{"id":"https://openalex.org/W2809452033","doi":"https://doi.org/10.1109/tpds.2018.2849705","title":"Competitiveness of a Non-Linear Block-Space GPU Thread Map for Simplex Domains","display_name":"Competitiveness of a Non-Linear Block-Space GPU Thread Map for Simplex Domains","publication_year":2018,"publication_date":"2018-06-22","ids":{"openalex":"https://openalex.org/W2809452033","doi":"https://doi.org/10.1109/tpds.2018.2849705","mag":"2809452033"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2018.2849705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2849705","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-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/A5088815725","display_name":"Crist\u00f3bal A. Navarro","orcid":"https://orcid.org/0000-0001-7090-9904"},"institutions":[{"id":"https://openalex.org/I16465266","display_name":"Austral University of Chile","ror":"https://ror.org/029ycp228","country_code":"CL","type":"education","lineage":["https://openalex.org/I16465266"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Cristobal A. Navarro","raw_affiliation_strings":["Institute of Informatics, Austral University of Chile, Valdivia, Regi\u00f3n de los R\u00edos, Chile"],"raw_orcid":"https://orcid.org/0000-0001-7090-9904","affiliations":[{"raw_affiliation_string":"Institute of Informatics, Austral University of Chile, Valdivia, Regi\u00f3n de los R\u00edos, Chile","institution_ids":["https://openalex.org/I16465266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060319632","display_name":"Matthieu Vernier","orcid":"https://orcid.org/0000-0002-3265-4709"},"institutions":[{"id":"https://openalex.org/I16465266","display_name":"Austral University of Chile","ror":"https://ror.org/029ycp228","country_code":"CL","type":"education","lineage":["https://openalex.org/I16465266"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Matthieu Vernier","raw_affiliation_strings":["Institute of Informatics, Austral University of Chile, Valdivia, Regi\u00f3n de los R\u00edos, Chile"],"raw_orcid":"https://orcid.org/0000-0002-3265-4709","affiliations":[{"raw_affiliation_string":"Institute of Informatics, Austral University of Chile, Valdivia, Regi\u00f3n de los R\u00edos, Chile","institution_ids":["https://openalex.org/I16465266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009309241","display_name":"Benjam\u00edn Bustos","orcid":"https://orcid.org/0000-0002-3955-361X"},"institutions":[{"id":"https://openalex.org/I4210167034","display_name":"Millennium Institute for Integrative Biology","ror":"https://ror.org/05xcmte05","country_code":"CL","type":"other","lineage":["https://openalex.org/I4210167034"]},{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Benjamin Bustos","raw_affiliation_strings":["Millenium Institute for Foundational Research on Data, University of Chile, Santiago, Chile","[Department of Computer Science, Millenium Institute for Foundational Research on Data, University of Chile, Santiago, Chile]"],"raw_orcid":"https://orcid.org/0000-0002-3955-361X","affiliations":[{"raw_affiliation_string":"Millenium Institute for Foundational Research on Data, University of Chile, Santiago, Chile","institution_ids":["https://openalex.org/I4210167034"]},{"raw_affiliation_string":"[Department of Computer Science, Millenium Institute for Foundational Research on Data, University of Chile, Santiago, Chile]","institution_ids":["https://openalex.org/I4210167034","https://openalex.org/I69737025"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085139932","display_name":"Nancy Hitschfeld","orcid":"https://orcid.org/0000-0003-4923-4679"},"institutions":[{"id":"https://openalex.org/I69737025","display_name":"University of Chile","ror":"https://ror.org/047gc3g35","country_code":"CL","type":"education","lineage":["https://openalex.org/I69737025"]}],"countries":["CL"],"is_corresponding":false,"raw_author_name":"Nancy Hitschfeld","raw_affiliation_strings":["Computer Science Department, University of Chile, Santiago, Chile","Computer Science Dept., University of Chile, Santiago, Chile#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Chile, Santiago, Chile","institution_ids":["https://openalex.org/I69737025"]},{"raw_affiliation_string":"Computer Science Dept., University of Chile, Santiago, Chile#TAB#","institution_ids":["https://openalex.org/I69737025"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.848,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.7887334,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"29","issue":"12","first_page":"2728","last_page":"2741"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12292","display_name":"Graph Theory and Algorithms","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9970999956130981,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9894000291824341,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/computer-science","display_name":"Computer science","score":0.7876588702201843},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7189394235610962},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6617171168327332},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5236475467681885},{"id":"https://openalex.org/keywords/simplex","display_name":"Simplex","score":0.4893888831138611},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.44742706418037415},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.44130122661590576},{"id":"https://openalex.org/keywords/linear-programming","display_name":"Linear programming","score":0.41769498586654663},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.39421531558036804},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.2960781455039978},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.2839151620864868},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2605670988559723},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18691298365592957},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10997751355171204},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.09519034624099731}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7876588702201843},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7189394235610962},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6617171168327332},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5236475467681885},{"id":"https://openalex.org/C62438384","wikidata":"https://www.wikidata.org/wiki/Q331350","display_name":"Simplex","level":2,"score":0.4893888831138611},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.44742706418037415},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.44130122661590576},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.41769498586654663},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.39421531558036804},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2960781455039978},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.2839151620864868},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2605670988559723},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18691298365592957},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10997751355171204},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.09519034624099731}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2018.2849705","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2849705","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5094858153","display_name":null,"funder_award_id":"1181506","funder_id":"https://openalex.org/F4320338073","funder_display_name":"Fondo Nacional de Desarrollo Cient\u00edfico y Tecnol\u00f3gico"},{"id":"https://openalex.org/G6300189063","display_name":null,"funder_award_id":"3160182","funder_id":"https://openalex.org/F4320338073","funder_display_name":"Fondo Nacional de Desarrollo Cient\u00edfico y Tecnol\u00f3gico"}],"funders":[{"id":"https://openalex.org/F4320338073","display_name":"Fondo Nacional de Desarrollo Cient\u00edfico y Tecnol\u00f3gico","ror":"https://ror.org/02ap3w078"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W26556108","https://openalex.org/W73744677","https://openalex.org/W1623277219","https://openalex.org/W1675130169","https://openalex.org/W1762731526","https://openalex.org/W1847196819","https://openalex.org/W1922994609","https://openalex.org/W1975879668","https://openalex.org/W1984222112","https://openalex.org/W2000335122","https://openalex.org/W2005657120","https://openalex.org/W2006543911","https://openalex.org/W2011777324","https://openalex.org/W2028499920","https://openalex.org/W2040583861","https://openalex.org/W2041454931","https://openalex.org/W2050883661","https://openalex.org/W2060104647","https://openalex.org/W2065208324","https://openalex.org/W2070443692","https://openalex.org/W2095921114","https://openalex.org/W2101779504","https://openalex.org/W2116511687","https://openalex.org/W2118036437","https://openalex.org/W2148869717","https://openalex.org/W2182846020","https://openalex.org/W2243938989","https://openalex.org/W2295862081","https://openalex.org/W2536676298","https://openalex.org/W2542099479","https://openalex.org/W2736299064","https://openalex.org/W2962835744","https://openalex.org/W4243099941","https://openalex.org/W4250981202","https://openalex.org/W6603045754","https://openalex.org/W6636576719","https://openalex.org/W6686100961","https://openalex.org/W6690753023"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"This":[0],"work":[1],"presents":[2],"and":[3,42,48,68,110],"studies":[4],"the":[5,31,55,70,81],"efficiency":[6],"problem":[7],"of":[8,33,38,91,105],"mapping":[9],"GPU":[10,77,127],"threads":[11],"onto":[12],"simplex":[13],"domains.":[14],"A":[15],"non-linear":[16],"map":[17,72],"<inline-formula><tex-math":[18,40,62,89,103,113,122],"notation=\"LaTeX\">$\\lambda":[19,63,123],"(\\omega)$</tex-math></inline-formula>":[20,124],"is":[21,66],"formulated":[22],"based":[23],"on":[24,132],"a":[25,36,125,144],"block-space":[26],"enumeration":[27],"principle":[28],"that":[29,61,135],"reduces":[30],"number":[32],"thread-blocks":[34],"by":[35],"factor":[37],"approximately":[39],"notation=\"LaTeX\">$2\\times$</tex-math></inline-formula>":[41],"<inline-formula>":[43],"<tex-math":[44],"notation=\"LaTeX\">$6\\times$</tex-math></inline-formula>":[45],"for":[46,107,115],"2-simplex":[47,94,145],"3-simplex":[49,97,147],"domains,":[50],"respectively,":[51],"when":[52,73],"compared":[53],"to":[54,88,102,112],"standard":[56],"approach.":[57],"Performance":[58],"results":[59,119],"show":[60],"(\\omega)$</tex-math>":[64],"</inline-formula>":[65],"competitive":[67],"even":[69],"fastest":[71],"ran":[74],"in":[75,93,143],"recent":[76],"architectures":[78],"such":[79],"as":[80],"Tesla":[82],"V100,":[83],"where":[84],"it":[85,99],"reaches":[86,100],"up":[87,101,111],"notation=\"LaTeX\">$1.5\\times$</tex-math></inline-formula>":[90],"speedup":[92,106],"tests.":[95],"In":[96],"tests,":[98],"notation=\"LaTeX\">$2.3\\times$</tex-math></inline-formula>":[104],"small":[108],"workloads":[109],"notation=\"LaTeX\">$1.25\\times$</tex-math></inline-formula>":[114],"larger":[116],"ones.":[117],"The":[118],"obtained":[120],"make":[121],"useful":[126],"optimization":[128],"technique":[129],"with":[130],"applications":[131],"parallel":[133],"problems":[134],"define":[136],"all-pairs,":[137],"all-triplets":[138],"or":[139,146],"nearest":[140],"neighbors":[141],"interactions":[142],"domain.":[148]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}