Dr.Jit: A Just-In-Time Compiler for Differentiable Rendering

TL;DR

Dr.Jit is a just-in-time compiler that accelerates physically based rendering and its derivatives by optimizing high-level code and simplifying the development of differentiable rendering algorithms, enabling faster research and more efficient computations.

Contribution

It introduces a JIT compiler that traces and specializes simulation code, and provides fine-grained control over automatic differentiation for differentiable rendering.

Findings

Achieves state-of-the-art performance on CPUs and GPUs.

Reduces redundant computations in differentiation processes.

Facilitates development of differentiable rendering algorithms.

Abstract

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.