8484792709350586},{"id":"https://openalex.org/keywords/loader","display_name":"Loader","score":0.7988243103027344},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5997651219367981},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4928031265735626},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.41993600130081177},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40556392073631287},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.3733718693256378},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2276638150215149}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8484792709350586},{"id":"https://openalex.org/C2779041774","wikidata":"https://www.wikidata.org/wiki/Q650550","display_name":"Loader","level":2,"score":0.7988243103027344},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5997651219367981},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4928031265735626},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.41993600130081177},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40556392073631287},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.3733718693256378},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2276638150215149}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3680546","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3680546","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1145/3680546","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3680546","pdf_url":null,"source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.5400000214576721,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G6420210134","display_name":null,"funder_award_id":"CNS-2008072","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"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W1686810756","https://openalex.org/W2117539524","https://openalex.org/W2147800946","https://openalex.org/W2194775991","https://openalex.org/W2612445135","https://openalex.org/W2734941459","https://openalex.org/W2798515322","https://openalex.org/W2883283076","https://openalex.org/W2900042580","https://openalex.org/W2946408574","https://openalex.org/W2957236078","https://openalex.org/W2964081807","https://openalex.org/W2964330541","https://openalex.org/W2972087877","https://openalex.org/W2977730164","https://openalex.org/W2990062730","https://openalex.org/W3022513626","https://openalex.org/W3037585619","https://openalex.org/W3043413334","https://openalex.org/W3087861083","https://openalex.org/W3105067168","https://openalex.org/W3185792040","https://openalex.org/W3194040310","https://openalex.org/W3206418153","https://openalex.org/W4281657584","https://openalex.org/W4287661392","https://openalex.org/W4287724000","https://openalex.org/W4287813281","https://openalex.org/W4292973398","https://openalex.org/W4297775537","https://openalex.org/W6765518731"],"related_works":["https://openalex.org/W2365193102","https://openalex.org/W2343312170","https://openalex.org/W2392969333","https://openalex.org/W2380220463","https://openalex.org/W2745521454","https://openalex.org/W2363418592","https://openalex.org/W2061615910","https://openalex.org/W2385186581","https://openalex.org/W2388122603","https://openalex.org/W2357710548"],"abstract_inverted_index":{"Deep":[0,47],"Neural":[1],"Networks":[2],"(DNNs)":[3],"have":[4],"been":[5],"applied":[6],"as":[7,214],"an":[8,184],"effective":[9],"machine":[10],"learning":[11],"algorithm":[12],"to":[13,22,51,98,115,178,197,204,217],"tackle":[14],"problems":[15],"in":[16,36,101,234],"different":[17],"domains.":[18],"However,":[19],"the":[20,37,70,80,136,152,162,167,180,191,211,225,248],"endeavor":[21],"train":[23],"sophisticated":[24],"DNN":[25,44,53],"models":[26],"can":[27,256],"stretch":[28],"from":[29],"days":[30],"into":[31],"weeks,":[32],"presenting":[33],"substantial":[34],"obstacles":[35],"realm":[38],"of":[39,73,82,138,164,241],"research":[40,74],"focused":[41],"on":[42,85,126,160,166],"large-scale":[43],"architectures.":[45],"Distributed":[46],"Learning":[48],"(DDL)":[49],"contributes":[50],"accelerating":[52],"training":[54,57,90,118,153,169,187,227],"by":[55],"distributing":[56],"workloads":[58],"across":[59,247,272],"multiple":[60,121],"computation":[61],"accelerators,":[62],"for":[63,144,183,238],"example,":[64],"graphics":[65],"processing":[66,108],"units":[67],"(GPUs).":[68],"Despite":[69],"considerable":[71],"amount":[72],"directed":[75],"toward":[76],"enhancing":[77],"DDL":[78,102,122,186,207,236,242],"training,":[79],"influence":[81],"data":[83],"loading":[84],"GPU":[86,148,219],"utilization":[87],"and":[88,111,131,141,150,201,209,222,231,245,262],"overall":[89,226],"efficacy":[91],"remains":[92],"relatively":[93],"overlooked.":[94],"It":[95],"is":[96,195],"non-trivial":[97],"optimize":[99],"data-loading":[100,165],"applications":[103,123,208,243],"that":[104,254],"need":[105],"intensive":[106],"central":[107],"unit":[109],"(CPU)":[110],"input/output":[112],"(I/O)":[113],"resources":[114,203,270],"process":[116],"enormous":[117],"data.":[119],"When":[120],"are":[124],"deployed":[125],"a":[127,139,174,215,235,239,258,263],"system":[128],"(e.g.,":[129],"Cloud":[130],"High-Performance":[132],"Computing":[133],"(HPC)":[134],"system),":[135],"lack":[137],"practical":[140],"efficient":[142],"technique":[143],"data-loader":[145,212],"allocation":[146,213],"incurs":[147],"idleness":[149],"degrades":[151],"throughput.":[154,170,228],"Therefore,":[155],"our":[156],"work":[157],"first":[158],"focuses":[159],"investigating":[161],"impact":[163],"global":[168],"We":[171,229],"then":[172],"propose":[173],"throughput":[175,182,260],"prediction":[176],"model":[177],"predict":[179],"maximum":[181],"individual":[185],"application.":[188],"By":[189],"leveraging":[190],"predicted":[192],"results,":[193],"A-Dloader":[194,233,255],"designed":[196],"dynamically":[198],"allocate":[199],"CPU":[200],"I/O":[202],"concurrently":[205],"running":[206],"use":[210],"knob":[216],"reduce":[218],"idle":[220],"intervals":[221],"thus":[223],"improve":[224],"implement":[230],"evaluate":[232],"framework":[237],"series":[240],"arriving":[244],"completing":[246],"runtime.":[249],"Our":[250],"experimental":[251],"results":[252],"show":[253],"achieve":[257],"28.9%":[259],"improvement":[261,266],"10%":[264],"makespan":[265],"compared":[267],"with":[268],"allocating":[269],"evenly":[271],"applications.":[273]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}