Today the Khronos Group, the keeper of the OpenCL spec (among others, like OpenGL), announced the release of version 1.1 of OpenCL, as well as a C++ wrapper API for OpenCL and conformance tests
OpenCL 1.1 adds significant functionality for enhanced parallel programming flexibility, functionality and performance including:
- New data types including 3-component vectors and additional image formats;
- Handling commands from multiple hosts and processing buffers across multiple devices;
- Operations on regions of a buffer including read, write and copy of 1D, 2D or 3D rectangular regions;
- Enhanced use of events to drive and control command execution;
- Additional OpenCL C built-in functions such as integer clamp, shuffle and asynchronous strided copies;
- Improved OpenGL interoperability through efficient sharing of images and buffers by linking OpenCL and OpenGL events.
[UPDATE] NVIDIA sent along an email to point out that their drivers have also been revved to support the new version of the specification. You can get there here.
“The use of heterogeneous parallel processing to transform computing in fields such as entertainment, science and industry is a trend that shows no signs of slowing, thanks to the wide range of tools that developers have at their disposal today,” said Sanford Russell, general manager of GPU Computing at NVIDIA. “NVIDIA’s full weight is behind OpenCL 1.1, as evidenced by immediate availability of the driver on our website today, along with the industry’s broadest set of tools for taking advantage of NVIDIA GPUs for general purpose computation.”