Open bkloppenborg opened 12 years ago
Most of the CPU-side computations should use doubles by default, then drop precision (if needed) to push the values to the OpenCL/OpenGL device. C++ templates and runtime editing of kernels could deal with most of these issues.
Most of the CPU-side computations should use doubles by default, then drop precision (if needed) to push the values to the OpenCL/OpenGL device. C++ templates and runtime editing of kernels could deal with most of these issues.