NVIDIA CUDA Toolkit

NVIDIA, a leading force in graphics processing units (GPUs), recently released a major new update to the CUDA parallel computing platform. This new version features three key enhancements that make parallel programing with GPUs easier, more accessible and faster, improving options for scientists and engineers seeking to advance their simulations and research. These enhancements include a redesigned Visual Profiler with automated performance analysis, a new and nimbler compiler based on the LLVM open-source compiler infrastructure and hundreds of new imaging and signal-processing functions, with the latter doubling the size of the NVIDIA Performance Primitives library. The latest CUDA release is available for free download for Linux, Mac OS and Windows from NVIDIA's Web site.

http://www.nvidia.com/cuda