Tensor Algebra Processing Primitives (TAPP): Towards a Standard for Tensor Operations

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Brandejs, Jan, Hörnblad, Niklas, Valeev, Edward F., Heinecke, Alexander, Hammond, Jeff, Matthews, Devin, Bientinesi, Paolo
Formato: Preprint
Publicado: 2026
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866918284245336064
author Brandejs, Jan
Hörnblad, Niklas
Valeev, Edward F.
Heinecke, Alexander
Hammond, Jeff
Matthews, Devin
Bientinesi, Paolo
author_facet Brandejs, Jan
Hörnblad, Niklas
Valeev, Edward F.
Heinecke, Alexander
Hammond, Jeff
Matthews, Devin
Bientinesi, Paolo
contents To address the absence of a universal standard interface for tensor operations, we introduce the Tensor Algebra Processing Primitives (TAPP), a C-based interface designed to decouple the application layer from hardware-specific implementations. We provide a mathematical formulation of tensor contractions and a reference implementation to ensure correctness and facilitate the validation of optimized kernels. Developed through community consensus involving academic and industrial stakeholders, TAPP aims to enable performance portability and resolving dependency challenges. The viability of the standard is demonstrated through successful integrations with the TBLIS and cuTENSOR libraries, as well as the DIRAC quantum chemistry package.
format Preprint
id arxiv_https___arxiv_org_abs_2601_07827
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Tensor Algebra Processing Primitives (TAPP): Towards a Standard for Tensor Operations
Brandejs, Jan
Hörnblad, Niklas
Valeev, Edward F.
Heinecke, Alexander
Hammond, Jeff
Matthews, Devin
Bientinesi, Paolo
Mathematical Software
To address the absence of a universal standard interface for tensor operations, we introduce the Tensor Algebra Processing Primitives (TAPP), a C-based interface designed to decouple the application layer from hardware-specific implementations. We provide a mathematical formulation of tensor contractions and a reference implementation to ensure correctness and facilitate the validation of optimized kernels. Developed through community consensus involving academic and industrial stakeholders, TAPP aims to enable performance portability and resolving dependency challenges. The viability of the standard is demonstrated through successful integrations with the TBLIS and cuTENSOR libraries, as well as the DIRAC quantum chemistry package.
title Tensor Algebra Processing Primitives (TAPP): Towards a Standard for Tensor Operations
topic Mathematical Software
url https://arxiv.org/abs/2601.07827