NVIDIA Sionna: An Open-Source Library for 6G Physical-Layer Research
Sionna™ is a GPU-accelerated open-source library for link-level simulations. It enables rapid prototyping of complex communication system architectures and provides native support for the integration of machine learning in 6G signal processing.
Key Features
Democratize 6G Research
Sionna implements a wide range of carefully tested state-of-the-art algorithms that can be used for benchmarking and end-to-end performance evaluation. This allows you to focus on your research, making it more impactful and reproducible, while spending less time implementing components outside your area of expertise. Sionna is a valuable tool for physical-layer research on next-generation communication systems, such as 6G.
Supports 5G, 6G, and Much More
Sionna is developed, continuously extended, and used by NVIDIA to drive 5G and 6G physical-layer research. It supports a growing set of features, such as multi-user multiple-input multiple-output (MU-MIMO) link-level simulations with 5G-compliant low-density parity-check (LDPC) and Polar codes, 3GPP TR38.901 channel models and ray tracing, orthogonal frequency-division multiplexing (OFDM), channel estimation, and more.
Modular, Extensible, and Scalable
Every building block is an independent module that can be easily tested, understood, and modified according to your needs. Sionna provides a high-level Python application programming interface (API) to easily model complex communication systems while providing full flexibility to adapt to your research. Based on TensorFlow, Sionna scales automatically across multiple GPUs.
Jumpstart Your Research
Sionna comes with extensive documentation, including many tutorials that help you get started as quickly as possible. Sionna supports NVIDIA GPUs right out of the box, which makes it super fast and perfectly suited for machine learning research in communications.
Benefits
Native AI Support
Sionna is the first fully differentiable link-level simulator, which makes the integration of neural networks a breeze.
Integrated Research Platform
Sionna combines link-level and channel simulation capabilities with native machine learning and GPU support.
Open-Source
Sionna is Python-based, open-source, and welcomes contributions from third parties.