14 DAY TRIAL // The OpenCL cross-platform, open standard for parallel programming of modern processors has just been updated, to version 1.2.
OpenCL 1.2 brings a number of enhancements and performance optimizations over the OpenCL 1.1 standard unveiled eighteen months ago.
It should allow for greater programming flexibility, performance and functionality, these being the fruits of the labors of over thirty companies.
“AMD promotes industry standards like OpenCL 1.2 that encourage developer freedom and creativity,” said Manju Hegde, corporate vice president, AMD Fusion Experience Program.
“In addition to being one of the leading contributors to the OpenCL working group and specifications, AMD Accelerated Processing Units (APUs) and GPUs are the perfect platforms to take advantage of the potential of OpenCL – for developers and end-users.”
Device partitioning into sub-devices, for one, is allowed to applications that need to closely control work assignment to specific compute units, or to those that need to reserve part of the device for priority/latency-sensitive tasks.
The same feature helps when shared hardware resources, like cache memory, need to be handled in a particular way.
Another new feature is the ability to compile and link objects separately, for creating libraries of OpenCL programs that other programs can later link to.
Furthermore, 1D images are supported, as well as 1D & 2D image arrays. Furthermore, the OpenGL sharing extension allows OpenCL images to be made from OpenGL 1D and 1D & 2D textures / texture arrays.
There are other assets as well, related to DirectX 9 and 11 and kernel usability, among other things.
“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 Neil Trevett, chair of the OpenCL working group, president of the Khronos Group and vice president of mobile content at NVIDIA.
“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.”