{"id":"https://openalex.org/W4404787801","doi":"https://doi.org/10.1145/3652892.3654792","title":"Optimal Resource Efficiency with Fairness in Heterogeneous GPU Clusters","display_name":"Optimal Resource Efficiency with Fairness in Heterogeneous GPU Clusters","publication_year":2024,"publication_date":"2024-11-27","ids":{"openalex":"https://openalex.org/W4404787801","doi":"https://doi.org/10.1145/3652892.3654792"},"language":"en","primary_location":{"id":"doi:10.1145/3652892.3654792","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652892.3654792","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652892.3654792?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th International Middleware Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3652892.3654792?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005355007","display_name":"Zizhao Mo","orcid":"https://orcid.org/0000-0002-3590-4400"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":true,"raw_author_name":"Zizhao Mo","raw_affiliation_strings":["University of Macau, Macau, Macao"],"raw_orcid":"https://orcid.org/0000-0002-3590-4400","affiliations":[{"raw_affiliation_string":"University of Macau, Macau, Macao","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017636962","display_name":"Huanle Xu","orcid":"https://orcid.org/0000-0001-6657-1154"},"institutions":[{"id":"https://openalex.org/I204512498","display_name":"University of Macau","ror":"https://ror.org/01r4q9n85","country_code":"MO","type":"education","lineage":["https://openalex.org/I204512498"]}],"countries":["MO"],"is_corresponding":false,"raw_author_name":"Huanle Xu","raw_affiliation_strings":["University of Macau, Macau, Macao"],"raw_orcid":"https://orcid.org/0000-0001-6657-1154","affiliations":[{"raw_affiliation_string":"University of Macau, Macau, Macao","institution_ids":["https://openalex.org/I204512498"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020413351","display_name":"Wing Cheong Lau","orcid":"https://orcid.org/0000-0003-1179-7855"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Wing Cheong Lau","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-1179-7855","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005355007"],"corresponding_institution_ids":["https://openalex.org/I204512498"],"apc_list":null,"apc_paid":null,"fwci":6.714,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.96884297,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"36","last_page":"48"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9986000061035156,"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":0.9986000061035156,"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":0.9983000159263611,"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/T12288","display_name":"Optimization and Search Problems","score":0.9975000023841858,"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":0.7351188659667969},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.5231220126152039},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.48812779784202576},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.433645099401474},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.4327489733695984},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3348351716995239},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3298981487751007},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.12753060460090637}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7351188659667969},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.5231220126152039},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.48812779784202576},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.433645099401474},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.4327489733695984},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3348351716995239},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3298981487751007},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.12753060460090637}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3652892.3654792","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652892.3654792","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652892.3654792?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th International Middleware Conference","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3652892.3654792","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3652892.3654792","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3652892.3654792?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 25th International Middleware Conference","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.5899999737739563,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320311133","display_name":"United Mitochondrial Disease Foundation","ror":"https://ror.org/0528q0t18"},{"id":"https://openalex.org/F4320322841","display_name":"Universidade de Macau","ror":"https://ror.org/01r4q9n85"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4404787801.pdf"},"referenced_works_count":39,"referenced_works":["https://openalex.org/W1670635083","https://openalex.org/W1890643295","https://openalex.org/W1969844906","https://openalex.org/W1987354455","https://openalex.org/W2013901835","https://openalex.org/W2022678927","https://openalex.org/W2056830486","https://openalex.org/W2073440460","https://openalex.org/W2104338317","https://openalex.org/W2109488193","https://openalex.org/W2123878303","https://openalex.org/W2124827397","https://openalex.org/W2128426273","https://openalex.org/W2171872428","https://openalex.org/W2219413783","https://openalex.org/W2339906866","https://openalex.org/W2548213059","https://openalex.org/W2562160379","https://openalex.org/W2612690371","https://openalex.org/W2808563793","https://openalex.org/W2910100551","https://openalex.org/W2910737461","https://openalex.org/W2912720049","https://openalex.org/W2919594608","https://openalex.org/W2963150697","https://openalex.org/W2982356264","https://openalex.org/W3022298203","https://openalex.org/W3022548332","https://openalex.org/W3080999573","https://openalex.org/W3145843217","https://openalex.org/W3154142431","https://openalex.org/W3197816522","https://openalex.org/W4236974103","https://openalex.org/W4237645939","https://openalex.org/W4245843336","https://openalex.org/W4285212262","https://openalex.org/W6727321242","https://openalex.org/W6739901393","https://openalex.org/W6784871562"],"related_works":["https://openalex.org/W2012954338","https://openalex.org/W2392023973","https://openalex.org/W2056717482","https://openalex.org/W3189307731","https://openalex.org/W1428699136","https://openalex.org/W2949962288","https://openalex.org/W2364686214","https://openalex.org/W2030707850","https://openalex.org/W2096672917","https://openalex.org/W2005148983"],"abstract_inverted_index":{"Ensuring":[0],"the":[1],"highest":[2],"training":[3,20,36],"throughput":[4],"to":[5],"maximize":[6],"resource":[7],"efficiency,":[8],"while":[9],"maintaining":[10],"fairness":[11,32,56],"among":[12],"users,":[13],"is":[14],"critical":[15],"for":[16],"deep":[17],"learning":[18],"(DL)":[19],"in":[21],"heterogeneous":[22,43],"GPU":[23],"clusters.":[24],"However,":[25],"current":[26],"DL":[27],"schedulers":[28],"provide":[29],"only":[30],"limited":[31],"properties":[33],"and":[34,55],"suboptimal":[35],"throughput,":[37],"impeding":[38],"tenants":[39],"from":[40,50],"effectively":[41],"leveraging":[42],"resources.":[44],"The":[45],"underlying":[46],"design":[47],"challenge":[48],"stems":[49],"inherent":[51],"conflicts":[52],"between":[53],"efficiency":[54],"properties.":[57]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7}],"updated_date":"2026-03-11T06:11:40.159057","created_date":"2025-10-10T00:00:00"}