Aerial cuBB

The NVIDIA cuBB SDK provides GPU accelerated 5G signal processing pipeline including cuPHY for Layer 1 PHY, cuMAC for L2 scheduler, delivering unprecedented throughput and efficiency by keeping all the processing within the high-performance GPU memory.

Aerial cuBB is a software-defined, scalable, modular, highly programmable and cloud-native, without any fixed function accelerators. Enables the ecosystem to flexibly adopt necessary modules for their commercial products.

Aerial cuBB has the following key components:

• cuPHY: L1 library of the Aerial CUDA-Accelerated RAN. It is designed as an inline accelerator to run on NVIDIA GPUs and it does not require any additional hardware accelerator.

• cuMAC: L2 MAC Scheduler library of the Aerial CUDA-Accelerated RAN for accelerating 5G/6G MAC layer scheduler functions with NVIDIA GPUs.