AMD and Penguin delivered small supercomputing clusters to NYU, MIT, Rice to help in the fight for Covid-19 research. With a combined power of seven petaflops, the New York University (NYU), Massachusetts Institute of Technology (MIT), and Rice University will have some more computing power under the hood.
A petaflop is a unit of computing speed equal to one million million (1012) floating-point operations per second.
The donation is part of a high-performance computing (HPC) initiative that aims to help with the Covid-19 research. One of the best-known types of HPC solutions is the supercomputer. A supercomputer contains thousands of compute nodes that work together to complete one or more tasks. This is called parallel processing.
AMD will provide the Epyc CPUs and Radeon Instinct GPUs and will fund the cluster, while Penguin will construct and deploy the systems. With the aid of Gigabyte, who will supply G290-Z21 compute nodes, and DataBank, who will donate space for a small computing pod available over the cloud, the efforts of the companies involved in this endeavor hope to add to the growing Covid-19 HPC Consortium, which currently features around 483 petaflops of power across 5m CPU cores and 50k GPUs.
At the moment, the universities included in the program have systems capable of performing more than one petaflop. With the help of AMD and Penguin computing cloud system, NYU, MIT, and Rice will add seven more petaflops. The systems are thanks to the AMD 15 million COVID-19 HPC fund that was inaugurated in April.
AMD CEO Dr. Lisa Su said that donated HPC systems are strategically important to viral research. She also added that AMD hopes that the aid provided by the company will help stimulate the development of “potential therapeutics and vaccines”.