{"id":"https://openalex.org/W4206191901","doi":"https://doi.org/10.1109/milcom52596.2021.9652907","title":"Towards an Accurate Latency Model for Convolutional Neural Network Layers on GPUs","display_name":"Towards an Accurate Latency Model for Convolutional Neural Network Layers on GPUs","publication_year":2021,"publication_date":"2021-11-29","ids":{"openalex":"https://openalex.org/W4206191901","doi":"https://doi.org/10.1109/milcom52596.2021.9652907"},"language":"en","primary_location":{"id":"doi:10.1109/milcom52596.2021.9652907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/milcom52596.2021.9652907","pdf_url":null,"source":{"id":"https://openalex.org/S4363608138","display_name":"MILCOM 2021 - 2021 IEEE Military Communications Conference (MILCOM)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MILCOM 2021 - 2021 IEEE Military Communications Conference (MILCOM)","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/A5100320430","display_name":"Jinyang Li","orcid":"https://orcid.org/0000-0002-1900-0719"},"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":"Jinyang Li","raw_affiliation_strings":["University of Illinois,Urbana-Champaign","University of Illinois, Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois,Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois, Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084554685","display_name":"Runyu Ma","orcid":null},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Runyu Ma","raw_affiliation_strings":["George Mason University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Mason University","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041724753","display_name":"Vikram Sharma Mailthody","orcid":"https://orcid.org/0000-0002-9611-8075"},"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":"Vikram Sharma Mailthody","raw_affiliation_strings":["University of Illinois,Urbana-Champaign","University of Illinois, Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois,Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois, Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011915615","display_name":"Colin Samplawski","orcid":null},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Colin Samplawski","raw_affiliation_strings":["University of Massachusetts Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023142437","display_name":"Benjamin M. Marlin","orcid":"https://orcid.org/0000-0002-2626-3410"},"institutions":[{"id":"https://openalex.org/I24603500","display_name":"University of Massachusetts Amherst","ror":"https://ror.org/0072zz521","country_code":"US","type":"education","lineage":["https://openalex.org/I24603500"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benjamin Marlin","raw_affiliation_strings":["University of Massachusetts Amherst"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Massachusetts Amherst","institution_ids":["https://openalex.org/I24603500"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065505890","display_name":"Songqing Chen","orcid":"https://orcid.org/0000-0003-4650-7125"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Songqing Chen","raw_affiliation_strings":["George Mason University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Mason University","institution_ids":["https://openalex.org/I162714631"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102736697","display_name":"Shuochao Yao","orcid":"https://orcid.org/0000-0001-7446-1430"},"institutions":[{"id":"https://openalex.org/I162714631","display_name":"George Mason University","ror":"https://ror.org/02jqj7156","country_code":"US","type":"education","lineage":["https://openalex.org/I162714631"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuochao Yao","raw_affiliation_strings":["George Mason University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"George Mason University","institution_ids":["https://openalex.org/I162714631"]}]},{"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","University of Illinois, Urbana-Champaign"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Illinois,Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]},{"raw_affiliation_string":"University of Illinois, Urbana-Champaign","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"904","last_page":"909"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9991000294685364,"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":0.9991000294685364,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9918000102043152,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9914000034332275,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8869397640228271},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.6630051136016846},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6588600277900696},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6439577341079712},{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.643317461013794},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5777857303619385},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.5243006944656372},{"id":"https://openalex.org/keywords/workload","display_name":"Workload","score":0.49686411023139954},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4674815535545349},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.45871666073799133},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.45585426688194275},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4110926389694214},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.362240731716156},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3534281849861145},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3046227693557739},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15426436066627502}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8869397640228271},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.6630051136016846},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6588600277900696},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6439577341079712},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.643317461013794},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5777857303619385},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.5243006944656372},{"id":"https://openalex.org/C2778476105","wikidata":"https://www.wikidata.org/wiki/Q628539","display_name":"Workload","level":2,"score":0.49686411023139954},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4674815535545349},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.45871666073799133},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.45585426688194275},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4110926389694214},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.362240731716156},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3534281849861145},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3046227693557739},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15426436066627502},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/milcom52596.2021.9652907","is_oa":false,"landing_page_url":"https://doi.org/10.1109/milcom52596.2021.9652907","pdf_url":null,"source":{"id":"https://openalex.org/S4363608138","display_name":"MILCOM 2021 - 2021 IEEE Military Communications Conference (MILCOM)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"MILCOM 2021 - 2021 IEEE Military Communications Conference (MILCOM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth","score":0.6000000238418579}],"awards":[{"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/G8667858287","display_name":null,"funder_award_id":"CPS 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/F4320306077","display_name":"Boeing","ror":"https://ror.org/04sm5zn07"},{"id":"https://openalex.org/F4320338295","display_name":"Army Research Laboratory","ror":"https://ror.org/011hc8f90"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2093843662","https://openalex.org/W2619500264","https://openalex.org/W2752512710","https://openalex.org/W2886851211","https://openalex.org/W2953264125","https://openalex.org/W2962965870","https://openalex.org/W2963728985","https://openalex.org/W2987755031","https://openalex.org/W3004853346","https://openalex.org/W3105696640","https://openalex.org/W3165698711","https://openalex.org/W3213084269","https://openalex.org/W4287715829","https://openalex.org/W4289305285","https://openalex.org/W4302296459","https://openalex.org/W6637151318","https://openalex.org/W6673829052","https://openalex.org/W6726275242","https://openalex.org/W6780506207"],"related_works":["https://openalex.org/W2479014312","https://openalex.org/W1583465708","https://openalex.org/W4312417841","https://openalex.org/W4321369474","https://openalex.org/W2348361596","https://openalex.org/W4310880831","https://openalex.org/W2521117258","https://openalex.org/W3210895857","https://openalex.org/W2904058793","https://openalex.org/W4220896354"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNN)":[3],"have":[4,76],"shown":[5],"great":[6],"success":[7],"in":[8,50,114,157,166],"many":[9],"sensing":[10],"and":[11,89,117,171,174,186,203],"recognition":[12],"applications.":[13],"However,":[14,60],"the":[15,63,77,87,98,106,115,150,153,167,176],"excessive":[16],"resource":[17],"demand":[18],"remains":[19],"a":[20,36,58,71,93,140],"major":[21,163],"barrier":[22],"against":[23],"their":[24],"deployment":[25],"on":[26,138,200],"low-end":[27],"devices.":[28],"Optimizations,":[29],"such":[30],"as":[31,92],"model":[32,56,143,182,197],"compression,":[33],"are":[34],"thus":[35],"need":[37,123],"for":[38,144,149],"practical":[39],"deployment.":[40],"To":[41],"fully":[42],"exploit":[43],"existing":[44],"system":[45,118],"resources,":[46],"platform-aware":[47],"optimizations":[48],"emerged":[49],"recent":[51],"years,":[52],"where":[53],"an":[54],"execution-time":[55],"becomes":[57],"necessity.":[59],"non-monotonicity":[61],"over":[62,82],"network":[64],"configuration":[65],"space":[66],"makes":[67],"execution":[68,155],"time":[69,156],"modeling":[70],"challenging":[72],"task.":[73],"Data-driven":[74],"approaches":[75],"advantage":[78],"of":[79,100,152],"being":[80],"portable":[81],"different":[83,201],"platforms":[84,202],"by":[85,130],"treating":[86],"hardware":[88],"software":[90],"stack":[91],"black":[94],"box":[95],"but":[96,126],"at":[97],"cost":[99],"extremely":[101],"long":[102],"profiling":[103,125,189],"time.":[104],"On":[105],"other":[107],"hand,":[108],"analytical":[109],"models":[110],"can":[111,187],"be":[112],"found":[113],"architecture":[116],"literature":[119],"that":[120,147,195],"do":[121],"not":[122],"heavy":[124],"require":[127],"laborious":[128],"analysis":[129],"domain":[131],"experts.":[132],"In":[133],"this":[134],"paper,":[135],"we":[136],"focus":[137],"building":[139],"general":[141],"latency":[142,170],"convolutional":[145],"layers":[146],"account":[148],"majority":[151],"total":[154],"CNN":[158,204],"models.":[159,205],"We":[160],"identify":[161],"two":[162],"non-linear":[164],"modes":[165],"relationship":[168],"between":[169],"convolution":[172],"parameters,":[173],"analyze":[175],"mechanism":[177],"behind":[178],"them.":[179],"The":[180,191],"resulting":[181],"has":[183],"better":[184],"interpretability":[185],"reduce":[188],"workload.":[190],"evaluation":[192],"results":[193],"show":[194],"our":[196],"outperforms":[198],"baselines":[199]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":5}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}