{"id":"https://openalex.org/W4405104082","doi":"https://doi.org/10.1109/milcom61039.2024.10773756","title":"A Performance Prediction-based DNN Partitioner for Edge TPU Pipelining","display_name":"A Performance Prediction-based DNN Partitioner for Edge TPU Pipelining","publication_year":2024,"publication_date":"2024-10-28","ids":{"openalex":"https://openalex.org/W4405104082","doi":"https://doi.org/10.1109/milcom61039.2024.10773756"},"language":"en","primary_location":{"id":"doi:10.1109/milcom61039.2024.10773756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/milcom61039.2024.10773756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MILCOM 2024 - 2024 IEEE Military Communications Conference (MILCOM)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://laas.hal.science/hal-04844549/document","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Bohua Zou","orcid":null},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Bohua Zou","raw_affiliation_strings":["Technical University of Munich,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042767630","display_name":"Binqi Sun","orcid":"https://orcid.org/0000-0002-9764-6259"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Binqi Sun","raw_affiliation_strings":["Technical University of Munich,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088066154","display_name":"Y. Charlie Hu","orcid":"https://orcid.org/0009-0003-8096-7077"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yigong Hu","raw_affiliation_strings":["University of Illinois Urbana-Champaign,USA","UIUC - University of Illinois at Urbana-Champaign [Urbana] (205 N. Mathews Ave., Urbana-Champaign, IL 61801 - United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"UIUC - University of Illinois at Urbana-Champaign [Urbana] (205 N. Mathews Ave., Urbana-Champaign, IL 61801 - United States)","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078957436","display_name":"Tomasz Kloda","orcid":"https://orcid.org/0000-0003-0822-4976"},"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/I190497903","display_name":"Laboratoire d'Analyse et d'Architecture des Syst\u00e8mes","ror":"https://ror.org/03vcm6439","country_code":"FR","type":"facility","lineage":["https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I1294671590","https://openalex.org/I190497903","https://openalex.org/I193033237","https://openalex.org/I196454796","https://openalex.org/I205747304","https://openalex.org/I4210095849","https://openalex.org/I4210152422","https://openalex.org/I4210159245","https://openalex.org/I4405258862","https://openalex.org/I4405259414"]},{"id":"https://openalex.org/I196454796","display_name":"Institut National des Sciences Appliqu\u00e9es de Toulouse","ror":"https://ror.org/01h8pf755","country_code":"FR","type":"education","lineage":["https://openalex.org/I196454796"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Tomasz Kloda","raw_affiliation_strings":["LAAS-CNRS, Universit&#x00E9; de Toulouse, INSA,Toulouse,France","LAAS-TRUST - Trustworthy systems: foundations and practices (France)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"LAAS-CNRS, Universit&#x00E9; de Toulouse, INSA,Toulouse,France","institution_ids":["https://openalex.org/I196454796","https://openalex.org/I1294671590","https://openalex.org/I190497903"]},{"raw_affiliation_string":"LAAS-TRUST - Trustworthy systems: foundations and practices (France)","institution_ids":["https://openalex.org/I190497903"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060442004","display_name":"Marco Caccamo","orcid":"https://orcid.org/0000-0003-2328-044X"},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Marco Caccamo","raw_affiliation_strings":["Technical University of Munich,Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Technical University of Munich,Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087114395","display_name":"Tarek Abdelzaher","orcid":"https://orcid.org/0000-0003-3883-7220"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tarek Abdelzaher","raw_affiliation_strings":["University of Illinois Urbana-Champaign,USA","UIUC - University of Illinois at Urbana-Champaign [Urbana] (205 N. Mathews Ave., Urbana-Champaign, IL 61801 - United States)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois Urbana-Champaign,USA","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"UIUC - University of Illinois at Urbana-Champaign [Urbana] (205 N. Mathews Ave., Urbana-Champaign, IL 61801 - United States)","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9944000244140625,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9944000244140625,"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/T11478","display_name":"Caching and Content Delivery","score":0.9873999953269958,"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"}},{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.9843000173568726,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7345913052558899},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.6159398555755615},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5135705471038818},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.42358213663101196},{"id":"https://openalex.org/keywords/software-pipelining","display_name":"Software pipelining","score":0.414590060710907},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3015711009502411},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.12615293264389038},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.0592210590839386}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7345913052558899},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.6159398555755615},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5135705471038818},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.42358213663101196},{"id":"https://openalex.org/C188854837","wikidata":"https://www.wikidata.org/wiki/Q268469","display_name":"Software pipelining","level":3,"score":0.414590060710907},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3015711009502411},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.12615293264389038},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.0592210590839386}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/milcom61039.2024.10773756","is_oa":false,"landing_page_url":"https://doi.org/10.1109/milcom61039.2024.10773756","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MILCOM 2024 - 2024 IEEE Military Communications Conference (MILCOM)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04844549v1","is_oa":true,"landing_page_url":"https://laas.hal.science/hal-04844549","pdf_url":"https://laas.hal.science/hal-04844549/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://milcom2024.ieee-milcom.org/","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"pmh:oai:HAL:hal-04844549v1","is_oa":true,"landing_page_url":"https://laas.hal.science/hal-04844549","pdf_url":"https://laas.hal.science/hal-04844549/document","source":{"id":"https://openalex.org/S4306402512","display_name":"HAL (Le Centre pour la Communication Scientifique Directe)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1294671590","host_organization_name":"Centre National de la Recherche Scientifique","host_organization_lineage":["https://openalex.org/I1294671590"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"https://milcom2024.ieee-milcom.org/","raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7","score":0.699999988079071}],"awards":[{"id":"https://openalex.org/G1034401897","display_name":null,"funder_award_id":"W911NF-17-2-0196","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G1452086972","display_name":null,"funder_award_id":"JUMP 2.0","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"},{"id":"https://openalex.org/G1637379582","display_name":null,"funder_award_id":"W911NF-17-2-0196","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G5259331294","display_name":null,"funder_award_id":"W911NF","funder_id":"https://openalex.org/F4320338295","funder_display_name":"Army Research Laboratory"},{"id":"https://openalex.org/G717040255","display_name":null,"funder_award_id":"CNS 20-38817","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8938883616","display_name":null,"funder_award_id":"20-38817","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320337807","display_name":"U.S. Army Combat Capabilities Development Command","ror":null},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4405104082.pdf"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2097117768","https://openalex.org/W2194775991","https://openalex.org/W2907492528","https://openalex.org/W2942465044","https://openalex.org/W2963446712","https://openalex.org/W3088933492","https://openalex.org/W3090495278","https://openalex.org/W3134295251","https://openalex.org/W3143394933","https://openalex.org/W3172133322","https://openalex.org/W3188167723","https://openalex.org/W3211394146","https://openalex.org/W4206191901","https://openalex.org/W4313452782","https://openalex.org/W4313549783","https://openalex.org/W4381886068","https://openalex.org/W4385245566","https://openalex.org/W4386764047","https://openalex.org/W4386764509","https://openalex.org/W4390189386","https://openalex.org/W4391204796","https://openalex.org/W4392971993","https://openalex.org/W4400034462","https://openalex.org/W4400064288","https://openalex.org/W6631190155","https://openalex.org/W6739901393","https://openalex.org/W6759402996","https://openalex.org/W6791871424","https://openalex.org/W6804049574"],"related_works":["https://openalex.org/W1603958403","https://openalex.org/W1976397984","https://openalex.org/W4232563190","https://openalex.org/W2083147443","https://openalex.org/W2034393996","https://openalex.org/W1816081266","https://openalex.org/W1567574506","https://openalex.org/W2038654640","https://openalex.org/W2571417379","https://openalex.org/W2117559535"],"abstract_inverted_index":{"Intelligent":[0],"IoT":[1],"applications":[2],"deployed":[3],"in":[4,92],"adversarial":[5],"environments":[6],"often":[7,55],"operate":[8],"without":[9],"reliable":[10],"cloud":[11],"connections,":[12],"requiring":[13],"local":[14],"execution":[15],"of":[16,136],"AI":[17,31],"pipelines":[18],"on":[19,120,151,162],"resource-constrained":[20],"edge":[21],"devices.":[22],"Edge":[23,50,121],"Tensor":[24],"Processing":[25],"Unit":[26],"(TPU)":[27],"is":[28,89],"a":[29,111,127],"specialized":[30],"hardware":[32],"accelerator":[33],"known":[34],"for":[35,117],"its":[36],"low":[37],"power":[38],"consumption":[39],"and":[40,77,99,155,175,184],"high":[41],"computational":[42],"efficiency.":[43],"To":[44,105],"optimize":[45],"DNN":[46,52,118,138],"performance":[47,102,113],"across":[48,66],"multiple":[49],"TPUs,":[51],"models":[53,119,164],"are":[54,103],"pipelined":[56],"by":[57,180],"partitioning":[58,115,173],"them":[59],"into":[60],"segments.":[61],"However,":[62],"uneven":[63],"workload":[64],"distribution":[65],"these":[67,107],"segments":[68],"can":[69],"lead":[70],"to":[71,82,130,182,188],"latency":[72],"bottlenecks,":[73],"reducing":[74,177],"overall":[75],"throughput,":[76],"increasing":[78],"memory":[79,97],"access":[80],"due":[81],"the":[83,133,152,166],"limited":[84],"on-chip":[85],"memory.":[86],"This":[87,124],"issue":[88],"especially":[90],"concerning":[91],"mission-critical":[93],"applications,":[94],"where":[95],"minimizing":[96],"contention":[98],"ensuring":[100],"robust":[101],"critical.":[104],"overcome":[106],"challenges,":[108],"we":[109],"develop":[110],"novel":[112],"prediction-based":[114],"tool":[116,125],"TPU":[122],"pipelines.":[123],"uses":[126],"Transformer-based":[128],"model":[129,154],"accurately":[131],"predict":[132],"inference":[134],"time":[135,179],"individual":[137],"segments,":[139],"enabling":[140],"more":[141],"efficient":[142],"partitioning.":[143],"We":[144],"introduce":[145],"two":[146],"methods:":[147],"one":[148],"relying":[149],"solely":[150],"prediction":[153,158],"another":[156],"combining":[157],"with":[159],"profiling.":[160],"Tested":[161],"120":[163],"from":[165],"NASBench-101":[167],"dataset,":[168],"both":[169],"methods":[170],"significantly":[171],"improved":[172],"robustness":[174],"efficiency,":[176],"solving":[178],"up":[181],"98.86%":[183],"97.21%,":[185],"respectively,":[186],"compared":[187],"traditional":[189],"profiling-based":[190],"approaches,":[191],"while":[192],"maintaining":[193],"comparable":[194],"bottleneck":[195],"latencies.":[196]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
