{"id":"https://openalex.org/W2885579974","doi":"https://doi.org/10.1109/rtas.2018.00028","title":"S^3DNN: Supervised Streaming and Scheduling for GPU-Accelerated Real-Time DNN Workloads","display_name":"S^3DNN: Supervised Streaming and Scheduling for GPU-Accelerated Real-Time DNN Workloads","publication_year":2018,"publication_date":"2018-04-01","ids":{"openalex":"https://openalex.org/W2885579974","doi":"https://doi.org/10.1109/rtas.2018.00028","mag":"2885579974"},"language":"en","primary_location":{"id":"doi:10.1109/rtas.2018.00028","doi":"https://doi.org/10.1109/rtas.2018.00028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rtas.2018.00028","pdf_url":null,"source":{"id":"https://openalex.org/S4210197441","display_name":"IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS)","issn_l":"1080-1812","issn":["1080-1812","2375-5342"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS)","raw_type":"proceedings-article"},"parent_works":[],"lineage":["https://openalex.org/W2885579974"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"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/A5065527608","display_name":"Husheng Zhou","orcid":"https://orcid.org/0000-0003-0614-4980","observed_orcids":["https://orcid.org/0000-0003-0614-4980"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Husheng Zhou","raw_affiliation_strings":["The University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076059064","display_name":"Soroush Bateni","orcid":"https://orcid.org/0000-0002-5448-3664","observed_orcids":["https://orcid.org/0000-0002-5448-3664"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Soroush Bateni","raw_affiliation_strings":["The University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100331624","display_name":"Cong Liu","orcid":"https://orcid.org/0000-0002-9796-1371","observed_orcids":["https://orcid.org/0000-0002-9796-1371"]},"institutions":[{"id":"https://openalex.org/I162577319","display_name":"The University of Texas at Dallas","ror":"https://ror.org/049emcs32","country_code":"US","type":"education","lineage":["https://openalex.org/I162577319"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cong Liu","raw_affiliation_strings":["The University of Texas at Dallas"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The University of Texas at Dallas","institution_ids":["https://openalex.org/I162577319"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I162577319"],"apc_list":null,"apc_paid":null,"fwci":6.2096,"has_fulltext":false,"cited_by_count":94,"citation_normalized_percentile":{"value":0.97583954,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"190","last_page":"201"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.6172000169754028,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.6172000169754028,"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.3718000054359436,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.004600000102072954,"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/deadline-aware-scheduling","display_name":"deadline-aware scheduling","score":0.9229999780654907},{"id":"https://openalex.org/keywords/cuda-streams","display_name":"CUDA streams","score":0.9210000038146973},{"id":"https://openalex.org/keywords/data-fusion","display_name":"data fusion","score":0.4860000014305115},{"id":"https://openalex.org/keywords/throughput","display_name":"throughput","score":0.671999990940094},{"id":"https://openalex.org/keywords/multitasking","display_name":"multitasking","score":0.6150000095367432},{"id":"https://openalex.org/keywords/embedded-systems","display_name":"embedded systems","score":0.781000018119812},{"id":"https://openalex.org/keywords/autonomous-driving","display_name":"autonomous driving","score":0.777999997138977}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8983704447746277},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5705743432044983},{"id":"https://openalex.org/C193702766","wikidata":"https://www.wikidata.org/wiki/Q1414548","display_name":"Concurrency","level":2,"score":0.5446211695671082},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.528312623500824},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.4896472096443176},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.40665531158447266},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34986650943756104},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.32680433988571167},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1895754337310791},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rtas.2018.00028","doi":"https://doi.org/10.1109/rtas.2018.00028","is_oa":false,"landing_page_url":"https://doi.org/10.1109/rtas.2018.00028","pdf_url":null,"source":{"id":"https://openalex.org/S4210197441","display_name":"IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS)","issn_l":"1080-1812","issn":["1080-1812","2375-5342"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W115476871","https://openalex.org/W639708223","https://openalex.org/W1483870316","https://openalex.org/W1506474685","https://openalex.org/W1536680647","https://openalex.org/W1651324627","https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W1890479029","https://openalex.org/W1969701927","https://openalex.org/W1973567737","https://openalex.org/W1994272002","https://openalex.org/W2026883296","https://openalex.org/W2029016069","https://openalex.org/W2031489346","https://openalex.org/W2036176301","https://openalex.org/W2072652898","https://openalex.org/W2092145442","https://openalex.org/W2097117768","https://openalex.org/W2097643185","https://openalex.org/W2102605133","https://openalex.org/W2110909602","https://openalex.org/W2119112357","https://openalex.org/W2143303748","https://openalex.org/W2148440649","https://openalex.org/W2150476673","https://openalex.org/W2153375074","https://openalex.org/W2155893237","https://openalex.org/W2159911284","https://openalex.org/W2163605009","https://openalex.org/W2163923247","https://openalex.org/W2167222293","https://openalex.org/W2468875367","https://openalex.org/W2550831128","https://openalex.org/W2727020690","https://openalex.org/W2765719692","https://openalex.org/W3003292416","https://openalex.org/W4235366964","https://openalex.org/W4241847236"],"related_works":["https://openalex.org/W4414332261","https://openalex.org/W4414197909","https://openalex.org/W7117693778","https://openalex.org/W4401568379","https://openalex.org/W4381894143","https://openalex.org/W4367043644","https://openalex.org/W7153008123","https://openalex.org/W3014810041","https://openalex.org/W3215253865","https://openalex.org/W7117536227"],"abstract_inverted_index":{"Deep":[0],"Neural":[1],"Networks":[2],"(DNNs)":[3],"are":[4],"being":[5],"widely":[6],"applied":[7],"in":[8,95,187,233],"many":[9],"advanced":[10],"embedded":[11],"systems":[12],"that":[13,86,117,136,215],"require":[14],"autonomous":[15,19],"decision":[16],"making,":[17],"e.g.,":[18,225],"driving":[20],"and":[21,111,128,133,152,160,191,209,229,236],"robotics.":[22],"To":[23,147],"handle":[24],"resource-demanding":[25],"DNN":[26,53,71,91,121,164,171,222],"workloads,":[27,165],"graphic":[28],"processing":[29,223],"units":[30],"(GPUs)":[31],"have":[32,183,192],"been":[33,44,63],"used":[34],"as":[35,57],"the":[36,49,67,74,88,103,142,199],"main":[37],"acceleration":[38],"engine.":[39],"Although":[40],"much":[41],"research":[42],"has":[43,62],"conducted":[45,193],"to":[46,54,65,123,227],"algorithmically":[47],"optimize":[48],"efficiency":[50],"of":[51,69,90,108,163,169,196,201,207],"applying":[52],"applications":[55],"such":[56],"object":[58],"recognition,":[59],"limited":[60],"attention":[61],"given":[64],"optimizing":[66],"execution":[68,89],"GPU-accelerated":[70,189,221],"workloads":[72,92],"at":[73],"system":[75,84,190,208],"level.":[76],"In":[77],"this":[78],"paper,":[79],"we":[80],"propose":[81],"S^3DNN,":[82],"a":[83,96,115,129,138,157,170,175,188,204],"solution":[85],"optimizes":[87,102],"on":[93],"GPU":[94,178],"real-time":[97,109,153,234],"multi-tasking":[98],"environment,":[99],"which":[100],"simultaneously":[101,148],"two":[104],"(sometimes)":[105],"conflicting":[106],"goals":[107],"correctness":[110],"throughput.":[112],"S^3DNN":[113,155,186,202,216],"contains":[114],"governor":[116],"selectively":[118],"gathers":[119],"system-wide":[120],"requests":[122],"perform":[124],"smart":[125],"data":[126],"fusion,":[127],"novel":[130],"supervised":[131],"streaming":[132],"scheduling":[134],"framework":[135],"combines":[137],"deadline-aware":[139],"scheduler":[140],"with":[141],"concurrency-enabled":[143],"CUDA":[144],"stream":[145],"technique.":[146],"maximize":[149],"concurrency-induced":[150],"benefits":[151],"performance,":[154],"explores":[156],"rather":[158],"interesting":[159],"unique":[161],"characteristic":[162],"where":[166],"multiple":[167],"layers":[168],"instance":[172],"often":[173],"exhibit":[174],"gradually":[176],"decreased":[177],"resource":[179],"utilization":[180],"pattern.":[181],"We":[182],"fully":[184],"implemented":[185],"extensive":[194],"sets":[195],"experiments":[197],"evaluating":[198],"efficacy":[200],"under":[203],"wide":[205],"range":[206],"workload":[210],"scenarios.":[211],"The":[212],"results":[213],"show":[214],"significantly":[217],"improves":[218],"upon":[219],"state-of-the-art":[220],"frameworks,":[224],"up":[226],"37%":[228],"over":[230],"40%":[231],"improvements":[232],"performance":[235],"throughput,":[237],"respectively.":[238]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":15},{"year":2022,"cited_by_count":15},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":14},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":3}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2018-08-22T00:00:00"}