{"id":"https://openalex.org/W4390188667","doi":"https://doi.org/10.1109/hpec58863.2023.10363534","title":"Creating a Dataset for High-Performance Computing Code Translation using LLMs: A Bridge Between OpenMP Fortran and C++","display_name":"Creating a Dataset for High-Performance Computing Code Translation using LLMs: A Bridge Between OpenMP Fortran and C++","publication_year":2023,"publication_date":"2023-09-25","ids":{"openalex":"https://openalex.org/W4390188667","doi":"https://doi.org/10.1109/hpec58863.2023.10363534"},"language":"en","primary_location":{"id":"doi:10.1109/hpec58863.2023.10363534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec58863.2023.10363534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.osti.gov/servlets/purl/2328217","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103063202","display_name":"Bin Lei","orcid":"https://orcid.org/0000-0001-8749-8144"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bin Lei","raw_affiliation_strings":["University of Connecticut Storrs,Dept. Computer Science and Engineering,USA","Dept. Computer Science and Engineering, University of Connecticut Storrs, USA"],"affiliations":[{"raw_affiliation_string":"University of Connecticut Storrs,Dept. Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I140172145"]},{"raw_affiliation_string":"Dept. Computer Science and Engineering, University of Connecticut Storrs, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030060072","display_name":"Caiwen Ding","orcid":"https://orcid.org/0000-0003-0891-1231"},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Caiwen Ding","raw_affiliation_strings":["University of Connecticut Storrs,Dept. Computer Science and Engineering,USA","Dept. Computer Science and Engineering, University of Connecticut Storrs, USA"],"affiliations":[{"raw_affiliation_string":"University of Connecticut Storrs,Dept. Computer Science and Engineering,USA","institution_ids":["https://openalex.org/I140172145"]},{"raw_affiliation_string":"Dept. Computer Science and Engineering, University of Connecticut Storrs, USA","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013180203","display_name":"Le Chen","orcid":"https://orcid.org/0000-0003-3847-4108"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Le Chen","raw_affiliation_strings":["Lawrence Livermore National Laboratory,Livermore,USA","Lawrence Livermore National Laboratory, Livermore, USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory,Livermore,USA","institution_ids":["https://openalex.org/I1282311441"]},{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035121838","display_name":"Pei\u2010Hung Lin","orcid":"https://orcid.org/0000-0003-4977-814X"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pei-Hung Lin","raw_affiliation_strings":["Lawrence Livermore National Laboratory,Livermore,USA","Lawrence Livermore National Laboratory, Livermore, USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory,Livermore,USA","institution_ids":["https://openalex.org/I1282311441"]},{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, USA","institution_ids":["https://openalex.org/I1282311441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034222191","display_name":"Chunhua Liao","orcid":"https://orcid.org/0000-0001-6477-0547"},"institutions":[{"id":"https://openalex.org/I1282311441","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53","country_code":"US","type":"facility","lineage":["https://openalex.org/I1282311441","https://openalex.org/I1330989302","https://openalex.org/I198811213","https://openalex.org/I4210138311"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chunhua Liao","raw_affiliation_strings":["Lawrence Livermore National Laboratory,Livermore,USA","Lawrence Livermore National Laboratory, Livermore, USA"],"affiliations":[{"raw_affiliation_string":"Lawrence Livermore National Laboratory,Livermore,USA","institution_ids":["https://openalex.org/I1282311441"]},{"raw_affiliation_string":"Lawrence Livermore National Laboratory, Livermore, USA","institution_ids":["https://openalex.org/I1282311441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5103063202"],"corresponding_institution_ids":["https://openalex.org/I140172145"],"apc_list":null,"apc_paid":null,"fwci":5.4018,"has_fulltext":true,"cited_by_count":12,"citation_normalized_percentile":{"value":0.96071768,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.996399998664856,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.996399998664856,"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"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9902999997138977,"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/T10028","display_name":"Topic Modeling","score":0.9896000027656555,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8016108870506287},{"id":"https://openalex.org/keywords/fortran","display_name":"Fortran","score":0.7647550106048584},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.5718749165534973},{"id":"https://openalex.org/keywords/supercomputer","display_name":"Supercomputer","score":0.5505273342132568},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.49299952387809753},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.46929818391799927},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4475008547306061},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.43735408782958984},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.428554505109787},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.4261282682418823},{"id":"https://openalex.org/keywords/python","display_name":"Python (programming language)","score":0.41627979278564453},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.40351730585098267},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.35753315687179565},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.24522671103477478}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8016108870506287},{"id":"https://openalex.org/C2778241615","wikidata":"https://www.wikidata.org/wiki/Q83303","display_name":"Fortran","level":2,"score":0.7647550106048584},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.5718749165534973},{"id":"https://openalex.org/C83283714","wikidata":"https://www.wikidata.org/wiki/Q121117","display_name":"Supercomputer","level":2,"score":0.5505273342132568},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.49299952387809753},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.46929818391799927},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4475008547306061},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.43735408782958984},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.428554505109787},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.4261282682418823},{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.41627979278564453},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40351730585098267},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.35753315687179565},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.24522671103477478},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/hpec58863.2023.10363534","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec58863.2023.10363534","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"},{"id":"pmh:oai:osti.gov:2328217","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2328217","pdf_url":"https://www.osti.gov/servlets/purl/2328217","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null}],"best_oa_location":{"id":"pmh:oai:osti.gov:2328217","is_oa":true,"landing_page_url":"https://www.osti.gov/biblio/2328217","pdf_url":"https://www.osti.gov/servlets/purl/2328217","source":{"id":"https://openalex.org/S4306402487","display_name":"OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I139351228","host_organization_name":"Office of Scientific and Technical Information","host_organization_lineage":["https://openalex.org/I139351228"],"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":null},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5522089832","display_name":null,"funder_award_id":"DE-AC52-07NA27344","funder_id":"https://openalex.org/F4320338286","funder_display_name":"Lawrence Livermore National Laboratory"}],"funders":[{"id":"https://openalex.org/F4320338286","display_name":"Lawrence Livermore National Laboratory","ror":"https://ror.org/041nk4h53"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390188667.pdf","grobid_xml":"https://content.openalex.org/works/W4390188667.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1525215176","https://openalex.org/W1651373482","https://openalex.org/W1983545421","https://openalex.org/W2082089653","https://openalex.org/W2115628787","https://openalex.org/W2581223690","https://openalex.org/W2767510344","https://openalex.org/W2897962465","https://openalex.org/W2899771611","https://openalex.org/W3003339503","https://openalex.org/W3011495430","https://openalex.org/W3081168214","https://openalex.org/W3089307846","https://openalex.org/W3098044990","https://openalex.org/W3140854437","https://openalex.org/W4229005866","https://openalex.org/W4321472057","https://openalex.org/W4376167329","https://openalex.org/W4394664141","https://openalex.org/W6636831568","https://openalex.org/W6755311862","https://openalex.org/W6811340617","https://openalex.org/W6850182213","https://openalex.org/W6852746770","https://openalex.org/W6864870587"],"related_works":["https://openalex.org/W2384867379","https://openalex.org/W4400094300","https://openalex.org/W2066731161","https://openalex.org/W2329539859","https://openalex.org/W1986195078","https://openalex.org/W2227905990","https://openalex.org/W2765823764","https://openalex.org/W3214280620","https://openalex.org/W1974990957","https://openalex.org/W2789551765"],"abstract_inverted_index":{"In":[0],"this":[1,66],"study,":[2],"we":[3],"present":[4],"a":[5,30,42,85],"novel":[6],"dataset":[7,26,51,67,112,129,143],"for":[8,139],"training":[9],"machine":[10],"learning":[11],"models":[12,76,79,95],"translating":[13],"between":[14],"OpenMP":[15,35],"Fortran":[16],"and":[17,23,58],"C++":[18],"code.":[19],"To":[20],"ensure":[21],"reliability":[22],"applicability,":[24],"the":[25,70,124,134],"is":[27,38,52,116,144],"created":[28],"from":[29],"range":[31],"of":[32,49,73,87,127,136],"representative":[33],"open-source":[34],"benchmarks.":[36],"It":[37,115],"also":[39,117],"refined":[40],"using":[41,54,110],"meticulous":[43],"code":[44,137],"similarity":[45],"test.":[46],"The":[47,106,142],"effectiveness":[48],"our":[50,111,128],"assessed":[53],"both":[55],"quantitative":[56],"(CodeBLEU)":[57],"qualitative":[59],"(human":[60],"evaluation)":[61],"methods.":[62],"We":[63],"showcase":[64],"how":[65],"significantly":[68],"elevates":[69],"translation":[71,138],"competencies":[72],"large":[74],"language":[75],"(LLMs).":[77],"Specifically,":[78],"without":[80],"prior":[81],"coding":[82,98],"knowledge":[83],"experienced":[84],"boost":[86],"x":[88,103],"5.1":[89],"in":[90,130,133],"their":[91],"CodeBLEU":[92],"scores,":[93],"while":[94],"with":[96],"some":[97],"familiarity":[99],"saw":[100],"an":[101],"impressive":[102],"9.9-fold":[104],"increase.":[105],"best":[107],"fine-tuned":[108],"model":[109],"outperforms":[113],"GPT-4.":[114],"reaching":[118],"human-level":[119],"accuracy.":[120],"This":[121],"work":[122],"underscores":[123],"immense":[125],"potential":[126],"propelling":[131],"advancements":[132],"domain":[135],"high-performance":[140],"computing.":[141],"accessible":[145],"at":[146],"https://github.com/bin123apple/Fortran-CPP-HPC-code-translation-dataset.":[147]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":5}],"updated_date":"2026-04-18T07:56:08.524223","created_date":"2025-10-10T00:00:00"}