Name: Anonymous 2011-02-17 23:56
Clang/LLVM was already being used by AMD and nVidia internally for their shader and GPU compute kernel compilers for HLSL, GLSL, DirectCompute, CUDA, and OpenCL, but for the first time, ARM, AMD, Intel, nVidia, Imagination Technologies and Apple will be committing additional engineers to work together on developing a common open-source OpenCL front-end as a main part of the Clang/LLVM project. They will also be focusing on building back-ends that seamlessly target multiple heterogeneous hardware environments, allowing you to run compute kernels on CPU cores and different GPUs from different manufacturers simultaneously within the same system.
Also, Imagination Tech. just submitted first silicon for OpenCL EP certification. Expect OpenCL on mobile devices later this year.
http://www.imgtec.com/News/Release/index.asp?NewsID=610
http://blogs.arm.com/multimedia/263-why-opencl-will-be-on-every-smartphone-in-2014/
Clang/LLVM will be powering it all. This kind of cooperation among corporate players would never have happened with a GPL'd compiler.
Also, Imagination Tech. just submitted first silicon for OpenCL EP certification. Expect OpenCL on mobile devices later this year.
http://www.imgtec.com/News/Release/index.asp?NewsID=610
http://blogs.arm.com/multimedia/263-why-opencl-will-be-on-every-smartphone-in-2014/
Clang/LLVM will be powering it all. This kind of cooperation among corporate players would never have happened with a GPL'd compiler.