NVIDIA has announced a new reference design platform, allowing organizations to quickly build GPU-accelerated Arm-based servers. NVIDIA believes that this will help promote a “new era” of high-performance computing for an ever-increasing array of applications in science and industry.
NVIDIA has announced a new reference design platform, allowing organizations to quickly build GPU-accelerated Arm-based servers. NVIDIA believes that this will help promote a “new era” of high-performance computing for an ever-increasing array of applications in science and industry.
The reference design platform includes both hardware and software building blocks and was designed in response to the HPC community’s need for a more diverse range of CPU architectures. As such, it gives supercomputing centers, hyperscale-cloud operators and enterprises the ability to combine NVIDIA’s accelerated computing platform with the latest Arm-based server platforms.
Joining NVIDIA in building this reference platform are the following:
- Arm and its ecosystem partners (e.g., Ampere, Fujitsu and Marvell), which will help make sure their GPUs will work Arm-based processors
- Cray (a Hewlett Packard Enterprise company) and HPE, two early providers of Arm-based servers.
- NVIDIA’s ecosystem of developers such as GROMACS, LAMMPS, MILC, NAMD, Quantum Espresso and Relion, which will bring GPU acceleration to Arm for HPC applications
- NVIDIA and its HPC-application ecosystem partners, who have compiled extensive code to bring GPU acceleration to their applications on the Arm platform.
- Leading Linux distributors Canonical, Red Hat, Inc., and SUSE, which will help enable the Arm ecosystem.
Supercomputing centers have began testing GPU-accelerated Arm-based computing systems.
Sign up for the StorageReview newsletter
