{"id":"https://openalex.org/W3116118308","doi":"https://doi.org/10.1109/hpec43674.2020.9286203","title":"A Comprehensive Comparison and Analysis of OpenACC and OpenMP 4.5 for NVIDIA GPUs","display_name":"A Comprehensive Comparison and Analysis of OpenACC and OpenMP 4.5 for NVIDIA GPUs","publication_year":2020,"publication_date":"2020-09-22","ids":{"openalex":"https://openalex.org/W3116118308","doi":"https://doi.org/10.1109/hpec43674.2020.9286203","mag":"3116118308"},"language":"en","primary_location":{"id":"doi:10.1109/hpec43674.2020.9286203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},"type":"article","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/A5113833486","display_name":"R. Usha","orcid":null},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"R. Usha","raw_affiliation_strings":["Centre for Development of Advanced Computing, Bengaluru"],"affiliations":[{"raw_affiliation_string":"Centre for Development of Advanced Computing, Bengaluru","institution_ids":["https://openalex.org/I1331500379"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5083595244","display_name":"Prachi Pandey","orcid":null},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Prachi Pandey","raw_affiliation_strings":["Centre for Development of Advanced Computing, Bengaluru"],"affiliations":[{"raw_affiliation_string":"Centre for Development of Advanced Computing, Bengaluru","institution_ids":["https://openalex.org/I1331500379"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063628285","display_name":"N. Mangala","orcid":null},"institutions":[{"id":"https://openalex.org/I1331500379","display_name":"Centre for Development of Advanced Computing","ror":"https://ror.org/022abst40","country_code":"IN","type":"facility","lineage":["https://openalex.org/I1331500379","https://openalex.org/I4210121746"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"N. Mangala","raw_affiliation_strings":["Centre for Development of Advanced Computing, Bengaluru"],"affiliations":[{"raw_affiliation_string":"Centre for Development of Advanced Computing, Bengaluru","institution_ids":["https://openalex.org/I1331500379"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5113833486"],"corresponding_institution_ids":["https://openalex.org/I1331500379"],"apc_list":null,"apc_paid":null,"fwci":0.6931,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.69265389,"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":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9976000189781189,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.995199978351593,"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/software-portability","display_name":"Software portability","score":0.8892648816108704},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8805846571922302},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.7205125093460083},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.6979614496231079},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5904155373573303},{"id":"https://openalex.org/keywords/programming-paradigm","display_name":"Programming paradigm","score":0.5524753332138062},{"id":"https://openalex.org/keywords/directive","display_name":"Directive","score":0.5359467267990112},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.3715912699699402},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.3602569103240967}],"concepts":[{"id":"https://openalex.org/C63000827","wikidata":"https://www.wikidata.org/wiki/Q3080428","display_name":"Software portability","level":2,"score":0.8892648816108704},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8805846571922302},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.7205125093460083},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.6979614496231079},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5904155373573303},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.5524753332138062},{"id":"https://openalex.org/C2779547435","wikidata":"https://www.wikidata.org/wiki/Q1121492","display_name":"Directive","level":2,"score":0.5359467267990112},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.3715912699699402},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.3602569103240967},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/hpec43674.2020.9286203","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286203","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1979527452","https://openalex.org/W2056862683","https://openalex.org/W2105672886","https://openalex.org/W2124937104","https://openalex.org/W2131324202","https://openalex.org/W2399715892","https://openalex.org/W2560598258","https://openalex.org/W2734023159","https://openalex.org/W2735645074","https://openalex.org/W2759010960","https://openalex.org/W2898149606","https://openalex.org/W2912579397","https://openalex.org/W2964456834","https://openalex.org/W2966972202","https://openalex.org/W3025629042","https://openalex.org/W3146039865","https://openalex.org/W4237817413"],"related_works":["https://openalex.org/W107105315","https://openalex.org/W3020739840","https://openalex.org/W2913998709","https://openalex.org/W4386875822","https://openalex.org/W3177128669","https://openalex.org/W2076165488","https://openalex.org/W2111416043","https://openalex.org/W2460870572","https://openalex.org/W4243399827","https://openalex.org/W4236300446"],"abstract_inverted_index":{"HPC":[0],"systems":[1],"having":[2],"accelerator":[3],"attached":[4],"to":[5,15,117],"it":[6],"is":[7,19],"the":[8,42,47,51,101,110,113],"new":[9],"normal.":[10],"However,":[11],"programming":[12,27,43],"these":[13,73],"accelerators":[14],"get":[16],"good":[17],"performance":[18],"very":[20],"complex":[21],"and":[22,31,65,82,97],"tedious.":[23],"Hence,":[24],"directive":[25],"based":[26],"such":[28],"as":[29],"OpenMP":[30,63],"OpenACC":[32,66],"are":[33,100],"gaining":[34],"wide":[35],"popularity":[36],"for":[37,67,103],"parallel":[38],"programming.":[39,69],"They":[40],"simplify":[41],"experience":[44],"by":[45],"abstracting":[46],"low-level":[48],"complexities":[49],"from":[50],"user.":[52],"In":[53],"this":[54],"paper,":[55],"we":[56],"have":[57],"done":[58],"an":[59],"extensive":[60],"comparison":[61,71],"of":[62,72],"4.5":[64],"GPU":[68],"Performance":[70,98],"two":[74],"APIs":[75],"on":[76],"NVIDIA":[77],"Tesla":[78],"GPUs":[79],"namely,":[80],"P100":[81],"V100":[83],"has":[84,120],"also":[85,121],"been":[86,122],"captured.":[87],"Data":[88],"Transfer":[89],"times,":[90,93],"Kernel":[91],"Execution":[92,95],"Total":[94],"times":[96],"portability":[99],"criteria":[102],"comparison.":[104],"The":[105],"challenges":[106],"faced":[107],"while":[108],"parallelizing":[109],"applications":[111],"using":[112],"directives":[114],"thus":[115],"leading":[116],"improper":[118],"outputs":[119],"dotted.":[123]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":4},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}