Cerebras and Ranovus Secure $45M DARPA Contract for Advanced AI Computing System

Cerebras Systems, Ranovus win $45 million US military deal to speed up chip connections

SAN FRANCISCO, April 1 (Reuters) - Cerebras Systems, a Silicon Valley-based AI chip company, and Canadian chip startup Ranovus said on Tuesday that they had been awarded a $45 million contract from the U.S. military to speed up connections between computing chips. Cerebras, which aims to challenge Nvidia in the AI chip race, has already filed for an initial public offering. Unlike most competitors whose chips are a bit larger than a U.S. postage stamp, Cerebras makes chips the size of a dinner plate. It is betting its roughly foot-wide chip can outperform Nvidia's cluster of smaller chips. The contract with the Defense Advanced Research Projects Agency (DARPA) will focus on connecting Cerebras chips together with networking technology from Ranovus, an Ottawa, Ontario-based firm with backing from the Canadian government. Ranovus uses light, rather than electrical signals, to transfer information between chips more quickly and using less power. The challenge of integrating these optical connections directly with computing chips has kicked of a funding frenzy as startups seek different ways to solve the problem. Cerebras and Ranovus would not provide details on how they plan to tackle this, but said DARPA was looking for computing systems capable of simulating complex battlefields in real time. "We want to do something that's 150 times faster and uses three watts instead of 30," Cerebras CEO Andrew Feldman told Reuters on Monday. "That's why we brought the idea to DARPA. They have a reputation for providing funding for extremely difficult, extremely transformative projects." Ranovus has produced demonstration chips with Advanced Micro Devices (AMD.O), opens new tab and Taiwan's MediaTek (2454.TW), opens new tab, but said the collaboration with Cerebras will involve new technology that it has not yet shown. "What we plan to do together is something very different," Ranovus CEO Hamid Arabzadeh told Reuters. "There are new things that we have developed in the past year that we're going to bring into this project, which we haven't publicly announced." Reporting by Stephen Nellis in San Francisco; Editing by Himani Sarkar Our Standards: The Thomson Reuters Trust Principles., opens new tab Suggested Topics:Artificial Intelligence

Cerebras wins DARPA contract to build AI system with co-packaged optics - SiliconANGLE

Cerebras wins DARPA contract to build AI system with co-packaged optics Cerebras Systems Inc., the creator of a wafer-scale chip with nearly one million cores, has won a hardware development contract from the U.S. Defense Advanced Research Projects Agency. Reuters reported that the agreement is worth $45 million. As part of the project, Cerebras will develop a new "high-performance computing system" for DARPA. The system will combine the company's chip with co-packaged optics technology from Ranovus Inc., a Canadian semiconductor startup. Sunnyvale, California-based Cerebras develops a chip known as the WSE-3 (pictured) that is optimized for artificial intelligence workloads. It's the size of a silicon wafer and features four trillion transistors organized into 900,000 cores. There's also a 44-gigabyte pool of onboard SRAM memory. Cerebras positions the WSE-3 as a more efficient alternative to traditional graphics cards. In many cases, the chip's large onboard SRAM pool allows it to store all the data that AI models generate during processing. This removes the need to move data off the WSE-3 to external RAM. Because onboard SRAM is considerably more power-efficient than external RAM, the WSE-3 can move data to and from its cores using less electricity than graphics cards that have less onboard memory. The computing system that Cerebras is building for DARPA will also feature "wafer scale co-packaged optics" from Ranovus. According to Reuters, the latter technology will be used to link together multiple WSE-3 chips to create AI clusters. Data center operators often connect the servers in their AI clusters to one another with fiber-optic cables. Before data can travel over a fiber-optic cable, it has to be turned into light beams. After the light arrives at its destination, it has to be turned back into electrical signals to facilitate processing. Those tasks were historically performed by network devices called pluggable transceivers. Co-packaged optics technology seeks to remove the need for standalone pluggable transceivers. It does so by integrating a transceiver directly into the processors that power an AI cluster. According to Cerebras, integrating Ranovus's co-packaged optics with its chips will make customers' AI clusters more efficient and boost their network capacity in the process. "Cerebras will deliver a platform capable of real-time, high-fidelity simulations for the most challenging physical environment simulations and the largest scale AI workloads," said Cerebras Chief Executive Officer Andrew Feldman. The new hardware development contract is not the only project that Cerebras is carrying out for DARPA. The chipmaker is also involved in a second research initiative, the DRBE program, that seeks to create a virtual environment for testing wireless communications systems. The project will see Cerebras and its partners build a radio frequency "emulation supercomputer" for DARPA.