Gaining improved performance from computers has always been a major concern. One approach is to use devices such as graphics processing units; another approach involves AI accelerator chips to speed up machine learning models. Using accelerators effectively, however, remains a challenge. Argonne scientists will describe their work on developing a RISC-V Accelerator, which can be customized for AI tasks such as deep learning. Ian Foster, director of Argonne’s Data Science and Learning division, will give an invited presentation on trillion-parameter foundation models as discovery accelerators. And Murali Emani, a computer scientist in the Argonne Leadership Computing Facility, will lead a Birds of a Feather session on the topic democratizing AI accelerators for HPC applications. He will also join colleagues in a tutorial on programming novel AI accelerators for scientific computing.