{"id":"https://openalex.org/W4246740707","doi":"https://doi.org/10.1109/cgo.2015.7054183","title":"Characterizing and enhancing global memory data coalescing on GPUs","display_name":"Characterizing and enhancing global memory data coalescing on GPUs","publication_year":2015,"publication_date":"2015-02-01","ids":{"openalex":"https://openalex.org/W4246740707","doi":"https://doi.org/10.1109/cgo.2015.7054183"},"language":"en","primary_location":{"id":"doi:10.1109/cgo.2015.7054183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo.2015.7054183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 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/A5001721269","display_name":"Naznin Fauzia","orcid":null},"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":true,"raw_author_name":"Naznin Fauzia","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040769038","display_name":"Louis-No\u00ebl Pouchet","orcid":"https://orcid.org/0000-0001-5103-3097"},"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":"Louis-Noel Pouchet","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027517817","display_name":"P. Sadayappan","orcid":"https://orcid.org/0000-0002-4737-2034"},"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":"P. Sadayappan","raw_affiliation_strings":["The Ohio State University"],"affiliations":[{"raw_affiliation_string":"The Ohio State University","institution_ids":["https://openalex.org/I52357470"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5001721269"],"corresponding_institution_ids":["https://openalex.org/I52357470"],"apc_list":null,"apc_paid":null,"fwci":3.973,"has_fulltext":false,"cited_by_count":35,"citation_normalized_percentile":{"value":0.94031679,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"12","last_page":"22"},"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":0.9986000061035156,"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"}},{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8911672830581665},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.6724154949188232},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.621900200843811},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5198638439178467},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3632424771785736},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.34383147954940796},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.195431649684906}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8911672830581665},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.6724154949188232},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.621900200843811},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5198638439178467},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3632424771785736},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.34383147954940796},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.195431649684906},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"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:10.1109/cgo.2015.7054183","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cgo.2015.7054183","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE/ACM International Symposium on Code Generation and Optimization (CGO)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4099999964237213,"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W1491178396","https://openalex.org/W1782174992","https://openalex.org/W1863336885","https://openalex.org/W1991457994","https://openalex.org/W2016888570","https://openalex.org/W2032391783","https://openalex.org/W2038543880","https://openalex.org/W2048558763","https://openalex.org/W2063656563","https://openalex.org/W2064677272","https://openalex.org/W2067479799","https://openalex.org/W2072680607","https://openalex.org/W2077143534","https://openalex.org/W2078994750","https://openalex.org/W2080592089","https://openalex.org/W2083056254","https://openalex.org/W2107483876","https://openalex.org/W2108559751","https://openalex.org/W2116963870","https://openalex.org/W2126026097","https://openalex.org/W2128022558","https://openalex.org/W2128120785","https://openalex.org/W2129232868","https://openalex.org/W2149234156","https://openalex.org/W2475431187","https://openalex.org/W2481788784","https://openalex.org/W2564927691","https://openalex.org/W2983923412","https://openalex.org/W3013976982","https://openalex.org/W3143589697","https://openalex.org/W3152199537","https://openalex.org/W3163798569","https://openalex.org/W3203568064","https://openalex.org/W4231316372","https://openalex.org/W4295539146","https://openalex.org/W6637873805","https://openalex.org/W6639351857","https://openalex.org/W6662580226","https://openalex.org/W6676285487","https://openalex.org/W6730584767","https://openalex.org/W7065096706"],"related_works":["https://openalex.org/W2117014006","https://openalex.org/W4233815414","https://openalex.org/W2372170743","https://openalex.org/W1558545464","https://openalex.org/W2074301136","https://openalex.org/W1984303163","https://openalex.org/W1509211761","https://openalex.org/W4245302940","https://openalex.org/W1566886392","https://openalex.org/W2298102683"],"abstract_inverted_index":{"Effective":[0],"parallel":[1],"programming":[2],"for":[3,24],"GPUs":[4],"requires":[5],"careful":[6],"attention":[7],"to":[8,30,68,79],"several":[9],"factors,":[10],"including":[11],"ensuring":[12],"coalesced":[13,86],"access":[14,41,83,87],"of":[15,107,113],"data":[16,40],"from":[17,93,115],"global":[18,81],"memory.":[19],"There":[20],"is":[21,65],"a":[22,35,59,99,111],"need":[23],"tools":[25,109],"that":[26],"can":[27],"provide":[28],"feedback":[29,92],"users":[31],"about":[32],"statements":[33],"in":[34,45,74],"GPU":[36],"kernel":[37],"where":[38,62],"non-coalesced":[39],"occurs,":[42],"and":[43,70,118],"assistance":[44],"fixing":[46],"the":[47,94,105,108,116],"problem.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52],"address":[53],"both":[54],"these":[55],"needs.":[56],"We":[57],"develop":[58],"two-stage":[60],"framework":[61],"dynamic":[63,95],"analysis":[64,96],"first":[66],"used":[67],"detect":[69],"characterize":[71],"uncoalesced":[72],"accesses":[73],"arbitrary":[75],"PTX":[76],"programs.":[77],"Transformations":[78],"optimize":[80],"memory":[82],"by":[84],"introducing":[85],"are":[88],"then":[89],"implemented,":[90],"using":[91,98],"or":[97],"model-driven":[100],"approach.":[101],"Experimental":[102],"results":[103],"demonstrate":[104],"use":[106],"on":[110],"number":[112],"benchmarks":[114],"Rodinia":[117],"Polybench":[119],"suites.":[120]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":5},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":3}],"updated_date":"2026-03-06T13:50:29.536080","created_date":"2025-10-10T00:00:00"}