{
  "abstract": "In this manuscript we outline a computational strategy to leverage a vendor-optimized implementation of the Ozaki scheme I for floating point emulation as part of an implementation of the Transpose-Transpose-GEMM-Transpose (TTGT) pattern for tensor contractions, and assess its potential to accelerate two of the most expensive tensor contractions appearing in relativistic coupled cluster theory in high-end accelerators such as the NVIDIA Blackwell B200 system in which there is a strong differential in the performance of computations for double and lower precision datatypes. Our results indicate that this emulation-based TTGT strategy can provide significant speedups compared to runs without emulation, and can be competitive with state-of-the-art, vendor-optimized tensor contraction libraries using native double precision as compute datatype. More importantly, our scheme provides a path towards easily allowing users to tune the desired accuracy in the tensor contraction steps, including cases where precision between single and double is sufficient for the application.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2611.06533",
  "author_total": 4,
  "authors": [
    {
      "name": "Maxime Le"
    },
    {
      "name": "Ryan Benazzouk"
    },
    {
      "name": "Jan Brandejs"
    },
    {
      "name": "Andre Severo Pereira Gomes"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/648y9wc1p6afe.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2611.06533",
  "fulltext_url": null,
  "id": "648y9wc1p6afe",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2611.06533",
  "language": null,
  "licence": "CC-BY-SA-4.0",
  "licence_label": "CC BY-SA 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-sa/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "physics.chem-ph"
    ]
  ],
  "openalex": null,
  "pdf_url": "https://arxiv.org/pdf/2611.06533",
  "pmcid": null,
  "pmid": null,
  "published": "2026-11-04",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/648y9wc1p6afe.ris",
  "sources": [
    {
      "first_seen": "2026-11-05T15:20:56Z",
      "native_id": "2611.06533",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2611.06533"
    }
  ],
  "subjects": [
    {
      "field": "chemistry",
      "origin": "arxiv:physics.chem-ph",
      "subfield": "physical"
    }
  ],
  "title": "Exploiting floating point emulation in tensor contractions in relativistic coupled cluster theory",
  "title_text": "Exploiting floating point emulation in tensor contractions in relativistic coupled cluster theory",
  "type": "preprint",
  "updated_at": "2026-11-09T00:20:20Z",
  "url": "https://research.draconitic.com/paper/648y9wc1p6afe",
  "venue": "arXiv",
  "versions": []
}