imlincomb

Implementation

OpenCL

Usage

output = imlincomb_ATI(a, input1, b, input2);

Class Support

output, input1 and input2 are uint8 types. a and b are double types.

Algorithm

A linear combination of two images. In our implementation, 16 uint8 data are packed into uint vector 4

to maximize the utilization of the memory bandwidth (CPU-GPU data transfer and GPU device data transfer).

Despite the extra computations involved in kernel because of packing and unpacking, the overall GPU

performance might still be improved.