{"id":"https://openalex.org/W2122677725","doi":"https://doi.org/10.1109/ipdps.2013.79","title":"Optimizing and Auto-Tuning Iterative Stencil Loops for GPUs with the In-Plane Method","display_name":"Optimizing and Auto-Tuning Iterative Stencil Loops for GPUs with the In-Plane Method","publication_year":2013,"publication_date":"2013-05-01","ids":{"openalex":"https://openalex.org/W2122677725","doi":"https://doi.org/10.1109/ipdps.2013.79","mag":"2122677725"},"language":"en","primary_location":{"id":"doi:10.1109/ipdps.2013.79","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2013.79","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 27th International Symposium on Parallel and Distributed Processing","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/A5103180941","display_name":"Wai Teng Tang","orcid":"https://orcid.org/0000-0002-6553-1270"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Wai Teng Tang","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore","Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, , Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, , Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080332038","display_name":"Wen Jun Tan","orcid":"https://orcid.org/0000-0003-2204-0639"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wen Jun Tan","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore","Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, , Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, , Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103348679","display_name":"Ratna Krishnamoorthy","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Ratna Krishnamoorthy","raw_affiliation_strings":["Department of Computer Science, School of Computing, National University of Singapore, Singapore","Department of Computer Science, National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Computer Science, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063229833","display_name":"Yi Wen Wong","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yi Wen Wong","raw_affiliation_strings":["Department of Computer Science, School of Computing, National University of Singapore, Singapore","Department of Computer Science, National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Computer Science, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051958317","display_name":"Shyh-Hao Kuo","orcid":null},"institutions":[{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]},{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shyh-Hao Kuo","raw_affiliation_strings":["Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore","Inst. of High Performance Comput., Agency for Sci., Technol., & Res., Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Inst. of High Performance Comput., Agency for Sci., Technol., & Res., Singapore, Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001599295","display_name":"Rick Siow Mong Goh","orcid":"https://orcid.org/0000-0001-9116-1595"},"institutions":[{"id":"https://openalex.org/I115228651","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09","country_code":"SG","type":"government","lineage":["https://openalex.org/I115228651"]},{"id":"https://openalex.org/I3004594783","display_name":"Institute of High Performance Computing","ror":"https://ror.org/02n0ejh50","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3004594783","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Rick Siow Mong Goh","raw_affiliation_strings":["Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore","Inst. of High Performance Comput., Agency for Sci., Technol., & Res., Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Institute of High Performance Computing, Agency for Science, Technology and Research, Singapore","institution_ids":["https://openalex.org/I3004594783","https://openalex.org/I115228651"]},{"raw_affiliation_string":"Inst. of High Performance Comput., Agency for Sci., Technol., & Res., Singapore, Singapore","institution_ids":["https://openalex.org/I115228651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055281326","display_name":"Stephen John Turner","orcid":"https://orcid.org/0000-0002-7421-9801"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Stephen John Turner","raw_affiliation_strings":["School of Computer Engineering, Nanyang Technological University, Singapore","Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, , Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computer Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]},{"raw_affiliation_string":"Sch. of Comput. Eng., Nanyang Technol. Univ., Singapore, , Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023989495","display_name":"Weng\u2010Fai Wong","orcid":"https://orcid.org/0000-0002-4281-2053"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Weng-Fai Wong","raw_affiliation_strings":["Department of Computer Science, School of Computing, National University of Singapore, Singapore","Department of Computer Science, National University of Singapore, Singapore, Singapore"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Computer Science, National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5103180941"],"corresponding_institution_ids":["https://openalex.org/I172675005"],"apc_list":null,"apc_paid":null,"fwci":1.8913,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.865637,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"452","last_page":"462"},"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/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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9821000099182129,"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":0.9758706092834473},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.8353577852249146},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8084094524383545},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.7298339009284973},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7224677205085754},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6938644647598267},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.53788822889328},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5294339656829834},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.425165593624115},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.410258024930954},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25950610637664795}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.9758706092834473},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.8353577852249146},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8084094524383545},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.7298339009284973},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7224677205085754},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6938644647598267},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.53788822889328},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5294339656829834},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.425165593624115},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.410258024930954},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25950610637664795},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/ipdps.2013.79","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ipdps.2013.79","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE 27th International Symposium on Parallel and Distributed Processing","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/78272","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/78272","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","issn_l":null,"issn":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.5199999809265137,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W588863486","https://openalex.org/W1967264375","https://openalex.org/W1983771518","https://openalex.org/W1987588924","https://openalex.org/W2000842323","https://openalex.org/W2015935981","https://openalex.org/W2016618963","https://openalex.org/W2035701183","https://openalex.org/W2039378765","https://openalex.org/W2049875313","https://openalex.org/W2052196304","https://openalex.org/W2074833026","https://openalex.org/W2084977935","https://openalex.org/W2095875205","https://openalex.org/W2096369748","https://openalex.org/W2104512032","https://openalex.org/W2113190809","https://openalex.org/W2113754927","https://openalex.org/W2119042753","https://openalex.org/W2129471558","https://openalex.org/W2135682468","https://openalex.org/W2150319905","https://openalex.org/W2154078685","https://openalex.org/W2154786353","https://openalex.org/W2167523268","https://openalex.org/W3139770841","https://openalex.org/W3147336131","https://openalex.org/W3152199537","https://openalex.org/W4249968602","https://openalex.org/W6617425210","https://openalex.org/W6654374846","https://openalex.org/W6674395002","https://openalex.org/W6684406925"],"related_works":["https://openalex.org/W1973046741","https://openalex.org/W2983282793","https://openalex.org/W1977185554","https://openalex.org/W2076165488","https://openalex.org/W2177020196","https://openalex.org/W3189307731","https://openalex.org/W2949962288","https://openalex.org/W2364686214","https://openalex.org/W1428699136","https://openalex.org/W1998560227"],"abstract_inverted_index":{"Stencils":[0],"represent":[1],"an":[2,94],"important":[3,51],"class":[4],"of":[5,16,36,55,133],"computations":[6,19,75],"that":[7,130],"are":[8,23],"used":[9,120],"in":[10,20,52,87],"many":[11,15],"scientific":[12,21],"disciplines.":[13],"Increasingly,":[14],"the":[17,37,43,47,53,83,88,102,124],"stencil":[18,44,74],"applications":[22],"being":[24],"offloaded":[25],"to":[26,28,100,121,140],"GPUs":[27,77],"improve":[29],"running":[30],"times.":[31],"Since":[32],"a":[33,69,131],"large":[34],"part":[35],"simulation":[38,62],"time":[39],"is":[40,49,119],"spent":[41],"inside":[42],"kernels,":[45],"optimizing":[46],"kernel":[48],"therefore":[50],"context":[54],"achieving":[56],"greater":[57],"computation":[58],"efficiencies":[59],"and":[60,78,118],"reducing":[61],"time.":[63],"In":[64],"this":[65],"work,":[66],"we":[67],"proposed":[68,116],"novel":[70],"in-plane":[71],"method":[72,85,99],"for":[73,97,105,114],"on":[76],"compared":[79,139],"its":[80],"performance":[81,110],"with":[82],"conventional":[84],"implemented":[86,93],"Nvidia":[89],"SDK.":[90],"We":[91],"also":[92],"auto-tuning":[95,125],"framework":[96],"our":[98,115],"select":[101],"optimal":[103],"parameters":[104],"different":[106],"GPU":[107],"architectures.":[108],"A":[109],"model":[111],"was":[112],"developed":[113],"method,":[117],"speed":[122],"up":[123],"process.":[126],"Our":[127],"results":[128],"show":[129],"speedup":[132],"nearly":[134],"2\u00d7":[135],"can":[136],"be":[137],"achieved":[138],"Nvidia's":[141],"implementation.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3},{"year":2015,"cited_by_count":5},{"year":2014,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}