{"id":"https://openalex.org/W2626935846","doi":"https://doi.org/10.1145/3079856.3080205","title":"Decoupled Affine Computation for SIMT GPUs","display_name":"Decoupled Affine Computation for SIMT GPUs","publication_year":2017,"publication_date":"2017-06-15","ids":{"openalex":"https://openalex.org/W2626935846","doi":"https://doi.org/10.1145/3079856.3080205","mag":"2626935846"},"language":"en","primary_location":{"id":"doi:10.1145/3079856.3080205","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3079856.3080205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th Annual International Symposium on Computer Architecture","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/A5100437082","display_name":"Kai Wang","orcid":"https://orcid.org/0000-0003-0053-3352"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kai Wang","raw_affiliation_strings":["Department of Computer Science, The University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103038181","display_name":"Calvin Lin","orcid":"https://orcid.org/0000-0001-6284-4629"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Calvin Lin","raw_affiliation_strings":["Department of Computer Science, The University of Texas at Austin"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Texas at Austin","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100437082"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":2.4785,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.90641743,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"295","last_page":"306"},"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.9993000030517578,"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":0.9986000061035156,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.8157307505607605},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7895920276641846},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7890506982803345},{"id":"https://openalex.org/keywords/affine-transformation","display_name":"Affine transformation","score":0.7727059125900269},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5558621287345886},{"id":"https://openalex.org/keywords/decoupling","display_name":"Decoupling (probability)","score":0.5061642527580261},{"id":"https://openalex.org/keywords/cas-latency","display_name":"CAS latency","score":0.5019702911376953},{"id":"https://openalex.org/keywords/independence","display_name":"Independence (probability theory)","score":0.45250001549720764},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.35975509881973267},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.340034544467926},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.18315976858139038},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.13222408294677734},{"id":"https://openalex.org/keywords/semiconductor-memory","display_name":"Semiconductor memory","score":0.10215002298355103},{"id":"https://openalex.org/keywords/pure-mathematics","display_name":"Pure mathematics","score":0.06791433691978455}],"concepts":[{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.8157307505607605},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7895920276641846},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7890506982803345},{"id":"https://openalex.org/C92757383","wikidata":"https://www.wikidata.org/wiki/Q382497","display_name":"Affine transformation","level":2,"score":0.7727059125900269},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5558621287345886},{"id":"https://openalex.org/C205606062","wikidata":"https://www.wikidata.org/wiki/Q5249645","display_name":"Decoupling (probability)","level":2,"score":0.5061642527580261},{"id":"https://openalex.org/C189930140","wikidata":"https://www.wikidata.org/wiki/Q1112878","display_name":"CAS latency","level":4,"score":0.5019702911376953},{"id":"https://openalex.org/C35651441","wikidata":"https://www.wikidata.org/wiki/Q625303","display_name":"Independence (probability theory)","level":2,"score":0.45250001549720764},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.35975509881973267},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.340034544467926},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.18315976858139038},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.13222408294677734},{"id":"https://openalex.org/C98986596","wikidata":"https://www.wikidata.org/wiki/Q1143031","display_name":"Semiconductor memory","level":2,"score":0.10215002298355103},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.06791433691978455},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C100800780","wikidata":"https://www.wikidata.org/wiki/Q1175867","display_name":"Memory controller","level":3,"score":0.0},{"id":"https://openalex.org/C133731056","wikidata":"https://www.wikidata.org/wiki/Q4917288","display_name":"Control engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3079856.3080205","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3079856.3080205","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 44th Annual International Symposium on Computer Architecture","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.9200000166893005,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1485193134","https://openalex.org/W1492601037","https://openalex.org/W1555915743","https://openalex.org/W1727627327","https://openalex.org/W1979527452","https://openalex.org/W1983235612","https://openalex.org/W2029076579","https://openalex.org/W2029926205","https://openalex.org/W2042411977","https://openalex.org/W2080592089","https://openalex.org/W2090584832","https://openalex.org/W2093043622","https://openalex.org/W2118826546","https://openalex.org/W2125310891","https://openalex.org/W2138761132","https://openalex.org/W2139427807","https://openalex.org/W2143798346","https://openalex.org/W2154790323","https://openalex.org/W2166918318","https://openalex.org/W2167399819","https://openalex.org/W2273440736","https://openalex.org/W2289175783","https://openalex.org/W2315868086","https://openalex.org/W2316269269","https://openalex.org/W2414217512","https://openalex.org/W3138340923"],"related_works":["https://openalex.org/W2152950565","https://openalex.org/W3103825105","https://openalex.org/W1617565119","https://openalex.org/W160381218","https://openalex.org/W2512958550","https://openalex.org/W2329266651","https://openalex.org/W2004102934","https://openalex.org/W2800626838","https://openalex.org/W4297098431","https://openalex.org/W2437914309"],"abstract_inverted_index":{"This":[0,44],"paper":[1],"introduces":[2],"a":[3,74],"method":[4],"of":[5,10],"decoupling":[6,45],"affine":[7,27,89],"computations---a":[8],"class":[9],"expressions":[11],"that":[12,25,87],"produces":[13],"extremely":[14],"regular":[15],"values":[16],"across":[17],"SIMT":[18],"threads---from":[19],"the":[20,26,40,56,78,82],"main":[21,41],"execution":[22,42],"stream,":[23],"so":[24],"computations":[28],"can":[29],"be":[30],"performed":[31],"with":[32,36],"greater":[33,37],"efficiency":[34],"and":[35],"independence":[38],"from":[39],"stream.":[43],"has":[46],"two":[47],"benefits:":[48],"(1)":[49],"For":[50],"compute-bound":[51],"programs,":[52],"it":[53,65,71],"significantly":[54,66],"reduces":[55,67],"dynamic":[57],"warp":[58],"instruction":[59],"count;":[60],"(2)":[61],"for":[62,77],"memory-bound":[63],"workloads,":[64],"memory":[68,84],"latency,":[69],"since":[70],"acts":[72],"as":[73],"non-speculative":[75],"prefetcher":[76],"data":[79],"specified":[80],"by":[81],"many":[83],"address":[85],"calculations":[86],"are":[88],"computations.":[90]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":4},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":6}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
