{"id":"https://openalex.org/W4395668837","doi":"https://doi.org/10.1145/3625687.3625789","title":"Miriam: Exploiting Elastic Kernels for Real-time Multi-DNN Inference on Edge GPU","display_name":"Miriam: Exploiting Elastic Kernels for Real-time Multi-DNN Inference on Edge GPU","publication_year":2023,"publication_date":"2023-11-12","ids":{"openalex":"https://openalex.org/W4395668837","doi":"https://doi.org/10.1145/3625687.3625789"},"language":"en","primary_location":{"id":"doi:10.1145/3625687.3625789","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3625687.3625789","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3625687.3625789","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM Conference on Embedded Networked Sensor Systems","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/10.1145/3625687.3625789","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Zhihe Zhao","orcid":"https://orcid.org/0000-0001-7997-1798"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Zhihe Zhao","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0001-7997-1798","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049748462","display_name":"Neiwen Ling","orcid":"https://orcid.org/0000-0003-2072-1502"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Neiwen Ling","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0000-0003-2072-1502","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I177725633"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002245169","display_name":"Nan Guan","orcid":"https://orcid.org/0000-0003-3775-911X"},"institutions":[{"id":"https://openalex.org/I168719708","display_name":"City University of Hong Kong","ror":"https://ror.org/03q8dnn23","country_code":"HK","type":"education","lineage":["https://openalex.org/I168719708"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Nan Guan","raw_affiliation_strings":["City University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-3775-911X","affiliations":[{"raw_affiliation_string":"City University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I168719708"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072780737","display_name":"Guoliang Xing","orcid":"https://orcid.org/0000-0003-1772-7751"},"institutions":[{"id":"https://openalex.org/I177725633","display_name":"Chinese University of Hong Kong","ror":"https://ror.org/00t33hh48","country_code":"HK","type":"education","lineage":["https://openalex.org/I177725633"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Guoliang Xing","raw_affiliation_strings":["The Chinese University of Hong Kong, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0003-1772-7751","affiliations":[{"raw_affiliation_string":"The Chinese University of Hong Kong, Hong Kong, China","institution_ids":["https://openalex.org/I177725633"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.6087,"has_fulltext":true,"cited_by_count":14,"citation_normalized_percentile":{"value":0.89784082,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"97","last_page":"110"},"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":0.9958000183105469,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9941999912261963,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7562255263328552},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6751742362976074},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.6735333800315857},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4481217861175537},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.44080185890197754},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.42443251609802246},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.39987367391586304},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37580469250679016},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.06323957443237305}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7562255263328552},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6751742362976074},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.6735333800315857},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4481217861175537},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.44080185890197754},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.42443251609802246},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.39987367391586304},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37580469250679016},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.06323957443237305}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3625687.3625789","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3625687.3625789","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3625687.3625789","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM Conference on Embedded Networked Sensor Systems","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3625687.3625789","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3625687.3625789","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3625687.3625789","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM Conference on Embedded Networked Sensor Systems","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4395668837.pdf","grobid_xml":"https://content.openalex.org/works/W4395668837.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W164384110","https://openalex.org/W1968391520","https://openalex.org/W2134427337","https://openalex.org/W2194775991","https://openalex.org/W2510980549","https://openalex.org/W2554796001","https://openalex.org/W2581065617","https://openalex.org/W2618530766","https://openalex.org/W2625157458","https://openalex.org/W2897268228","https://openalex.org/W2898495092","https://openalex.org/W2918317383","https://openalex.org/W2963240192","https://openalex.org/W2963495494","https://openalex.org/W3002400545","https://openalex.org/W3011377185","https://openalex.org/W3014810041","https://openalex.org/W3017087102","https://openalex.org/W3088076788","https://openalex.org/W3133730715","https://openalex.org/W3136585513","https://openalex.org/W3157306683","https://openalex.org/W3160220816","https://openalex.org/W3165292244","https://openalex.org/W3173358825","https://openalex.org/W3208777667","https://openalex.org/W3212621679","https://openalex.org/W4283020086","https://openalex.org/W4285815152","https://openalex.org/W4317926960","https://openalex.org/W4320060064","https://openalex.org/W4320519434","https://openalex.org/W4367277020","https://openalex.org/W4372271902","https://openalex.org/W6785429063"],"related_works":["https://openalex.org/W2505380084","https://openalex.org/W2086739451","https://openalex.org/W3183233360","https://openalex.org/W2073137634","https://openalex.org/W1980160788","https://openalex.org/W1656096860","https://openalex.org/W2095928260","https://openalex.org/W2268149564","https://openalex.org/W1984739956","https://openalex.org/W2763312740"],"abstract_inverted_index":{"Many":[0],"applications":[1],"such":[2],"as":[3],"autonomous":[4],"driving":[5],"and":[6,53,86],"augmented":[7],"reality,":[8],"require":[9],"the":[10],"concurrent":[11],"running":[12],"of":[13,23,35,43,145],"multiple":[14,29],"deep":[15],"neural":[16],"networks":[17],"(DNN)":[18],"that":[19,123],"poses":[20],"different":[21],"levels":[22,34],"real-time":[24],"performance":[25],"requirements.":[26],"However,":[27],"coordinating":[28],"DNN":[30,96,105,114],"tasks":[31],"with":[32,111],"varying":[33],"criticality":[36],"on":[37,75,109,117],"edge":[38,49,76,119],"GPUs":[39,50],"remains":[40],"an":[41,83],"area":[42],"limited":[44],"study.":[45],"Unlike":[46],"server-level":[47],"GPUs,":[48],"are":[51],"resource-limited":[52],"lack":[54],"hardware-level":[55],"resource":[56,61],"management":[57],"mechanisms":[58],"for":[59,72,139],"avoiding":[60],"contention.":[62],"Therefore,":[63],"we":[64,101],"propose":[65],"Miriam,":[66,100],"a":[67,87,103],"contention-aware":[68],"task":[69],"coordination":[70],"framework":[71],"multi-DNN":[73],"inference":[74,106],"GPU.":[77],"Miriam":[78,124],"consolidates":[79],"two":[80,118],"main":[81],"components,":[82],"elastic-kernel":[84],"generator,":[85],"runtime":[88],"dynamic":[89],"kernel":[90],"coordinator,":[91],"to":[92,143],"support":[93],"mixed":[94],"critical":[95,140],"inference.":[97],"To":[98],"evaluate":[99],"build":[102],"new":[104],"benchmark":[107],"based":[108],"CUDA":[110],"diverse":[112],"representative":[113],"workloads.":[115],"Experiments":[116],"GPU":[120],"platforms":[121],"show":[122],"can":[125],"increase":[126],"system":[127],"throughput":[128],"by":[129],"92%":[130],"while":[131],"only":[132],"incurring":[133],"less":[134],"than":[135],"10%":[136],"latency":[137],"overhead":[138],"tasks,":[141],"compared":[142],"state":[144],"art":[146],"baselines.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":8}],"updated_date":"2026-08-25T07:29:55.448023","created_date":"2025-10-10T00:00:00"}