From left, LANL Interim Deputy Director for Science, Technology and Engineering Mark Chadwick, DOE Secretary David Turk, NVIDIA CEO Jensen Huang, LANL Director Thom Mason, Hewlett Packard Enterprise CEO Antonio Neri and NNSA Los Alamos Field Office Manager Ted Wyka at the 2024 Venado ribbon cutting event held Monday at Los Alamos National Laboratory. Courtesy/LANL

National Security AI Office Director Jason Pruet, left, serves as the moderator for the panel discussion held during the unveiling of Los Alamos National Laboratory’s newest supercomputer, Venado, Monday at LANL. The panel discussion featured NVIDIA CEO Jensen Huang, second from left, LANL Director Thom Mason, Hewlett Packard Enterprise CEO Antonio Neri and DOE Secretary David Turk. Courtesy/LANL

By KIRSTEN LASKEY
Los Alamos Daily Post
kirsten@ladailypost.com

In a nondescript room inside the Los Alamos National Laboratory’s (LANL) Nicholas C. Metropolis Center for Modeling and Simulation, which is equal in size to a football field, a mechanical whirring sound can be heard. The hum is generated from large supercomputing units working their technological magic.

Monday, laboratory leaders, Department of Energy Secretary David Turk, as well as NVIDIA Chief Executive Officer Jensen Huang, Hewlett Packard Enterprise (HPE) Chief Executive Officer Antonio Neri and others celebrated the newest addition to the center’s supercomputing floor: Venado.

The event included a panel discussion and ribbon cutting ceremony for Venado. The newest supercomputer stands out from its neighbors due to its one-of-kind, cutting edge technology.

Achieving this feat was a collaboration between LANL, HPE and NVIDIA.

“Venado adds to our cutting-edge supercomputing that advances national security and basic research, and it will accelerate how we integrate artificial intelligence into meeting those challenges,” LANL Director Thom Mason said in a press release.

During the panel discussion, he noted that the laboratory has long participated in the successes of supercomputers.

“We’ve been part of every successful wave in the field,” Mason said.

Huang added that for more than 30 years, the frontiers have been pushed for excellence in computing, but the last four years seemed to be different.

“We’ve been in a boiling state for some time,” he said.

Unveiling Venado is a real high point, and, as Turk said, touches on four features that should really be leaned into.

These features, he said, are: new investments in supercomputing, data sets, partnerships and people.

Regarding people, Turk said, “(Their) level of expertise and the history of expertise, we need to lean into that.”

According to the press release, the NVIDIA Grace Hopper Superchips combine an Arm-based NVIDIA central processing unit with a NVIDIA Hopper architecture-based graphics processing unit to address high performance computing and giant-scale artificial intelligence applications. The superchips can execute millions more instructions per second, usually at lower cost and power consumption, than preceding chip technology. In early-scale tests Venado has shown significant results in atomistic simulations for materials science and high-resolution astrophysics simulations.

“Our supercomputing capabilities represent a critical component of how national laboratories tackle important problems,” Turk said in the press release. “With its ability to incorporate artificial intelligence approaches, we are looking forward to seeing how the Venado system at Los Alamos can deliver new and meaningful results for areas of interest.”

Venado’s computing capacity will house 2,560 direct, liquid-cooled Grace Hopper superchips in the exascale-class HPE Cray EX supercomputer. The system, will also use 920 NVIDIA Grace CPU Superchips, making it the first large-scale system with NVIDIA Grace CPU superchips deployed in the United States. NVIDIA packs 144 Arm cores in a Grace CPU Superchip to deliver an immediate performance boost to a wide range of HPC applications.

“As the first U.S. supercomputer powered by NVIDIA Grace Hopper, the Venado system delivers groundbreaking performance and energy efficiency to accelerate scientific discovery,” said Ian Buck, vice president of hyperscale and HPC at NVIDIA, in the press release. “Through our continued work with Los Alamos and HPE, Venado will be a magnificent scientific instrument for researchers to achieve breakthroughs in materials science, renewable energy, astrophysics and more.”

During Monday’s event, HPC Deputy Division Leader Marckus Berndt emphasized that Venado can be utilized across the laboratory.

“We’re excited about it,” he said. “It’s an institutional resource.”

According to the press release, the Venado system was built to prioritize overall performance and workflow efficiency. The system is networked with HPE Slingshot 11 interconnect to supercharge the performance of the entire system with extremely high-speed networking. Additional HPE Cray supercomputing software improves modeling and simulation workloads, helping researchers make new discoveries by leveraging AI and machine learning to harness insights. Designed and manufactured in HPE’s facility in Chippewa Falls, Wisc., Venado takes its name from one of the highest peaks in New Mexico’s Sangre de Cristo mountains. The system was delivered to Los Alamos in March.

Berndt said during Monday’s event that the supercomputer is expected to be fully functional by early summer.

“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 in the press release. “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.”

Venado is the outcome of a codesign process that will form the basis for ongoing collaboration focused on developing a broad spectrum of computing, memory and software technologies. Codesign draws on the combined expertise of vendors, hardware architects, system software developers, domain scientists, computer scientists and applied mathematicians working together to make informed decisions about hardware and software components.

From left, Hewlett Packard CEO Antonio Neri, NVIDIA CEO Jensen Huang, LANL Interim Deputy Director for Science, Technology and Engineering Mark Chadwick, DOE Secretary David Turk, LANL Director Thom Mason, and LANL HPC Program Manager. Jim Lujan tour the supercomputing floor inside the Nicholas C. Metropolis Center for Modeling and Simulation during the ribbon cutting event Monday. Courtesy/LANL