AWS has announced its plans to launch the Project Ceiba supercomputer, which will utilize 16,384 GH200 NVL32 Grace Hopper Superchips. This state-of-the-art computer is expected to provide an impressive 65 exaflops of AI performance and boast up to 9.5 petabytes of total memory. Once operational, it will become the most powerful cloud computer in the world.
According to Jensen Huang, the founder and CEO of Nvidia, "Generative AI is transforming cloud workloads and putting accelerated computing at the foundation of diverse content generation." He further adds, "Driven by a common mission to deliver cost-effective state-of-the-art generative AI to every customer, Nvidia and AWS are collaborating across the entire computing stack, spanning AI infrastructure, acceleration libraries, foundation models, to generative AI services."
AWS will be the first cloud provider to offer Nvidia GH200 Grace Hopper Superchips with multi-node NVLink technology. Each GH200 Superchip combines an Arm-based Grace CPU with an Nvidia Hopper architecture GPU on the same module. This groundbreaking technology allows a single Amazon EC2 instance with GH200 NVL32 to provide up to 20 TB of shared memory, enabling it to power terabyte-scale workloads.
"This new supercomputer will be set up inside of AWS infrastructure hosted by AWS and used to develop new AI for graphics, large language model research, image, video, 3D, generative AI, digital biology, robotics research, self-driving cars, and more," says Nvidia's Vice President, Ian Buck.
The launch of the Project Ceiba supercomputer marks a significant milestone in the field of cloud computing. With its unparalleled AI performance and massive memory capacity, it is poised to revolutionize various industries, from graphics and language model research to robotics and self-driving cars. AWS and Nvidia's collaboration demonstrates their commitment to delivering cutting-edge technology and advancing the field of generative AI.