Working on High Performance Computing and fundamental Numerical Analysis Algorithms for problems in science, engineering, and medicine.
The solutions to grand challenge problems in science and engineering require unprecedented computing power. Near future supercomputing platforms will rely on millions of possibly heterogeneous cores to deliver multi-petaflop performance. The design and deployment of algorithms that scale well on such platforms will be critical for exploiting the new architectures effectively. Nevertheless, few existing codes can scale to such large numbers of processors.
The mission of the Parallel Algorithms for Data Analysis and Simulation (PADAS) group is to integrate applied mathematics and computer science to design and deploy algorithms for grand challenge problems that scale to leadership computing platforms. The group is working on fundamental numerical and high performance computing algorithms for integral equations, partial differential equations, scientific machine learning, inverse problems, model reduction, and linear and nonlinear solvers.
Ongoing projects include applications tumor growth modeling, direct numerical simulation of particulate flows, medical image analysis, additive manufacturing, plasma physics, and remote sensing.