Meta has formed a partnership with British semiconductor firm Arm to develop a new class of CPUs to support growing AI workloads and general purpose computing. CPUs are the processors in computers that make AI training and inference possible, and as we work to build the next generation of AI and enable personal superintelligence for everyone, our data centers are outgrowing the abilities of traditional CPUs. Through a collaboration with Arm, Meta plans to co-develop multiple generations of cutting-edge CPUs built to enable massive compute power in limited space, supporting the AI-optimized data centers and large gigawatt-scale AI deployments that are central to AI innovations.
“Delivering AI experiences at global scale demands a robust and adaptable portfolio of custom silicon solutions, purpose built to accelerate AI workloads and optimize performance across Meta’s platforms. We worked alongside Arm to develop the Arm AGI CPU to deploy an efficient compute platform that significantly improves our data center performance density and supports a multi-generation roadmap for our evolving AI systems.”
– Santosh Janardhan, Head of Infrastructure, Meta
The first release, Arm AGI CPU, is Arm’s first ever data center CPU designed specifically for the AI era, delivering faster performance per rack far more efficiently than legacy CPUs. Meta will serve as the lead partner and co developer for the Arm AGI CPU, which has been developed to optimize infrastructure for Meta’s family of apps and work alongside its custom MTIA silicon. The Arm AGI CPU will be available to the broader AI ecosystem through Arm and the company says it will be releasing board and rack designs for this CPU under the Open Compute Project later this year.
