Hi,
I'm seeing articles on IVB GPU and seems currently GPUOpenCL support is lacking double precision support which is supported in GPU HW.. In directcompute is supported but seems no in OCL.. do you plan to expose basic double precesion operations as in directcompute (i.e. add, sub, mul,etc..) before full cl_khr_fp64 support?
Also seems there is support for D3D10 interop but IVB has d3d11 support so add please request for d3d11 interop.. seems it's a optional CL 1.2 ext but this would be good before full OpenCL 1.2 support..
thanks..



