{"id":"https://openalex.org/W4398226075","doi":"https://doi.org/10.1109/tcad.2024.3404413","title":"Rethinking Latency-Aware DNN Design With GPU Tail Effect Analysis","display_name":"Rethinking Latency-Aware DNN Design With GPU Tail Effect Analysis","publication_year":2024,"publication_date":"2024-05-22","ids":{"openalex":"https://openalex.org/W4398226075","doi":"https://doi.org/10.1109/tcad.2024.3404413"},"language":"en","primary_location":{"id":"doi:10.1109/tcad.2024.3404413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2024.3404413","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.13016/m20hnm-cbw2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103085687","display_name":"Fuxun Yu","orcid":"https://orcid.org/0000-0002-4880-6658"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fuxun Yu","raw_affiliation_strings":["Department of Research and Development, Microsoft Corporation, Redmond, WA, USA","Microsoft, USA"],"raw_orcid":"https://orcid.org/0000-0002-4880-6658","affiliations":[{"raw_affiliation_string":"Department of Research and Development, Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030027584","display_name":"Zirui Xu","orcid":"https://orcid.org/0000-0002-3556-9358"},"institutions":[{"id":"https://openalex.org/I4210115892","display_name":"CVS Health (United States)","ror":"https://ror.org/02jfw4p72","country_code":"US","type":"company","lineage":["https://openalex.org/I4210115892"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zirui Xu","raw_affiliation_strings":["Department of Research and Development, CVS Health Corporation, Woonsocket, RI, USA","CVS Helalth, USA"],"raw_orcid":"https://orcid.org/0000-0002-3556-9358","affiliations":[{"raw_affiliation_string":"Department of Research and Development, CVS Health Corporation, Woonsocket, RI, USA","institution_ids":["https://openalex.org/I4210115892"]},{"raw_affiliation_string":"CVS Helalth, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070325443","display_name":"Longfei Shangguan","orcid":"https://orcid.org/0000-0002-1153-7087"},"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":"Longfei Shangguan","raw_affiliation_strings":["Department of Computer Science, University of Pittsburgh, Pittsburgh, PA, USA","University of Pittsburgh, USA"],"raw_orcid":"https://orcid.org/0000-0002-1153-7087","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Pittsburgh, Pittsburgh, PA, USA","institution_ids":["https://openalex.org/I170201317"]},{"raw_affiliation_string":"University of Pittsburgh, USA","institution_ids":["https://openalex.org/I170201317"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102729322","display_name":"Di Wang","orcid":"https://orcid.org/0000-0001-8003-9738"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Di Wang","raw_affiliation_strings":["Department of Research and Development, Microsoft Corporation, Redmond, WA, USA","Microsoft, USA"],"raw_orcid":"https://orcid.org/0000-0001-8003-9738","affiliations":[{"raw_affiliation_string":"Department of Research and Development, Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032077042","display_name":"Dimitrios Stamoulis","orcid":"https://orcid.org/0000-0003-1682-9350"},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dimitrios Stamoulis","raw_affiliation_strings":["Department of Research and Development, Microsoft Corporation, Redmond, WA, USA","Microsoft, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Research and Development, Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075264465","display_name":"Rishi Madhok","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Rishi Madhok","raw_affiliation_strings":["Department of Research and Development, Microsoft Corporation, Redmond, WA, USA","Microsoft, USA"],"raw_orcid":"https://orcid.org/0000-0001-8124-5744","affiliations":[{"raw_affiliation_string":"Department of Research and Development, Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076846509","display_name":"Nikolaos Karianakis","orcid":null},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikolaos Karianakis","raw_affiliation_strings":["Department of Research and Development, Microsoft Corporation, Redmond, WA, USA","Microsoft, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Research and Development, Microsoft Corporation, Redmond, WA, USA","institution_ids":["https://openalex.org/I1290206253"]},{"raw_affiliation_string":"Microsoft, USA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413657","display_name":"Ang Li","orcid":"https://orcid.org/0000-0003-3734-9137"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ang Li","raw_affiliation_strings":["Department of Electrical and Computer Engineering, University of Maryland at College Park, College Park, MD, USA","University of Maryland, College Park, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, University of Maryland at College Park, College Park, MD, USA","institution_ids":["https://openalex.org/I66946132"]},{"raw_affiliation_string":"University of Maryland, College Park, USA","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":null,"display_name":"ChenChen Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I79272384","display_name":"University of Maryland, Baltimore County","ror":"https://ror.org/02qskvh78","country_code":"US","type":"education","lineage":["https://openalex.org/I79272384"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"ChenChen Liu","raw_affiliation_strings":["Department of Computer Science and Electrical Engineering, University of Maryland at Baltimore County, Baltimore, MD, USA","University of Maryland, Baltimore County, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Electrical Engineering, University of Maryland at Baltimore County, Baltimore, MD, USA","institution_ids":["https://openalex.org/I79272384"]},{"raw_affiliation_string":"University of Maryland, Baltimore County, USA","institution_ids":["https://openalex.org/I79272384"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058073627","display_name":"Yiran Chen","orcid":"https://orcid.org/0000-0002-1486-8412"},"institutions":[{"id":"https://openalex.org/I170897317","display_name":"Duke University","ror":"https://ror.org/00py81415","country_code":"US","type":"education","lineage":["https://openalex.org/I170897317"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yiran Chen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA","Duke University, USA"],"raw_orcid":"https://orcid.org/0000-0002-1486-8412","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA","institution_ids":["https://openalex.org/I170897317"]},{"raw_affiliation_string":"Duke University, USA","institution_ids":["https://openalex.org/I170897317"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100441957","display_name":"Xiang Chen","orcid":"https://orcid.org/0000-0003-2790-976X"},"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"]},{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]}],"countries":["CN","US"],"is_corresponding":false,"raw_author_name":"Xiang Chen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, George Mason University, Fairfax, VA, USA","George Mason University, USA","Peking University, China"],"raw_orcid":"https://orcid.org/0000-0003-2790-976X","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, George Mason University, Fairfax, VA, USA","institution_ids":["https://openalex.org/I162714631"]},{"raw_affiliation_string":"George Mason University, USA","institution_ids":["https://openalex.org/I162714631"]},{"raw_affiliation_string":"Peking University, China","institution_ids":["https://openalex.org/I20231570"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.07615402,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"44","issue":"1","first_page":"266","last_page":"279"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9767000079154968,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9767000079154968,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.961899995803833,"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/T12676","display_name":"Machine Learning and ELM","score":0.9254999756813049,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.668046236038208},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6548300385475159},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4524692893028259},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.34986329078674316},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.08442482352256775}],"concepts":[{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.668046236038208},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6548300385475159},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4524692893028259},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.34986329078674316},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.08442482352256775}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/tcad.2024.3404413","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcad.2024.3404413","pdf_url":null,"source":{"id":"https://openalex.org/S100835903","display_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","issn_l":"0278-0070","issn":["0278-0070","1937-4151"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems","raw_type":"journal-article"},{"id":"pmh:oai:mdsoar.org:11603/34887","is_oa":false,"landing_page_url":"http://hdl.handle.net/11603/34887","pdf_url":null,"source":{"id":"https://openalex.org/S4306402556","display_name":"Maryland Shared Open Access Repository (USMAI Consortium)","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":null,"raw_type":"Text"},{"id":"doi:10.13016/m20hnm-cbw2","is_oa":true,"landing_page_url":"https://doi.org/10.13016/m20hnm-cbw2","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article-journal"}],"best_oa_location":{"id":"doi:10.13016/m20hnm-cbw2","is_oa":true,"landing_page_url":"https://doi.org/10.13016/m20hnm-cbw2","pdf_url":null,"source":{"id":"https://openalex.org/S4306402644","display_name":"Digital Repository at the University of Maryland (University of Maryland College Park)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I66946132","host_organization_name":"University of Maryland, College Park","host_organization_lineage":["https://openalex.org/I66946132"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article-journal"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2143612262","https://openalex.org/W2194775991","https://openalex.org/W2804032941","https://openalex.org/W2808168148","https://openalex.org/W2886851211","https://openalex.org/W2928560789","https://openalex.org/W2945357343","https://openalex.org/W2949941638","https://openalex.org/W2955425717","https://openalex.org/W2962851801","https://openalex.org/W2962861284","https://openalex.org/W2963163009","https://openalex.org/W2963363373","https://openalex.org/W2963918968","https://openalex.org/W2967733054","https://openalex.org/W2980137827","https://openalex.org/W2981758446","https://openalex.org/W3034513523","https://openalex.org/W3037681773","https://openalex.org/W3094502228","https://openalex.org/W3138516171","https://openalex.org/W3165698711","https://openalex.org/W4239072543","https://openalex.org/W4251637954","https://openalex.org/W4297775537","https://openalex.org/W4386065441","https://openalex.org/W4386083031","https://openalex.org/W4395113676","https://openalex.org/W6637373629","https://openalex.org/W6737664043","https://openalex.org/W6751349269","https://openalex.org/W6758474236","https://openalex.org/W6762718338","https://openalex.org/W6857137501"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052","https://openalex.org/W2382290278","https://openalex.org/W4395014643"],"abstract_inverted_index":{"As":[0],"the":[1,27,45,49,71,76,86,100,105,112],"size":[2],"of":[3,75,88,109],"Deep":[4],"Neural":[5,20],"Networks":[6],"(DNNs)":[7],"continues":[8],"to":[9,33,130],"grow,":[10],"their":[11,30],"runtime":[12,37,140],"latency":[13,38,55,141,150],"also":[14],"scales.":[15],"While":[16],"model":[17,143],"pruning":[18,135,155],"and":[19,54,84,96,104,126,134,137,142,156],"Architecture":[21],"Search":[22],"(NAS)":[23],"can":[24],"effectively":[25],"reduce":[26],"computation":[28],"workload,":[29],"effectiveness":[31],"fails":[32],"consistently":[34],"translate":[35],"into":[36],"reduction.":[39],"In":[40],"this":[41],"paper,":[42],"we":[43],"identify":[44],"root":[46],"cause":[47],"behind":[48],"mismatch":[50],"between":[51],"workload":[52,82,108],"reduction":[53,56,151],"is":[57],"GPU":[58,89],"tail":[59,90,113],"effect":[60,91,114],"\u2013":[61],"a":[62,121],"classic":[63],"system":[64],"issue":[65],"caused":[66],"by":[67],"resource":[68],"under-utilization":[69],"in":[70],"last":[72],"processing":[73],"wave":[74],"GPU.":[77],"We":[78,118],"conduct":[79],"detailed":[80],"DNN":[81,94,116,127,154],"characterization":[83],"demonstrate":[85],"prevalence":[87],"across":[92],"different":[93],"architectures,":[95],"meanwhile":[97],"reveal":[98],"that":[99],"unique":[101],"deep":[102],"structure":[103],"light-weight":[106],"layer":[107],"DNNs":[110],"exacerbate":[111],"for":[115],"inference.":[117],"then":[119],"propose":[120],"tail-awareness":[122],"design":[123],"space":[124],"enhancement":[125],"optimization":[128],"algorithm":[129],"optimize":[131],"existing":[132],"NAS":[133,157],"designs":[136],"achieve":[138],"better":[139],"accuracy":[144],"performance.":[145],"Extensive":[146],"experiments":[147],"show":[148],"11%-27%":[149],"over":[152],"SOTA":[153],"methods.":[158]},"counts_by_year":[],"updated_date":"2026-07-26T07:53:14.480251","created_date":"2025-10-10T00:00:00"}
