Report on the second Toulouse Tensor Workshop

TL;DR

The paper reports the second Toulouse Tensor Workshop, which centers on standardizing tensor contractions via the Tensor Algebra Processing Primitives (TAPP) interface following the 2024 workshop. It documents the formation and progress of the TAPP-WG, the publication of a detailed whitepaper describing the reference implementation, and a DIRAC use case illustrating Fortran bindings and integration with a high-level einsum workflow. It presents a tensor contraction survey showing contractions are performance-critical, sparsity and symmetries are key, and adoption as a backend (e.g., NumPy/PyTorch) is a viable path. It also outlines plans to extend standardization to a higher-level interface, prioritize block sparsity on single-node platforms, and postpone distributed-memory standardization while maintaining WG-driven collaboration and community feedback.

Abstract

This report documents the program of the second Toulouse Tensor Workshop which took place at the University of Toulouse on September 17-19, 2025, and summarizes the main points of discussion. This workshop follows the first Workshop (CECAM workshop on Tensor Contraction Library Standardization), which took place in Toulouse one year earlier, on May 24-25, 2024 and led to the formation of a tensor standardization working group, which has since specified a low-level standard interface for tensor operations available freely on GitHub. The 2025 workshop brought together developers of applications which rely extensively on tensor computations such as quantum many-body simulations in chemistry and physics (material science and electronic structure calculations), as well as developers and experts of tensor software who have the know-how to provide the technical support for such applications. The workshop enabled the community to provide feedback on the specified low-level interface and how it can be further refined. It also initiated a discussion on how the standardization efforts should be oriented in the near feature, in particular on what should be higher-level interfaces and how to tackle other requirements of the community such as tensor decompositions, symmetric tensors and structured sparsity support.