Using GPU's to Accelerate Stencil-based Computation Kernels for the Development of Large Scale Scientific Applications on Heterogeneous Systems

摘要

We present CaCUDA - a GPGPU kernel abstraction and a paral-lel programming framework for developing highly efficient large scale scientific applications using stencil computations on hybrid CPU/GPU architectures. CaCUDA is built upon the Cactus com-putational toolkit, an open source problem solving environment de-signed for scientists and engineers. Due to the flexibility and exten-sibility of the Cactus toolkit, the addition of a GPGPU program-ming framework required no changes to the Cactus infrastructure, guaranteeing that existing features and modules will continue to work without modification. CaCUDA was tested and benchmarked using a 3D CFD code based on a finite difference discretization of Navier-Stokes equations.