{"id":"https://openalex.org/W4385765206","doi":"https://doi.org/10.1177/10943420231188079","title":"Heterogeneous programming using OpenMP and CUDA/HIP for hybrid CPU-GPU scientific applications","display_name":"Heterogeneous programming using OpenMP and CUDA/HIP for hybrid CPU-GPU scientific applications","publication_year":2023,"publication_date":"2023-08-11","ids":{"openalex":"https://openalex.org/W4385765206","doi":"https://doi.org/10.1177/10943420231188079"},"language":"en","primary_location":{"id":"doi:10.1177/10943420231188079","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420231188079","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://upcommons.upc.edu/bitstreams/1a028c05-32fe-4dcb-a359-6c3ddc77bb6e/download","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036427962","display_name":"Marc Gonz\u00e1lez","orcid":"https://orcid.org/0000-0002-3780-1106"},"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"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Marc Gonzalez Tallada","raw_affiliation_strings":["Computer Architecture Department, Universitat Polit\u00e8cnica de Catalunya-BarcelonaTECH, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Computer Architecture Department, Universitat Polit\u00e8cnica de Catalunya-BarcelonaTECH, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5000717476","display_name":"Enric Morancho","orcid":"https://orcid.org/0000-0003-2403-8145"},"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"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Enric Morancho","raw_affiliation_strings":["Computer Architecture Department, Universitat Polit\u00e8cnica de Catalunya-BarcelonaTECH, Barcelona, Spain"],"affiliations":[{"raw_affiliation_string":"Computer Architecture Department, Universitat Polit\u00e8cnica de Catalunya-BarcelonaTECH, Barcelona, Spain","institution_ids":["https://openalex.org/I9617848"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5036427962"],"corresponding_institution_ids":["https://openalex.org/I9617848"],"apc_list":null,"apc_paid":null,"fwci":2.4425,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.88645418,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":98},"biblio":{"volume":"37","issue":"5","first_page":"626","last_page":"646"},"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":0.9998000264167786,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9951000213623047,"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/computer-science","display_name":"Computer science","score":0.8822618722915649},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7789953947067261},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.7428624629974365},{"id":"https://openalex.org/keywords/thread","display_name":"Thread (computing)","score":0.5220146775245667},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4761243462562561},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4404584467411041},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.41290417313575745},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15156587958335876},{"id":"https://openalex.org/keywords/graphics","display_name":"Graphics","score":0.1132824718952179}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8822618722915649},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7789953947067261},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.7428624629974365},{"id":"https://openalex.org/C138101251","wikidata":"https://www.wikidata.org/wiki/Q213092","display_name":"Thread (computing)","level":2,"score":0.5220146775245667},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4761243462562561},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4404584467411041},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.41290417313575745},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15156587958335876},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.1132824718952179},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","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}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1177/10943420231188079","is_oa":false,"landing_page_url":"https://doi.org/10.1177/10943420231188079","pdf_url":null,"source":{"id":"https://openalex.org/S60606485","display_name":"The International Journal of High Performance Computing Applications","issn_l":"1094-3420","issn":["1094-3420","1741-2846"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320017","host_organization_name":"SAGE Publishing","host_organization_lineage":["https://openalex.org/P4310320017"],"host_organization_lineage_names":["SAGE Publishing"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"The International Journal of High Performance Computing Applications","raw_type":"journal-article"},{"id":"pmh:oai:upcommons.upc.edu:2117/395515","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/395515","pdf_url":"https://upcommons.upc.edu/bitstreams/1a028c05-32fe-4dcb-a359-6c3ddc77bb6e/download","source":{"id":"https://openalex.org/S4210207057","display_name":"QRU Quaderns de Recerca en Urbanisme","issn_l":"2014-9689","issn":["2014-9689","2385-6777"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310322448","host_organization_name":"Q71272178","host_organization_lineage":["https://openalex.org/P4310322448"],"host_organization_lineage_names":["Q71272178"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:upcommons.upc.edu:2117/395515","is_oa":true,"landing_page_url":"https://hdl.handle.net/2117/395515","pdf_url":"https://upcommons.upc.edu/bitstreams/1a028c05-32fe-4dcb-a359-6c3ddc77bb6e/download","source":{"id":"https://openalex.org/S4210207057","display_name":"QRU Quaderns de Recerca en Urbanisme","issn_l":"2014-9689","issn":["2014-9689","2385-6777"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310322448","host_organization_name":"Q71272178","host_organization_lineage":["https://openalex.org/P4310322448"],"host_organization_lineage_names":["Q71272178"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4431839286","display_name":null,"funder_award_id":"PID2019-107255GB","funder_id":"https://openalex.org/F4320323737","funder_display_name":"Ministerio de Ciencia y Tecnolog\u00eda"}],"funders":[{"id":"https://openalex.org/F4320323737","display_name":"Ministerio de Ciencia y Tecnolog\u00eda","ror":"https://ror.org/034900433"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385765206.pdf","grobid_xml":"https://content.openalex.org/works/W4385765206.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W31923072","https://openalex.org/W153259801","https://openalex.org/W1546315506","https://openalex.org/W1575732703","https://openalex.org/W1720285298","https://openalex.org/W1887586770","https://openalex.org/W1993338334","https://openalex.org/W2005148983","https://openalex.org/W2011652244","https://openalex.org/W2017587301","https://openalex.org/W2024639384","https://openalex.org/W2031906600","https://openalex.org/W2037574360","https://openalex.org/W2073593865","https://openalex.org/W2083734282","https://openalex.org/W2086500526","https://openalex.org/W2093883529","https://openalex.org/W2097686029","https://openalex.org/W2104008467","https://openalex.org/W2108266785","https://openalex.org/W2112121929","https://openalex.org/W2118717320","https://openalex.org/W2121893797","https://openalex.org/W2122653654","https://openalex.org/W2132719357","https://openalex.org/W2135644880","https://openalex.org/W2142421493","https://openalex.org/W2142677441","https://openalex.org/W2147412083","https://openalex.org/W2150303942","https://openalex.org/W2167243874","https://openalex.org/W2171473263","https://openalex.org/W2176823226","https://openalex.org/W2305268528","https://openalex.org/W2584314560","https://openalex.org/W2762746832","https://openalex.org/W2935041335","https://openalex.org/W3048271386","https://openalex.org/W3109840095","https://openalex.org/W3130862573","https://openalex.org/W3139769037","https://openalex.org/W3195693051","https://openalex.org/W4231477146","https://openalex.org/W4248767818","https://openalex.org/W4250908905"],"related_works":["https://openalex.org/W2521491708","https://openalex.org/W3213381848","https://openalex.org/W2135947393","https://openalex.org/W4236883517","https://openalex.org/W2734747031","https://openalex.org/W2034135205","https://openalex.org/W2170268965","https://openalex.org/W2070468128","https://openalex.org/W4225426762","https://openalex.org/W3156477716"],"abstract_inverted_index":{"Hybrid":[0],"computer":[1],"systems":[2],"combine":[3],"compute":[4,97],"units":[5,98],"(CUs)":[6],"of":[7,20,27,39,56,82,99,110,121,148,169,218],"different":[8,100],"nature":[9,101],"like":[10],"CPUs,":[11],"GPUs":[12],"and":[13,43,54,92,103,116,124,130,139,158,179,187],"FPGAs.":[14],"Simultaneously":[15],"exploiting":[16],"the":[17,28,37,44,52,75,83,108,119,146,216],"computing":[18,166],"power":[19],"these":[21],"CUs":[22],"requires":[23],"a":[24,78,154,159,165,210],"careful":[25],"decomposition":[26],"applications":[29],"into":[30],"balanced":[31],"parallel":[32],"tasks":[33],"according":[34],"to":[35,96,113,205,209],"both":[36,90],"performance":[38],"each":[40],"CU":[41],"type":[42],"communication":[45],"costs":[46],"among":[47],"them.":[48],"This":[49],"paper":[50,73,106],"describes":[51,74,107],"design":[53],"implementation":[55,88,109],"runtime":[57,111],"support":[58,112],"for":[59,77,136],"OpenMP":[60,115],"hybrid":[61,79,129,198],"GPU-CPU":[62],"applications,":[63],"when":[64],"mixed":[65],"with":[66,150,195,207],"GPU-oriented":[67],"programming":[68],"models":[69],"(e.g.":[70],"CUDA/HIP).":[71],"The":[72,87,105],"case":[76],"multi-level":[80],"parallelization":[81],"NPB-MZ":[84],"benchmark":[85],"suite.":[86],"exploits":[89],"coarse-grain":[91],"fine-grain":[93],"parallelism,":[94],"mapped":[95],"(GPUs":[102],"CPUs).":[104],"bridge":[114],"HIP,":[117],"introducing":[118],"abstractions":[120],"Computing":[122],"Unit":[123],"Data":[125],"Placement.":[126],"We":[127],"compare":[128],"non-hybrid":[131,211],"executions":[132,199],"under":[133],"state-of-the-art":[134],"schedulers":[135,149],"OpenMP:":[137],"static":[138,161],"dynamic":[140],"task":[141,156,162],"schedulings.":[142],"Then,":[143],"we":[144],"improve":[145],"set":[147],"two":[151],"additional":[152],"variants:":[153],"memorizing-dynamic":[155],"scheduling":[157],"profile-based":[160],"scheduling.":[163],"On":[164],"node":[167],"composed":[168],"one":[170],"AMD":[171,191],"EPYC":[172],"7742":[173],"@":[174],"2.250":[175],"GHz":[176],"(64":[177],"cores":[178],"2":[180,188],"threads/core,":[181],"totalling":[182],"128":[183],"threads":[184],"per":[185],"node)":[186],"\u00d7":[189],"GPU":[190,212],"Radeon":[192],"Instinct":[193],"MI50":[194],"32":[196],"GB,":[197],"present":[200],"speedups":[201],"from":[202],"1.10\u00d7":[203],"up":[204],"3.5\u00d7":[206],"respect":[208],"implementation,":[213],"depending":[214],"on":[215],"number":[217],"activated":[219],"CUs.":[220]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}