Intel Aurora Supercomputer Ready To Break Records With Nearly 64K GPUs Across 10K Blades

Intel's Data Center Max products are very impressive, but you may have had a hard time getting your hands on one even though they officially launched way back in November of last year. How come? Because they've all been going to Argonne National Laboratory. The Aurora supercomputer hosted there was planned to host 10,624 compute blades, each with two Xeon Max CPUs and six Intel Max Series GPUs—that's Ponte Vecchio, if you weren't paying attention when we told you about it before.




Intel crows that Aurora should be the fastest supercomputer in the world, at least by the measure of the TOP500 list. In fact, it expects that Aurora will be the first 2-exaflop system. That number is so large it's hard to even imagine, but it's two quintillion floating-point operations per second, or 2,000,000,000,000,000,000. It's two-thousand petaflops, or two million TFLOPS in slightly more familiar units. This comes after AMD stole the 1-exaflop landmark with Frontier late last year.


What exactly will all this power be used for? Well, you know, stuff. Jokes aside, Intel says that Aurora will be used for the usual supercomputer HPC stuff: fluids simulation, neuron and photon transport simulations, electronic structure calculations, fusion plasma simulations (as shown in the slide above), and of course, developing generative AI models.


Using Aurora, Intel, HPE, and Argonne are apparently working on a state-of-the-art generative AI model trained using "general text, scientific texts, scientific data, and code" with 1 trillion parameters. For perspective on that number, the popular Stable Diffusion only has 890 million parameters. Of course, number of parameters isn't everything; Stable Diffusion produces markedly better results than models like DALL-E 2 which came before, and which had over 3.5 billion parameters. Intel hopes the new model will be applicable to all types of research.

Despite the announcement today that the system is fully-loaded with its compute blades, there's no hard performance data to talk about from the full system. Intel boasts of great results from its CPUs and GPUs inside the Aurora—40% faster than the competition in "real-world HPC", twice as fast as AMD's MI250X on OpenMC—but we won't know if the whole machine met its goals until the TOP500 list is updated this November.