updated 12:50 pm EDT, Fri August 22, 2008
NVIDIA CUDA 2.0 Final
NVIDIA today formally released the finished version of CUDA 2.0. The second generation of the company's general-purpose programming language for its video chipsets supports 64-bit versions of Mac OS X and Windows Vista and adds support for instructions that can help offload more specific tasks from the main processor to the video card, such as 3D textures and hardware-accelerated interpolation of information.
These advancements are particularly useful for volume reconstruction in medicine or for seismic computing in the oil industry, NVIDIA says.
The Santa Clara, California firm also hopes to use CUDA 2.0 as a motivator for creative teams with the inclusion of a reference plugin for Adobe's Photoshop. The blank slate allows developers to create filters and other effects of their own that use CUDA to process images more quickly than would be possible relying on the system CPU alone.
Apps written with CUDA require a card with one of NVIDIA's chipsets built with its unified shader architecture, including all GeForce 8- and 9-series cards as well as newer Quadro FX cards. Its Tesla and Quadro Plex general-purpose acceleration cards also support the feature.
Apple quietly posted CUDA 2.0 to its website but at the time didn't indicate itself that the release was the final version for Mac OS X.