Maryam Mehri Dehnavi University of Toronto, Canada The Power of Less: Harnessing Sparsity for Performance Optimization
Bronson Messer Oak Ridge National Laboratory, U.S. Frontier: The World’s Most Powerful Computer for Science
Simon McIntosh-Smith University of Bristol, United Kingdom Performance Portability in the Age of Diverse Exascale Architectures
Barry Smith Flatiron Institute, Simons Foundation, U.S. Prospects for Efficient General-purpose Algebraic Solver Libraries for Multi-node GPU System
Rasmus Tamstorf U.S. Do We Still Need Floating Point Arithmetic?
Ana Lucia Varbanescu University of Twente, Netherlands Towards Zero-waste Computing Through Co-design: The Case of Graph Processing
Mohamed Wahib Riken Center for Computational Science, Japan Challenges of Scaling Deep Learning on HPC Systems