{"id":"https://openalex.org/W2072625243","doi":"https://doi.org/10.1109/hpec.2014.7040968","title":"Optimized three-dimensional stencil computation on Fermi and Kepler GPUs","display_name":"Optimized three-dimensional stencil computation on Fermi and Kepler GPUs","publication_year":2014,"publication_date":"2014-09-01","ids":{"openalex":"https://openalex.org/W2072625243","doi":"https://doi.org/10.1109/hpec.2014.7040968","mag":"2072625243"},"language":"en","primary_location":{"id":"doi:10.1109/hpec.2014.7040968","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2014.7040968","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5020183359","display_name":"Anamaria Vizitiu","orcid":"https://orcid.org/0000-0002-4289-0385"},"institutions":[{"id":"https://openalex.org/I4210095246","display_name":"Siemens (Romania)","ror":"https://ror.org/00sexkk33","country_code":"RO","type":"company","lineage":["https://openalex.org/I1325886976","https://openalex.org/I4210095246"]},{"id":"https://openalex.org/I3123573182","display_name":"Transylvania University of Bra\u0219ov","ror":"https://ror.org/01cg9ws23","country_code":"RO","type":"education","lineage":["https://openalex.org/I3123573182"]}],"countries":["RO"],"is_corresponding":true,"raw_author_name":"Anamaria Vizitiu","raw_affiliation_strings":["Siemens Corporate Technology, SC Siemens SRL, Transilvania University of Bra\u015fov, Bra\u015fov, Romania","Siemens Corporate Technology, SC Siemens SRL, Department of Automation and Information Technology, Transilvania University of Brasov, Romania"],"affiliations":[{"raw_affiliation_string":"Siemens Corporate Technology, SC Siemens SRL, Transilvania University of Bra\u015fov, Bra\u015fov, Romania","institution_ids":["https://openalex.org/I3123573182","https://openalex.org/I4210095246"]},{"raw_affiliation_string":"Siemens Corporate Technology, SC Siemens SRL, Department of Automation and Information Technology, Transilvania University of Brasov, Romania","institution_ids":["https://openalex.org/I3123573182","https://openalex.org/I4210095246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006236000","display_name":"Lucian Itu","orcid":"https://orcid.org/0000-0002-2205-497X"},"institutions":[{"id":"https://openalex.org/I4210095246","display_name":"Siemens (Romania)","ror":"https://ror.org/00sexkk33","country_code":"RO","type":"company","lineage":["https://openalex.org/I1325886976","https://openalex.org/I4210095246"]},{"id":"https://openalex.org/I3123573182","display_name":"Transylvania University of Bra\u0219ov","ror":"https://ror.org/01cg9ws23","country_code":"RO","type":"education","lineage":["https://openalex.org/I3123573182"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Lucian Itu","raw_affiliation_strings":["Siemens Corporate Technology, SC Siemens SRL, Transilvania University of Bra\u015fov, Bra\u015fov, Romania","Siemens Corporate Technology, SC Siemens SRL, Department of Automation and Information Technology, Transilvania University of Brasov, Romania"],"affiliations":[{"raw_affiliation_string":"Siemens Corporate Technology, SC Siemens SRL, Transilvania University of Bra\u015fov, Bra\u015fov, Romania","institution_ids":["https://openalex.org/I3123573182","https://openalex.org/I4210095246"]},{"raw_affiliation_string":"Siemens Corporate Technology, SC Siemens SRL, Department of Automation and Information Technology, Transilvania University of Brasov, Romania","institution_ids":["https://openalex.org/I3123573182","https://openalex.org/I4210095246"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112797335","display_name":"Cosmin Nita","orcid":null},"institutions":[{"id":"https://openalex.org/I3123573182","display_name":"Transylvania University of Bra\u0219ov","ror":"https://ror.org/01cg9ws23","country_code":"RO","type":"education","lineage":["https://openalex.org/I3123573182"]},{"id":"https://openalex.org/I4210095246","display_name":"Siemens (Romania)","ror":"https://ror.org/00sexkk33","country_code":"RO","type":"company","lineage":["https://openalex.org/I1325886976","https://openalex.org/I4210095246"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Cosmin Nita","raw_affiliation_strings":["Siemens Corporate Technology, SC Siemens SRL, Transilvania University of Bra\u015fov, Bra\u015fov, Romania","Siemens Corporate Technology, SC Siemens SRL, Department of Automation and Information Technology, Transilvania University of Brasov, Romania"],"affiliations":[{"raw_affiliation_string":"Siemens Corporate Technology, SC Siemens SRL, Transilvania University of Bra\u015fov, Bra\u015fov, Romania","institution_ids":["https://openalex.org/I3123573182","https://openalex.org/I4210095246"]},{"raw_affiliation_string":"Siemens Corporate Technology, SC Siemens SRL, Department of Automation and Information Technology, Transilvania University of Brasov, Romania","institution_ids":["https://openalex.org/I3123573182","https://openalex.org/I4210095246"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5086074270","display_name":"Constantin Suciu","orcid":"https://orcid.org/0009-0004-1253-6360"},"institutions":[{"id":"https://openalex.org/I4210095246","display_name":"Siemens (Romania)","ror":"https://ror.org/00sexkk33","country_code":"RO","type":"company","lineage":["https://openalex.org/I1325886976","https://openalex.org/I4210095246"]},{"id":"https://openalex.org/I3123573182","display_name":"Transylvania University of Bra\u0219ov","ror":"https://ror.org/01cg9ws23","country_code":"RO","type":"education","lineage":["https://openalex.org/I3123573182"]}],"countries":["RO"],"is_corresponding":false,"raw_author_name":"Constantin Suciu","raw_affiliation_strings":["Siemens Corporate Technology, SC Siemens SRL, Transilvania University of Bra\u015fov, Bra\u015fov, Romania","Siemens Corporate Technology, SC Siemens SRL, Department of Automation and Information Technology, Transilvania University of Brasov, Romania"],"affiliations":[{"raw_affiliation_string":"Siemens Corporate Technology, SC Siemens SRL, Transilvania University of Bra\u015fov, Bra\u015fov, Romania","institution_ids":["https://openalex.org/I3123573182","https://openalex.org/I4210095246"]},{"raw_affiliation_string":"Siemens Corporate Technology, SC Siemens SRL, Department of Automation and Information Technology, Transilvania University of Brasov, Romania","institution_ids":["https://openalex.org/I3123573182","https://openalex.org/I4210095246"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5020183359"],"corresponding_institution_ids":["https://openalex.org/I3123573182","https://openalex.org/I4210095246"],"apc_list":null,"apc_paid":null,"fwci":1.5324,"has_fulltext":false,"cited_by_count":20,"citation_normalized_percentile":{"value":0.83005145,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9929999709129333,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.9091984033584595},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8192422389984131},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.814711332321167},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6749510169029236},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.5675670504570007},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5516680479049683},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5242912173271179},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.4818354845046997},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.47177886962890625},{"id":"https://openalex.org/keywords/kepler","display_name":"Kepler","score":0.43978869915008545},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.25288498401641846},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.111409991979599},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.08394411206245422}],"concepts":[{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.9091984033584595},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8192422389984131},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.814711332321167},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6749510169029236},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.5675670504570007},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5516680479049683},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5242912173271179},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.4818354845046997},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.47177886962890625},{"id":"https://openalex.org/C207963374","wikidata":"https://www.wikidata.org/wiki/Q47592","display_name":"Kepler","level":3,"score":0.43978869915008545},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25288498401641846},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.111409991979599},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.08394411206245422},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C150846664","wikidata":"https://www.wikidata.org/wiki/Q7602306","display_name":"Stars","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec.2014.7040968","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec.2014.7040968","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2014 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8700000047683716,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W55678618","https://openalex.org/W1762731526","https://openalex.org/W1820993528","https://openalex.org/W1917541634","https://openalex.org/W2046239430","https://openalex.org/W2056295840","https://openalex.org/W2063656563","https://openalex.org/W2070487325","https://openalex.org/W2096672917","https://openalex.org/W2113190809","https://openalex.org/W2154078685","https://openalex.org/W2154786353","https://openalex.org/W2167623835","https://openalex.org/W2183420951","https://openalex.org/W2398736067","https://openalex.org/W6602287663","https://openalex.org/W6664917920","https://openalex.org/W6682805176","https://openalex.org/W6686093555"],"related_works":["https://openalex.org/W3105129168","https://openalex.org/W2804920739","https://openalex.org/W4316371992","https://openalex.org/W2186216222","https://openalex.org/W2392765154","https://openalex.org/W2564509292","https://openalex.org/W2008005532","https://openalex.org/W1971603802","https://openalex.org/W1795008753","https://openalex.org/W2131257462"],"abstract_inverted_index":{"Stencil":[0],"based":[1,13],"algorithms":[2],"are":[3,39,82],"used":[4],"intensively":[5],"in":[6],"scientific":[7,49],"computations.":[8,50],"Graphics":[9],"Processing":[10],"Units":[11],"(GPU)":[12],"implementations":[14,55],"of":[15,88,153,170,179,182],"stencil":[16,36],"computations":[17],"speed-up":[18],"the":[19,43,86,93,97,143,151,168,177,180],"execution":[20,171],"significantly":[21],"compared":[22],"to":[23,73,84,142,176],"conventional":[24],"CPU":[25],"only":[26],"systems.":[27],"In":[28],"this":[29],"paper":[30],"we":[31,66,149],"focus":[32],"on":[33],"double":[34],"precision":[35],"computations,":[37],"which":[38,71],"required":[40],"for":[41,48,92,103,127,137,158],"meeting":[42],"high":[44],"accuracy":[45],"requirements,":[46],"inherent":[47],"Starting":[51],"from":[52],"two":[53,57,94],"baseline":[54],"(using":[56],"dimensional":[58,61],"and":[59,79,111,114,161],"three":[60],"thread":[62,108],"block":[63,109],"structures":[64],"respectively),":[65],"employ":[67],"different":[68,89,144],"optimization":[69,90,135],"techniques":[70,91],"lead":[72],"seven":[74],"kernel":[75,105],"versions.":[76],"Both":[77],"Fermi":[78,128],"Kepler":[80,138,154],"GPUs":[81,139],"used,":[83],"evaluate":[85,150],"impact":[87],"architectures.":[95],"Overall,":[96],"GTX680":[98],"GPU":[99,155],"card":[100],"performs":[101],"best":[102],"a":[104,132],"with":[106],"2D":[107],"structure":[110],"optimized":[112],"register":[113],"shared":[115,122],"memory":[116,123],"usage.":[117],"We":[118],"show":[119],"that,":[120],"whereas":[121],"is":[124,131,173],"not":[125],"essential":[126],"GPUs,":[129],"it":[130],"highly":[133],"efficient":[134],"technique":[136],"(mainly":[140],"due":[141],"L1":[145],"cache":[146],"usage).":[147],"Furthermore,":[148],"performance":[152],"cards":[156],"designed":[157],"desktop":[159],"PCs":[160],"notebook":[162],"PCs.":[163],"The":[164],"results":[165],"indicate":[166],"that":[167],"ratio":[169,181],"time":[172],"roughly":[174],"equal":[175],"inverse":[178],"power":[183],"consumption.":[184]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
