cuTensorNet: A High-Performance Library for Tensor Network Computations

Welcome to the cuTensorNet library documentation!

NVIDIA cuTensorNet is a high-performance library for tensor network computations, a component of the NVIDIA cuQuantum SDK. Functionalities of cuTensorNet are described in Overview with installation and usage guide provided in Getting Started.

Key Features

  • Based on NVIDIA’s high-performance tensor linear algebra library: cuTENSOR

  • Provides APIs for:

    • Creating a tensor or tensor network object

    • Finding a low-cost contraction path for any given tensor network

    • Finding a low-overhead slicing for the tensor network contraction to meet specified memory constraints

    • Tuning the path finder configuration for better performance

    • Performing tensor network contraction plan auto-tuning and its subsequent execution

    • Performing tensor decomposition using QR or SVD

    • Applying a gate operand to a pair of connected tensors

    • Enabling automatic distributed parallelization in the contraction path finder and executor

    • Enabling custom memory management

    • Logging

Support

  • Supported GPU Architectures: Volta, Ampere, Hopper

  • Supported OS: Linux

  • Supported CPU Architectures: x86_64, ARM64, ppc64le

Prerequisites

Contents