NVIDIA Aerial
NVIDIA Aerial™ is a suite of accelerated computing platforms, software, and services for designing, simulating, and operating wireless networks. Aerial contains hardened RAN software libraries for telcos, cloud service providers (CSPs), and enterprises building commercial 5G networks. Academic and industry researchers can access Aerial on cloud or on-premises setups for advanced wireless and AI/machine learning (ML) research for 6G.
NVIDIA Aerial cuPHY is a cloud-native, software-defined platform optimized to run 5G/6G-compatible gNB physical layer (L1/PHY) workloads on NVIDIA DPU/NIC and GPU hardware. It successfully fulfills the promise of Open RAN by providing the complete source code access for a standards-compliant, multi-vendor interoperable, high-performance solution. Aerial cuPHY has been optimized for commercial deployments providing a competitive total cost of ownership (TCO) when deployed on NVIDIA’s commercial-off-the-shelf (COTS) hardware.
Aerial Omniverse Digital Twin is a large-scale simulation platform that powers physically accurate wireless environments. Aerial Omniverse Digital Twin leverages NVIDIA GPUs to deliver the highest level of performance needed to enable a realistic NDT. This accelerates the evolution of new features in wireless networks by giving you a new paradigm shift to design, test and deploy wireless networks.
Aerial Data Lake can be used in conjunction with the NVIDIA pyAerial library to generate training data for layer-1 pipelines built on neural networks. An Aerial Data Lake database consists of RF samples from a 7.2x fronthaul interface together with layer-2 meta-information to enable database search and query operations. A pyAerial pipeline can access samples from Aerial Data Lake database using the Data Lake Python APIs, and transform that data into training data for any function in the pipeline. Figure 2 illustrates data ingress from a Data Lake database into a pyAerial pipeline and using standard Python file I/O to generate training data for a soft de-mapper.
Aerial cuMAC, a Layer 2 MAC scheduler acceleration library, is developed to improve spectral efficiency by introducing a multi-cell scheduler with enhanced algorithms within Layer 2 of the RAN protocol stack. The MAC scheduler, controls how resources are scheduled for all the user equipments (UEs), across all cells, determining the overall spectral efficiency achieved in each cell. cuMAC will provide a net increase in overall performance per watt measured at the cell level, compared to baseline single cell scheduler approaches. NVIDIA is developing cuMAC on the GPU, to bring efficient MAC scheduler implementations to the telco world.
The NVIDIA Aerial RAN CoLab Over-the-Air (ARC-OTA for short) is a full-featured platform targeted for next generation wireless evolution that eases developer onboarding and algorithm development in real time networks. ARC-OTA equips developers, researchers, operators and network equipment providers with all requisite components necessary to deploy a campus network for research.
pyAerial is a Python library of physical layer components that can be used as part of the workflow in taking a design from simulation to real-time operation. It helps with end-to-end verification of a neural receiver, and helps bridge the gap from the world of training and simulation in TensorFlow/PyTorch to real-time operation in an over-the-air testbed.