Large Language Models (LLMs) are increasingly being leveraged for generating and translating scientific computer codes by both domain-experts and non-domain experts. Fortran has served as one of the go to programming languages in legacy high-performance computing (HPC) for scientific discoveries. Despite growing adoption, LLM-based code translation of legacy code-bases has not been thoroughly assessed or quantified for its usability. Here, we studied the applicability of LLM-based translation of Fortran to C++ as a step towards building an agentic-workflow using open-weight LLMs on two different computational platforms. We statistically quantified the compilation accuracy of the translated C++ codes, measured the similarity of the LLM translated code to the human translated C++ code, and statistically quantified the output similarity of the Fortran to C++ translation.
@article{arxiv.2504.15424,
title = {LLM-Assisted Translation of Legacy FORTRAN Codes to C++: A Cross-Platform Study},
author = {Nishath Rajiv Ranasinghe and Shawn M. Jones and Michal Kucer and Ayan Biswas and Daniel O'Malley and Alexander Buschmann Most and Selma Liliane Wanna and Ajay Sreekumar},
journal= {arXiv preprint arXiv:2504.15424},
year = {2025}
}