{"id":"https://openalex.org/W2013419729","doi":"https://doi.org/10.1109/hipc.2010.5713187","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":"2010-12-01","ids":{"openalex":"https://openalex.org/W2013419729","doi":"https://doi.org/10.1109/hipc.2010.5713187","mag":"2013419729"},"language":"en","primary_location":{"id":"doi:10.1109/hipc.2010.5713187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2010.5713187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 International Conference on High Performance Computing","raw_type":"proceedings-article"},"type":"conference-paper","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":false,"raw_author_name":"Wenjing Ma","raw_affiliation_strings":["Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210#TAB#","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":["Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Ohio State Uinversity, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH 43210#TAB#","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":0.5264,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.59155977,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9987999796867371,"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":0.8843593597412109},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7672766447067261},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6945082545280457},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.6563182473182678},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.5759437084197998},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4744074046611786},{"id":"https://openalex.org/keywords/memory-model","display_name":"Memory model","score":0.467059463262558},{"id":"https://openalex.org/keywords/control-flow","display_name":"Control flow","score":0.46224120259284973},{"id":"https://openalex.org/keywords/uniform-memory-access","display_name":"Uniform memory access","score":0.4481946527957916},{"id":"https://openalex.org/keywords/nested-loop-join","display_name":"Nested loop join","score":0.43644189834594727},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.4221235513687134},{"id":"https://openalex.org/keywords/memory-management","display_name":"Memory management","score":0.3884621560573578},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.19289615750312805},{"id":"https://openalex.org/keywords/overlay","display_name":"Overlay","score":0.11124667525291443}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8843593597412109},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7672766447067261},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6945082545280457},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.6563182473182678},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.5759437084197998},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4744074046611786},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.467059463262558},{"id":"https://openalex.org/C160191386","wikidata":"https://www.wikidata.org/wiki/Q868299","display_name":"Control flow","level":2,"score":0.46224120259284973},{"id":"https://openalex.org/C51290061","wikidata":"https://www.wikidata.org/wiki/Q1936765","display_name":"Uniform memory access","level":4,"score":0.4481946527957916},{"id":"https://openalex.org/C1306188","wikidata":"https://www.wikidata.org/wiki/Q4060687","display_name":"Nested loop join","level":2,"score":0.43644189834594727},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.4221235513687134},{"id":"https://openalex.org/C176649486","wikidata":"https://www.wikidata.org/wiki/Q2308807","display_name":"Memory management","level":3,"score":0.3884621560573578},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.19289615750312805},{"id":"https://openalex.org/C136085584","wikidata":"https://www.wikidata.org/wiki/Q910289","display_name":"Overlay","level":2,"score":0.11124667525291443}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hipc.2010.5713187","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hipc.2010.5713187","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 International Conference on High Performance Computing","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":44,"referenced_works":["https://openalex.org/W67367039","https://openalex.org/W123564486","https://openalex.org/W196542726","https://openalex.org/W1537323515","https://openalex.org/W1549929312","https://openalex.org/W1550210730","https://openalex.org/W1871680789","https://openalex.org/W1964031104","https://openalex.org/W1971784203","https://openalex.org/W1993385165","https://openalex.org/W2001033342","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/W2133754926","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/W2319660501","https://openalex.org/W3001659479","https://openalex.org/W3006533007","https://openalex.org/W3129711340","https://openalex.org/W3148529197","https://openalex.org/W4246166885","https://openalex.org/W4248008732","https://openalex.org/W6602746267","https://openalex.org/W6632590119","https://openalex.org/W6661273561"],"related_works":["https://openalex.org/W2118496883","https://openalex.org/W2606565524","https://openalex.org/W2811273125","https://openalex.org/W4317827391","https://openalex.org/W4352974250","https://openalex.org/W2115061140","https://openalex.org/W4311294724","https://openalex.org/W2126827366","https://openalex.org/W2157828735","https://openalex.org/W2164718670"],"abstract_inverted_index":{"General":[0],"purpose":[1],"computing":[2],"using":[3,19,186],"GPUs":[4,25,33,54],"is":[5,26,148],"becoming":[6],"increasingly":[7],"popular,":[8],"because":[9],"of":[10,159],"GPU's":[11],"extremely":[12],"favorable":[13],"performance/price":[14],"ratio.":[15],"Besides":[16],"application":[17,189],"development":[18],"CUDA,":[20],"automatic":[21],"code":[22],"generation":[23],"for":[24,44,209],"also":[27,34,169,206],"receiving":[28],"attention.":[29],"Like":[30],"standard":[31],"processors,":[32],"have":[35,55],"a":[36,56,114,137,152,197],"memory":[37,103,127],"hierarchy,":[38],"which":[39,68,141],"must":[40],"be":[41],"carefully":[42],"optimized":[43],"in":[45],"order":[46],"to":[47,62,67,72,78,113,151,180],"achieve":[48],"efficient":[49],"execution.":[50,109],"Specifically,":[51],"modern":[52],"NVIDIA":[53],"very":[57],"small":[58],"programmable":[59],"cache,":[60],"referred":[61],"as":[63,130],"shared":[64,102,126,166],"memory,":[65],"accesses":[66,77],"are":[69,98],"nearly":[70],"100":[71],"150":[73],"times":[74],"faster":[75],"than":[76],"the":[79,101,108,125],"regular":[80],"device":[81],"memory.":[82,167],"An":[83],"automatically":[84],"generated":[85],"or":[86],"hand-written":[87],"CUDA":[88],"program":[89],"can":[90,142,175],"explicitly":[91],"control":[92,145],"what":[93],"variables":[94],"and":[95,123,147,162,202],"array":[96,163],"sections":[97,164],"allocated":[99],"on":[100,165],"at":[104],"any":[105],"point":[106],"during":[107],"This,":[110],"however,":[111],"leads":[112],"difficult":[115],"optimization":[116],"problem.":[117,134],"In":[118],"this":[119],"paper,":[120],"we":[121],"formulate":[122],"solve":[124],"allocation":[128,158],"problem":[129],"an":[131],"integer":[132,193],"programming":[133,194],"We":[135,156,168],"present":[136],"global":[138],"(intraprocedural)":[139],"framework":[140,174,195],"model":[143],"structured":[144],"flow,":[146],"not":[149],"restricted":[150],"single":[153],"loop":[154,178,204],"nest.":[155],"consider":[157],"scalars,":[160],"arrays,":[161],"briefly":[170],"show":[171,190],"how":[172],"our":[173,192,203],"suggest":[176],"useful":[177],"transformations":[179,205],"further":[181],"improve":[182,207],"performance.":[183],"Our":[184],"experiments":[185],"several":[187],"non-scientific":[188],"that":[191],"outperforms":[196],"recently":[198],"published":[199],"heuristic":[200],"method,":[201],"performance":[208],"many":[210],"applications.":[211]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}