Dr. Mohammad Nabian
Senior Software Engineer at NVIDIA
NVIDIA
Santa Clara, California

Monday, May 2, 2022
3:30 pm (CT)

Abstract

We present NVIDIA Modulus, a neural network framework that offers building blocks for a developing physics machine learning surrogate models trained using both physics and data. Modulus accelerates stimulations across a wide range of disciplines in science and engineering and addresses a wide range of use cases - coupled forward simulations without any training data, inverse and data assimilation problems, parameterized simulations, super-resolution, etc. Modulus is customizable with API's that enable user extensions to geometry, physics, and network architecture. It has advanced network architectures that are optimized for high- performance GPU computing and offers scalable performance for multi-GPU and multi-Node implementation.