The Khronos Group announced the latest iteration in the OpenCL specification today. Version 1.1 adds quite a bit of new functionality given recent comments and additions from both the user and vendor community.
The clear commercial opportunity to unleash the power of heterogeneous parallel processing that drove multiple OpenCL 1.0 implementations has also fueled the ongoing industry cooperation to create OpenCL 1.1,” said Neil Trevett, chair of the OpenCL working group, president of the Khronos Group and vice president at NVIDIA. “The OpenCL 1.1 specification is being released 18 months after OpenCL 1.0 to enable programmers to take even more effective advantage of parallel computing resources while protecting their existing investment in OpenCL code.”
New functionality include:
- 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
Quite a few vendors had quotes associated with the release, but we’ll spare you the nasty details. If you’re really interested in hearing more about the spec, Khronos will be on hand at SIGGRAPH in Los Angeles to host an OpenCL BOF.
In the mean time, check out their release here.