I am working with OpenMP 4.5 Accelerator Model on platform equipped with Intel Xeon Phi coprorcessors. I would like to use CPU + MIC to joint problem solving. I need use mechanism similar to Intel Offload into. I would like to transfer immediately data from buffer A from card to buffer B. Example of this is presented on code bellow.
#pragma offload target(mic : 0) \
out(A[0:size] : REUSE into(B[0:size])
{ }
I would like to do it using OpenMP Accelerator Model. It is possible?
