OpenCL ratchets up to version 1.2
Open source heterogeneous standard adds new capabilities
OpenCL, the open-source standard for programming heterogeneous computing systems – aka CPU/GPU mashups – has reached version 1.2 with the ratification and public release of its latest specification documentation.
"The OpenCL working group is listening carefully to feedback from the developer and middleware community to provide significant and timely functionality for heterogeneous computing in this cross vendor open standard," said OpenCL working group chair Neil Trevett in a statement  accompanying Tuesday's anouncement.
Trevett – who is also the president of OpenCL's caretaker, the Khronos Group  and Nvidia's VP of mobile content – went on to say that "The OpenCL working group is also broadening its membership and has growing representation from the mobile and embedded industries and is enabling innovative devices such as FPGAs to be driven through OpenCL."
Version 1.2 adds a number of upgrades to OpenCL 1.1, which was released in June of last year, including device partitioning, new compilation and library-linking capabilities, enhanced image support, DirectX 9 media surface and DirectX 11 surface sharing, and more. The new version is backwards-compatible with OpenCL 1.1, Khronos says.
If you or someone on your development team happen to be at the SC11  supercomputing confab underway this week in Seattle, you might want to check out the Khronos Group's "Birds of a Feather " (BOF) session on Wednesday at 5:30pm – be there or be square.
More information about the new release can be found in the 377-page OpenCL Specification Version 1.2  document. If that's a bit weighty for you, an eight-page Quick Reference Card  is also available. ®