Powered by AMD, Frontier Expected to be World’s Fastest Supercomputer
To enable exascale-class scientific research, AMD in collaboration with the U.S. Department of Energy, Oak Ridge National Laboratory, and Cray Inc., will create the Frontier system the next generation of supercomputer, expected to deliver more than 1.5 exaflops of peak processing power.
To solve some of the toughest challenges in the world today, the Frontier system is designed to simulate, model, and advance the understanding of the interactions underlying the science of weather, sub-atomic structures, genomics, physics, and more. As examples, the following scientific areas are currently being researched using supercomputers today:
Biological research teams are investigating protein engineering to enable new types of industry, design new pharmaceuticals and medical therapies, in order to improve human lives.
Climate Scientists simulate the behavior of the world’s oceans and atmosphere, and to model abrupt climate change, helping us understand what we need to do to keep the earth a nurturing and hospitable place.
Scientists are studying the nature of materials at the smallest possible scale - from power generation and transmission to the production of faster, smaller, more versatile computers and storage devices.
AMD is a proven provider of both processor and graphics technology - creating intelligent ecosystems that work efficiently together. To enable the Frontier system to meet the demanding needs of scientific research, four key AMD technologies will be leveraged: EPYC™ processors, Radeon Instinct™ accelerators, Infinity Fabric technologies, and ROCm (Radeon Open eCosystem), an open software ecosystem for heterogeneous compute.
AMD EPYC™ Processors
Our EPYC™ processors are driving a new era in the datacenter, with exceptional scalability, energy efficiency, memory bandwidth, and I/O capability. This makes our EPYC™ processor an excellent choice for HPC solutions. The Frontier system will be utilizing a custom EPYC™ CPU optimized for HPC and AI computation.
AMD Radeon Instinct™
Radeon Instinct™ accelerators provide flexible high performance compute engines, high bandwidth memory, and scalable fabric and communications technologies. To support the computational challenges of the Frontier system, Radeon Instinct™ accelerators will be configured in a tightly integrated, highly efficient 4:1 GPU to CPU ratio.
AMD Infinity Fabric Technologies
In order to scale performance of these complimentary processors to exascale levels we will enhance our AMD Infinity Fabric. Providing unified, coherent connectivity between CPU, GPU, and memory, Infinity Fabric streamlines data movement, enabling faster execution of complex calculations or analysis of large scientific data sets.
Open Software Ecosystem
Great hardware needs great software. The ROCm open software ecosystem is an open-source platform for HPC-class heterogeneous compute and world-class datacenter system designs. The ROCm open ecosystem incorporates optimized drivers, compilers, libraries, support for OpenMP, and the tools needed for large HPC systems including the ability to code down to the metal, if desired. These elements are key for getting the utmost efficiency out of a compute system of this magnitude. AMD, in conjunction with Cray Inc. will provide the developers working on the Frontier system the open, accelerated computing platform to take science to the exascale era.
Stay up to date with the latest news from AMD
©2019 Advanced Micro Devices, Inc. All rights reserved. AMD, the AMD Arrow logo, Ryzen, Radeon, EPYC, Radeon Instinct, and combinations thereof are trademarks of Advanced Micro Devices, Inc.