Jacobi and Gauss-Seidel preconditioned complex conjugate gradient method with GPU acceleration for finite element method

In this paper two implementations of iterative solvers for solving complex symmetric and sparse systems resulting from finite element method applied to wave equation are discussed. The problem under investigation is a dielectric resonator antenna (DRA) discretized by FEM with vector elements of the second order (LT/QN). The solvers use the preconditioned conjugate gradient (pcg) method implemented on Graphics Processing Unit (GPU) along with two preconditioning techniques. Some of the proposed GPU implementations show remarkable speedup comparing to CPU-based implementation. Convergence of GPU and CPU implementations issue is also discussed.