{"id":"https://openalex.org/W3085823996","doi":"https://doi.org/10.1109/hpcs48598.2019.9188081","title":"Analysis of a Self-Similar GPU Thread Map for Data-parallel m-Simplex Domains","display_name":"Analysis of a Self-Similar GPU Thread Map for Data-parallel m-Simplex Domains","publication_year":2019,"publication_date":"2019-07-01","ids":{"openalex":"https://openalex.org/W3085823996","doi":"https://doi.org/10.1109/hpcs48598.2019.9188081","mag":"3085823996"},"language":"en","primary_location":{"id":"doi:10.1109/hpcs48598.2019.9188081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcs48598.2019.9188081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on High Performance Computing & Simulation (HPCS)","raw_type":"proceedings-article"},"type":"conference-paper","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, Universidad Austral de Chile, Valdivia, Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Informatics, Universidad Austral de Chile, Valdivia, 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/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":["Department of Computer Science, University of Chile, Santiago, Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Chile, Santiago, Chile","institution_ids":["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":["Department of Computer Science, University of Chile, Santiago, Chile"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Chile, Santiago, Chile","institution_ids":["https://openalex.org/I69737025"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22309845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"abs 1108 5815","issue":null,"first_page":"1002","last_page":"1010"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9987000226974487,"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":0.9987000226974487,"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/T10829","display_name":"Interconnection Networks and Systems","score":0.9955000281333923,"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/T10792","display_name":"Matrix Theory and Algorithms","score":0.9894999861717224,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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/simplex","display_name":"Simplex","score":0.7802753448486328},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.710593581199646},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6635537147521973},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6114263534545898},{"id":"https://openalex.org/keywords/minimum-bounding-box","display_name":"Minimum bounding box","score":0.4822883903980255},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4224911332130432},{"id":"https://openalex.org/keywords/simplex-algorithm","display_name":"Simplex algorithm","score":0.42125070095062256},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.327467679977417},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32224828004837036},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21692541241645813},{"id":"https://openalex.org/keywords/linear-programming","display_name":"Linear programming","score":0.10451918840408325},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.0987505316734314}],"concepts":[{"id":"https://openalex.org/C62438384","wikidata":"https://www.wikidata.org/wiki/Q331350","display_name":"Simplex","level":2,"score":0.7802753448486328},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.710593581199646},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6635537147521973},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6114263534545898},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.4822883903980255},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4224911332130432},{"id":"https://openalex.org/C144521790","wikidata":"https://www.wikidata.org/wiki/Q134164","display_name":"Simplex algorithm","level":3,"score":0.42125070095062256},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.327467679977417},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32224828004837036},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21692541241645813},{"id":"https://openalex.org/C41045048","wikidata":"https://www.wikidata.org/wiki/Q202843","display_name":"Linear programming","level":2,"score":0.10451918840408325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.0987505316734314},{"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpcs48598.2019.9188081","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcs48598.2019.9188081","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on High Performance Computing & Simulation (HPCS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W26556108","https://openalex.org/W1623277219","https://openalex.org/W2000335122","https://openalex.org/W2006543911","https://openalex.org/W2021280432","https://openalex.org/W2027087033","https://openalex.org/W2037813611","https://openalex.org/W2041454931","https://openalex.org/W2050883661","https://openalex.org/W2060104647","https://openalex.org/W2101779504","https://openalex.org/W2116511687","https://openalex.org/W2182846020","https://openalex.org/W2219568914","https://openalex.org/W2243938989","https://openalex.org/W2536676298","https://openalex.org/W2542099479","https://openalex.org/W2809452033","https://openalex.org/W2962835744","https://openalex.org/W4243099941","https://openalex.org/W4250981202","https://openalex.org/W6636576719","https://openalex.org/W6688738241","https://openalex.org/W6690753023","https://openalex.org/W6719622332"],"related_works":["https://openalex.org/W2185826091","https://openalex.org/W2048470382","https://openalex.org/W2477407501","https://openalex.org/W2384679317","https://openalex.org/W2911215968","https://openalex.org/W1570109187","https://openalex.org/W1583787753","https://openalex.org/W2491692165","https://openalex.org/W2366013513","https://openalex.org/W2020093019"],"abstract_inverted_index":{"This":[0],"work":[1,37],"analyzes":[2],"the":[3,25,40,88,105,115,122,141,154],"possible":[4],"performance":[5,64],"benefits":[6],"one":[7],"could":[8],"obtain":[9,71,170],"by":[10],"employing":[11],"a":[12,43,52,101,147,171,183],"Self-Similar":[13],"type":[14],"of":[15,28,35,42,55,63,112,153,156],"GPU":[16,126],"thread":[17,66],"map":[18,46,123,142,173],"on":[19,51,100],"data-parallel":[20],"m-simplex":[21],"domains,":[22],"which":[23,69,162],"is":[24,74,91,146],"geometrical":[26],"representation":[27],"several":[29],"interaction":[30],"problems.":[31],"The":[32],"main":[33],"contributions":[34],"this":[36],"are":[38],"(1)":[39],"proposal":[41],"new":[44],"block-space":[45],"H":[47],":":[48],"Zm\u2192":[49],"Zmbased":[50],"self-similar":[53],"set":[54],"sub-orthotopes,":[56],"and":[57,65,76,81,129,151],"(2)":[58],"its":[59],"analysis":[60],"in":[61,167],"terms":[62],"space,":[67],"from":[68],"we":[70,137,163],"that":[72,139,174],"H(\u03c9)":[73,172],"time":[75,83],"space":[77,180],"efficient":[78,84,181],"for":[79,85,161],"2-simplices":[80],"only":[82],"3-simplices":[86],"unless":[87],"theoretical":[89,106],"model":[90],"relaxed":[92],"to":[93,110,143,169],"allow":[94],"concurrent":[95],"parallel":[96],"spaces.":[97],"Experimental":[98],"tests":[99],"2-simplex":[102],"domain":[103],"support":[104],"results,":[107],"giving":[108],"up":[109],"30%":[111],"speedup":[113],"over":[114],"standard":[116],"approach.":[117,185],"We":[118],"also":[119],"show":[120,138],"how":[121],"can":[124,175],"utilize":[125],"tensor":[127],"cores":[128],"further":[130],"accelerate":[131],"through":[132],"fast":[133],"matrix-multiply-accumulate":[134],"operations.":[135],"Finally,":[136],"extending":[140],"general":[144],"m-simplices":[145],"non-trivial":[148],"optimization":[149],"problem":[150],"depends":[152],"choice":[155],"two":[157],"parameters":[158],"r,":[159],"\u03b2,":[160],"provide":[164],"some":[165],"insights":[166],"order":[168],"be":[176],"m!":[177],"times":[178],"more":[179],"than":[182],"bounding-box":[184]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}