Blasting Through Lattice Calculations using CUDA

Modern graphics hardware is well suited to highly parallel nu-merical tasks and provides significant cost and performance benefits. Graphics hardware vendors are now making avail-able development tools to support high performance comput-ing. NVIDIA’S CUDAplatform, in particular, offers direct access to graphics hardware through a programming language similar to C. Using the CUDA platform we have implemented a Dirac-Wilson operator which runs at an effective 68 Gigaflops on the Tesla C870 GPU. The recently released GTX 280 GPU runs this same code at 92 Gigaflops and we expect improvement pending code optimization.