I'm developing an open-source API that uses multiple OpenCL devices to compute kernels, adding features like pipelining and load balancing, but now I need to add a device-to-device pipeline such that a GPU will send data to another GPU without touching system RAM, only through inter-pci-e connection. What is the OpenCL API command for that? I guess this command
should have that but its documentation in Khronos site doesn't tell anything about it.
Details about my project:
thank you for your time.