{"id":"https://openalex.org/W4402044606","doi":"https://doi.org/10.1145/3625549.3658654","title":"ElasticRoom: Multi-Tenant DNN Inference Engine via Co-design with Resource-constrained Compilation and Strong Priority Scheduling","display_name":"ElasticRoom: Multi-Tenant DNN Inference Engine via Co-design with Resource-constrained Compilation and Strong Priority Scheduling","publication_year":2024,"publication_date":"2024-06-03","ids":{"openalex":"https://openalex.org/W4402044606","doi":"https://doi.org/10.1145/3625549.3658654"},"language":"en","primary_location":{"id":"doi:10.1145/3625549.3658654","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3625549.3658654","pdf_url":null,"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 33rd International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.1145/3625549.3658654","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5093960327","display_name":"Lixian Ma","orcid":"https://orcid.org/0009-0007-1081-0356"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Lixian Ma","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033803498","display_name":"H.Z. Chen","orcid":"https://orcid.org/0009-0008-0634-6842"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoruo Chen","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027464011","display_name":"En Shao","orcid":"https://orcid.org/0000-0002-9678-7228"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"En Shao","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035662158","display_name":"Leping Wang","orcid":"https://orcid.org/0009-0009-4940-5598"},"institutions":[{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Leping Wang","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100377840","display_name":"Quan Chen","orcid":"https://orcid.org/0000-0001-5832-0347"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Chen","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5006750799","display_name":"Guangming Tan","orcid":"https://orcid.org/0000-0002-6361-5948"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangming Tan","raw_affiliation_strings":["State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"State Key Lab of Processors, Institute of Computing Technology, CAS, Beijing, China","institution_ids":["https://openalex.org/I4210090176"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5093960327"],"corresponding_institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.5263,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.65339678,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"14"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9933000206947327,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.9901999831199646,"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":0.7614398002624512},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6080089211463928},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5406820774078369},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.43071994185447693},{"id":"https://openalex.org/keywords/inference-engine","display_name":"Inference engine","score":0.41470810770988464},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.14267900586128235},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.14228561520576477}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7614398002624512},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6080089211463928},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5406820774078369},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.43071994185447693},{"id":"https://openalex.org/C46743427","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference engine","level":3,"score":0.41470810770988464},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.14267900586128235},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.14228561520576477},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3625549.3658654","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3625549.3658654","pdf_url":null,"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 33rd International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3625549.3658654","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3625549.3658654","pdf_url":null,"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 33rd International Symposium on High-Performance Parallel and Distributed Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2044656908","display_name":null,"funder_award_id":"Z211100002121143","funder_id":"https://openalex.org/F4320334978","funder_display_name":"Beijing Nova Program"},{"id":"https://openalex.org/G5338259777","display_name":null,"funder_award_id":"20220484217","funder_id":"https://openalex.org/F4320334978","funder_display_name":"Beijing Nova Program"}],"funders":[{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W95608104","https://openalex.org/W2150851481","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2323693848","https://openalex.org/W2565600385","https://openalex.org/W2605178034","https://openalex.org/W2734941459","https://openalex.org/W2804032941","https://openalex.org/W2891285910","https://openalex.org/W2914209329","https://openalex.org/W2954698171","https://openalex.org/W2963037989","https://openalex.org/W2982157693","https://openalex.org/W3011377185","https://openalex.org/W3033527233","https://openalex.org/W3035582633","https://openalex.org/W3097411828","https://openalex.org/W3125923813","https://openalex.org/W3133730715","https://openalex.org/W3186368531","https://openalex.org/W3208777667","https://openalex.org/W3209449653","https://openalex.org/W3217445637","https://openalex.org/W4200579819","https://openalex.org/W4214512541","https://openalex.org/W4220914069","https://openalex.org/W4242709165","https://openalex.org/W4251637954","https://openalex.org/W4281932226","https://openalex.org/W4312641748","https://openalex.org/W4318541538","https://openalex.org/W4360831842","https://openalex.org/W4387321091","https://openalex.org/W6739901393","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W2057057690","https://openalex.org/W2368184788","https://openalex.org/W2358964818","https://openalex.org/W2359535128","https://openalex.org/W2381332051","https://openalex.org/W2321443665","https://openalex.org/W2375699995","https://openalex.org/W2043719711","https://openalex.org/W2140069467","https://openalex.org/W2364072231"],"abstract_inverted_index":{"GPU":[0,52,82,87],"partition":[1,53,83],"mechanisms":[2,54,84],"in":[3,10,39,61,77],"run-time":[4],"software":[5],"have":[6],"been":[7],"widely":[8],"used":[9],"job":[11,92],"scheduler":[12],"and":[13,21,33,55,67,90],"multi-tenant":[14],"computing":[15],"system":[16],"to":[17,85],"improve":[18],"resource":[19,88],"utilization":[20,89],"throughput.":[22],"The":[23,73],"latency":[24,69],"requirements":[25],"of":[26,80],"different":[27],"DNN":[28,47],"requests,":[29,35],"such":[30],"as":[31],"real-time":[32,71],"best-effort":[34],"often":[36],"exhibit":[37],"variations":[38],"computational":[40],"systems":[41],"that":[42],"handle":[43],"batch":[44],"tasks":[45],"for":[46,70],"inference.":[48],"However,":[49],"the":[50,78],"existing":[51,81],"state-of-the-art":[56],"scheduling":[57],"approaches":[58],"face":[59],"challenges":[60],"effectively":[62],"promising":[63],"both":[64],"high":[65],"throughput":[66],"low":[68],"requests.":[72],"current":[74],"limitation":[75],"lies":[76],"inability":[79],"enhance":[86],"ensure":[91],"priority":[93],"simultaneously.":[94]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2025-12-26T23:08:49.675405","created_date":"2025-10-10T00:00:00"}
