{"id":"https://openalex.org/W4392265917","doi":"https://doi.org/10.1109/cgo57630.2024.10444795","title":"Energy-Aware Tile Size Selection for Affine Programs on GPUs","display_name":"Energy-Aware Tile Size Selection for Affine Programs on GPUs","publication_year":2024,"publication_date":"2024-02-28","ids":{"openalex":"https://openalex.org/W4392265917","doi":"https://doi.org/10.1109/cgo57630.2024.10444795"},"language":"en","primary_location":{"id":"doi:10.1109/cgo57630.2024.10444795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo57630.2024.10444795","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","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/A5066866134","display_name":"Malith Jayaweera","orcid":null},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Malith Jayaweera","raw_affiliation_strings":["Northeastern University,Department of Electrical and Computer Engineering,Boston,MA,USA","Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University,Department of Electrical and Computer Engineering,Boston,MA,USA","institution_ids":["https://openalex.org/I12912129"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048530008","display_name":"Martin Kong","orcid":"https://orcid.org/0000-0001-8008-0220"},"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":"Martin Kong","raw_affiliation_strings":["The Ohio State University,Department of Computer Science and Engineering,Columbus,OH,USA","Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA"],"affiliations":[{"raw_affiliation_string":"The Ohio State University,Department of Computer Science and Engineering,Columbus,OH,USA","institution_ids":["https://openalex.org/I52357470"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, The Ohio State University, Columbus, OH, USA","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100651384","display_name":"Yanzhi Wang","orcid":"https://orcid.org/0000-0002-3024-7990"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yanzhi Wang","raw_affiliation_strings":["Northeastern University,Department of Electrical and Computer Engineering,Boston,MA,USA","Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University,Department of Electrical and Computer Engineering,Boston,MA,USA","institution_ids":["https://openalex.org/I12912129"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061128237","display_name":"David Kaeli","orcid":"https://orcid.org/0000-0002-5692-0151"},"institutions":[{"id":"https://openalex.org/I12912129","display_name":"Northeastern University","ror":"https://ror.org/04t5xt781","country_code":"US","type":"education","lineage":["https://openalex.org/I12912129"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"David Kaeli","raw_affiliation_strings":["Northeastern University,Department of Electrical and Computer Engineering,Boston,MA,USA","Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA"],"affiliations":[{"raw_affiliation_string":"Northeastern University,Department of Electrical and Computer Engineering,Boston,MA,USA","institution_ids":["https://openalex.org/I12912129"]},{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Northeastern University, Boston, MA, USA","institution_ids":["https://openalex.org/I12912129"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5066866134"],"corresponding_institution_ids":["https://openalex.org/I12912129"],"apc_list":null,"apc_paid":null,"fwci":2.8789,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.9122261,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"13","last_page":"27"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.998199999332428,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9926999807357788,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.804206371307373},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.7012017965316772},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.5827758312225342},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.533258855342865},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.5155927538871765},{"id":"https://openalex.org/keywords/tile","display_name":"Tile","score":0.5085471868515015},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4964779019355774},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4661822021007538},{"id":"https://openalex.org/keywords/performance-improvement","display_name":"Performance improvement","score":0.4369314908981323},{"id":"https://openalex.org/keywords/solver","display_name":"Solver","score":0.4224418103694916},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12687841057777405}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.804206371307373},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.7012017965316772},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.5827758312225342},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.533258855342865},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.5155927538871765},{"id":"https://openalex.org/C2780728851","wikidata":"https://www.wikidata.org/wiki/Q468402","display_name":"Tile","level":2,"score":0.5085471868515015},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4964779019355774},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4661822021007538},{"id":"https://openalex.org/C2778915421","wikidata":"https://www.wikidata.org/wiki/Q3643177","display_name":"Performance improvement","level":2,"score":0.4369314908981323},{"id":"https://openalex.org/C2778770139","wikidata":"https://www.wikidata.org/wiki/Q1966904","display_name":"Solver","level":2,"score":0.4224418103694916},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12687841057777405},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cgo57630.2024.10444795","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo57630.2024.10444795","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8299999833106995,"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy"}],"awards":[{"id":"https://openalex.org/G2488707916","display_name":null,"funder_award_id":"2234376","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1480909796","https://openalex.org/W1505447236","https://openalex.org/W1964354616","https://openalex.org/W2027806965","https://openalex.org/W2029822446","https://openalex.org/W2064430610","https://openalex.org/W2077143534","https://openalex.org/W2080982747","https://openalex.org/W2084917734","https://openalex.org/W2089913281","https://openalex.org/W2091041639","https://openalex.org/W2096661534","https://openalex.org/W2100218206","https://openalex.org/W2102976251","https://openalex.org/W2108737583","https://openalex.org/W2141280299","https://openalex.org/W2149756939","https://openalex.org/W2154078685","https://openalex.org/W2158158791","https://openalex.org/W2164705472","https://openalex.org/W2170059648","https://openalex.org/W2172073571","https://openalex.org/W2296218291","https://openalex.org/W2318529993","https://openalex.org/W2318697942","https://openalex.org/W2346144740","https://openalex.org/W2429898963","https://openalex.org/W2528110265","https://openalex.org/W2557363651","https://openalex.org/W2567319156","https://openalex.org/W2578611031","https://openalex.org/W2735793669","https://openalex.org/W2767882261","https://openalex.org/W2770722083","https://openalex.org/W2788111881","https://openalex.org/W2794513473","https://openalex.org/W2795915628","https://openalex.org/W2896096668","https://openalex.org/W2963809228","https://openalex.org/W3006451002","https://openalex.org/W3054696703","https://openalex.org/W3098742859","https://openalex.org/W3133572203","https://openalex.org/W3171525923","https://openalex.org/W3206857466","https://openalex.org/W3214154787","https://openalex.org/W4231316372","https://openalex.org/W4233973673","https://openalex.org/W4237024478","https://openalex.org/W4250602606","https://openalex.org/W4250700635","https://openalex.org/W4318328349","https://openalex.org/W4403961418","https://openalex.org/W6644191541","https://openalex.org/W6659068835","https://openalex.org/W6693540781","https://openalex.org/W6751349269","https://openalex.org/W6851122062"],"related_works":["https://openalex.org/W2114959296","https://openalex.org/W38346124","https://openalex.org/W2502442966","https://openalex.org/W2138666621","https://openalex.org/W2383936314","https://openalex.org/W1992771654","https://openalex.org/W2022661278","https://openalex.org/W2777914781","https://openalex.org/W4246369972","https://openalex.org/W4244869112"],"abstract_inverted_index":{"Loop":[0],"tiling":[1],"is":[2],"a":[3],"high-order":[4],"transformation":[5],"used":[6],"to":[7,20,66,104,127,147],"increase":[8],"data":[9],"locality":[10],"and":[11,23,61,79,109,118,121,140,144],"performance.":[12],"While":[13],"previous":[14],"work":[15],"has":[16,31],"considered":[17],"its":[18,25],"application":[19],"several":[21,130],"domains":[22],"architectures,":[24],"potential":[26],"impact":[27],"on":[28,86,115,129,151],"energy":[29,81,110],"efficiency":[30],"been":[32],"largely":[33],"ignored.":[34],"In":[35],"this":[36],"work,":[37],"we":[38,136],"present":[39],"an":[40],"Energy-Aware":[41],"Tile":[42],"Size":[43],"Selection":[44],"Scheme":[45],"(EATSS)":[46],"for":[47,58],"affine":[48,59,131,154],"programs":[49,60],"targeting":[50],"GPUs.":[51],"We":[52,112],"automatically":[53],"derive":[54],"non-linear":[55],"integer":[56],"formulations":[57],"use":[62],"the":[63,87,91],"Z3":[64],"solver":[65],"find":[67],"effective":[68],"tile":[69],"sizes":[70],"that":[71,89],"meet":[72],"architectural":[73],"resource":[74],"constraints,":[75],"while":[76],"maximizing":[77],"performance":[78,108],"minimizing":[80],"consumption.":[82],"Our":[83],"approach":[84],"builds":[85],"insight":[88],"reducing":[90],"liveness":[92],"of":[93],"in-cache":[94],"data,":[95],"together":[96],"with":[97],"exploiting":[98],"automatic":[99],"power":[100],"scaling,":[101],"can":[102],"lead":[103],"substantial":[105],"gains":[106],"in":[107],"efficiency.":[111],"evaluate":[113],"EATSS":[114],"NVIDIA":[116],"Xavier":[117],"GA100":[119],"GPUs,":[120],"report":[122],"median":[123],"performance-per-Watt":[124],"improvement":[125,143,150],"relative":[126],"PPCG":[128],"kernels.":[132,155],"On":[133],"Polybench":[134],"kernels,":[135],"achieve":[137],"1.5":[138],"\u00d7":[139,142,149],"1.2":[141],"obtain":[145],"up":[146],"6.3":[148],"non-Polybench":[152],"high-dimensional":[153]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":4}],"updated_date":"2026-04-14T08:04:32.555800","created_date":"2025-10-10T00:00:00"}