The Khronos Group announced version 1.2 of OpenCL today, an update that gives programmers tighter control over how they run software on graphics chips.
OpenCL is a standard interface that makes it easier for programmers to tap into the "GPGPU" idea--general-purpose graphical processing unit, which runs software such as game physics engines on a computing device's graphics hardware rather than on its central processing unit (CPU). With OpenCL, or with another technology such as Microsoft's rival DirectCompute, a programmer can use a GPGPU approach without having to worry about the particulars of individual graphics chips.
Among the features in OpenCL 1.2:
Device partitioning lets programmers confine applications or tasks to parts of the graphics chip. That tighter control makes it easier to reserve part of it for high-priority tasks, for example.
Better sharing of some information between OpenCL and Microsoft DirectX 9 and 11 hardware acceleration technology for situations when both programming interfaces are needed.
Better mechanisms to let OpenCL software tap into custom hardware abilities such as video encoding or decoding or digital signal processing.