The latest release-candidate version enables software developers to port their applications to Nvidia Graphic Processor Units.

NVIDIA today announced the latest version of the NVIDIA CUDA Toolkit is available for free to parallel programming developers.

First announced February 2011, the NVIDIA CUDA 4.0 Toolkit features a number of capabilities designed to make parallel programming easier, and enable more developers to port their applications to GPUs, including: Unified Virtual Addressing, GPU-to-GPU communication, enhanced C++ template libraries, and more.

Initially available to CUDA registered developers, the CUDA Toolkit 4.0 release candidate is now available free of charge for all developers at:  http://developer.nvidia.com/cuda-downloads.

For more information on the features and capabilities of the CUDA Toolkit 4.0 and on GPGPU applications, please visit: www.nvidia.com/cuda.

All CUDA parallel programmers are invited to join the CUDA Registered Developer Program for ongoing access to early software releases, tools, resources, and information to maximize the potential of CUDA and parallel computing.  Visit http://www.developer.nvidia.com/ for more information.