Intel’s Aurora becomes the fastest AI system by achieving exascale computing

by

in

– Intel, Argonne National Laboratory, and HPE collaborated to create the Aurora supercomputer, which reached speeds of 1.012 exaflops.
– The supercomputer is AI-focused and has the potential to revolutionize scientific discovery.
– Aurora is powered by Intel Data Center GPU Max Series and innovative Intel Xe GPU architecture, enabling groundbreaking research and development in various fields.

Intel, in collaboration with Argonne National Laboratory and Hewlett Packard Enterprise (HPE), has announced that their Aurora supercomputer has surpassed the exascale computing threshold, reaching speeds of 1.012 exaflops. This makes Aurora the fastest AI-focused system, with the potential to aid in significant scientific discoveries.

Ogi Brkic, Intel’s VP and GM of Data Centre AI Solutions, believes that the Aurora supercomputer’s achievement will lead to groundbreaking discoveries in various fields, including climate patterns and the mysteries of the universe. Supercomputers like Aurora play a vital role in tackling complex scientific challenges that can benefit humanity.

Aurora is not only known for its speed but also for its innovation and utility. The supercomputer is designed as an AI-centric system, allowing researchers to utilize generative AI models and accelerate scientific discovery. It has already produced remarkable work, such as mapping the human brain’s neurons and advancing drug design through machine learning.

The core of Aurora is powered by the Intel Data Center GPU Max Series, based on the Intel Xe GPU architecture, optimized for AI and HPC tasks. This technology enables parallel processing capabilities necessary for handling complex neural network computations. The supercomputer boasts a large GPU cluster, consisting of 166 racks, 10,624 compute blades, and 63,744 Intel Data Center GPU Max Series units.

Intel is also expanding its Tiber Developer Cloud to support the evaluation, innovation, and optimization of AI models and workloads on a larger scale. They are dedicated to advancing HPC and AI into new realms of discovery and innovation, with new supercomputers integrating Intel technologies expected to transform scientific fields like climate change modeling and fusion energy breakthroughs.

Source link