Supercomputing for Science and AI
Supercomputers empower us to tackle the most challenging problems in scientific simulation by achieving unprecedented levels of performance. This talk will explore how today’s exascale-class supercomputers are driving breakthroughs across disciplines, from unraveling the mysteries of the universe to training large AI models.
These cutting-edge systems integrate the most powerful processors and accelerators, scaled to tens or even hundreds of thousands of nodes while leveraging ultra-low-latency, high-bandwidth networking. Paired with specialized software, they unleash immense parallel performance potential, enabling researchers and engineers to address the world’s most complex computational challenges with precision and speed.
The presentation will provide an overview of the technology underlying these supercomputers and showcase key use cases from our national labs. These examples will highlight how exascale computing is revolutionizing scientific discovery, pushing the boundaries of AI advancement, and exploring solutions for some of humanity's most pressing problems.
Programming descriptions are generated by participants and do not necessarily reflect the opinions of SXSW.
Judy Hill
Lawrence Livermore National Laboratory
Mike Ignatowski
AMD