{"id":"https://openalex.org/W7124146323","doi":"https://doi.org/10.1109/icpads67057.2025.11323118","title":"Layer Fusion-Accelerated Online Scheduling for Multi-Tenancy on Heterogeneous DNN Accelerators","display_name":"Layer Fusion-Accelerated Online Scheduling for Multi-Tenancy on Heterogeneous DNN Accelerators","publication_year":2025,"publication_date":"2025-12-14","ids":{"openalex":"https://openalex.org/W7124146323","doi":"https://doi.org/10.1109/icpads67057.2025.11323118"},"language":null,"primary_location":{"id":"doi:10.1109/icpads67057.2025.11323118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5122998527","display_name":"Lei Jia","orcid":null},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Jia","raw_affiliation_strings":["ShanghaiTech University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078879004","display_name":"Zhaojun Ni","orcid":"https://orcid.org/0009-0000-7161-792X"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaojun Ni","raw_affiliation_strings":["ShanghaiTech University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081936534","display_name":"Y. Wang","orcid":"https://orcid.org/0009-0002-8443-8407"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yutong Wang","raw_affiliation_strings":["ShanghaiTech University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085181578","display_name":"Siting Liu","orcid":"https://orcid.org/0000-0002-2454-5561"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Siting Liu","raw_affiliation_strings":["ShanghaiTech University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101615008","display_name":"Chundong Wang","orcid":"https://orcid.org/0000-0001-9069-2650"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chundong Wang","raw_affiliation_strings":["ShanghaiTech University,Shanghai,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ShanghaiTech University,Shanghai,China","institution_ids":["https://openalex.org/I30809798"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I30809798"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.5436999797821045,"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":0.5436999797821045,"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":0.1160999983549118,"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/T14347","display_name":"Big Data and Digital Economy","score":0.08110000193119049,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6827999949455261},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.5748999714851379},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5669000148773193},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4745999872684479},{"id":"https://openalex.org/keywords/quality-of-service","display_name":"Quality of service","score":0.4542999863624573},{"id":"https://openalex.org/keywords/application-layer","display_name":"Application layer","score":0.38769999146461487},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.3831999897956848},{"id":"https://openalex.org/keywords/downtime","display_name":"Downtime","score":0.3379000127315521}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7991999983787537},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6827999949455261},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.5748999714851379},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5669000148773193},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4745999872684479},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4683000147342682},{"id":"https://openalex.org/C5119721","wikidata":"https://www.wikidata.org/wiki/Q220501","display_name":"Quality of service","level":2,"score":0.4542999863624573},{"id":"https://openalex.org/C190793597","wikidata":"https://www.wikidata.org/wiki/Q189768","display_name":"Application layer","level":3,"score":0.38769999146461487},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.3831999897956848},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.3828999996185303},{"id":"https://openalex.org/C180591934","wikidata":"https://www.wikidata.org/wiki/Q1253369","display_name":"Downtime","level":2,"score":0.3379000127315521},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.31769999861717224},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3125},{"id":"https://openalex.org/C31689143","wikidata":"https://www.wikidata.org/wiki/Q733809","display_name":"Fair-share scheduling","level":3,"score":0.310699999332428},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.3028999865055084},{"id":"https://openalex.org/C196921405","wikidata":"https://www.wikidata.org/wiki/Q786431","display_name":"Online algorithm","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2782999873161316},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.2662000060081482},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C20277647","wikidata":"https://www.wikidata.org/wiki/Q5227234","display_name":"Data access layer","level":3,"score":0.25600001215934753},{"id":"https://openalex.org/C2984822820","wikidata":"https://www.wikidata.org/wiki/Q1123036","display_name":"Processor scheduling","level":3,"score":0.2517000138759613},{"id":"https://openalex.org/C12570599","wikidata":"https://www.wikidata.org/wiki/Q2891044","display_name":"Link layer","level":3,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpads67057.2025.11323118","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpads67057.2025.11323118","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 31th International Conference on Parallel and Distributed Systems (ICPADS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.616236686706543}],"awards":[{"id":"https://openalex.org/G1900651086","display_name":null,"funder_award_id":"2022YFB4401700","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5550268690","display_name":null,"funder_award_id":"62204155","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8861585767","display_name":"\u9762\u5411\u5e94\u7528\u9700\u6c42\u8f6f\u786c\u4ef6\u534f\u540c\u8bbe\u8ba1\u6570\u636e\u7cfb\u7edf\u5173\u952e\u95ee\u9898\u7814\u7a76","funder_award_id":"23ZR1442300","funder_id":"https://openalex.org/F4320309612","funder_display_name":"Natural Science Foundation of Shanghai"}],"funders":[{"id":"https://openalex.org/F4320309612","display_name":"Natural Science Foundation of Shanghai","ror":null},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W2289252105","https://openalex.org/W2604319603","https://openalex.org/W2605330055","https://openalex.org/W2919115771","https://openalex.org/W2940862705","https://openalex.org/W3016939927","https://openalex.org/W3043406639","https://openalex.org/W3101026687","https://openalex.org/W3130281579","https://openalex.org/W3130554079","https://openalex.org/W3158233068","https://openalex.org/W4280489237","https://openalex.org/W4360831791","https://openalex.org/W4360831984","https://openalex.org/W4379115810","https://openalex.org/W4380874786","https://openalex.org/W4381894472","https://openalex.org/W4393186093","https://openalex.org/W4393207688","https://openalex.org/W4396949777","https://openalex.org/W4400232507","https://openalex.org/W4402475847","https://openalex.org/W4404133691","https://openalex.org/W4406265863","https://openalex.org/W4409568286"],"related_works":[],"abstract_inverted_index":{"Today,":[0],"hardware":[1],"accelerators":[2],"are":[3],"being":[4],"deployed":[5],"in":[6],"cloud":[7],"and":[8,38,61,125],"edge":[9],"computing":[10],"to":[11,71,102,135],"serve":[12],"DNN":[13,93],"inference":[14,86],"jobs":[15,43,87],"that":[16],"multiple":[17],"tenants":[18,82],"keep":[19],"issuing.":[20],"The":[21,31],"use":[22],"of":[23,34,41,76,128],"heterogeneous":[24,89],"multi-core":[25,104],"accelerator":[26],"systems":[27],"has":[28],"been":[29],"considered.":[30],"intricate":[32],"nature":[33],"one":[35],"such":[36,115],"system":[37],"the":[39,48,74,117,121,126],"dynamicity":[40],"multi-tenant":[42],"over":[44],"time":[45],"yet":[46],"make":[47],"scheduling":[49,65],"a":[50,63],"complex":[51],"problem.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56],"study":[57],"layer":[58,105,108,129],"fusion":[59],"techniques":[60],"propose":[62],"new":[64],"algorithm":[66],"named":[67],"Lucas.":[68],"Lucas":[69,98,138],"aims":[70],"maximally":[72],"meet":[73],"Quality":[75],"Service":[77,142],"(QoS)":[78],"requirements":[79],"for":[80],"all":[81],"when":[83],"mapping":[84],"their":[85],"onto":[88],"accelerators.":[90],"After":[91],"breaking":[92],"layers":[94,122],"into":[95],"fine-grained":[96],"units,":[97],"online":[99],"decides":[100],"whether":[101],"perform":[103],"fusion,":[106,109],"single-core":[107],"or":[110],"layer-by-layer":[111],"execution":[112],"regarding":[113],"factors":[114],"as":[116],"memory":[118],"bandwidth":[119],"consumption,":[120],"awaiting":[123],"execution,":[124],"cost":[127],"fusion.":[130],"Evaluation":[131],"shows":[132],"that,":[133],"compared":[134],"state-of-the-art":[136],"schedulers,":[137],"achieves":[139],"significantly":[140],"higher":[141],"Level":[143],"Agreement":[144],"(SLA)":[145],"compliance":[146],"across":[147],"various":[148],"workloads.":[149]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-15T00:00:00"}
