Hewlett Packard Enterprise (HPE) has made a remarkable mark on the global supercomputing landscape, delivering the top three supercomputers in the world, including three of the top four in Saudi Arabia. Among these is El Capitan, a supercomputer that demonstrates the immense potential of AI-driven scientific discovery, showcasing groundbreaking performance capabilities.
Mohammad Alrehaili, HPE’s Middle East Managing Director, highlighted that El Capitan’s success emphasizes the significance of investing in advanced supercomputing capabilities, particularly in the Middle East, to accelerate AI-driven research and foster the development of the AI ecosystem. He expressed confidence that the region will see further investments in supercomputing as it aims to lead in AI development.
El Capitan, designed for the National Nuclear Security Administration (NNSA) and Lawrence Livermore National Laboratory (LLNL) in partnership with AMD, achieved an astounding 1.742 exaflops on the November 2024 edition of the TOP500, securing its position as the world’s most powerful supercomputer. It also ranks as one of the top 20 most energy-efficient systems globally. El Capitan joins two other HPE-built supercomputers, Frontier at Oak Ridge National Laboratory (ORNL) and Aurora at Argonne National Laboratory (ANL), in the ranks of the world’s three verified exascale systems.
HPE-built supercomputers collectively dominate in performance share, with over 5.75 exaflops across the TOP500 list of the world’s fastest systems. Seven of the top 10 supercomputers are powered by HPE’s advanced Cray Supercomputing EX systems, which feature the industry’s first 100% fanless direct liquid cooling system architecture.
El Capitan was created to help the United States maintain its competitive edge in national security, using high-fidelity modeling and simulation to solve complex problems that can only be tackled through exascale computing. It will also support the country’s AI-driven scientific research in areas like nuclear science, materials discovery, and fusion energy.
Frontier, ranked second at 1.353 exaflops, was the first system in the world to break the exascale barrier in 2022. Built in collaboration with ORNL and AMD, Frontier is revolutionizing AI-powered research in fields like cancer research, drug discovery, nuclear fusion, and supernovae.
Aurora, ranking third, was co-built by Intel and HPE. It is advancing research on data-intensive projects such as aircraft design, cancer treatments, and sustainable energy. Researchers in the Aurora Early Science Programme are making key breakthroughs, including the 3D-mapping of neuron connections in the brain and the development of new protein sequences for vaccines.
HPE’s leadership in supercomputing extends to Europe, where its Cray Supercomputing EX powers the region’s three most powerful AI-enabled systems. HPE’s innovative 100% fanless direct liquid-cooled solutions have been featured among the most energy-efficient supercomputers globally. These supercomputers are optimized for both precision and speed, making them ideal for groundbreaking research in fields like climate science and space exploration.
With over 50 years of experience in deploying reliable direct liquid cooling systems, HPE’s supercomputers incorporate eight advanced cooling elements, reducing energy consumption by up to 94% compared to traditional air-cooling systems. Additionally, the liquid-cooled HPE Slingshot interconnect with Dragonfly topology ensures that supercomputers complete workloads faster and with lower overall energy requirements.
HPE’s HPC software solutions enable customers to monitor and regulate power usage, further driving energy efficiency. These innovations demonstrate why HPE continues to build some of the world’s most energy-efficient supercomputers.
