In the generic case, the PL block consumes data via the stream interface. It then generates a data stream and forwards it to the array interface, where inside there is a FIFO that receives the PL stream and converts it into an AIE-ML stream. The AIE-ML stream is then routed to the AIE-ML destination function. Depending on whether the communication is block-based or stream-based, DMA, and ping-pong buffers could be involved.
The following figure shows an example. The AIE-ML and PL can communicate using DMA in the AIE-ML tile. The DMA moves the stream into a memory block neighboring the consuming AIE-ML. The first diagram represents the logical view and the second diagram represents the physical view.
Figure 1. Logical View of AIE-ML to PL
Data Communication via Shared Memory
Figure 2. Physical View of AIE-ML to PL Data Communication via Shared Memory
