In a landmark achievement announced at ISC High Performance 2024, Hewlett Packard Enterprise (HPE) has unveiled Aurora, the world’s second exascale supercomputer. Developed in collaboration with Intel for the United States Department of Energy’s Argonne National Laboratory, Aurora has reached an astounding 1.012 exaflops on 87% of its system, securing its position as the world's second-fastest supercomputer, according to the TOP500 list of the most powerful supercomputers. HPE, a global leader in supercomputing, has not only delivered its second exascale system with Aurora but also crafted the largest AI-capable system globally. Aurora clinched the top spot on the HPL Mixed Precision (MxP) Benchmark by achieving 10.6 exaflops on 89% of its system, underscoring its monumental computational prowess.
“We are honoured to celebrate another significant milestone in exascale with Aurora, which delivers massive compute capabilities to make breakthrough scientific discoveries and help solve the world’s toughest problems,” said Trish Damkroger, senior vice president and general manager, HPC & AI Infrastructure Solutions at HPE. “We are proud of the strong partnership with the U.S. Department of Energy, Argonne National Laboratory, and Intel to realise a system of this scale and magnitude that was made possible through our joint innovative engineering, multiple teams, and most importantly, shared value of delivering state-of-the-art technology to fuel science and benefit humankind.”
Exascale computing represents a quantum leap in processing power, capable of performing one quintillion operations per second. This extraordinary capability enables scientists to tackle some of humanity’s most complex and pressing problems. Aurora is constructed using the HPE Cray EX supercomputer, designed specifically to handle the immense scale and demands of exascale computing. It also features the largest deployment of open, Ethernet-based supercomputing interconnect with HPE Slingshot, connecting 75,000 compute node endpoints, 2,400 storage and service network endpoints, and 5,600 switches. This sophisticated network architecture enhances performance by ensuring high-speed communication across Aurora's 10,624 compute blades, powered by 21,248 Intel® Xeon® CPU Max Series processors and 63,744 Intel® Data Center GPU Max units, making it one of the largest GPU clusters in existence. Aurora’s design as an AI-capable system from the ground up enables researchers to leverage generative AI models to accelerate scientific discovery. Early applications of AI on Aurora include intricate brain mapping to decode the human brain’s 80 billion neurons, advancing high-energy particle physics through deep learning, and expediting drug design and discovery via machine learning.
“Aurora is a first-of-its-kind supercomputer and we expect it to be a game-changer for researchers,” said Rick Stevens, associate laboratory director and distinguished fellow at Argonne National Laboratory. “Reaching this milestone with a second exascale system in the U.S. is an incredibly significant achievement that will advance open science initiatives globally.”
The creation of the Aurora exascale supercomputer is a testament to the robust partnership between HPE, Intel, the U.S. Department of Energy, and Argonne National Laboratory. This collaborative effort exemplifies the vital role of private-public partnerships in driving scientific and technological advancements. Through the Aurora Early Science Program, researchers have successfully optimised and stress-tested the system, running a wide range of programming models, languages, and applications, demonstrating the system's versatility and robustness.
“The Aurora supercomputer was designed to support the research and science communities within the HPC and AI space,” said Ogi Brkic, Intel vice president and general manager, of Data Center AI Solutions. “Our ongoing collaboration with Argonne National Laboratory and HPE has resulted in promising early science success stories. And we’re excited to see what’s to come as we optimize system performance to accelerate the science and march toward what is next.”
Aurora's achievement of exascale computing on a partial run, utilizing 9,234 of its total nodes, marks a significant milestone. Housed at the Argonne Leadership Computing Facility (ALCF), a part of the U.S. Department of Energy’s Office of Science user facility, Aurora stands as an open science system. This monumental installation underscores the profound impact of exascale computing, heralding a new era of scientific exploration and discovery.
Comments