Skip to yearly menu bar Skip to main content


Poster
in
Workshop: Beyond Bayes: Paths Towards Universal Reasoning Systems

P21: Reverse-Mode Automatic Differentiation and Optimization of GPU Kernels via Enzyme

William Moses


Abstract:

Authors: William S. Moses, Valentin Churavy, Ludger Paehler, Jan Hückelheim, Sri Hari Krishna Narayanan, Michel Schanen, Johannes Doerfert

originally published at SC '21

Abstract: Computing derivatives is key to many algorithms in scientific computing and machine learning such as optimization, uncertainty quantification, and stability analysis. Enzyme is a LLVM compiler plugin that performs reverse-mode automatic differentiation (AD) and thus generates high performance gradients of programs in languages including C/C++, Fortran, Julia, and Rust. Prior to this work, Enzyme and other AD tools were not capable of generating gradients of GPU kernels. Our paper presents a combination of novel techniques that make Enzyme the first fully automatic reversemode AD tool to generate gradients of GPU kernels. Since unlike other tools Enzyme performs automatic differentiation within a general-purpose compiler, we are able to introduce several novel GPU and AD-specific optimizations. To show the generality and efficiency of our approach, we compute gradients of five GPU-based HPC applications, executed on NVIDIA and AMD GPUs. All benchmarks run within an order of magnitude of the original program’s execution time. Without GPU and AD-specific optimizations, gradients of GPU kernels either fail to run from a lack of resources or have infeasible overhead. Finally, we demonstrate that increasing the problem size by either increasing the number of threads or increasing the work per thread, does not substantially impact the overhead from differentiation.

Chat is not available.