{"id":"https://openalex.org/W4416956233","doi":"https://doi.org/10.1145/3769102.3772715","title":"SEEB-GPU: Early-Exit Aware Scheduling and Batching for Edge GPU Inference","display_name":"SEEB-GPU: Early-Exit Aware Scheduling and Batching for Edge GPU Inference","publication_year":2025,"publication_date":"2025-12-03","ids":{"openalex":"https://openalex.org/W4416956233","doi":"https://doi.org/10.1145/3769102.3772715"},"language":null,"primary_location":{"id":"doi:10.1145/3769102.3772715","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769102.3772715","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3769102.3772715","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 Tenth ACM/IEEE Symposium on Edge Computing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3769102.3772715","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5020129565","display_name":"Srinivasan Subramaniyan","orcid":"https://orcid.org/0000-0002-5848-5667"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Srinivasan Subramaniyan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, The Ohio State University, Columbus, Ohio, USA"],"raw_orcid":"https://orcid.org/0000-0002-5848-5667","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, The Ohio State University, Columbus, Ohio, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Rudra Joshi","orcid":"https://orcid.org/0009-0004-0134-1082"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rudra Joshi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, The Ohio State University, Columbus, Ohio, USA"],"raw_orcid":"https://orcid.org/0009-0004-0134-1082","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, The Ohio State University, Columbus, Ohio, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100658019","display_name":"Xiaorui Wang","orcid":"https://orcid.org/0000-0001-9633-1418"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaorui Wang","raw_affiliation_strings":["Department of Electrical and Computer Engineering, The Ohio State University, Columbus, Ohio, USA"],"raw_orcid":"https://orcid.org/0000-0001-9633-1418","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, The Ohio State University, Columbus, Ohio, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082375623","display_name":"Marco Brocanelli","orcid":"https://orcid.org/0000-0002-3603-1402"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Marco Brocanelli","raw_affiliation_strings":["Department of Electrical and Computer Engineering, The Ohio State University, Columbus, Ohio, USA"],"raw_orcid":"https://orcid.org/0000-0002-3603-1402","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, The Ohio State University, Columbus, Ohio, USA","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.2946000099182129,"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"}},"topics":[{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.2946000099182129,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.2393999993801117,"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.09149999916553497,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.7199000120162964},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6840999722480774},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.679099977016449},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6690000295639038},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.541100025177002},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.5400999784469604},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5371999740600586}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8098999857902527},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.7199000120162964},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6840999722480774},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.679099977016449},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6690000295639038},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.541100025177002},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.5400999784469604},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5371999740600586},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5307999849319458},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.5295000076293945},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4867999851703644},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.414900004863739},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3492000102996826},{"id":"https://openalex.org/C2780378061","wikidata":"https://www.wikidata.org/wiki/Q25351891","display_name":"Service (business)","level":2,"score":0.31209999322891235},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.3037000000476837},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.2791000008583069},{"id":"https://openalex.org/C55416958","wikidata":"https://www.wikidata.org/wiki/Q6206757","display_name":"Job shop scheduling","level":3,"score":0.2728999853134155},{"id":"https://openalex.org/C2988105877","wikidata":"https://www.wikidata.org/wiki/Q1341685","display_name":"Inference system","level":5,"score":0.2596000134944916},{"id":"https://openalex.org/C70388272","wikidata":"https://www.wikidata.org/wiki/Q5968558","display_name":"IBM","level":2,"score":0.25209999084472656}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3769102.3772715","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769102.3772715","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3769102.3772715","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 Tenth ACM/IEEE Symposium on Edge Computing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3769102.3772715","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3769102.3772715","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3769102.3772715","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 Tenth ACM/IEEE Symposium on Edge Computing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1180984159","display_name":null,"funder_award_id":"CNS-2421244","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3325930382","display_name":"CAREER: Enhancing Energy Efficiency in Mobile Augmented Reality Apps","funder_award_id":"2421244","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7224660672","display_name":"CNS Core: Small: Leveraging Hardware Counters to Improve the Performance and Energy Efficiency of Mobile Apps","funder_award_id":"2149533","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7663540438","display_name":null,"funder_award_id":"CNS-2149533","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4416956233.pdf","grobid_xml":"https://content.openalex.org/works/W4416956233.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1951319388","https://openalex.org/W1965804146","https://openalex.org/W2756489700","https://openalex.org/W2772948367","https://openalex.org/W2962677625","https://openalex.org/W2981207549","https://openalex.org/W2998218113","https://openalex.org/W3020079565","https://openalex.org/W3081980877","https://openalex.org/W3097411828","https://openalex.org/W3127161477","https://openalex.org/W3130689885","https://openalex.org/W3161088809","https://openalex.org/W3186368531","https://openalex.org/W4200404225","https://openalex.org/W4206943884","https://openalex.org/W4210338699","https://openalex.org/W4221109509","https://openalex.org/W4283810142","https://openalex.org/W4293232522","https://openalex.org/W4295791054","https://openalex.org/W4312198983","https://openalex.org/W4312754493","https://openalex.org/W4360831842","https://openalex.org/W4367046915","https://openalex.org/W4381885923","https://openalex.org/W4385585396","https://openalex.org/W4399323669","https://openalex.org/W4399450878","https://openalex.org/W4400277194","https://openalex.org/W4403196715","https://openalex.org/W4413380271"],"related_works":[],"abstract_inverted_index":{"The":[0],"deployment":[1],"of":[2],"deep":[3],"neural":[4],"networks":[5],"(DNNs)":[6],"on":[7],"edge":[8,36],"devices":[9],"is":[10],"becoming":[11],"increasingly":[12],"common":[13],"in":[14,33,44,55],"latency-sensitive":[15],"applications":[16],"such":[17],"as":[18],"autonomous":[19],"driving,":[20],"real-time":[21],"video":[22],"analytics,":[23],"and":[24,35,53],"augmented":[25],"reality.":[26],"However,":[27],"modern":[28],"DNNs":[29],"are":[30],"rapidly":[31],"growing":[32],"complexity,":[34],"GPUs":[37],"often":[38],"lack":[39],"the":[40],"computational":[41],"resources":[42],"available":[43],"cloud":[45],"counterparts.":[46],"This":[47],"leads":[48],"to":[49],"increased":[50],"inference":[51],"latency":[52],"challenges":[54],"meeting":[56],"strict":[57],"Service":[58],"Level":[59],"Agreements":[60],"(SLAs).":[61]},"counts_by_year":[{"year":2026,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-12-03T00:00:00"}