{"id":"https://openalex.org/W4411800487","doi":"https://doi.org/10.1109/ccgrid64434.2025.00066","title":"Energy Efficient Scheduling of AI/ML Workloads on Multi Instance Gpus with Dynamic Repartitioning","display_name":"Energy Efficient Scheduling of AI/ML Workloads on Multi Instance Gpus with Dynamic Repartitioning","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4411800487","doi":"https://doi.org/10.1109/ccgrid64434.2025.00066"},"language":"en","primary_location":{"id":"doi:10.1109/ccgrid64434.2025.00066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccgrid64434.2025.00066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 25th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2606.25082","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5118706987","display_name":"Ellie Lipe","orcid":null},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ellie Lipe","raw_affiliation_strings":["Columbia University,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University,New York,USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086017439","display_name":"Neel Karia","orcid":"https://orcid.org/0000-0003-2751-9526"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neel Karia","raw_affiliation_strings":["Columbia University,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University,New York,USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021442818","display_name":"Connor Espenshade","orcid":"https://orcid.org/0000-0002-8318-2596"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Connor Espenshade","raw_affiliation_strings":["Columbia University,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University,New York,USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054641291","display_name":"Clifford Stein","orcid":"https://orcid.org/0000-0002-0614-6620"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Clifford Stein","raw_affiliation_strings":["Columbia University,New York,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Columbia University,New York,USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056044784","display_name":"Asser Tantawi","orcid":"https://orcid.org/0000-0001-6598-8863"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Asser Tantawi","raw_affiliation_strings":["IBM TJ Watson Research Center,Yorktown Heights,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center,Yorktown Heights,USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086114919","display_name":"Olivier Tardieu","orcid":"https://orcid.org/0000-0002-8377-6757"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Olivier Tardieu","raw_affiliation_strings":["IBM TJ Watson Research Center,Yorktown Heights,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IBM TJ Watson Research Center,Yorktown Heights,USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.8743,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.96271123,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"53","last_page":"62"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9952999949455261,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9952999949455261,"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":0.9937000274658203,"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":0.9926999807357788,"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":0.7275412678718567},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6636672019958496},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5661218166351318},{"id":"https://openalex.org/keywords/processor-scheduling","display_name":"Processor scheduling","score":0.4315219521522522},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.42310184240341187},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4071559011936188},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.33033448457717896},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.30715546011924744},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.1300012469291687}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7275412678718567},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6636672019958496},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5661218166351318},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.4315219521522522},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.42310184240341187},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4071559011936188},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.33033448457717896},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.30715546011924744},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.1300012469291687},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/ccgrid64434.2025.00066","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ccgrid64434.2025.00066","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 25th International Symposium on Cluster, Cloud and Internet Computing (CCGrid)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2606.25082","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.25082","pdf_url":"https://arxiv.org/pdf/2606.25082","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2606.25082","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.25082","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2606.25082","is_oa":true,"landing_page_url":"https://arxiv.org/abs/2606.25082","pdf_url":"https://arxiv.org/pdf/2606.25082","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.8899999856948853}],"awards":[],"funders":[{"id":"https://openalex.org/F4320307762","display_name":"International Business Machines Corporation","ror":"https://ror.org/05hh8d621"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4411800487.pdf","grobid_xml":"https://content.openalex.org/works/W4411800487.grobid-xml"},"referenced_works_count":22,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W2052362679","https://openalex.org/W2128130220","https://openalex.org/W2546571074","https://openalex.org/W2982625995","https://openalex.org/W3089811425","https://openalex.org/W3092885859","https://openalex.org/W3103559770","https://openalex.org/W3196963192","https://openalex.org/W3200486361","https://openalex.org/W3207530029","https://openalex.org/W4287889735","https://openalex.org/W4289828024","https://openalex.org/W4293025059","https://openalex.org/W4304192541","https://openalex.org/W4366564134","https://openalex.org/W4386707690","https://openalex.org/W4388855507","https://openalex.org/W4394945061","https://openalex.org/W6802095294","https://openalex.org/W6842315983","https://openalex.org/W7067822191"],"related_works":["https://openalex.org/W1809394610","https://openalex.org/W2128410848","https://openalex.org/W2118368532","https://openalex.org/W2014085448","https://openalex.org/W2102390841","https://openalex.org/W3047653192","https://openalex.org/W2096289371","https://openalex.org/W2126232624","https://openalex.org/W2434525066","https://openalex.org/W3140149227"],"abstract_inverted_index":{"Increasing":[0],"demand":[1],"from":[2,80],"AI/ML":[3],"workloads":[4],"is":[5,62],"exacerbating":[6],"the":[7,33,81,91,93,98,112,192,232],"rising":[8],"energy":[9,218],"consumption":[10,219],"of":[11,194,217,231],"data":[12,36,187],"centers.":[13],"Recent":[14],"advances":[15],"in":[16,27,42,51,55,90],"hardware":[17],"such":[18],"as":[19,83,85,142],"NVIDIA's":[20],"Multi":[21],"Instance":[22],"GPUs":[23],"(MIGs)":[24],"offer":[25],"improvements":[26],"flexibility":[28],"and":[29,32,115,127,161,206,220,243],"computational":[30],"power":[31],"opportunity":[34],"for":[35,65,97,138,241],"centers":[37],"to":[38,118,145,171,213],"manage":[39],"incoming":[40],"jobs":[41],"energy-efficient":[43],"ways,":[44],"while":[45],"maintaining":[46],"acceptable":[47],"performance.":[48],"The":[49],"challenge":[50],"achieving":[52],"this":[53],"multi-objective":[54,147,215],"a":[56,66,78,102,133,139,143,146,163,176,180,214,239],"MIG":[57,68,104,141],"environment":[58],"through":[59],"job":[60,79,94],"scheduling":[61,74,100,136,150,159],"multi-faceted.":[63],"Firstly,":[64],"given":[67],"configuration,":[69],"one":[70],"seeks":[71],"an":[72],"easy-toimplement":[73],"algorithm":[75,198],"which":[76,88],"selects":[77],"queue":[82,236],"well":[84],"decides":[86],"on":[87,185],"slice":[89],"configuration":[92,105],"runs.":[95],"Secondly,":[96],"identified":[99],"algorithm,":[101],"particular":[103],"may":[106,116],"not":[107],"always":[108],"be":[109,119],"suitable":[110],"(as":[111],"workload":[113,182],"fluctuates)":[114],"need":[117],"repartitioned.":[120],"We":[121,131],"tackle":[122],"both":[123],"problems":[124],"using":[125,179],"simulations":[126],"reinforcement":[128,169],"learning":[129,170],"(RL).":[130],"present":[132],"dynamic":[134,173,196],"repartitioning":[135,174,197,201],"framework":[137],"single":[140],"solution":[144],"heterogeneous":[148],"machine":[149],"problem":[151],"with":[152],"preemption.":[153],"In":[154],"particular,":[155],"we":[156,167,190],"compare":[157],"four":[158],"algorithms":[160],"identify":[162],"promising":[164],"one.":[165],"Then,":[166],"employ":[168],"perform":[172],"over":[175,199],"day.":[177],"Furthermore,":[178],"diurnal":[181],"pattern":[183],"based":[184],"real-world":[186],"center":[188],"traces,":[189],"demonstrate":[191],"superiority":[193],"our":[195],"twice-daily":[200],"(26%),":[202],"static":[203],"partitioning":[204,208],"(31%)":[205],"no":[207],"at":[209,228],"all":[210],"(68%)":[211],"according":[212],"function":[216],"tardiness.":[221],"Our":[222],"results":[223],"indicate":[224],"specific":[225],"preferred":[226],"configurations":[227],"different":[229,235],"times":[230],"day":[233],"under":[234],"conditions,":[237],"suggesting":[238],"policy":[240],"predictive":[242],"automatic":[244],"reconfiguration.":[245]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}