{"id":"https://openalex.org/W3046181883","doi":"https://doi.org/10.1109/mm.2020.3012514","title":"Countering Load-to-Use Stalls in the NVIDIA Turing GPU","display_name":"Countering Load-to-Use Stalls in the NVIDIA Turing GPU","publication_year":2020,"publication_date":"2020-07-28","ids":{"openalex":"https://openalex.org/W3046181883","doi":"https://doi.org/10.1109/mm.2020.3012514","mag":"3046181883"},"language":"en","primary_location":{"id":"doi:10.1109/mm.2020.3012514","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mm.2020.3012514","pdf_url":null,"source":{"id":"https://openalex.org/S59697426","display_name":"IEEE Micro","issn_l":"0272-1732","issn":["0272-1732","1937-4143"],"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 Micro","raw_type":"journal-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/A5074023662","display_name":"Ram Rangan","orcid":"https://orcid.org/0000-0003-4191-4151"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Ram Rangan","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076305257","display_name":"Naman Turakhia","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Naman Turakhia","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078238387","display_name":"Alexandre Joly","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandre Joly","raw_affiliation_strings":["NVIDIA"],"affiliations":[{"raw_affiliation_string":"NVIDIA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5074023662"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4625,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.66517842,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"40","issue":"6","first_page":"59","last_page":"66"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9983999729156494,"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9980999827384949,"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/T11017","display_name":"Chaos-based Image/Signal Encryption","score":0.9965000152587891,"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":0.8541603088378906},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7419094443321228},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5373145341873169},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.527862012386322},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2838976979255676},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.22222551703453064}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8541603088378906},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7419094443321228},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5373145341873169},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.527862012386322},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2838976979255676},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.22222551703453064}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/mm.2020.3012514","is_oa":false,"landing_page_url":"https://doi.org/10.1109/mm.2020.3012514","pdf_url":null,"source":{"id":"https://openalex.org/S59697426","display_name":"IEEE Micro","issn_l":"0272-1732","issn":["0272-1732","1937-4143"],"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 Micro","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.6100000143051147,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W762076161","https://openalex.org/W2029926205","https://openalex.org/W2084110734","https://openalex.org/W2118826546","https://openalex.org/W2142033140","https://openalex.org/W2982236015","https://openalex.org/W6657044653"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W3213381848","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759"],"abstract_inverted_index":{"Among":[0],"its":[1],"various":[2],"improvements":[3],"over":[4],"prior":[5],"NVIDIA":[6,9],"GPUs,":[7],"the":[8,41,46,83,94,127],"Turing":[10],"GPU":[11],"boasts":[12],"of":[13,86,88,96,135],"four":[14],"key":[15],"performance":[16],"enhancements":[17,85,129],"to":[18,43,61,120],"effectively":[19],"counter":[20],"memory":[21,32,37,52,73],"load-to-use":[22,80],"stalls.":[23,81],"First,":[24],"reduced":[25],"latency":[26,122],"on":[27,137],"L1":[28,47,64,76],"hits":[29,77],"for":[30,68],"global":[31],"loads":[33],"helps":[34],"lower":[35],"average":[36,133],"lookup":[38],"latency.":[39],"Next,":[40],"ability":[42],"dynamically":[44],"configure":[45],"data":[48,65],"RAM":[49],"between":[50],"cacheable":[51],"and":[53,78,93,113],"scratchpad":[54],"or":[55,100],"shared":[56,72],"memory,":[57],"enables":[58],"driver":[59],"software":[60],"opportunistically":[62],"maximize":[63],"cache":[66],"size":[67],"programs":[69],"with":[70,105],"low":[71],"requirements,":[74],"increasing":[75],"reducing":[79],"Finally,":[82],"twin":[84],"doubling":[87],"vector":[89,110],"register":[90,102,111],"file":[91,103],"capacity":[92],"addition":[95],"a":[97,106],"dedicated":[98],"scalar":[99],"uniform":[101,107],"along":[104],"datapath,":[108],"ease":[109],"pressure":[112],"enable":[114],"higher":[115],"warp":[116],"level":[117],"parallelism,":[118],"leading":[119],"better":[121],"tolerance.":[123],"We":[124],"find":[125],"that":[126],"above":[128],"combined":[130],"deliver":[131],"an":[132],"speedup":[134],"11%":[136],"modern":[138],"gaming":[139],"applications.":[140]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}