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 data buffer.
Kernels consume input stream or buffer of data and produce output stream or buffer
of data. Kernels access data streams in a sample-by-sample fashion.
For additional details on buffer APIs, refer to Input and Output Buffers. For additional details on stream APIs, refer to Streaming Data API.
AI Engine kernels can also have RTP ports that are updated or read by PS. For more information about RTP ports, refer to Runtime Graph Control API.