{"id":"https://openalex.org/W3170658679","doi":"https://doi.org/10.1109/tc.2021.3084407","title":"AEML: An Acceleration Engine for Multi-GPU Load-balancing in Distributed Heterogeneous Environment","display_name":"AEML: An Acceleration Engine for Multi-GPU Load-balancing in Distributed Heterogeneous Environment","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3170658679","doi":"https://doi.org/10.1109/tc.2021.3084407","mag":"3170658679"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2021.3084407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2021.3084407","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","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/A5008574161","display_name":"Zhuo Tang","orcid":"https://orcid.org/0000-0001-9081-8153"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zhuo Tang","raw_affiliation_strings":["College of information Science and Engineering, Hunan university, Changsha, Hunan province, China, 410082 (e-mail: ztang@hnu.edu.cn)"],"affiliations":[{"raw_affiliation_string":"College of information Science and Engineering, Hunan university, Changsha, Hunan province, China, 410082 (e-mail: ztang@hnu.edu.cn)","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062552066","display_name":"Lifan Du","orcid":null},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lifan Du","raw_affiliation_strings":["College of Computer Science and Electronic Engineering, Hunan University, 12569 Changsha, Hunan, China, (e-mail: dulifan@hnu.edu.cn)"],"affiliations":[{"raw_affiliation_string":"College of Computer Science and Electronic Engineering, Hunan University, 12569 Changsha, Hunan, China, (e-mail: dulifan@hnu.edu.cn)","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100646177","display_name":"Xuedong Zhang","orcid":"https://orcid.org/0000-0003-2456-2342"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuedong Zhang","raw_affiliation_strings":["Hunan University, Hunan University College of Computer Science and Electronic Engineering, 534789 Changsha, Hunan, China, 410082 (e-mail: zxd@hnu.edu.cn)"],"affiliations":[{"raw_affiliation_string":"Hunan University, Hunan University College of Computer Science and Electronic Engineering, 534789 Changsha, Hunan, China, 410082 (e-mail: zxd@hnu.edu.cn)","institution_ids":["https://openalex.org/I16609230"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101863951","display_name":"Li Yang","orcid":"https://orcid.org/0000-0002-8929-7554"},"institutions":[{"id":"https://openalex.org/I56934997","display_name":"Changsha University of Science and Technology","ror":"https://ror.org/03yph8055","country_code":"CN","type":"education","lineage":["https://openalex.org/I56934997"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Yang","raw_affiliation_strings":["College of Computer and Communication Engineering, Changsha University of Science and Technology, 12418 Changsha, Hunan, China, (e-mail: yanglixt@126.com)"],"affiliations":[{"raw_affiliation_string":"College of Computer and Communication Engineering, Changsha University of Science and Technology, 12418 Changsha, Hunan, China, (e-mail: yanglixt@126.com)","institution_ids":["https://openalex.org/I56934997"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078793726","display_name":"Kenli Li","orcid":"https://orcid.org/0000-0002-2635-7716"},"institutions":[{"id":"https://openalex.org/I16609230","display_name":"Hunan University","ror":"https://ror.org/05htk5m33","country_code":"CN","type":"education","lineage":["https://openalex.org/I16609230"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kenli Li","raw_affiliation_strings":["College of Information Science and Engineering, Hunan unversity, Changsha, Hunan, China, 410082 (e-mail: lkl@hnu.edu.cn)"],"affiliations":[{"raw_affiliation_string":"College of Information Science and Engineering, Hunan unversity, Changsha, Hunan, China, 410082 (e-mail: lkl@hnu.edu.cn)","institution_ids":["https://openalex.org/I16609230"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5008574161"],"corresponding_institution_ids":["https://openalex.org/I16609230"],"apc_list":null,"apc_paid":null,"fwci":5.5081,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.95890053,"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":"1"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9995999932289124,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9993000030517578,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9955999851226807,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8848692178726196},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6539690494537354},{"id":"https://openalex.org/keywords/load-balancing","display_name":"Load balancing (electrical power)","score":0.6474358439445496},{"id":"https://openalex.org/keywords/symmetric-multiprocessor-system","display_name":"Symmetric multiprocessor system","score":0.6255162954330444},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5812146663665771},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5743283033370972},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5702930092811584},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.5161022543907166},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.4812564551830292},{"id":"https://openalex.org/keywords/computer-cluster","display_name":"Computer cluster","score":0.45055297017097473},{"id":"https://openalex.org/keywords/distributed-computing-environment","display_name":"Distributed Computing Environment","score":0.42813464999198914},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.42255792021751404},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4127231538295746},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.4104878604412079},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.18815726041793823},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.11243888735771179},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.10386219620704651}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8848692178726196},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6539690494537354},{"id":"https://openalex.org/C138959212","wikidata":"https://www.wikidata.org/wiki/Q1806783","display_name":"Load balancing (electrical power)","level":3,"score":0.6474358439445496},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.6255162954330444},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5812146663665771},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5743283033370972},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5702930092811584},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.5161022543907166},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.4812564551830292},{"id":"https://openalex.org/C29140674","wikidata":"https://www.wikidata.org/wiki/Q206637","display_name":"Computer cluster","level":2,"score":0.45055297017097473},{"id":"https://openalex.org/C3739613","wikidata":"https://www.wikidata.org/wiki/Q679003","display_name":"Distributed Computing Environment","level":2,"score":0.42813464999198914},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.42255792021751404},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4127231538295746},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4104878604412079},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.18815726041793823},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.11243888735771179},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.10386219620704651},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2021.3084407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2021.3084407","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1502544429","https://openalex.org/W1964981582","https://openalex.org/W1984296775","https://openalex.org/W1992245639","https://openalex.org/W1994001225","https://openalex.org/W2025388037","https://openalex.org/W2059959080","https://openalex.org/W2060312180","https://openalex.org/W2084115832","https://openalex.org/W2103838950","https://openalex.org/W2139605600","https://openalex.org/W2173213060","https://openalex.org/W2414493891","https://openalex.org/W2482213519","https://openalex.org/W2517766082","https://openalex.org/W2521121845","https://openalex.org/W2523064693","https://openalex.org/W2541249444","https://openalex.org/W2577308859","https://openalex.org/W2584612194","https://openalex.org/W2728765559","https://openalex.org/W2741639990","https://openalex.org/W2767064019","https://openalex.org/W2783772867","https://openalex.org/W2975712713","https://openalex.org/W3124352525","https://openalex.org/W4248767818","https://openalex.org/W6754818105","https://openalex.org/W6759814162"],"related_works":["https://openalex.org/W2533382481","https://openalex.org/W1981821074","https://openalex.org/W3037515626","https://openalex.org/W4394633758","https://openalex.org/W2151156597","https://openalex.org/W2122178759","https://openalex.org/W2968530953","https://openalex.org/W2375309128","https://openalex.org/W2537242250","https://openalex.org/W2371048081"],"abstract_inverted_index":{"For":[0],"the":[1,39,43,46,58,117,169,185],"rapid":[2],"growth":[3],"computation":[4],"requirements":[5],"in":[6,63,77],"big":[7],"data":[8],"and":[9,90,109,146,162,190],"artificial":[10],"intelligence":[11],"area,":[12],"CPU-GPU":[13],"heterogeneous":[14,79,96,101,196],"clusters":[15],"can":[16,82,114,182],"provide":[17],"more":[18],"powerful":[19],"computing":[20,32,40,186],"capacity":[21,41],"compared":[22],"to":[23],"CPU":[24],"clusters.":[25],"The":[26,152],"number":[27],"of":[28,42,48,57,119,154,171,188],"GPUs":[29,85,108,189],"on":[30,106,159],"single":[31],"node":[33],"is":[34,54,157],"scalable,":[35],"which":[36,113],"greatly":[37],"improves":[38],"cluster":[44,50],"under":[45],"condition":[47],"limited":[49],"size.":[51],"However,":[52],"there":[53],"a":[55,100,128,133,139,147],"lack":[56],"effective":[59],"load-balancing":[60,76],"scheduling":[61,144],"model":[62,104,123],"multi-GPU":[64,75],"hardware":[65],"environment.":[66,80],"This":[67],"paper":[68],"proposes":[69],"AEML,":[70],"an":[71],"acceleration":[72],"engine":[73],"for":[74],"distributed":[78,87],"AEML":[81,155,172,181],"effectively":[83,115],"integrate":[84],"into":[86],"processing":[88],"framework":[89],"achieve":[91,191],"great":[92,192],"load-balance":[93,193],"among":[94,194],"multiple":[95,107,110,120,174,195],"GPUs.":[97,121,197],"We":[98,166],"propose":[99],"task":[102,130,143],"execution":[103],"based":[105,158],"streams":[111,149],"(MGMS),":[112],"balance":[116],"workload":[118],"MGMS":[122],"utilizes":[124],"four":[125],"core":[126],"techniques:":[127],"fine-grained":[129],"mapping":[131],"mechanism,":[132],"device":[134],"resource":[135],"unified":[136],"management":[137],"scheme,":[138],"novel":[140],"resource-aware":[141],"GPU":[142],"strategy":[145],"feedback-based":[148],"adjustment":[150],"scheme.":[151],"implementation":[153],"system":[156],"Spark":[160],"2.4.1":[161],"NVIDIA":[163],"CUDA":[164],"10.0.":[165],"comprehensively":[167],"evaluate":[168],"performance":[170],"with":[173],"typical":[175],"benchmarks.":[176],"Experimental":[177],"results":[178],"show":[179],"that":[180],"fully":[183],"exploit":[184],"power":[187]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}