AI Engine kernels operate on either streams or blocks of data. AI Engine kernels operate on data of specific types, for example, int32 and cint32. A block of data used by a kernel is called a window of data. Kernels consume input stream or window of data and produce output stream or window of data. Kernels access data streams in a sample-by-sample fashion. For additional details on the window and stream APIs, see Window and Streaming Data API.
AI Engine kernels can also have RTP ports to be updated or read by PS. For more information about RTP, see Run-Time Graph Control API in the AI Engine Tools and Flows User Guide (UG1076).