For Intel+NVIDIA dual-GPU "Optimus" setups, an application can export NvOptimusEnablement
as explained in OptimusRenderingPolicies.pdf. This option allows an application to ensure the use of the high-speed discrete GPU without needing profile updates or user interaction, which is usually desired for certain classes of applictions.
Is there an equivalent trick for systems with AMD GPUs (Windows-only is fine), and if so, what is it? I have not been able to find any concrete information via Googling; only a lot of people asking the same question on various forums with no answers, or SO articles on the NVIDIA trick with a "maybe AMD has something similar, I don't know" comment.