{"id":"https://openalex.org/W3113743942","doi":"https://doi.org/10.1109/hpec43674.2020.9286209","title":"Architectural Analysis of Deep Learning on Edge Accelerators","display_name":"Architectural Analysis of Deep Learning on Edge Accelerators","publication_year":2020,"publication_date":"2020-09-22","ids":{"openalex":"https://openalex.org/W3113743942","doi":"https://doi.org/10.1109/hpec43674.2020.9286209","mag":"3113743942"},"language":"en","primary_location":{"id":"doi:10.1109/hpec43674.2020.9286209","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5050164067","display_name":"Luke Kljucaric","orcid":"https://orcid.org/0000-0001-6793-3524"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Luke Kljucaric","raw_affiliation_strings":["University of Pittsburgh NSF Center for Space, High-performance, and Resilient Computing (SHREC), Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh NSF Center for Space, High-performance, and Resilient Computing (SHREC), Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030662717","display_name":"Alex Johnson","orcid":"https://orcid.org/0000-0001-7261-1087"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alex Johnson","raw_affiliation_strings":["University of Pittsburgh NSF Center for Space, High-performance, and Resilient Computing (SHREC), Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh NSF Center for Space, High-performance, and Resilient Computing (SHREC), Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082898376","display_name":"Alan D. George","orcid":"https://orcid.org/0000-0001-9665-2879"},"institutions":[{"id":"https://openalex.org/I170201317","display_name":"University of Pittsburgh","ror":"https://ror.org/01an3r305","country_code":"US","type":"education","lineage":["https://openalex.org/I170201317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Alan D. George","raw_affiliation_strings":["University of Pittsburgh NSF Center for Space, High-performance, and Resilient Computing (SHREC), Pittsburgh, PA, USA"],"affiliations":[{"raw_affiliation_string":"University of Pittsburgh NSF Center for Space, High-performance, and Resilient Computing (SHREC), Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5050164067"],"corresponding_institution_ids":["https://openalex.org/I170201317"],"apc_list":null,"apc_paid":null,"fwci":1.376,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.8420782,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9976999759674072,"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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9970999956130981,"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":0.8478860855102539},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.6956582069396973},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5924810171127319},{"id":"https://openalex.org/keywords/optical-character-recognition","display_name":"Optical character recognition","score":0.539209246635437},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.527353823184967},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.5098689794540405},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5051780343055725},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.47881728410720825},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.47745493054389954},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.46215230226516724},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4595640301704407},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.4518654942512512},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4326298236846924},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4126168489456177},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3919888138771057},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39010706543922424},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.2663768529891968},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.204015851020813},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.20127299427986145},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2001875936985016}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8478860855102539},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.6956582069396973},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5924810171127319},{"id":"https://openalex.org/C546480517","wikidata":"https://www.wikidata.org/wiki/Q167555","display_name":"Optical character recognition","level":3,"score":0.539209246635437},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.527353823184967},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.5098689794540405},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5051780343055725},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.47881728410720825},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.47745493054389954},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.46215230226516724},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4595640301704407},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4518654942512512},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4326298236846924},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4126168489456177},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3919888138771057},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39010706543922424},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.2663768529891968},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.204015851020813},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.20127299427986145},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2001875936985016},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec43674.2020.9286209","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286209","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W4097205","https://openalex.org/W1977295820","https://openalex.org/W2097117768","https://openalex.org/W2155893237","https://openalex.org/W2161663128","https://openalex.org/W2163605009","https://openalex.org/W2170866695","https://openalex.org/W2246760854","https://openalex.org/W2739601332","https://openalex.org/W2889797931","https://openalex.org/W2892341857","https://openalex.org/W2921877691","https://openalex.org/W2944027133","https://openalex.org/W2952667345","https://openalex.org/W2953235111","https://openalex.org/W2964461548","https://openalex.org/W2988271927","https://openalex.org/W3008591352","https://openalex.org/W3018558340","https://openalex.org/W6691194387","https://openalex.org/W6753770798"],"related_works":["https://openalex.org/W4238897586","https://openalex.org/W435179959","https://openalex.org/W2619091065","https://openalex.org/W3046471834","https://openalex.org/W3082465740","https://openalex.org/W4390945455","https://openalex.org/W3109468088","https://openalex.org/W3103283503","https://openalex.org/W4372271774","https://openalex.org/W4317624842"],"abstract_inverted_index":{"As":[0],"computer":[1],"architectures":[2,117,163,211],"continue":[3],"to":[4,11,37,69,99,216],"integrate":[5],"application-specific":[6],"hardware,":[7],"it":[8],"is":[9,36],"critical":[10],"understand":[12],"the":[13,87,108,158,186,222,228,238,244],"relative":[14],"performance":[15,171,187,248],"of":[16,24,42,126,137,143,172,185,188,221],"devices":[17,75,94,177,226],"for":[18,30,79,147,168,232],"maximum":[19],"app":[20],"acceleration.":[21],"The":[22,170,195,219],"goal":[23],"benchmarking":[25],"suites,":[26],"such":[27,63],"as":[28,64],"MLPerf":[29],"analyzing":[31],"machine-learning":[32],"(ML)":[33],"hardware":[34,44,77,98,121],"performance,":[35],"standardize":[38],"a":[39,123,134],"fair":[40],"comparison":[41],"different":[43,61],"architectures.":[45],"However,":[46],"there":[47],"are":[48,52,139,154,164,212],"many":[49,74,162],"apps":[50,106],"that":[51,59,118,183],"not":[53,157,165],"well":[54],"represented":[55],"by":[56,91],"these":[57,152,173],"standards":[58],"require":[60],"workloads,":[62],"ML":[65,105],"models":[66,153,174,190],"and":[67,133,156,207,224,234,249],"datasets,":[68],"achieve":[70],"similar":[71],"goals.":[72],"Additionally,":[73,237],"feature":[76,96,119],"optimized":[78,167],"data":[80],"types":[81],"other":[82,189],"than":[83],"32-bit":[84],"floating-point":[85],"numbers,":[86],"standard":[88],"representation":[89],"defined":[90],"MLPerf.":[92],"Edge-computing":[93],"often":[95],"app-specific":[97],"offload":[100],"common":[101],"operations":[102],"found":[103],"in":[104,141,178,247],"from":[107],"constrained":[109],"CPU.":[110],"This":[111],"research":[112],"analyzes":[113],"multiple":[114],"low-power":[115],"compute":[116],"ML-specific":[120],"on":[122],"case":[124],"study":[125],"handwritten":[127],"Chinese":[128],"character":[129,149],"recognition.":[130,150],"Specifically,":[131],"AlexNet":[132,233],"custom":[135,155],"version":[136],"GoogLeNet":[138],"benchmarked":[140],"terms":[142],"their":[144,217],"streaming":[145,230],"latency":[146,231],"optical":[148],"Considering":[151],"most":[159],"widely":[160],"used,":[161],"specifically":[166],"them.":[169],"can":[175,191],"stress":[176],"different,":[179],"yet":[180],"insightful,":[181],"ways":[182],"generalizations":[184],"be":[192],"drawn":[193],"from.":[194],"NVIDIA":[196],"Jetson":[197],"AGX":[198,223],"Xavier":[199],"(AGX),":[200],"Intel":[201],"Neural":[202],"Compute":[203],"Stick":[204],"2":[205],"(NCS2),":[206],"Google":[208],"Edge":[209],"TPU":[210,225],"analyzed":[213],"with":[214],"respect":[215],"performance.":[218],"design":[220,242],"showcased":[227],"lowest":[229],"GoogLeNet,":[235],"respectively.":[236],"tightly-integrated":[239],"N":[240],"CS2":[241],"showed":[243],"best":[245],"generalizability":[246],"efficiency":[250],"across":[251],"neural":[252],"networks.":[253]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":4}],"updated_date":"2026-04-02T15:55:50.835912","created_date":"2025-10-10T00:00:00"}