{
  "abstract": "Foundation machine-learning interatomic potentials (MLIPs) offer one model for many chemistries, but their deep, globally coupled architectures do not fit the spatial decomposition that scales classical and short-ranged MLIPs. We present pair_style uma, a LAMMPS pair style that evaluates the Universal Model for Atoms (UMA) through LibTorch on NVIDIA and Intel GPUs from a single source tree. It reimplements FairChem's edge-sharded graph parallelism in C++ over exported TorchScript modules, with one MPI rank per device, NCCL or oneCCL collectives, and the whole energy and force path in double precision. The strain-gradient virial is carried through the exported modules and the cross-device reductions, so that fix npt runs on both vendors' hardware. We measure NPT capacity and cost on one 4xA100-40GB node, one 8xH200 node, and one 12-tile Intel node, and on up to 32 Intel nodes. Without activation checkpointing, one node holds NaCl cells of about 8,000 atoms (A100, 0.21 ns/day), 22,000 atoms (Intel, 0.10 ns/day), and 47,000 atoms (H200, 0.16 ns/day). Graph parallelism raises the capacity of a single device by 8.0x on H200 and 4.6x on A100. Across nodes, capacity grows to about 779,000 atoms on 32 Intel nodes, with a slower speed at 0.007 ns/day. On H200 and A100, a FLOP count of FairChem's graph-parallel predictor gives lower bounds of 31% and 51% of FP64 peak. From one omat checkpoint and with no refit, nine 100 ps NPT heating ramps (NaCl, equiatomic Pt-Ru, and equiatomic (HfNbTaTiZr)N, on all three node types) ran to completion.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2611.03892",
  "author_total": 2,
  "authors": [
    {
      "name": "Xiaoli Yan"
    },
    {
      "name": "Eliu Huerta"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/dy1gkzrkg6gp9.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2611.03892",
  "fulltext_url": null,
  "id": "dy1gkzrkg6gp9",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2611.03892",
  "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",
      "cs.CE"
    ],
    [
      "arxiv",
      "physics.chem-ph"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2611.03892",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-02",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/dy1gkzrkg6gp9.ris",
  "sources": [
    {
      "first_seen": "2026-11-04T15:21:25Z",
      "native_id": "2611.03892",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2611.03892"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "arxiv:physics.chem-ph",
      "subfield": "physical"
    }
  ],
  "title": "Isothermal-Isobaric Molecular Dynamics with a Foundation Interatomic Potential in LAMMPS across NVIDIA and Intel GPUs",
  "title_text": "Isothermal-Isobaric Molecular Dynamics with a Foundation Interatomic Potential in LAMMPS across NVIDIA and Intel GPUs",
  "type": "preprint",
  "updated_at": "2026-11-06T18:21:01Z",
  "url": "https://research.draconitic.com/paper/dy1gkzrkg6gp9",
  "venue": "arXiv",
  "versions": []
}