Sionna: An Open-Source Library for Next-Generation Physical Layer Research

TL;DR

Sionna addresses the need for fast, differentiable, and reproducible link-level simulations for 6G research by providing a GPU-accelerated, TensorFlow-based framework with modular, differentiable layers and a broad set of state-of-the-art algorithms. Its design emphasizes tensor-based computation, end-to-end learning, and native NN integration, enabling rapid prototyping and rigorous benchmarking. Planned extensions include an integrated ray tracer and custom CUDA kernels to support environment-specific channels, further bridging research and real-world deployment. Overall, Sionna aims to accelerate exploration of next-generation wireless concepts (e.g., RIS, THz, sensing) by offering scalable, end-to-end, differentiable simulations with community-driven growth.

Abstract

Sionna is a GPU-accelerated open-source library for link-level simulations based on TensorFlow. It enables the rapid prototyping of complex communication system architectures and provides native support for the integration of neural networks. Sionna implements a wide breadth of carefully tested state-of-the-art algorithms that can be used for benchmarking and end-to-end performance evaluation. This allows researchers to focus on their research, making it more impactful and reproducible, while saving time implementing components outside their area of expertise. This white paper provides a brief introduction to Sionna, explains its design principles and features, as well as future extensions, such as integrated ray tracing and custom CUDA kernels. We believe that Sionna is a valuable tool for research on next-generation communication systems, such as 6G, and we welcome contributions from our community.

Figures (1)

• Figure 1: Example of a coverage map (path gain [dB]) and ray-traced propagation paths rendered on top of a scene by Sionna RT.