{"id":"https://openalex.org/W4392543698","doi":"https://doi.org/10.1109/tetci.2024.3369628","title":"Scalable Heterogeneous Scheduling Based Model Parallelism for Real-Time Inference of Large-Scale Deep Neural Networks","display_name":"Scalable Heterogeneous Scheduling Based Model Parallelism for Real-Time Inference of Large-Scale Deep Neural Networks","publication_year":2024,"publication_date":"2024-03-07","ids":{"openalex":"https://openalex.org/W4392543698","doi":"https://doi.org/10.1109/tetci.2024.3369628"},"language":"en","primary_location":{"id":"doi:10.1109/tetci.2024.3369628","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2024.3369628","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"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 Emerging Topics in Computational Intelligence","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/A5071736086","display_name":"Xiaofeng Zou","orcid":"https://orcid.org/0000-0002-5823-6345"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Zou","raw_affiliation_strings":["School of Future Technology, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-5823-6345","affiliations":[{"raw_affiliation_string":"School of Future Technology, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100622590","display_name":"Cen Chen","orcid":"https://orcid.org/0000-0003-1389-0148"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cen Chen","raw_affiliation_strings":["School of Future Technology, South China University of Technology, Guangzhou, China","Pazhou Laboratory, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0003-1389-0148","affiliations":[{"raw_affiliation_string":"School of Future Technology, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"Pazhou Laboratory, Guangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084211536","display_name":"Pei-Ying Lin","orcid":"https://orcid.org/0000-0002-8118-9700"},"institutions":[{"id":"https://openalex.org/I4610292","display_name":"Xiangtan University","ror":"https://ror.org/00xsfaz62","country_code":"CN","type":"education","lineage":["https://openalex.org/I4610292"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peiying Lin","raw_affiliation_strings":["School of Computer Science & School of Cyberspace Science, Xiangtan University (XTU), Xiangtan, China"],"raw_orcid":"https://orcid.org/0000-0002-8118-9700","affiliations":[{"raw_affiliation_string":"School of Computer Science & School of Cyberspace Science, Xiangtan University (XTU), Xiangtan, China","institution_ids":["https://openalex.org/I4610292"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021959086","display_name":"Luochuan Zhang","orcid":"https://orcid.org/0009-0004-6301-7843"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luochuan Zhang","raw_affiliation_strings":["School of Future Technology, South China University of Technology, Guangzhou, China"],"raw_orcid":"https://orcid.org/0009-0004-6301-7843","affiliations":[{"raw_affiliation_string":"School of Future Technology, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010906829","display_name":"Yanwu Xu","orcid":"https://orcid.org/0000-0002-1779-931X"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwu Xu","raw_affiliation_strings":["School of Future Technology, South China University of Technology, Guangzhou, China","Pazhou Laboratory, Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-1779-931X","affiliations":[{"raw_affiliation_string":"School of Future Technology, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]},{"raw_affiliation_string":"Pazhou Laboratory, Guangzhou, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100385495","display_name":"Wenjie Zhang","orcid":"https://orcid.org/0000-0001-5949-0268"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wenjie Zhang","raw_affiliation_strings":["Department of Electrical Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-5949-0268","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, The Hong Kong Polytechnic University, Kowloon, Hong Kong","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.2219,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.81378758,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"8","issue":"4","first_page":"2962","last_page":"2973"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9153000116348267,"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"}},"topics":[{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9153000116348267,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9053999781608582,"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":0.7907721996307373},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6838270425796509},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.607322096824646},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5347778797149658},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5193020701408386},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.49650293588638306},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4434373080730438},{"id":"https://openalex.org/keywords/data-parallelism","display_name":"Data parallelism","score":0.42313092947006226},{"id":"https://openalex.org/keywords/parallelism","display_name":"Parallelism (grammar)","score":0.41620194911956787},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36598166823387146},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.32113102078437805},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.07606199383735657},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.06533265113830566}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7907721996307373},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6838270425796509},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.607322096824646},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5347778797149658},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5193020701408386},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49650293588638306},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4434373080730438},{"id":"https://openalex.org/C61483411","wikidata":"https://www.wikidata.org/wiki/Q3124522","display_name":"Data parallelism","level":3,"score":0.42313092947006226},{"id":"https://openalex.org/C2781172179","wikidata":"https://www.wikidata.org/wiki/Q853109","display_name":"Parallelism (grammar)","level":2,"score":0.41620194911956787},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36598166823387146},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.32113102078437805},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.07606199383735657},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.06533265113830566},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tetci.2024.3369628","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tetci.2024.3369628","pdf_url":null,"source":{"id":"https://openalex.org/S4210210251","display_name":"IEEE Transactions on Emerging Topics in Computational Intelligence","issn_l":"2471-285X","issn":["2471-285X"],"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 Emerging Topics in Computational Intelligence","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8413847059","display_name":null,"funder_award_id":"x2wjD2230230","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"}],"funders":[{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W2057108708","https://openalex.org/W2065689629","https://openalex.org/W2118953734","https://openalex.org/W2149294210","https://openalex.org/W2194775991","https://openalex.org/W2343962288","https://openalex.org/W2565516711","https://openalex.org/W2728444714","https://openalex.org/W2792063935","https://openalex.org/W2883867401","https://openalex.org/W2896457183","https://openalex.org/W2904688592","https://openalex.org/W2950865323","https://openalex.org/W2954427512","https://openalex.org/W2962711501","https://openalex.org/W2970155754","https://openalex.org/W3005070048","https://openalex.org/W3014807190","https://openalex.org/W3014810041","https://openalex.org/W3088609916","https://openalex.org/W3113399930","https://openalex.org/W3114160010","https://openalex.org/W3132015947","https://openalex.org/W3175937250","https://openalex.org/W3206019042","https://openalex.org/W3213228850","https://openalex.org/W4280641199","https://openalex.org/W4288089799","https://openalex.org/W4311301302","https://openalex.org/W4365420394","https://openalex.org/W4385245566","https://openalex.org/W6637373629","https://openalex.org/W6738144653","https://openalex.org/W6739917289","https://openalex.org/W6748687944","https://openalex.org/W6751627690","https://openalex.org/W6753584990","https://openalex.org/W6754777574","https://openalex.org/W6756718674","https://openalex.org/W6766225098","https://openalex.org/W6769627184","https://openalex.org/W6778729859","https://openalex.org/W6778883912","https://openalex.org/W6780239866","https://openalex.org/W6780805062","https://openalex.org/W7065064605"],"related_works":["https://openalex.org/W2950520577","https://openalex.org/W1554644772","https://openalex.org/W2003935582","https://openalex.org/W2494130044","https://openalex.org/W3170887803","https://openalex.org/W74409296","https://openalex.org/W3209384898","https://openalex.org/W1595834484","https://openalex.org/W1991844655","https://openalex.org/W2593878938"],"abstract_inverted_index":{"Scaling":[0],"up":[1],"the":[2,12,17,26,33,41,56,63,120,139,191,206,219,226],"capacity":[3,57],"of":[4,11,36,58,66,112,123,156,194,208,221],"deep":[5],"neural":[6],"networks":[7],"(DNN)":[8],"is":[9,61,225],"one":[10],"effective":[13],"approaches":[14,210],"to":[15,79,132,137,160,184],"improve":[16],"model":[18,75,107,140,237],"quality":[19],"for":[20,109,158,181,236,243],"several":[21],"different":[22],"DNN-based":[23],"applications,":[24],"making":[25],"DNN":[27,195,216,246],"models":[28,60],"continuously":[29],"grow.":[30],"To":[31,169,218],"promote":[32],"execution":[34,192],"efficiency":[35],"large":[37],"and":[38,49,130,164,199,214,233,239],"complex":[39],"models,":[40,196],"devices":[42],"are":[43],"becoming":[44],"increasingly":[45],"heterogeneous":[46,116,134,182],"with":[47],"CPUs":[48],"domain-specific":[50],"hardware":[51],"accelerators.":[52],"In":[53,100],"many":[54],"cases,":[55],"large-scale":[59,113,162,215,245],"beyond":[62],"memory":[64,200],"limit":[65],"a":[67,81,154,174],"single":[68],"accelerator.":[69],"Recent":[70],"work":[71,228],"has":[72],"shown":[73],"that":[74,147,229],"parallelism,":[76,238],"which":[77],"aims":[78],"partition":[80,141,177],"DNN's":[82],"computational":[83],"graph":[84],"on":[85,105,115],"multiple":[86],"devices,":[87],"can":[88],"not":[89],"only":[90],"address":[91,185],"this":[92,101,170],"problem":[93],"while":[94],"also":[95],"provide":[96],"significant":[97],"performance":[98],"improvements.":[99],"work,":[102],"we":[103,144,172],"focus":[104],"optimizing":[106],"parallelism":[108],"timely":[110],"inference":[111],"DNNs":[114,124],"processors.":[117],"We":[118,204],"transform":[119],"computation":[121,167],"graphs":[122,128],"into":[125,202],"directed":[126],"acyclic":[127],"(DAGs)":[129],"propose":[131,173],"utilize":[133],"scheduling":[135,151,179,232],"methods":[136,152,235],"determine":[138],"plan.":[142],"Nevertheless,":[143],"have":[145,153,165],"found":[146],"current":[148],"efficient":[149],"DAG":[150,176,231],"lot":[155],"room":[157],"improvement":[159],"process":[161],"DAGs":[163],"high":[166,197],"complexity.":[168],"end,":[171],"scalable":[175],"assisted":[178],"method":[180],"processors":[183],"these":[186],"problems.":[187],"Our":[188],"approach":[189],"takes":[190],"time":[193],"scalability,":[198],"constraints":[201],"consideration.":[203],"demonstrate":[205],"effectiveness":[207],"our":[209,222],"using":[211],"both":[212],"small-":[213],"models.":[217],"best":[220],"knowledge,":[223],"it":[224],"first":[227],"explores":[230],"partitioning":[234],"provides":[240],"new":[241],"avenues":[242],"accelerating":[244],"inference.":[247]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}