SC23 is just around the corner! Those joining us in Denver on November 12-17 have an outstanding opportunity to see and experience many advancements in AI and HPC. This year, Intel plans several demonstrations showcasing Intel and partner technologies and how those advancements enable breakthroughs in science and industry. Below are a few ways to see our AI and HPC-related technology in action and learn about its real-world benefits for developers and organizations of all sizes.
Experience the Intel Theater Sessions and Intel Developer Hub
Please join us at the Intel Developer Hub in booth #617 for live code tutorial experiences using Intel software and hardware! Find out more at Intel.com/SC.
We will also host a series of tech talks from Intel representatives and ecosystem experts, sharing the latest details about Intel-based solutions and their benefits to the HPC community.
Data scientists and developers will also have an opportunity to interact with Intel’s diverse portfolio of products, tools, and solutions. Attendees will experience live code tutorials centered on the latest Intel® Xeon® CPU Max and Intel® GPU Max Series, Large Language Models, Generative AI, Intel® Gaudi®2 clusters on Intel Developer Cloud, CUDA and SYCL migration, and more. Visitors can also connect with Intel experts and the developer community to test drive the latest toolkits that enable innovative solutions, accelerate performance, and increase productivity.
Technology Demos Galore!
Come see several demonstrations of HPC technology in action and how the latest technologies accelerate AI training, inference, and modeling:
HPC and AI Demo on Intel® Data Center GPU Max Series
This live demo will showcase how HPC and an AI workload can run on the same server using different shells. Through a demo server featuring Intel Data Center GPU Max and Xelink Bridges, Intel will offer tips on server setup and ways to optimize files and configuration data for heavy workloads.
AI Accelerated Molecular Dynamics
Check out a real-time molecular dynamics (MD) simulation of one million gold atoms’ thermal conductivity and radial distribution. This demo will show how the next-generation Intel Xeon CPU Max Series (Granite Rapids) makes the most of Multiplexer Combined Ranks (MCR) DIMM memory and Intel® Advanced Matrix Extensions for AI training and inference in HPC scenarios.
Accelerating LLMs and Multi-Modal Models
Visit our booth to explore a BridgeTower multi-modal model trained on two million human-generated descriptions of New Yorker cartoons. Attendees can interact with the demo and input prompts. A second demo shows model training in real-time through a head-to-head performance comparison of Intel Gaudi2 accelerators and Nvidia H100 GPUs.
Argonne National Laboratory Team Presents Scaling LLM on Aurora for Protein-Protein Interactions
Generative AI and large-language models for inference at scale will transform medical research. Argonne National Laboratory team members will demonstrate how Aurora will assist with generative AI-driven drug design. Attendees can interact with a LLaMA-2 inference model, tuned for genomics and drug information, and run interactive queries on a supercomputer in the same way medical researchers can.
Visualizing Tumor Cell Trajectories on Aurora
The forthcoming Aurora Exascale HPC system at Argonne National Laboratory, featuring the Intel Xeon CPU Max, Intel Data Center GPU Max, and the Intel® oneAPI Rendering Toolkit will enable breakthrough science. The Intel booth will feature Dr. Amanda Randles’ HARVEY simulation model, allowing attendees to visualize the human arterial system at a cellular level. The interactive demo runs on several Aurora blades using OSPRay, Intel Embree 4.0, and Open Image Denoise 2.0.
Join us there!
We look forward to connecting with you at the Intel booth, #617. Check out the latest schedule of demos, workshops tech talks and more!
Notices & Disclaimers
Performance varies by use, configuration and other factors. Learn more at www.Intel.com/PerformanceIndex
Performance results are based on testing as of dates shown in configurations and may not reflect all publicly available updates. See backup for configuration details. No product or component can be absolutely secure.
Intel technologies may require enabled hardware, software or service activation.
No product or component can be absolutely secure.
© Intel Corporation. Intel, the Intel logo, and other Intel marks are trademarks of Intel Corporation or its subsidiaries. Other names and brands may be claimed as the property of others.
You must be a registered user to add a comment. If you've already registered, sign in. Otherwise, register and sign in.