Kernel Inputs and Outputs - Kernel Inputs and Outputs - 2026.1 English - UG1603

AI Engine-ML Kernel and Graph Programming Guide (UG1603)

Document ID
UG1603
Release Date
2026-07-08
Version
2026.1 English

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.