Location: Room P11 – Peony Jr 4511 (Level 4)
Abstract: The industry is experiencing a resurgence of interest in diverse computing architectures, with Arm technology leading this transformation. NVIDIA’s GH200 Grace Hopper™ Superchip exemplifies this trend, combining the NVIDIA Hopper GPU with the Grace CPU, featuring 72 high-performance Armv9 cores on a single die. This integration delivers competitive FP64 TFlops performance and up to 500GB/s memory bandwidth, all while maintaining industry-leading power efficiency. The tutorial aims to unlock the full potential of the Grace CPU and Grace Hopper GH200 Superchip for scientific computing. Experts will guide attendees through the process of compiling, executing, profiling, and optimizing code for Arm architecture, dispelling the notion that changing CPU architectures is challenging. The session will also demonstrate how to leverage the GH200’s unique architecture using various programming models, supported by practical examples that attendees can replicate. To facilitate hands-on learning, remote access to NVIDIA GH200 will be provided.
Important Notes to Participants: Please bring your laptop to fully participate in the interactive portions of the workshop.
Pre-requisites: No previous knowledge or experience on Arm-based systems is needed.
For any enquiries, please contact: SCA25_NV_GraceHopper@nvidia.com
Programme:
| Time | Session |
| 09:30am – 09:45am | Session 1: Registration, Logistics and Welcome – Filippo Spiga, Dr Gabriel Noaje |
| 09:45am – 10:30am | Session 2: NVIDIA Grace™, NVIDIA GH200 Grace Hopper™ Superchip, and NVIDIA GB200 Grace™ Blackwell Superchip Products and Platforms – Gabriel Noaje |
| 10:30am – 11:00am | Tea Break |
| 11:00am – 11:30am | The Fastest and Energy Efficient Supercomputers – HPE Cray EX Supercomputer featuring NVIDIA GH200 Grace Hopper Superchip – De-Iou Tsai |
| 11:30am – 12:00am | Session 3: Hardware Deep Dive – Filippo Spiga |
| 12:00am – 12:30pm | Session 4: CPU Software Deep Dive – Filippo Spiga |
| 12:30pm – 01:30pm | Lunch |
| 01:30pm – 02:00pm | Session 5: Programming Models Deep Dive – Filippo Spiga |
| 2:00pm – 02:30pm | NVIDIA Grace Hopper (GH200) Superchip Customer Experience – Dr Pascal Jahan Elahi |
| 02:30pm – 03:00pm | Session 6: Getting Ready for Hands-On + Live Demo – Filippo Spiga |
| 03:00pm – 03:30pm | Tea Break |
| 03:30pm – 04:45pm | NVIDIA Grace Hopper (GH200) Superchip Participants’ Hands-on / Bring Your Own Code – Filippo Spiga, Dr Gabriel Noaje, Dr Wei Fang |
| 04:45pm – 05:00pm | Wrap Up and Q&A Filippo Spiga, Dr Gabriel Noaje |
