{"id":"https://openalex.org/W1999238645","doi":"https://doi.org/10.1145/2458523.2458528","title":"Memory reuse optimizations in the R-Stream compiler","display_name":"Memory reuse optimizations in the R-Stream compiler","publication_year":2013,"publication_date":"2013-03-16","ids":{"openalex":"https://openalex.org/W1999238645","doi":"https://doi.org/10.1145/2458523.2458528","mag":"1999238645"},"language":"en","primary_location":{"id":"doi:10.1145/2458523.2458528","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2458523.2458528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Workshop on General Purpose Processor Using Graphics Processing Units","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/A5017292577","display_name":"Nicolas Vasilache","orcid":"https://orcid.org/0000-0002-4096-3325"},"institutions":[{"id":"https://openalex.org/I4210102519","display_name":"Reservoir Labs (United States)","ror":"https://ror.org/01a3m3f05","country_code":"US","type":"company","lineage":["https://openalex.org/I4210102519"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nicolas Vasilache","raw_affiliation_strings":["Reservoir Labs Inc., New-York, NY"],"affiliations":[{"raw_affiliation_string":"Reservoir Labs Inc., New-York, NY","institution_ids":["https://openalex.org/I4210102519"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104040289","display_name":"Muthu Manikandan Baskaran","orcid":null},"institutions":[{"id":"https://openalex.org/I4210102519","display_name":"Reservoir Labs (United States)","ror":"https://ror.org/01a3m3f05","country_code":"US","type":"company","lineage":["https://openalex.org/I4210102519"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Muthu Baskaran","raw_affiliation_strings":["Reservoir Labs Inc., New-York, NY"],"affiliations":[{"raw_affiliation_string":"Reservoir Labs Inc., New-York, NY","institution_ids":["https://openalex.org/I4210102519"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047696430","display_name":"Beno\u00eet Meister","orcid":"https://orcid.org/0000-0003-1975-1376"},"institutions":[{"id":"https://openalex.org/I4210102519","display_name":"Reservoir Labs (United States)","ror":"https://ror.org/01a3m3f05","country_code":"US","type":"company","lineage":["https://openalex.org/I4210102519"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Benoit Meister","raw_affiliation_strings":["Reservoir Labs Inc., New-York, NY"],"affiliations":[{"raw_affiliation_string":"Reservoir Labs Inc., New-York, NY","institution_ids":["https://openalex.org/I4210102519"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108503417","display_name":"Richard Lethin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210102519","display_name":"Reservoir Labs (United States)","ror":"https://ror.org/01a3m3f05","country_code":"US","type":"company","lineage":["https://openalex.org/I4210102519"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Richard Lethin","raw_affiliation_strings":["Reservoir Labs Inc., New-York, NY"],"affiliations":[{"raw_affiliation_string":"Reservoir Labs Inc., New-York, NY","institution_ids":["https://openalex.org/I4210102519"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5017292577"],"corresponding_institution_ids":["https://openalex.org/I4210102519"],"apc_list":null,"apc_paid":null,"fwci":2.2065,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.87385055,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"42","last_page":"53"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9954000115394592,"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":0.9932000041007996,"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":0.8917532563209534},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7229028940200806},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6237891912460327},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.6119149923324585},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4948427081108093},{"id":"https://openalex.org/keywords/compile-time","display_name":"Compile time","score":0.463739275932312},{"id":"https://openalex.org/keywords/memory-model","display_name":"Memory model","score":0.4585205912590027},{"id":"https://openalex.org/keywords/shared-memory","display_name":"Shared memory","score":0.45786502957344055},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4403045177459717},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.43523332476615906},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.21321332454681396}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8917532563209534},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7229028940200806},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6237891912460327},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.6119149923324585},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4948427081108093},{"id":"https://openalex.org/C200833197","wikidata":"https://www.wikidata.org/wiki/Q333707","display_name":"Compile time","level":3,"score":0.463739275932312},{"id":"https://openalex.org/C12186640","wikidata":"https://www.wikidata.org/wiki/Q6815743","display_name":"Memory model","level":3,"score":0.4585205912590027},{"id":"https://openalex.org/C133875982","wikidata":"https://www.wikidata.org/wiki/Q764810","display_name":"Shared memory","level":2,"score":0.45786502957344055},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4403045177459717},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.43523332476615906},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.21321332454681396},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2458523.2458528","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2458523.2458528","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th Workshop on General Purpose Processor Using Graphics Processing Units","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure","score":0.6399999856948853}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W93506392","https://openalex.org/W288065879","https://openalex.org/W1494930385","https://openalex.org/W1533186609","https://openalex.org/W1872629992","https://openalex.org/W1970141743","https://openalex.org/W1992851788","https://openalex.org/W2010196134","https://openalex.org/W2032391783","https://openalex.org/W2049875313","https://openalex.org/W2071110673","https://openalex.org/W2077805988","https://openalex.org/W2092988381","https://openalex.org/W2098925700","https://openalex.org/W2110301098","https://openalex.org/W2113190809","https://openalex.org/W2115026893","https://openalex.org/W2129232868","https://openalex.org/W2135056392","https://openalex.org/W2154078685","https://openalex.org/W2296218291","https://openalex.org/W2520810317","https://openalex.org/W2983923412","https://openalex.org/W3203568064","https://openalex.org/W4229866061","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2371266106","https://openalex.org/W2117382851","https://openalex.org/W3006505070","https://openalex.org/W2382449560","https://openalex.org/W2767298477","https://openalex.org/W2110432562","https://openalex.org/W2117864619","https://openalex.org/W2025344","https://openalex.org/W2090337950","https://openalex.org/W2104121286"],"abstract_inverted_index":{"We":[0,69],"propose":[1],"a":[2,107,122],"new":[3],"set":[4],"of":[5,35,52,73,87,90,97,101,114,128,164],"automated":[6],"techniques":[7,19,134,146],"to":[8,63,94,161],"optimize":[9],"memory":[10,57,111,129],"reuse":[11,100,113],"in":[12,50,132],"programs":[13],"with":[14,41,92,139],"explicitly":[15],"managed":[16],"memory.":[17,125],"Our":[18],"are":[20,149],"inspired":[21],"by":[22],"hand-tuned":[23,64],"seismic":[24],"kernels":[25],"on":[26,80],"GPUs.":[27],"The":[28,126,145],"solutions":[29],"we":[30,130,147],"develop":[31],"reduce":[32],"the":[33,117,136],"cost":[34],"transferring":[36],"data":[37,102,115],"across":[38,103],"multiple":[39],"memories":[40],"different":[42,88],"bandwidth,":[43],"latency":[44],"and":[45,58,78,112,142,152],"addressability":[46],"properties.":[47],"They":[48],"result":[49],"reduction":[51,96],"communication":[53],"volumes":[54],"from":[55],"main":[56],"faster":[59],"execution":[60],"speeds,":[61],"comparable":[62],"implementations,":[65],"for":[66],"out-of-place":[67],"stencils.":[68],"discuss":[70],"various":[71],"steps":[72],"our":[74,133,156],"source-to-source":[75],"compiler":[76,157],"infrastructure":[77],"focus":[79],"specific":[81],"optimizations":[82],"which":[83],"comprise:":[84],"flexible":[85],"generation":[86],"granularities":[89],"communications":[91],"respect":[93],"computations,":[95],"redundant":[98],"transfers,":[99],"processing":[104,119],"elements":[105,120],"using":[106,121],"globally":[108],"addressable":[109],"local":[110,123],"within":[116,155],"same":[118],"private":[124],"models":[127],"consider":[131],"support":[135],"GPU":[137],"model":[138],"device,":[140],"shared":[141],"register":[143],"memories.":[144],"derive":[148],"generally":[150],"applicable":[151],"their":[153],"formulation":[154],"can":[158],"be":[159],"extended":[160],"other":[162],"types":[163],"architectures.":[165]},"counts_by_year":[{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}