Computing derivatives is key to many algorithms in scientific computing and machine
learning such as optimization, uncertainty quantification, and stability analysis. Enzyme is a …

Derivatives are key to numerous science, engineering, and machine learning applications.
While existing tools generate derivatives of programs in a single language, modern parallel …

This article presents our work toward correct and efficient automatic differentiation of
OpenMP parallel worksharing loops in forward and reverse mode. Automatic differentiation …

Stencil loops are a common motif in computations including convolutional neural networks,
structured-mesh solvers for partial differential equations, and image processing. Stencil …

The open-source multiphysics suite SU2 features discrete adjoints by means of operator
overloading automatic differentiation (AD). While both primal and discrete adjoint solvers …

Automatic differentiation (AD) is a technique for computing the derivative of function F: R n→
R m defined by a computer program. Modern applications of AD, such as machine learning …

Algorithmic differentiation (AD) is a tool for generating discrete adjoint solvers, which
efficiently compute gradients of functions with many inputs, for example for use in gradient …

We present the new software OpDiLib, a universal add-on for classical operator overloading
AD tools that enables the automatic differentiation (AD) of OpenMP parallelized code. With it …

We present Zygote, an algorithmic differentiation (AD) system for the Julia language. Zygote
is designed to address the needs of both the machine learning and scientific computing …

This paper presents a novel combination of reverse mode automatic differentiation and
formal methods, to enable efficient differentiation of (or backpropagation through) shared …