AXI Streaming Intel® FPGA IP for PCI Express* User Guide

Download PDF
ID 790711
Date 7/08/2024
Public
Document Table of Contents
Document Table of Contents x
1. Introduction 2. Features 3. Getting Started with the AXI Streaming Intel® FPGA IP for PCI Express* 4. IP Architecture and Functional Description 5. AXI Streaming Intel® FPGA IP for PCI Express* Parameters 6. Interfaces and Signals 7. Register Descriptions 8. Document Revision History for the AXI Streaming Intel® FPGA IP for PCI Express* User Guide A. Specifications B. Simulating the Design Example
1. Introduction x
1.1. Goal of the AXI Streaming Intel® FPGA IP for PCI Express* User Guide 1.2. Intended Audience for the AXI Streaming Intel® FPGA IP for PCI Express* User Guide 1.3. What is PCI Express* ? 1.4. What are the Intel® FPGA IPs for PCI Express* ? 1.5. What is the AXI Streaming Intel® FPGA IP for PCI Express* ? 1.6. Example Use Models 1.7. Design Flow Requirements
1.7. Design Flow Requirements x
1.7.1. Design Software 1.7.2. Hardware
2. Features x
2.1. Supported Features 2.2. Device Family Support 2.3. Performance
3. Getting Started with the AXI Streaming Intel® FPGA IP for PCI Express* x
3.1. Download and Install Quartus Software 3.2. Obtain and Install Intel FPGA IPs and Licenses 3.3. Configure and Generate the AXI Streaming Intel® FPGA IP for PCI Express* 3.4. About the AXI Streaming Intel® FPGA IP for PCI Express Design Examples 3.5. Instantiate and Connect the AXI Streaming Intel® FPGA IP for PCI Express* Interfaces 3.6. Simulate the AXI Streaming Intel® FPGA IP for PCI Express* IP Variant 3.7. Compile the AXI Streaming Intel® FPGA IP for PCI Express* IP Variant 3.8. Software Drivers for AXI Streaming Intel® FPGA IP for PCI Express* IP Variant 3.9. Build the Application for the AXI Streaming Intel® FPGA IP for PCI Express* IP Variant 3.10. Verification with the AXI Streaming Intel® FPGA IP for PCI Express* IP Variant 3.11. Debugging with the AXI Streaming Intel® FPGA IP for PCI Express* IP Variant
3.4. About the AXI Streaming Intel® FPGA IP for PCI Express Design Examples x
3.4.1. Functional Description for the Programmed Input/Output (PIO) Design Example 3.4.2. Functional Description for the Single Root I/O Virtualization (SR-IOV) Design Example 3.4.3. Functional Description for the Performance Design Example
3.5. Instantiate and Connect the AXI Streaming Intel® FPGA IP for PCI Express* Interfaces x
3.5.1. Clocking and Resets 3.5.2. Application Packet Datapath 3.5.3. Enabling Additional Features 3.5.4. Enabling Optional Interfaces
3.6. Simulate the AXI Streaming Intel® FPGA IP for PCI Express* IP Variant x
3.6.1. Simulating the Design Example
3.6.1. Simulating the Design Example x
3.6.1.1. Steps to Run Simulations
3.6.1.1. Steps to Run Simulations x
3.6.1.1.1. VCS* Simulator
3.8. Software Drivers for AXI Streaming Intel® FPGA IP for PCI Express* IP Variant x
3.8.1. Installing the Linux Kernel Driver
3.9. Build the Application for the AXI Streaming Intel® FPGA IP for PCI Express* IP Variant x
3.9.1. Running the Design Example
3.9.1. Running the Design Example x
3.9.1.1. Running the PIO Design Example
3.11. Debugging with the AXI Streaming Intel® FPGA IP for PCI Express* IP Variant x
3.11.1. Debugging Link Training Issues 3.11.2. Debugging Data Transfer and Performance Issues
3.11.1. Debugging Link Training Issues x
3.11.1.1. Operating System Tools and Utilities 3.11.1.2. Signal Tap Logic Analyzer 3.11.1.3. Additional Debug Tools
3.11.2. Debugging Data Transfer and Performance Issues x
3.11.2.1. Advanced Error Reporting (AER) 3.11.2.2. Second-Level Debug Tools
4. IP Architecture and Functional Description x
4.1. Clocks and Resets 4.2. PCIe Hard IP (HIP) 4.3. HIP Interface (IF) Adaptor 4.4. Application Error Reporting 4.5. Debug Toolkit and Hard IP (HIP) Reconfiguration Interface 4.6. Configuration Space Extension 4.7. Control Shadow 4.8. Configuration Intercept Interface 4.9. Power Management 4.10. Legacy Interrupt 4.11. Credit Handling 4.12. Completion Timeout 4.13. Transaction Ordering 4.14. Page Request Service (PRS) Events 4.15. TX Non-Posted Metering Requirement on Application 4.16. MSI Pending 4.17. D-State Status 4.18. Configuration Retry Status Enable 4.19. AXI-Streaming Interface 4.20. Precision Time Measurement (PTM) [F/R-Tiles Only]
5. AXI Streaming Intel® FPGA IP for PCI Express* Parameters x
5.1. Parameter Editor Parameters
6. Interfaces and Signals x
6.1. Overview 6.2. Clocks and Resets 6.3. Application Packet Interface 6.4. Configuration Extension Bus Interface 6.5. Configuration Intercept Interface 6.6. Function Level Reset Interface 6.7. Control Shadow Interface (st_ctrlshadow) 6.8. Completion Timeout Interface (st_cplto) 6.9. Miscellaneous Signals 6.10. Control and Status Register Responder Interface (lite_csr) 6.11. Error Interface (st_err) 6.12. VF Error Flag Interface (vf_err/sent_vfnonfatalmsg) 6.13. VIRTIO PCI* Configuration Access Interface 6.14. Serial Data Signals
6.2. Clocks and Resets x
6.2.1. Interface Clock Signals 6.2.2. Interface Reset Signals
6.3. Application Packet Interface x
6.3.1. Header Format 6.3.2. Prefix Format 6.3.3. Function Number Format 6.3.4. BAR Number Format 6.3.5. Data and Header Packing Schemes 6.3.6. Application Packet Transmit Interface (st_tx) 6.3.7. Application Packet Receive Interface (st_rx) 6.3.8. Flow Control Credit Handling
6.3.5. Data and Header Packing Schemes x
6.3.5.1. HIP Native Mode Packing 6.3.5.2. Compact Packing 6.3.5.3. Simple Packing
6.3.5.1. HIP Native Mode Packing x
6.3.5.1.1. Application Logic Guidelines for the AXI Streaming TX Interface in HIP Native Mode (R-Tile) 6.3.5.1.2. Application Logic Guidelines for the AXI Streaming RX Interface in HIP Native Mode
6.3.5.2. Compact Packing x
6.3.5.2.1. Application Logic Guidelines for the AXI Streaming TX Interface in Compact Mode (P/R-Tiles) 6.3.5.2.2. Application Logic Guidelines for the AXI Streaming RX Interface in Compact Mode (P/R-Tiles)
6.3.5.3. Simple Packing x
6.3.5.3.1. Application Logic Guidelines for the AXI Streaming TX Interface in Simple Mode (P/R-Tiles) 6.3.5.3.2. Application Logic Guidelines for the AXI Streaming RX Interface in Simple Mode (P/R-Tiles)
6.3.8. Flow Control Credit Handling x
6.3.8.1. Application Transmit Flow Control Credit Interface (st_txcrdt) 6.3.8.2. Application Receive Flow Control Credit Interface (st_rxcrdt) (R-Tile Only)
6.4. Configuration Extension Bus Interface x
6.4.1. Configuration Extension Bus Request Interface (st_cebreq) 6.4.2. Configuration Extension Bus Response Interface (st_cebresp)
6.5. Configuration Intercept Interface x
6.5.1. Configuration Intercept Request Interface (st_ciireq) 6.5.2. Configuration Intercept Response Interface (st_ciiresp)
6.6. Function Level Reset Interface x
6.6.1. Function Level Reset Received Interface (st_flrrcvd) 6.6.2. Function Level Reset Completion Interface (st_flrcmpl)
6.13. VIRTIO PCI* Configuration Access Interface x
6.13.1. VIRTIO PCI* Config Access Request Interface (st_virtio_pcicfgreq) 6.13.2. VIRTIO PCI* Config Access Completion Interface (st_virtio_pcicfgcmpl)
7. Register Descriptions x
7.1. Register Address Map 7.2. PCIe Configuration Space 7.3. AXI Streaming Intel® FPGA IP for PCI Express* Soft Register Address Map
7.2. PCIe Configuration Space x
7.2.1. PCIe Configuration Space Registers
7.3. AXI Streaming Intel® FPGA IP for PCI Express* Soft Register Address Map x
7.3.1. AXI Streaming Intel® FPGA IP for PCI Express* Control Registers 7.3.2. IP Debug Registers 7.3.3. IP Performance Monitor Registers
7.3.1. AXI Streaming Intel® FPGA IP for PCI Express* Control Registers x
7.3.1.1. AXI Streaming Intel® FPGA IP for PCI Express* Version 7.3.1.2. AXI Streaming Intel® FPGA IP for PCI Express* Features 7.3.1.3. AXI Streaming Intel® FPGA IP for PCI Express* Interface Attributes 7.3.1.4. HOT PLUG GEN CTRL 7.3.1.5. POWER MANAGEMENT CTRL 7.3.1.6. LEGACY INTERRUPT CTRL 7.3.1.7. CFG REG IA CTRL 7.3.1.8. CFG REG IA FN NUM 7.3.1.9. CFG REG IA WRDATA 7.3.1.10. CFG REG IA RDDATA 7.3.1.11. PRS CTRL 7.3.1.12. MSI PENDING CTRL 7.3.1.13. MSI PENDING 7.3.1.14. D-STATE STS 7.3.1.15. CFG RETRY CTRL
7.3.2. IP Debug Registers x
7.3.2.1. HIP Status 7.3.2.2. HIP BP CYCLES 7.3.2.3. HIA BP CYCLES 7.3.2.4. APP BP CYCLES 7.3.2.5. HIA RX BP CYCLES
7.3.3. IP Performance Monitor Registers x
7.3.3.1. PERFMON CTRL 7.3.3.2. TX MRD TLP 7.3.3.3. TX MWR TLP 7.3.3.4. TX MSG TLP 7.3.3.5. TX CFGWR TLP 7.3.3.6. TX CFGRD TLP 7.3.3.7. RX MRD TLP 7.3.3.8. RX MWR TLP 7.3.3.9. RX MSG TLP 7.3.3.10. RX CFGWR TLP 7.3.3.11. RX CFGRD TLP 7.3.3.12. TX MEM DATA 7.3.3.13. TX CPL DATA 7.3.3.14. RX MEM DATA 7.3.3.15. RX CPL DATA
A. Specifications x
A.1. P-Tile Specifications A.2. F-Tile Specifications A.3. R-Tile Specifications
A.1. P-Tile Specifications x
A.1.1. P-Tile Completion Buffer Size A.1.2. Power Management A.1.3. MSI and MSI-X
A.2. F-Tile Specifications x
A.2.1. F-Tile Completion Buffer Size A.2.2. Power Management
A.3. R-Tile Specifications x
A.3.1. R-Tile Completion Buffer Size A.3.2. Power Management A.3.3. MSI and MSI-X
B. Simulating the Design Example x
B.1. Testbench
B.1. Testbench x
B.1.1. Testbench Modules B.1.2. Test Driver Module B.1.3. PIO Design Example Testbench B.1.4. Root Port BFM
1. Introduction
2. Features
3. Getting Started with the AXI Streaming Intel® FPGA IP for PCI Express*
4. IP Architecture and Functional Description
5. AXI Streaming Intel® FPGA IP for PCI Express* Parameters
6. Interfaces and Signals
7. Register Descriptions
8. Document Revision History for the AXI Streaming Intel® FPGA IP for PCI Express* User Guide
A. Specifications
B. Simulating the Design Example

B.1. Testbench

The testbench uses a test driver module, altpcietb_bfm_rp_gen5_x16.sv, to initiate the configuration and memory transactions. At startup, the test driver module displays information from the Root Port and Endpoint Configuration Space registers, so that you can correlate to the parameters you specified using the Parameter Editor.

The example design and testbench are dynamically generated based on the configuration that you choose for the AXI Streaming Intel® FPGA IP for PCI Express* . The testbench uses the parameters that you specify in the Parameter Editor in Quartus® Prime.

This testbench simulates a Gen5 ×16 PCI Express link using the serial PCI Express interface.

Figure 64. PIO Design Example Simulation Testbench
When configured as an Endpoint variation, the testbench instantiates a design example with an AXI Streaming IP Endpoint and a Root Port BFM containing a second AXI Streaming IP (configured as a Root Port) to interface with the Endpoint. For more details on this Root Port BFM, refer to Root Port BFM. The Root Port BFM provides the following functions:

  • A configuration routine that sets up all the basic configuration registers in the Endpoint. This configuration allows the Endpoint application to be the target and initiator of PCI Express transactions.

  • A Verilog HDL procedure interface to initiate PCI Express transactions to the Endpoint.

This testbench simulates the scenario of a single Root Port talking to a single Endpoint.

The testbench uses a test driver module, altpcietb_bfm_rp_gen5_x16.sv, to initiate the configuration and memory transactions. At startup, the test driver module displays information from the Root Port and Endpoint Configuration Space registers, so that you can correlate to the parameters you specified using the Parameter Editor.

Note: The Intel testbench and Root Port BFM provide a simple method to do basic testing of the Application Layer logic that interfaces to the variation. This BFM allows you to create and run simple task stimuli to exercise basic functionality of the Intel example design. The testbench and Root Port BFM are not intended to be a substitute for a full verification environment. Corner cases and certain traffic profile stimuli are not covered. Refer to the items listed below for further details. To ensure the best verification coverage possible, Intel suggests strongly that you obtain commercially available PCI Express verification IP and tools, in combination with performing extensive hardware testing.
Your Application Layer design may need to handle at least the following scenarios that are not possible to create with the Intel testbench and the Root Port BFM, or are due to the limitations of the example design:

  • It is unable to generate or receive Vendor Defined Messages. Some systems generate Vendor Defined Messages. The Hard IP block simply passes these messages on to the Application Layer. Consequently, you should make the decision, based on your application, whether to design the Application Layer to process them.

  • It can only handle received read requests that are less than or equal to 256 bits or 8 DW. Many systems are capable of handling larger read requests that are then returned in multiple completions.

  • It always returns a single completion for every read request. Some systems split completions on every 64-byte address boundary.
  • It always returns completions in the same order the read requests were issued. Some systems generate the completions out-of-order.

  • It is unable to generate zero-length read requests that some systems generate as flush requests following some write transactions. The Application Layer must be capable of generating the completions to the zero-length read requests.

  • It does not support parity.
  • It does not support multi-function designs.
  • It does not support Single Root I/O Virtualization (SR-IOV).

Section Content
Testbench Modules
Test Driver Module
PIO Design Example Testbench
Root Port BFM

Level Two Title