Intel’s most powerful supercomputer ready to power up

Argonne National Laboratory’s most powerful supercomputer is ready, and the lab, along with Intel, HPE and the Department of Energy, hopes to have it up and running by the end of this year.

“Theoretically, Aurora will be able to do more than two computing exaflops, which is more than 2 billion calculations per second,” the lab says.

The staggering performance numbers are made possible by thousands of chips. However, quantum computing seems to be just around the corner, so this could be a unique machine that leads the way into the future.

Aurora Supercomputer

The supercomputer is made up of 10,624 rectangular sheets that weigh 70 pounds each. The last one was safely installed on June 22. The blades are stored in 166 racks containing 64 blades each. At its ALCF data center, Argonne says Aurora occupies the space of two professional basketball courts. This is because it is made up of eight rows.

Each blade contains memory, networking, cooling, two Intel Xeon Max Series CPUs, six Intel Max Series GPUs, and other components.

Aurora project manager at ALCF, Susan Coghlan, stated, “We look forward to putting Aurora through its paces to make sure everything works as intended before releasing the system to the broader scientific community.”

63,744 Intel Data Center GPU Max Series “Ponte Vecchio” processors and 21,248 Intel Xeon CPU Max Series “Sapphire Rapids” processors are also included in the headline numbers, along with more than 1,024 storage nodes with a combined capacity of 220 petabytes and a maximum bandwidth of 31 terabytes per second.

See also  Apple introduces iPhone 13 Pro and iPhone 13 Pro Max with 120 Hz display

All of this, according to Intel and its partners, should make supercomputing more efficient and powerful when it comes to running models to tackle problems like fighting climate change and other anthropogenic problems.

According to Rick Stevens, associate laboratory director at Argonne National Laboratory, “we’re going to be using Aurora to train some large-scale open source generative AI models for science” as we move toward acceptance testing.

Subscribe to our latest newsletter

To read our exclusive content, sign up now. $5/month, $50/year

Categories: Technology
Source: vtt.edu.vn

Leave a Comment