The Portland Group has released a Fortran compiler for NVIDIA CUDA, you can find it over here.
Graphic processing units or GPUs have evolved into programmable, highly parallel computational units with very high memory bandwidth. GPU designs are optimized for the computations found in graphics rendering, but are general enough to be useful in many data-parallel, compute-intensive programs common in high-performance computing (HPC).
CUDA™ is the architecture of the NVIDIA line of GPUs. Currently, the CUDA programming environment is comprised of an extended C compiler and tool chain, known as CUDA C. CUDA C allows direct programming of the GPU from a high level language.
PGI and NVIDIA announced in June 2009 that they are working in cooperation to develop CUDA Fortran. CUDA Fortran includes a Fortran 2003 compiler and tool chain for programming NVIDIA GPUs using Fortran. PGI will support CUDA Fortran with a release of its Fortran compiler later in 2009.