{"id":"https://openalex.org/W2800041898","doi":"https://doi.org/10.1155/2018/6093054","title":"A Strategy for Automatic Performance Tuning of Stencil Computations on GPUs","display_name":"A Strategy for Automatic Performance Tuning of Stencil Computations on GPUs","publication_year":2018,"publication_date":"2018-05-28","ids":{"openalex":"https://openalex.org/W2800041898","doi":"https://doi.org/10.1155/2018/6093054","mag":"2800041898"},"language":"en","primary_location":{"id":"doi:10.1155/2018/6093054","is_oa":true,"landing_page_url":"http://doi.org/10.1155/2018/6093054","pdf_url":"http://downloads.hindawi.com/journals/sp/2018/6093054.pdf","source":{"id":"https://openalex.org/S166774750","display_name":"Scientific Programming","issn_l":"1058-9244","issn":["1058-9244","1875-919X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Programming","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"http://downloads.hindawi.com/journals/sp/2018/6093054.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5075794357","display_name":"Joseph Garvey","orcid":"https://orcid.org/0000-0001-7834-8339"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Joseph D. Garvey","raw_affiliation_strings":["Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON, Canada M5S 3G4"],"affiliations":[{"raw_affiliation_string":"Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON, Canada M5S 3G4","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080157948","display_name":"Tarek S. Abdelrahman","orcid":"https://orcid.org/0000-0002-2985-4873"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Tarek S. Abdelrahman","raw_affiliation_strings":["Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON, Canada M5S 3G4"],"affiliations":[{"raw_affiliation_string":"Edward S. Rogers Sr. Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON, Canada M5S 3G4","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5080157948"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":{"value":1800,"currency":"USD","value_usd":1800},"apc_paid":{"value":1800,"currency":"USD","value_usd":1800},"fwci":0.5255,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.61273944,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"2018","issue":null,"first_page":"1","last_page":"24"},"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/T12808","display_name":"Ferroelectric and Negative Capacitance Devices","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"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":0.9905399680137634},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8103790283203125},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.6815396547317505},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6521518230438232},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.6461785435676575},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.5101204514503479},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.48312804102897644},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47108685970306396},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.42022082209587097},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4028494954109192},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1671002209186554},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.14409014582633972}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.9905399680137634},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8103790283203125},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.6815396547317505},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6521518230438232},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.6461785435676575},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.5101204514503479},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.48312804102897644},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47108685970306396},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.42022082209587097},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4028494954109192},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1671002209186554},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.14409014582633972},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1155/2018/6093054","is_oa":true,"landing_page_url":"http://doi.org/10.1155/2018/6093054","pdf_url":"http://downloads.hindawi.com/journals/sp/2018/6093054.pdf","source":{"id":"https://openalex.org/S166774750","display_name":"Scientific Programming","issn_l":"1058-9244","issn":["1058-9244","1875-919X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Programming","raw_type":"journal-article"},{"id":"pmh:oai:utoronto.scholaris.ca:1807/88410","is_oa":true,"landing_page_url":"http://hdl.handle.net/1807/88410","pdf_url":"https://utoronto.scholaris.ca/bitstreams/56fa2ac0-d8f8-4f5e-bd11-328c220b9228/download","source":{"id":"https://openalex.org/S7407055458","display_name":"TSpace","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"pmh:oai:doaj.org/article:810cb98537c5492186019c8fb2a2c151","is_oa":true,"landing_page_url":"https://doaj.org/article/810cb98537c5492186019c8fb2a2c151","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scientific Programming, Vol 2018 (2018)","raw_type":"article"},{"id":"pmh:oai:hindawi.com:10.1155/2018/6093054","is_oa":true,"landing_page_url":"https://doi.org/10.1155/2018/6093054","pdf_url":null,"source":{"id":"https://openalex.org/S4306400340","display_name":"Hindawi Journal of Chemistry (Hindawi)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210126990","host_organization_name":"Hindawi (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210126990"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Research Article"}],"best_oa_location":{"id":"doi:10.1155/2018/6093054","is_oa":true,"landing_page_url":"http://doi.org/10.1155/2018/6093054","pdf_url":"http://downloads.hindawi.com/journals/sp/2018/6093054.pdf","source":{"id":"https://openalex.org/S166774750","display_name":"Scientific Programming","issn_l":"1058-9244","issn":["1058-9244","1875-919X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319869","host_organization_name":"Hindawi Publishing Corporation","host_organization_lineage":["https://openalex.org/P4310319869"],"host_organization_lineage_names":["Hindawi Publishing Corporation"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Scientific Programming","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.4000000059604645,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G2165548363","display_name":null,"funder_award_id":"Canada","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"},{"id":"https://openalex.org/G8284766523","display_name":null,"funder_award_id":"(NSERC)","funder_id":"https://openalex.org/F4320334593","funder_display_name":"Natural Sciences and Engineering Research Council of Canada"}],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2800041898.pdf","grobid_xml":"https://content.openalex.org/works/W2800041898.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W1863336885","https://openalex.org/W1972616929","https://openalex.org/W2003264742","https://openalex.org/W2028873795","https://openalex.org/W2072916763","https://openalex.org/W2133990480","https://openalex.org/W2911964244"],"related_works":["https://openalex.org/W3105129168","https://openalex.org/W2804920739","https://openalex.org/W2177020196","https://openalex.org/W3189307731","https://openalex.org/W1428699136","https://openalex.org/W2949962288","https://openalex.org/W2364686214","https://openalex.org/W1998560227","https://openalex.org/W1429949169","https://openalex.org/W3139770841"],"abstract_inverted_index":{"We":[0,56,74,99,160],"propose":[1],"and":[2,48,109,133,146,156,173,175],"evaluate":[3,162],"a":[4,12,24,40,54,58,95,114],"novel":[5],"strategy":[6,22,164],"for":[7,79,165],"tuning":[8],"the":[9,30,77,84,102,118,128,151],"performance":[10,149],"of":[11,14,60,69,104,117],"class":[13],"stencil":[15,64,72,167],"computations":[16],"on":[17,107,127,150],"Graphics":[18],"Processing":[19],"Units.":[20],"The":[21],"uses":[23],"machine":[25],"learning":[26],"model":[27],"to":[28,33,93,113,139],"predict":[29],"optimal":[31],"way":[32],"load":[34],"data":[35],"from":[36],"memory":[37],"followed":[38],"by":[39,81],"heuristic":[41],"that":[42,66,83,90,123],"divides":[43],"other":[44],"optimizations":[45],"into":[46],"groups":[47],"exhaustively":[49],"explores":[50],"one":[51],"group":[52],"at":[53],"time.":[55,159],"use":[57],"set":[59],"104":[61],"synthetic":[62],"OpenCL":[63],"benchmarks":[65],"are":[67,124],"representative":[68],"many":[70],"real":[71],"computations.":[73],"first":[75],"demonstrate":[76,101],"need":[78],"auto-tuning":[80],"showing":[82],"optimization":[85],"space":[86],"is":[87],"sufficiently":[88],"complex":[89],"simple":[91],"approaches":[92],"determining":[94],"high-performing":[96],"configuration":[97],"fail.":[98],"then":[100],"effectiveness":[103],"our":[105,163],"approach":[106],"NVIDIA":[108],"AMD":[110],"GPUs.":[111],"Relative":[112,138],"random":[115],"sampling":[116],"space,":[119],"we":[120,143],"find":[121],"configurations":[122],"12%/32%":[125],"faster":[126],"NVIDIA/AMD":[129],"platform":[130],"in":[131,154,176],"71%":[132],"4%":[134],"less":[135,158],"time,":[136],"respectively.":[137],"an":[140],"expert":[141,179],"search,":[142],"achieve":[144],"5%":[145],"9%":[147],"better":[148],"two":[152],"platforms":[153],"89%":[155],"76%":[157],"also":[161],"different":[166],"computational":[168],"intensities,":[169],"varying":[170],"array":[171],"sizes":[172],"shapes,":[174],"combination":[177],"with":[178],"search.":[180]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}
