AXI Multichannel DMA Intel® FPGA IP for PCI Express* User Guide
ID
817911
Date
4/07/2025
Public
A newer version of this document is available. Customers should click here to go to the newest version.
5.3.1. PCIe AXI-ST TX Interface (ss_tx_st)
5.3.2. PCIe AXI-ST RX Interface (ss_rx_st)
5.3.3. Control and Status Register Interface (ss_csr_lite)
5.3.4. Flow Control Credit Interface
5.3.5. Configuration Intercept Interface (CII)
5.3.6. Completion Timeout Interface (ss_cplto)
5.3.7. Function Level Reset Interface
5.3.8. Control Shadow Interface (ss_ctrlshadow)
5.4.1. H2D AXI-ST Source (h2d_st_initatr)
5.4.2. D2H AXI-ST Sink (d2h_st_respndr)
5.4.3. H2D/D2H AXI-MM Master
5.4.4. BAM AXI-MM Master (bam_mm_initatr)
5.4.5. BAS AXI-MM Slave (bas_mm_respndr)
5.4.6. PIO AXI-Lite Master (pio_lite_initiatr)
5.4.7. HIP Reconfig AXI-Lite Slave (user_csr_lite)
5.4.8. User Event MSI-X (user_msix)
5.4.9. User Event MSI (user_msi)
5.4.10. User Function Level Reset (user_flr)
5.4.11. User Configuration Intercept Interface - EP Only
5.4.12. Configuration Slave (cs_lite_respndr) - RP Only
6.4.1. Functional Description
In this device-side packet loopback design example, the Host initially sets up specific memory locations within its memory. Data from the Host memory is then transferred to the device-side memory by the AXI Multichannel DMA for PCI Express IP through Host-to-Device (H2D) DMA operations. Subsequently, the IP loops this data back to the Host memory using Device-to-Host (D2H) DMA operations.
Additionally, the design example enables the AXI-Lite PIO master, which bypasses the DMA path. This allows the application running in the Host to perform single, non-bursting register read/write operations with the on-chip memory block.
Figure 23. AXI Streaming Device-side Packet Loopback Design Example