CUDA Fortran Compiler
CUDA is the architecture of the NVIDIA line of GPUs. CUDA Fortran includes a Fortran 2003 compiler and tool chain for programming NVIDIA GPUs using Fortran. The system supports four key abstractions: cooperating threads organized into thread groups, shared memory and barrier synchronization within thread groups, and coordinated independent thread groups organized into a grid. The CUDA threads are organized into thread blocks, and each thread has a global thread block index, and a local thread index within its thread block.