Tag Archives: Intel

Correctly enabling cl_khr_fp64 in both OpenCL 1.1 and 1.2

I started most of my OpenCL development on Nvidia GPUs, which still only support OpenCL 1.1.  When I started testing code that used double precision arithmetic on AMD Radeon GPUs, I kept running into a warning about the cl_khr_fp64 extension.  The reason for this is, of course, that in OpenCL 1.2 cl_khr_fp64 moved from an optional extension to an optional core feature.  Therefore, the #pragma OPENCL EXTENSION cl_khr_fp64 : enable was no longer needed. Continue reading