{"id":"https://openalex.org/W4408049809","doi":"https://doi.org/10.1145/3710848.3710863","title":"SGDRC: Software-Defined Dynamic Resource Control for Concurrent DNN Inference on NVIDIA GPUs","display_name":"SGDRC: Software-Defined Dynamic Resource Control for Concurrent DNN Inference on NVIDIA GPUs","publication_year":2025,"publication_date":"2025-02-28","ids":{"openalex":"https://openalex.org/W4408049809","doi":"https://doi.org/10.1145/3710848.3710863"},"language":"en","primary_location":{"id":"doi:10.1145/3710848.3710863","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3710848.3710863","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3710848.3710863","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","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/10.1145/3710848.3710863","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yongkang Zhang","orcid":"https://orcid.org/0000-0002-4745-3176"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Yongkang Zhang","raw_affiliation_strings":["HKUST, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-4745-3176","affiliations":[{"raw_affiliation_string":"HKUST, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Haoxuan Yu","orcid":"https://orcid.org/0009-0008-9677-7960"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Haoxuan Yu","raw_affiliation_strings":["HKUST, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0008-9677-7960","affiliations":[{"raw_affiliation_string":"HKUST, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108121442","display_name":"Chenxia Han","orcid":null},"institutions":[{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chenxia Han","raw_affiliation_strings":["CUHK, Hong Kong, China"],"raw_orcid":"https://orcid.org/0009-0006-3301-3811","affiliations":[{"raw_affiliation_string":"CUHK, Hong Kong, China","institution_ids":["https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100522990","display_name":"Cheng Wang","orcid":"https://orcid.org/0000-0002-4232-4746"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng Wang","raw_affiliation_strings":["Alibaba Group, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-4232-4746","affiliations":[{"raw_affiliation_string":"Alibaba Group, Shenzhen, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038360007","display_name":"Baotong Lu","orcid":"https://orcid.org/0000-0002-0230-1048"},"institutions":[{"id":"https://openalex.org/I4210113369","display_name":"Microsoft Research Asia (China)","ror":"https://ror.org/0300m5276","country_code":"CN","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4210113369"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Baotong Lu","raw_affiliation_strings":["Microsoft Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0230-1048","affiliations":[{"raw_affiliation_string":"Microsoft Research, Beijing, China","institution_ids":["https://openalex.org/I4210113369"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101919549","display_name":"Yunzhe Li","orcid":"https://orcid.org/0000-0002-5073-5561"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunzhe Li","raw_affiliation_strings":["China University of Geosciences, Wuhan, China","Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5073-5561","affiliations":[{"raw_affiliation_string":"China University of Geosciences, Wuhan, China","institution_ids":["https://openalex.org/I3124059619"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031038452","display_name":"Zhifeng Jiang","orcid":"https://orcid.org/0000-0002-7024-441X"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhifeng Jiang","raw_affiliation_strings":["HKUST, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-7024-441X","affiliations":[{"raw_affiliation_string":"HKUST, Hong Kong, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100319866","display_name":"Li Yang","orcid":"https://orcid.org/0000-0002-9337-1382"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]},{"id":"https://openalex.org/I3124059619","display_name":"China University of Geosciences","ror":"https://ror.org/04gcegc37","country_code":"CN","type":"education","lineage":["https://openalex.org/I3124059619"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Li","raw_affiliation_strings":["China University of Geosciences, Wuhan, China","Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9337-1382","affiliations":[{"raw_affiliation_string":"China University of Geosciences, Wuhan, China","institution_ids":["https://openalex.org/I3124059619"]},{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100730785","display_name":"Xiaowen Chu","orcid":"https://orcid.org/0000-0001-9745-4372"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Xiaowen Chu","raw_affiliation_strings":["HKUST (Guangzhou), Guangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9745-4372","affiliations":[{"raw_affiliation_string":"HKUST (Guangzhou), Guangzhou, China","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002675628","display_name":"Huaicheng Li","orcid":"https://orcid.org/0000-0002-3155-0203"},"institutions":[{"id":"https://openalex.org/I859038795","display_name":"Virginia Tech","ror":"https://ror.org/02smfhw86","country_code":"US","type":"education","lineage":["https://openalex.org/I859038795"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huaicheng Li","raw_affiliation_strings":["Virginia Tech, Blacksburg, USA"],"raw_orcid":"https://orcid.org/0000-0002-3155-0203","affiliations":[{"raw_affiliation_string":"Virginia Tech, Blacksburg, USA","institution_ids":["https://openalex.org/I859038795"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":10,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.7398,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.92559903,"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":"267","last_page":"281"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.994700014591217,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.994700014591217,"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/T10761","display_name":"Vehicular Ad Hoc Networks (VANETs)","score":0.9932000041007996,"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"}},{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9847999811172485,"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":0.8121774196624756},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6180429458618164},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.5170053243637085},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.47389426827430725},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4560298025608063},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.44850340485572815},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.44567278027534485},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.37376219034194946},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3733212351799011},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19851049780845642},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.06952372193336487}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8121774196624756},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6180429458618164},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5170053243637085},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.47389426827430725},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4560298025608063},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.44850340485572815},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.44567278027534485},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.37376219034194946},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3733212351799011},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19851049780845642},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.06952372193336487}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3710848.3710863","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3710848.3710863","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3710848.3710863","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-148051","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-148051","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"doi:10.1145/3710848.3710863","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3710848.3710863","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3710848.3710863","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4408049809.pdf"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1506474685","https://openalex.org/W1954144304","https://openalex.org/W1968391520","https://openalex.org/W2054495773","https://openalex.org/W2163687928","https://openalex.org/W2194775991","https://openalex.org/W2296602564","https://openalex.org/W2566356404","https://openalex.org/W2604787577","https://openalex.org/W2751343396","https://openalex.org/W2786171709","https://openalex.org/W2885579974","https://openalex.org/W2908906661","https://openalex.org/W2918317383","https://openalex.org/W2933406884","https://openalex.org/W2954698171","https://openalex.org/W2963446712","https://openalex.org/W3037807633","https://openalex.org/W3122286897","https://openalex.org/W3158398662","https://openalex.org/W3208777667","https://openalex.org/W4280607375","https://openalex.org/W4289828024","https://openalex.org/W4308374170","https://openalex.org/W4312199201","https://openalex.org/W4318541666","https://openalex.org/W4360831842","https://openalex.org/W4381885923","https://openalex.org/W4383988581","https://openalex.org/W4386076400","https://openalex.org/W4387321503","https://openalex.org/W4388858680","https://openalex.org/W4391013532","https://openalex.org/W4392538976","https://openalex.org/W4402048557"],"related_works":["https://openalex.org/W2055243143","https://openalex.org/W1986418932","https://openalex.org/W2357796999","https://openalex.org/W4321636575","https://openalex.org/W2741131631","https://openalex.org/W2045526782","https://openalex.org/W4405841813","https://openalex.org/W2156919374","https://openalex.org/W1483472507","https://openalex.org/W1984019423"],"abstract_inverted_index":{"Cloud":[0],"service":[1],"providers":[2],"heavily":[3],"colocate":[4],"high-priority,":[5],"latency":[6],"sensitive":[7],"(LS),":[8],"and":[9,46,83,87],"low-priority,":[10],"best-effort":[11],"(BE)":[12],"DNN":[13],"inference":[14],"services":[15],"on":[16,39],"the":[17,28,40,84,97],"same":[18],"GPU":[19,31,56,123],"to":[20,65,69,105,112,120],"improve":[21],"resource":[22,57,99,116],"utilization":[23],"in":[24],"data":[25],"centers.":[26],"Among":[27],"critical":[29],"shared":[30],"resources,":[32],"there":[33],"has":[34],"been":[35],"very":[36],"limited":[37],"analysis":[38],"dynamic":[41],"allocation":[42],"of":[43,94],"compute":[44],"units":[45],"VRAM":[47,80,88],"bandwidth,":[48],"mainly":[49],"for":[50,79],"two":[51],"reasons:":[52],"(1)":[53],"The":[54],"native":[55],"management":[58],"solutions":[59],"are":[60,91],"either":[61,107],"hardware-specific,":[62],"or":[63,72,114],"unable":[64],"dynamically":[66],"allocate":[67],"resources":[68],"different":[70],"tenants,":[71],"both;":[73],"(2)":[74],"NVIDIA":[75],"doesn't":[76],"expose":[77],"interfaces":[78],"bandwidth":[81],"allocation,":[82],"software":[85],"stack":[86],"channel":[89],"architectures":[90],"black-box,":[92],"both":[93],"which":[95],"limit":[96],"software-level":[98],"management.":[100],"These":[101],"drive":[102],"prior":[103],"work":[104],"design":[106],"conservative":[108],"sharing":[109],"policies":[110],"detrimental":[111],"throughput,":[113],"static":[115],"partitioning":[117],"only":[118],"applicable":[119],"a":[121],"few":[122],"models.":[124]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
