high performance computing on graphics processing units: hgpu.org

There are several possibilities to speed-up an iterative solver, e.g. by applying an efficient preconditioner to decrease the number of required iterations, or by parallelizing the given algorithm, etc. To acquire maximum performance from a massively parallelized environment, different parts of such a solver must be asynchronously parallelized to avoid expensive cooperation between threads. The aim of this work is to introduce a parallel computing environment, the Graphic Processing Unit (GPU) [1, 2], to accelerate the matrix multiplication of the conjugate gradient solver applied to wave propagation problems.