How are multiple OpenGL ES contexts handled? That is, for the same application. Does one have some kind of control over scheduling? Would it be efficient GPU wise to have some compute shader launched from one context while shadow map rendering is launched from an another one (assuming compute shader is indeed ALU bound and not bandwidth bound)?
You don't get any additional control over GPU scheduling using multiple contexts; the only real advantage is that you can use multiple CPU cores to generate the GPU workloads.
Thanks.