Distributed differentiable rendering for Mitsuba 3

Mitsuba 3 is a research-oriented renderer capable of auto-differentiation and inverse rendering. It currently runs on a single CPU or GPU, hence unable to take advantage of distributed computing or multi-gpu systems. Our work provides a library that overcomes this constraint, allowing both the forward rendering and differentiable rendering to occur on a cluster of machines or multiple GPUs on a single machine. This is exposed to the user using an API similar to that of base Mitsuba. We have also implemented adaptive image-space sampling, allowing the renderer to preferrably spend computational resources on demanding regions of the image, which leads to less noisy images at a fixed computation time compared to traditional rendering.