{"id":"https://openalex.org/W2510640601","doi":"https://doi.org/10.1109/tc.2016.2604372","title":"Optimizing Data Placement on GPU Memory: A Portable Approach","display_name":"Optimizing Data Placement on GPU Memory: A Portable Approach","publication_year":2016,"publication_date":"2016-08-30","ids":{"openalex":"https://openalex.org/W2510640601","doi":"https://doi.org/10.1109/tc.2016.2604372","mag":"2510640601"},"language":"en","primary_location":{"id":"doi:10.1109/tc.2016.2604372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2016.2604372","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-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/A5103032013","display_name":"Guoyang Chen","orcid":"https://orcid.org/0000-0002-5531-8986"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Guoyang Chen","raw_affiliation_strings":["North Carolina State University, Raleigh, NC"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100624451","display_name":"Xipeng Shen","orcid":"https://orcid.org/0000-0003-3599-8010"},"institutions":[{"id":"https://openalex.org/I137902535","display_name":"North Carolina State University","ror":"https://ror.org/04tj63d06","country_code":"US","type":"education","lineage":["https://openalex.org/I137902535"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xipeng Shen","raw_affiliation_strings":["North Carolina State University, Raleigh, NC"],"affiliations":[{"raw_affiliation_string":"North Carolina State University, Raleigh, NC","institution_ids":["https://openalex.org/I137902535"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059368105","display_name":"Bo Wu","orcid":"https://orcid.org/0000-0001-6658-6452"},"institutions":[{"id":"https://openalex.org/I167576493","display_name":"Colorado School of Mines","ror":"https://ror.org/04raf6v53","country_code":"US","type":"education","lineage":["https://openalex.org/I167576493"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bo Wu","raw_affiliation_strings":["Colorado Schools of Mines, Golden, CO"],"affiliations":[{"raw_affiliation_string":"Colorado Schools of Mines, Golden, CO","institution_ids":["https://openalex.org/I167576493"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100407387","display_name":"Dong Li","orcid":"https://orcid.org/0000-0001-9336-0694"},"institutions":[{"id":"https://openalex.org/I156087764","display_name":"University of California, Merced","ror":"https://ror.org/00d9ah105","country_code":"US","type":"education","lineage":["https://openalex.org/I156087764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dong Li","raw_affiliation_strings":["University of California, Merced, CA"],"affiliations":[{"raw_affiliation_string":"University of California, Merced, CA","institution_ids":["https://openalex.org/I156087764"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103032013"],"corresponding_institution_ids":["https://openalex.org/I137902535"],"apc_list":null,"apc_paid":null,"fwci":2.838,"has_fulltext":false,"cited_by_count":13,"citation_normalized_percentile":{"value":0.90455144,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"66","issue":"3","first_page":"473","last_page":"487"},"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":0.9998000264167786,"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/T10772","display_name":"Distributed systems and fault tolerance","score":0.9991999864578247,"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":0.9208784103393555},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.6825933456420898},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6613427400588989},{"id":"https://openalex.org/keywords/profiling","display_name":"Profiling (computer programming)","score":0.6570292711257935},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6003801226615906},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.47876110672950745},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.44463449716567993},{"id":"https://openalex.org/keywords/data-access","display_name":"Data access","score":0.44233161211013794},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.404492050409317},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.33025306463241577},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15540212392807007}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9208784103393555},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.6825933456420898},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6613427400588989},{"id":"https://openalex.org/C187191949","wikidata":"https://www.wikidata.org/wiki/Q1138496","display_name":"Profiling (computer programming)","level":2,"score":0.6570292711257935},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6003801226615906},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.47876110672950745},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.44463449716567993},{"id":"https://openalex.org/C47487241","wikidata":"https://www.wikidata.org/wiki/Q5227230","display_name":"Data access","level":2,"score":0.44233161211013794},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.404492050409317},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.33025306463241577},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15540212392807007}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tc.2016.2604372","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tc.2016.2604372","pdf_url":null,"source":{"id":"https://openalex.org/S157670870","display_name":"IEEE Transactions on Computers","issn_l":"0018-9340","issn":["0018-9340","1557-9956","2326-3814"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Computers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G460697733","display_name":null,"funder_award_id":"1320796","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W1489227727","https://openalex.org/W1517684295","https://openalex.org/W1936410615","https://openalex.org/W1968391520","https://openalex.org/W1976229529","https://openalex.org/W2013419729","https://openalex.org/W2016352575","https://openalex.org/W2016618963","https://openalex.org/W2020572638","https://openalex.org/W2024717934","https://openalex.org/W2025397373","https://openalex.org/W2035080386","https://openalex.org/W2048588974","https://openalex.org/W2059252667","https://openalex.org/W2072680607","https://openalex.org/W2080592089","https://openalex.org/W2083056254","https://openalex.org/W2091553595","https://openalex.org/W2095908137","https://openalex.org/W2102843684","https://openalex.org/W2104305170","https://openalex.org/W2110195531","https://openalex.org/W2113282196","https://openalex.org/W2120062497","https://openalex.org/W2120829734","https://openalex.org/W2128329055","https://openalex.org/W2129232868","https://openalex.org/W2130336316","https://openalex.org/W2130604611","https://openalex.org/W2142769604","https://openalex.org/W2147193503","https://openalex.org/W2149234156","https://openalex.org/W2155131419","https://openalex.org/W2160875256","https://openalex.org/W2167334577","https://openalex.org/W2170666978","https://openalex.org/W2401669432","https://openalex.org/W2997701623","https://openalex.org/W3139006581","https://openalex.org/W3143589697","https://openalex.org/W4238930179","https://openalex.org/W4241057782","https://openalex.org/W6653757291","https://openalex.org/W6684763460","https://openalex.org/W6712952616","https://openalex.org/W6980693441","https://openalex.org/W7065096706"],"related_works":["https://openalex.org/W2002505081","https://openalex.org/W2083681681","https://openalex.org/W2577630842","https://openalex.org/W3146558274","https://openalex.org/W1172579163","https://openalex.org/W1488300410","https://openalex.org/W2138790427","https://openalex.org/W4246454774","https://openalex.org/W2162051035","https://openalex.org/W1597127505"],"abstract_inverted_index":{"Modern":[0],"GPUs":[1],"feature":[2],"complex":[3],"memory":[4,14,25,70],"system":[5,71],"designs.":[6],"One":[7],"GPU":[8,39,160,173,176],"may":[9],"contain":[10],"many":[11,29,172],"types":[12],"of":[13,15,38,59,103,115,133,145,158],"different":[16],"properties.":[17],"The":[18],"best":[19,128],"way":[20],"to":[21,28,171],"place":[22],"data":[23,40,60,77,92,129,153],"in":[24],"is":[26,46],"sensitive":[27],"factors":[30],"(e.g.,":[31],"program":[32,179],"inputs,":[33],"architectures),":[34],"making":[35],"portable":[36],"optimizations":[37,58],"placement":[41,61,93],"a":[42,47,63,66,73,84,100,119,142,146,159],"difficult":[43],"challenge.":[44],"PORPLE":[45,164],"recently":[48],"proposed":[49],"method":[50],"that":[51,110],"overcomes":[52],"the":[53,95,113,127,131,138,162],"difficulties":[54],"by":[55],"enabling":[56],"online":[57],"through":[62],"three-way":[64],"synergy:":[65],"specification":[67],"language":[68],"for":[69,76,87,123,126,136,155],"description,":[72],"compiler":[74],"framework":[75],"access":[78],"analysis":[79],"and":[80,83,90,106,141,178],"code":[81],"staging,":[82],"runtime":[85],"library":[86],"efficiently":[88,124],"finding":[89],"materializing":[91],"on":[94,169],"fly.":[96],"This":[97],"article":[98],"provides":[99],"comprehensive":[101],"description":[102],"this":[104],"method,":[105],"presents":[107],"several":[108],"extensions":[109],"significantly":[111],"improve":[112],"scalability":[114],"PORPLE,":[116],"which":[117],"include":[118],"novel":[120],"algorithm":[121],"design":[122],"searching":[125],"placements,":[130],"use":[132],"active":[134],"profiling":[135],"reducing":[137],"online-profiling":[139],"overhead,":[140],"systematic":[143],"examination":[144],"path-based":[147],"performance":[148],"model.":[149],"By":[150],"automatically":[151],"tailoring":[152],"placements":[154],"each":[156],"execution":[157],"program,":[161],"enhanced":[163],"brings":[165],"significant":[166],"speedups":[167],"(1.72X":[168],"average)":[170],"kernels":[174],"across":[175],"architectures":[177],"inputs.":[180]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":2},{"year":2017,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}