The largest chip ever built, WSE-2 has transformed the artificial intelligence landscape, powering the industry’s fastest AI supercomputer, the Cerebras CS-2
SUNNYVALE, Calif. & MOUNTAIN VIEW, Calif.–(BUSINESS WIRE)–#AI—Cerebras Systems, the pioneer in accelerating artificial intelligence (AI) compute, and the Computer History Museum (CHM), the leading institution decoding technology – its computing past, digital present, and future impact on humanity – today unveiled a new display featuring Cerebras’ Wafer-Scale Engine (WSE). As the largest computer chip in the world, roughly the size of a dinner plate, WSE-2 contains 2.6 trillion transistors, 850,000 AI optimized cores, and is optimized in every way for AI work.
“At CHM, we are dedicated to decoding the history and impact of computing and technological innovation on the human experience,” said Dan’l Lewin, President & CEO, Computer History Museum. “Cerebras Systems’ extraordinary accomplishment of inventing the world’s first and only wafer-scale processor marks a key milestone in the history of computing, and we’ve only just begun to see the incredible impact that Cerebras Systems and their customers are having across AI for drug discovery, climate change, cancer research, and so much more.”
“It is the honor of a lifetime to be accepted into the Computer History Museum’s world-renowned collection,” said Andrew Feldman, CEO and co-founder of Cerebras Systems. “When we started Cerebras, we set out to transform the compute landscape. For us, that meant doing fearless engineering in relentless pursuit of the extraordinary. In the process, our team was able to overcome challenges across design, fabrication and packaging – all of which had been considered impossible for the entire 70-year history of computers – and create the world’s first wafer-scale processor. I am incredibly proud of our team and grateful to CHM for adding us to their collection and preserving our collective history.”
In AI, chip size is profoundly important. Big chips process information more quickly, producing answers in less time. As the largest chip ever made – 56 times larger than the competition – the WSE-2 powers the Cerebras CS-2, the industry’s fastest AI computer. The WSE-2 is manufactured by TSMC on its 7nm-node and is the second-generation Wafer Scale Engine. The WSE-2 was delivered less than two years after the WSE-1, and more than doubles all performance characteristics – the transistor count, core count, memory, memory bandwidth and fabric bandwidth. Not only did Cerebras build the largest chip in the history of the computer industry, they showed that it could quickly and easily be shrunk to new fabrication geometries.
On every performance metric, the WSE-2 is orders of magnitude faster than legacy graphics processing units. The CS-2 provides the deep learning compute resources equivalent to hundreds of GPUs, while providing the ease of programming, management and deployment of a single device.
“There are more transistors – by far – in this one Cerebras chip, than in all 100,000 computing objects in the Museum’s permanent collection combined,” said Dag Spicer, Senior Curator, Computer History Museum.
With every component optimized for AI work, the CS-2 delivers more compute performance at less space and less power than any other system. It does this while radically reducing programming complexity, wall-clock compute time, and time to solution. Depending on workload, from AI to HPC, CS-2 delivers hundreds or thousands of times more performance than legacy alternatives. A single CS-2 replaces clusters of hundreds or thousands of GPUs that consume dozens of racks, use hundreds of kilowatts of power, and take months to configure and program. At only 26 inches tall, the CS-2 fits in one-third of a standard data center rack.
With customers in North America, Asia, Europe and the Middle East, Cerebras Systems is delivering industry leading AI solutions to a growing roster of customers in the enterprise, government, and high performance computing (HPC) segments, including GlaxoSmithKline, AstraZeneca, TotalEnergies, nference, Argonne National Laboratory, Lawrence Livermore National Laboratory, Pittsburgh Supercomputing Center, Leibniz Supercomputing Centre, National Center for Supercomputing Applications, Edinburgh Parallel Computing Centre (EPCC), National Energy Technology Laboratory, and Tokyo Electron Devices.
For more information on the new WSE display at the Computer History Museum, please tune into a livestream conversation on Wednesday, August 3 at 2:30 pm PT with Cerebras Systems CEO Andrew Feldman and Computer History Museum President & CEO Dan’l Lewin https://www.youtube.com/computerhistory/live.
About Cerebras Systems
Cerebras Systems is a team of pioneering computer architects, computer scientists, deep learning researchers, and engineers of all types. We have come together to build a new class of computer system, designed for the singular purpose of accelerating AI and changing the future of AI work forever. Our flagship product, the CS-2 system is powered by the world’s largest processor – the 850,000 core Cerebras WSE-2 enables customers to accelerate their deep learning work by orders of magnitude over graphics processing units.