{"id":"https://openalex.org/W3022298203","doi":"https://doi.org/10.1145/3342195.3387555","title":"Balancing efficiency and fairness in heterogeneous GPU clusters for deep learning","display_name":"Balancing efficiency and fairness in heterogeneous GPU clusters for deep learning","publication_year":2020,"publication_date":"2020-04-15","ids":{"openalex":"https://openalex.org/W3022298203","doi":"https://doi.org/10.1145/3342195.3387555","mag":"3022298203"},"language":"en","primary_location":{"id":"doi:10.1145/3342195.3387555","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3342195.3387555","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fifteenth European Conference on Computer Systems","raw_type":"proceedings-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/A5030635177","display_name":"Shubham Chaudhary","orcid":"https://orcid.org/0000-0003-3800-9310"},"institutions":[{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shubham Chaudhary","raw_affiliation_strings":["Microsoft Research India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research India","institution_ids":["https://openalex.org/I4210124949"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015355530","display_name":"Ramachandran Ramjee","orcid":"https://orcid.org/0000-0003-0007-6040"},"institutions":[{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Ramachandran Ramjee","raw_affiliation_strings":["Microsoft Research India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research India","institution_ids":["https://openalex.org/I4210124949"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049023640","display_name":"Muthian Sivathanu","orcid":"https://orcid.org/0009-0004-6190-9733"},"institutions":[{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Muthian Sivathanu","raw_affiliation_strings":["Microsoft Research India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research India","institution_ids":["https://openalex.org/I4210124949"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060166632","display_name":"Nipun Kwatra","orcid":"https://orcid.org/0000-0003-0354-6204"},"institutions":[{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Nipun Kwatra","raw_affiliation_strings":["Microsoft Research India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research India","institution_ids":["https://openalex.org/I4210124949"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000323931","display_name":"Srinidhi Viswanatha","orcid":null},"institutions":[{"id":"https://openalex.org/I4210124949","display_name":"Microsoft Research (India)","ror":"https://ror.org/02w7f3w92","country_code":"IN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210124949"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Srinidhi Viswanatha","raw_affiliation_strings":["Microsoft Research India"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research India","institution_ids":["https://openalex.org/I4210124949"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":9.6141,"has_fulltext":false,"cited_by_count":134,"citation_normalized_percentile":{"value":0.98435296,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9991000294685364,"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/T11612","display_name":"Stochastic Gradient Optimization Techniques","score":0.9991000294685364,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9980999827384949,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9975000023841858,"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":0.8568821549415588},{"id":"https://openalex.org/keywords/gpu-cluster","display_name":"GPU cluster","score":0.7068506479263306},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.5712152123451233},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.49840831756591797},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.46904855966567993},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3818046748638153},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.3510633409023285},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.15430516004562378}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8568821549415588},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.7068506479263306},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.5712152123451233},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.49840831756591797},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.46904855966567993},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3818046748638153},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3510633409023285},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.15430516004562378},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3342195.3387555","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3342195.3387555","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Fifteenth European Conference on Computer Systems","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Decent work and economic growth","id":"https://metadata.un.org/sdg/8","score":0.4399999976158142}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W1487076132","https://openalex.org/W1493893823","https://openalex.org/W1499798934","https://openalex.org/W1558004581","https://openalex.org/W1890643295","https://openalex.org/W1971326463","https://openalex.org/W2022678927","https://openalex.org/W2055748525","https://openalex.org/W2100830825","https://openalex.org/W2104276806","https://openalex.org/W2105947650","https://openalex.org/W2107403482","https://openalex.org/W2111087562","https://openalex.org/W2121927366","https://openalex.org/W2163961697","https://openalex.org/W2173520492","https://openalex.org/W2194775991","https://openalex.org/W2296335794","https://openalex.org/W2476548250","https://openalex.org/W2508573783","https://openalex.org/W2549139847","https://openalex.org/W2572234696","https://openalex.org/W2576355797","https://openalex.org/W2798515322","https://openalex.org/W2809420642","https://openalex.org/W2899071864","https://openalex.org/W2919594608","https://openalex.org/W2963403751","https://openalex.org/W2995435108","https://openalex.org/W3136172274","https://openalex.org/W3162118826","https://openalex.org/W4241974762","https://openalex.org/W6600349396","https://openalex.org/W6607094058","https://openalex.org/W6634708352"],"related_works":["https://openalex.org/W2082176405","https://openalex.org/W2238531340","https://openalex.org/W2067902980","https://openalex.org/W2017587301","https://openalex.org/W2071296827","https://openalex.org/W1827514603","https://openalex.org/W2030707850","https://openalex.org/W2393232088","https://openalex.org/W2965037703","https://openalex.org/W2086392083"],"abstract_inverted_index":{"We":[0],"present":[1],"Gandivafair,":[2],"a":[3,35],"distributed,":[4],"fair":[5],"share":[6,34],"scheduler":[7,46],"that":[8,47],"balances":[9],"conflicting":[10],"goals":[11],"of":[12],"efficiency":[13],"and":[14],"fairness":[15],"in":[16],"GPU":[17,50],"clusters":[18],"for":[19],"deep":[20],"learning":[21],"training":[22],"(DLT).":[23],"Gandivafair":[24,42],"provides":[25],"performance":[26],"isolation":[27],"between":[28],"users,":[29],"enabling":[30],"multiple":[31],"users":[32],"to":[33],"single":[36],"cluster,":[37],"thus,":[38],"maximizing":[39],"cluster":[40],"efficiency.":[41],"is":[43],"the":[44],"first":[45],"allocates":[48],"cluster-wide":[49],"time":[51],"fairly":[52],"among":[53],"active":[54],"users.":[55]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":33},{"year":2024,"cited_by_count":28},{"year":2023,"cited_by_count":20},{"year":2022,"cited_by_count":30},{"year":2021,"cited_by_count":13},{"year":2020,"cited_by_count":8},{"year":2018,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
