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)?
Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries (“Qualcomm”). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.
OpenGL-ES is limited by having a single active rendering thread. Multiple OpenGLES contexts may be helpful for bookkeeping purposes but there's no feasible way to avoid having synchronous processing with the GPU.
Vulkan offers advantanges in this area, if it makes sense in your case to port/develop the applicaiton to the new API.
Seems like you asked the same question in the Mali developer forum...and the answer remains the same. OpenGL ES behaves differently from the newer graphics API like Vulkan in that most of the finer grain control is in the driver not at the API level.