Aurora supercomputer breaks exascale barrier

Aurora’s pace and synthetic intelligence capabilities will rework scientific analysis and allow breakthroughs in among the world’s most urgent challenges, from local weather and supplies science to vitality storage and fusion vitality.

The Aurora supercomputer on the U.S. Division of Vitality’s (DOE) Argonne Nationwide Laboratory has formally surpassed the exascale threshold, measuring greater than a quintillion calculations per second on the brand new Top500 record. The outcomes have been introduced right now on the ISC High Performance 2024 conference in Hamburg, Germany.

In its newest submission to the semi-annual record of the world’s strongest supercomputers, Aurora registered 1.012 exaflops utilizing 87% of the system’s 10,624 nodes. After making its Top500 debut in November 2023, the Argonne system retained its spot because the second quickest supercomputer and joined DOE’s Oak Ridge Nationwide Laboratory’s Frontier because the world’s second exascale machine. Aurora additionally earned the highest spot in a measure of synthetic intelligence (AI) efficiency, attaining 10.6 exaflops on the HPL-MxP benchmark.

“We’re thrilled to see Aurora join the exascale club,” mentioned Michael Papka, director of the Argonne Management Computing Facility (ALCF), a DOE Workplace of Science person facility at Argonne. “I’m extremely proud of the Aurora team’s ongoing efforts to get the system up and running for the research community. We can’t wait to see what the full system will be capable of.”

As one of many world’s quickest supercomputers, Aurora offers scientists a strong new software for finishing up analysis involving simulation, AI and knowledge evaluation. The state-of-the-art system is not going to solely allow breakthroughs in science and engineering but in addition spur new advances in know-how and bolster the nation’s innovation infrastructure.

“Aurora is fundamentally transforming how we do science for our country,” Argonne Laboratory Director Paul Kearns mentioned. “It will accelerate scientific discovery by combining high performance computing and AI to fight climate change, develop life-saving medical treatments, create new materials, understand the universe and so much more.”

“Aurora excels at tackling both traditional scientific computing problems and AI-powered research,” added Rick Stevens, Argonne’s affiliate lab director for Computing, Setting and Life Sciences. “As AI continues to reshape the scientific landscape, Aurora gives us a platform to develop new tools and approaches that will significantly accelerate the pace of research.”

Constructed by Intel and Hewlett Packard Enterprise (HPE), Aurora’s first-of-its-kind structure contains new applied sciences being deployed at an unprecedented scale. The supercomputer’s 63,744 graphics processing models (GPUs) make it the world’s largest GPU-powered system but. It additionally has extra endpoints in its interconnect know-how than another system so far.

The Aurora set up staff, which incorporates workers from Argonne, Intel and HPE, continues to work by way of system validation, verification and scale-up actions. Their work has included addressing varied {hardware} and software program points that emerge as the huge system nears full-scale operations.

Groups taking part within the ALCF’s Aurora Early Science Program and DOE’s Exascale Computing Venture have been making ready to run their analysis tasks on Aurora for the previous a number of years. The groups have demonstrated robust early efficiency good points whereas scaling and optimizing codes for the system. The preliminary Aurora tasks embrace efforts to advance analysis in cosmology, fusion vitality science, drug discovery and the design of recent supplies for clear vitality applied sciences.

“Hitting exascale is a huge milestone but enabling groundbreaking science is the ultimate goal,” mentioned Susan Coghlan, ALCF challenge director for Aurora. “The new performance numbers, along with some promising runs from our early science teams, give us a glimpse of what will be possible with Aurora.”