{"id":"https://openalex.org/W2120062497","doi":"https://doi.org/10.1145/1854273.1854348","title":"An integer programming framework for optimizing shared memory use on GPUs","display_name":"An integer programming framework for optimizing shared memory use on GPUs","publication_year":2010,"publication_date":"2010-09-11","ids":{"openalex":"https://openalex.org/W2120062497","doi":"https://doi.org/10.1145/1854273.1854348","mag":"2120062497"},"language":"en","primary_location":{"id":"doi:10.1145/1854273.1854348","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1854273.1854348","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th international conference on Parallel architectures and compilation techniques","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/A5100695928","display_name":"Wenjing Ma","orcid":"https://orcid.org/0000-0002-1795-4498"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Wenjing Ma","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA","[Department of Computer Science & Engineering, The Ohio State University, Columbus, USA]"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"[Department of Computer Science & Engineering, The Ohio State University, Columbus, USA]","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025342178","display_name":"Gagan Agrawal","orcid":"https://orcid.org/0000-0002-2923-5327"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gagan Agrawal","raw_affiliation_strings":["The Ohio State University, Columbus, OH, USA","[Department of Computer Science & Engineering, The Ohio State University, Columbus, USA]"],"affiliations":[{"raw_affiliation_string":"The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"[Department of Computer Science & Engineering, The Ohio State University, Columbus, USA]","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100695928"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":2.4969,"has_fulltext":false,"cited_by_count":27,"citation_normalized_percentile":{"value":0.90218753,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"553","last_page":"554"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9994000196456909,"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/T11181","display_name":"Advanced Data Storage Technologies","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":0.8767440915107727},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.8041483163833618},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.7586352825164795},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6549979448318481},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.6307610869407654},{"id":"https://openalex.org/keywords/uniform-memory-access","display_name":"Uniform memory access","score":0.5154836773872375},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.486946702003479},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.4267699420452118},{"id":"https://openalex.org/keywords/memory-model","display_name":"Memory model","score":0.4133085608482361},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2140882909297943},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.09116929769515991}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8767440915107727},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.8041483163833618},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.7586352825164795},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6549979448318481},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.6307610869407654},{"id":"https://openalex.org/C51290061","wikidata":"https://www.wikidata.org/wiki/Q1936765","display_name":"Uniform memory access","level":4,"score":0.5154836773872375},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.486946702003479},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.4267699420452118},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.4133085608482361},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2140882909297943},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.09116929769515991}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1854273.1854348","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1854273.1854348","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th international conference on Parallel architectures and compilation techniques","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W67367039","https://openalex.org/W123564486","https://openalex.org/W196542726","https://openalex.org/W1549929312","https://openalex.org/W1550210730","https://openalex.org/W1964031104","https://openalex.org/W1971784203","https://openalex.org/W1993385165","https://openalex.org/W2003804316","https://openalex.org/W2039781906","https://openalex.org/W2042629708","https://openalex.org/W2043473567","https://openalex.org/W2044636417","https://openalex.org/W2049633694","https://openalex.org/W2060171681","https://openalex.org/W2080554063","https://openalex.org/W2112482891","https://openalex.org/W2116963870","https://openalex.org/W2129817042","https://openalex.org/W2135866892","https://openalex.org/W2140191557","https://openalex.org/W2146606012","https://openalex.org/W2152401677","https://openalex.org/W2153185479","https://openalex.org/W2153492376","https://openalex.org/W2162528816","https://openalex.org/W2163229756","https://openalex.org/W2167345029","https://openalex.org/W2170634604","https://openalex.org/W2206925937","https://openalex.org/W3129711340","https://openalex.org/W3148529197"],"related_works":["https://openalex.org/W4317827391","https://openalex.org/W2349791858","https://openalex.org/W2811273125","https://openalex.org/W254684032","https://openalex.org/W1578381328","https://openalex.org/W1839004754","https://openalex.org/W120214571","https://openalex.org/W1848192231","https://openalex.org/W2186451538","https://openalex.org/W40577698"],"abstract_inverted_index":{"General":[0],"purpose":[1],"computing":[2],"using":[3],"GPUs":[4,19,40],"is":[5],"becoming":[6],"increasingly":[7],"popular,":[8],"because":[9],"of":[10],"GPU's":[11],"extremely":[12],"favorable":[13],"performance/price":[14],"ratio.":[15],"Like":[16],"standard":[17],"processors,":[18],"also":[20],"have":[21,41],"a":[22,42,100],"memory":[23,89],"hierarchy,":[24],"which":[25,54],"must":[26],"be":[27],"carefully":[28],"optimized":[29],"for":[30],"in":[31],"order":[32],"to":[33,48,53,58,64,99],"achieve":[34],"efficient":[35],"execution.":[36,95],"Specifically,":[37],"modern":[38],"NVIDIA":[39],"very":[43],"small":[44],"programmable":[45],"cache,":[46],"referred":[47],"as":[49],"shared":[50,88],"memory,":[51],"accesses":[52,63],"are":[55,84],"nearly":[56],"100":[57],"150":[59],"times":[60],"faster":[61],"than":[62],"the":[65,87,94],"regular":[66],"device":[67],"memory.":[68],"An":[69],"automatically":[70],"generated":[71],"or":[72],"hand-written":[73],"CUDA":[74],"program":[75],"can":[76],"explicitly":[77],"control":[78],"what":[79],"variables":[80],"and":[81],"array":[82],"sections":[83],"allocated":[85],"on":[86],"at":[90],"any":[91],"point":[92],"during":[93],"This,":[96],"however,":[97],"leads":[98],"difficult":[101],"optimization":[102],"problem.":[103]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":5},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":4},{"year":2013,"cited_by_count":4},{"year":2012,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}