Comment by kllrnohj

Not many GPUs support full pre-emption. And by "not many" I mean like Nvidia desktop GPUs only added this shockingly recently ( specifically with Pascal generation: https://docs.nvidia.com/cuda/pascal-tuning-guide/index.html#... )

Otherwise GPUs typically do context "pre-emption" by basically being cooperative and just injecting yield statements in the command queue or on things like tile boundaries for tile based renderers. So the smallest chunk of work they can yield between ends up actually being quite large, and with a full user-supplied program in the middle