{"id":"https://openalex.org/W4405632002","doi":"https://doi.org/10.1109/tpds.2024.3520395","title":"CAT: Cellular Automata on Tensor Cores","display_name":"CAT: Cellular Automata on Tensor Cores","publication_year":2024,"publication_date":"2024-12-20","ids":{"openalex":"https://openalex.org/W4405632002","doi":"https://doi.org/10.1109/tpds.2024.3520395"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2024.3520395","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2024.3520395","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":true,"raw_author_name":"Crist\u00f3bal A. Navarro","raw_affiliation_strings":["Institute of Informatics, Austral University of Chile, Valdivia, Chile","Department of Informatics of Austral University of Chile, Chile"],"affiliations":[{"raw_affiliation_string":"Institute of Informatics, Austral University of Chile, Valdivia, Chile","institution_ids":["https://openalex.org/I16465266"]},{"raw_affiliation_string":"Department of Informatics of Austral University of Chile, Chile","institution_ids":["https://openalex.org/I16465266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067650702","display_name":"Felipe A. Quezada","orcid":"https://orcid.org/0000-0002-3384-2840"},"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":"Felipe A. Quezada","raw_affiliation_strings":["Institute of Informatics, Austral University of Chile, Valdivia, Chile","Department of Informatics of Austral University of Chile, Chile"],"affiliations":[{"raw_affiliation_string":"Institute of Informatics, Austral University of Chile, Valdivia, Chile","institution_ids":["https://openalex.org/I16465266"]},{"raw_affiliation_string":"Department of Informatics of Austral University of Chile, Chile","institution_ids":["https://openalex.org/I16465266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031739604","display_name":"Enzo Meneses","orcid":"https://orcid.org/0000-0002-8405-9151"},"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":"Enzo Meneses","raw_affiliation_strings":["Institute of Informatics, Austral University of Chile, Valdivia, Chile","Department of Informatics of Austral University of Chile, Chile"],"affiliations":[{"raw_affiliation_string":"Institute of Informatics, Austral University of Chile, Valdivia, Chile","institution_ids":["https://openalex.org/I16465266"]},{"raw_affiliation_string":"Department of Informatics of Austral University of Chile, Chile","institution_ids":["https://openalex.org/I16465266"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085478645","display_name":"H\u00e9ctor Ferrada","orcid":"https://orcid.org/0000-0002-8334-4540"},"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":"H\u00e9ctor Ferrada","raw_affiliation_strings":["Institute of Informatics, Austral University of Chile, Valdivia, Chile","Department of Informatics of Austral University of Chile, Chile"],"affiliations":[{"raw_affiliation_string":"Institute of Informatics, Austral University of Chile, Valdivia, Chile","institution_ids":["https://openalex.org/I16465266"]},{"raw_affiliation_string":"Department of Informatics of Austral University of Chile, Chile","institution_ids":["https://openalex.org/I16465266"]}]},{"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 Department, University of Chile, Chile"],"affiliations":[{"raw_affiliation_string":"Computer Science Department, University of Chile, Santiago, Chile","institution_ids":["https://openalex.org/I69737025"]},{"raw_affiliation_string":"Computer Science Department, University of Chile, Chile","institution_ids":["https://openalex.org/I69737025"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5088815725"],"corresponding_institution_ids":["https://openalex.org/I16465266"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.27307796,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"2","first_page":"341","last_page":"355"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12162","display_name":"Cellular Automata and Applications","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T12162","display_name":"Cellular Automata and Applications","score":0.9998999834060669,"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/computer-science","display_name":"Computer science","score":0.7572853565216064},{"id":"https://openalex.org/keywords/cellular-automaton","display_name":"Cellular automaton","score":0.6406092643737793},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.4757123589515686},{"id":"https://openalex.org/keywords/tensor","display_name":"Tensor (intrinsic definition)","score":0.45869913697242737},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3431078791618347},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.34082943201065063},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.207990825176239},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09560075402259827}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7572853565216064},{"id":"https://openalex.org/C35527583","wikidata":"https://www.wikidata.org/wiki/Q189156","display_name":"Cellular automaton","level":2,"score":0.6406092643737793},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.4757123589515686},{"id":"https://openalex.org/C155281189","wikidata":"https://www.wikidata.org/wiki/Q3518150","display_name":"Tensor (intrinsic definition)","level":2,"score":0.45869913697242737},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3431078791618347},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.34082943201065063},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.207990825176239},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09560075402259827},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tpds.2024.3520395","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2024.3520395","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":[{"score":0.7599999904632568,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W59319272","https://openalex.org/W960482492","https://openalex.org/W1492951184","https://openalex.org/W1525868962","https://openalex.org/W1584086289","https://openalex.org/W1675665627","https://openalex.org/W1985494198","https://openalex.org/W2001024377","https://openalex.org/W2005082970","https://openalex.org/W2006682606","https://openalex.org/W2008803423","https://openalex.org/W2028873795","https://openalex.org/W2056141163","https://openalex.org/W2067479799","https://openalex.org/W2078291859","https://openalex.org/W2118036437","https://openalex.org/W2154078685","https://openalex.org/W2295359065","https://openalex.org/W2479544240","https://openalex.org/W2605251831","https://openalex.org/W2791673912","https://openalex.org/W2996929894","https://openalex.org/W3044913359","https://openalex.org/W3183654450","https://openalex.org/W4200117381","https://openalex.org/W4206206987","https://openalex.org/W4220830352","https://openalex.org/W4283029140","https://openalex.org/W4321636820","https://openalex.org/W4376632753","https://openalex.org/W4391987273","https://openalex.org/W4398774961","https://openalex.org/W6799372109","https://openalex.org/W6804637634","https://openalex.org/W6809451142"],"related_works":["https://openalex.org/W2164619678","https://openalex.org/W2113544496","https://openalex.org/W2360313292","https://openalex.org/W2067777412","https://openalex.org/W1669105318","https://openalex.org/W2359527201","https://openalex.org/W2353714615","https://openalex.org/W2141069492","https://openalex.org/W1986870597","https://openalex.org/W2124122503"],"abstract_inverted_index":{"Cellular":[0],"automata":[1],"(CA)":[2],"are":[3,20],"simulation":[4],"models":[5],"that":[6,84,131,138],"can":[7,30,85,305],"produce":[8],"complex":[9],"emergent":[10],"behaviors":[11],"from":[12,182,232],"simple":[13],"local":[14],"rules.":[15],"Although":[16,289],"state-of-the-art":[17,178,211],"GPU":[18,49,80,179,200,212,249,273,295,309,346],"solutions":[19],"already":[21],"fast":[22,60],"due":[23],"to":[24,57,195,204,332],"their":[25,28,70],"data-parallel":[26],"nature,":[27],"performance":[29,246,266,291],"rapidly":[31],"degrade":[32],"in":[33,54,88,222,317,336,344,348],"CA":[34,87,124,337],"with":[35,159,325,338],"a":[36,79,96,199,253,268,300,339],"large":[37,312,340],"neighborhood":[38,341],"radius.":[39,313],"With":[40],"the":[41,47,63,90,117,132,144,160,176,209,223,239,284,345,349],"inclusion":[42],"of":[43,65,99,123,193,216,278],"tensor":[44,81,296],"cores":[45],"across":[46,248],"entire":[48,145],"ecosystem,":[50],"interest":[51],"has":[52],"grown":[53],"finding":[55],"ways":[56],"leverage":[58],"these":[59],"units":[61],"outside":[62],"field":[64],"artificial":[66],"intelligence,":[67],"which":[68,89],"was":[69,280],"original":[71],"purpose.":[72],"In":[73,214],"this":[74,318],"work,":[75],"we":[76],"present":[77],"CAT,":[78],"core":[82],"approach":[83,302,324],"accelerate":[86],"cell":[91],"transition":[92],"function":[93],"acts":[94],"on":[95],"weighted":[97],"summation":[98],"its":[100,155,265,290],"neighborhood.":[101],"CAT":[102,139,168,185,219,251,279,321],"is":[103,135,169,172,220,238,292,299],"evaluated":[104],"theoretically,":[105],"using":[106,116,283],"an":[107,323],"extended":[108],"PRAM":[109],"cost":[110,133],"model,":[111],"as":[112,114,125,303,322],"well":[113],"empirically":[115],"Larger":[118],"Than":[119],"Life":[120],"(LTL)":[121],"family":[122],"case":[126],"studies.":[127],"The":[128,314],"results":[129,315],"confirm":[130],"model":[134],"accurate,":[136],"showing":[137],"exhibits":[140],"constant":[141],"time":[142],"throughout":[143],"radius":[146,165],"range":[147,224],"<inline-formula><tex-math":[148,166,183,196,205,225,233],"notation=\"LaTeX\">$1":[149,226],"\\leq":[150,152,227,229],"r":[151,228],"16$</tex-math></inline-formula>,":[153],"and":[154,171,202,231,347],"theoretical":[156],"speedups":[157,192],"agree":[158],"empirical":[161],"results.":[162],"At":[163],"low":[164],"notation=\"LaTeX\">$r=1,2$</tex-math></inline-formula>,":[167],"competitive":[170,221],"only":[173],"surpassed":[174],"by":[175],"fastest":[177,210],"solution.":[180],"Starting":[181],"notation=\"LaTeX\">$r=3$</tex-math></inline-formula>,":[184],"progressively":[186],"outperforms":[187],"all":[188],"other":[189],"approaches,":[190],"reaching":[191],"up":[194,203],"notation=\"LaTeX\">$101\\times$</tex-math></inline-formula>":[197],"over":[198,208],"baseline":[201],"notation=\"LaTeX\">$\\sim":[206],"\\!14\\times$</tex-math></inline-formula>":[207],"approach.":[213,243],"terms":[215],"energy":[217,241],"efficiency,":[218],"4$</tex-math></inline-formula>":[230],"notation=\"LaTeX\">$r":[234],"\\geq":[235],"5$</tex-math></inline-formula>":[236],"it":[237,262,298,304],"most":[240],"efficient":[242],"As":[244],"for":[245,259,328],"scaling":[247],"architectures,":[250],"shows":[252],"promising":[254,301],"trend":[255],"that,":[256],"if":[257],"continues":[258],"future":[260],"generations,":[261],"would":[263],"increase":[264],"at":[267,311],"higher":[269],"rate":[270],"than":[271],"classical":[272],"solutions.":[274],"A":[275],"CPU":[276],"version":[277],"also":[281],"explored,":[282],"recently":[285],"introduced":[286],"AMX":[287],"instructions.":[288],"still":[293,306],"below":[294],"cores,":[297],"outperform":[307],"some":[308],"approaches":[310],"obtained":[316],"work":[319],"put":[320],"great":[326],"potential":[327],"scientists":[329],"who":[330],"need":[331],"study":[333],"emerging":[334],"phenomena":[335],"radius,":[342],"both":[343],"CPU.":[350]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}