{"id":"https://openalex.org/W2070897293","doi":"https://doi.org/10.1145/2677036","title":"Automatic and Portable Mapping of Data Parallel Programs to OpenCL for GPU-Based Heterogeneous Systems","display_name":"Automatic and Portable Mapping of Data Parallel Programs to OpenCL for GPU-Based Heterogeneous Systems","publication_year":2014,"publication_date":"2014-12-08","ids":{"openalex":"https://openalex.org/W2070897293","doi":"https://doi.org/10.1145/2677036","mag":"2070897293"},"language":"en","primary_location":{"id":"doi:10.1145/2677036","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2677036","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2677036","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/2677036","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100401045","display_name":"Zheng Wang","orcid":"https://orcid.org/0000-0001-6157-0662"},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Zheng Wang","raw_affiliation_strings":["Lancaster University","Lancaster University ()"],"affiliations":[{"raw_affiliation_string":"Lancaster University","institution_ids":["https://openalex.org/I67415387"]},{"raw_affiliation_string":"Lancaster University ()","institution_ids":["https://openalex.org/I67415387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077188995","display_name":"Dominik Grewe","orcid":null},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dominik Grewe","raw_affiliation_strings":["University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5027001025","display_name":"Michael O\u2019Boyle","orcid":"https://orcid.org/0000-0003-1619-5052"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Michael F. P. O\u2019boyle","raw_affiliation_strings":["University of Edinburgh"],"affiliations":[{"raw_affiliation_string":"University of Edinburgh","institution_ids":["https://openalex.org/I98677209"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100401045"],"corresponding_institution_ids":["https://openalex.org/I67415387"],"apc_list":null,"apc_paid":null,"fwci":3.7806,"has_fulltext":true,"cited_by_count":53,"citation_normalized_percentile":{"value":0.93342426,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"11","issue":"4","first_page":"1","last_page":"26"},"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":0.9977999925613403,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9898999929428101,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9166884422302246},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7252063751220703},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.717247486114502},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6738471984863281},{"id":"https://openalex.org/keywords/multi-core-processor","display_name":"Multi-core processor","score":0.6195856928825378},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.5964739918708801},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.5812798738479614},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.5654813051223755},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.5075877904891968},{"id":"https://openalex.org/keywords/host","display_name":"Host (biology)","score":0.4616827368736267},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.41280892491340637},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.3458852767944336},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.2593483328819275},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.19160938262939453},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.14607414603233337}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9166884422302246},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7252063751220703},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.717247486114502},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6738471984863281},{"id":"https://openalex.org/C78766204","wikidata":"https://www.wikidata.org/wiki/Q555032","display_name":"Multi-core processor","level":2,"score":0.6195856928825378},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.5964739918708801},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5812798738479614},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.5654813051223755},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.5075877904891968},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.4616827368736267},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.41280892491340637},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3458852767944336},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.2593483328819275},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.19160938262939453},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.14607414603233337},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","level":0,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2677036","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2677036","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2677036","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:151217","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:eprints.lancs.ac.uk:89213","is_oa":false,"landing_page_url":"https://eprints.lancs.ac.uk/id/eprint/89213/","pdf_url":null,"source":{"id":"https://openalex.org/S4306401916","display_name":"Lancaster EPrints (Lancaster University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67415387","host_organization_name":"Lancaster University","host_organization_lineage":["https://openalex.org/I67415387"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.1145/2677036","is_oa":true,"landing_page_url":"https://doi.org/10.1145/2677036","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/2677036","source":{"id":"https://openalex.org/S26056741","display_name":"ACM Transactions on Architecture and Code Optimization","issn_l":"1544-3566","issn":["1544-3566","1544-3973"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Architecture and Code Optimization","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.5199999809265137}],"awards":[{"id":"https://openalex.org/G369688390","display_name":null,"funder_award_id":"EP/M015793/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2070897293.pdf","grobid_xml":"https://content.openalex.org/works/W2070897293.grobid-xml"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W91689834","https://openalex.org/W145625079","https://openalex.org/W1537323515","https://openalex.org/W1552624537","https://openalex.org/W1558412961","https://openalex.org/W1782174992","https://openalex.org/W1805440014","https://openalex.org/W1966124831","https://openalex.org/W1982020565","https://openalex.org/W1987564528","https://openalex.org/W1992851788","https://openalex.org/W2005985523","https://openalex.org/W2007516655","https://openalex.org/W2016352575","https://openalex.org/W2016357834","https://openalex.org/W2017579069","https://openalex.org/W2028122240","https://openalex.org/W2032039029","https://openalex.org/W2033139628","https://openalex.org/W2046976279","https://openalex.org/W2048205898","https://openalex.org/W2048441570","https://openalex.org/W2053546108","https://openalex.org/W2056579078","https://openalex.org/W2077143534","https://openalex.org/W2083304636","https://openalex.org/W2098426571","https://openalex.org/W2099404643","https://openalex.org/W2099680095","https://openalex.org/W2101483132","https://openalex.org/W2105874735","https://openalex.org/W2105937753","https://openalex.org/W2111309482","https://openalex.org/W2121893797","https://openalex.org/W2124556751","https://openalex.org/W2125055259","https://openalex.org/W2126026097","https://openalex.org/W2129232868","https://openalex.org/W2131135493","https://openalex.org/W2140375692","https://openalex.org/W2142769604","https://openalex.org/W2149234156","https://openalex.org/W2150476673","https://openalex.org/W2154786353","https://openalex.org/W2159481344","https://openalex.org/W2160241055","https://openalex.org/W2160875256","https://openalex.org/W2166536280","https://openalex.org/W2166918318","https://openalex.org/W2167101788","https://openalex.org/W2170634604","https://openalex.org/W2564927691","https://openalex.org/W2594987874","https://openalex.org/W4235447137","https://openalex.org/W4235762625"],"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/W2792081825"],"abstract_inverted_index":{"General-purpose":[0],"GPU-based":[1,112],"systems":[2],"are":[3],"highly":[4],"attractive,":[5],"as":[6],"they":[7],"give":[8],"potentially":[9],"massive":[10],"performance":[11,62],"at":[12],"little":[13],"cost.":[14],"Realizing":[15],"such":[16],"potential":[17],"is":[18,51,80],"challenging":[19],"due":[20],"to":[21,32,60,71,76,100],"the":[22,83,87,93,101],"complexity":[23],"of":[24,48,120],"programming.":[25],"This":[26],"article":[27],"presents":[28],"a":[29,73,140],"compiler-based":[30],"approach":[31,99,144],"automatically":[33],"generate":[34],"optimized":[35],"OpenCL":[36,84],"code":[37,85,91,157],"from":[38],"data":[39,58],"parallel":[40,104],"OpenMP":[41,90],"programs":[42],"for":[43],"GPUs.":[44],"A":[45],"key":[46],"feature":[47],"our":[49,98],"scheme":[50],"that":[52],"it":[53,79,109],"leverages":[54],"existing":[55],"transformations,":[56,59],"especially":[57],"improve":[61],"on":[63,86,92,110,127,146],"GPU":[64,88,156],"architectures":[65],"and":[66,107,122,125,132],"uses":[67],"automatic":[68,155],"machine":[69],"learning":[70],"build":[72],"predictive":[74],"model":[75],"determine":[77],"if":[78],"worthwhile":[81],"running":[82],"or":[89],"multicore":[94],"host.":[95],"We":[96,114],"applied":[97],"entire":[102],"NAS":[103],"benchmark":[105],"suite":[106],"evaluated":[108],"distinct":[111],"systems.":[113],"achieved":[115],"average":[116],"(up":[117],"to)":[118],"speedups":[119,151],"4.51\u00d7":[121],"4.20\u00d7":[123],"(143\u00d7":[124],"67\u00d7)":[126],"Core":[128,133],"i7/NVIDIA":[129],"GeForce":[130],"GTX580":[131],"i7/AMD":[134],"Radeon":[135],"7970":[136],"platforms,":[137],"respectively,":[138],"over":[139,152],"sequential":[141],"baseline.":[142],"Our":[143],"achieves,":[145],"average,":[147],"greater":[148],"than":[149],"10\u00d7":[150],"two":[153],"state-of-the-art":[154],"generators.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":8},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":8},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":2}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}