/cdn.vox-cdn.com/uploads/chorus_asset/file/23962442/acastro_STK067__03.jpg)
/cdn.vox-cdn.com/uploads/chorus_asset/file/24247717/lp_logo_3.0.jpg){kind=logo}
/cdn.vox-cdn.com/uploads/chorus_asset/file/24016885/STK093_Google_04.jpg)
/cdn.vox-cdn.com/uploads/chorus_asset/file/24808816/Starfield__The_Settled_Systems___Supra_Et_Ultra_____Starfield__The_Settled_Systems___Su)
[ad_1]
Argonne National Laboratory’s most powerful supercomputer is now complete, and its creators, together with Intel, HPE and the Department of Energy, are expected to bring it online by the end of this year.
According to the laboratory“Aurora will theoretically be able to deliver more than two exaflops of computing power, or more than 2 billion billion calculations per second.”
Behind the astonishing performance figures are thousands of chips, although with quantum computing progressing rapidly, this could be a truly one-of-a-kind supercomputer that leads the way to the future.
aurora supercomputer
At least 10,624 70-pound rectangular blades make up the supercomputer, the last of which was successfully installed on June 22. The blades are housed in 166 racks, each with 64 blades. Spread across eight rows, Argonne says the Aurora occupies the space of two professional basketball courts in its ALCF data center.
Each blade houses two Intel Xeon Max Series CPUs, six Intel Max Series GPUs, memory, networking and cooling technologies.
ALCF project director for Aurora, Susan Coghlan, said: “We’re looking forward to putting Aurora through its paces to make sure everything works as intended, before handing the system over to the wider scientific community. “
Other key figures include 63,744 Intel data center GPU Max series ‘Ponte Vecchio’ and 21,248 Intel Xeon CPU Max series ‘Sapphire Rapids’ processors, as well as more than 1,024 storage nodes with a total capacity of 220 petabytes and a total bandwidth of 31 terabytes per second is the max. ,
Intel and its partners hope that all of this will enable more efficient and powerful supercomputing when it comes to running models to help tackle the world’s problems, such as climate change and other anthropogenic matters.
Meanwhile, Rick Stevens, associate laboratory director at Argonne National Laboratory, said: “While we work towards acceptance testing, we’re looking forward to using Aurora to train some large-scale open-source generative AI models for science.” going to do.”
