Bridges-2 Webinar Series

2024 Webinars

A Hands-On Introduction to Quantum Computing with NVIDIA’s CUDA Quantum

Date: April 19, 2024, 1-2pm ET

Dr. Pooja Rao, NVIDIA

Quantum computing leverages the quantum aspects of the physical world to introduce novel methods of information processing. These methods can be combined with classical high-performance computing to build scalable and performant applications. In this hands-on workshop, we will explore the fundamentals of quantum computing and apply them to construct quantum applications. As future workloads are anticipated to be mostly hybrid, the workshop will also introduce tools for interfacing quantum and classical components through a commonly used machine learning workflow. For this workshop, we will use Bridges-2 to demonstrate the Python API of NVIDIA’s CUDA Quantum, an open-source hybrid platform that integrates CPU, GPU, and QPU (quantum processing unit) computing while abstracting away the complexity of this integration from the user.

About the presenter: Dr. Pooja Rao is a Senior Quantum Application Engineer at NVIDIA, specializing in the intersection of quantum and high-performance computing. Her primary interests lie in quantum-assisted machine learning and leveraging quantum computing for fluid applications. During her doctoral and postdoctoral research, she focused on developing numerical methods and computational algorithms to simulate fluid flow across diverse scales and in various contexts. Her work ranged from turbulence modeling of fluid instabilities encountered in inertial confinement fusion to simulating fluid-particle transfer phenomena in multi-scale aerospace applications.

2023 Webinars

Parallel Physics-informed Neural Networks via Domain Decomposition

Date: January 25, 2023, 1 pm – 2 pm Eastern time

During this webinar, a team from Brown University presented a parallel algorithm for conservative PINNs and extended PINNs constructed with a hybrid programming model described by MPI + X, where X ∈{CPUs ,GPUs}.

Multi-GPU MuST

Date: April 19, 2023, 1 pm – 2 pm Eastern time

The MuST package is computational software designed for ab-initio electronic structure calculations for solids. This webinar will  describe how to accelerate electronic structure calculations using MuST on multiple GPUs on Bridges-2.

GROMACS on Bridges-2: Optimizing Job Scripts for Performance and Efficiency

Date: June 9, 2 pm – 3 pm Eastern time

This webinar will discuss the run-time options that can affect the performance of a GROMACS job on Bridges-2.

Data-driven computational pipelines

Date: June 26, 2023, 2 pm – 3 pm Eastern time

This webinar reviews frameworks which can empower researchers to build robust and scalable data-driven computational pipelines on Bridges-2.

Utilizing Bridges-2 for Deep Learning Distributed Training

Date: September 26, 2023, 1 pm – 2 pm Eastern time

We will show how to deploy multi-GPU training for deep learning applications, such as with Pytorch and Tensorflow frameworks, using Bridges-2. Topics include how to modify code to run training on a single node or multiple nodes, how to set up an environment, how to run jobs in either interactive or batch mode or with a Jupyter notebook, and factors that affect performance.  

 

 

Parallel Physics-informed Neural Networks via Domain Decomposition

Date: January 25, 2023, 1 pm – 2 pm Eastern time

During this webinar, a team from Brown University presented a parallel algorithm for conservative PINNs and extended PINNs constructed with a hybrid programming model described by MPI + X, where X ∈{CPUs ,GPUs}.

​Multi-GPU MuST

Date: April 19, 2023, 1 pm – 2 pm Eastern time

The MuST package is computational software designed for ab-initio electronic structure calculations for solids. This webinar will  describe how to accelerate electronic structure calculations using MuST on multiple GPUs on Bridges-2.

​GROMACS on Bridges-2: Optimizing Job Scripts for Performance and Efficiency

Date: June 9, 2 pm – 3 pm Eastern time

This webinar will discuss the run-time options that can affect the performance of a GROMACS job on Bridges-2.

 

Data-driven computational pipelines

Date: June 26, 2023, 2 pm – 3 pm Eastern time

This webinar reviews frameworks which can empower researchers to build robust and scalable data-driven computational pipelines on Bridges-2.

 

Utilizing Bridges-2 for Deep Learning Distributed Training

Date: September 26, 2023, 1 pm – 2 pm Eastern time

We will show how to deploy multi-GPU training for deep learning applications, such as with Pytorch and Tensorflow frameworks, using Bridges-2. Topics include how to modify code to run training on a single node or multiple nodes, how to set up an environment, how to run jobs in either interactive or batch mode or with a Jupyter notebook, and factors that affect performance.