{"id":"https://openalex.org/W2774096293","doi":"https://doi.org/10.1109/tpds.2018.2872064","title":"Effective Extensible Programming: Unleashing Julia on GPUs","display_name":"Effective Extensible Programming: Unleashing Julia on GPUs","publication_year":2018,"publication_date":"2018-09-24","ids":{"openalex":"https://openalex.org/W2774096293","doi":"https://doi.org/10.1109/tpds.2018.2872064","mag":"2774096293"},"language":"en","primary_location":{"id":"doi:10.1109/tpds.2018.2872064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2872064","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1712.03112","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Tim Besard","orcid":"https://orcid.org/0000-0001-7826-8021"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Tim Besard","raw_affiliation_strings":["Department of Electronics and Information Systems, Ghent University, Gent, Belgium"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems, Ghent University, Gent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Christophe Foket","orcid":null},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Christophe Foket","raw_affiliation_strings":["Department of Electronics and Information Systems, Ghent University, Gent, Belgium"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems, Ghent University, Gent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]},{"author_position":"last","author":{"id":null,"display_name":"Bjorn De Sutter","orcid":"https://orcid.org/0000-0003-0317-2089"},"institutions":[{"id":"https://openalex.org/I32597200","display_name":"Ghent University","ror":"https://ror.org/00cv9y106","country_code":"BE","type":"education","lineage":["https://openalex.org/I32597200"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Bjorn De Sutter","raw_affiliation_strings":["Department of Electronics and Information Systems, Ghent University, Gent, Belgium"],"affiliations":[{"raw_affiliation_string":"Department of Electronics and Information Systems, Ghent University, Gent, Belgium","institution_ids":["https://openalex.org/I32597200"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I32597200"],"apc_list":null,"apc_paid":null,"fwci":10.2475,"has_fulltext":false,"cited_by_count":206,"citation_normalized_percentile":{"value":0.98696054,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"30","issue":"4","first_page":"827","last_page":"841"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.8604999780654907,"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":0.8604999780654907,"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/T11424","display_name":"Security and Verification in Computing","score":0.019600000232458115,"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/T10904","display_name":"Embedded Systems Design Techniques","score":0.018400000408291817,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.795199990272522},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7159000039100647},{"id":"https://openalex.org/keywords/programmer","display_name":"Programmer","score":0.6331999897956848},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.5435000061988831},{"id":"https://openalex.org/keywords/reuse","display_name":"Reuse","score":0.49410000443458557},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4496000111103058},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.38600000739097595},{"id":"https://openalex.org/keywords/optimizing-compiler","display_name":"Optimizing compiler","score":0.37950000166893005},{"id":"https://openalex.org/keywords/code-generation","display_name":"Code generation","score":0.374099999666214}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9035000205039978},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.795199990272522},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7159000039100647},{"id":"https://openalex.org/C2778514511","wikidata":"https://www.wikidata.org/wiki/Q1374194","display_name":"Programmer","level":2,"score":0.6331999897956848},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.6134999990463257},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5480999946594238},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.5435000061988831},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.49410000443458557},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.46720001101493835},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4496000111103058},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.38600000739097595},{"id":"https://openalex.org/C190902152","wikidata":"https://www.wikidata.org/wiki/Q1325106","display_name":"Optimizing compiler","level":3,"score":0.37950000166893005},{"id":"https://openalex.org/C133162039","wikidata":"https://www.wikidata.org/wiki/Q1061077","display_name":"Code generation","level":3,"score":0.374099999666214},{"id":"https://openalex.org/C2778583558","wikidata":"https://www.wikidata.org/wiki/Q771245","display_name":"Code reuse","level":3,"score":0.3529999852180481},{"id":"https://openalex.org/C131531359","wikidata":"https://www.wikidata.org/wiki/Q5421926","display_name":"Extensible programming","level":5,"score":0.33899998664855957},{"id":"https://openalex.org/C119263510","wikidata":"https://www.wikidata.org/wiki/Q7248501","display_name":"Programming domain","level":4,"score":0.31679999828338623},{"id":"https://openalex.org/C37785467","wikidata":"https://www.wikidata.org/wiki/Q385325","display_name":"Modelica","level":2,"score":0.31189998984336853},{"id":"https://openalex.org/C19024347","wikidata":"https://www.wikidata.org/wiki/Q211496","display_name":"High-level programming language","level":3,"score":0.30309998989105225},{"id":"https://openalex.org/C32833848","wikidata":"https://www.wikidata.org/wiki/Q4115054","display_name":"Extensibility","level":2,"score":0.29010000824928284},{"id":"https://openalex.org/C76782552","wikidata":"https://www.wikidata.org/wiki/Q110546","display_name":"Just-in-time compilation","level":3,"score":0.289900004863739},{"id":"https://openalex.org/C76518257","wikidata":"https://www.wikidata.org/wiki/Q271680","display_name":"Software framework","level":5,"score":0.28859999775886536},{"id":"https://openalex.org/C150762246","wikidata":"https://www.wikidata.org/wiki/Q4354073","display_name":"Reactive programming","level":4,"score":0.2883000075817108},{"id":"https://openalex.org/C137364921","wikidata":"https://www.wikidata.org/wiki/Q27929394","display_name":"Parallel programming model","level":3,"score":0.27300000190734863},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.27160000801086426},{"id":"https://openalex.org/C145628200","wikidata":"https://www.wikidata.org/wiki/Q238137","display_name":"Fourth-generation programming language","level":5,"score":0.27140000462532043},{"id":"https://openalex.org/C50033165","wikidata":"https://www.wikidata.org/wiki/Q15712089","display_name":"Inductive programming","level":3,"score":0.26750001311302185},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2635999917984009},{"id":"https://openalex.org/C172430144","wikidata":"https://www.wikidata.org/wiki/Q17111997","display_name":"Symmetric multiprocessor system","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C149810388","wikidata":"https://www.wikidata.org/wiki/Q5374873","display_name":"Emulation","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C148047603","wikidata":"https://www.wikidata.org/wiki/Q1014612","display_name":"Parallelizable manifold","level":2,"score":0.2540999948978424},{"id":"https://openalex.org/C42383842","wikidata":"https://www.wikidata.org/wiki/Q193076","display_name":"Functional programming","level":2,"score":0.2522999942302704}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tpds.2018.2872064","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpds.2018.2872064","pdf_url":null,"source":{"id":"https://openalex.org/S97130795","display_name":"IEEE Transactions on Parallel and Distributed Systems","issn_l":"1045-9219","issn":["1045-9219","1558-2183","2161-9883"],"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 Parallel and Distributed Systems","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1712.03112","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.03112","pdf_url":"https://arxiv.org/pdf/1712.03112","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:archive.ugent.be:8607745","is_oa":false,"landing_page_url":"https://biblio.ugent.be/publication/8607745","pdf_url":null,"source":{"id":"https://openalex.org/S4306400478","display_name":"Ghent University Academic Bibliography (Ghent University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I32597200","host_organization_name":"Ghent University","host_organization_lineage":["https://openalex.org/I32597200"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"ISSN: 1558-2183","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:zenodo.org:2162864","is_oa":true,"landing_page_url":"https://zenodo.org/record/2162864","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Transactions on Parallel and Distributed Systems","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1712.03112","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.03112","pdf_url":"https://arxiv.org/pdf/1712.03112","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":32,"referenced_works":["https://openalex.org/W787819206","https://openalex.org/W1988057723","https://openalex.org/W1991224458","https://openalex.org/W2002257715","https://openalex.org/W2008844983","https://openalex.org/W2013570889","https://openalex.org/W2034798008","https://openalex.org/W2055844022","https://openalex.org/W2060990118","https://openalex.org/W2075745057","https://openalex.org/W2080592089","https://openalex.org/W2087946090","https://openalex.org/W2104958979","https://openalex.org/W2107911628","https://openalex.org/W2120575449","https://openalex.org/W2245493112","https://openalex.org/W2292282166","https://openalex.org/W2492686975","https://openalex.org/W2524556139","https://openalex.org/W2548173935","https://openalex.org/W2560096094","https://openalex.org/W2801128564","https://openalex.org/W3003483880","https://openalex.org/W4229666556","https://openalex.org/W4239045242","https://openalex.org/W4246166885","https://openalex.org/W6638075843","https://openalex.org/W6640977091","https://openalex.org/W6665744230","https://openalex.org/W6684528527","https://openalex.org/W6687402135","https://openalex.org/W6729705997"],"related_works":[],"abstract_inverted_index":{"GPUs":[0,82],"and":[1,26,101,106,123],"other":[2],"accelerators":[3],"are":[4,37],"popular":[5],"devices":[6,15],"for":[7,63,80,126],"accelerating":[8],"compute-intensive,":[9],"parallelizable":[10],"applications.":[11],"However,":[12],"programming":[13,33,71,86,119],"these":[14],"is":[16,24,27],"a":[17,31],"difficult":[18],"task.":[19],"Writing":[20],"efficient":[21],"device":[22],"code":[23],"challenging,":[25],"typically":[28],"done":[29],"in":[30],"low-level":[32],"language.":[34,72,87],"High-level":[35],"languages":[36],"rarely":[38],"supported,":[39],"or":[40,66],"do":[41],"not":[42],"integrate":[43],"with":[44,90],"the":[45,48,84,91,97,103,116,142],"rest":[46],"of":[47,109,115,141],"high-level":[49,117],"language":[50,120],"ecosystem.":[51],"To":[52],"overcome":[53],"this,":[54],"we":[55,94],"propose":[56],"compiler":[57],"infrastructure":[58],"to":[59,68,83,99,139],"efficiently":[60],"add":[61],"support":[62,79],"new":[64,104,122],"hardware":[65],"environments":[67],"an":[69],"existing":[70,92,110],"We":[73],"evaluate":[74],"our":[75],"approach":[76],"by":[77],"adding":[78],"NVIDIA":[81,144],"Julia":[85,118],"By":[88],"integrating":[89],"compiler,":[93,105],"significantly":[95],"lower":[96],"cost":[98],"implement":[100],"maintain":[102],"facilitate":[107],"reuse":[108],"application":[111,136],"code.":[112],"Moreover,":[113],"use":[114],"enables":[121],"dynamic":[124],"approaches":[125],"GPU":[127],"programming.":[128],"This":[129],"greatly":[130],"improves":[131],"programmer":[132],"productivity,":[133],"while":[134],"maintaining":[135],"performance":[137],"similar":[138],"that":[140],"official":[143],"CUDA":[145],"toolkit.":[146]},"counts_by_year":[{"year":2026,"cited_by_count":7},{"year":2025,"cited_by_count":42},{"year":2024,"cited_by_count":45},{"year":2023,"cited_by_count":35},{"year":2022,"cited_by_count":38},{"year":2021,"cited_by_count":19},{"year":2020,"cited_by_count":19},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-07T14:57:38.498316","created_date":"2017-12-22T00:00:00"}