{"id":"https://openalex.org/W4388662073","doi":"https://doi.org/10.1145/3581784.3607042","title":"Mirage: Towards Low-interruption Services on Batch GPU Clusters with Reinforcement Learning","display_name":"Mirage: Towards Low-interruption Services on Batch GPU Clusters with Reinforcement Learning","publication_year":2023,"publication_date":"2023-11-11","ids":{"openalex":"https://openalex.org/W4388662073","doi":"https://doi.org/10.1145/3581784.3607042"},"language":"en","primary_location":{"id":"doi:10.1145/3581784.3607042","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581784.3607042","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581784.3607042","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","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/10.1145/3581784.3607042","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103088798","display_name":"Q.L. Ding","orcid":"https://orcid.org/0009-0003-8695-0145"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Qiyang Ding","raw_affiliation_strings":["University of Texas at Austin, Austin, United States of America"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, United States of America","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106479642","display_name":"Pengfei Zheng","orcid":"https://orcid.org/0009-0004-8498-2749"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pengfei Zheng","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, United States of America"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, United States of America","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092346422","display_name":"Shreyas Kudari","orcid":"https://orcid.org/0009-0005-3612-4093"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shreyas Kudari","raw_affiliation_strings":["University of Texas at Austin, Austin, United States of America"],"affiliations":[{"raw_affiliation_string":"University of Texas at Austin, Austin, United States of America","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082710354","display_name":"Shivaram Venkataraman","orcid":"https://orcid.org/0000-0001-9575-7935"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shivaram Venkataraman","raw_affiliation_strings":["University of Wisconsin-Madison, Madison, United States of America"],"affiliations":[{"raw_affiliation_string":"University of Wisconsin-Madison, Madison, United States of America","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100422982","display_name":"Zhao Zhang","orcid":"https://orcid.org/0000-0001-5921-0035"},"institutions":[{"id":"https://openalex.org/I4388891828","display_name":"Texas Advanced Computing Center","ror":"https://ror.org/00xg4bh43","country_code":null,"type":"facility","lineage":["https://openalex.org/I4388891828","https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhao Zhang","raw_affiliation_strings":["Texas Advanced Computing Center (TACC), Austin, United States of America"],"affiliations":[{"raw_affiliation_string":"Texas Advanced Computing Center (TACC), Austin, United States of America","institution_ids":["https://openalex.org/I4388891828"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103088798"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":1.359,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.85985942,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.998199999332428,"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":0.998199999332428,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9955000281333923,"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/T13553","display_name":"Age of Information Optimization","score":0.9947999715805054,"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":0.7897784113883972},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7646888494491577},{"id":"https://openalex.org/keywords/generality","display_name":"Generality","score":0.7234802842140198},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5348725914955139},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5176480412483215},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.5135231614112854},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45875218510627747},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3995194435119629},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3587748408317566}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7897784113883972},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7646888494491577},{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.7234802842140198},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5348725914955139},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5176480412483215},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.5135231614112854},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45875218510627747},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3995194435119629},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3587748408317566},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581784.3607042","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581784.3607042","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581784.3607042","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3581784.3607042","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3581784.3607042","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3581784.3607042","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Decent work and economic growth","score":0.5699999928474426,"id":"https://metadata.un.org/sdg/8"}],"awards":[{"id":"https://openalex.org/G1736414626","display_name":null,"funder_award_id":"2112606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8767938004","display_name":null,"funder_award_id":"OAC-2112606","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4388662073.pdf","grobid_xml":"https://content.openalex.org/works/W4388662073.grobid-xml"},"referenced_works_count":21,"referenced_works":["https://openalex.org/W1596936080","https://openalex.org/W1982262386","https://openalex.org/W2068238590","https://openalex.org/W2075914362","https://openalex.org/W2076995567","https://openalex.org/W2126020875","https://openalex.org/W2145339207","https://openalex.org/W2159714423","https://openalex.org/W2295598076","https://openalex.org/W2674963269","https://openalex.org/W2767897789","https://openalex.org/W2780624097","https://openalex.org/W2902907165","https://openalex.org/W2968986602","https://openalex.org/W3018990562","https://openalex.org/W3104062568","https://openalex.org/W3129362935","https://openalex.org/W3177828909","https://openalex.org/W3180201702","https://openalex.org/W4213019189","https://openalex.org/W4287757595"],"related_works":["https://openalex.org/W2045049461","https://openalex.org/W4381094582","https://openalex.org/W1978893398","https://openalex.org/W1977906818","https://openalex.org/W2201908702","https://openalex.org/W2369625323","https://openalex.org/W2364579609","https://openalex.org/W1522139108","https://openalex.org/W2353528968","https://openalex.org/W2032776242"],"abstract_inverted_index":{"Accommodating":[0],"long-running":[1],"deep":[2],"learning":[3,82,85],"(DL)":[4],"training":[5],"and":[6,39,53,76,83,94,115,149],"inference":[7],"jobs":[8,38,153],"is":[9],"challenging":[10],"on":[11,43,161],"GPU":[12,103],"clusters":[13],"that":[14,57,132,141],"use":[15],"traditional":[16],"batch":[17,37],"schedulers,":[18],"such":[19],"as":[20],"Slurm.":[21],"Given":[22],"fixed":[23],"wall":[24],"clock":[25],"time":[26],"limits,":[27],"DL":[28],"researchers":[29],"usually":[30],"need":[31],"to":[32],"run":[33],"a":[34,73,78,110,128],"sequence":[35],"of":[36,72,80,112,152],"experience":[40],"long":[41],"interruptions":[42,47],"overloaded":[44],"machines.":[45],"Such":[46],"significantly":[48],"lower":[49],"the":[50,64,70,113,121,134,142,162],"research":[51],"productivity":[52],"QoS":[54],"for":[55],"services":[56],"are":[58],"deployed":[59],"in":[60],"production.":[61],"To":[62],"mitigate":[63],"issues":[65],"from":[66,101],"interruption,":[67],"we":[68,105],"propose":[69],"design":[71],"proactive":[74],"provisioner":[75,131],"investigate":[77],"set":[79],"statistical":[81],"reinforcement":[84],"(RL)":[86],"techniques,":[87],"including":[88],"random":[89],"forest,":[90],"xgboost,":[91],"Deep":[92],"Q-Network,":[93],"policy":[95],"gradient.":[96],"Using":[97],"production":[98],"job":[99],"traces":[100],"three":[102,163],"clusters,":[104],"train":[106],"each":[107],"model":[108],"using":[109,120],"subset":[111],"trace":[114],"then":[116],"evaluate":[117],"their":[118],"generality":[119],"remaining":[122],"validation":[123],"subset.":[124],"We":[125],"introduce":[126],"Mirage,":[127],"Slurm-compatible":[129],"resource":[130],"integrates":[133],"candidate":[135],"ML":[136],"methods.":[137],"Our":[138],"experiments":[139],"show":[140],"Mirage":[143],"can":[144],"reduce":[145],"interruption":[146,156],"by":[147],"17--100%":[148],"safeguard":[150],"23%-76%":[151],"with":[154],"zero":[155],"across":[157],"varying":[158],"load":[159],"levels":[160],"clusters.":[164]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}