{"id":"https://openalex.org/W3028670792","doi":"https://doi.org/10.1145/3378678.3391881","title":"OpenMP to CUDA graphs","display_name":"OpenMP to CUDA graphs","publication_year":2020,"publication_date":"2020-05-25","ids":{"openalex":"https://openalex.org/W3028670792","doi":"https://doi.org/10.1145/3378678.3391881","mag":"3028670792"},"language":"en","primary_location":{"id":"doi:10.1145/3378678.3391881","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3378678.3391881","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23th International Workshop on Software and Compilers for Embedded Systems","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/2117/190303","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5049416277","display_name":"Chenle Yu","orcid":"https://orcid.org/0000-0002-1802-8680"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]},{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Chenle Yu","raw_affiliation_strings":["Barcelona Supercomputing Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026777110","display_name":"Sara Royuela","orcid":"https://orcid.org/0000-0002-7644-0868"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]},{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Sara Royuela","raw_affiliation_strings":["Barcelona Supercomputing Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037858669","display_name":"Eduardo Qui\u00f1ones","orcid":"https://orcid.org/0000-0002-5465-964X"},"institutions":[{"id":"https://openalex.org/I9617848","display_name":"Universitat Polit\u00e8cnica de Catalunya","ror":"https://ror.org/03mb6wj31","country_code":"ES","type":"education","lineage":["https://openalex.org/I9617848"]},{"id":"https://openalex.org/I2799803557","display_name":"Barcelona Supercomputing Center","ror":"https://ror.org/05sd8tv96","country_code":"ES","type":"facility","lineage":["https://openalex.org/I2799803557","https://openalex.org/I9617848"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Eduardo Qui\u00f1ones","raw_affiliation_strings":["Barcelona Supercomputing Center"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Barcelona Supercomputing Center","institution_ids":["https://openalex.org/I9617848","https://openalex.org/I2799803557"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5049416277"],"corresponding_institution_ids":["https://openalex.org/I2799803557","https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":2.1223,"has_fulltext":false,"cited_by_count":18,"citation_normalized_percentile":{"value":0.86997603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"42","last_page":"47"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9994999766349792,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9975000023841858,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.8854689598083496},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8466715812683105},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.7737308740615845},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7447795867919922},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.561809778213501},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.48310399055480957},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.4569888114929199},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.43991440534591675},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4165421426296234},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.28770801424980164},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.18727722764015198},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.15408775210380554}],"concepts":[{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.8854689598083496},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8466715812683105},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.7737308740615845},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7447795867919922},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.561809778213501},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.48310399055480957},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.4569888114929199},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.43991440534591675},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4165421426296234},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.28770801424980164},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.18727722764015198},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.15408775210380554},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3378678.3391881","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3378678.3391881","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 23th International Workshop on Software and Compilers for Embedded Systems","raw_type":"proceedings-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/190303","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/190303","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference lecture"}],"best_oa_location":{"id":"pmh:oai:upcommons.upc.edu:2117/190303","is_oa":true,"landing_page_url":"http://hdl.handle.net/2117/190303","pdf_url":null,"source":{"id":"https://openalex.org/S4377196262","display_name":"UPCommons institutional repository (Universitat Polit\u00e8cnica de Catalunya)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9617848","host_organization_name":"Universitat Polit\u00e8cnica de Catalunya","host_organization_lineage":["https://openalex.org/I9617848"],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference lecture"},"sustainable_development_goals":[{"score":0.5099999904632568,"id":"https://metadata.un.org/sdg/8","display_name":"Decent work and economic growth"}],"awards":[{"id":"https://openalex.org/G3557450546","display_name":"A Model-driven development framework for highly Parallel and EneRgy-Efficient computation supporting multi-criteria optimisation","funder_award_id":"871669","funder_id":"https://openalex.org/F4320338475","funder_display_name":"H2020 LEIT Information and Communication Technologies"}],"funders":[{"id":"https://openalex.org/F4320338475","display_name":"H2020 LEIT Information and Communication Technologies","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W1483717008","https://openalex.org/W1782174992","https://openalex.org/W1970112521","https://openalex.org/W1981021840","https://openalex.org/W1981969960","https://openalex.org/W1984222112","https://openalex.org/W1997751072","https://openalex.org/W1998284301","https://openalex.org/W2002194229","https://openalex.org/W2018408367","https://openalex.org/W2019143817","https://openalex.org/W2026418498","https://openalex.org/W2051696543","https://openalex.org/W2071828104","https://openalex.org/W2122078011","https://openalex.org/W2126026097","https://openalex.org/W2142677441","https://openalex.org/W2154056489","https://openalex.org/W2170634604","https://openalex.org/W2289627868","https://openalex.org/W2296181849","https://openalex.org/W2559687348","https://openalex.org/W2612954225","https://openalex.org/W2750107630","https://openalex.org/W2888990589","https://openalex.org/W3013976982","https://openalex.org/W3036102121","https://openalex.org/W4231383420"],"related_works":["https://openalex.org/W2062837242","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/W2370314112","https://openalex.org/W1912958759","https://openalex.org/W2792081825"],"abstract_inverted_index":{"Heterogeneous":[0],"computing":[1,10],"is":[2,42,61],"increasingly":[3],"being":[4],"used":[5],"in":[6,82],"a":[7,62,88,107,119],"diversity":[8],"of":[9,30,37,49,75,104,106,118],"systems,":[11],"ranging":[12],"from":[13,134],"HPC":[14,136],"to":[15,20,27,44],"the":[16,23,28,35,46,102,115,135,141,144],"real-time":[17],"embedded":[18,138],"domain,":[19],"cope":[21],"with":[22,114],"performance":[24,47,116],"requirements.":[25],"Due":[26],"variety":[29],"accelerators,":[31],"e.g.,":[32],"FPGAs,":[33],"GPUs,":[34],"use":[36],"high-level":[38,64,108],"parallel":[39],"programming":[40,65,109,121],"models":[41,73],"desirable":[43],"exploit":[45],"capabilities":[48],"them,":[50],"while":[51],"maintaining":[52],"an":[53],"adequate":[54],"productivity":[55],"level.":[56],"In":[57],"that":[58,67,93],"regard,":[59],"OpenMP":[60,96],"well-known":[63],"model":[66,110,122],"incorporates":[68],"powerful":[69],"task":[70],"and":[71,79,137,143],"accelerator":[72],"capable":[74],"efficiently":[76],"exploiting":[77],"structured":[78],"unstructured":[80],"parallelism":[81],"heterogeneous":[83],"computing.":[84],"This":[85],"paper":[86],"presents":[87],"novel":[89],"compiler":[90],"transformation":[91],"technique":[92],"automatically":[94],"transforms":[95],"code":[97],"into":[98],"CUDA":[99],"graphs,":[100],"combining":[101],"benefits":[103,117],"programmability":[105],"such":[111,123],"as":[112,124],"OpenMP,":[113],"low-level":[120],"CUDA.":[125],"Evaluations":[126],"have":[127],"been":[128],"performed":[129],"on":[130],"two":[131],"NVIDIA":[132],"GPUs":[133],"domains,":[139],"i.e.,":[140],"V100":[142],"Jetson":[145],"AGX":[146],"respectively.":[147]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-05-06T08:25:59.206177","created_date":"2020-06-05T00:00:00"}