Intel, in collaboration with Argonne National Laboratory and Hewlett Packard Enterprise (HPE), has revealed that its Aurora supercomputer has exceeded the exascale computing threshold reaching speeds of 1.012 exaflops to turn into the quickest AI-focused system.
“The Aurora supercomputer surpassing exascale will permit it to pave the highway to tomorrow’s discoveries,” mentioned Ogi Brkic, Intel’s VP and GM of Knowledge Centre AI Options. “From understanding local weather patterns to unravelling the mysteries of the universe, supercomputers function a compass guiding us towards fixing actually tough scientific challenges which will enhance humanity.”
Aurora has not solely excelled in velocity but additionally in innovation and utility. Designed from the outset as an AI-centric supercomputer, Aurora allows researchers to leverage generative AI fashions, considerably accelerating scientific discovery.
Groundbreaking work has already been achieved utilizing Aurora, together with mapping the 80 billion neurons of the human mind, enhancing high-energy particle physics with deep studying, and accelerating drug design and discovery by machine studying.
On the core of Aurora lies the Intel Knowledge Middle GPU Max Collection, constructed on the modern Intel Xe GPU structure, optimised for each AI and HPC duties. This technological basis allows parallel processing capabilities, essential for dealing with advanced neural community AI computations.
Particulars shared in regards to the supercomputer spotlight its grand scale, consisting of 166 racks, 10,624 compute blades, 21,248 Intel Xeon CPU Max Collection processors, and 63,744 Intel Knowledge Middle GPU Max Collection models, making it the most important GPU cluster worldwide.
Alongside the {hardware}, Intel’s suite of software program instruments – together with the Intel® oneAPI DPC++/C++ Compiler and an array of efficiency libraries – enhance developer flexibility and system scalability.
Intel can also be increasing its Tiber Developer Cloud, incorporating new state-of-the-art {hardware} and enhanced service capabilities to assist the analysis, innovation, and optimisation of AI fashions and workloads on a big scale.
Wanting ahead, the deployment of recent supercomputers built-in with Intel applied sciences is predicted to remodel numerous scientific fields. Methods like CMCC’s Cassandra will advance local weather change modelling, whereas ENEA’s CRESCO 8 helps breakthroughs in fusion vitality, amongst others, underscoring Intel’s dedication to advancing HPC and AI into new realms of discovery and innovation.
(Picture Credit score: Intel)
See additionally: Chuck Ros, SoftServe: Delivering transformative AI solutions responsibly
Need to be taught extra about AI and large knowledge from business leaders? Try AI & Big Data Expo going down in Amsterdam, California, and London. The excellent occasion is co-located with different main occasions together with Intelligent Automation Conference, BlockX, Digital Transformation Week, and Cyber Security & Cloud Expo.
Discover different upcoming enterprise know-how occasions and webinars powered by TechForge here.