{"id":"https://openalex.org/W2480662436","doi":"https://doi.org/10.1109/ipdps.2016.73","title":"Mystic: Predictive Scheduling for GPU Based Cloud Servers Using Machine Learning","display_name":"Mystic: Predictive Scheduling for GPU Based Cloud Servers Using Machine Learning","publication_year":2016,"publication_date":"2016-05-01","ids":{"openalex":"https://openalex.org/W2480662436","doi":"https://doi.org/10.1109/ipdps.2016.73","mag":"2480662436"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2016.73","doi":"https://doi.org/10.1109/ipdps.2016.73","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2016.73","pdf_url":null,"source":{"id":"https://openalex.org/S4210174069","display_name":"IEEE International Parallel and Distributed Processing Symposium (IPDPS)","issn_l":"1530-2075","issn":["1530-2075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-2","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5019687323","display_name":"Yash Ukidave","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yash Ukidave","raw_affiliation_strings":["Department of Electrical & Computer Engineering, Northeastern University, Boston, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering, Northeastern University, Boston, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100460314","display_name":"Xiangyu Li","orcid":"https://orcid.org/0000-0002-4226-1255","observed_orcids":["https://orcid.org/0000-0002-4226-1255","https://orcid.org/0009-0006-8784-8697"]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiangyu Li","raw_affiliation_strings":["Department of Electrical & Computer Engineering, Northeastern University, Boston, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering, Northeastern University, Boston, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061128237","display_name":"David R Kaeli","orcid":"https://orcid.org/0000-0002-5692-0151","observed_orcids":["https://orcid.org/0000-0002-5692-0151"]},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Kaeli","raw_affiliation_strings":["Department of Electrical & Computer Engineering, Northeastern University, Boston, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical & Computer Engineering, Northeastern University, Boston, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":4.9155,"has_fulltext":false,"cited_by_count":65,"citation_normalized_percentile":{"value":0.96142362,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"353","last_page":"362"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.7422000169754028,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.7422000169754028,"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"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.18930000066757202,"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":0.05490000173449516,"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/gpu-scheduling","display_name":"GPU scheduling","score":0.8619999885559082},{"id":"https://openalex.org/keywords/interference-aware-scheduling","display_name":"interference-aware scheduling","score":0.7950000166893005},{"id":"https://openalex.org/keywords/resource-contention","display_name":"resource contention","score":0.6629999876022339},{"id":"https://openalex.org/keywords/collaborative-filtering","display_name":"collaborative filtering","score":0.8500000238418579},{"id":"https://openalex.org/keywords/cloud-server","display_name":"cloud server","score":0.6790000200271606},{"id":"https://openalex.org/keywords/gpu-clusters","display_name":"GPU clusters","score":0.8790000081062317},{"id":"https://openalex.org/keywords/system-throughput","display_name":"system throughput","score":0.7720000147819519},{"id":"https://openalex.org/keywords/gpu-utilization","display_name":"GPU utilization","score":0.6420000195503235}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8626794815063477},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6960633993148804},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.6904086470603943},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.5853400230407715},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5322076678276062},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5164427757263184},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4652586579322815},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.45095789432525635},{"id":"https://openalex.org/C2781335571","wikidata":"https://www.wikidata.org/wiki/Q2633544","display_name":"GPU cluster","level":3,"score":0.43315330147743225},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.39676666259765625},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3552705645561218},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3307255208492279},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18406793475151062},{"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:10.1109/ipdps.2016.73","doi":"https://doi.org/10.1109/ipdps.2016.73","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2016.73","pdf_url":null,"source":{"id":"https://openalex.org/S4210174069","display_name":"IEEE International Parallel and Distributed Processing Symposium (IPDPS)","issn_l":"1530-2075","issn":["1530-2075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","jufo-2","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Parallel and Distributed Processing Symposium (IPDPS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1580293593","https://openalex.org/W1630733292","https://openalex.org/W1651324627","https://openalex.org/W1667652561","https://openalex.org/W1713367009","https://openalex.org/W1972645849","https://openalex.org/W1980731865","https://openalex.org/W1981426552","https://openalex.org/W1996212904","https://openalex.org/W2005574683","https://openalex.org/W2019659243","https://openalex.org/W2038662769","https://openalex.org/W2054141820","https://openalex.org/W2067231500","https://openalex.org/W2078994750","https://openalex.org/W2097643185","https://openalex.org/W2102709380","https://openalex.org/W2103981209","https://openalex.org/W2119222363","https://openalex.org/W2121893797","https://openalex.org/W2124861237","https://openalex.org/W2126118553","https://openalex.org/W2128120785","https://openalex.org/W2129381159","https://openalex.org/W2149234156","https://openalex.org/W2159094788","https://openalex.org/W2166942589","https://openalex.org/W2169150754","https://openalex.org/W2273440736","https://openalex.org/W2341535507","https://openalex.org/W3112784795","https://openalex.org/W4235366964","https://openalex.org/W4285719527","https://openalex.org/W6703949738"],"related_works":["https://openalex.org/W2765903126","https://openalex.org/W3090549252","https://openalex.org/W3095283736","https://openalex.org/W3164445276","https://openalex.org/W3094153456","https://openalex.org/W7123580574","https://openalex.org/W7221035877","https://openalex.org/W3205296744","https://openalex.org/W7124766782","https://openalex.org/W3175847870"],"abstract_inverted_index":{"GPUs":[0,27],"have":[1],"become":[2],"the":[3,23,40,45,79,127,152,168,174,179,183,191,231,243],"primary":[4],"choice":[5],"of":[6,19,37,63,112,124,129,203,230],"accelerators":[7],"for":[8,26,34,76,85,109,133,209,228],"high-end":[9],"data":[10],"centers":[11],"and":[12,65,98,117,173,177,185,198,250],"cloud":[13,118],"servers,":[14],"which":[15,53,93],"can":[16,94],"host":[17],"thousands":[18],"disparate":[20],"applications.":[21,137,233],"With":[22],"growing":[24],"demands":[25],"on":[28,39,114,214,248,255],"clusters,":[29,87],"there":[30],"arises":[31],"a":[32,140,215,252],"need":[33],"efficient":[35,110],"co-execution":[36,111],"applications":[38,50,64,113,161,172,208],"same":[41],"accelerator":[42],"device.":[43],"However,":[44],"resource":[46],"contention":[47],"among":[48],"co-executing":[49,158],"causes":[51],"interference":[52,135,153,184],"leads":[54],"to":[55,144,151,181],"degradation":[56],"in":[57,257],"execution":[58],"performance,":[59],"impacts":[60],"QoS":[61],"requirements":[62],"lowers":[66],"overall":[67],"system":[68,187,244],"throughput.":[69,188],"While":[70],"previous":[71],"work":[72],"has":[73],"proposed":[74],"techniques":[75],"detecting":[77,134],"interference,":[78],"existing":[80],"solutions":[81],"are":[82],"either":[83],"developed":[84],"CPU":[86],"or":[88],"use":[89,128],"static":[90],"profiling":[91],"approaches":[92],"be":[95],"computationally":[96],"intensive":[97],"do":[99],"not":[100],"scale":[101],"well.":[102],"We":[103,138,189],"present":[104],"Mystic,":[105],"an":[106,146],"interference-aware":[107],"scheduler":[108,180],"GPU-based":[115],"clusters":[116],"servers.":[119],"The":[120],"most":[121],"important":[122],"feature":[123],"Mystic":[125,166,211,241],"is":[126,212],"learning-based":[130],"analytical":[131],"models":[132],"between":[136,170],"leverage":[139],"collaborative":[141],"filtering":[142],"framework":[143,224],"characterize":[145],"incoming":[147],"application":[148],"with":[149,159,194,219,236],"respect":[150],"it":[154],"may":[155],"cause":[156],"when":[157],"other":[160],"while":[162],"sharing":[163],"GPU":[164,207,217,258],"resources.":[165],"identifies":[167],"similarities":[169],"new":[171],"executing":[175],"applications,":[176,197],"guides":[178],"minimize":[182],"improve":[186],"train":[190],"learning":[192],"model":[193],"42":[195],"CUDA":[196],"consider":[199],"another":[200],"separate":[201],"set":[202],"55":[204],"diverse,":[205],"real-world":[206],"evaluation.":[210],"evaluated":[213,232],"live":[216],"cluster":[218],"32":[220],"NVIDIA":[221],"GPUs.":[222],"Our":[223],"achieves":[225,251],"performance":[226],"guarantees":[227],"90.3%":[229],"When":[234],"compared":[235],"state-of-the":[237],"art":[238],"interference-oblivious":[239],"schedulers,":[240],"improves":[242],"throughput":[245],"by":[246],"27.5%":[247],"average,":[249],"16.3%":[253],"improvement":[254],"average":[256],"utilization.":[259]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":5}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2016-08-23T00:00:00"}