Solvers That Don't Choose Sides - sTiles: Faster Linear Algebra for the Computations that Run Underneath Your Models
In this talk, I will present our work toward productive, precision-aware scientific computing, beginning with high-level programming abstractions in Julia.
Overview
Sparse or dense is a verdict most solvers make once for an entire matrix; sTiles makes it tile by tile, covering the full range from sparse to fully dense in a single solver and outpacing the established sparse direct solvers.
Presenters
Brief Biography
Esmail Abdul Fattah holds a Ph.D. in Statistics from KAUST, where he is now a postdoctoral researcher in high-performance computing. His work connects the two fields to scale Bayesian inference, bringing HPC to approximate methods such as INLA. This includes GPU-accelerated sparse factorizations and selected inversion for structured matrices through the sTiles framework, and extending INLA to non-sparse models. He also works on applications in spatial and spatio-temporal disease mapping. His Ph.D. research received KAUST's 2023 Al-Kindi Research Award.
Related People
Related Researchers
Esmail Abdul Fattah
- Postdoctoral Research Fellow, Statistics