{"id":"https://openalex.org/W2417236060","doi":"https://doi.org/10.1145/2925426.2926253","title":"Tag-Split Cache for Efficient GPGPU Cache Utilization","display_name":"Tag-Split Cache for Efficient GPGPU Cache Utilization","publication_year":2016,"publication_date":"2016-06-01","ids":{"openalex":"https://openalex.org/W2417236060","doi":"https://doi.org/10.1145/2925426.2926253","mag":"2417236060"},"language":"en","primary_location":{"id":"doi:10.1145/2925426.2926253","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2925426.2926253","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2926253&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Supercomputing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"http://dl.acm.org/ft_gateway.cfm?id=2926253&type=pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069592458","display_name":"Lingda Li","orcid":"https://orcid.org/0000-0003-3431-0173"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Lingda Li","raw_affiliation_strings":["Department of Computer Science, Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070117880","display_name":"Ari B. Hayes","orcid":null},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ari B. Hayes","raw_affiliation_strings":["Department of Computer Science, Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]},{"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"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Pacific Northwest National Lab","institution_ids":["https://openalex.org/I142606810"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071204460","display_name":"Eddy Z. Zhang","orcid":"https://orcid.org/0000-0002-3815-4318"},"institutions":[{"id":"https://openalex.org/I4210096112","display_name":"Rutgers Sexual and Reproductive Health and Rights","ror":"https://ror.org/00rcvgx40","country_code":"NL","type":"other","lineage":["https://openalex.org/I4210096112"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Eddy Z. Zhang","raw_affiliation_strings":["Department of Computer Science, Rutgers University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Rutgers University","institution_ids":["https://openalex.org/I4210096112"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"12"},"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":0.9995999932289124,"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":0.9976999759674072,"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/cache","display_name":"Cache","score":0.8774945735931396},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8575197458267212},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.8299074172973633},{"id":"https://openalex.org/keywords/cache-coloring","display_name":"Cache coloring","score":0.8270779252052307},{"id":"https://openalex.org/keywords/cache-pollution","display_name":"Cache pollution","score":0.7994236350059509},{"id":"https://openalex.org/keywords/cache-invalidation","display_name":"Cache invalidation","score":0.7687768936157227},{"id":"https://openalex.org/keywords/page-cache","display_name":"Page cache","score":0.7470755577087402},{"id":"https://openalex.org/keywords/smart-cache","display_name":"Smart Cache","score":0.7379209399223328},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7104682326316833},{"id":"https://openalex.org/keywords/cache-oblivious-algorithm","display_name":"Cache-oblivious algorithm","score":0.5883297920227051},{"id":"https://openalex.org/keywords/mesi-protocol","display_name":"MESI protocol","score":0.47684040665626526},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.4065425992012024},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3790147006511688}],"concepts":[{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.8774945735931396},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8575197458267212},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.8299074172973633},{"id":"https://openalex.org/C201148951","wikidata":"https://www.wikidata.org/wiki/Q5015976","display_name":"Cache coloring","level":4,"score":0.8270779252052307},{"id":"https://openalex.org/C113166858","wikidata":"https://www.wikidata.org/wiki/Q5015981","display_name":"Cache pollution","level":5,"score":0.7994236350059509},{"id":"https://openalex.org/C25536678","wikidata":"https://www.wikidata.org/wiki/Q5015977","display_name":"Cache invalidation","level":5,"score":0.7687768936157227},{"id":"https://openalex.org/C36340418","wikidata":"https://www.wikidata.org/wiki/Q7124288","display_name":"Page cache","level":5,"score":0.7470755577087402},{"id":"https://openalex.org/C167713795","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"Smart Cache","level":5,"score":0.7379209399223328},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7104682326316833},{"id":"https://openalex.org/C59687516","wikidata":"https://www.wikidata.org/wiki/Q5015938","display_name":"Cache-oblivious algorithm","level":5,"score":0.5883297920227051},{"id":"https://openalex.org/C120936851","wikidata":"https://www.wikidata.org/wiki/Q1408065","display_name":"MESI protocol","level":5,"score":0.47684040665626526},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.4065425992012024},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3790147006511688}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2925426.2926253","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2925426.2926253","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2926253&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Supercomputing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/2925426.2926253","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2925426.2926253","pdf_url":"http://dl.acm.org/ft_gateway.cfm?id=2926253&type=pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2016 International Conference on Supercomputing","raw_type":"proceedings-article"},"sustainable_development_goals":[],"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/G1967746503","display_name":null,"funder_award_id":"DE-AC05-76RL01830","funder_id":"https://openalex.org/F4320338354","funder_display_name":"Pacific Northwest National Laboratory"},{"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/G282579023","display_name":null,"funder_award_id":"NSF-CCF-142150","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"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/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/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/G7761881832","display_name":null,"funder_award_id":"NSF-CCF-142150,","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"}],"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/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320333987","display_name":"Research Council, Rutgers, The State University of New Jersey","ror":null},{"id":"https://openalex.org/F4320337531","display_name":"Defense Sciences Office, DARPA","ror":"https://ror.org/0447fe631"},{"id":"https://openalex.org/F4320338354","display_name":"Pacific Northwest National Laboratory","ror":"https://ror.org/05h992307"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2417236060.pdf","grobid_xml":"https://content.openalex.org/works/W2417236060.grobid-xml"},"referenced_works_count":33,"referenced_works":["https://openalex.org/W1965644370","https://openalex.org/W1979527452","https://openalex.org/W1982996921","https://openalex.org/W1984271364","https://openalex.org/W1989061323","https://openalex.org/W2016481757","https://openalex.org/W2020572638","https://openalex.org/W2026486547","https://openalex.org/W2027806965","https://openalex.org/W2029577083","https://openalex.org/W2033486618","https://openalex.org/W2038932419","https://openalex.org/W2047060659","https://openalex.org/W2048441570","https://openalex.org/W2053744175","https://openalex.org/W2062527253","https://openalex.org/W2065132365","https://openalex.org/W2067441262","https://openalex.org/W2080592089","https://openalex.org/W2080958936","https://openalex.org/W2084309410","https://openalex.org/W2091583059","https://openalex.org/W2092406519","https://openalex.org/W2093043622","https://openalex.org/W2098505406","https://openalex.org/W2119296805","https://openalex.org/W2124350608","https://openalex.org/W2141302915","https://openalex.org/W2144650313","https://openalex.org/W2151460056","https://openalex.org/W2161402454","https://openalex.org/W2273440736","https://openalex.org/W4231459869"],"related_works":["https://openalex.org/W2098406302","https://openalex.org/W2184371594","https://openalex.org/W4312759433","https://openalex.org/W2535115842","https://openalex.org/W2734782074","https://openalex.org/W2148571123","https://openalex.org/W2546991807","https://openalex.org/W2801630946","https://openalex.org/W273173017","https://openalex.org/W2539551105"],"abstract_inverted_index":{"Modern":[0],"GPUs":[1],"employ":[2],"cache":[3,13,38,42,60,69,73,78,85,108,119,140],"to":[4,18,80,100,122],"improve":[5,41],"memory":[6,20,90],"system":[7],"efficiency.":[8],"However,":[9],"large":[10,56],"amount":[11,57],"of":[12,58,84,150],"space":[14,43,86],"is":[15],"underutilized":[16],"due":[17],"irregular":[19],"accesses":[21],"and":[22,104],"poor":[23],"spatial":[24,130],"locality":[25],"which":[26],"exhibited":[27],"commonly":[28],"in":[29,111],"GPU":[30],"applications.":[31,151],"Our":[32,132],"experiments":[33],"show":[34],"that":[35,75,135],"using":[36],"smaller":[37],"lines":[39],"could":[40],"utilization,":[44],"but":[45],"it":[46,105],"also":[47,116,153],"frequently":[48],"suffers":[49],"from":[50],"significant":[51],"performance":[52,124,141],"loss":[53,125],"by":[54,142],"introducing":[55],"extra":[59],"requests.":[61],"In":[62],"this":[63],"work,":[64],"we":[65],"propose":[66],"a":[67,147],"novel":[68],"design":[70],"named":[71],"tag-split":[72],"(TSC)":[74],"enables":[76],"fine-grained":[77],"storage":[79,102,120],"address":[81],"the":[82,138],"problem":[83],"underutilization":[87],"while":[88],"keeping":[89],"request":[91],"number":[92],"unchanged.":[93],"TSC":[94,114,136],"divides":[95],"tag":[96],"into":[97],"two":[98],"parts":[99],"reduce":[101],"overhead,":[103],"supports":[106],"multiple":[107],"line":[109],"replacement":[110],"one":[112],"cycle.":[113],"can":[115],"automatically":[117],"adjust":[118],"granularity":[121],"avoid":[123],"for":[126],"applications":[127],"with":[128],"good":[129],"locality.":[131],"evaluation":[133],"shows":[134],"improves":[137],"baseline":[139],"17.2%":[143],"on":[144],"average":[145],"across":[146],"wide":[148],"range":[149],"It":[152],"out-performs":[154],"other":[155],"previous":[156],"techniques":[157],"significantly.":[158]},"counts_by_year":[{"year":2022,"cited_by_count":2},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}
