This site requires Javascript in order to view all its content. Please enable Javascript in order to access all the functionality of this web site. Here are the instructions how to enable JavaScript in your web browser.

NVIDIA at SC21

SC21

November 14–19, 2021

Add to calendar

Join us online at Supercomputing 2021 (SC21) to see how GPU computing and high-performance networking are transforming computational science and AI. We’ll feature a virtual theater with speakers from leading industries and domains, along with demos, related content, and more. Stay tuned for more information.

Schedule at a Glance

At SC21, explore a range of groundbreaking work in the field of accelerated computing. Take a closer look at the scheduled NVIDIA sessions that are part of this year’s program.

Tutorials and Workshops
Programs and Exhibits

Sunday 11/14	Monday 11/15	Tuesday 11/16	Wednesday 11/7	Thursday 11/18	Friday 11/19
Deep Learning at Scale 8:00 a.m.–5:00 p.m. CST \| Tutorial					PEHC: Programming Environments for Heterogeneous Computing 8:30 a.m.–12:00 p.m. CST \| Workshop
Efficient Distributed GPU Programming for Exascale 8:00 a.m.–5:00 p.m. CST \| Tutorial
Performance Tuning with the Roofline Model on GPUs and CPUs 8:00 a.m.–5:00 p.m. CST \| Tutorial
P3HPC: 2021 International Workshop on Performance, Portability, and Productivity in HPC 9:00 a.m.–5:30 p.m. CST \| Workshop	7th Workshop on Machine Learning in High-Performance Environments 9:00 a.m.–5:30 p.m. CST \| Workshop

Sunday 11/14	Monday 11/15	Tuesday 11/16	Wednesday 11/17	Thursday 11/18	Friday 11/19
					SmartNICs: The Future or Folly? 8:30 a.m.–10:00 a.m. CST \| Panel
		Beyond the Hype: Is There a Typical AI/ML Storage Workload? 10:30 a.m.–2:00 p.m. CST \| Panel		Resource Disaggregation in High-Performance Computing 10:30 a.m.–12:00 p.m. CST \| Panel
		Heterogeneity in Hardware: Opportunities and Challenges for Software and Applications 10:30 a.m.–12:00 p.m. CST \| Panel
			Efficient Large-Scale Language Model Training on GPU Clusters Using Megatron-LM 1:30 p.m.–2:00 p.m. CST \| Paper
		Non-Recurring Engineering (NRE) Best Practices: A Case Study with the NERSC/NVIDIA OpenMP Contract 3:30 p.m.–4:00 p.m. CST \| Paper

Virtual Theater

Hear from industry leaders, scientists, and researchers as they explain their groundbreaking work utilizing GPU and high-performance InfiniBand networking technologies. Tune in during the week of November 15 to watch short, on-demand talks at your own pace.

High-Performance InfiniBand Networking Technologies

Featured Demos

In a series of live and recorded demos, explore how NVIDIA technologies are transforming a variety of industries with new capabilities—highlighting the latest breakthroughs in AI, HPC, accelerated data science, healthcare, visualization, and more. Tune in during the week of November 15 to watch short, on-demand talks at your own pace.

Developer Zone

Changing the World, One Line of Code at a Time

We believe that developers are the inspired, technical minds transforming the world around us with new innovations. Whether they’re tackling challenges at the cutting edge of physics or trying to tame a worldwide pandemic, developers are problem solvers. NVIDIA developers are pursuing more breakthroughs than ever before and solving our most challenging problems.

Join

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

Join the NVIDIA Developer Program

Learn

Get the latest on featured products, new releases, and announcements.

Read Developer News

Get Started

Access technical how-to guides, instructions, and sample code.

Explore Developer Blogs

Deep Learning Institute

Get Hands-On Training in Accelerated Computing

Develop the skills you need to do your life’s work in accelerated computing, data science, AI, and more through the NVIDIA Deep Learning Institute (DLI).

Receive 50% off the instructor-led virtual workshop Fundamentals of Accelerated Computing with CUDA^® C/C++ during SC21 with code DLISC21. Space is limited.

Register today

DLI is offering a free enrollment code to the first 300 supercomputing enthusiasts. Choose from an extensive catalog of self-paced, online training and benefit from access to GPUs in the cloud.

Get a free code

DLI Instructor-Led Virtual Workshop:

Fundamentals of Accelerated Computing with CUDA C/C++
Thursday, November 18, 2021 | 9:00 a.m.–5:00 p.m. CST