The HPC Project initiative has introduced the first version of the Par4all open parallelization platform. Par4all includes automatic code generation for NVIDIA GPU-based hybrid machines. The HPC Project and the computer research center [CRI] at the French Ecole des Mines in Paris have now released the first version.
From their release:
Par4all 1.0 is dedicated to hybrid computing approaches using GPU (graphic processing units). From a C or FORTRAN application, Par4all automatically generates a parallel code including CUDA compilable on NVIDIA GPU. The generated code is readable and completely traceable with the original code without any calls to the Par4all tool chain. The original code remains the reference and future other technological choices are open. The whole process works like a usual compilation.
By the end of 2010, Par4all will also include optimizations for the latest NVIDIA Fermi platform. For more info, check out their website here.