Middleware for Programming NVIDIA GPUs From Fortran 9X

There is a revolution taking place in computing with the availability of commodity graphical processors capable of several hundred gigaflop performance and with multicore CPUs. Using these it should be possible to have relatively inexpensive teraflop workstations. These machines however are not so easily programmed, and scientific computing may not map on to them. Over the past year, the major graphics vendors have realized there is a market for these in HPC, and have started producing tools to allow programming them from high level languages, ATI's Close-To-Machine (CTM) and NVIDIA's CUDA.