{"id":"https://openalex.org/W2089482246","doi":"https://doi.org/10.1145/1531743.1531766","title":"A control-structure splitting optimization for GPGPU","display_name":"A control-structure splitting optimization for GPGPU","publication_year":2009,"publication_date":"2009-05-18","ids":{"openalex":"https://openalex.org/W2089482246","doi":"https://doi.org/10.1145/1531743.1531766","mag":"2089482246"},"language":"en","primary_location":{"id":"doi:10.1145/1531743.1531766","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1531743.1531766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM conference on Computing frontiers","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/A5025888312","display_name":"Snaider Carrillo","orcid":"https://orcid.org/0000-0003-0804-3382"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Snaider Carrillo","raw_affiliation_strings":["University of Delaware, Newark, USA","University of delaware, Newark, USA"],"affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, USA","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"University of delaware, Newark, USA","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027240262","display_name":"Jakob Siegel","orcid":null},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jakob Siegel","raw_affiliation_strings":["University of Delaware, Newark, USA","University of delaware, Newark, USA"],"affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, USA","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"University of delaware, Newark, USA","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100452133","display_name":"Xiaoming Li","orcid":"https://orcid.org/0000-0002-7397-723X"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoming Li","raw_affiliation_strings":["University of Delaware, Newark, USA","University of delaware, Newark, USA"],"affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, USA","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"University of delaware, Newark, USA","institution_ids":["https://openalex.org/I86501945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5025888312"],"corresponding_institution_ids":["https://openalex.org/I86501945"],"apc_list":null,"apc_paid":null,"fwci":5.0126,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.95668476,"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":"147","last_page":"150"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9908999800682068,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9883999824523926,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8200505971908569},{"id":"https://openalex.org/keywords/serialization","display_name":"Serialization","score":0.8098423480987549},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.7599498629570007},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6461541056632996},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5479552149772644},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.5386236906051636},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.48774510622024536},{"id":"https://openalex.org/keywords/central-processing-unit","display_name":"Central processing unit","score":0.484497994184494},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.4527837932109833},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2599436044692993},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.20691627264022827}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8200505971908569},{"id":"https://openalex.org/C52723943","wikidata":"https://www.wikidata.org/wiki/Q1127410","display_name":"Serialization","level":2,"score":0.8098423480987549},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.7599498629570007},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6461541056632996},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5479552149772644},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.5386236906051636},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.48774510622024536},{"id":"https://openalex.org/C49154492","wikidata":"https://www.wikidata.org/wiki/Q5300","display_name":"Central processing unit","level":2,"score":0.484497994184494},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.4527837932109833},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2599436044692993},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.20691627264022827},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1531743.1531766","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1531743.1531766","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM conference on Computing frontiers","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":4,"referenced_works":["https://openalex.org/W1664235680","https://openalex.org/W1992851788","https://openalex.org/W2164417656","https://openalex.org/W4388316717"],"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":{"Control":[0],"statements":[1,24,65,88],"in":[2,90],"a":[3,55],"GPU":[4,19,60,74],"program":[5],"such":[6],"as":[7],"loops":[8],"and":[9,32,75],"branches":[10],"pose":[11],"serious":[12],"challenges":[13],"for":[14],"the":[15,28,35,41,59,63,67,86,93],"efficient":[16],"usage":[17],"of":[18,30,37,43],"resources":[20],"because":[21,69],"those":[22],"control":[23,64,87],"will":[25],"lead":[26],"to":[27,66,84],"serialization":[29],"threads":[31,44],"consequently":[33],"ruin":[34],"occupancy":[36],"GPU,":[38],"that":[39,52],"is,":[40],"number":[42],"running":[45],"concurrently.":[46],"Unlike":[47],"traditional":[48],"vector":[49],"processing":[50],"units":[51],"are":[53],"inside":[54],"general":[56],"purpose":[57],"processor,":[58],"cannot":[61],"leave":[62],"CPU":[68,76],"fine-grain":[70],"statement":[71],"scheduling":[72],"between":[73],"is":[77],"impossible.":[78],"We":[79],"need":[80],"an":[81],"effective":[82],"method":[83],"handle":[85],"\"just":[89],"place\"":[91],"on":[92],"GPUs.":[94]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":4},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":7}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}