{"id":"https://openalex.org/W4414500258","doi":"https://doi.org/10.1109/aicas64808.2025.11173087","title":"GEMMify: A Unified Model for Layer-Wise DNN Performance Prediction on Edge GPUs","display_name":"GEMMify: A Unified Model for Layer-Wise DNN Performance Prediction on Edge GPUs","publication_year":2025,"publication_date":"2025-04-28","ids":{"openalex":"https://openalex.org/W4414500258","doi":"https://doi.org/10.1109/aicas64808.2025.11173087"},"language":"en","primary_location":{"id":"doi:10.1109/aicas64808.2025.11173087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aicas64808.2025.11173087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 7th International Conference on Artificial Intelligence Circuits and Systems (AICAS)","raw_type":"proceedings-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/A5048739952","display_name":"Mewe-Hezoudah Kahanam","orcid":null},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I28221208","display_name":"Institut National des Sciences Appliqu\u00e9es de Rennes","ror":"https://ror.org/04xaa4j22","country_code":"FR","type":"education","lineage":["https://openalex.org/I28221208"]},{"id":"https://openalex.org/I4210100151","display_name":"Institut d'\u00c9lectronique et des Technologies du num\u00e9Rique","ror":"https://ror.org/013q33h79","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I28221208","https://openalex.org/I4210095849","https://openalex.org/I4210100151","https://openalex.org/I56067802","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Mewe-Hezoudah Kahanam","raw_affiliation_strings":["Univ. Rennes, INSA Rennes,IETR, CNRS UMR6164","INETUM (Tunisia)"],"affiliations":[{"raw_affiliation_string":"Univ. Rennes, INSA Rennes,IETR, CNRS UMR6164","institution_ids":["https://openalex.org/I4210100151","https://openalex.org/I28221208","https://openalex.org/I56067802","https://openalex.org/I1294671590"]},{"raw_affiliation_string":"INETUM (Tunisia)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075043317","display_name":"Karol Desnos","orcid":"https://orcid.org/0000-0003-1527-9668"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I28221208","display_name":"Institut National des Sciences Appliqu\u00e9es de Rennes","ror":"https://ror.org/04xaa4j22","country_code":"FR","type":"education","lineage":["https://openalex.org/I28221208"]},{"id":"https://openalex.org/I4210100151","display_name":"Institut d'\u00c9lectronique et des Technologies du num\u00e9Rique","ror":"https://ror.org/013q33h79","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I28221208","https://openalex.org/I4210095849","https://openalex.org/I4210100151","https://openalex.org/I56067802","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Karol Desnos","raw_affiliation_strings":["Univ. Rennes, INSA Rennes,IETR, CNRS UMR6164"],"affiliations":[{"raw_affiliation_string":"Univ. Rennes, INSA Rennes,IETR, CNRS UMR6164","institution_ids":["https://openalex.org/I4210100151","https://openalex.org/I28221208","https://openalex.org/I56067802","https://openalex.org/I1294671590"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111496334","display_name":"Guillaume Fortier","orcid":null},"institutions":[{"id":"https://openalex.org/I4210137888","display_name":"U.S. National Arboretum","ror":"https://ror.org/03xcerw48","country_code":"US","type":"archive","lineage":["https://openalex.org/I1312222531","https://openalex.org/I1336096307","https://openalex.org/I4210137888","https://openalex.org/I4210138094"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guillaume Fortier","raw_affiliation_strings":["Inetum France","INETUM (Tunisia)"],"affiliations":[{"raw_affiliation_string":"Inetum France","institution_ids":["https://openalex.org/I4210137888"]},{"raw_affiliation_string":"INETUM (Tunisia)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046104895","display_name":"Maxime Pelcat","orcid":"https://orcid.org/0000-0002-1158-0915"},"institutions":[{"id":"https://openalex.org/I1294671590","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73","country_code":"FR","type":"government","lineage":["https://openalex.org/I1294671590"]},{"id":"https://openalex.org/I28221208","display_name":"Institut National des Sciences Appliqu\u00e9es de Rennes","ror":"https://ror.org/04xaa4j22","country_code":"FR","type":"education","lineage":["https://openalex.org/I28221208"]},{"id":"https://openalex.org/I4210100151","display_name":"Institut d'\u00c9lectronique et des Technologies du num\u00e9Rique","ror":"https://ror.org/013q33h79","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I28221208","https://openalex.org/I4210095849","https://openalex.org/I4210100151","https://openalex.org/I56067802","https://openalex.org/I97188460"]},{"id":"https://openalex.org/I56067802","display_name":"Universit\u00e9 de Rennes","ror":"https://ror.org/015m7wh34","country_code":"FR","type":"education","lineage":["https://openalex.org/I56067802"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Maxime Pelcat","raw_affiliation_strings":["Univ. Rennes, INSA Rennes,IETR, CNRS UMR6164"],"affiliations":[{"raw_affiliation_string":"Univ. Rennes, INSA Rennes,IETR, CNRS UMR6164","institution_ids":["https://openalex.org/I4210100151","https://openalex.org/I28221208","https://openalex.org/I56067802","https://openalex.org/I1294671590"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5048739952"],"corresponding_institution_ids":["https://openalex.org/I1294671590","https://openalex.org/I28221208","https://openalex.org/I4210100151","https://openalex.org/I56067802"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26030934,"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":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9735999703407288,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9735999703407288,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9616000056266785,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10714","display_name":"Software-Defined Networks and 5G","score":0.9455999732017517,"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/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6391000151634216},{"id":"https://openalex.org/keywords/performance-prediction","display_name":"Performance prediction","score":0.6317999958992004},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.6108999848365784},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.5460000038146973},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.5177000164985657},{"id":"https://openalex.org/keywords/unified-model","display_name":"Unified Model","score":0.4902999997138977},{"id":"https://openalex.org/keywords/matrix-multiplication","display_name":"Matrix multiplication","score":0.4214000105857849},{"id":"https://openalex.org/keywords/ranging","display_name":"Ranging","score":0.41760000586509705},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.41190001368522644}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7821000218391418},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6391000151634216},{"id":"https://openalex.org/C2777115002","wikidata":"https://www.wikidata.org/wiki/Q7168246","display_name":"Performance prediction","level":2,"score":0.6317999958992004},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.6108999848365784},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5460000038146973},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.5177000164985657},{"id":"https://openalex.org/C45493050","wikidata":"https://www.wikidata.org/wiki/Q7884934","display_name":"Unified Model","level":2,"score":0.4902999997138977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.46549999713897705},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.44920000433921814},{"id":"https://openalex.org/C17349429","wikidata":"https://www.wikidata.org/wiki/Q1049914","display_name":"Matrix multiplication","level":3,"score":0.4214000105857849},{"id":"https://openalex.org/C115051666","wikidata":"https://www.wikidata.org/wiki/Q6522493","display_name":"Ranging","level":2,"score":0.41760000586509705},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.41190001368522644},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.4056999981403351},{"id":"https://openalex.org/C2780595030","wikidata":"https://www.wikidata.org/wiki/Q3860309","display_name":"Multiplication (music)","level":2,"score":0.39259999990463257},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.34869998693466187},{"id":"https://openalex.org/C167085575","wikidata":"https://www.wikidata.org/wiki/Q6803654","display_name":"Mean squared prediction error","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.31439998745918274},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.30979999899864197},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.30550000071525574},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3041999936103821},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.3012999892234802},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2937000095844269},{"id":"https://openalex.org/C122383733","wikidata":"https://www.wikidata.org/wiki/Q865920","display_name":"Approximation error","level":2,"score":0.2935999929904938},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.290800005197525},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.25060001015663147}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/aicas64808.2025.11173087","is_oa":false,"landing_page_url":"https://doi.org/10.1109/aicas64808.2025.11173087","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE 7th International Conference on Artificial Intelligence Circuits and Systems (AICAS)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-05127830v1","is_oa":false,"landing_page_url":"https://hal.science/hal-05127830","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"The 7th IEEE International Conference on Artificial Intelligence Circuits and Systems, Apr 2025, Bordeaux (France), France. ⟨10.1109/AICAS64808.2025.11173087⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1005811612","https://openalex.org/W2798544842","https://openalex.org/W2903557836","https://openalex.org/W2995763407","https://openalex.org/W3037032032","https://openalex.org/W3094502228","https://openalex.org/W3135013702","https://openalex.org/W3183603480","https://openalex.org/W3205805162","https://openalex.org/W3214897310","https://openalex.org/W4221014749","https://openalex.org/W4229443721","https://openalex.org/W4308090454","https://openalex.org/W4376277519","https://openalex.org/W4386106797"],"related_works":[],"abstract_inverted_index":{"Performance":[0],"prediction":[1,115],"techniques":[2],"enable":[3],"early":[4],"design":[5],"space":[6],"exploration":[7],"to":[8,30,142],"create":[9],"and":[10,54,71,79,95],"deploy":[11],"cost-effective":[12],"Deep":[13],"Neural":[14],"Networks":[15],"(DNNs).":[16],"Specifically,":[17],"layer-wise":[18,92],"DNN":[19,48,73],"performance":[20,25,114],"predictions":[21],"produce":[22],"a":[23,41,86,117],"fine-grained":[24],"breakdown":[26],"of":[27,47,98],"DNNs,":[28],"proving":[29],"be":[31],"valuable":[32],"for":[33,44,89,109],"automated":[34],"model":[35,43],"optimization.":[36],"However,":[37],"current":[38],"methods":[39],"embed":[40],"predictive":[42],"each":[45],"type":[46],"layer,":[49],"which":[50],"increases":[51],"their":[52,56],"complexity":[53],"lowers":[55],"practicality":[57],"when":[58],"targeting":[59],"novel":[60,87],"neural":[61],"networks.":[62],"Using":[63],"similarities":[64],"between":[65],"General":[66],"Matrix":[67],"Multiplication":[68],"(GEMM)":[69],"operations":[70],"main":[72,111],"layers,":[74,83,112],"such":[75],"as":[76,106],"convolutional":[77],"(CONV)":[78],"fully":[80],"connected":[81],"(FC)":[82],"we":[84],"introduce":[85],"method":[88,102,131],"predicting":[90],"the":[91,110,122,129],"power,":[93],"latency,":[94],"energy":[96],"consumption":[97],"DNNs.":[99],"The":[100],"proposed":[101,130],"uses":[103],"GEMM":[104],"dimensions":[105],"common":[107],"features":[108],"allowing":[113],"using":[116],"single":[118],"model.":[119],"Experiments":[120],"on":[121],"Jetson":[123],"Orin":[124],"edge":[125],"device":[126],"show":[127],"that":[128],"achieves":[132],"state-of-the-art":[133],"Mean":[134],"Absolute":[135],"Percentage":[136],"Error":[137],"(MAPE)":[138],"ranging":[139],"from":[140],"9.77%":[141],"15.28%":[143],"while":[144],"offering":[145],"widely":[146],"applicable":[147],"models.":[148]},"counts_by_year":[],"updated_date":"2026-03-27T14:29:43.386196","created_date":"2025-10-10T00:00:00"}