I have a couple of CUDA applications that I’d like to port to OpenCL. One of the processes in these two applications shares a common piece of device memory that is allocated and shared via the cudaIpcOpenMemHandle and cudaIpcGetMemHandle functions. Is there similar support in the OpenCL standard? If not, is there a chance that there will be anytime in the near future?
This topic was automatically closed 183 days after the last reply. New replies are no longer allowed.