Supercomputing 2022 Conference

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 SC22

Event: November 13-18, 2022
Kay Bailey Hutchison Convention Center, Dallas, Texas

Add to Calendar

Join us at Supercomputing 2022 (SC22) to see how accelerated computing and high-performance networking are transforming computational science and AI. A special address, theater presentations, demos, developer content, and much more will be featured on our website. You can also join us onsite and engage with our partners on the showfloor.

NVIDIA SC22 Special Address

Hear about the latest innovations from NVIDIA’s Jensen Huang, Ian Buck, Tim Costa, Geetika Gupta, and Dion Harris on November 14, 9:00 a.m. CT.

Watch Video

NVIDIA SC22
Special Address

Hear about the latest innovations from NVIDIA’s Jensen Huang, Ian Buck, Tim Costa, Geetika Gupta, and Dion Harris on November 14, 9:00 a.m. CT.

Save the Date

Schedule at a Glance

At SC22, 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
Panels, Papers, Birds of a Feather (BoF)

Sunday 11/13	Monday 11/14	Tuesday 11/15	Wednesday 11/16	Thursday 11/17	Friday 11/18
2022 International Workshop on Performance Portability and Productivity (P3HPC) 8:30 a.m.–5:00 p.m. CT Workshop	The First Workshop on Federated and Privacy Preserving AI for HPC 8:30 a.m.–12:00 p.m. CT Workshop				HiPar22—Opening Remarks 8:30–8:40 a.m. CT Workshop
8th Workshop on Machine Learning in HPC Environments 8:30 a.m.–5:00 p.m. CT Workshop	Efficient Distributed GPU Programming for Exascale 8:30 a.m.–5:00 p.m. CT Tutorial
Women in HPC: Diversifying the HPC Community and Engaging Males Allies 8:30 a.m.–5:00 p.m. CT Workshop	Performance Tuning with the Roofline Model on GPU and CPUs 8:30 a.m.–5:00 p.m. CT Tutorial
Third International Workshop on Quantum Computing Software 8:30 a.m.–5:00 p.m. CT Workshop	Teaching Accelerated Computing and Deep Learning at a Large-Scale with the NVIDIA Deep Learning Institute 9:45am - 10:00am CT Workshop
Deep Learning at Scale 8:30 a.m.–5:00 p.m. CT Tutorial	Frontier vs. the Exascale Report: Why So Long? And Are We Really There Yet? 10:30–11:00 a.m. CT Workshop		Supercomputing: Transforming Every Field of Discovery 11:30 a.m.–12:00 p.m. CT Exhibitor Forum		HiPar22—Closing Remarks 11:50 a.m.–12:00 p.m. CT Workshop
	Task Fusion in Distributed Runtimes 10:52–11:14 a.m. CT Workshop				Accelerating Datalog Applications with cuDF 11:50 a.m.–12:00 p.m. CT Workshop
	Approaching Exascale: Best Practices for Training a Diverse Workforce Using Hackathons 11:00–11:15 a.m. CT Workshop
	A DPU Solution for Container Overlay Networks 11:25–11:35 a.m. CT Workshop
Accelerating Portable HPC Applications with Standard C++ 1:30–5:00 p.m. CT Tutorial	HPC Systems Professionals Workshops (HPCSYSPROS22) 1:30–5:00 p.m. CT Workshop
	Benchmarking Fortran DO CONCURRENT on CPUs and GPUs Using BabelStream 3:00pm - 4:00pm CT Workshop
	One Step Closer to Converged Computing: Achieving Scalability with Cloud-Native HPC 3:10–3:40 p.m. CT Workshop

Sunday 11/13	Monday 11/14	Tuesday 11/15	Wednesday 11/16	Thursday 11/17	Friday 11/18
		Custom 8-Bit Floating Point Value Format for Reducing Shared Memory Bank Conflict in Approximate Nearest Neighbor Search 8:30 a.m.–5:00 p.m. CT Research Poster
		Artificial intelligence Reconstructs Missing Climate Information 8:30 a.m.–5:00 p.m. CT Research Poster		Transforming the Future of HPC with Silicon Photonics 10:30 a.m.–12:00 p.m. CT Panel
	ECP—Invited Talks: Career Stories 12:15–1:15 p.m. CT Early Career Program	InfiniBand In-Network Computing and DPU Technologies and Roa dmap 12:15–1:15 p.m. CT BoF	Americas HPC Collaboration 12:15–1:15 p.m. CT BoF	Another Step Towards a Sustainable HPC Outreach Ecosystem 12:15–1:15 p.m. CT Bof
	ECP—Invited Talks: Work-Life Balance 12:15–1:15 p.m. CT Early Career Program	Use Cases for SPEC HPC Benchmarks 12:15–1:15 p.m. CT BoF	25th Graph500 List 4:30–5:00 p.m. CT BoF	Scientific Digital Twin in HPC 12:15–1:15 p.m. CT BoF
		OpenACC User Experience: Relevance, Hackathons, and Roadmaps 5:15–6:45 p.m. CT BoF	WholeGraph: A Fast Neural Network Training Framework with Multi-GPU Distributed Shared Memory Architecture 4:30–5:00 p.m. CT Paper	Lessons Learned on MPI+Threads Communication 2:00–2:30 p.m. CT Paper
		Arm Diversity Unified: Standardization in Hardware and Software 5:15–6:45 p.m. CT BoF	Ursus: Fast, Secure File System Metadata Search for Both Privileged and Unprivileged Users 4:30–5:00 p.m. CT Paper	Do Domain-Specific Processors Need Domain-Specific Networks? 3:30–5:00 p.m. CT Panel
			Unified Communication X (UCX) Community 5:15–6:45 p.m. CT BoF
			Continuum Computing 5:15–6:45 p.m. CT BoF
			Best Practices for Training an Exascale Workforce Using Applied Hackathons and Bootcamps 5:15–6:45 p.m. CT BoF
			Software Engineering and Reuse in Modeling, Simulation, and Data Analytics for Science and Engineering 5:15–6:45 p.m. CT BoF

Featured Demos

In a series of demos, explore how NVIDIA technologies are transforming a variety of industries with new capabilities—highlighting the latest breakthroughs in HPC.

Building a Data Center Digital Twin in NVIDIA Omniverse

Data centers are complex to plan, build, and continuously operate and manage. With NVIDIA Omniverse™, data center architects and operators can build full-fidelity, real-time, interactive digital twins of their data centers, connecting the infrastructure, simulation, layout, network stack, and monitoring tools they use today.

Watch the Demo

What's New in CUDA Developer Tools: Profiling NVIDIA Hopper and Workflow Enhancements

The latest updates to CUDA developer tools include workflow enhancements, new supported environments, and profiling features for the latest NVIDIA Hopper™-based platforms. Explore an overview of the highlights, including Arm® GUI support, SDK Manager improvements, and new performance metrics for CPU and GPU profiling.

Watch the Demo

NVIDIA Self-Healing Network Technology Enables Unbreakable Data Centers

In today’s networks, a traditional subnet manager will recognize failed links and recalculate routes, taking up to 5 seconds for 1,000 nodes and 30 seconds for 10,000 or more nodes. The self-healing network capabilities of NVIDIA Quantum InfiniBand switches overcome link failures, enabling network recovery much faster than any other software-based solution.

Watch the Demo

Accelerating HPC Applications with the NVIDIA BlueField Data Processing Unit

The NVIDIA® BlueField® data processing unit (DPU) ignites unprecedented innovation and performance for modern scientific computing applications. A DPU can process an application’s communication in parallel with its computation, resulting in increased application performance.

Watch the Demo

Virtual Theater

Hear from industry leaders, scientists, and researchers as they explain their groundbreaking work utilizing NVIDIA technologies. Tune in during the week of November 14 to watch short, on-demand talks at your own pace.

View Sessions

Accelerate Your Work with the NVIDIA Developer Program

The Community That Builds

Take a look inside the NVIDIA Developer Program to discover the tools, training, and support it provides to help developers do their life’s work.

Join Today

Replay GTC

NVIDIA GTC is the developer conference for the era of AI and the metaverse. Replay top technical talks from the event on-demand.

Watch Top Developer Sessions

Stay up to Date

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

Read Developer News

Learn

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

Explore Developer Blogs

Get Hands-On Training with the NVIDIA Deep Learning Institute

Develop the skills you need to do your life’s work in accelerated computing, data science, and AI and earn certificates of subject-matter competency through the NVIDIA Deep Learning Institute (DLI).

Instructor-Led Workshops

Receive 50% off the DLI instructor-led hands-on virtual workshops offered through January 2023 with code DLISC22. Space is limited.

View Workshop Schedule

Top Sessions in Self-Paced Training

Introduction to Physics-Informed Machine Learning with NVIDIA Modulus
An Even Easier Introduction to CUDA®
Fundamentals of Accelerated Computing with OpenACC®

View All Self-Paced Courses

Meet Our Partners

Get Updates to The Latest Supercomputing News

Section

Section

First Name

Last Name

Business Email Address

Organization / University Name

Industry

Job Role

Location

Preferred Language

State/Province

developerOptIns hidden field

Send me the latest developer news, announcements, and more from NVIDIA. I can unsubscribe at any time.

NVIDIA Privacy Policy

本人知悉且同意 NVIDIA Corporation 基于调研、活动组织的目的对本人的上述信息的收集和处理，并已经阅读并同意 <a href="https://www.nvidia.cn/about-nvidia/privacy-policy/" target="_blank">NVIDIA 隐私政策</a>。

本人知悉且同意，因调研、活动组织的必须，以及相对应的 NVIDIA 内部管理和系统操作的需要，上述信息会被传输到位于美国的 NVIDIA Corporation 按照符合 <a href="https://www.nvidia.cn/about-nvidia/privacy-policy/" target="_blank">NVIDIA 隐私政策</a>的方式进行存储，您可以通过发送邮件至 <a href="mailto:privacy@nvidia.com">privacy@nvidia.com</a> 进行联系以解决相关问题，实现可适用的数据保护法所规定的权利。