Exascale Day is not only about creating the world’s fastest supercomputer. It's about celebrating how the industry helps solve some of the world’s toughest challenges to create a better future for all of us.
Here are just a few Hewlett Packard Enterprise (HPE) | AMD systems making an impact.
- El Capitan is designed to deliver performance of over two exaflops for the safety, security, and reliability of the nation’s nuclear stockpile in the absence of underground testing. El Capitan will also support unclassified mission areas of interest to national security including material discovery, high energy-density physics, and nuclear data.
- Frontier is delivering 1.206 exaflops of performance, which is equivalent to 1.206 quintillion calculations per second, and is being used to help discover cures for cancer, predict natural disasters, to create cleaner-burning gasoline engines, engineer nuclear reactors that fit on a tabletop, and learn about the origin of the universe.
- Hunter and Herder plan to deliver exascale in two stages to provide cutting-edge infrastructure for industry applications such as AI, and high-performance data analytics. The Baden-Württemberg’s high-tech engineering community will tap into these systems, including the small and medium-sized enterprises that form the backbone of the regional economy.
Behind rack doors, HPE’s leadership-class Cray EX supercomputers, HPE Slingshot interconnects, Cray ClusterStor storage, direct liquid cooling, HPE software, and services. AMD Instinct™ accelerators, AMD EPYC™ processors, AMD Infinity Fabric™ technology and ROCm™ software provide the engines and superchargers inside with a focus on performance and efficiency.
According to the University of Stuttgart, “Exascale systems are capable of carrying out very computationally intensive processes at high speed. Their incredible performance capacity is based on graphics processing units, or GPUs. These graphics processors not only make it possible to process large amounts of data simultaneously, but also to carry out parallel calculations faster, more efficiently and much more sustainably.”
The AMD Instinct™ MI300A accelerated processing unit (APU) unifies CPU and GPU processor chiplets and high-bandwidth memory into a single package. By reducing the physical distance between processors and creating unified memory, the APU enables fast data transfer speeds, impressive HPC performance, easier programmability and great energy efficiency. This can reduce the energy required to operate Hunter, in comparison to the previous system Hawk, by approximately 80% at peak performance.
Taking flight, GE Aerospace is leveraging Frontier’s immense computational power to simulate full-scale engines under actual flight conditions, visualize air flow at microscopic levels, and gain unprecedented insights into turbulence and aerodynamics. These simulations are accelerating the design process, enabling more sustainable aviation solutions, and contributing to the CFM RISE program's goal of reducing fuel consumption and CO2 emissions by at least 20%.
“Frontier is allowing us to go beyond standard engineering analysis and to do things that were impossible before this machine,” says Trevor Wood, senior principal engineer at the GE Aerospace Research Center.
Together, AMD and HPE are powering the future of supercomputing in the Exascale era. It would have been impossible to reach these lofty goals without the U.S. Department of Energy’s vision, perseverance, and collaboration throughout this journey. Here’s a toast to those who have given, and continue to give so much to make the world a better place. Thank you and congratulations!
