{"id":"https://openalex.org/W2588449239","doi":"https://doi.org/10.1145/3038228.3038236","title":"Launch-Time Optimization of OpenCL GPU Kernels","display_name":"Launch-Time Optimization of OpenCL GPU Kernels","publication_year":2017,"publication_date":"2017-02-04","ids":{"openalex":"https://openalex.org/W2588449239","doi":"https://doi.org/10.1145/3038228.3038236","mag":"2588449239"},"language":"en","primary_location":{"id":"doi:10.1145/3038228.3038236","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3038228.3038236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the General Purpose GPUs","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/A5055962173","display_name":"Andrew S. D. Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Andrew S. D. Lee","raw_affiliation_strings":["University of Toronto, The Edward S. Rogers Sr. Department of Electrical and Computer Engineering, Toronto, Ontario, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, The Edward S. Rogers Sr. Department of Electrical and Computer Engineering, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080157948","display_name":"Tarek S. Abdelrahman","orcid":"https://orcid.org/0000-0002-2985-4873"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Tarek S. Abdelrahman","raw_affiliation_strings":["University of Toronto, The Edward S. Rogers Sr. Department of Electrical and Computer Engineering, Toronto, Ontario, Canada"],"affiliations":[{"raw_affiliation_string":"University of Toronto, The Edward S. Rogers Sr. Department of Electrical and Computer Engineering, Toronto, Ontario, Canada","institution_ids":["https://openalex.org/I185261750"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5055962173"],"corresponding_institution_ids":["https://openalex.org/I185261750"],"apc_list":null,"apc_paid":null,"fwci":0.9013,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.72544351,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"32","last_page":"41"},"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9955999851226807,"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":0.9919000267982483,"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/kernel","display_name":"Kernel (algebra)","score":0.8391307592391968},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7978201508522034},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7785754799842834},{"id":"https://openalex.org/keywords/constant","display_name":"Constant (computer programming)","score":0.7176022529602051},{"id":"https://openalex.org/keywords/loop-unrolling","display_name":"Loop unrolling","score":0.6514228582382202},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6242534518241882},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.47520408034324646},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.47470369935035706},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.46472981572151184},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.41036438941955566},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.2786977291107178},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.16796544194221497},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.15666037797927856},{"id":"https://openalex.org/keywords/geometry","display_name":"Geometry","score":0.12325310707092285},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.07812950015068054},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.059226810932159424}],"concepts":[{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.8391307592391968},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7978201508522034},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7785754799842834},{"id":"https://openalex.org/C2777027219","wikidata":"https://www.wikidata.org/wiki/Q1284190","display_name":"Constant (computer programming)","level":2,"score":0.7176022529602051},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.6514228582382202},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6242534518241882},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.47520408034324646},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.47470369935035706},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.46472981572151184},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.41036438941955566},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.2786977291107178},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.16796544194221497},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.15666037797927856},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.12325310707092285},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.07812950015068054},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.059226810932159424},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3038228.3038236","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3038228.3038236","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the General Purpose GPUs","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320308258","display_name":"Qualcomm","ror":"https://ror.org/002zrf773"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W1717365219","https://openalex.org/W1782174992","https://openalex.org/W1808614931","https://openalex.org/W1984222112","https://openalex.org/W1985074935","https://openalex.org/W2012630996","https://openalex.org/W2080592089","https://openalex.org/W2108315152","https://openalex.org/W2112185810","https://openalex.org/W2114067856","https://openalex.org/W2115824361","https://openalex.org/W2128046183","https://openalex.org/W2136944230","https://openalex.org/W2143659699","https://openalex.org/W2153185479","https://openalex.org/W2160875256","https://openalex.org/W2165296157","https://openalex.org/W2167675119","https://openalex.org/W2255673220","https://openalex.org/W2292282166","https://openalex.org/W2293015622","https://openalex.org/W3138798301","https://openalex.org/W4242680074"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"OpenCL":[0],"compiles":[1],"a":[2],"GPU":[3],"kernel":[4,14,29],"first":[5],"and":[6,21,31,66],"then":[7],"launches":[8],"it":[9],"for":[10],"execution,":[11,41],"providing":[12],"the":[13,28,32,42],"at":[15],"this":[16],"launch":[17,23,33],"with":[18],"its":[19,22,53],"arguments":[20],"geometry.":[24],"Although":[25],"some":[26],"of":[27],"inputs":[30],"geometry":[34],"remain":[35],"constant":[36,60,62],"across":[37],"all":[38],"threads":[39],"during":[40],"compiler":[43],"is":[44],"unable":[45],"to":[46,55],"treat":[47],"them":[48],"as":[49],"such,":[50],"which":[51],"limits":[52],"ability":[54],"apply":[56],"several":[57],"optimizations,":[58],"including":[59],"propagation,":[61],"folding,":[63],"strength":[64],"reduction":[65],"loop":[67],"unrolling.":[68]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
