The Venado supercomputer has been launched at Los Alamos National Laboratory (LANL).
The HPE Cray EX supercomputer will be housed at the Laboratory’s Nicholas C. Metropolis Center for Modeling and Simulation in Los Alamos, New Mexico.
The system consists of 2,560 direct, liquid-cooled Nvidia Grace Hopper Superchips; 920 Nvidia Grace CPU Superchips, each of which contains 144 Arm cores; and is networked with HPE Slingshot 11 interconnect.
In a statement, LANL said the system is “the first large-scale system with Nvidia Grace CPU superchips deployed in the United States.”
LANL has not confirmed the compute power of Venado but when it was first announced in May 2022, LANL, HPE, and Nvidia said the system would be capable of 10 exaflops of peak AI performance.
However, they did not clarify the precision of the benchmark at the time and it has since been reported that Venado was rated using FP8 precision, meaning it doesn’t challenge the world’s current most powerful supercomputer, the 1.194 exaflops Frontier.
“Powerful supercomputing with AI-driven capabilities will enable researchers to make high-impact breakthroughs and solve real-world problems in this next era of scientific discovery,” said Trish Damkroger, senior vice president and general manager, HPC & AI Infrastructure Solutions at HPE.
“Los Alamos National Laboratory continues to demonstrate cutting-edge research and engineering achievements with industry-leading supercomputing. We are proud of our longstanding relationship with the Lab to build Venado, together with Nvidia, to deliver innovative AI solutions that will accelerate discoveries and make impactful contributions in fields like materials science and energy research.”
Based in Santa Fe, New Mexico, LANL was set up in the 1940s as a key site during the Manhattan Project to develop nuclear weapons. Today, the site is home to a number of supercomputers, including the Crossroads system, which was installed in September 2023.