Learned from https://docs.nvidia.com/vpi/architecture.html

The Programmable Vision Accelerator (PVA) is a processor in NVIDIA® Jetson AGX Xavier™ and NVIDIA® Jetson Xavier™ NX devices that is specialized for image processing and computer vision algorithms.

Use the PVA backend when you need to leave the GPU free to run other tasks that only it can perform, such as deep learning inference stages and algorithms only implemented on CUDA backend.

PVA hardware is much more power-efficient than CPU and CUDA hardware. Therefore, use the PVA backend where possible if power is at a premium.

Each Jetson AGX Xavier or Jetson Xavier NX device comprises two PVA processors, each one contains two vector processors. Therefore, the device can execute at most four independent PVA tasks concurrently.

When multiple VPI streams have the PVA backend enabled, they each choose one available PVA vector processor in round-robin succession.


A PVA backend is not necessarily faster than a CUDA or CPU backend for any particular algorithm.