The XDMA Subsystem can be configured as a high performance direct memory access (DMA) data mover between the PCI Express® and AXI memory spaces. As a DMA, the subsystem can be configured with either an AXI (memory mapped) interface or with an AXI streaming interface to allow for direct connection to RTL logic. Either interface can be used for high performance block data movement between the PCIe® address space and the AXI address space using the provided character driver. In addition to the basic DMA functionality, the DMA supports up to four upstream and downstream channels, the ability for PCIe traffic to bypass the DMA engine (Host DMA Bypass), and an optional descriptor bypass to manage descriptors from the AMD Versal™ Adaptive SoC for applications that demand the highest performance and lowest latency.
This diagram refers to the Requester Request (RQ)/Requester Completion (RC) interfaces, and the Completer Request (CQ)/Completer Completion (CC) interfaces. For more information about these, see the Versal Adaptive SoC Integrated Block for PCI Express LogiCORE IP Product Guide (PG343).