Intel, in collaboration with Argonne National Laboratory and Hewlett Packard Enterprise (HPE), has claimed that its Aurora supercomputer has broken the exascale barrier with 1,012 exaflops and is also the “world’s fastest AI system dedicated to AI for open science” by achieving 10.6 AI exaflops.
Aurora is slightly behind the Frontier system at Oak Ridge National Laboratory in Tennessee, which previously achieved 1,206 exaflops, but being the second supercomputer to break the exascale barrier is a huge achievement, especially considering that Aurora is still in operation. and is not yet completely complete.
HPC thread placed it at number 2 in his top 500 list in November 2023. But that ranking was achieved because only “half of Aurora ran the HPL benchmark.” In the most recent rankings announced in May 2024Aurora was still in second place (behind Frontier), but the new HPL score improved significantly from the previously recorded 585.34 petaflops.
Paving the way for tomorrow’s discoveries
Designed from the ground up for AI research, Aurora consists of 10,624 compute blades, 21,248 Intel Xeon CPU Max Series processors, and 63,744 Intel Data Center GPU Max Series units, all housed in 166 racks.
Ogi Brkic, Intel’s vice president and general manager of Data Center AI Solutions, said: “The Aurora exascale supercomputer will enable it to pave the way for tomorrow’s discoveries. From understanding climate patterns to unraveling the mysteries of the universe, supercomputers serve as a compass that guides us to solving truly difficult scientific challenges that can improve humanity.”
Future plans for Aurora range from climate change modeling to breakthroughs in fusion energy, atomistic simulations and tackling memory-related problems in the design of future power plants.
If you’re interested in seeing what Aurora looks like, the Argonne National Laboratory has provided a tour that you can view below.