{"id":"https://openalex.org/W2896831700","doi":"https://doi.org/10.1145/3243176.3243196","title":"Cost-driven thread coarsening for GPU kernels","display_name":"Cost-driven thread coarsening for GPU kernels","publication_year":2018,"publication_date":"2018-10-10","ids":{"openalex":"https://openalex.org/W2896831700","doi":"https://doi.org/10.1145/3243176.3243196","mag":"2896831700"},"language":"en","primary_location":{"id":"doi:10.1145/3243176.3243196","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3243176.3243196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th International Conference on Parallel Architectures and Compilation Techniques","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/A5006793409","display_name":"Prithayan Barua","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Prithayan Barua","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067511475","display_name":"Jun Shirako","orcid":"https://orcid.org/0000-0002-7900-7680"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Shirako","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043513001","display_name":"Vivek Sarkar","orcid":"https://orcid.org/0000-0002-3433-8830"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Vivek Sarkar","raw_affiliation_strings":["Georgia Institute of Technology"],"affiliations":[{"raw_affiliation_string":"Georgia Institute of Technology","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5006793409"],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":0.7574,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.7023955,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"14"},"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":0.9983000159263611,"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/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"}}],"keywords":[{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.709467351436615},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.688555121421814},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6294679045677185},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.5746316313743591},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.48402804136276245},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.36415112018585205},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.2275429368019104},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14383673667907715}],"concepts":[{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.709467351436615},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.688555121421814},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6294679045677185},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.5746316313743591},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.48402804136276245},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.36415112018585205},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.2275429368019104},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14383673667907715}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3243176.3243196","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3243176.3243196","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 27th International Conference on Parallel Architectures and Compilation Techniques","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W73145541","https://openalex.org/W1983545421","https://openalex.org/W1984222112","https://openalex.org/W1985074935","https://openalex.org/W1989562524","https://openalex.org/W2017113046","https://openalex.org/W2063186542","https://openalex.org/W2063397164","https://openalex.org/W2067479799","https://openalex.org/W2080592089","https://openalex.org/W2093726305","https://openalex.org/W2098118692","https://openalex.org/W2130597822","https://openalex.org/W2142769604","https://openalex.org/W2143708379","https://openalex.org/W2144344516","https://openalex.org/W2167334577","https://openalex.org/W2523475814","https://openalex.org/W2534888058","https://openalex.org/W2618564128","https://openalex.org/W4251430302"],"related_works":["https://openalex.org/W2505380084","https://openalex.org/W2023832055","https://openalex.org/W2082485924","https://openalex.org/W1980160788","https://openalex.org/W1656096860","https://openalex.org/W2095928260","https://openalex.org/W2405661381","https://openalex.org/W2268149564","https://openalex.org/W1984739956","https://openalex.org/W2763312740"],"abstract_inverted_index":{"Directive-based":[0],"programming":[1,26],"models":[2,27],"like":[3],"OpenACC":[4],"provide":[5],"a":[6,73,81,98],"higher":[7],"level":[8,37],"abstraction":[9],"and":[10,20],"low":[11],"overhead":[12],"approach":[13],"of":[14,42,80,97],"porting":[15],"existing":[16],"applications":[17,49],"to":[18,38,75,91],"GPGPUs":[19],"other":[21],"heterogeneous":[22],"HPC":[23],"hardware.":[24],"Such":[25],"increase":[28],"the":[29,35,60,77,87,93],"design":[30],"space":[31],"exploration":[32],"possible":[33],"at":[34],"compiler":[36],"exploit":[39,59],"specific":[40],"features":[41],"different":[43],"architectures.":[44],"We":[45],"observed":[46],"that":[47],"traditional":[48],"designed":[50],"for":[51],"latency":[52],"optimized":[53,62],"out-of-order":[54],"pipelined":[55,64],"CPUs":[56],"do":[57],"not":[58],"throughput":[61,79],"in-order":[63],"GPU":[65],"architecture":[66],"efficiently.":[67],"In":[68],"this":[69],"paper":[70],"we":[71,85],"develop":[72],"model":[74],"estimate":[76],"memory":[78,94],"given":[82,99],"application.":[83],"Then":[84],"use":[86],"loop":[88],"interleave":[89],"transformation":[90],"improve":[92],"bandwidth":[95],"utilization":[96],"kernel.":[100]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":5},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}