Free Shipping on orders over US$39.99 How to make these links

Computer History Museum Honors Cerebras Systems with New Display for Wafer-Scale Engine


SUNNYVALE, Calif. & MOUNTAIN VIEW, Calif.–(BUSINESS WIRE)–Cerebral Systems, the pioneer in accelerating artificial intelligence (AI) computation, and the Computer History Museum (CHM), the leading institution for decoding technology – computing’s past, digital present, and future impact on humanity – today opens a new display showing Cerebras’ Wafer-Scale Makina (WSE). As the world’s largest computer chip, roughly the size of a dinner plate, WSE-2 has 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 achievement in inventing the world’s first and only wafer-scale processor marks an important milestone in the history of computing, and we are only just beginning to see the incredible impact that will have of Cerebras Systems and their customers across AI. drug discovery, climate change, cancer research, and more.”

“This 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 change 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 throughout design, fabrication and packaging – all of which were considered impossible for the entire 70-year history of computers – and created the world’s first wafer-scale processor. I am very proud of our team and grateful to CHM for adding us in their collection and preservation of our collective history.

In AI, chip size matters a lot. Larger chips process information faster, producing responses 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 at its 7nm-node and is the second generation Wafer Scale Engine. WSE-2 was delivered less than two years after WSE-1, and more than doubled 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 demonstrated that it can be quickly and easily reduced to new fabrication geometries.

In every performance metric, the WSE-2 is faster than legacy graphics processing units. CS-2 provides deep learning computing resources equivalent to hundreds of GPUs, while providing ease of programming, management and deployment on 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, CS-2 delivers more compute performance in less space and less power than any other system. It does this while radically reducing programming complexity, wall clock computation time, and solution time. Depending on the workload, from AI to HPC, CS-2 delivers hundreds or thousands of times more performance than legacy replacements. 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 into one-third of a standard data center rack.

With customers in North America, Asia, Europe and the Middle East, Cerebras Systems delivers industry-leading AI solutions to a growing roster of enterprise, government, and high performance computing (HPC) customers. parts, including GlaxoSmithKline, AstraZeneca, TotalEnergies, nference, Argonne National Laboratory, Lawrence Livermore National Laboratory, Pittsburgh Supercomputing Center, Leibniz Supercomputing Center, National Center for Supercomputing Applications, Edinburgh Parallel Computing Center (EPCC), National Energy Technology Laboratory, and Tokyo Electron Devices.

For more information on the new WSE display at the Computer History Museum, please tune in to 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 group of pioneering computer architects, computer scientists, deep learning researchers, and engineers of all kinds. We are coming together to build a new kind of computing system, designed for the single 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 allows customers to accelerate their deep learning workloads by orders of magnitude size of graphics processing units.



Source link

We will be happy to hear your thoughts

Leave a reply

Info Bbea
Logo
Enable registration in settings - general
Compare items
  • Total (0)
Compare
0
Shopping cart