{"id":"https://openalex.org/W4233293392","doi":"https://doi.org/10.1201/b10376-25","title":"Auto-Tuning Stencil Computations on Multicore and Accel- erators","display_name":"Auto-Tuning Stencil Computations on Multicore and Accel- erators","publication_year":2010,"publication_date":"2010-12-07","ids":{"openalex":"https://openalex.org/W4233293392","doi":"https://doi.org/10.1201/b10376-25"},"language":"en","primary_location":{"id":"doi:10.1201/b10376-25","is_oa":true,"landing_page_url":"https://doi.org/10.1201/b10376-25","pdf_url":"https://api.taylorfrancis.com/content/chapters/edit/download?identifierName=doi&identifierValue=10.1201/b10376-25&type=chapterpdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Computing with Multicore and Accelerators","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://api.taylorfrancis.com/content/chapters/edit/download?identifierName=doi&identifierValue=10.1201/b10376-25&type=chapterpdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104047193","display_name":"Kaushik Datta","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Kaushik Datta","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102746800","display_name":"Samuel Williams","orcid":"https://orcid.org/0000-0002-8327-5717"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Samuel Williams","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003269014","display_name":"\u0412. \u041c. \u0412\u043e\u043b\u043a\u043e\u0432","orcid":"https://orcid.org/0000-0003-0350-4186"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Vasily Volkov","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101932170","display_name":"Jonathan Carter","orcid":"https://orcid.org/0000-0001-9006-7636"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jonathan Carter","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5113842004","display_name":"Leonid Oliker","orcid":"https://orcid.org/0000-0002-7923-2896"},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Leonid Oliker","raw_affiliation_strings":["Lawrence Berkeley National Laboratory"],"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010873686","display_name":"John Shalf","orcid":"https://orcid.org/0000-0002-0608-3690"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"John Shalf","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5091741596","display_name":"Katherine Yelick","orcid":"https://orcid.org/0000-0003-0957-701X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Katherine Yelick","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5104047193"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.37,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.67214397,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"253","last_page":"288"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991000294685364,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.996999979019165,"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/stencil","display_name":"Stencil","score":0.9437698125839233},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5347145199775696},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.46874454617500305},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.443838894367218},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.34354087710380554},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.13182109594345093}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.9437698125839233},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5347145199775696},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.46874454617500305},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.443838894367218},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.34354087710380554},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.13182109594345093}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1201/b10376-25","is_oa":true,"landing_page_url":"https://doi.org/10.1201/b10376-25","pdf_url":"https://api.taylorfrancis.com/content/chapters/edit/download?identifierName=doi&identifierValue=10.1201/b10376-25&type=chapterpdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Computing with Multicore and Accelerators","raw_type":"book-chapter"}],"best_oa_location":{"id":"doi:10.1201/b10376-25","is_oa":true,"landing_page_url":"https://doi.org/10.1201/b10376-25","pdf_url":"https://api.taylorfrancis.com/content/chapters/edit/download?identifierName=doi&identifierValue=10.1201/b10376-25&type=chapterpdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Computing with Multicore and Accelerators","raw_type":"book-chapter"},"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5299999713897705}],"awards":[{"id":"https://openalex.org/G1065316766","display_name":null,"funder_award_id":"Award","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G1286236842","display_name":null,"funder_award_id":"-AC02-05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G3083819904","display_name":null,"funder_award_id":"05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4015171322","display_name":null,"funder_award_id":"0953100","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G425189044","display_name":null,"funder_award_id":"DE-AC02-05CH","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G4384726126","display_name":null,"funder_award_id":"24894","funder_id":"https://openalex.org/F4320307102","funder_display_name":"Intel Corporation"},{"id":"https://openalex.org/G4501827968","display_name":null,"funder_award_id":"AC02-05CH11231","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G4565140552","display_name":null,"funder_award_id":"-AC02-05CH11231","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G4610648879","display_name":null,"funder_award_id":"DE-AC02-05CH112","funder_id":"https://openalex.org/F4320338292","funder_display_name":"Lawrence Berkeley National Laboratory"},{"id":"https://openalex.org/G4719203796","display_name":null,"funder_award_id":"0833136","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4841871747","display_name":null,"funder_award_id":"DE_AC02-05CH11231","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G490593687","display_name":null,"funder_award_id":"Intel","funder_id":"https://openalex.org/F4320306087","funder_display_name":"Semiconductor Research Corporation"},{"id":"https://openalex.org/G4979187122","display_name":null,"funder_award_id":"DE-AC02-05CH1123","funder_id":"https://openalex.org/F4320338292","funder_display_name":"Lawrence Berkeley National Laboratory"},{"id":"https://openalex.org/G498139845","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G5206177008","display_name":null,"funder_award_id":"DE-AC02-05CH11231","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5315912995","display_name":null,"funder_award_id":"11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G5539140862","display_name":null,"funder_award_id":"DE-AC02-05CH11231","funder_id":"https://openalex.org/F4320307102","funder_display_name":"Intel Corporation"},{"id":"https://openalex.org/G5616020913","display_name":null,"funder_award_id":"024263","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5706129643","display_name":null,"funder_award_id":"024894","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G5802748842","display_name":null,"funder_award_id":"DE-AC02-05CH112","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G5921281487","display_name":null,"funder_award_id":"number","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6330738325","display_name":null,"funder_award_id":"DE_AC02_05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6348972864","display_name":null,"funder_award_id":"AC02-05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6418351505","display_name":null,"funder_award_id":"DIG07-10227","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G6429026066","display_name":null,"funder_award_id":"DE-AC02-05CH112","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6558272803","display_name":null,"funder_award_id":"DE-AC02","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G6671297155","display_name":null,"funder_award_id":"CAREER","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6894402473","display_name":null,"funder_award_id":"Fellowship","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7233692708","display_name":null,"funder_award_id":"DE-AC02-05CH11231","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7340683655","display_name":null,"funder_award_id":"E-AC02-05CH11231","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7354628648","display_name":null,"funder_award_id":"05CH11231","funder_id":"https://openalex.org/F4320338292","funder_display_name":"Lawrence Berkeley National Laboratory"},{"id":"https://openalex.org/G7406122311","display_name":null,"funder_award_id":"AC02-05CH1123","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G7664691372","display_name":null,"funder_award_id":"DE-AC02-05CH1123","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G7766933102","display_name":"ITR/NGS: Automatic Performance Tuning for Large Scale Scientific Applications","funder_award_id":"0325873","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7825954517","display_name":null,"funder_award_id":"DE-AC02-05CH1123","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G8306346728","display_name":null,"funder_award_id":"AC02-05CH11231","funder_id":"https://openalex.org/F4320338292","funder_display_name":"Lawrence Berkeley National Laboratory"},{"id":"https://openalex.org/G8325766496","display_name":null,"funder_award_id":"DIG07-10227","funder_id":"https://openalex.org/F4320307102","funder_display_name":"Intel Corporation"},{"id":"https://openalex.org/G8414908677","display_name":null,"funder_award_id":"DE-AC0","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"},{"id":"https://openalex.org/G848032724","display_name":null,"funder_award_id":"Science","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G8798833609","display_name":null,"funder_award_id":"024894","funder_id":"https://openalex.org/F4320307102","funder_display_name":"Intel Corporation"},{"id":"https://openalex.org/G8840554483","display_name":null,"funder_award_id":"024263","funder_id":"https://openalex.org/F4320307102","funder_display_name":"Intel Corporation"},{"id":"https://openalex.org/G897164627","display_name":null,"funder_award_id":"DE-AC02_05CH11231","funder_id":"https://openalex.org/F4320332359","funder_display_name":"Office of Science"},{"id":"https://openalex.org/G969889393","display_name":null,"funder_award_id":"DE-AC02-","funder_id":"https://openalex.org/F4320306084","funder_display_name":"U.S. Department of Energy"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320306084","display_name":"U.S. Department of Energy","ror":"https://ror.org/01bj3aw27"},{"id":"https://openalex.org/F4320306087","display_name":"Semiconductor Research Corporation","ror":"https://ror.org/047z4n946"},{"id":"https://openalex.org/F4320307102","display_name":"Intel Corporation","ror":"https://ror.org/01ek73717"},{"id":"https://openalex.org/F4320309321","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320338292","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4233293392.pdf","grobid_xml":"https://content.openalex.org/works/W4233293392.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2039378765","https://openalex.org/W2003798513","https://openalex.org/W2890431355","https://openalex.org/W2151764765","https://openalex.org/W4376875029","https://openalex.org/W2097757554","https://openalex.org/W3149084271","https://openalex.org/W2150319905","https://openalex.org/W2962978274","https://openalex.org/W1429949169"],"abstract_inverted_index":{"The":[0,76],"recent":[1],"transformation":[2],"from":[3,12],"an":[4,22,56],"environment":[5,23],"where":[6,24],"gains":[7,25],"in":[8,51,230],"computational":[9],"performance":[10,37,174],"came":[11],"increasing":[13,33],"clock":[14],"frequency":[15],"and":[16,58,66,156,178,193,224],"other":[17],"hardware":[18,110],"engineering":[19],"innovations,":[20],"to":[21,62,104,112,136,161,232],"are":[26,91],"realized":[27],"through":[28],"the":[29,42,85,141,157,163,214,220,233,236],"deployment":[30],"of":[31,35,44,87,118,144,147,159,216,235],"ever":[32],"numbers":[34],"modest":[36],"cores":[38,107],"has":[39],"profoundly":[40],"changed":[41],"landscape":[43],"scientific":[45],"application":[46,79],"programming.":[47],"This":[48],"exponential":[49],"increase":[50],"core":[52],"count":[53],"represents":[54,129],"both":[55],"opportunity":[57],"a":[59,130,148,204],"challenge:":[60],"access":[61,187],"petascale":[63],"simulation":[64],"capabilities":[65],"beyond":[67],"will":[68],"require":[69,115],"that":[70,90,108,114,151],"this":[71,137],"concurrency":[72],"be":[73,228],"efficiently":[74],"exploited.":[75],"problem":[77,138],"for":[78,125],"programmers":[80],"is":[81,139,207],"further":[82],"compounded":[83],"by":[84,183,191,197],"diversity":[86],"multicore":[88],"architectures":[89],"now":[92],"emerging":[93,134],"[4].":[94],"From":[95],"relatively":[96,105],"complex":[97,101],"out-of-order":[98],"CPUs":[99],"with":[100,175,209],"cache":[102,198,221],"structures,":[103],"simple":[106],"support":[109],"multithreading,":[111],"chips":[113],"explicit":[116],"use":[117],"software":[119],"controlled":[120],"memory,":[121],"designing":[122],"optimal":[123],"code":[124,149],"these":[126,160,225],"different":[127],"platforms":[128],"serious":[131],"impediment.":[132],"An":[133],"solution":[135],"auto-tuning:":[140],"automatic":[142],"generation":[143],"many":[145],"versions":[146],"kernel":[150],"incorporate":[152],"various":[153],"tuning":[154,168,211],"strategies,":[155],"benchmarking":[158],"select":[162],"highest":[164],"performing":[165],"version.":[166],"Typical":[167],"strategies":[169,238],"might":[170],"include:":[171],"maximizing":[172,180],"incore":[173],"loop":[176,217],"unrolling":[177,218],"restructuring;":[179],"memory":[181,186,195],"bandwidth":[182],"exploiting":[184],"non-uniform":[185],"(NUMA),":[188],"engaging":[189],"prefetch":[190],"directives;":[192],"minimizing":[194],"traffic":[196],"blocking":[199,222],"or":[200,219],"array":[201],"padding.":[202],"Often":[203],"key":[205],"parameter":[206],"associated":[208],"each":[210],"strategy":[212],"(e.g.,":[213],"amount":[215],"factor),":[223],"parameters":[226],"must":[227],"explored":[229],"addition":[231],"layering":[234],"basic":[237],"themselves.":[239]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2022-05-12T00:00:00"}