14 DAY TRIAL // OpenCL is a relatively new specification but has already become quite popular as an open standard for cross-platform, parallel programming of modern processors. Basically, it is a backward compatible specification jointly developed by a large number of industry-leading companies, including AMD, Apple, ARM, IBM, Apple, Blizzard, Activision, NVIDIA, Intel and many more. Processors have evolved, of course, which means that this specification must also be updated if parallel programming is to gain any measure of flexibility and performance benefits.
OpenCL 1.1 allows processors to handle commands from multiple hosts and processing buffers across multiple devices. Additionally, command execution is driven and controlled through enhanced use of events. Furthermore, OpenGL interoperability is improved through efficient sharing of images and buffers, by linking OpenCL and OpenGL events.
This is not all that the new specification enables, of course. For one, OpenCL 1.1 confers support for new data types, even 3-component vectors and additional image formats. Operations on regions of a buffer (read, write copy of 1D, 2D or 3D rectangles) are also made possible. Finally, to complement the assets of the new standard, Khronos Group has also finished up the C++ wrapper API.
“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,” he added.
“The release of OpenCL 1.1 is coming at a perfect time, capitalizing on the rapidly growing interest in GPU computing across the industry,” stated Manju Hegde, corporate vice president, Fusion Experience Program, AMD. “As one of the most committed supporters of OpenCL through our ATI Stream Software Development Kit, AMD is poised to unleash the true potential of application acceleration with our AMD Fusion Family of APUs, scheduled for release in 2011.”