{"id":"https://openalex.org/W1984268668","doi":"https://doi.org/10.1145/2628071.2671425","title":"Data-reuse Optimizations for pipelined Tiling with Parametric Tile Sizes","display_name":"Data-reuse Optimizations for pipelined Tiling with Parametric Tile Sizes","publication_year":2014,"publication_date":"2014-08-24","ids":{"openalex":"https://openalex.org/W1984268668","doi":"https://doi.org/10.1145/2628071.2671425","mag":"1984268668"},"language":"en","primary_location":{"id":"doi:10.1145/2628071.2671425","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2628071.2671425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Parallel architectures and compilation","raw_type":"proceedings-article"},"type":"preprint","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/A5031053505","display_name":"Alexandre Isoard","orcid":null},"institutions":[{"id":"https://openalex.org/I113428412","display_name":"\u00c9cole Normale Sup\u00e9rieure de Lyon","ror":"https://ror.org/04zmssz18","country_code":"FR","type":"education","lineage":["https://openalex.org/I113428412","https://openalex.org/I203339264"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Alexandre Isoard","raw_affiliation_strings":["ENS de Lyon, Lyon, France"],"affiliations":[{"raw_affiliation_string":"ENS de Lyon, Lyon, France","institution_ids":["https://openalex.org/I113428412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5031053505"],"corresponding_institution_ids":["https://openalex.org/I113428412"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.08523121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"509","last_page":"510"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"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"}},"topics":[{"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"}},{"id":"https://openalex.org/T12162","display_name":"Cellular Automata and Applications","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9987000226974487,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/loop-tiling","display_name":"Loop tiling","score":0.8781082034111023},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.814493715763092},{"id":"https://openalex.org/keywords/tile","display_name":"Tile","score":0.7195703387260437},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6828263998031616},{"id":"https://openalex.org/keywords/parametric-statistics","display_name":"Parametric statistics","score":0.5991013050079346},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5801646113395691},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.5226259827613831},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.4376847743988037},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4268642067909241},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3299194574356079},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.325467586517334},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.32521408796310425},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0899321436882019},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08035525679588318}],"concepts":[{"id":"https://openalex.org/C11799548","wikidata":"https://www.wikidata.org/wiki/Q6675847","display_name":"Loop tiling","level":3,"score":0.8781082034111023},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.814493715763092},{"id":"https://openalex.org/C2780728851","wikidata":"https://www.wikidata.org/wiki/Q468402","display_name":"Tile","level":2,"score":0.7195703387260437},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6828263998031616},{"id":"https://openalex.org/C117251300","wikidata":"https://www.wikidata.org/wiki/Q1849855","display_name":"Parametric statistics","level":2,"score":0.5991013050079346},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5801646113395691},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.5226259827613831},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.4376847743988037},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4268642067909241},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3299194574356079},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.325467586517334},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.32521408796310425},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0899321436882019},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08035525679588318},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2628071.2671425","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2628071.2671425","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd international conference on Parallel architectures and compilation","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322892","display_name":"Centre National de la Recherche Scientifique","ror":"https://ror.org/02feahw73"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W2077143534","https://openalex.org/W2123286830","https://openalex.org/W2141280299","https://openalex.org/W2280560448","https://openalex.org/W4229866061"],"related_works":["https://openalex.org/W2114959296","https://openalex.org/W38346124","https://openalex.org/W2502442966","https://openalex.org/W1545258949","https://openalex.org/W2011263215","https://openalex.org/W4238138329","https://openalex.org/W2124711255","https://openalex.org/W1487545099","https://openalex.org/W3213145857","https://openalex.org/W2142761843"],"abstract_inverted_index":{"Loop":[0],"tiling":[1,69],"is":[2,70,93,148],"a":[3,115,159,232],"loop":[4,68],"transformation":[5],"widely":[6],"used":[7],"to":[8,15,20,140],"improve":[9],"spatial":[10],"and":[11,19,44,50,157,164,217,223],"temporal":[12],"data":[13,42,60,98,146,166],"locality,":[14],"increase":[16],"computation":[17],"granularity,":[18],"enable":[21],"blocking":[22,202],"algorithms,":[23,203],"which":[24,76,92],"are":[25,39,108,129],"particularly":[26],"useful":[27],"when":[28,127],"offloading":[29],"kernels":[30],"on":[31,215],"platforms":[32],"with":[33,118,171,184,228],"small":[34],"memories.":[35,182],"When":[36],"hardware":[37],"caches":[38],"not":[40],"available,":[41],"transfers":[43],"local":[45,83,181],"storage":[46],"must":[47],"be":[48,56,207],"software-managed,":[49],"some":[51],"useless":[52],"external":[53],"communications":[54],"can":[55,153,206,210],"avoided":[57],"by":[58,197],"exploiting":[59],"reuse":[61,147],"between":[62],"tiles.":[63],"An":[64],"important":[65],"parameter":[66],"of":[67,73,80,201,225],"the":[71,74,78,81,94,100,136,162,179,193,221],"sizes":[72,102,177],"tiles,":[75,91,170],"impact":[77],"size":[79],"required":[82],"memory.":[84],"However,":[85],"for":[86,96,144,168,178,192],"most":[87],"analyses":[88],"involving":[89],"several":[90],"case":[95],"inter-tile":[97,145,172],"reuse,":[99,173],"tile":[101,134,141],"induce":[103],"non-linear":[104],"constraints,":[105],"unless":[106],"they":[107],"numerical":[109],"constants.":[110],"This":[111,122],"complicates":[112],"or":[113],"prevents":[114],"parametric":[116,137,160,198],"analysis":[117,143],"polyhedral":[119],"optimization":[120],"techniques.":[121],"extended":[123],"abstract":[124],"shows":[125],"that,":[126],"tiles":[128],"executed":[130],"in":[131,158,231],"sequence":[132],"along":[133],"axes,":[135],"(with":[138],"respect":[139],"sizes)":[142],"nevertheless":[149],"possible,":[150],"i.e.,":[151],"one":[152],"determine,":[154],"at":[155],"compile-time":[156],"fashion,":[161],"copy-in":[163],"copy-out":[165],"sets":[167],"all":[169],"as":[174,176],"well":[175],"induced":[180],"Combined":[183],"hierarchical":[185],"tiling,":[186,229],"this":[187],"result":[188],"opens":[189],"new":[190],"perspectives":[191],"automatic":[194],"generation,":[195],"guided":[196],"cost":[199],"models,":[200],"where":[204],"blocks":[205],"pipelined":[208],"and/or":[209],"contain":[211],"parallelism.":[212],"Previous":[213],"work":[214],"FPGAs":[216],"GPUs":[218],"already":[219],"showed":[220],"interest":[222],"feasibility":[224],"such":[226],"automation":[227],"but":[230],"non-parametric":[233],"fashion.":[234]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
