Creating a Dataset Supporting Translation Between OpenMP Fortran and C++ Code
Preprint
Abstract
In this study, we present a novel dataset for training machine learning models translating between OpenMP Fortran and C++ code. To ensure reliability and applicability, the dataset is initially refined using a meticulous code similarity test. The effectiveness of our dataset is assessed using both quantitative (CodeBLEU) and qualitative (human evaluation) methods. We demonstrate how this dataset can significantly improve the translation capabilities of large-scale language models, with improvements of \times 5.1 for models with no prior coding knowledge and \times 9.9 for models with some coding familiarity. Our work highlights the potential of this dataset to advance the field of code translation for high-performance computing.Keywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Chat2VIS: Generating Data Visualizations via Natural Language Using ChatGPT, Codex and GPT-3 Large Language ModelsIEEE Access, 2023
- Review of deep learning: concepts, CNN architectures, challenges, applications, future directionsJournal of Big Data, 2021
- AI for Science: Report on the Department of Energy (DOE) Town Halls on
Artificial Intelligence (AI) for Science2020
- Automatic Fortran to C++ conversion with FABLESource Code for Biology and Medicine, 2012
- The MeqTrees software system and its use for third-generation calibration of radio interferometersAstronomy & Astrophysics, 2010
- Attribute grammar paradigms—a high-level methodology in language implementationACM Computing Surveys, 1995