{
  "abstract": "Legacy Fortran physics packages in atmospheric models such as CESM, WRF, and E3SM pose a barrier to GPU modernization, while manual porting requires accelerator-programming expertise. We present LAFT (LLM-Assisted Fortran Translation), an agentic framework for converting Fortran atmospheric physics parameterizations into GPU-accelerated JAX while preserving numerical agreement with the Fortran reference. LAFT coordinates source-code analysis, translation, repair, runtime validation, and performance profiling. It combines a deterministic front end for metadata extraction and bridge generation, structured translation prompts, numerical validation, and profiling-guided feedback to identify inefficient execution patterns. The bridge handles array-layout conversion separately from scientific computation. We evaluate LAFT using the Kessler warm-rain microphysics scheme and four LLMs: Claude, GPT, Gemini, and Qwen. All four validated translations reproduce the Fortran reference outputs to near floating-point precision for the evaluated case, but their GPU performance differs substantially with execution design. The Gemini-generated implementation achieves up to a 357-fold speedup over serial Fortran in cached execution at 1,000,000 atmospheric columns, excluding compilation and host-device transfers. The results demonstrate that numerical agreement alone does not ensure efficient GPU execution and motivate combining numerical validation with hardware-aware performance analysis. LAFT provides a practical workflow for modernizing legacy atmospheric physics code through LLM-assisted translation, deterministic interface generation, automated validation and repair, and reproducible profiling.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2610.12662",
  "author_total": 5,
  "authors": [
    {
      "name": "Iris Linck"
    },
    {
      "name": "John Dennis"
    },
    {
      "name": "John Schreck"
    },
    {
      "name": "Karen Stengel"
    },
    {
      "name": "David John Gagne II"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/bbbhprq6dyd45.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2610.12662",
  "fulltext_url": null,
  "id": "bbbhprq6dyd45",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2610.12662",
  "language": null,
  "licence": "CC-BY-4.0",
  "licence_label": "CC BY 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "physics.ao-ph"
    ],
    [
      "arxiv",
      "physics.comp-ph"
    ],
    [
      "openalex",
      "1708|Parallel Computing and Optimization Techniques"
    ]
  ],
  "openalex": "W7221527707",
  "pdf_url": "https://arxiv.org/pdf/2610.12662",
  "pmcid": null,
  "pmid": null,
  "published": "2026-10-08",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/bbbhprq6dyd45.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:28:36Z",
      "native_id": "2610.12662",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2610.12662"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "arxiv:physics.ao-ph",
      "subfield": "atmospheric"
    },
    {
      "field": "physics",
      "origin": "arxiv:physics.comp-ph",
      "subfield": "computational"
    }
  ],
  "title": "Evaluating LLMs for Translating Legacy Fortran Atmospheric Physics to GPU-Accelerated JAX",
  "title_text": "Evaluating LLMs for Translating Legacy Fortran Atmospheric Physics to GPU-Accelerated JAX",
  "type": "preprint",
  "updated_at": "2026-10-30T12:28:36Z",
  "url": "https://research.draconitic.com/paper/bbbhprq6dyd45",
  "venue": "arXiv",
  "versions": []
}