{"id":"https://openalex.org/W4413426111","doi":"https://doi.org/10.1109/coins65080.2025.11125772","title":"Accelerating Hardware-Aware NAS with ML-Based Edge GPU Performance Modeling","display_name":"Accelerating Hardware-Aware NAS with ML-Based Edge GPU Performance Modeling","publication_year":2025,"publication_date":"2025-08-04","ids":{"openalex":"https://openalex.org/W4413426111","doi":"https://doi.org/10.1109/coins65080.2025.11125772"},"language":"en","primary_location":{"id":"doi:10.1109/coins65080.2025.11125772","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coins65080.2025.11125772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5109797009","display_name":"Aishneet Juneja","orcid":null},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aishneet Juneja","raw_affiliation_strings":["University of South Carolina,Computer Science and Engineering,Columbia,SC,USA,29208"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of South Carolina,Computer Science and Engineering,Columbia,SC,USA,29208","institution_ids":["https://openalex.org/I155781252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5119386729","display_name":"Matthew Grenier","orcid":null},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthew Grenier","raw_affiliation_strings":["University of South Carolina,Computer Science and Engineering,Columbia,SC,USA,29208"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of South Carolina,Computer Science and Engineering,Columbia,SC,USA,29208","institution_ids":["https://openalex.org/I155781252"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070940234","display_name":"Md Hasibul Amin","orcid":"https://orcid.org/0000-0002-9919-6626"},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Md Hasibul Amin","raw_affiliation_strings":["University of South Carolina,Computer Science and Engineering,Columbia,SC,USA,29208"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of South Carolina,Computer Science and Engineering,Columbia,SC,USA,29208","institution_ids":["https://openalex.org/I155781252"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5115597960","display_name":"Ramtin Zand","orcid":"https://orcid.org/0000-0002-1786-1152"},"institutions":[{"id":"https://openalex.org/I155781252","display_name":"University of South Carolina","ror":"https://ror.org/02b6qw903","country_code":"US","type":"education","lineage":["https://openalex.org/I155781252"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ramtin Zand","raw_affiliation_strings":["University of South Carolina,Computer Science and Engineering,Columbia,SC,USA,29208"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of South Carolina,Computer Science and Engineering,Columbia,SC,USA,29208","institution_ids":["https://openalex.org/I155781252"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I155781252"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20210652,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9836000204086304,"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":0.9836000204086304,"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":0.946399986743927,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9340999722480774,"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":0.7707050442695618},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.477085679769516},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4441211521625519},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.42117980122566223},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.352155864238739},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.33391353487968445},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3261330723762512},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.31536173820495605},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.17591670155525208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.114389568567276}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7707050442695618},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.477085679769516},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4441211521625519},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.42117980122566223},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.352155864238739},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.33391353487968445},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3261330723762512},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.31536173820495605},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.17591670155525208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.114389568567276}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/coins65080.2025.11125772","is_oa":false,"landing_page_url":"https://doi.org/10.1109/coins65080.2025.11125772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Omni-layer Intelligent Systems (COINS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.75,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1487564550","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2172654076","https://openalex.org/W2194775991","https://openalex.org/W2531409750","https://openalex.org/W2883780447","https://openalex.org/W2963163009","https://openalex.org/W2997109118","https://openalex.org/W3096533519","https://openalex.org/W3122132656","https://openalex.org/W3157708976","https://openalex.org/W4280558014","https://openalex.org/W4285105424","https://openalex.org/W4378498585","https://openalex.org/W4401386003","https://openalex.org/W4404371390","https://openalex.org/W4408146433"],"related_works":["https://openalex.org/W2505380084","https://openalex.org/W4400333498","https://openalex.org/W2086739451","https://openalex.org/W3183233360","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":{"In":[0],"this":[1,36],"paper,":[2],"we":[3,38],"introduce":[4],"a":[5,40,51,85,103],"machine":[6],"learning-based":[7,135],"performance":[8,78,136],"modeling":[9],"framework":[10],"that":[11,111],"accurately":[12],"predicts":[13],"both":[14],"inference":[15],"latency":[16,46],"and":[17,47,91,142],"energy":[18,48],"consumption":[19],"of":[20,45,54,88,125,134],"neural":[21,105],"networks":[22],"deployed":[23],"on":[24],"edge":[25,149],"GPUs,":[26],"specifically":[27],"targeting":[28],"the":[29,114,123,126,132],"NVIDIA":[30],"Jetson":[31],"Nano":[32],"platform.":[33],"To":[34],"support":[35],"effort,":[37],"construct":[39],"comprehensive":[41],"benchmark":[42],"dataset":[43],"consisting":[44],"measurements":[49],"for":[50,148],"wide":[52],"range":[53],"deep":[55,144],"learning":[56,145],"models,":[57],"spanning":[58],"from":[59,117],"lightweight":[60],"architectures":[61,90],"with":[62,71],"100":[63],"million":[64],"multiply-accumulate":[65],"(MAC)":[66],"operations":[67],"to":[68,73,94,119,138],"large":[69],"models":[70],"up":[72],"50":[74],"billion":[75],"MACs.":[76],"Our":[77],"modeler":[79],"demonstrates":[80],"high":[81],"predictive":[82],"accuracy":[83],"across":[84],"diverse":[86],"set":[87],"well-known":[89],"generalizes":[92],"effectively":[93],"unseen":[95],"models.":[96],"We":[97],"further":[98],"integrate":[99],"our":[100],"predictor":[101],"into":[102],"hardware-aware":[104,143],"architecture":[106],"search":[107],"(NAS)":[108],"framework,":[109],"showing":[110],"it":[112],"accelerates":[113],"NAS":[115],"process":[116],"days":[118],"hours":[120],"without":[121],"sacrificing":[122],"quality":[124],"selected":[127],"architectures.":[128],"This":[129],"work":[130],"highlights":[131],"potential":[133],"estimation":[137],"enable":[139],"fast,":[140],"efficient,":[141],"model":[146],"design":[147],"deployment.":[150]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}