{"id":"https://openalex.org/W2058358643","doi":"https://doi.org/10.1109/iscas.2013.6571993","title":"DRAM access reduction in GPUs by thread-block scheduling for overlapped data reuse","display_name":"DRAM access reduction in GPUs by thread-block scheduling for overlapped data reuse","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2058358643","doi":"https://doi.org/10.1109/iscas.2013.6571993","mag":"2058358643"},"language":"en","primary_location":{"id":"doi:10.1109/iscas.2013.6571993","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas.2013.6571993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Symposium on Circuits and Systems (ISCAS2013)","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/A5102022480","display_name":"Seung\u2010Yeol Lee","orcid":"https://orcid.org/0000-0002-8987-9749"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seungyeol Lee","raw_affiliation_strings":["Department of Electrical Engineering, Seoul National University, Seoul, South Korea","Dept. of Electr. Eng., Seoul Nat. Univ., Seoul, South Korea#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Dept. of Electr. Eng., Seoul Nat. Univ., Seoul, South Korea#TAB#","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5110451967","display_name":"Wonyong Sung","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonyong Sung","raw_affiliation_strings":["Department of Electrical Engineering, Seoul National University, Seoul, South Korea","Dept. of Electr. Eng., Seoul Nat. Univ., Seoul, South Korea#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Seoul National University, Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Dept. of Electr. Eng., Seoul Nat. Univ., Seoul, South Korea#TAB#","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12151223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"5","issue":null,"first_page":"901","last_page":"904"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9991000294685364,"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":0.8651224374771118},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7239287495613098},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.5959902405738831},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5184749960899353},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.45904654264450073},{"id":"https://openalex.org/keywords/page-cache","display_name":"Page cache","score":0.4109411835670471},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3681105971336365},{"id":"https://openalex.org/keywords/cpu-cache","display_name":"CPU cache","score":0.35403889417648315},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3275361657142639},{"id":"https://openalex.org/keywords/cache-algorithms","display_name":"Cache algorithms","score":0.2885352373123169},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.21296754479408264}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8651224374771118},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7239287495613098},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.5959902405738831},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5184749960899353},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.45904654264450073},{"id":"https://openalex.org/C36340418","wikidata":"https://www.wikidata.org/wiki/Q7124288","display_name":"Page cache","level":5,"score":0.4109411835670471},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3681105971336365},{"id":"https://openalex.org/C189783530","wikidata":"https://www.wikidata.org/wiki/Q352090","display_name":"CPU cache","level":3,"score":0.35403889417648315},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3275361657142639},{"id":"https://openalex.org/C38556500","wikidata":"https://www.wikidata.org/wiki/Q13404475","display_name":"Cache algorithms","level":4,"score":0.2885352373123169},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.21296754479408264}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iscas.2013.6571993","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas.2013.6571993","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Symposium on Circuits and Systems (ISCAS2013)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6899999976158142,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1536051636","https://openalex.org/W1968347730","https://openalex.org/W1992851788","https://openalex.org/W2003368909","https://openalex.org/W2010418442","https://openalex.org/W2016352575","https://openalex.org/W2033597569","https://openalex.org/W2040314537","https://openalex.org/W2063249715","https://openalex.org/W2080592089","https://openalex.org/W2119609467","https://openalex.org/W2129960401","https://openalex.org/W2135736783","https://openalex.org/W2153492376","https://openalex.org/W2155917287","https://openalex.org/W2398736067","https://openalex.org/W2620746779","https://openalex.org/W3004256893","https://openalex.org/W3143589697","https://openalex.org/W4237521714","https://openalex.org/W6631783819","https://openalex.org/W6738527174","https://openalex.org/W7065096706"],"related_works":["https://openalex.org/W2539712666","https://openalex.org/W2118932116","https://openalex.org/W4235330364","https://openalex.org/W2099372890","https://openalex.org/W2037579040","https://openalex.org/W2509523906","https://openalex.org/W2012518269","https://openalex.org/W2167303720","https://openalex.org/W4243772489","https://openalex.org/W2537026945"],"abstract_inverted_index":{"General":[0],"Purpose":[1],"Graphics":[2],"Processing":[3],"Units":[4],"(GPG-PUs)":[5],"show":[6],"very":[7,18,50],"high":[8,31,51],"throughput":[9],"when":[10],"executing":[11],"parallel":[12],"programs.":[13,99],"However,":[14],"they":[15],"usually":[16],"demand":[17],"large":[19],"DRAM":[20,41,74,112],"bandwidth":[21],"and":[22,71,109],"consume":[23],"much":[24],"power":[25],"for":[26],"memory":[27,75],"access.":[28,76],"Although":[29],"recent":[30],"performance":[32],"GPGPUs":[33],"equip":[34],"L2":[35,69],"cache":[36,44,56,70],"to":[37,104,116],"absorb":[38],"some":[39],"of":[40,53,87],"accesses,":[42],"the":[43,54,73,81,85,105,111],"hit":[45],"ratio":[46],"can":[47,66,92],"hardly":[48],"be":[49,94],"because":[52],"limited":[55],"size.":[57],"We":[58],"propose":[59],"a":[60],"GPU":[61,88],"thread-block":[62],"scheduling":[63,78,86],"method":[64,79,91],"that":[65],"better":[67],"utilize":[68],"reduce":[72],"This":[77,90,100],"exploits":[80],"inter-block":[82],"locality":[83],"in":[84],"thread-blocks.":[89],"easily":[93],"implemented":[95],"by":[96,114],"modifying":[97],"application":[98],"technique":[101],"is":[102],"applied":[103],"Hotspot":[106],"benchmark":[107],"programs,":[108],"reduces":[110],"access":[113],"up":[115],"39%.":[117]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}