{"id":"https://openalex.org/W2786544209","doi":"https://doi.org/10.1145/3178487.3178500","title":"Register optimizations for stencils on GPUs","display_name":"Register optimizations for stencils on GPUs","publication_year":2018,"publication_date":"2018-02-06","ids":{"openalex":"https://openalex.org/W2786544209","doi":"https://doi.org/10.1145/3178487.3178500","mag":"2786544209"},"language":"en","primary_location":{"id":"doi:10.1145/3178487.3178500","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3178487.3178500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"},"type":"preprint","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/A5101918264","display_name":"Prashant Singh Rawat","orcid":"https://orcid.org/0000-0003-3189-3983"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Prashant Singh Rawat","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5089282120","display_name":"Fabrice Rastello","orcid":"https://orcid.org/0000-0002-6589-9956"},"institutions":[{"id":"https://openalex.org/I1326498283","display_name":"Institut national de recherche en informatique et en automatique","ror":"https://ror.org/02kvxyf05","country_code":"FR","type":"funder","lineage":["https://openalex.org/I1326498283"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Fabrice Rastello","raw_affiliation_strings":["INRIA"],"affiliations":[{"raw_affiliation_string":"INRIA","institution_ids":["https://openalex.org/I1326498283"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015460842","display_name":"Aravind Sukumaran-Rajam","orcid":"https://orcid.org/0000-0002-4062-0293"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aravind Sukumaran-Rajam","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040769038","display_name":"Louis-No\u00ebl Pouchet","orcid":"https://orcid.org/0000-0001-5103-3097"},"institutions":[{"id":"https://openalex.org/I92446798","display_name":"Colorado State University","ror":"https://ror.org/03k1gpj17","country_code":"US","type":"education","lineage":["https://openalex.org/I92446798"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Louis-No\u00ebl Pouchet","raw_affiliation_strings":["Colorado State University"],"affiliations":[{"raw_affiliation_string":"Colorado State University","institution_ids":["https://openalex.org/I92446798"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039624297","display_name":"Atanas Rountev","orcid":"https://orcid.org/0000-0003-4556-4937"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Atanas Rountev","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027517817","display_name":"P. Sadayappan","orcid":"https://orcid.org/0000-0002-4737-2034"},"institutions":[{"id":"https://openalex.org/I52357470","display_name":"The Ohio State University","ror":"https://ror.org/00rs6vg23","country_code":"US","type":"education","lineage":["https://openalex.org/I52357470"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"P. Sadayappan","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5101918264"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":8.63682846,"has_fulltext":false,"cited_by_count":44,"citation_normalized_percentile":{"value":0.97750886,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"168","last_page":"182"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":1.0,"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":1.0,"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":0.9966999888420105,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9959999918937683,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/register-allocation","display_name":"Register allocation","score":0.8839869499206543},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8482042551040649},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7148839235305786},{"id":"https://openalex.org/keywords/loop-unrolling","display_name":"Loop unrolling","score":0.6943099498748779},{"id":"https://openalex.org/keywords/stencil","display_name":"Stencil","score":0.6936979293823242},{"id":"https://openalex.org/keywords/allocator","display_name":"Allocator","score":0.65019291639328},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.5033194422721863},{"id":"https://openalex.org/keywords/register-file","display_name":"Register file","score":0.46080541610717773},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4221065640449524},{"id":"https://openalex.org/keywords/register","display_name":"Register (sociolinguistics)","score":0.4117274880409241},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3300219178199768},{"id":"https://openalex.org/keywords/instruction-set","display_name":"Instruction set","score":0.31951814889907837},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.2575702667236328},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.137793630361557}],"concepts":[{"id":"https://openalex.org/C128916667","wikidata":"https://www.wikidata.org/wiki/Q1343660","display_name":"Register allocation","level":3,"score":0.8839869499206543},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8482042551040649},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7148839235305786},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.6943099498748779},{"id":"https://openalex.org/C76752949","wikidata":"https://www.wikidata.org/wiki/Q7607499","display_name":"Stencil","level":2,"score":0.6936979293823242},{"id":"https://openalex.org/C162262903","wikidata":"https://www.wikidata.org/wiki/Q343527","display_name":"Allocator","level":2,"score":0.65019291639328},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.5033194422721863},{"id":"https://openalex.org/C117280010","wikidata":"https://www.wikidata.org/wiki/Q180944","display_name":"Register file","level":3,"score":0.46080541610717773},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4221065640449524},{"id":"https://openalex.org/C2779235478","wikidata":"https://www.wikidata.org/wiki/Q286576","display_name":"Register (sociolinguistics)","level":2,"score":0.4117274880409241},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3300219178199768},{"id":"https://openalex.org/C202491316","wikidata":"https://www.wikidata.org/wiki/Q272683","display_name":"Instruction set","level":2,"score":0.31951814889907837},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.2575702667236328},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.137793630361557},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3178487.3178500","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3178487.3178500","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23rd ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332359","display_name":"Office of Science","ror":"https://ror.org/00mmn6b08"},{"id":"https://openalex.org/F4320332369","display_name":"National Nuclear Security Administration","ror":"https://ror.org/03sk1we31"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":60,"referenced_works":["https://openalex.org/W14568393","https://openalex.org/W73145541","https://openalex.org/W1491178396","https://openalex.org/W1492882524","https://openalex.org/W1510117796","https://openalex.org/W1514885320","https://openalex.org/W1577524924","https://openalex.org/W1607259217","https://openalex.org/W1779740778","https://openalex.org/W1795008753","https://openalex.org/W1964859463","https://openalex.org/W1972501001","https://openalex.org/W1973532523","https://openalex.org/W1979984064","https://openalex.org/W1997230820","https://openalex.org/W1997375049","https://openalex.org/W2023415862","https://openalex.org/W2024598204","https://openalex.org/W2034761517","https://openalex.org/W2044636417","https://openalex.org/W2045503187","https://openalex.org/W2049510645","https://openalex.org/W2065941861","https://openalex.org/W2070053315","https://openalex.org/W2070961300","https://openalex.org/W2073061372","https://openalex.org/W2075728160","https://openalex.org/W2078504799","https://openalex.org/W2084917734","https://openalex.org/W2101182628","https://openalex.org/W2102182691","https://openalex.org/W2107139334","https://openalex.org/W2107428139","https://openalex.org/W2107725926","https://openalex.org/W2118866757","https://openalex.org/W2129704946","https://openalex.org/W2131570835","https://openalex.org/W2133352531","https://openalex.org/W2139505074","https://openalex.org/W2139827696","https://openalex.org/W2140191557","https://openalex.org/W2140339776","https://openalex.org/W2145456033","https://openalex.org/W2151764765","https://openalex.org/W2153185479","https://openalex.org/W2159959523","https://openalex.org/W2164363152","https://openalex.org/W2212195622","https://openalex.org/W2232645663","https://openalex.org/W2278840053","https://openalex.org/W2292282166","https://openalex.org/W2345717615","https://openalex.org/W2417757850","https://openalex.org/W2512431201","https://openalex.org/W2554796001","https://openalex.org/W3148529197","https://openalex.org/W4234787094","https://openalex.org/W4235662649","https://openalex.org/W4250204977","https://openalex.org/W4320063484"],"related_works":["https://openalex.org/W1529768310","https://openalex.org/W4390073573","https://openalex.org/W2155935413","https://openalex.org/W2078229301","https://openalex.org/W4252189340","https://openalex.org/W2083879870","https://openalex.org/W4243517647","https://openalex.org/W2142891960","https://openalex.org/W4241759337","https://openalex.org/W4214554355"],"abstract_inverted_index":{"The":[0,124],"recent":[1],"advent":[2],"of":[3,42,87,106,126,137],"compute-intensive":[4],"GPU":[5],"architecture":[6],"has":[7],"allowed":[8],"application":[9,141],"developers":[10],"to":[11,28,69],"explore":[12],"high-order":[13,77],"3D":[14],"stencils":[15,26,138],"for":[16,24,63,74,117,121],"better":[17],"computational":[18],"accuracy.":[19],"A":[20],"common":[21],"optimization":[22],"strategy":[23],"such":[25,35,75],"is":[27,49,129],"expose":[29],"sufficient":[30],"data":[31],"reuse":[32],"by":[33,53],"means":[34],"as":[36,103],"loop":[37],"unrolling,":[38],"with":[39,83,108],"the":[40,46,127],"expectation":[41],"register-level":[43],"reuse.":[44],"However,":[45],"resulting":[47,79],"code":[48,82],"often":[50],"highly":[51],"constrained":[52],"register":[54,59,72,88,119],"pressure.":[55],"While":[56],"current":[57],"state-of-the-art":[58],"allocators":[60],"are":[61,67],"satisfactory":[62],"most":[64],"applications,":[65],"they":[66],"unable":[68],"effectively":[70],"manage":[71],"pressure":[73],"complex":[76],"stencils,":[78],"in":[80],"sub-optimal":[81],"a":[84,95,104,135],"large":[85],"number":[86],"spills.":[89],"In":[90],"this":[91],"paper,":[92],"we":[93],"develop":[94],"statement":[96],"reordering":[97],"framework":[98],"that":[99],"models":[100],"stencil":[101],"computations":[102],"DAG":[105],"trees":[107],"shared":[109],"leaves,":[110],"and":[111],"adapts":[112],"an":[113],"optimal":[114],"scheduling":[115],"algorithm":[116],"minimizing":[118],"usage":[120],"expression":[122],"trees.":[123],"effectiveness":[125],"approach":[128],"demonstrated":[130],"through":[131],"experimental":[132],"results":[133],"on":[134],"range":[136],"extracted":[139],"from":[140],"codes.":[142]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":9},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":9},{"year":2018,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
