{"id":"https://openalex.org/W1967157628","doi":"https://doi.org/10.1145/2247684.2247699","title":"A study towards optimal data layout for GPU computing","display_name":"A study towards optimal data layout for GPU computing","publication_year":2012,"publication_date":"2012-06-11","ids":{"openalex":"https://openalex.org/W1967157628","doi":"https://doi.org/10.1145/2247684.2247699","mag":"1967157628"},"language":"en","primary_location":{"id":"doi:10.1145/2247684.2247699","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2247684.2247699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2012 ACM SIGPLAN Workshop on Memory Systems Performance and Correctness","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/A5049890668","display_name":"Eddy Z. Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Eddy Z. Zhang","raw_affiliation_strings":["The College of William and Mary"],"affiliations":[{"raw_affiliation_string":"The College of William and Mary","institution_ids":["https://openalex.org/I16285277"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100452557","display_name":"Han Li","orcid":"https://orcid.org/0000-0001-5101-5542"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Han Li","raw_affiliation_strings":["The College of William and Mary"],"affiliations":[{"raw_affiliation_string":"The College of William and Mary","institution_ids":["https://openalex.org/I16285277"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100624451","display_name":"Xipeng Shen","orcid":"https://orcid.org/0000-0003-3599-8010"},"institutions":[{"id":"https://openalex.org/I16285277","display_name":"William & Mary","ror":"https://ror.org/03hsf0573","country_code":"US","type":"education","lineage":["https://openalex.org/I16285277"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xipeng Shen","raw_affiliation_strings":["The College of William and Mary"],"affiliations":[{"raw_affiliation_string":"The College of William and Mary","institution_ids":["https://openalex.org/I16285277"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049890668"],"corresponding_institution_ids":["https://openalex.org/I16285277"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.04937231,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"72","last_page":"73"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998000264167786,"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":0.9998000264167786,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9987999796867371,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9979000091552734,"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/computer-science","display_name":"Computer science","score":0.8673460483551025},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.6060351729393005},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6009142398834229},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5629448890686035},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5150578022003174},{"id":"https://openalex.org/keywords/data-space","display_name":"Data space","score":0.474504679441452},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.42819744348526},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3371984362602234},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11633795499801636},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09716984629631042}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8673460483551025},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.6060351729393005},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6009142398834229},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5629448890686035},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5150578022003174},{"id":"https://openalex.org/C2988382989","wikidata":"https://www.wikidata.org/wiki/Q370685","display_name":"Data space","level":2,"score":0.474504679441452},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.42819744348526},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3371984362602234},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11633795499801636},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09716984629631042},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2247684.2247699","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2247684.2247699","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2012 ACM SIGPLAN Workshop on Memory Systems Performance and Correctness","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":2,"referenced_works":["https://openalex.org/W2128329055","https://openalex.org/W2141170493"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W2023572661","https://openalex.org/W4245975140","https://openalex.org/W2532592438","https://openalex.org/W2136877600","https://openalex.org/W2119260685","https://openalex.org/W2039100193","https://openalex.org/W2984179089"],"abstract_inverted_index":{"The":[0],"performance":[1],"of":[2,19,53,75,85],"Graphic":[3],"Processing":[4],"Units":[5],"(GPU)":[6],"is":[7,35],"sensitive":[8],"to":[9,29,46,61],"irregular":[10,21],"memory":[11],"references.":[12],"A":[13],"recent":[14],"study":[15],"shows":[16],"the":[17,32,47,51,78,86],"promise":[18],"eliminating":[20],"references":[22],"through":[23],"runtime":[24],"thread-data":[25],"remapping.":[26],"However,":[27],"how":[28],"efficiently":[30],"determine":[31],"optimal":[33,65],"mapping":[34],"yet":[36],"an":[37],"open":[38],"question.":[39],"This":[40],"paper":[41],"presents":[42],"some":[43],"initial":[44],"exploration":[45],"question,":[48],"especially":[49],"in":[50],"dimension":[52],"data":[54,66,88],"layout":[55],"optimization.":[56],"It":[57],"describes":[58],"three":[59],"algorithms":[60,71],"compute":[62],"or":[63],"approximate":[64],"layouts":[67],"for":[68],"GPU.":[69],"These":[70],"exhibit":[72],"a":[73],"spectrum":[74],"tradeoff":[76],"among":[77],"space":[79],"cost,":[80,82],"time":[81],"and":[83],"quality":[84],"resulting":[87],"layouts.":[89]},"counts_by_year":[{"year":2020,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}