{"id":"https://openalex.org/W2998901775","doi":"https://doi.org/10.1109/ipccc47392.2019.8958760","title":"GPUs Cache Performance Estimation using Reuse Distance Analysis","display_name":"GPUs Cache Performance Estimation using Reuse Distance Analysis","publication_year":2019,"publication_date":"2019-10-01","ids":{"openalex":"https://openalex.org/W2998901775","doi":"https://doi.org/10.1109/ipccc47392.2019.8958760","mag":"2998901775"},"language":"en","primary_location":{"id":"doi:10.1109/ipccc47392.2019.8958760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipccc47392.2019.8958760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 38th International Performance Computing and Communications Conference (IPCCC)","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/A5001017727","display_name":"Yehia Arafa","orcid":"https://orcid.org/0000-0002-5186-3012"},"institutions":[{"id":"https://openalex.org/I10052268","display_name":"New Mexico State University","ror":"https://ror.org/00hpz7z43","country_code":"US","type":"education","lineage":["https://openalex.org/I10052268"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yehia Arafa","raw_affiliation_strings":["Klipsch School of Electrical and Computer Engineering, New Mexico State University, Las Cruces, NM, USA"],"affiliations":[{"raw_affiliation_string":"Klipsch School of Electrical and Computer Engineering, New Mexico State University, Las Cruces, NM, USA","institution_ids":["https://openalex.org/I10052268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063725454","display_name":"Gopinath Chennupati","orcid":"https://orcid.org/0000-0002-6223-8570"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gopinath Chennupati","raw_affiliation_strings":["Los Alamos National Laboratory, Los Alamos, NM, USA"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5074965377","display_name":"Atanu Barai","orcid":"https://orcid.org/0000-0002-6879-4455"},"institutions":[{"id":"https://openalex.org/I10052268","display_name":"New Mexico State University","ror":"https://ror.org/00hpz7z43","country_code":"US","type":"education","lineage":["https://openalex.org/I10052268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Atanu Barai","raw_affiliation_strings":["Klipsch School of Electrical and Computer Engineering, New Mexico State University, Las Cruces, NM, USA"],"affiliations":[{"raw_affiliation_string":"Klipsch School of Electrical and Computer Engineering, New Mexico State University, Las Cruces, NM, USA","institution_ids":["https://openalex.org/I10052268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087778749","display_name":"Abdel\u2010Hameed A. Badawy","orcid":"https://orcid.org/0000-0001-8027-1449"},"institutions":[{"id":"https://openalex.org/I10052268","display_name":"New Mexico State University","ror":"https://ror.org/00hpz7z43","country_code":"US","type":"education","lineage":["https://openalex.org/I10052268"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdel-Hameed A. Badawy","raw_affiliation_strings":["Klipsch School of Electrical and Computer Engineering, New Mexico State University, Las Cruces, NM, USA"],"affiliations":[{"raw_affiliation_string":"Klipsch School of Electrical and Computer Engineering, New Mexico State University, Las Cruces, NM, USA","institution_ids":["https://openalex.org/I10052268"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053809539","display_name":"Nandakishore Santhi","orcid":"https://orcid.org/0000-0002-4755-7821"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nandakishore Santhi","raw_affiliation_strings":["Los Alamos National Laboratory, Los Alamos, NM, USA"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073911119","display_name":"Stephan Eidenbenz","orcid":"https://orcid.org/0000-0002-2628-1854"},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephan Eidenbenz","raw_affiliation_strings":["Los Alamos National Laboratory, Los Alamos, NM, USA"],"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory, Los Alamos, NM, USA","institution_ids":["https://openalex.org/I1343871089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5001017727"],"corresponding_institution_ids":["https://openalex.org/I10052268"],"apc_list":null,"apc_paid":null,"fwci":1.4767,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.82373184,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9998000264167786,"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/T11269","display_name":"Algorithms and Data Compression","score":0.996999979019165,"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/computer-science","display_name":"Computer science","score":0.8062288761138916},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.6905354261398315},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6100501418113708},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.505479097366333},{"id":"https://openalex.org/keywords/estimation","display_name":"Estimation","score":0.4811466932296753},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.39180153608322144}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8062288761138916},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6905354261398315},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6100501418113708},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.505479097366333},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.4811466932296753},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.39180153608322144},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ipccc47392.2019.8958760","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipccc47392.2019.8958760","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE 38th International Performance Computing and Communications Conference (IPCCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W645173616","https://openalex.org/W1979527452","https://openalex.org/W1984222112","https://openalex.org/W1991862572","https://openalex.org/W2024717934","https://openalex.org/W2029891792","https://openalex.org/W2032616619","https://openalex.org/W2033486618","https://openalex.org/W2060087084","https://openalex.org/W2062527253","https://openalex.org/W2080592089","https://openalex.org/W2084309410","https://openalex.org/W2091250014","https://openalex.org/W2094066970","https://openalex.org/W2098290747","https://openalex.org/W2101320423","https://openalex.org/W2104840748","https://openalex.org/W2112686638","https://openalex.org/W2117610793","https://openalex.org/W2128046183","https://openalex.org/W2128120785","https://openalex.org/W2397454561","https://openalex.org/W2528928843","https://openalex.org/W2574647542","https://openalex.org/W2605443074","https://openalex.org/W2777727847","https://openalex.org/W2783894799","https://openalex.org/W2785384037","https://openalex.org/W2796649226","https://openalex.org/W2903738101","https://openalex.org/W2921788688","https://openalex.org/W2947179428","https://openalex.org/W2991330024","https://openalex.org/W4237024478","https://openalex.org/W4241057782","https://openalex.org/W4250244364","https://openalex.org/W6712681754","https://openalex.org/W6746990507","https://openalex.org/W6750448596"],"related_works":["https://openalex.org/W2384475851","https://openalex.org/W2000444236","https://openalex.org/W2353602216","https://openalex.org/W2367078749","https://openalex.org/W2381798600","https://openalex.org/W1910583078","https://openalex.org/W2351618306","https://openalex.org/W2133117170","https://openalex.org/W2999162218","https://openalex.org/W1537443268"],"abstract_inverted_index":{"GPU":[0],"architects":[1],"have":[2],"introduced":[3],"on-chip":[4],"memories":[5],"in":[6,45,75],"GPUs":[7],"to":[8,14,18,27,41,65,102,133,155,183],"provide":[9],"local":[10],"storage":[11],"nearby":[12],"processing":[13],"reduce":[15],"the":[16,19,29,42,67,91,96,104,134,141,146,150,156,163,168,172,184,209],"traffic":[17],"device":[20,158],"global":[21],"memory.":[22],"From":[23],"then":[24],"on-wards,":[25],"modeling":[26],"predict":[28,66,103],"cache":[30,69,166,211],"performance":[31,70],"has":[32,51],"been":[33,53],"an":[34,86,100],"active":[35],"area":[36],"of":[37,90,99,145],"research.":[38],"However,":[39],"due":[40],"complexities":[43],"found":[44],"this":[46,50,58],"highly":[47],"parallel":[48],"hardware,":[49],"not":[52],"a":[54,62],"straightforward":[55],"task.":[56],"In":[57],"paper,":[59],"we":[60],"propose":[61],"memory":[63,97,109,174],"model":[64,78,132,147,200],"entire":[68],"(L1":[71],"&":[72],"L2":[73,164],"caches)":[74],"GPUs.":[76],"Our":[77],"is":[79,111,152,176,191,201],"based":[80],"on":[81,177],"reuse":[82,92],"distance.":[83],"We":[84,118],"use":[85,119],"analytical":[87],"probabilistic":[88],"measure":[89],"distance":[93],"distributions":[94],"from":[95,123],"traces":[98],"application":[101],"hit":[105],"rates.":[106],"The":[107,137],"application\u2019s":[108,173],"trace":[110,175],"extracted":[112],"using":[113],"NVIDIA\u2019s":[114],"SASSI":[115],"instrumentation":[116],"tool.":[117],"20":[120],"different":[121,210],"kernels":[122,151,185],"Polybench":[124],"and":[125,129,222],"Rodinia":[126],"benchmark":[127],"suites":[128],"compare":[130],"our":[131,199],"real":[135,157],"hardware.":[136],"results":[138],"show":[139],"that":[140],"average":[142,178],"prediction":[143],"accuracy":[144,161],"over":[148],"all":[149],"86.7%":[153],"compared":[154,182],"with":[159],"higher":[160],"for":[162,218],"(95.26%)":[165],"than":[167,194],"L1.":[169],"Furthermore,":[170,198],"extracting":[171],"4.":[179],"9x":[180],"slower":[181],"running":[186],"without":[187],"instrumentation.":[188],"This":[189],"overhead":[190],"much":[192],"smaller":[193],"other":[195],"published":[196],"results.":[197],"very":[202],"flexible":[203],"where":[204],"it":[205,214],"takes":[206],"into":[207],"account":[208],"parameters":[212],"thus":[213],"can":[215],"be":[216],"used":[217],"design":[219],"space":[220],"exploration":[221],"sensitivity":[223],"analysis.":[224]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":3}],"updated_date":"2026-03-25T13:04:00.132906","created_date":"2025-10-10T00:00:00"}