Arria® V Avalon® Memory-Mapped (Avalon-MM) Interface for PCI Express* Solutions: User Guide

Download PDF
ID 683773
Date 10/25/2024
Public
Document Table of Contents
Document Table of Contents x
1. Datasheet 2. Getting Started with the Avalon-MM Arria V Hard IP for PCI Express 3. Parameter Settings 4. Interfaces and Signal Descriptions 5. Registers 6. Reset and Clocks 7. Interrupts for Endpoints 8. Error Handling A. PCI Express Protocol Stack 9. Design Implementation 10. Additional Features 11. Transceiver PHY IP Reconfiguration 12. Debugging B. Frequently Asked Questions for PCI Express C. Lane Initialization and Reversal D. Document Revision History
1. Datasheet x
1.1. Avalon-MM Interface for PCIe Datasheet 1.2. Features 1.3. Release Information 1.4. Device Family Support 1.5. Configurations 1.6. Example Designs 1.7. IP Core Verification 1.8. Performance and Resource Utilization 1.9. Recommended Speed Grades 1.10. Creating a Design for PCI Express
1.7. IP Core Verification x
1.7.1. Compatibility Testing Environment
2. Getting Started with the Avalon-MM Arria V Hard IP for PCI Express x
2.1. Running Platform Designer 2.2. Generating the Example Design 2.3. Running a Gate-Level Simulation 2.4. Simulating the Single DWord Design 2.5. Understanding Channel Placement Guidelines 2.6. Generating Synthesis Files 2.7. Compiling the Design in the Quartus® Prime Software 2.8. Programming a Device
3. Parameter Settings x
3.1. Avalon-MM System Settings 3.2. Base Address Register (BAR) Settings 3.3. Device Identification Registers 3.4. Device Capabilities 3.5. Error Reporting 3.6. Link Capabilities 3.7. MSI and MSI-X Capabilities 3.8. Power Management 3.9. Avalon Memory‑Mapped System Settings
4. Interfaces and Signal Descriptions x
4.1. 64- or 128-Bit Avalon-MM Interface to the Endpoint Application Layer 4.2. Clock Signals 4.3. Reset Signals 4.4. Hard IP Status 4.5. Interrupts for Endpoints when Multiple MSI/MSI-X Support Is Enabled 4.6. Physical Layer Interface Signals
4.1. 64- or 128-Bit Avalon-MM Interface to the Endpoint Application Layer x
4.1.1. 32-Bit Non-Bursting Avalon-MM Control Register Access (CRA) Slave Signals 4.1.2. Bursting and Non-Bursting Avalon® -MM Module Signals 4.1.3. 64- or 128-Bit Bursting TX Avalon-MM Slave Signals
4.6. Physical Layer Interface Signals x
4.6.1. Transceiver Reconfiguration 4.6.2. Hard IP Status Extension 4.6.3. Serial Interface Signals 4.6.4. PIPE Interface Signals 4.6.5. Test Signals
4.6.2. Hard IP Status Extension x
4.6.2.1. Configuration Space Register Access 4.6.2.2. Configuration Space Register Access Timing
4.6.3. Serial Interface Signals x
4.6.3.1. Physical Layout of Hard IP in Arria V Devices 4.6.3.2. Channel Placement in Arria V Devices
5. Registers x
5.1. Correspondence between Configuration Space Registers and the PCIe Specification 5.2. Type 0 Configuration Space Registers 5.3. Type 1 Configuration Space Registers 5.4. PCI Express Capability Structures 5.5. Intel-Defined VSEC Registers 5.6. CvP Registers 5.7. 64- or 128-Bit Avalon-MM Bridge Register Descriptions 5.8. Programming Model for Avalon-MM Root Port 5.9. Uncorrectable Internal Error Mask Register 5.10. Uncorrectable Internal Error Status Register 5.11. Correctable Internal Error Mask Register 5.12. Correctable Internal Error Status Register
5.7. 64- or 128-Bit Avalon-MM Bridge Register Descriptions x
5.7.1. Avalon-MM to PCI Express Interrupt Registers
5.7.1. Avalon-MM to PCI Express Interrupt Registers x
5.7.1.1. Avalon-MM to PCI Express Interrupt Status Registers 5.7.1.2. Avalon-MM to PCI Express Interrupt Enable Registers 5.7.1.3. PCI Express Mailbox Registers 5.7.1.4. Avalon-MM-to-PCI Express Address Translation Table 5.7.1.5. PCI Express to Avalon-MM Interrupt Status and Enable Registers for Endpoints 5.7.1.6. Avalon-MM Mailbox Registers 5.7.1.7. Control Register Access (CRA) Avalon-MM Slave Port
5.8. Programming Model for Avalon-MM Root Port x
5.8.1. Sending a Write TLP 5.8.2. Sending a Read TLP or Receiving a Non-Posted Completion TLP 5.8.3. Examples of Reading and Writing BAR0 Using the CRA Interface 5.8.4. PCI Express to Avalon-MM Interrupt Status and Enable Registers for Root Ports 5.8.5. Root Port TLP Data Registers
6. Reset and Clocks x
6.1. Reset Sequence for Hard IP for PCI Express IP Core and Application Layer 6.2. Clocks
6.2. Clocks x
6.2.1. Clock Domains 6.2.2. Clock Summary
6.2.1. Clock Domains x
6.2.1.1. pclk 6.2.1.2. coreclkout_hip 6.2.1.3. pld_clk
7. Interrupts for Endpoints x
7.1. Enabling MSI or Legacy Interrupts 7.2. Generation of Avalon-MM Interrupts 7.3. Interrupts for Endpoints Using the Avalon-MM Interface with Multiple MSI/MSI-X Support
8. Error Handling x
8.1. Physical Layer Errors 8.2. Data Link Layer Errors 8.3. Transaction Layer Errors 8.4. Error Reporting and Data Poisoning 8.5. Uncorrectable and Correctable Error Status Bits
A. PCI Express Protocol Stack x
A.1. Top-Level Interfaces A.2. Data Link Layer A.3. Physical Layer A.4. 32-Bit PCI Express Avalon-MM Bridge A.5. Completer Only Single Dword Endpoint
A.1. Top-Level Interfaces x
A.1.1. Avalon-MM Interface A.1.2. Clocks and Reset A.1.3. Transceiver Reconfiguration A.1.4. Interrupts A.1.5. PIPE
A.4. 32-Bit PCI Express Avalon-MM Bridge x
A.4.1. Avalon‑MM Bridge TLPs A.4.2. Avalon-MM-to-PCI Express Write Requests A.4.3. Avalon-MM-to-PCI Express Upstream Read Requests A.4.4. PCI Express-to-Avalon-MM Read Completions A.4.5. PCI Express-to-Avalon-MM Downstream Write Requests A.4.6. PCI Express-to-Avalon-MM Downstream Read Requests A.4.7. Avalon-MM-to-PCI Express Read Completions A.4.8. PCI Express-to-Avalon-MM Address Translation for 32-Bit Bridge A.4.9. Minimizing BAR Sizes and the PCIe Address Space A.4.10. Avalon® -MM-to-PCI Express Address Translation Algorithm for 32-Bit Addressing
A.5. Completer Only Single Dword Endpoint x
A.5.1. RX Block A.5.2. Avalon-MM RX Master Block A.5.3. TX Block A.5.4. Interrupt Handler Block
9. Design Implementation x
9.1. Making Analog QSF Assignments Using the Assignment Editor 9.2. Making Pin Assignments 9.3. Recommended Reset Sequence to Avoid Link Training Issues
10. Additional Features x
10.1. Configuration over Protocol (CvP) 10.2. Autonomous Mode 10.3. ECRC
10.2. Autonomous Mode x
10.2.1. Enabling Autonomous Mode 10.2.2. Enabling CvP Initialization
10.3. ECRC x
10.3.1. ECRC on the RX Path 10.3.2. ECRC on the TX Path
11. Transceiver PHY IP Reconfiguration x
11.1. Connecting the Transceiver Reconfiguration Controller IP Core 11.2. Transceiver Reconfiguration Controller Connectivity for Designs Using CvP
12. Debugging x
12.1. Hardware Bring-Up Issues 12.2. Link Training 12.3. Use Third-Party PCIe Analyzer 12.4. BIOS Enumeration Issues
D. Document Revision History x
D.1. Arria® V and Cyclone® V Avalon® Memory Mapped (Avalon-MM) Interface for PCIe* Solutions User Guide Revision History
1. Datasheet
2. Getting Started with the Avalon-MM Arria V Hard IP for PCI Express
3. Parameter Settings
4. Interfaces and Signal Descriptions
5. Registers
6. Reset and Clocks
7. Interrupts for Endpoints
8. Error Handling
A. PCI Express Protocol Stack
9. Design Implementation
10. Additional Features
11. Transceiver PHY IP Reconfiguration
12. Debugging
B. Frequently Asked Questions for PCI Express
C. Lane Initialization and Reversal
D. Document Revision History

A.4.9. Minimizing BAR Sizes and the PCIe Address Space

For designs that include multiple BARs, you may need to modify the base address assignments auto‑assigned by Platform Designer in order to minimize the address space that the BARs consume. For example, consider a Platform Designer system with the following components:

  • Offchip_Data_Mem DDR3 (SDRAM Controller with UniPHY) controlling 256 MB of memory—Platform Designer auto‑assigned a base address of 0x00000000
  • Quick_Data_Mem (On-Chip Memory (RAM or ROM)) of 4 KB—Platform Designer auto‑assigned a base address of 0x10000000
  • Instruction_Mem (On-Chip Memory (RAM or ROM)) of 64 KB—Platform Designer auto‑assigned a base address of 0x10020000
  • PCIe (Avalon‑MM Arria V Hard IP for PCI Express)
    • Cra (Avalon‑MM Slave)—auto assigned base address of 0x10004000
    • Rxm_BAR0 connects to Offchip_Data_Mem DD R3 avl
    • Rxm_BAR2 connects to Quick_Data_Mem s1
    • Rxm_BAR4 connects to PCIe. Cra Avalon MM Slave
  • Nios2 (Nios® II Processor)
    • data_master connects to PCIe Cra, Offchip_Data_Mem DDR3 avl, Quick_Data_Mem s1, Instruction_Mem s1, Nios2 jtag_debug_module
    • instruction_master connects to Instruction_Mem s1
Figure 39.  Platform Designer System for PCI Express with Poor Address Space UtilizationThe following figure uses a filter to hide the Conduit interfaces that are not relevant in this discussion.
Figure 40. Poor Address MapThe following figure illustrates the address map for this system.

The auto‑assigned base addresses result in the following three large BARs:

  • BAR0 is 28 bits. This is the optimal size because it addresses the Offchip_Data_Mem which requires 28 address bits.
  • BAR2 is 29 bits. BAR2 addresses the Quick_Data_Mem which is 4 KB. It should only require 12 address bits; however, it is consuming 512 MBytes of address space.
  • BAR4 is also 29 bits. BAR4 address PCIe Cra is 16 KB. It should only require 14 address bits; however, it is also consuming 512 MB of address space.

This design is consuming 1.25 GB of PCIe address space when only 276 MB are actually required. The solution is to edit the address map to place the base address of each BAR at 0x0000_0000. The following figure illustrates the optimized address map.

Figure 41. Optimized Address Map
Figure 42. Reduced Address Bits for BAR2 and BAR4The following figure shows the number of address bits required when the smaller memories accessed by BAR2 and BAR4 have a base address of 0x0000_0000.

For cases where the BAR Avalon-MM RX master port connects to more than one Avalon‑MM slave, assign the base addresses of the slaves sequentially and place the slaves in the smallest power‑of‑two‑sized address space possible. Doing so minimizes the system address space used by the BAR.

Level Two Title