Trending Articles
Trending Topics
Trending
Hewlett Packard Enterprise (HPE) has announced the delivery of the El Capitan supercomputer to the United States Department of Energy’s (DOE) Lawrence Livermore National Laboratory (LLNL).
HPE says the supercomputer runs at 1.742 exaflops and can achieve 58.8 gigaflops performance per watt. The system is powered by HPE’s Cray EX supercomputing solution, which features AMD Instinct M1300A APUs.
Its performance is boosted by the HPE Slingshot interconnect, an Ethernet-based high-speed fabric connecting more than 11,000 nodes for parallel computation. According to the LLNL, El Capitan is 22 times faster than the supercomputer it replaces.
Additionally, El Capitan is 100% fanless and is instead supported by HPE’s direct liquid cooling system architecture.
“El Capitan marks another significant milestone in exascale supercomputing, bringing monumental performance, energy efficiency and the capabilities to accelerate AI-driven scientific discovery and make incredible breakthroughs to strengthen national security and unlock new opportunities in renewable energy,” HPC and AI infrastructure solutions Senior VP and General Manager Trish Damkroger said.
El Capitan will run AI models for classified and unclassified workloads, while helping the National Nuclear Security Administration’s (NNSA) Tri-Labs – LLNL, Sandia National Laboratories and Los Alamos National Laboratory – to meet the growing safety, security and reliability of the country’s nuclear stockpile by performing current and future stockpile modernisation efforts.
El Capitan will also aid in national security missions, and be used for material discovery, nuclear data and high energy density science, HPE said.
Enterprises, research institutes and government agencies around the world are training & tuning AI models to drive innovation & unlock breakthroughs. These projects have two things in common: The data sets are vast, and speed is an absolute priority. Turnkey solutions from HPE combine hardware, software, and services to help you scale your AI models at supercomputing speed and unleash the power of generative AI.
“This long-anticipated resource will allow us to perform the high-fidelity 3D modelling and simulation we need to effectively carry out our national security mission,” said Rob Neely, Program Director of LLNL’s weapon simulation and computing.
“We have a large team of people who have been getting applications ready to unleash the power of this system – many of them with the help of HPE in our Center of Excellence – and I can’t wait to demonstrate the capabilities to our sponsors and supporters.
“We are also committed to investing in AI on El Capitan and will be using the system for large-scale AI training and inference to make our calculations faster, more efficient, and potentially more accurate. Having a capability that is dialled in for both modelling and simulation and AI workloads, all in one system, is very exciting.”
With El Capitan, HPE now holds the top three spots on the November 2024 edition of the Top 500 list of the world’s fastest supercomputers. Coming in at number one spot is El Capitan, followed by Frontier at Oak Ridge National Laboratory in number two with Aurora at Argonne National Laboratory ranking number three.
