{"id":"https://openalex.org/W2128546436","doi":"https://doi.org/10.1145/2442516.2442546","title":"Data layout optimization for GPGPU architectures","display_name":"Data layout optimization for GPGPU architectures","publication_year":2013,"publication_date":"2013-02-23","ids":{"openalex":"https://openalex.org/W2128546436","doi":"https://doi.org/10.1145/2442516.2442546","mag":"2128546436"},"language":"en","primary_location":{"id":"doi:10.1145/2442516.2442546","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2442516.2442546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM SIGPLAN symposium on Principles and practice of parallel programming","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100361897","display_name":"Jun Liu","orcid":"https://orcid.org/0000-0002-6253-4900"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jun Liu","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA","The Pennsylvania State University , University Park, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105717223","display_name":"Wei Ding","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Ding","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA","The Pennsylvania State University , University Park, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059470113","display_name":"Ohyoung Jang","orcid":null},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ohyoung Jang","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA","The Pennsylvania State University , University Park, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007116603","display_name":"Mahmut Kandemir","orcid":"https://orcid.org/0000-0002-9940-9951"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mahmut Kandemir","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA","The Pennsylvania State University , University Park, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130769515"],"apc_list":null,"apc_paid":null,"fwci":0.1793,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.42303055,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"283","last_page":"284"},"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/T10829","display_name":"Interconnection Networks and Systems","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/cuda","display_name":"CUDA","score":0.8947535753250122},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8750386834144592},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.7962058186531067},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7483206987380981},{"id":"https://openalex.org/keywords/memory-hierarchy","display_name":"Memory hierarchy","score":0.7354797124862671},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.731874942779541},{"id":"https://openalex.org/keywords/transformation","display_name":"Transformation (genetics)","score":0.46765488386154175},{"id":"https://openalex.org/keywords/loop-fusion","display_name":"Loop fusion","score":0.44150322675704956},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.4371640086174011},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.40536898374557495},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.2480185627937317},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.20362445712089539},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10022765398025513},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.09842324256896973}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8947535753250122},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8750386834144592},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.7962058186531067},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7483206987380981},{"id":"https://openalex.org/C2778100165","wikidata":"https://www.wikidata.org/wiki/Q1589327","display_name":"Memory hierarchy","level":3,"score":0.7354797124862671},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.731874942779541},{"id":"https://openalex.org/C204241405","wikidata":"https://www.wikidata.org/wiki/Q461499","display_name":"Transformation (genetics)","level":3,"score":0.46765488386154175},{"id":"https://openalex.org/C82653869","wikidata":"https://www.wikidata.org/wiki/Q6675821","display_name":"Loop fusion","level":3,"score":0.44150322675704956},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.4371640086174011},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.40536898374557495},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.2480185627937317},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.20362445712089539},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10022765398025513},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09842324256896973},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2442516.2442546","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2442516.2442546","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th ACM SIGPLAN symposium on Principles and practice of parallel programming","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":3,"referenced_works":["https://openalex.org/W2016939324","https://openalex.org/W2034761517","https://openalex.org/W2080592089"],"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/W2128546436"],"abstract_inverted_index":{"GPUs":[0],"are":[1],"being":[2],"widely":[3,107],"used":[4],"in":[5,33,53,129],"accelerating":[6],"general-purpose":[7,31],"applications,":[8],"leading":[9],"to":[10,28,63,84,121],"the":[11,48,51,54,60,64,86,123,126,135,174],"emergence":[12],"of":[13,50,67,125,155],"GPGPU":[14,70,92],"architectures.":[15],"New":[16],"programming":[17,30],"models,":[18],"e.g.,":[19],"Compute":[20],"Unified":[21],"Device":[22],"Architecture":[23],"(CUDA),":[24],"have":[25],"been":[26],"proposed":[27,175],"facilitate":[29],"computations":[32],"GPGPUs.":[34],"However,":[35],"writing":[36],"high-performance":[37],"CUDA":[38,167],"codes":[39],"manually":[40],"is":[41],"still":[42],"tedious":[43],"and":[44,100,138,145],"difficult.":[45],"In":[46,73],"particular,":[47],"organization":[49],"data":[52,80,98,116,157,176],"memory":[55,71,93,137],"space":[56],"can":[57],"greatly":[58],"affect":[59],"performance":[61],"due":[62],"unique":[65],"features":[66],"a":[68,91,106,112],"custom":[69],"hierarchy.":[72],"this":[74],"work,":[75],"we":[76,119],"propose":[77],"an":[78,152,165],"automatic":[79],"layout":[81,124,158],"transformation":[82,177],"framework":[83],"solve":[85],"key":[87],"issues":[88],"associated":[89],"with":[90],"hierarchy":[94],"(i.e.,":[95],"channel":[96],"skewing,":[97],"coalescing,":[99],"bank":[101],"conflicts).":[102],"Our":[103],"approach":[104,178],"employs":[105],"applicable":[108],"strategy":[109,160],"based":[110],"on":[111,164,183],"novel":[113],"concept":[114],"called":[115],"localization.":[117],"Specifically,":[118],"try":[120],"optimize":[122],"arrays":[127],"accessed":[128],"affine":[130],"loop":[131],"nests,":[132],"for":[133],"both":[134,142],"device":[136],"shared":[139],"memory,":[140],"at":[141],"coarse":[143],"grain":[144,147],"fine":[146],"parallelization":[148],"levels.":[149],"We":[150],"performed":[151],"experimental":[153],"evaluation":[154],"our":[156],"optimization":[159],"using":[161],"15":[162],"benchmarks":[163],"NVIDIA":[166],"GPU":[168],"device.":[169],"The":[170],"results":[171],"show":[172],"that":[173],"brings":[179],"around":[180],"4.3X":[181],"speedup":[182],"average.":[184]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}