{
  "abstract": "Operational pseudospectral atmospheric models such as the ECMWF Integrated Forecasting System (IFS) run today almost exclusively on CPUs; GPU ports are under active development but not yet used in production. These models rely on the Spherical Harmonic Transform (SHT). Each time-step requires forward and inverse SHTs, and both passes depend on global pencil transposition that redistribute multi-dimensional arrays across compute nodes. At large node counts these global collectives dominate wall-clock time. We investigate GPU-resident lossy compression, using representative fields from the DYAMOND high-resolution operational dataset as input, and combining measured GPU compression throughput with SimGrid network simulation, we show that ZFP at 16 bits per value (rate-16), about the same storage budget as float16, matches the communication-time reduction of float16 truncation while delivering approximately $\\mathbf{1600\\times}$ lower mean relative error. ZFP at 8 bits per value (rate-8) achieves approximately $\\mathbf{1.93\\times}$ the speedup of float16 while retaining $\\mathbf{4\\times}$ lower mean relative error.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2609.24294",
  "author_total": 2,
  "authors": [
    {
      "name": "Lorenzo Breschi"
    },
    {
      "name": "Flavio Vella"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/frryajc1n9c0k.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2609.24294",
  "fulltext_url": null,
  "id": "frryajc1n9c0k",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2609.24294",
  "language": null,
  "licence": "LicenseRef-arXiv-nonexclusive-1.0",
  "licence_label": "arXiv licence",
  "licence_source": "article",
  "licence_url": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "cs.DC"
    ],
    [
      "arxiv",
      "physics.ao-ph"
    ],
    [
      "openalex",
      "1708|Parallel Computing and Optimization Techniques"
    ]
  ],
  "openalex": "W7214058484",
  "pdf_url": "https://arxiv.org/pdf/2609.24294",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-21",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/frryajc1n9c0k.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:23:19Z",
      "native_id": "2609.24294",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2609.24294"
    }
  ],
  "subjects": [
    {
      "field": "earth",
      "origin": "arxiv:physics.ao-ph",
      "subfield": "atmospheric"
    }
  ],
  "title": "Toward GPU-Resident Climate Models: A Feasibility Study on Lossy Compression for the Spherical Harmonic Transform's Communication Bottleneck",
  "title_text": "Toward GPU-Resident Climate Models: A Feasibility Study on Lossy Compression for the Spherical Harmonic Transform's Communication Bottleneck",
  "type": "preprint",
  "updated_at": "2026-10-30T12:23:19Z",
  "url": "https://research.draconitic.com/paper/frryajc1n9c0k",
  "venue": "arXiv",
  "versions": []
}