Dr.Jit: A Just-In-Time Compiler for Differentiable Rendering
For researchers in physically based rendering and differentiable rendering, Dr.Jit provides a tool that combines high performance with ease of development, addressing the bottleneck of efficient derivative computation.
Dr.Jit is a just-in-time compiler for physically based rendering that achieves state-of-the-art performance on CPUs and GPUs by specializing and simplifying high-level simulation code, and it simplifies differentiable rendering by providing fine-grained control over automatic differentiation and globally tracking data dependencies to remove redundant computation.
Dr$.$Jit is a new just-in-time compiler for physically based rendering and its derivative. Dr$.$Jit expedites research on these topics in two ways: first, it traces high-level simulation code (e.g., written in Python) and aggressively simplifies and specializes the resulting program representation, producing data-parallel kernels with state-of-the-art performance on CPUs and GPUs. Second, it simplifies the development of differentiable rendering algorithms. Efficient methods in this area turn the derivative of a simulation into a simulation of the derivative. Dr$.$Jit provides fine-grained control over the process of automatic differentiation to help with this transformation. Specialization is particularly helpful in the context of differentiation, since large parts of the simulation ultimately do not influence the computed gradients. Dr$.$Jit tracks data dependencies globally to find and remove redundant computation.