{"id":"https://openalex.org/W2062527253","doi":"https://doi.org/10.1145/2751205.2751237","title":"Locality-Driven Dynamic GPU Cache Bypassing","display_name":"Locality-Driven Dynamic GPU Cache Bypassing","publication_year":2015,"publication_date":"2015-06-02","ids":{"openalex":"https://openalex.org/W2062527253","doi":"https://doi.org/10.1145/2751205.2751237","mag":"2062527253"},"language":"en","primary_location":{"id":"doi:10.1145/2751205.2751237","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2751205.2751237","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2751237&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM on International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=2751237&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100323120","display_name":"Chao Li","orcid":"https://orcid.org/0000-0002-6946-4335"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chao Li","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5043209884","display_name":"Shuaiwen Leon Song","orcid":"https://orcid.org/0000-0002-8402-1436"},"institutions":[{"id":"https://openalex.org/I142606810","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307","country_code":"US","type":"facility","lineage":["https://openalex.org/I1325736334","https://openalex.org/I1330989302","https://openalex.org/I142606810","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Shuaiwen Leon Song","raw_affiliation_strings":["Pacific Northwest National Lab, Richland, WA, USA","Pacific Northwest National Laboratories Richland WA USA"],"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Lab, Richland, WA, USA","institution_ids":["https://openalex.org/I142606810"]},{"raw_affiliation_string":"Pacific Northwest National Laboratories Richland WA USA","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037376215","display_name":"Hongwen Dai","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongwen Dai","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004915198","display_name":"Albert Sidelnik","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Albert Sidelnik","raw_affiliation_strings":["NVIDIA Research, Santa Clara, CA, USA",", NVIDIA Research, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA Research, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":", NVIDIA Research, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054590774","display_name":"Siva Kumar Sastry Hari","orcid":"https://orcid.org/0000-0001-8346-7981"},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siva Kumar Sastry Hari","raw_affiliation_strings":["NVIDIA Research, Santa Clara, CA, USA",", NVIDIA Research, Santa Clara, CA, USA"],"affiliations":[{"raw_affiliation_string":"NVIDIA Research, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]},{"raw_affiliation_string":", NVIDIA Research, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072755725","display_name":"Huiyang Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Huiyang Zhou","raw_affiliation_strings":["North Carolina State University, Raleigh, NC, USA"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC, USA","institution_ids":["https://openalex.org/I137902535"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100323120"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":18.136,"has_fulltext":true,"cited_by_count":109,"citation_normalized_percentile":{"value":0.99568221,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"67","last_page":"77"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9991999864578247,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8857742547988892},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7080749869346619},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.6860544085502625},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.6447495222091675},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.48246222734451294},{"id":"https://openalex.org/keywords/cache-pollution","display_name":"Cache pollution","score":0.4626833498477936},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.43788453936576843},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.43602582812309265},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.4354647099971771},{"id":"https://openalex.org/keywords/page-cache","display_name":"Page cache","score":0.41296103596687317},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.4036547839641571},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.36911651492118835},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.25943076610565186}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8857742547988892},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7080749869346619},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.6860544085502625},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.6447495222091675},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.48246222734451294},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.4626833498477936},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.43788453936576843},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.43602582812309265},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.4354647099971771},{"id":"https://openalex.org/C36340418","wikidata":"https://www.wikidata.org/wiki/Q7124288","display_name":"Page cache","level":5,"score":0.41296103596687317},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.4036547839641571},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.36911651492118835},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.25943076610565186},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2751205.2751237","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2751205.2751237","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2751237&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM on International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2751205.2751237","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2751205.2751237","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2751237&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 29th ACM on International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8299999833106995,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G1899721271","display_name":null,"funder_award_id":"AC05-76RL01830","funder_id":"https://openalex.org/F4320306250","funder_display_name":"Battelle"},{"id":"https://openalex.org/G2506945562","display_name":null,"funder_award_id":"76RL01830","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2510423872","display_name":null,"funder_award_id":"AC05-76RL01830","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G2865512842","display_name":null,"funder_award_id":"DE-AC05-76RL01830","funder_id":"https://openalex.org/F4320337506","funder_display_name":"Advanced Scientific Computing Research"},{"id":"https://openalex.org/G5200347334","display_name":null,"funder_award_id":"DE-AC05-76RL01830","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G5269527469","display_name":null,"funder_award_id":"DE-AC05-76RL0","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G5321382714","display_name":null,"funder_award_id":"76RL01830","funder_id":"https://openalex.org/F4320338354","funder_display_name":"Pacific Northwest National Laboratory"},{"id":"https://openalex.org/G5726405315","display_name":null,"funder_award_id":"DE-AC05","funder_id":"https://openalex.org/F4320306250","funder_display_name":"Battelle"},{"id":"https://openalex.org/G6397265742","display_name":null,"funder_award_id":"Beyond Standard Modeling","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6664334341","display_name":null,"funder_award_id":"DE-AC05-76RL01830","funder_id":"https://openalex.org/F4320306250","funder_display_name":"Battelle"},{"id":"https://openalex.org/G7200503492","display_name":null,"funder_award_id":"DE-AC05-76RL01830","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7560550554","display_name":null,"funder_award_id":"76RL01830","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7995982022","display_name":null,"funder_award_id":"DE-AC05","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8236974595","display_name":null,"funder_award_id":"DE-AC05-76RL0183","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8277545319","display_name":null,"funder_award_id":"DE-AC05-76RL01830.","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8414908677","display_name":null,"funder_award_id":"DE-AC0","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G998451652","display_name":null,"funder_award_id":"DE-AC05-76RL01830.","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320306250","display_name":"Battelle","ror":"https://ror.org/01h5tnr73"},{"id":"https://openalex.org/F4320337506","display_name":"Advanced Scientific Computing Research","ror":"https://ror.org/0012c7r22"},{"id":"https://openalex.org/F4320338354","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2062527253.pdf","grobid_xml":"https://content.openalex.org/works/W2062527253.grobid-xml"},"referenced_works_count":30,"referenced_works":["https://openalex.org/W1970643910","https://openalex.org/W1979527452","https://openalex.org/W1982996921","https://openalex.org/W1997162567","https://openalex.org/W1997352364","https://openalex.org/W2010133494","https://openalex.org/W2016352575","https://openalex.org/W2020572638","https://openalex.org/W2027806965","https://openalex.org/W2029577083","https://openalex.org/W2031043969","https://openalex.org/W2047060659","https://openalex.org/W2065562952","https://openalex.org/W2067441262","https://openalex.org/W2080592089","https://openalex.org/W2084309410","https://openalex.org/W2090584832","https://openalex.org/W2095258606","https://openalex.org/W2097336080","https://openalex.org/W2100901045","https://openalex.org/W2105937753","https://openalex.org/W2109432325","https://openalex.org/W2117610793","https://openalex.org/W2130749431","https://openalex.org/W2131926352","https://openalex.org/W2135089498","https://openalex.org/W2142444503","https://openalex.org/W2150073849","https://openalex.org/W2152956697","https://openalex.org/W4233785673"],"related_works":["https://openalex.org/W2020176098","https://openalex.org/W2535115842","https://openalex.org/W2298260853","https://openalex.org/W2363769136","https://openalex.org/W2118932116","https://openalex.org/W2012518269","https://openalex.org/W2086718556","https://openalex.org/W1496086148","https://openalex.org/W1965891727","https://openalex.org/W1860107648"],"abstract_inverted_index":{"This":[0],"paper":[1],"presents":[2],"novel":[3],"cache":[4,82,86],"optimizations":[5],"for":[6,21,53,66,101],"massively":[7],"parallel,":[8],"throughput-oriented":[9],"architectures":[10],"like":[11],"GPUs.":[12],"L1":[13,45,64],"data":[14,26],"caches":[15],"(L1":[16],"D-caches)":[17],"are":[18,89],"critical":[19],"resources":[20],"providing":[22],"high-bandwidth":[23],"and":[24,49],"low-latency":[25],"accesses.":[27],"However,":[28],"the":[29,41,59,81],"high":[30],"number":[31],"of":[32,44,73],"simultaneous":[33],"requests":[34,74],"from":[35],"single-instruction":[36],"multiple-thread":[37],"(SIMT)":[38],"cores":[39],"makes":[40],"limited":[42],"capacity":[43],"D-caches":[46,65],"a":[47,70],"performance":[48],"energy":[50],"bottleneck,":[51],"especially":[52],"memory-intensive":[54],"applications.":[55],"We":[56],"observe":[57],"that":[58],"memory":[60],"access":[61],"streams":[62],"to":[63],"many":[67],"applications":[68],"contain":[69],"significant":[71],"amount":[72],"with":[75],"low":[76],"reuse,":[77],"which":[78,106],"greatly":[79],"reduce":[80],"efficacy.":[83],"Existing":[84],"GPU":[85],"management":[87],"schemes":[88],"either":[90],"based":[91,97],"on":[92],"conditional/reactive":[93],"solutions":[94],"or":[95],"hit-rate":[96],"designs":[98],"specifically":[99],"developed":[100],"CPU":[102],"last":[103],"level":[104],"caches,":[105],"can":[107],"limit":[108],"overall":[109],"performance.":[110]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":22},{"year":2018,"cited_by_count":21},{"year":2017,"cited_by_count":16},{"year":2016,"cited_by_count":13},{"year":2015,"cited_by_count":5}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}