{"id":"https://openalex.org/W2916922955","doi":"https://doi.org/10.1109/cahpc.2018.8645848","title":"Automated GPU Grid Geometry Selection for OPENMP Kernels","display_name":"Automated GPU Grid Geometry Selection for OPENMP Kernels","publication_year":2018,"publication_date":"2018-09-01","ids":{"openalex":"https://openalex.org/W2916922955","doi":"https://doi.org/10.1109/cahpc.2018.8645848","mag":"2916922955"},"language":"en","primary_location":{"id":"doi:10.1109/cahpc.2018.8645848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cahpc.2018.8645848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)","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/A5028682148","display_name":"Taylor Lloyd","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Taylor Lloyd","raw_affiliation_strings":["University of Alberta, Edmonton, Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048684499","display_name":"Artem Chikin","orcid":null},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Artem Chikin","raw_affiliation_strings":["University of Alberta, Edmonton, Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013167629","display_name":"Sanket Kedia","orcid":null},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sanket Kedia","raw_affiliation_strings":["IIT Kharagpur, Kharagpur, India"],"affiliations":[{"raw_affiliation_string":"IIT Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107889083","display_name":"Dhruv Jain","orcid":null},"institutions":[{"id":"https://openalex.org/I145894827","display_name":"Indian Institute of Technology Kharagpur","ror":"https://ror.org/03w5sq511","country_code":"IN","type":"education","lineage":["https://openalex.org/I145894827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Dhruv Jain","raw_affiliation_strings":["IIT Kharagpur, Kharagpur, India"],"affiliations":[{"raw_affiliation_string":"IIT Kharagpur, Kharagpur, India","institution_ids":["https://openalex.org/I145894827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048554669","display_name":"Jos\u00e9 Nelson Amaral","orcid":"https://orcid.org/0000-0002-9943-1809"},"institutions":[{"id":"https://openalex.org/I154425047","display_name":"University of Alberta","ror":"https://ror.org/0160cpw27","country_code":"CA","type":"education","lineage":["https://openalex.org/I154425047"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Jose Nelson Amaral","raw_affiliation_strings":["University of Alberta, Edmonton, Canada"],"affiliations":[{"raw_affiliation_string":"University of Alberta, Edmonton, Canada","institution_ids":["https://openalex.org/I154425047"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5028682148"],"corresponding_institution_ids":["https://openalex.org/I154425047"],"apc_list":null,"apc_paid":null,"fwci":1.0099,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.76484967,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"442","last_page":"449"},"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":0.9973999857902527,"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":0.995199978351593,"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/compiler","display_name":"Compiler","score":0.7902936339378357},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7801094055175781},{"id":"https://openalex.org/keywords/grid","display_name":"Grid","score":0.7231032848358154},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.6514232754707336},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.6500033140182495},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.6110533475875854},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5760261416435242},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.5083696246147156},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.47425806522369385},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.40848299860954285},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35472989082336426},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.30584147572517395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.27347320318222046},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.14491933584213257},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09651502966880798}],"concepts":[{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7902936339378357},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7801094055175781},{"id":"https://openalex.org/C187691185","wikidata":"https://www.wikidata.org/wiki/Q2020720","display_name":"Grid","level":2,"score":0.7231032848358154},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6514232754707336},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.6500033140182495},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.6110533475875854},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5760261416435242},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.5083696246147156},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.47425806522369385},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.40848299860954285},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35472989082336426},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.30584147572517395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.27347320318222046},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.14491933584213257},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09651502966880798},{"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:10.1109/cahpc.2018.8645848","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cahpc.2018.8645848","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 30th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1972971542","https://openalex.org/W1982020565","https://openalex.org/W1983078445","https://openalex.org/W1988888548","https://openalex.org/W2000857901","https://openalex.org/W2056579078","https://openalex.org/W2126026097","https://openalex.org/W2128120785","https://openalex.org/W2166536280","https://openalex.org/W2171436656","https://openalex.org/W2180288011","https://openalex.org/W2211541975","https://openalex.org/W2911964244"],"related_works":["https://openalex.org/W4240253816","https://openalex.org/W3096456556","https://openalex.org/W2169584677","https://openalex.org/W2979513934","https://openalex.org/W4232954277","https://openalex.org/W2020341030","https://openalex.org/W2749133591","https://openalex.org/W2367473450","https://openalex.org/W23346600","https://openalex.org/W2460280200"],"abstract_inverted_index":{"Modern":[0],"supercomputers":[1],"are":[2,45],"increasingly":[3],"using":[4],"GPUs":[5],"to":[6,29,131,145],"improve":[7],"performance":[8,79,127],"per":[9],"watt.":[10],"Generating":[11],"GPU":[12,32],"code":[13],"for":[14,47,72,115],"target":[15],"regions":[16],"in":[17,77,125,159],"openMP":[18],"4.0,":[19],"or":[20],"later":[21],"versions,":[22],"requires":[23],"the":[24,31,52,88,97,100,109,112,116,143,147,151],"selection":[25],"of":[26,85,99,108,111,118,129,138],"grid":[27,57],"geometry":[28,58,71],"execute":[30],"kernel.":[33],"Existing":[34],"industrial-strength":[35],"compilers":[36],"use":[37],"a":[38,63,69,78,82,119,126,135],"simple":[39],"heuristic":[40,122,154],"with":[41,81,134],"arbitrary":[42],"numbers":[43],"that":[44,66,123,155],"constant":[46],"all":[48],"kernels.":[49],"After":[50],"characterizing":[51],"relationship":[53],"between":[54],"region":[55],"features,":[56],"and":[59,75,150],"performance,":[60],"we":[61],"built":[62],"machine-learning":[64,148],"model":[65],"successfully":[67],"predicts":[68],"suitable":[70],"such":[73],"kernels":[74],"results":[76,110],"improvement":[80,128],"geometric":[83,136],"mean":[84,137],"5%":[86],"across":[87],"benchmarks":[89],"studied.":[90],"However,":[91],"this":[92],"prediction":[93],"is":[94,102],"impractical":[95],"because":[96],"overhead":[98],"predictor":[101,113],"too":[103],"high.":[104],"A":[105],"careful":[106],"study":[107],"allowed":[114],"development":[117],"practical":[120,152],"low-overhead":[121,153],"resulted":[124],"up":[130],"7":[132],"times":[133],"25.9%.":[139],"This":[140],"paper":[141],"describes":[142],"methodology":[144],"build":[146],"model,":[149],"can":[156],"be":[157],"used":[158],"industry-strong":[160],"compilers.":[161]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}