Currently, AMD's existing FSR upscaling technology relies on a spatial upscaler that utilizes AMD's Edge-Adaptive Spatial Upsampling and Robust Contrast-Adaptive Sharpening.
Nope. Only FSR 1 relied on spatial upscaling, without relying on other data such as frame history or motion vectors. FSR 2 supports temporal data.
Current-gen FSR 3 technology also uses a combination of super resolution temporal upscaling technology and frame generation/FG.
Nonetheless, with the introduction of AMD's XDNA NPUs in its latest Ryzen desktop and mobile APUs, it makes sense that AMD would go this route. Adding AI to all of its software portfolio will help increase the adoption rate of its new NPU-equipped APUs.
If AMD is building its AI-flavored version of FSR for its XDNA NPUs, it might only support Ryzen 8000 series mobile CPUs and Ryzen 8000 series desktop APUs.
You do realize that
apart from NPUs (for accelerated AI enablement), we also have Radeon RX 7000 series RDNA 3 GPUs with
AI accelerators ?
Current-gen RDNA 3 sports dedicated AI acceleration with Wave MMA (matrix multiply-accumulate) instructions, which can help improve AI-based performance and also benefits ray tracing instructions, similar to Nvidia's Tensor cores.
So will future
next-gen iterations of the RDNA arch GPUs, where AI-based upscaling might help.