Explore featured sessions for High Performance Computing.

From weather forecasting and energy exploration to computational chemistry and molecular dynamics, NVIDIA HPC technologies optimize over 1800 applications across scientific domains and industries. Users can tap into GPU-powered parallel processing and InfiniBand Networking to accelerate advanced, large-scale applications, paving the way to scientific discovery.


Jensen Huang | NVIDIA | Founder and CEO

Watch the keynote replay to hear Jensen Huang's insight into how NVIDIA is driving the rapid pace of technology advancements to help solve the world's toughest challenges.

Featured Speakers

Tim Costa

A Deep Dive into the Latest HPC Software

Tim Costa 
Group Product Manager, HPC Software, NVIDIA

Linfeng Zhang

AI-Assisted Physical Modeling in the Cloud-Native Era

Linfeng Zhang
Chief Scientific Officer, DP Technology

Zoe Ryan

GPU Acceleration in Python using CuPy and Numba

Zoe Ryan
Solutions Architect, NVIDIA

Jack Deslippe

Early Science Results on the NERSC Perlmutter NVIDIA A100-Powered HPC System

Jack Deslippe
Application Performance Group Leader, NERSC

Sessions By Topic

HPC - Supercomputing

  • Accelerated Computing for the Era of Exascale AI

    • Ian Buck, Vice President and General Manager of Accelerated Computing, NVIDIA

    Discover the possibility, power, and performance of AI computing from concept to reality. NVIDIA's Ian Buck, vice president of accelerated computing, will provide an in-depth overview of the latest news, innovations, and technologies that will help companies, industries, and nations reap the benefits of exascale AI supercomputing.

  • Physics-informed Neural Networks for Wave Propagation Using NVIDIA SimNet

    • Harpreet Sethi, Ph.D. Student, Colorado School of Mines

    Recent developments in physics-informed neural networks (PINNs) — neural networks that are trained using the loss functions in the form of PDEs — have shown promising results for computing the numerical solutions of partial differential equations. In this work, we study the accuracy and performance of PINNs using NVIDIA SimNet, an AI-accelerated simulation toolkit, for solving wave equations.

  • Advancing Scientific Discoveries with AI

    • Bharatkumar Sharma, GPU Advocate, NVIDIA
    • Alankar Alankar, Associate Professor, Indian Institute of Technology Bombay
    • Souvik Chakraborty, Assistant Professor, Indian Institute of Technology Delhi

    Convergence of HPC and AI has evolved with a new set of methods to complement conventional modeling and simulation to increase the potential to solve science’s greatest challenges. This panel discussion will focus on the necessity to develop and teach AI to students of the scientific community. We'll cover results achieved in different scientific domains like climate, computational fluid dynamics, molecular dynamics, and many more.

  • JUWELS Booster: Early Experience with the System

    • Andreas Herten, Researcher GPUs in HPC, Jülich Supercomputing Centre

    In November 2020, the first Booster module of the JUWELS supercomputer was put into production, providing more than 70 petaFLOP per second performance through 3,744 A100 GPUs, connected with InfiniBand HDR200 in a DragonFly+ topology. We'll present JUWELS Booster and the unique features of Europe's fastest supercomputer. We'll show experiences from working together with developers and highlight notable scientific results.

HPC - Climate / Weather / Ocean Modeling

  • Progress and Challenges for Using Machine Learning in Weather and Climate Prediction

    • Peter Dueben, AI and Machine Learning Coordinator and Royal Society University Research Fellow, European Centre for Medium-Range Weather Forecasts

    This session will provide an overview on machine learning efforts at the European Centre for Medium Range Weather Forecasts. It will also discuss the challenges that need to be addressed to make the most of machine learning in the next five years in order to improve predictions and enhance our understanding of the Earth system.

  • Citizen Scientists Tackling Devastating Floods and Disaster Relief with Semi-supervised Deep Learning

    • Siddha Ganju, Data Scientist, NVIDIA
    • Sayak Paul, Deep Learning Associate, PyImageSearch

    A citizen science team devised a semi-supervised based pseudo-labeling solution for the NASA IMPACT flood segmentation challenge. Manually annotating of Sentinel-1 satellite imagery datasets is expensive, cumbersome, and often not scalable for petabytes worth of data captured by satellites every day. The team used NVIDIA V100 GPUs for training on the Google Cloud Platform and released all the code and trained models in open source, encouraging future citizen scientists to join the climate security challenge.

  • Global Climate Action

    • Geoffrey Levene, Director, World Wide AI Initiatives, NVIDIA
    • Sertac Karaman, Director, Laboratory for Information and Decision Systems, Massachusetts Institute of Technology (MIT)
    • Zac Flamig, Tech Lead, Amazon Sustainability Data Initiative, Amazon Web Services

    Learn how NVIDIA is developing partnerships with the Massachusetts Institute of Technology to create climate science IP through a worldwide consortium of public and private sector entitles and Amazon Web Services' Sustainable Data Initiative to provide all climate scientists in the world with the right data at the right time.

HPC - Scientific Visualization

  • A Tour of the New, Emerging ANARI Standard from Khronos

    • Jefferson Amstutz, Senior Software Engineer, NVIDIA

    This talk will provide an overview of the new ANARI API standard from Khronos — why it was created, and what the API looks like for developers. 3D rendering has a long history of innovation, with a large array of application domains that push the limits of hardware capability to deliver beautiful imagery. ANARI is a common front-end interface library that takes in-memory scene data and dispatches it to an underlying rendering engine.

  • NVIDIA IndeX in Omniverse: Scientific Visualization and Photo-real Depictions of Volume Data in a Collaborative Environment

    • Marc Nienhaus, Director, NVIDIA IndeX Product Technology, NVIDIA

    Scientific visualization focuses on generating images that convey the structure and the information inherent in complex, often large-scale data to assist scientists in their reasoning and decision-making processes. At the same time, photo-real depictions of the scientific data are essential for the scientists to publish their research results, ease communicating their findings to a wider audience, and promote the research work. NVIDIA IndeX in Omniverse enables the interactive scientific visualization and photo-real image generation of large-scale, complex volume data. 

Explore All Session Topics

NVIDIA Developer Program

Get the advanced tools and training you need to successfully build applications on all NVIDIA technology platforms.

Accelerate your Startup

Explore the startup track at GTC to learn how NVIDIA Inception can fuel your growth through go-to-market support, world-class training, and technology assistance.

Get Hands-On Training

Interested in developing key skills in AI, accelerated data science, or accelerated computing? Get hands-on instructor-led training from the NVIDIA Deep Learning Institute (DLI) and earn a certificate demonstrating subject matter competency.