{"id":"https://openalex.org/W4313229743","doi":"https://doi.org/10.1109/tpds.2022.3232715","title":"<i>iGniter:</i> Interference-Aware GPU Resource Provisioning for Predictable DNN Inference in the Cloud","display_name":"<i>iGniter:</i> Interference-Aware GPU Resource Provisioning for Predictable DNN Inference in the Cloud","publication_year":2022,"publication_date":"2022-12-28","ids":{"openalex":"https://openalex.org/W4313229743","doi":"https://doi.org/10.1109/tpds.2022.3232715"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2022.3232715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3232715","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5029626585","display_name":"Fei Xu","orcid":"https://orcid.org/0000-0003-1590-5323"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Fei Xu","raw_affiliation_strings":["Shanghai Key Laboratory of Multidimensional Information Processing, School of Computer Science and Technology, East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing, School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037914022","display_name":"Jianian Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianian Xu","raw_affiliation_strings":["Shanghai Key Laboratory of Multidimensional Information Processing, School of Computer Science and Technology, East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing, School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017575617","display_name":"Jiabin Chen","orcid":"https://orcid.org/0000-0002-4790-5873"},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiabin Chen","raw_affiliation_strings":["Shanghai Key Laboratory of Multidimensional Information Processing, School of Computer Science and Technology, East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing, School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100379221","display_name":"Li Chen","orcid":"https://orcid.org/0000-0002-2300-6996"},"institutions":[{"id":"https://openalex.org/I79516672","display_name":"University of Louisiana at Lafayette","ror":"https://ror.org/01x8rc503","country_code":"US","type":"education","lineage":["https://openalex.org/I2799628689","https://openalex.org/I79516672"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Li Chen","raw_affiliation_strings":["School of Computing and Informatics, University of Louisiana at Lafayette, Lafayette, LA, USA"],"affiliations":[{"raw_affiliation_string":"School of Computing and Informatics, University of Louisiana at Lafayette, Lafayette, LA, USA","institution_ids":["https://openalex.org/I79516672"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039055026","display_name":"Ruitao Shang","orcid":null},"institutions":[{"id":"https://openalex.org/I66867065","display_name":"East China Normal University","ror":"https://ror.org/02n96ep67","country_code":"CN","type":"education","lineage":["https://openalex.org/I66867065"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruitao Shang","raw_affiliation_strings":["Shanghai Key Laboratory of Multidimensional Information Processing, School of Computer Science and Technology, East China Normal University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Key Laboratory of Multidimensional Information Processing, School of Computer Science and Technology, East China Normal University, Shanghai, China","institution_ids":["https://openalex.org/I66867065"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760218","display_name":"Zhi Zhou","orcid":"https://orcid.org/0000-0002-0987-9344"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhi Zhou","raw_affiliation_strings":["Guangdong Key Laboratory of Big Data Analysis and Processing, School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong Province, China"],"affiliations":[{"raw_affiliation_string":"Guangdong Key Laboratory of Big Data Analysis and Processing, School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong Province, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048398271","display_name":"Fangming Liu","orcid":"https://orcid.org/0000-0002-8570-1345"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]},{"id":"https://openalex.org/I47720641","display_name":"Huazhong University of Science and Technology","ror":"https://ror.org/00p991c53","country_code":"CN","type":"education","lineage":["https://openalex.org/I47720641"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fangming Liu","raw_affiliation_strings":["Peng Cheng Laboratory, Shenzhen, Guangdong Province, China","Huazhong University of Science and Technology, Wuhan, Hubei, China"],"affiliations":[{"raw_affiliation_string":"Peng Cheng Laboratory, Shenzhen, Guangdong Province, China","institution_ids":["https://openalex.org/I4210136793"]},{"raw_affiliation_string":"Huazhong University of Science and Technology, Wuhan, Hubei, China","institution_ids":["https://openalex.org/I47720641"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5029626585"],"corresponding_institution_ids":["https://openalex.org/I66867065"],"apc_list":null,"apc_paid":null,"fwci":4.2259,"has_fulltext":false,"cited_by_count":42,"citation_normalized_percentile":{"value":0.9554044,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"34","issue":"3","first_page":"812","last_page":"827"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8857787251472473},{"id":"https://openalex.org/keywords/provisioning","display_name":"Provisioning","score":0.8506801128387451},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.821049690246582},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6769634485244751},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.46096158027648926},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.4138583540916443},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2609217166900635},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.18175330758094788},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16687393188476562}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8857787251472473},{"id":"https://openalex.org/C172191483","wikidata":"https://www.wikidata.org/wiki/Q1071806","display_name":"Provisioning","level":2,"score":0.8506801128387451},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.821049690246582},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6769634485244751},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.46096158027648926},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.4138583540916443},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2609217166900635},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.18175330758094788},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16687393188476562},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2022.3232715","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2022.3232715","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"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":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1595545560","https://openalex.org/W1968205029","https://openalex.org/W1980489165","https://openalex.org/W2071519731","https://openalex.org/W2108598243","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2461411193","https://openalex.org/W2604319603","https://openalex.org/W2604514113","https://openalex.org/W2618530766","https://openalex.org/W2918317383","https://openalex.org/W2962745591","https://openalex.org/W2963149401","https://openalex.org/W2982157693","https://openalex.org/W3020531607","https://openalex.org/W3097411828","https://openalex.org/W3106250896","https://openalex.org/W3133174490","https://openalex.org/W3157306683","https://openalex.org/W3200486361","https://openalex.org/W3209166877","https://openalex.org/W3210776666","https://openalex.org/W3214476430","https://openalex.org/W4206943884","https://openalex.org/W4214512541","https://openalex.org/W4214540558","https://openalex.org/W4214690606","https://openalex.org/W4231332361","https://openalex.org/W6611382325","https://openalex.org/W6635630268","https://openalex.org/W6637373629","https://openalex.org/W6730956707","https://openalex.org/W6757364461","https://openalex.org/W6766433103","https://openalex.org/W6779103662","https://openalex.org/W6798686915","https://openalex.org/W6802095294"],"related_works":["https://openalex.org/W2893779165","https://openalex.org/W2017432143","https://openalex.org/W1973694374","https://openalex.org/W4244478748","https://openalex.org/W2983574358","https://openalex.org/W2370475531","https://openalex.org/W4385924768","https://openalex.org/W2785227142","https://openalex.org/W572531444","https://openalex.org/W2945962340"],"abstract_inverted_index":{"GPUs":[0,24,76],"are":[1,143],"essential":[2],"to":[3,87,146,237,242],"accelerating":[4],"the":[5,119,137,148,161,175,193,218,232,243],"latency-sensitive":[6],"deep":[7],"neural":[8],"network":[9],"(DNN)":[10],"inference":[11,28,43,54,64,83,117,132,171,183,196,223],"workloads":[12,29,224],"in":[13,118,240],"cloud":[14],"datacenters.":[15],"To":[16],"fully":[17],"utilize":[18],"GPU":[19,34,57,79,108,154,162,201,245],"resources,":[20],"<i>spatial":[21],"sharing</i>":[22,74],"of":[23,52,75,124,177,181,189,221],"among":[25,41],"co-located":[26,42],"DNN":[27,53,116,131,182,209,222],"becomes":[30],"increasingly":[31],"compelling.":[32],"However,":[33],"sharing":[35],"inevitably":[36],"brings":[37],"<i>severe":[38],"performance":[39,65,92,133,149,172,180,219],"interference</i>":[40],"workloads,":[44],"as":[45],"motivated":[46],"by":[47,235],"an":[48,106],"empirical":[49],"measurement":[50],"study":[51],"on":[55,62,71,169,192,199,206],"EC2":[56,200],"instances.":[58,202],"While":[59],"existing":[60],"works":[61],"guaranteeing":[63],"service":[66],"level":[67],"objectives":[68],"(SLOs)":[69],"focus":[70],"either":[72],"<i>temporal":[73],"or":[77],"<i>reactive</i>":[78],"resource":[80,109,155,163,246],"scaling":[81],"and":[82,139,165,211],"migration":[84],"techniques,":[85],"how":[86],"<i>proactively</i>":[88],"mitigate":[89],"such":[90],"severe":[91],"interference":[93],"has":[94],"received":[95],"comparatively":[96],"little":[97],"attention.":[98],"In":[99],"this":[100],"paper,":[101],"we":[102],"propose":[103],"<i>iGniter</i>":[104,121,190,215],",":[105],"<i>interference-aware</i>":[107],"provisioning":[110,156,247],"framework":[111],"for":[112],"cost-efficiently":[113],"achieving":[114,178],"predictable":[115,179],"cloud.":[120],"is":[122],"comprised":[123],"two":[125],"key":[126],"components:":[127],"(1)":[128],"a":[129,187],"<i>lightweight</i>":[130],"model,":[134,173],"which":[135],"leverages":[136],"system":[138],"workload":[140],"metrics":[141],"that":[142,158,214],"practically":[144,226],"accessible":[145],"capture":[147],"interference;":[150],"(2)":[151],"A":[152],"<i>cost-efficient</i>":[153],"strategy":[157],"<i>jointly</i>":[159],"optimizes":[160],"allocation":[164],"adaptive":[166],"batching":[167],"based":[168,191],"our":[170],"with":[174,225],"aim":[176],"workloads.":[184],"We":[185],"implement":[186],"prototype":[188,204],"NVIDIA":[194],"Triton":[195],"server":[197],"hosted":[198],"Extensive":[203],"experiments":[205],"four":[207],"representative":[208],"models":[210],"datasets":[212],"demonstrate":[213],"can":[216],"guarantee":[217],"SLOs":[220],"acceptable":[227],"runtime":[228],"overhead,":[229],"while":[230],"saving":[231],"monetary":[233],"cost":[234],"up":[236],"<inline-formula><tex-math":[238],"notation=\"LaTeX\">$25\\%$</tex-math></inline-formula>":[239],"comparison":[241],"state-of-the-art":[244],"strategies.":[248]},"counts_by_year":[{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":22},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}