Profiling the AI Engine in Hardware - 2025.2 English - UG1076

An AI Engine event gives information about the system at a specific instant in time. An event that is associated with a timestamp, type and set of data values is referred to as a payload. The interpretation of the payload depends on the type of the event. A timestamp allows ordering of events, computation of causality relationships, and implementation of verifiers on a sequence of events.

For event modeling purposes, the key modules of the AI Engine array are as follows:

• Processor
• DMA
• Lock modules
• Memory
• I/O streams

You can view each module as an event generator/responder. Each module receives an event and responds to the event. New events can be generated as responses. Events are classified based on the generator of the events. Event definitions do not explicitly mention the timestamp.

Each event is described with a payload, which is a couple of values associated with the event. Each AI Engine, memory, DMA, or lock is addressable by a two-dimensional index <col, row>. This is the column and row index in the AI Engine array.