{"id":"https://openalex.org/W7116316096","doi":"https://doi.org/10.1145/3754598.3754623","title":"Scheduling based on Block Features for Concurrent Inference with Unseen DNN Models on GPU","display_name":"Scheduling based on Block Features for Concurrent Inference with Unseen DNN Models on GPU","publication_year":2025,"publication_date":"2025-09-08","ids":{"openalex":"https://openalex.org/W7116316096","doi":"https://doi.org/10.1145/3754598.3754623"},"language":null,"primary_location":{"id":"doi:10.1145/3754598.3754623","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3754598.3754623","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 54th International Conference on Parallel Processing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3754598.3754623","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5026437423","display_name":"Diaohan Luo","orcid":"https://orcid.org/0000-0002-4063-6818"},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Diaohan Luo","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4063-6818","affiliations":[{"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/A5120944121","display_name":"Zhen Tang","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhen Tang","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4778-7029","affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012188235","display_name":"Heran Gao","orcid":null},"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"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heran Gao","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0000-5985-9395","affiliations":[{"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/A5120909515","display_name":"Yuewen Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuewen Wu","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1323-2455","affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050804755","display_name":"H. Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Heng Wu","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7903-5879","affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I19820366"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120889914","display_name":"Xi Han","orcid":null},"institutions":[{"id":"https://openalex.org/I45129253","display_name":"University College London","ror":"https://ror.org/02jx3x895","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I45129253"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xi Han","raw_affiliation_strings":["University College London, London, United Kingdom"],"raw_orcid":"https://orcid.org/0009-0001-3385-1245","affiliations":[{"raw_affiliation_string":"University College London, London, United Kingdom","institution_ids":["https://openalex.org/I45129253"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5120894457","display_name":"Wenbo Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I131434179","display_name":"Nanjing University of Chinese Medicine","ror":"https://ror.org/04523zj19","country_code":"CN","type":"education","lineage":["https://openalex.org/I131434179"]},{"id":"https://openalex.org/I4210128818","display_name":"Institute of Software","ror":"https://ror.org/033dfsn42","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210128818"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenbo Zhang","raw_affiliation_strings":["Institute of Software, Chinese Academy of Sciences, Beijing, China; University of Chinese Academy of Sciences, Nanjing, Nanjing, China and Nanjing Institute of Software Technology, Nanjing, China"],"raw_orcid":"https://orcid.org/0000-0002-0237-5100","affiliations":[{"raw_affiliation_string":"Institute of Software, Chinese Academy of Sciences, Beijing, China; University of Chinese Academy of Sciences, Nanjing, Nanjing, China and Nanjing Institute of Software Technology, Nanjing, China","institution_ids":["https://openalex.org/I4210128818","https://openalex.org/I131434179"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.56207486,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"541","last_page":"552"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.6173999905586243,"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":0.6173999905586243,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.13030000030994415,"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/T14347","display_name":"Big Data and Digital Economy","score":0.03610000014305115,"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/inference","display_name":"Inference","score":0.6901999711990356},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.599399983882904},{"id":"https://openalex.org/keywords/resampling","display_name":"Resampling","score":0.42260000109672546},{"id":"https://openalex.org/keywords/greedy-algorithm","display_name":"Greedy algorithm","score":0.35100001096725464},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.34360000491142273},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.3156000077724457},{"id":"https://openalex.org/keywords/structured-prediction","display_name":"Structured prediction","score":0.3091000020503998}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8058000206947327},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6901999711990356},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.599399983882904},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5677000284194946},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5332000255584717},{"id":"https://openalex.org/C150921843","wikidata":"https://www.wikidata.org/wiki/Q1170431","display_name":"Resampling","level":2,"score":0.42260000109672546},{"id":"https://openalex.org/C51823790","wikidata":"https://www.wikidata.org/wiki/Q504353","display_name":"Greedy algorithm","level":2,"score":0.35100001096725464},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.3156000077724457},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.3091000020503998},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2946999967098236},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.2881999909877777},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2815000116825104},{"id":"https://openalex.org/C107568181","wikidata":"https://www.wikidata.org/wiki/Q5319000","display_name":"Dynamic priority scheduling","level":3,"score":0.2799000144004822},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2752000093460083},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.26829999685287476},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.2596000134944916},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2549999952316284}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3754598.3754623","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3754598.3754623","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 54th International Conference on Parallel Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3754598.3754623","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3754598.3754623","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 54th International Conference on Parallel Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5164901375","display_name":null,"funder_award_id":"2023YFB3308702","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G5727040439","display_name":null,"funder_award_id":"62302489","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5767087050","display_name":null,"funder_award_id":"XDA 0360301","funder_id":"https://openalex.org/F4320321133","funder_display_name":"Chinese Academy of Sciences"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321133","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2097117768","https://openalex.org/W2097643185","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2604514113","https://openalex.org/W2934853022","https://openalex.org/W2952562115","https://openalex.org/W2963446712","https://openalex.org/W2982157693","https://openalex.org/W3016939927","https://openalex.org/W3096858590","https://openalex.org/W3186289964","https://openalex.org/W3208777667","https://openalex.org/W3217445637","https://openalex.org/W4214597292","https://openalex.org/W4231332361","https://openalex.org/W4283020086","https://openalex.org/W4386707684","https://openalex.org/W4391623921","https://openalex.org/W4394923418","https://openalex.org/W4394944658","https://openalex.org/W4401408750","https://openalex.org/W4405756372"],"related_works":[],"abstract_inverted_index":{"Efficiently":[0],"scheduling":[1,18,87,130],"concurrent":[2,23,155],"deep":[3],"neural":[4],"network":[5],"(DNN)":[6],"inference":[7,24,116,156],"on":[8,30,90],"the":[9,54,70,152],"same":[10],"GPU":[11],"can":[12],"significantly":[13],"optimize":[14],"resource":[15],"utilization.":[16],"Such":[17],"requires":[19],"accurate":[20,64],"prediction":[21,34,48,118,158],"of":[22,57,72,154],"time.":[25],"Existing":[26],"approaches":[27],"primarily":[28],"rely":[29],"model-level":[31],"features":[32],"for":[33,119,147],"and":[35,40,68,94,127,138,161,166],"scheduling,":[36],"which":[37],"necessitates":[38],"retraining":[39],"resampling":[41],"when":[42],"encountering":[43],"unseen":[44,61,81,120,148],"models":[45,58,106],"to":[46,113,164],"ensure":[47],"accuracy.":[49],"However,":[50],"in":[51],"MLOps":[52],"pipelines,":[53],"rapid":[55],"iteration":[56],"introduces":[59,100],"numerous":[60],"models,":[62,82,149],"making":[63],"predictions":[65],"highly":[66],"challenging":[67],"increasing":[69,177],"risk":[71],"SLA":[73,171],"violations.":[74],"To":[75],"address":[76],"these":[77],"challenges":[78],"posed":[79],"by":[80,159,174,179],"we":[83],"present":[84],"SKADI,":[85],"a":[86,125],"framework":[88],"based":[89],"block-level":[91,101],"feature":[92,102],"extraction":[93],"two-stage":[95,128],"greedy":[96,129],"scheduling.":[97],"First,":[98],"SKADI":[99,150,169],"extraction,":[103],"decomposing":[104],"DNN":[105],"into":[107],"homogeneous":[108],"blocks":[109],"(contiguous":[110],"operator":[111],"sequences)":[112],"enable":[114],"zero-shot":[115],"time":[117,157],"models.":[121],"Second,":[122],"it":[123],"proposes":[124],"round-based":[126],"strategy":[131],"that":[132,146],"rapidly":[133],"selects":[134],"optimal":[135],"model":[136],"pairs":[137],"overlaps":[139],"their":[140],"critical":[141],"operators.":[142],"Experimental":[143],"results":[144],"show":[145],"reduces":[151,170],"MAPE":[153],"59.25%":[160],"57.55%":[162],"compared":[163],"DeInfer":[165],"Abacus.":[167],"Additionally,":[168],"violation":[172],"rates":[173],"70.6%":[175],"while":[176],"throughput":[178],"7.3%.":[180]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-12-21T00:00:00"}