OAKLAND, Calif. Nov 14(Reuters) – Silicon Valley startup Cerebras Systems, known in the industry for its dinner plate-sized chip made for artificial intelligence work, on Monday unveiled its AI supercomputer called Andromeda, which is now available for commercial and academic research.
Andromeda is built by linking up 16 Cerebras CS-2 systems, the company’s latest AI computer built around the over-sized chip called the Wafer-Scale Engine 2.
Cerebras said Andromeda can perform 1 exaflop worth of AI computing – or at least one quintillion (10 to the power of 18) operations per second – based on a precision of 16 bit floating point format.
The fastest U.S. supercomputer that is capable of doing nuclear weapons simulations called the Frontier at Oak Ridge National Laboratory breached the 1 exaflop performance based on 64 bit double precision format this year.
“They’re a bigger machine. We’re not beating them. They cost $600 million to build. This is less than $35 million,” said Andrew Feldman, founder and CEO of Cerebras when asked about the Frontier supercomputer.
He said that while complicated nuclear simulations and weather simulations historically ran in 64 bit double precision computers, this is a computationally expensive format, so researchers are looking into whether AI algorithms can eventually match such outcomes.
Feldman said Andromeda is owned by Cerebras and built at a high performance data center in Santa Clara, California called Colovore. Companies and researchers, including those from U.S. national labs can access it remotely, he said.