{"id":"https://openalex.org/W4409131830","doi":"https://doi.org/10.1109/hpec62836.2024.10938437","title":"ModelGauge: Inference Profiling of Deep-Learning Models","display_name":"ModelGauge: Inference Profiling of Deep-Learning Models","publication_year":2024,"publication_date":"2024-09-23","ids":{"openalex":"https://openalex.org/W4409131830","doi":"https://doi.org/10.1109/hpec62836.2024.10938437"},"language":"en","primary_location":{"id":"doi:10.1109/hpec62836.2024.10938437","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec62836.2024.10938437","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 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/A5094284604","display_name":"Calvin B. Gealy","orcid":"https://orcid.org/0000-0003-1173-0378"},"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":"Calvin B. Gealy","raw_affiliation_strings":["University of Pittsburgh,Electrical and Computer Engineering,Pittsburgh,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh,Electrical and Computer Engineering,Pittsburgh,United States","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042589258","display_name":"David Langerman","orcid":"https://orcid.org/0000-0001-8777-4655"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"David Langerman","raw_affiliation_strings":["NSF Center for Space, High-Performance, and Resilient Computing (SHREC),Pittsburgh,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"NSF Center for Space, High-Performance, and Resilient Computing (SHREC),Pittsburgh,United States","institution_ids":[]}]},{"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,Electrical and Computer Engineering,Pittsburgh,United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Pittsburgh,Electrical and Computer Engineering,Pittsburgh,United States","institution_ids":["https://openalex.org/I170201317"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3055,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.69252387,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.6855999827384949,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.6855999827384949,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.6597999930381775,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.6481000185012817,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/profiling","display_name":"Profiling (computer programming)","score":0.7692387104034424},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6967564821243286},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6802209615707397},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5564831495285034},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5425740480422974},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.42633256316185},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.06312429904937744}],"concepts":[{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.7692387104034424},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6967564821243286},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6802209615707397},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5564831495285034},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5425740480422974},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42633256316185},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.06312429904937744}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec62836.2024.10938437","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec62836.2024.10938437","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":12,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2964137095","https://openalex.org/W2992216616","https://openalex.org/W3179726888","https://openalex.org/W4221138647","https://openalex.org/W4393342166","https://openalex.org/W6749781174","https://openalex.org/W6762585180","https://openalex.org/W6769454693","https://openalex.org/W6787641489","https://openalex.org/W6793164127","https://openalex.org/W6802648153"],"related_works":["https://openalex.org/W2731899572","https://openalex.org/W2961085424","https://openalex.org/W3215138031","https://openalex.org/W4306674287","https://openalex.org/W3009238340","https://openalex.org/W4360585206","https://openalex.org/W4321369474","https://openalex.org/W4285208911","https://openalex.org/W4387369504","https://openalex.org/W3082895349"],"abstract_inverted_index":{"Identifying":[0],"trends":[1],"in":[2,23,158,206],"on-device":[3,96],"performance":[4],"between":[5,133,201],"different":[6,20,40,90],"deep-learning":[7],"models":[8,16,193,241,261],"is":[9,26,126,171,212,252],"often":[10],"challenging":[11],"given":[12],"the":[13,19,32,56,82,85,130,145,153,162,168,174,182,195,202,210,226,235,248],"variety":[14,259],"of":[15,38,84,147,155,204,247,260],"published":[17],"and":[18,35,48,94,116,136,143,179,192,198,209,234],"devices":[21,191],"used":[22,127],"deployment.":[24],"ModelGauge":[25,64,251],"a":[27,134,137,159,207,220,244,258],"proposed":[28],"solution":[29],"that":[30],"reports":[31],"latency,":[33],"memory,":[34],"bandwidth":[36],"behavior":[37,98,142],"many":[39,68,265],"inference":[41,78],"configurations.":[42],"Utilizing":[43],"ONNX":[44,58,91],"Runtime":[45],"for":[46,51,61,164,254],"CPUs":[47],"NVIDIA":[49,110,117,185],"TensorRT":[50],"GPUs,":[52],"as":[53,55],"well":[54],"standardized":[57],"model":[59,62,92,160,208],"format":[60],"definitions,":[63],"can":[65],"easily":[66],"profile":[67],"architectures,":[69],"allowing":[70],"deployment":[71],"engineers":[72],"easy":[73],"access":[74],"to":[75,128,140,161,238],"statistics":[76,256],"about":[77,257],"performance.":[79],"To":[80],"demonstrate":[81],"utility":[83,146],"tool,":[86],"we":[87,218],"compare":[88],"32":[89],"definitions":[93],"their":[95],"scaling":[97],"on":[99,173,181],"an":[100],"ARM":[101,175],"Cortex-A76":[102,176],"embedded":[103,114],"CPU,":[104,109],"AMD":[105],"EPYC":[106],"9374F":[107],"server":[108,119],"Jetson":[111],"Orin":[112],"Nano":[113],"GPU,":[115],"A100":[118,186],"GPU.":[120],"For":[121],"this":[122],"study,":[123],"Pearson":[124,169,199],"correlation":[125,170,200],"show":[129,144],"linear":[131,196],"relationship":[132],"metric":[135,222],"device":[138,236],"measurement":[139],"characterize":[141],"bulk":[148],"data":[149,227],"collection.":[150],"When":[151],"comparing":[152],"number":[154,203],"floating-point":[156],"operations":[157],"latency":[163,237],"single-image":[165],"batch":[166],"inference,":[167],"highest":[172],"at":[177,187,264],"0.990":[178],"lowest":[180],"highly":[183],"parallel":[184],"0.388.":[188],"Across":[189],"all":[190],"tested,":[194],"trend":[197],"parameters":[205],"memory":[211],"consistently":[213],"greater":[214],"than":[215],"0.9.":[216],"Additionally,":[217],"propose":[219],"new":[221],"found":[223],"by":[224],"analyzing":[225],"translation":[228],"lookaside":[229],"buffer":[230],"load":[231],"miss":[232],"count":[233],"help":[239],"indicate":[240],"not":[242],"using":[243],"significant":[245],"amount":[246],"device.":[249],"Overall,":[250],"useful":[253],"gathering":[255],"across":[262],"compute":[263],"scales.":[266]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}