{"id":"https://openalex.org/W4400810021","doi":"https://doi.org/10.1109/tpds.2024.3431189","title":"ElasticBatch: A Learning-Augmented Elastic Scheduling System for Batch Inference on MIG","display_name":"ElasticBatch: A Learning-Augmented Elastic Scheduling System for Batch Inference on MIG","publication_year":2024,"publication_date":"2024-07-19","ids":{"openalex":"https://openalex.org/W4400810021","doi":"https://doi.org/10.1109/tpds.2024.3431189"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2024.3431189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2024.3431189","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","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/A5048920164","display_name":"Jiaxing Qi","orcid":"https://orcid.org/0000-0002-9530-2858"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiaxing Qi","raw_affiliation_strings":["Sino-German Joint Software Institute, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-9530-2858","affiliations":[{"raw_affiliation_string":"Sino-German Joint Software Institute, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086945155","display_name":"Wencong Xiao","orcid":"https://orcid.org/0000-0002-3043-522X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wencong Xiao","raw_affiliation_strings":["Alibaba Group, Hangzhou, Zhejiang Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, Zhejiang Province, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5046708261","display_name":"Mingzhen Li","orcid":"https://orcid.org/0000-0002-4115-9072"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingzhen Li","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4115-9072","affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008330044","display_name":"Chaojie Yang","orcid":"https://orcid.org/0000-0002-4382-9965"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaojie Yang","raw_affiliation_strings":["Alibaba Group, Beijing, Chaoyang District, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, Chaoyang District, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100738496","display_name":"Yong Li","orcid":"https://orcid.org/0000-0002-0330-657X"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yong Li","raw_affiliation_strings":["Alibaba Group, Beijing, Chaoyang District, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Beijing, Chaoyang District, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101742150","display_name":"Wei Lin","orcid":"https://orcid.org/0000-0002-9363-6619"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Lin","raw_affiliation_strings":["Alibaba Group, Hangzhou, Zhejiang Province, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, Zhejiang Province, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018705589","display_name":"Hailong Yang","orcid":"https://orcid.org/0000-0003-1101-7927"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hailong Yang","raw_affiliation_strings":["Sino-German Joint Software Institute, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-1101-7927","affiliations":[{"raw_affiliation_string":"Sino-German Joint Software Institute, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I82880672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074183877","display_name":"Zhongzhi Luan","orcid":"https://orcid.org/0000-0002-7186-0556"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongzhi Luan","raw_affiliation_strings":["Sino-German Joint Software Institute, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7186-0556","affiliations":[{"raw_affiliation_string":"Sino-German Joint Software Institute, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I82880672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079362609","display_name":"Depei Qian","orcid":"https://orcid.org/0000-0002-5382-1473"},"institutions":[{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]},{"id":"https://openalex.org/I82880672","display_name":"Beihang University","ror":"https://ror.org/00wk2mp56","country_code":"CN","type":"education","lineage":["https://openalex.org/I82880672"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Depei Qian","raw_affiliation_strings":["Sino-German Joint Software Institute, Beihang University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-5382-1473","affiliations":[{"raw_affiliation_string":"Sino-German Joint Software Institute, Beihang University, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I82880672"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9366,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.75900252,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":98},"biblio":{"volume":"35","issue":"10","first_page":"1708","last_page":"1720"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.8816999793052673,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.8816999793052673,"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/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.8177000284194946,"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/T10603","display_name":"Smart Grid Energy Management","score":0.775600016117096,"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":0.842339277267456},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5922104120254517},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5718095302581787},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3634988069534302},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3596886992454529},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.13000482320785522}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.842339277267456},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5922104120254517},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5718095302581787},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3634988069534302},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3596886992454529},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.13000482320785522},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2024.3431189","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2024.3431189","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4039879177","display_name":null,"funder_award_id":"U23B2020","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5774836301","display_name":"\u9ad8\u6027\u80fd\u3001\u9ad8\u53ef\u6269\u5c55\u548c\u9ad8\u53ef\u79fb\u690d\u7684Stencil\u4ee3\u7801\u751f\u6210\u548c\u4f18\u5316\u6846\u67b6\u7814\u7a76","funder_award_id":"62072018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6139273093","display_name":null,"funder_award_id":"62322201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8014835415","display_name":null,"funder_award_id":"U22A2028","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335793","display_name":"Academic Excellence Foundation of BUAA for PHD Students","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1618905105","https://openalex.org/W1974799041","https://openalex.org/W2003193807","https://openalex.org/W2088794999","https://openalex.org/W2133176659","https://openalex.org/W2194775991","https://openalex.org/W2261059368","https://openalex.org/W2417137833","https://openalex.org/W2805454539","https://openalex.org/W2896457183","https://openalex.org/W2963323070","https://openalex.org/W2965373594","https://openalex.org/W2978017171","https://openalex.org/W2982157693","https://openalex.org/W3010528756","https://openalex.org/W3043571714","https://openalex.org/W3047373174","https://openalex.org/W3059280052","https://openalex.org/W3089718532","https://openalex.org/W3096609285","https://openalex.org/W3166736235","https://openalex.org/W3200486361","https://openalex.org/W4241050402","https://openalex.org/W4293025059","https://openalex.org/W4296079434","https://openalex.org/W4303443398","https://openalex.org/W4312998584","https://openalex.org/W4322718191","https://openalex.org/W4362707064","https://openalex.org/W4385988359","https://openalex.org/W6636501900","https://openalex.org/W6730956707","https://openalex.org/W6755207826","https://openalex.org/W6756009870","https://openalex.org/W6759814162","https://openalex.org/W6766673545","https://openalex.org/W6768851824","https://openalex.org/W6779103662","https://openalex.org/W6802095294","https://openalex.org/W6846002521","https://openalex.org/W6850625674","https://openalex.org/W6851960618"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"As":[0],"deep":[1],"learning":[2],"(DL)":[3],"technologies":[4],"become":[5],"ubiquitous,":[6],"GPU":[7,76,83,108,127],"clusters":[8],"are":[9],"deployed":[10],"for":[11,26],"inference":[12],"tasks":[13],"with":[14],"consistent":[15],"service":[16],"level":[17],"objectives":[18],"(SLOs).":[19],"Efficiently":[20],"utilizing":[21],"multiple":[22],"GPUs":[23],"is":[24],"crucial":[25],"throughput":[27],"and":[28,39,57,93,119,140],"cost-effectiveness.":[29],"This":[30,98],"article":[31],"addresses":[32],"the":[33,102],"challenges":[34,114],"posed":[35,115],"by":[36,85,116],"dynamic":[37,117],"input":[38],"NVIDIA":[40,120],"MIG":[41,80,121],"in":[42,75,112,133,144],"scheduling":[43,50],"DL":[44],"workloads.":[45],"We":[46],"present":[47],"ElasticBatch,":[48],"a":[49,59,72],"system":[51],"that":[52,69],"simplifies":[53],"configuration":[54],"through":[55],"bucketization":[56],"employs":[58],"machine":[60],"learning-based":[61],"pipeline":[62],"to":[63,79,87,101,125],"optimize":[64,126],"settings.":[65],"Our":[66],"experiments":[67],"demonstrate":[68],"ElasticBatch":[70],"achieves":[71],"50%":[73],"reduction":[74],"instances":[77],"compared":[78],"disablement,":[81],"increases":[82],"utilization":[84,106],"1.4%":[86],"6.5%":[88],"over":[89],"an":[90],"ideal":[91],"scheduler":[92],"significantly":[94],"reduces":[95],"profiling":[96],"time.":[97],"research":[99],"contributes":[100],"discourse":[103],"on":[104],"efficient":[105],"of":[107,135],"clusters.":[109],"ElasticBatch's":[110],"effectiveness":[111],"mitigating":[113],"inputs":[118],"underscores":[122],"its":[123],"potential":[124],"cluster":[128],"performance,":[129],"providing":[130],"tangible":[131],"benefits":[132],"terms":[134],"reduced":[136],"instances,":[137],"increased":[138],"utilization,":[139],"significant":[141],"time":[142],"savings":[143],"real-world":[145],"deployment":[146],"scenarios.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}