Nvidia recently introduced a reference design platform allowing companies to build GPU-accelerated Arm-based servers. The company is well acquainted with ARM as they have incorporated the architecture in their Tegra chips and other system-on-a-chip product for portable gaming, autonomous vehicles, robotics, and embedded AI computing.

At the SC19 supercomputing conference, the GPU company announced a collaboration with ARM and its ecosystem partners Ampere, Fujitsu, and Marvell, to ensure NVIDIA GPUs work well with Arm-based processors. This partnership has been brewing for quite a while now as earlier this year Nvidia officially announced support for processors with ARM architecture along with its entire stack of AI and HPC software.

In addition to making its own software compatible with Arm, NVIDIA is working closely with its broad ecosystem of developers to bring GPU acceleration to Arm for HPC applications such as GROMACS, LAMMPS, MILC, NAMD, Quantum Espresso and Relion. NVIDIA and its HPC-application ecosystem partners have compiled extensive code to bring GPU acceleration to their applications on the Arm platform.

To enable the Arm ecosystem, NVIDIA collaborated with leading Linux distributors Canonical, Red Hat, Inc., and SUSE, as well as the industry’s leading providers of essential HPC tools.

World-leading supercomputing centers have begun testing GPU-accelerated Arm-based computing systems. This includes Oak Ridge and Sandia National Laboratories, in the United States; the University of Bristol, in the United Kingdom; and Riken, in Japan.

– Nvidia Newsroom

ARM chips power most mobile devices around the world so the architecture remains power efficient by design. Since the architecture is licensed out, with ARM multiple silicon makers can be considered. Power consumption remains a big concern with HPCs and using ARM can offset this problem to a huge extent.

ARM’s use in HPCs and Data Centres is still small compared to x86 systems but Nvidia sees the potential here. Their arch-rival AMD has also started to compete fiercely in the HPC and Datacenter market with their EPYC server processors and Radeon Instinct GPU accelerators. Nvidia needs to adopt ARM early, as unlike some manufacturers, Nvidia doesn’t make CPUs, so they lack the CPU-GPU coherency AMD and Intel can offer.

The global HPC market was valued at USD 34.62 billion in 2017, mainly dominated by companies like IBM and Intel. It is expanding at pace every year and many analysts forecast a big boost with the onset of 5G. Many companies are trying to get a foothold here and this happens to be at a time when Intel’s IPC gains seem to have stagnated even with newer architectures.