Measured with NVIDIA's Performance tools for Windows and Linux. Timing figure represents time of kernel/function in milliseconds (rounded) on a single GPU. The benchmarks are performed on color images with 8-bits per channel except where mentioned otherwise. The list below is a small subset of 100+ features in CUVI.
Color Pipeline
Let's take a typical color pipeline and see its performance on one of the least powerful GPU modules; Jetson Nano. Any color pipeline almost always starts with the Raw image. Before converting to RGB, you might want to do some processing on the raw which may include applying look up tables, fpn removal and changing white balance. Next comes debayer followed by several further enhancements and a color space conversion to your desired format. This pipeline can perform in real-time on a decent entry level GPU.
Error creating thumbnail: Unable to save thumbnail to destination
Color pipeline where each box represents a function