hello everybody,
I know this question has already been posed, but results of a search here returns only pretty old results, leading myself to still questionning. By the way, I would like to know if a direct communication between fpga and nvidia gpu is possible, using the so called “directgpu rdma” and the dma engines of the fpga?
if yes, moreover, i would like to know if it would be possible to port such a thing on openCl instead of cuda?
thanks for any response,
regards