{"id":"https://openalex.org/W2069279716","doi":"https://doi.org/10.1145/1854273.1854351","title":"DMATiler","display_name":"DMATiler","publication_year":2010,"publication_date":"2010-09-11","ids":{"openalex":"https://openalex.org/W2069279716","doi":"https://doi.org/10.1145/1854273.1854351","mag":"2069279716"},"language":"en","primary_location":{"id":"doi:10.1145/1854273.1854351","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1854273.1854351","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/A5029380103","display_name":"Haibo Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Haibo Lin","raw_affiliation_strings":["IBM Research - China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"IBM Research - China, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100338134","display_name":"Tao Liu","orcid":"https://orcid.org/0000-0003-1873-5462"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Liu","raw_affiliation_strings":["IBM Research - China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"IBM Research - China, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004056135","display_name":"Huoding Li","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huoding Li","raw_affiliation_strings":["IBM Systems &amp; Technology Group, Beijing, China"],"affiliations":[{"raw_affiliation_string":"IBM Systems &amp; Technology Group, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100461265","display_name":"Tong Chen","orcid":"https://orcid.org/0000-0001-7269-146X"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tong Chen","raw_affiliation_strings":["IBM Watson Research Center, Yorktown Heights, USA"],"affiliations":[{"raw_affiliation_string":"IBM Watson Research Center, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072585176","display_name":"Lakshminarayanan Renganarayana","orcid":null},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lakshminarayanan Renganarayana","raw_affiliation_strings":["IBM Watson Research Center, Yorktown Heights, USA"],"affiliations":[{"raw_affiliation_string":"IBM Watson Research Center, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065458744","display_name":"John O\u2019Brien","orcid":"https://orcid.org/0000-0002-1006-4388"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"John Kevin O'Brien","raw_affiliation_strings":["IBM Watson Research Center, Yorktown Heights, USA"],"affiliations":[{"raw_affiliation_string":"IBM Watson Research Center, Yorktown Heights, USA","institution_ids":["https://openalex.org/I1341412227"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082634513","display_name":"Ling Shao","orcid":"https://orcid.org/0000-0002-8264-6117"},"institutions":[{"id":"https://openalex.org/I4210126794","display_name":"IBM Research (China)","ror":"https://ror.org/02yg1pf55","country_code":"CN","type":"company","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210114115","https://openalex.org/I4210126794"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ling Shao","raw_affiliation_strings":["IBM Research - China, Beijing, China"],"affiliations":[{"raw_affiliation_string":"IBM Research - China, Beijing, China","institution_ids":["https://openalex.org/I4210126794"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5029380103"],"corresponding_institution_ids":["https://openalex.org/I4210126794"],"apc_list":null,"apc_paid":null,"fwci":0.2497,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.56904693,"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":"559","last_page":"560"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9986000061035156,"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":0.9984999895095825,"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/loop-tiling","display_name":"Loop tiling","score":0.8738158941268921},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8629834651947021},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7657608985900879},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.7216094732284546},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.680460512638092},{"id":"https://openalex.org/keywords/loop-fission","display_name":"Loop fission","score":0.6468914151191711},{"id":"https://openalex.org/keywords/loop-fusion","display_name":"Loop fusion","score":0.5976473093032837},{"id":"https://openalex.org/keywords/loop-optimization","display_name":"Loop optimization","score":0.5419188141822815},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.5227532386779785},{"id":"https://openalex.org/keywords/loop","display_name":"Loop (graph theory)","score":0.47908908128738403},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.41566652059555054},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.3788526654243469},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3347707986831665}],"concepts":[{"id":"https://openalex.org/C11799548","wikidata":"https://www.wikidata.org/wiki/Q6675847","display_name":"Loop tiling","level":3,"score":0.8738158941268921},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8629834651947021},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7657608985900879},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.7216094732284546},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.680460512638092},{"id":"https://openalex.org/C134718785","wikidata":"https://www.wikidata.org/wiki/Q6675821","display_name":"Loop fission","level":3,"score":0.6468914151191711},{"id":"https://openalex.org/C82653869","wikidata":"https://www.wikidata.org/wiki/Q6675821","display_name":"Loop fusion","level":3,"score":0.5976473093032837},{"id":"https://openalex.org/C29331672","wikidata":"https://www.wikidata.org/wiki/Q3354468","display_name":"Loop optimization","level":4,"score":0.5419188141822815},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.5227532386779785},{"id":"https://openalex.org/C184670325","wikidata":"https://www.wikidata.org/wiki/Q512604","display_name":"Loop (graph theory)","level":2,"score":0.47908908128738403},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.41566652059555054},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.3788526654243469},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3347707986831665},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1854273.1854351","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1854273.1854351","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":7,"referenced_works":["https://openalex.org/W2024666804","https://openalex.org/W2080393180","https://openalex.org/W2112482891","https://openalex.org/W2123680107","https://openalex.org/W2152506070","https://openalex.org/W2296319761","https://openalex.org/W6678187016"],"related_works":["https://openalex.org/W1596526459","https://openalex.org/W2340721088","https://openalex.org/W2040522199","https://openalex.org/W2014071052","https://openalex.org/W2122418911","https://openalex.org/W2244841219","https://openalex.org/W1498734356","https://openalex.org/W2010414531","https://openalex.org/W3169195854","https://openalex.org/W2133860611"],"abstract_inverted_index":{"In":[0,24,50],"this":[1],"paper":[2],"we":[3],"present":[4],"the":[5,32,39,52,55,59,76,108,134,137,183],"design":[6],"and":[7,16,62,122,146,173],"implementation":[8],"of":[9,41,58,64,153,171,180],"a":[10,47,69,87,99,151],"DMATiler":[11,53,67,102,117,135,160],"which":[12],"combines":[13],"compiler":[14,33],"analysis":[15],"runtime":[17,35],"management":[18],"to":[19,74,106,126],"optimize":[20,128],"local":[21],"memory":[22],"performance.":[23],"traditional":[25],"cache":[26,36,43,168],"model":[27,73,78],"based":[28],"loop":[29,48,81,100,104,109,154,176],"tiling":[30],"optimizations,":[31],"approximates":[34],"misses":[37],"as":[38],"number":[40],"distinct":[42],"lines":[44],"touched":[45],"by":[46,95],"nest.":[49],"contrast,":[51],"has":[54],"full":[56],"control":[57],"addresses,":[60],"sizes,":[61],"sequences":[63],"data":[65,114,120,129],"transfers.":[66,130],"uses":[68,103],"simplified":[70],"DMA":[71,96,124],"performance":[72],"formulate":[75],"cost":[77],"for":[79,113,141,144],"DMA-tiled":[80],"nests,":[82],"then":[83],"solves":[84],"it":[85],"using":[86],"custom":[88],"gradient":[89],"descent":[90],"algorithm":[91],"with":[92,150],"heuristics":[93],"guided":[94],"characteristics.":[97],"Given":[98],"nest,":[101],"interchange":[105],"make":[107],"order":[110],"more":[111,163],"friendlier":[112],"movements.":[115],"Moreover,":[116],"applies":[118],"compressed":[119],"buffer":[121],"advanced":[123],"command":[125],"further":[127],"We":[131],"have":[132,147],"implemented":[133],"in":[136],"IBM":[138],"XL":[139],"C/C++":[140],"Multi-core":[142],"Acceleration":[143],"Linux,":[145],"conducted":[148],"experiments":[149],"set":[152],"nest":[155],"benchmarks.":[156],"The":[157],"results":[158],"show":[159],"is":[161],"much":[162],"efficient":[164],"than":[165],"software":[166],"controlled":[167],"(average":[169,178],"speedup":[170,179],"9.8x)":[172],"single":[174],"level":[175],"blocking":[177],"6.2x)":[181],"on":[182],"Cell":[184],"BE":[185],"processor.":[186]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2016-06-24T00:00:00"}
