{"id":"https://openalex.org/W6981978333","doi":null,"title":"Generating and Exploiting Deep Learning Variants to Increase Heterogeneous Resource Utilization in the NVIDIA Xavier","display_name":"Generating and Exploiting Deep Learning Variants to Increase Heterogeneous Resource Utilization in the NVIDIA Xavier","publication_year":null,"publication_date":null,"ids":{"openalex":"https://openalex.org/W6981978333"},"language":"en","primary_location":{"id":"pmh:oai:recercat.cat:2072/358759","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/166069","pdf_url":null,"source":{"id":"https://openalex.org/S4306402147","display_name":"RECERCAT (Consorci de Serveis Universitaris de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210090028","host_organization_name":"Consorci de Serveis Universitaris de Catalunya","host_organization_lineage":["https://openalex.org/I4210090028"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},"parent_works":[],"lineage":["https://openalex.org/W6981978333"],"child_works_count":0,"type":"conference-paper","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2117/166069","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023928169","display_name":"Roger Pujol","orcid":"https://orcid.org/0000-0002-1960-6358","observed_orcids":["https://orcid.org/0000-0002-1960-6358"]},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]},{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Pujol, Roger","raw_affiliation_strings":["Universitat Politecnica de Catalunya (UPC) , Spain Barcelona Supercomputing Center (BSC) , Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universitat Politecnica de Catalunya (UPC) , Spain Barcelona Supercomputing Center (BSC) , Spain","institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053049634","display_name":"Hamid Tabani","orcid":"https://orcid.org/0000-0002-6061-7470","observed_orcids":["https://orcid.org/0000-0002-6061-7470"]},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Tabani, Hamid","raw_affiliation_strings":["Barcelona Supercomputing Center (BSC) , Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center (BSC) , Spain","institution_ids":["https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012406621","display_name":"Leonidas Kosmidis","orcid":"https://orcid.org/0000-0001-9751-1058","observed_orcids":["https://orcid.org/0000-0001-9751-1058"]},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Kosmidis, Leonidas","raw_affiliation_strings":["Barcelona Supercomputing Center (BSC) , Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center (BSC) , Spain","institution_ids":["https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019602265","display_name":"Enrico Mezzetti","orcid":"https://orcid.org/0000-0002-1886-2931","observed_orcids":["https://orcid.org/0000-0002-1886-2931"]},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Mezzetti, Enrico","raw_affiliation_strings":["Barcelona Supercomputing Center (BSC) , Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center (BSC) , Spain","institution_ids":["https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020861175","display_name":"Jaume Abella","orcid":"https://orcid.org/0000-0001-7951-4028","observed_orcids":["https://orcid.org/0000-0001-7951-4028"]},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Abella, Jaume","raw_affiliation_strings":["Barcelona Supercomputing Center (BSC) , Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center (BSC) , Spain","institution_ids":["https://openalex.org/I2799803557"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026101378","display_name":"Francisco Javier Cazorla","orcid":"https://orcid.org/0000-0002-3344-376X","observed_orcids":["https://orcid.org/0000-0002-3344-376X"]},"institutions":[{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Cazorla, Francisco J.","raw_affiliation_strings":["Barcelona Supercomputing Center (BSC) , Spain"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center (BSC) , Spain","institution_ids":["https://openalex.org/I2799803557"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T10933","display_name":"Real-Time Systems Scheduling","score":0.4408999979496002,"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/T10933","display_name":"Real-Time Systems Scheduling","score":0.4408999979496002,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.32249999046325684,"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":0.21850000321865082,"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/deep-neural-network","display_name":"deep neural network","score":0.7490000128746033},{"id":"https://openalex.org/keywords/heterogeneous-computing","display_name":"heterogeneous computing","score":0.6729999780654907},{"id":"https://openalex.org/keywords/resource-utilization","display_name":"resource utilization","score":0.781000018119812},{"id":"https://openalex.org/keywords/autonomous-driving","display_name":"autonomous driving","score":0.734000027179718},{"id":"https://openalex.org/keywords/tensor-cores","display_name":"tensor cores","score":0.6700000166893005},{"id":"https://openalex.org/keywords/processor-cores","display_name":"processor cores","score":0.6420000195503235},{"id":"https://openalex.org/keywords/static-scheduling","display_name":"static scheduling","score":0.8970000147819519}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.847100019454956},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.7064999938011169},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.5073000192642212},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.49790000915527344},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48820000886917114},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.47540000081062317},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.4510999917984009},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4388999938964844},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.43320000171661377},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.42800000309944153},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4147000014781952},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.41260001063346863},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.37709999084472656},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3490000069141388},{"id":"https://openalex.org/C29202148","wikidata":"https://www.wikidata.org/wiki/Q287260","display_name":"Resource allocation","level":2,"score":0.325300008058548},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.3138999938964844},{"id":"https://openalex.org/C2164484","wikidata":"https://www.wikidata.org/wiki/Q5170150","display_name":"Core (optical fiber)","level":2,"score":0.30230000615119934},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.30090001225471497},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.28859999775886536},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.27390000224113464},{"id":"https://openalex.org/C2986737658","wikidata":"https://www.wikidata.org/wiki/Q30103009","display_name":"Tensor decomposition","level":3,"score":0.26840001344680786},{"id":"https://openalex.org/C2778562939","wikidata":"https://www.wikidata.org/wiki/Q1298791","display_name":"Synchronization (alternating current)","level":3,"score":0.2635999917984009},{"id":"https://openalex.org/C2780609101","wikidata":"https://www.wikidata.org/wiki/Q17156588","display_name":"Resource management (computing)","level":2,"score":0.2599000036716461},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.2500999867916107}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:recercat.cat:2072/358759","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/166069","pdf_url":null,"source":{"id":"https://openalex.org/S4306402147","display_name":"RECERCAT (Consorci de Serveis Universitaris de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210090028","host_organization_name":"Consorci de Serveis Universitaris de Catalunya","host_organization_lineage":["https://openalex.org/I4210090028"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:recercat.cat:2072/358759","doi":null,"is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/166069","pdf_url":null,"source":{"id":"https://openalex.org/S4306402147","display_name":"RECERCAT (Consorci de Serveis Universitaris de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I4210090028","host_organization_name":"Consorci de Serveis Universitaris de Catalunya","host_organization_lineage":["https://openalex.org/I4210090028"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G1053284885","display_name":"Sustainable Performance for High-Performance Embedded Computing Systems","funder_award_id":"772773","funder_id":"https://openalex.org/F4320338335","funder_display_name":"H2020 European Research Council"},{"id":"https://openalex.org/G3324247440","display_name":null,"funder_award_id":"TIN2015-65316-P","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"},{"id":"https://openalex.org/G434337789","display_name":null,"funder_award_id":"HORIZON2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5592594182","display_name":null,"funder_award_id":"TIN2015-65316","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"},{"id":"https://openalex.org/G8257141572","display_name":null,"funder_award_id":"RYC-2013-14717","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"},{"id":"https://openalex.org/G8786104484","display_name":null,"funder_award_id":"FJCI-2017-34095","funder_id":"https://openalex.org/F4320321837","funder_display_name":"Ministerio de Econom\u00eda y Competitividad"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321837","display_name":"Ministerio de Econom\u00eda y Competitividad","ror":"https://ror.org/034900433"},{"id":"https://openalex.org/F4320338335","display_name":"H2020 European Research Council","ror":"https://ror.org/0472cxd90"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W6981978333.pdf","grobid_xml":"https://content.openalex.org/works/W6981978333.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3121071986","https://openalex.org/W3010466514","https://openalex.org/W3029362297","https://openalex.org/W6941098310","https://openalex.org/W4409097657","https://openalex.org/W7163924367","https://openalex.org/W3176569963","https://openalex.org/W3215253865","https://openalex.org/W4401568379","https://openalex.org/W4367043644"],"abstract_inverted_index":{"Deep":[0,202],"learning-based":[1],"solutions":[2],"and,":[3],"in":[4,17,66,95,115,135,189],"particular,":[5],"deep":[6],"neural":[7],"networks":[8],"(DNNs)":[9],"are":[10,84],"at":[11,42],"the":[12,46,96,136,145,149,165,179,237,246],"heart":[13],"of":[14,57,90,104,130,144,148,239],"several":[15,37,109],"functionalities":[16],"critical-real":[18],"time":[19,44,119],"embedded":[20],"systems":[21,30],"(CRTES)":[22],"from":[23],"vision-based":[24],"perception":[25],"(object":[26],"detection":[27],"and":[28,63,79,102,163,176,182,197,241],"tracking)":[29],"to":[31,87,159,235],"trajectory":[32],"planning.":[33],"As":[34],"a":[35,55,214,232],"result,":[36],"DNN":[38,69,110,116,132,243],"instances":[39],"simultaneously":[40],"run":[41,172,188],"any":[43],"on":[45,75,173,245],"same":[47,247],"computing":[48,58,146,226],"platform.":[49,248],"However,":[50],"while":[51],"modern":[52],"GPUs":[53],"offer":[54],"variety":[56],"elements":[59,147,227],"(e.g.":[60],"CPUs,":[61],"GPUs,":[62],"specific":[64],"accelerators)":[65],"which":[67],"those":[68,224],"tasks":[70],"can":[71,156,171,187,228],"be":[72,157,229],"executed":[73],"depending":[74],"their":[76],"computational":[77],"requirements":[78,162],"temporal":[80],"constraints,":[81],"current":[82],"DNNs":[83],"mainly":[85],"programmed":[86],"exploit":[88],"one":[89],"them,":[91],"namely,":[92],"regular":[93,166,181],"cores":[94],"GPU.":[97],"This":[98],"creates":[99],"resource":[100,161,216],"imbalance":[101],"under-utilization":[103],"GPU":[105,180],"resources":[106],"when":[107],"executing":[108],"instances,":[111],"causing":[112],"an":[113],"increase":[114],"tasks'":[117],"execution":[118,238],"requirements.":[120],"In":[121],"this":[122],"paper,":[123],"(a)":[124],"we":[125,207,221],"develop":[126],"different":[127,215],"variants":[128,185,244],"(implementations)":[129],"well-known":[131],"libraries":[133],"used":[134],"Apollo":[137],"Autonomous":[138],"Driving":[139],"(AD)":[140],"software":[141],"for":[142],"each":[143,210],"latest":[150],"NVIDIA":[151],"Xavier":[152],"SoC.":[153],"Each":[154],"variant":[155],"configured":[158],"balance":[160],"performance:":[164],"CPU":[167],"core":[168,184],"implementation":[169],"that":[170,186,209],"2,":[174],"4,":[175],"6":[177],"cores;":[178],"Tensor":[183],"4":[190],"or":[191,199],"8":[192],"GPU's":[193],"Streaming":[194],"Multiprocessors":[195],"(SM);":[196],"1":[198],"2":[200],"NVIDIA's":[201],"Learning":[203],"Accelerators":[204],"(NVDLA);":[205],"(b)":[206],"show":[208,222],"particular":[211],"variant/configuration":[212],"offers":[213],"utilization/performance":[217],"point;":[218],"finally,":[219],"(c)":[220],"how":[223],"heterogeneous":[225],"exploited":[230],"by":[231],"static":[233],"scheduler":[234],"sustain":[236],"multiple":[240],"diverse":[242]},"counts_by_year":[],"updated_date":"2026-11-14T11:04:58.165337","created_date":"2025-10-10T00:00:00"}
