The landscape of software for tensor computations
arXiv:2103.13756
Abstract
Tensors (also commonly seen as multi-linear operators or as multi-dimensional arrays) are ubiquitous in scientific computing and in data science, and so are the software efforts for tensor operations. Particularly in recent years, we have observed an explosion in libraries, compilers, packages, and toolboxes; unfortunately these efforts are very much scattered among the different scientific domains, and inevitably suffer from replication, suboptimal implementations, and in many cases, limited visibility. As a first step towards countering these inefficiencies, here we survey and loosely classify software packages related to tensor computations. Our aim is to assemble a comprehensive and up-to-date snapshot of the tensor software landscape, with the intention of helping both users and developers. Aware of the difficulties inherent in any multi-discipline survey, we very much welcome the reader's help in amending and expanding our software list, which currently features 80 projects.
References in corpus (8)
- PyTorch: An Imperative Style, High-Performance Deep Learning Library
- The ITensor Software Library for Tensor Network Calculations
- DFacTo: Distributed Factorization of Tensors
- TensorNetwork: A Library for Physics and Machine Learning
- A High-Performance Sparse Tensor Algebra Compiler in Multi-Level IR
- On the Performance Prediction of BLAS-based Tensor Contractions
- TensorTrace: an application to contract tensor networks
- A Fast Implementation for the Canonical Polyadic Decomposition