The Portland Group has released PGI 2010, the latest release of its high-performance parallelising compilers and development tools for Linux, Mac OS X and Windows. The release includes full support for the PGI Accelerator Programming model v1.0 standard on x64 processor-based systems incorporating Nvidia Cuda-enabled Graphical Processing Units (GPUs). In addition to supporting high-level programming of accelerators using the PGI Accelerator programming model, the PGI Release 2010 also includes PGI Cuda Fortran, an explicit GPU programming model and application programming interface (API) that gives expert programmers direct control of all aspects of programming Nvidia GPUs.
The PGI Accelerator programming model is a collection of compiler directives used to specify regions of code in Fortran and C programs that can be offloaded from a host CPU to an attached accelerator to enhance performance. Applications optimised using the PGI Accelerator directives remain 100 per cent portable to other compilers and platforms, and execute on systems with or without a GPU accelerator.