Work

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

Year: 2026

Type: preprint

Abstract: 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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2601.07827

Authors: Brandejs, Jan, Hörnblad, Niklas, Valeev, Edward F., Heinecke, Alexander, Hammond, Jeff, Matthews, Devin, Bientinesi, Paolo

Institutions: Centre National de la Recherche Scientifique, Laboratoire de Chimie et Physique Quantiques, Umeå University, Southern Methodist University, Virginia Tech, Nvidia (United States)

Topic: Parallel Computing and Optimization Techniques

Subfield: Hardware and Architecture

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

Funders: National Science Foundation, U.S. Department of Energy, European Commission, Division of Chemistry

Awards: CAREER: Tensor Factorization Methods for High-Level Electronic Structure Theory, Collaborative Research: PPoSS: Large: A comprehensive framework for efficient, scalable, and performance-portable tensor applications, G434337789, PRACTICAL TENSOR HYPERCONTRACTION COUPLED CLUSTER METHODS FOR EXCITED STATE DYNAMICS, NUMERICALLY-EXACT RELATIVISTIC MANY-BODY ELECTRONIC STRUCTURE OF HEAVY ELEMENTS, G5877418170, G6128383262, G774187239

OpenAlex ID: W7123920918

Cites:

Cited by: 1

Related to: