NVIDIA's GH200 Grace Hopper Superchip offers strong potential for accelerating large-scale AI and HPC workflows through its tightly integrated CPU-GPU architecture. In this talk, we share CU Boulder Research Computing’s first-hand experience providing GH200 nodes to users. We'll cover the GH200 architecture, our approach to the software stack, an overview of our beta testing phase, and successful use cases on the GH200s. We'll conclude with future plans for the GH200 resources and provide guidance on how RMACC members can gain access to these GH200s for their research.
