AXI4-Stream switches in the AI Engine to PL tiles can directly communicate with the programmable logic using the AXI4-Stream interface. There are six streams from AI Engine to PL and eight streams from PL to each AI Engine column. From a bandwidth perspective, each AXI4-Stream interface can support the following.
- 24 GB/s from each AI Engine column to PL
- 32 GB/s from PL to each AI Engine column
In the VC1902 device, there are 50 columns of AI Engine tiles and AI Engine array interface tiles, however, only 39 array interface tiles are available to the PL interface. Therefore, the aggregate bandwidth for PL interface is approximately:
- 1.0 TB/s from AI Engine to PL
- 1.3 TB/s from PL to AI Engine
All bandwidth calculations assume a nominal 1 GHz AI Engine clock for the -1L speed grade devices at VCCINT = 0.70V. The number of array interface tiles available to the PL interface and total bandwidth of the AI Engine to PL interface for other devices and across different speed grades is specified in Versal AI Core Series Data Sheet: DC and AC Switching Characteristics (DS957).
The boundary-logic interface flip-flops are between the AI Engine-to-PL interface. They can be used to improve timing. By applying the boundary-logic interface (BLI) constraints to flip-flops in your design, you can automatically take advantage of this feature during design placement. Refer to the AI Engine-PL Interface Techniques for Timing section in Versal Adaptive SoC System Integration and Validation Methodology Guide (UG1388).