{"id":"https://openalex.org/W2020572638","doi":"https://doi.org/10.1145/2304576.2304582","title":"Characterizing and improving the use of demand-fetched caches in GPUs","display_name":"Characterizing and improving the use of demand-fetched caches in GPUs","publication_year":2012,"publication_date":"2012-06-25","ids":{"openalex":"https://openalex.org/W2020572638","doi":"https://doi.org/10.1145/2304576.2304582","mag":"2020572638"},"language":"en","primary_location":{"id":"doi:10.1145/2304576.2304582","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2304576.2304582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Supercomputing","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/A5068789333","display_name":"Wenhao Jia","orcid":"https://orcid.org/0000-0002-9699-0744"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wenhao Jia","raw_affiliation_strings":["Princeton University, Princeton, NJ, USA","Princeton University , Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Princeton University , Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103504814","display_name":"Kelly A. Shaw","orcid":null},"institutions":[{"id":"https://openalex.org/I158012942","display_name":"University of Richmond","ror":"https://ror.org/03y71xh61","country_code":"US","type":"education","lineage":["https://openalex.org/I158012942"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kelly A. Shaw","raw_affiliation_strings":["University of Richmond, Richmond, VA, USA"],"affiliations":[{"raw_affiliation_string":"University of Richmond, Richmond, VA, USA","institution_ids":["https://openalex.org/I158012942"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002015508","display_name":"Margaret Martonosi","orcid":"https://orcid.org/0000-0001-9683-8032"},"institutions":[{"id":"https://openalex.org/I20089843","display_name":"Princeton University","ror":"https://ror.org/00hx57361","country_code":"US","type":"education","lineage":["https://openalex.org/I20089843"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Margaret Martonosi","raw_affiliation_strings":["Princeton University, Princeton, NJ, USA","Princeton University , Princeton, NJ, USA"],"affiliations":[{"raw_affiliation_string":"Princeton University, Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]},{"raw_affiliation_string":"Princeton University , Princeton, NJ, USA","institution_ids":["https://openalex.org/I20089843"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5068789333"],"corresponding_institution_ids":["https://openalex.org/I20089843"],"apc_list":null,"apc_paid":null,"fwci":17.8188,"has_fulltext":false,"cited_by_count":151,"citation_normalized_percentile":{"value":0.99593239,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"15","last_page":"24"},"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":0.9993000030517578,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8768386840820312},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.6043133735656738},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5366342663764954},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.47371572256088257},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4716562330722809},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4555460512638092},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.45021891593933105},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.39727920293807983},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.29284942150115967},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.16789531707763672}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8768386840820312},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.6043133735656738},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5366342663764954},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.47371572256088257},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4716562330722809},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4555460512638092},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.45021891593933105},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.39727920293807983},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.29284942150115967},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.16789531707763672}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2304576.2304582","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2304576.2304582","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 26th ACM international conference on Supercomputing","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.362.3410","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.362.3410","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.princeton.edu/~wjia/gpucache.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1504291959","https://openalex.org/W2013247896","https://openalex.org/W2016888570","https://openalex.org/W2032309817","https://openalex.org/W2056971515","https://openalex.org/W2057411561","https://openalex.org/W2072768743","https://openalex.org/W2080285119","https://openalex.org/W2080592089","https://openalex.org/W2083056254","https://openalex.org/W2096661534","https://openalex.org/W2110195531","https://openalex.org/W2129232868","https://openalex.org/W2151142801","https://openalex.org/W2160875256","https://openalex.org/W2162528816","https://openalex.org/W2167334577","https://openalex.org/W2171134934","https://openalex.org/W4241513866"],"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/W2149078538","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825","https://openalex.org/W2893308117"],"abstract_inverted_index":{"Initially":[0],"introduced":[1],"as":[2,16],"special-purpose":[3],"accelerators":[4],"for":[5],"games":[6],"and":[7,54,86,95],"graphics":[8,10],"code,":[9],"processing":[11],"units":[12],"(GPUs)":[13],"have":[14,65,123],"emerged":[15],"widely-used":[17],"high-performance":[18],"parallel":[19],"computing":[20],"platforms.":[21],"GPUs":[22,37],"traditionally":[23],"provided":[24],"only":[25],"software-managed":[26],"local":[27],"memories":[28],"(or":[29],"scratchpads)":[30],"instead":[31,104],"of":[32,105],"demand-fetched":[33,68,134],"caches.":[34,60,135],"Increasingly,":[35],"however,":[36],"are":[38,49,83,131],"being":[39],"used":[40],"in":[41,58,70],"broader":[42],"application":[43,118],"domains":[44],"where":[45],"memory":[46,128],"access":[47],"patterns":[48,130],"both":[50],"harder":[51,55],"to":[52,56,92,97,133],"analyze":[53],"manage":[57],"software-controlled":[59],"In":[61],"response,":[62],"GPU":[63,110],"vendors":[64],"included":[66],"sizable":[67],"caches":[69,82],"recent":[71],"chip":[72],"designs.":[73],"Nonetheless,":[74],"several":[75],"problems":[76],"remain.":[77],"First,":[78],"since":[79,109],"these":[80],"hardware":[81],"quite":[84,113],"new":[85],"highly-configurable,":[87],"it":[88],"can":[89],"be":[90],"difficult":[91],"know":[93],"when":[94],"how":[96],"use":[98],"them;":[99],"they":[100],"sometimes":[101],"degrade":[102],"performance":[103],"improving":[106],"it.":[107],"Second,":[108],"programming":[111],"is":[112],"distinct":[114],"from":[115],"general-purpose":[116],"programming,":[117],"programmers":[119],"do":[120],"not":[121],"yet":[122],"solid":[124],"intuition":[125],"about":[126],"which":[127],"reference":[129],"amenable":[132]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":5},{"year":2019,"cited_by_count":14},{"year":2018,"cited_by_count":15},{"year":2017,"cited_by_count":20},{"year":2016,"cited_by_count":26},{"year":2015,"cited_by_count":29},{"year":2014,"cited_by_count":14},{"year":2013,"cited_by_count":17},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}