Robert Strzodka

TL;DR: Glift, an abstraction and generic template library for defining complex, random-access graphics processor (GPU) data structures, is presented and several new GPU data structures are characterized and implemented using reusable Glift components.

TL;DR: This survey paper compares native double precision solvers with emulated- and mixed-precision solvers of linear systems of equations as they typically arise in finite element discretisations and concludes that the mixed precision approach works very well with the parallel co-processors gaining speedup factors and area savings, while maintaining the same accuracy as a reference solver executing everything in double precision.

TL;DR: This paper extends previous work on a small GPU cluster by exploring the heterogeneous hardware approach for a large-scale system with up to 160 nodes, and leverages the high bandwidth of graphics processing units (GPUs) to increase the overall system bandwidth that is the decisive performance factor in this scenario.

TL;DR: This paper demonstrates that mixed precision schemes constitute a significant performance gain over native double precision and presents a new implementation of cyclic reduction for the parallel solution of tridiagonal systems and employs this scheme as a line relaxation smoother in a GPU-based multigrid solver.

TL;DR: This paper explores the coupling of coarse and fine-grained parallelism for Finite Element (FE) simulations based on efficient parallel multigrid solvers by addressing the issue of limited precision on GPUs by applying a mixed precision, iterative refinement technique.