Hewlett Packard Enterprise (NYSE: HPE) today announced it has expanded its collaboration with the U.S. Department of Energy’s Los Alamos National Laboratory (LANL) to build LANL a new supercomputer in early 2023. The new supercomputer builds on to LANL’s latest, diverse high-performance computing (HPC) system designs, which include HPE-powered systems using the industry’s leading CPUs and GPUs to target a range of workloads and R&D. It will be based on novel technologies using the HPE Cray EX supercomputer, which is an HPC architecture built from the ground-up for next-generation supercomputing such as for exascale-class systems, and features the new Arm-based NVIDIA Grace CPU, designed for larger scale HPC and AI applications, which was announced today.
LANL’s new, advanced system will deliver overall performance and workflow efficiency, improving modeling and simulation workloads to help researchers unlock discoveries across climate, diseases, materials and even nuclear deterrence. Researchers and engineers will also use the system’s compute and AI-accelerated capabilities to expand and strengthen existing efforts in artificial intelligence and machine learning, which are becoming increasingly valuable in harnessing insights from complex data.
“HPE has a strong, ongoing collaboration with the U.S. Department of Energy’s Los Alamos National Laboratory (LANL) to support LANL’s commitment to making significant contributions to the scientific community with advanced HPC systems using diverse architectures. These designs demonstrate the powerful flexibility and scale that HPE’s systems offer in supporting various CPU and GPU technologies built for tomorrow’s most demanding supercomputing workloads,” said Bill Mannel, vice president and general manager, HPC, at HPE. “We are pleased to continue collaborating with LANL to design a new system that offers greater performance, efficiency and workload optimization to target specific R&D needs and unlock a new level of innovation.”
Los Alamos National Laboratory and HPE expand the value of high performance computing with purpose-built systems using advanced, diverse architectures
LANL’s upcoming system showcases ongoing innovation for HPC and AI workloads by introducing new, diverse sets of architectures that are developed for specific R&D and engineering needs. The new system adds to LANL’s existing system designs that are powered by HPE’s world-leading HPC and AI platforms, which combine a comprehensive suite of compute, software, storage and networking solutions, and use the industry’s most advanced CPUs. LANL’s additional system designs, announced in the last six months, include:
- Continuing the fight against COVID-19 to support complex scientific research on the novel coronavirus with LANL’s Chicoma, which is based on the HPE Cray EX supercomputer, featuring the AMD EPYC™ 7H12 processor. The system will also include the HPE Cray software stack, direct-to-chip liquid cooling capabilities and the HPE Slingshot interconnect for purpose-built HPC networking.
- Advancing U.S. nuclear stockpile and security with Crossroads, a system that is part of the Alliance for Computing at Extreme Scale (ACES), a consortium between Los Alamos National Laboratory and Sandia National Laboratories. It will be sited at Los Alamos and will be used by the three National Nuclear Security Administration (NNSA) laboratories: Lawrence Livermore National Laboratory, Los Alamos National Laboratory and Sandia National Laboratories. Crossroads will have quadrupled performance, compared to its existing system (Trinity), by using the HPE Cray EX supercomputer featuring future Intel Xeon processors code-named “Sapphire Rapids” for powerful next-generation compute and AI-accelerated capabilities. The system will target critical modeling and simulation of nuclear weapons at high 3D resolutions to ensure reliability and security of the nuclear stockpile.
- Evaluating some of the world’s most demanding physical simulation workloads and accelerating time-to-insight from months to days in LANL’s system using HPE Apollo 80 Systems that feature Fujitsu A64FX Arm processors, along with the HPE Cray Programming Environment for a fully integrated software suite to improve productivity, application scalability, and performance. LANL will also leverage the technologies to support its ongoing commitment to deploying more efficient systems to decrease runtime of its demanding complex multi-physics applications.
About Hewlett Packard Enterprise
Hewlett Packard Enterprise is the global edge-to-cloud platform as-a-service company that helps organizations accelerate outcomes by unlocking value from all of their data, everywhere. Built on decades of reimagining the future and innovating to advance the way people live and work, HPE delivers unique, open and intelligent technology solutions, with a consistent experience across all clouds and edges, to help customers develop new business models, engage in new ways, and increase operational performance. For more information, visit: www.hpe.com.