BOOTCAMP: NVIDIA/HLRS SciML GPU Bootcamp

All communication will be done through Zoom, Slack and email.

Deep Learning (DL) has revolutionized the way of performing classification, pattern recognition, and regression tasks in various application areas. Scientific applications solving linear and non-linear equations with demanding accuracy and computational performance requirements can use a class of DL networks, called Physics-Informed Neural Networks (PINN). In fact, PINNs are specifically designed to integrate scientific computing equations, such as Ordinary Differential Equations (ODE), Partial Differential Equations (PDE), non-linear, and integral-differential equations into the DL network training.

This workshop introduces Scientific Machine Learning (SciML) with PINN and provides hands-on experience with the PDE solver NVIDIA Modulus, a neural network framework that blends the power of physics in the form of governing partial differential equations (PDEs) with data to build high-fidelity, parameterized surrogate models with near-real-time latency. This online Bootcamp is a hands-on learning experience where you will be guided through step-by-step instructions with teaching assistants on hand to help throughout.

The Bootcamp is co-organised by HLRS, OpenACC.org and NVIDIA for GCS, the Gauss Centre for Supercomputing.

Location

Online course
Organizer: HLRS, University of Stuttgart, Germany

Registration

Start date

Apr 26, 2023
09:00

End date

Apr 27, 2023
17:30

Language

English

Entry level

Intermediate

Course subject areas

Domain-Specific Courses

Simulation

Data in HPC / Deep Learning / Machine Learning

Topics

Artificial Intelligence

Big Data

Deep Learning

Machine Learning

Scientific Machine Learning

Back to list

Prerequisites and content levels

Prerequisites

Basic experience with Python. No GPU programming experience is required.
Some knowledge in PDE theory (e.g. weak formulation).

Content levels

Intermediate level: 3 hours
Advanced level: 7 hours

Learn more about course curricula and content levels.

Instructors

Dr. Niki Andreas Loppi (NVIDIA) - Lead instructor.

Dr. Mozhgan Kabiri Chimeh (NVIDIA).

Dr. Tobias Haas, Dr. Lorenzo Zanon, Dr. Khatuna Kakhiani (HLRS).

Agenda

(Subject to Change)

All times in CEST

Day 1 - Wednesday, April 26, 2023: 09:00 AM - 12:30 PM

09:00 AM - 09:15 AM: Welcome (Moderator and Host)
09:15 AM - 10:15 AM: Invited Talk by Dr. Alexander Heinlein, Delft University of Technology (TU Delft)
- Title: Neural networks with physical constraints, domain decomposition-based network architectures, and model order reduction
10:20 AM - 11:20 AM: Invited Talk by Dr. Clement Etienam, NVIDIA
- Title: An Accelerated Reservoir Inverse Modelling Workflow with NVIDIA’s Modulus
11:20 AM - 11:30 AM: Break
11:30 AM - 12:30 PM: Connecting to a Cluster

Day 2 - Thursday, April 27, 2023: 09:00 AM - 05:30 PM

09:00 AM - 09:05 AM: Welcome (Moderator and Host)
09:05 AM - 09:35 AM: Introduction: Data Driven vs PINN Approach (Lecture)
09:35 AM - 10:05 AM: What is NVIDIA Modulus? (Lecture)
10:05 AM - 11:35 AM: Lab 1: Solving Partial Differential Equations using Modulus
11:35 AM - 12:30 PM: Lab 2: Solving Transient Problems and Inverse Problems using Modulus
12:30 PM - 01:30 PM: Lunch Break
01:30 PM - 02:00 PM: Lab 2 (Continued)
02:00 PM - 05:15 PM: Mini Challenge
05:15 PM - 05:30 PM: Wrap up and Q&A

Hands-on sessions

Attendees will be given access to a GPU cluster for the duration of the Bootcamp.

The code is publicly available on github (tba).

Registration information

This course is offered in cooperation by HLRS, OpenACC.org and NVIDIA. Registration is done via www.openhackathons.org hosted by OpenACC-Standard.org. Your registration data will be transferred to these partners. For legal notes see the Privacy Policy.

Registration deadline: 05/04/2023.