Nvidia has partnered with the Georgia Institute of Technology to deploy the first artificial intelligence supercomputer hub designed for student use.
The initiative, dubbed the AI Makerspace, aims to democratize access to computing resources that are usually the preserve of large tech companies. Students will be able to access the cluster online for projects related to computer vision, large language models, robotics, generative AI design, and chemical or biomedical engineering.
Interconnected with a Nvidia Quantum-2 InfiniBand networking platform, the supercomputer is comprised of 20 Nvidia HGX H100 systems and 160 Nvidia H100 Tensor Core GPUs. No information about the total compute power offered by the Makerspace was provided but each individual eight-GPU HGX H100 system is capable of achieving 480 teraflops of FP64 compute power, meaning the system could potentially offer around 10 AI petaflops of compute power.
Georgia Tech said the system has been deployed by Penguin Solutions (formerly Penguin Computing), which has also provided a virtual gateway to the high-performance computing environment.
Students and staff will also have access to Nvidia’s Deep Learning Institute resources, including Nvidia workshops, certifications, curriculum-aided teaching kits, and access to the company’s developer community network.
“The launch of the AI Makerspace represents another milestone in Georgia Tech’s legacy of innovation and leadership in education,” said Raheem Beyah, dean of the College and Southern Company Chair. “Thanks to Nvidia’s advanced technology and expertise, our students at all levels have a path to make significant contributions and lead in the rapidly evolving field of AI.”