{"id":"https://openalex.org/W4390771379","doi":"https://doi.org/10.1109/les.2024.3351753","title":"Adaptive Kernel Merge and Fusion for Multi-Tenant Inference in Embedded GPUs","display_name":"Adaptive Kernel Merge and Fusion for Multi-Tenant Inference in Embedded GPUs","publication_year":2024,"publication_date":"2024-01-09","ids":{"openalex":"https://openalex.org/W4390771379","doi":"https://doi.org/10.1109/les.2024.3351753"},"language":"en","primary_location":{"id":"doi:10.1109/les.2024.3351753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/les.2024.3351753","pdf_url":null,"source":{"id":"https://openalex.org/S22443479","display_name":"IEEE Embedded Systems Letters","issn_l":"1943-0663","issn":["1943-0663","1943-0671"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Embedded Systems Letters","raw_type":"journal-article"},"type":"article","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/A5102603746","display_name":"Jaebeom Jeon","orcid":"https://orcid.org/0009-0009-2947-043X"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaebeom Jeon","raw_affiliation_strings":["School of Electrical Engineering, Korea University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0009-2947-043X","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055061586","display_name":"Gunjae Koo","orcid":"https://orcid.org/0000-0003-1706-6850"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Gunjae Koo","raw_affiliation_strings":["Department of Computer Science and Engineering, Korea University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-1706-6850","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040253395","display_name":"Myung Kuk Yoon","orcid":"https://orcid.org/0000-0002-9332-0251"},"institutions":[{"id":"https://openalex.org/I138925566","display_name":"Ewha Womans University","ror":"https://ror.org/053fp5c05","country_code":"KR","type":"education","lineage":["https://openalex.org/I138925566"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Myung Kuk Yoon","raw_affiliation_strings":["Department of Computer Science and Engineering, Ewha Womans University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0002-9332-0251","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ewha Womans University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I138925566"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5015526090","display_name":"Yunho Oh","orcid":"https://orcid.org/0000-0001-6442-3705"},"institutions":[{"id":"https://openalex.org/I197347611","display_name":"Korea University","ror":"https://ror.org/047dqcg40","country_code":"KR","type":"education","lineage":["https://openalex.org/I197347611"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Yunho Oh","raw_affiliation_strings":["School of Electrical Engineering, Korea University, Seoul, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0001-6442-3705","affiliations":[{"raw_affiliation_string":"School of Electrical Engineering, Korea University, Seoul, Republic of Korea","institution_ids":["https://openalex.org/I197347611"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2645,"currency":"USD","value_usd":2645},"apc_paid":null,"fwci":0.3092,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.48342836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"16","issue":"4","first_page":"421","last_page":"424"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9908999800682068,"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":0.9908999800682068,"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":0.9861999750137329,"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/T10080","display_name":"Energy Efficient Wireless Sensor Networks","score":0.9743000268936157,"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":0.8983177542686462},{"id":"https://openalex.org/keywords/context-switch","display_name":"Context switch","score":0.621286928653717},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6194775700569153},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6168050765991211},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5000081062316895},{"id":"https://openalex.org/keywords/queue","display_name":"Queue","score":0.49796056747436523},{"id":"https://openalex.org/keywords/merge","display_name":"Merge (version control)","score":0.46173083782196045},{"id":"https://openalex.org/keywords/queueing-theory","display_name":"Queueing theory","score":0.45379555225372314},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4220311939716339},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.39099711179733276},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3364613652229309},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.27080780267715454},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22312158346176147},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1264685094356537},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.08706367015838623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8983177542686462},{"id":"https://openalex.org/C53833338","wikidata":"https://www.wikidata.org/wiki/Q1061424","display_name":"Context switch","level":2,"score":0.621286928653717},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6194775700569153},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6168050765991211},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5000081062316895},{"id":"https://openalex.org/C160403385","wikidata":"https://www.wikidata.org/wiki/Q220543","display_name":"Queue","level":2,"score":0.49796056747436523},{"id":"https://openalex.org/C197129107","wikidata":"https://www.wikidata.org/wiki/Q1921621","display_name":"Merge (version control)","level":2,"score":0.46173083782196045},{"id":"https://openalex.org/C22684755","wikidata":"https://www.wikidata.org/wiki/Q847526","display_name":"Queueing theory","level":2,"score":0.45379555225372314},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4220311939716339},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.39099711179733276},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3364613652229309},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.27080780267715454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22312158346176147},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1264685094356537},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.08706367015838623},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"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:10.1109/les.2024.3351753","is_oa":false,"landing_page_url":"https://doi.org/10.1109/les.2024.3351753","pdf_url":null,"source":{"id":"https://openalex.org/S22443479","display_name":"IEEE Embedded Systems Letters","issn_l":"1943-0663","issn":["1943-0663","1943-0671"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Embedded Systems Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1743971674","display_name":null,"funder_award_id":"2021-0- 02068","funder_id":"https://openalex.org/F4320322030","funder_display_name":"Ministry of Science, ICT and Future Planning"},{"id":"https://openalex.org/G3157678707","display_name":null,"funder_award_id":"NRF-2022R1C1C1011021","funder_id":"https://openalex.org/F4320322030","funder_display_name":"Ministry of Science, ICT and Future Planning"},{"id":"https://openalex.org/G791844702","display_name":null,"funder_award_id":"NRF-2021R1C1C1012172","funder_id":"https://openalex.org/F4320322030","funder_display_name":"Ministry of Science, ICT and Future Planning"}],"funders":[{"id":"https://openalex.org/F4320322030","display_name":"Ministry of Science, ICT and Future Planning","ror":"https://ror.org/032e49973"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2084110734","https://openalex.org/W2146575011","https://openalex.org/W2153190325","https://openalex.org/W2194775991","https://openalex.org/W2618530766","https://openalex.org/W3216234944","https://openalex.org/W3217445637","https://openalex.org/W4367043644","https://openalex.org/W6637373629"],"related_works":["https://openalex.org/W4234886518","https://openalex.org/W2389591058","https://openalex.org/W2486541857","https://openalex.org/W2382112581","https://openalex.org/W3124036233","https://openalex.org/W2108840191","https://openalex.org/W2759366996","https://openalex.org/W2354081742","https://openalex.org/W2087244274","https://openalex.org/W3134218312"],"abstract_inverted_index":{"This":[0],"paper":[1,57],"proposes":[2,58],"a":[3,30,59,73,80,107,140],"new":[4,60],"scheme":[5],"that":[6,23,38,49,63,98],"improves":[7],"throughput":[8],"and":[9,37,65,85,149,161],"reduces":[10],"queuing":[11],"delay":[12],"while":[13],"running":[14,89],"multiple":[15],"inferences":[16],"in":[17,72,139],"embedded":[18,25],"GPU-based":[19],"systems.":[20],"We":[21,104],"observe":[22],"an":[24],"system":[26],"runs":[27],"inference":[28,39],"with":[29,119],"fixed":[31,81],"number":[32,82,127],"of":[33,83,128],"deep":[34],"learning":[35],"models":[36],"requests":[40,71,84,88],"often":[41],"use":[42],"the":[43,70,87,90,96,101,113,126,145],"same":[44,91],"model.":[45,92],"Unlike":[46],"prior":[47,167],"work":[48],"proposed":[50,76,114,146],"kernel":[51,109,117,147,158],"fusion":[52,118,150],"or":[53],"scheduling":[54],"techniques,":[55],"this":[56],"software":[61],"technique":[62,77,108,115],"merges":[64],"fuses":[66],"kernels":[67,97],"by":[68,135],"monitoring":[69],"queue.":[74],"The":[75],"first":[78],"monitors":[79],"groups":[86],"Then,":[93],"it":[94],"creates":[95],"iteratively":[99],"process":[100],"grouped":[102],"requests.":[103],"call":[105],"such":[106],"merging.":[110],"After":[111],"that,":[112],"performs":[116],"merged":[120],"kernels.":[121],"Eventually,":[122],"our":[123,143],"idea":[124],"minimizes":[125],"concurrent":[129],"kernels,":[130],"thus":[131],"mitigating":[132],"stalls":[133],"caused":[134],"frequent":[136],"context":[137],"switching":[138],"GPU.":[141],"In":[142],"evaluation,":[144],"merge":[148],"achieve":[151],"2.7\u00d7":[152],"better":[153],"throughput,":[154],"47%":[155],"shorter":[156,163],"average":[157],"execution":[159],"time,":[160],"63%":[162],"tail":[164],"latency":[165],"than":[166],"work.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-08-21T09:56:20.448147","created_date":"2025-10-10T00:00:00"}