List The world’s most powerful supercomputers have a new leader: supercomputer Captainbuilt by HPE for Lawrence Livermore National Laboratory (LLNL) United States Nuclear Security Administration (NNSA). The system features a continuous processing power of 1.74 exaflops, with a peak performance of 2.79 exaflops.

With its power, El Capitan dethroned the world’s most powerful supercomputer to date: the Frontier, which now becomes the second. It features AMD chips, specifically the AMD Instinct MI300A APU, which combines high-bandwidth CPU, GPU, and memory cores. Not only is it the fastest and most powerful computer, it is also among the 20 most sustainable supercomputers in the world.

The system includes more than 11,000 compute nodes and 5.4375 petabytes of memory, achieving peak performance 20 times that of LLNL’s previous supercomputer, Sierra, which reached a peak performance of 125 petaflops. It is developed from the HPE Cray Supercomputing EX system, designed specifically for exascale computing. Additionally, it integrates HPE’s direct liquid cooling solution.

El Capitan will allow the laboratory in which it is installed to significantly improve its ability to predict and model the performance of nuclear weapons, in addition to advances in various fields of science, as these systems are renewed and updated. In this way, LLNL will be able to better understand its situation and capacity and improve its ability to make informed safety decisions.

But that will not be the only task for which El Capitan will serve. Its computing power can also be used in various missions aimed at assisting in emergency situations. For example, during natural disasters and other man-made crises.

It will be able to do this, among other things, because it is able to offer a higher resolution in 3D modeling than was previously possible with other supercomputers. Either because they weren’t able to get them, or because it was too computationally expensive to get them on a regular basis.

In addition, El Capitan may also be able to more accurately replicate drugs, allowing for better analyzes of its ingredients and allowing scientists to incorporate more real-world factors such as environmental conditions or imperfections into their tests and analyses.

Until now, the calculations required to do this were either impossible or took weeks or months for LLNL’s systems to acquire. With this supercomputer, these calculations are solved in days and even hours.

In addition, it will also be used in modeling high-energy-density physics experiments such as inertial confinement fusion, studying ballistic reentry dynamics, and improving the understanding of materials behavior under extreme conditions.

Bronis R. de Supinski, LLNL Chief Technology Officer for Livermore Computingnoted that «Using the AMD Instinct MI300A APU, we developed a system that was previously unimaginable, pushing the limits of computing power while maintaining exceptional energy efficiency. As AI continues to dominate our industry, El Capitan allows us to integrate it with our traditional modeling and simulation workloads, opening new avenues of discovery across scientific disciplines.«.

On the side AMD, Forrest Norrod, Vice President and Chief Executive Officerthey emphasized that they are happy to see El Capitan «becoming the second AMD-powered supercomputer to break the exaflop barrier and becoming the world’s fastest supercomputer. Showcasing the incredible performance and efficiency of the AMD Instinct MI300 APU, this revolutionary machine is a tribute to the dedicated work between AMD, LLNL and HPE.«.