External Memory Interfaces Intel Agilex® 7 M-Series FPGA IP User Guide

Download PDF
ID 772538
Date 4/03/2023
Public

A newer version of this document is available. Customers should click here to go to the newest version.

Document Table of Contents
Document Table of Contents x
1. About the External Memory Interfaces Intel Agilex® 7 M-Series FPGA IP 2. Intel Agilex® 7 M-Series FPGA EMIF IP – Introduction 3. Intel Agilex® 7 M-Series FPGA EMIF IP – Product Architecture 4. Intel Agilex® 7 M-Series FPGA EMIF IP – End-User Signals 5. Intel Agilex® 7 M-Series FPGA EMIF IP – Simulating Memory IP 6. Intel Agilex 7 M-Series FPGA EMIF IP – DDR4 Support 7. Intel Agilex® 7 M-Series FPGA EMIF IP – DDR5 Support 8. Intel Agilex 7 M-Series FPGA EMIF IP – LPDDR5 Support 9. Intel Agilex® 7 M-Series FPGA EMIF IP – Timing Closure 10. Intel Agilex® 7 M-Series FPGA EMIF IP – Controller Optimization 11. Intel Agilex® 7 M-Series FPGA EMIF IP – Debugging 12. Document Revision History for External Memory Interfaces Intel Agilex® 7 M-Series FPGA IP User Guide
1. About the External Memory Interfaces Intel Agilex® 7 M-Series FPGA IP x
1.1. Release Information
2. Intel Agilex® 7 M-Series FPGA EMIF IP – Introduction x
2.1. Intel Agilex® 7 M-Series EMIF IP Protocol and Feature Support 2.2. Intel Agilex® 7 M-Series EMIF IP Design Flow 2.3. Intel Agilex® 7 M-Series EMIF IP Design Checklist
3. Intel Agilex® 7 M-Series FPGA EMIF IP – Product Architecture x
3.1. Intel Agilex® 7 M-Series EMIF Architecture: Introduction 3.2. Intel Agilex® 7 M-Series EMIF Sequencer 3.3. Intel Agilex® 7 M-Series EMIF Controller
3.1. Intel Agilex® 7 M-Series EMIF Architecture: Introduction x
3.1.1. Intel Agilex® 7 M-Series EMIF Architecture: I/O Subsystem 3.1.2. Intel Agilex® 7 M-Series EMIF Architecture: I/O SSM 3.1.3. Intel Agilex® 7 M-Series EMIF Architecture: I/O Bank 3.1.4. Intel Agilex® 7 M-Series EMIF Architecture: I/O Lane 3.1.5. Intel Agilex® 7 M-Series EMIF Architecture: Input DQS Clock Tree 3.1.6. Intel Agilex® 7 M-Series EMIF Architecture: PHY Clock Tree 3.1.7. Intel Agilex® 7 M-Series EMIF Architecture: PLL Reference Clock Networks 3.1.8. Intel Agilex® 7 M-Series EMIF Architecture: Clock Phase Alignment
3.1.3. Intel Agilex® 7 M-Series EMIF Architecture: I/O Bank x
3.1.3.1. DDR4 Pin Placement 3.1.3.2. DDR5 Pin Placement 3.1.3.3. LPDDR5 Pin Placement 3.1.3.4. I/O Sub-Bank Usage
3.2. Intel Agilex® 7 M-Series EMIF Sequencer x
3.2.1. Intel Agilex® 7 M-Series Mailbox Structure and Register Definitions
3.3. Intel Agilex® 7 M-Series EMIF Controller x
3.3.1. Hard Memory Controller
3.3.1. Hard Memory Controller x
3.3.1.1. Hard Memory Controller Features
4. Intel Agilex® 7 M-Series FPGA EMIF IP – End-User Signals x
4.1. Intel Agilex® 7 M-Series EMIF IP for DDR4 Interfaces 4.2. Intel Agilex® 7 M-Series EMIF IP for DDR5 Interfaces 4.3. Intel Agilex® 7 M-Series EMIF IP for LPDDR5 Interfaces
4.1. Intel Agilex® 7 M-Series EMIF IP for DDR4 Interfaces x
4.1.1. ref_clk for EMIF 4.1.2. core_init_n for EMIF 4.1.3. usr_async_clk for EMIF 4.1.4. usr_clk for EMIF 4.1.5. usr_rst_n for EMIF 4.1.6. s0_axi4 for EMIF 4.1.7. mem for EMIF 4.1.8. oct for EMIF 4.1.9. s0_axil_clk for EMIF 4.1.10. s0_axil_rst_n for EMIF 4.1.11. s0_axil for EMIF
4.2. Intel Agilex® 7 M-Series EMIF IP for DDR5 Interfaces x
4.2.1. ref_clk for EMIF 4.2.2. core_init_n for EMIF 4.2.3. usr_async_clk for EMIF 4.2.4. usr_clk for EMIF 4.2.5. usr_rst_n for EMIF 4.2.6. s0_axi4 for EMIF 4.2.7. mem for EMIF 4.2.8. oct for EMIF 4.2.9. s0_axil_clk for EMIF 4.2.10. s0_axil_rst_n for EMIF 4.2.11. s0_axil for EMIF
4.3. Intel Agilex® 7 M-Series EMIF IP for LPDDR5 Interfaces x
4.3.1. ref_clk for EMIF 4.3.2. core_init_n for EMIF 4.3.3. usr_async_clk for EMIF 4.3.4. usr_clk for EMIF 4.3.5. usr_rst_n for EMIF 4.3.6. s0_axi4 for EMIF 4.3.7. mem for EMIF 4.3.8. oct for EMIF 4.3.9. s0_axil_clk for EMIF 4.3.10. s0_axil_rst_n for EMIF 4.3.11. s0_axil for EMIF
5. Intel Agilex® 7 M-Series FPGA EMIF IP – Simulating Memory IP x
5.1. Simulation Walkthrough
5.1. Simulation Walkthrough x
5.1.1. Calibration 5.1.2. Simulation Scripts 5.1.3. Functional Simulation with Verilog HDL 5.1.4. Simulating the Design Example
6. Intel Agilex 7 M-Series FPGA EMIF IP – DDR4 Support x
6.1. Intel Agilex 7 M-Series FPGA EMIF IP Parameters for DDR4 6.2. Intel Agilex® 7 M-Series FPGA EMIF IP Pin and Resource Planning 6.3. DDR4 Board Design Guidelines
6.1. Intel Agilex 7 M-Series FPGA EMIF IP Parameters for DDR4 x
6.1.1. Intel Agilex 7 M-Series FPGA EMIF Memory Device Description IP (DDR4) Parameter Descriptions 6.1.2. Intel Agilex 7 M-Series FPGA EMIF IP Parameter Descriptions (DDR4)
6.2. Intel Agilex® 7 M-Series FPGA EMIF IP Pin and Resource Planning x
6.2.1. Intel Agilex® 7 M-Series FPGA EMIF IP Interface Pins 6.2.2. Intel Agilex® 7 M-Series FPGA EMIF IP Resources 6.2.3. Pin Guidelines for Intel Agilex® 7 M-Series FPGA EMIF IP 6.2.4. Pin Placements for Intel Agilex® 7 M-Series FPGA DDR4 EMIF IP
6.2.1. Intel Agilex® 7 M-Series FPGA EMIF IP Interface Pins x
6.2.1.1. Estimating Pin Requirements 6.2.1.2. DIMM Options 6.2.1.3. Maximum Number of Interfaces
6.2.2. Intel Agilex® 7 M-Series FPGA EMIF IP Resources x
6.2.2.1. OCT 6.2.2.2. PLL
6.2.4. Pin Placements for Intel Agilex® 7 M-Series FPGA DDR4 EMIF IP x
6.2.4.1. Address and Command Pin Placement for DDR4 6.2.4.2. DDR4 Data Width Mapping 6.2.4.3. General Guidelines 6.2.4.4. x4 DIMM Implementation 6.2.4.5. Specific Pin Connection Requirements 6.2.4.6. Command and Address Signals 6.2.4.7. Clock Signals 6.2.4.8. Data, Data Strobes, DM/DBI, and Optional ECC Signals
6.3. DDR4 Board Design Guidelines x
6.3.1. Terminations for DDR4 with Intel Agilex® 7 M-Series Devices 6.3.2. General Layout Routing Guidelines 6.3.3. Reference Stackup 6.3.4. Intel Agilex® 7 M-Series EMIF-Specific Routing Guidelines for Various DDR4 Topologies 6.3.5. DDR4 Routing Guidelines: Discrete (Component) Topologies
6.3.1. Terminations for DDR4 with Intel Agilex® 7 M-Series Devices x
6.3.1.1. Dynamic On-Chip Termination (OCT) 6.3.1.2. Dynamic On-Die Termination (ODT) in DDR4 6.3.1.3. Choosing Terminations on Intel Agilex® 7 M-Series FPGA Devices 6.3.1.4. On-Chip Termination Recommendations for Intel Agilex® 7 M-Series FPGA Devices
6.3.4. Intel Agilex® 7 M-Series EMIF-Specific Routing Guidelines for Various DDR4 Topologies x
6.3.4.1. One DIMM per Channel (1DPC) for UDIMM, RDIMM, and SODIMM DDR4 Topologies 6.3.4.2. Skew Matching Guidelines for DIMM Configurations 6.3.4.3. Power Delivery Recommendations for the Memory / DIMM Side
6.3.5. DDR4 Routing Guidelines: Discrete (Component) Topologies x
6.3.5.1. Single Rank x 8 Discrete (Component) Topology 6.3.5.2. Single Rank x 16 Discrete (Component) Topology 6.3.5.3. ADDR/CMD Reference Voltage/RESET Signal Routing Guidelines for Single Rank x 8 and Single Rank x 16 Discrete (Component) Topologies 6.3.5.4. Skew Matching Guidelines for DDR4 Discrete Configurations 6.3.5.5. Power Delivery Recommendations for DDR4 Discrete Configurations 6.3.5.6. Intel Agilex® 7 M-Series EMIF Pin Swapping Guidelines
6.3.5.6. Intel Agilex® 7 M-Series EMIF Pin Swapping Guidelines x
6.3.5.6.1. DDR4 Byte Lane Swapping 6.3.5.6.2. DDR4 Address and Command and CLK Lane 6.3.5.6.3. DDR4 Interface x8 Data Lane 6.3.5.6.4. DDR4 Interface x4 Data Lane
7. Intel Agilex® 7 M-Series FPGA EMIF IP – DDR5 Support x
7.1. Intel Agilex 7 M-Series FPGA EMIF IP Parameters for DDR5 7.2. Intel Agilex® 7 M-Series FPGA EMIF IP Pin and Resource Planning
7.1. Intel Agilex 7 M-Series FPGA EMIF IP Parameters for DDR5 x
7.1.1. Intel Agilex 7 M-Series FPGA EMIF Memory Device Description IP (DDR5) Parameter Descriptions 7.1.2. Intel Agilex 7 M-Series FPGA EMIF IP Parameter Descriptions (DDR5)
7.2. Intel Agilex® 7 M-Series FPGA EMIF IP Pin and Resource Planning x
7.2.1. Intel Agilex® 7 M-Series FPGA EMIF IP Interface Pins 7.2.2. Intel Agilex® 7 M-Series FPGA EMIF IP Resources 7.2.3. Pin Guidelines for Intel Agilex® 7 M-Series FPGA EMIF IP
7.2.1. Intel Agilex® 7 M-Series FPGA EMIF IP Interface Pins x
7.2.1.1. Estimating Pin Requirements 7.2.1.2. DIMM Options 7.2.1.3. Maximum Number of Interfaces
7.2.2. Intel Agilex® 7 M-Series FPGA EMIF IP Resources x
7.2.2.1. OCT 7.2.2.2. PLL
7.2.3. Pin Guidelines for Intel Agilex® 7 M-Series FPGA EMIF IP x
7.2.3.1. General Guidelines 7.2.3.2. x4 DIMM Implementation 7.2.3.3. Specific Pin Connection Requirements 7.2.3.4. Command and Address Signals 7.2.3.5. Clock Signals 7.2.3.6. Data, Data Strobes, DM/DBI, and Optional ECC Signals
8. Intel Agilex 7 M-Series FPGA EMIF IP – LPDDR5 Support x
8.1. Intel Agilex 7 M-Series FPGA EMIF IP Parameters for LPDDR5 8.2. Intel Agilex® 7 M-Series FPGA EMIF IP Pin and Resource Planning
8.1. Intel Agilex 7 M-Series FPGA EMIF IP Parameters for LPDDR5 x
8.1.1. Intel Agilex 7 M-Series FPGA EMIF Memory Device Description IP (LPDDR5) Parameter Descriptions 8.1.2. Intel Agilex 7 M-Series FPGA External Memory Interfaces (EMIF) IP Parameter Descriptions for LPDDR5
8.2. Intel Agilex® 7 M-Series FPGA EMIF IP Pin and Resource Planning x
8.2.1. Intel Agilex® 7 M-Series FPGA EMIF IP Interface Pins 8.2.2. Intel Agilex® 7 M-Series FPGA EMIF IP Resources 8.2.3. Pin Guidelines for Intel Agilex® 7 M-Series FPGA EMIF IP
8.2.1. Intel Agilex® 7 M-Series FPGA EMIF IP Interface Pins x
8.2.1.1. Estimating Pin Requirements 8.2.1.2. DIMM Options 8.2.1.3. Maximum Number of Interfaces
8.2.2. Intel Agilex® 7 M-Series FPGA EMIF IP Resources x
8.2.2.1. OCT 8.2.2.2. PLL
8.2.3. Pin Guidelines for Intel Agilex® 7 M-Series FPGA EMIF IP x
8.2.3.1. General Guidelines 8.2.3.2. Specific Pin Connection Requirements 8.2.3.3. Command and Address Signals 8.2.3.4. Clock Signals
9. Intel Agilex® 7 M-Series FPGA EMIF IP – Timing Closure x
9.1. Timing Closure 9.2. Optimizing Timing
9.1. Timing Closure x
9.1.1. Timing Analysis
9.1.1. Timing Analysis x
9.1.1.1. PHY or Core
10. Intel Agilex® 7 M-Series FPGA EMIF IP – Controller Optimization x
10.1. Interface Standard 10.2. Bank Management Efficiency 10.3. Data Transfer 10.4. Improving Controller Efficiency
10.4. Improving Controller Efficiency x
10.4.1. Frequency of Operation 10.4.2. Series of Reads or Writes
11. Intel Agilex® 7 M-Series FPGA EMIF IP – Debugging x
11.1. Interface Configuration Performance Issues 11.2. Functional Issue Evaluation 11.3. Timing Issue Characteristics 11.4. Verifying Memory IP Using the Signal Tap Logic Analyzer 11.5. Generating Traffic with the Test Engine IP
11.1. Interface Configuration Performance Issues x
11.1.1. Interface Configuration Bottleneck and Efficiency Issues
11.2. Functional Issue Evaluation x
11.2.1. Intel® IP Memory Model 11.2.2. Vendor Memory Model 11.2.3. Transcript Window Messages
11.3. Timing Issue Characteristics x
11.3.1. Evaluating FPGA Timing Issues 11.3.2. Evaluating External Memory Interface Timing Issues
1. About the External Memory Interfaces Intel Agilex® 7 M-Series FPGA IP
2. Intel Agilex® 7 M-Series FPGA EMIF IP – Introduction
3. Intel Agilex® 7 M-Series FPGA EMIF IP – Product Architecture
4. Intel Agilex® 7 M-Series FPGA EMIF IP – End-User Signals
5. Intel Agilex® 7 M-Series FPGA EMIF IP – Simulating Memory IP
6. Intel Agilex 7 M-Series FPGA EMIF IP – DDR4 Support
7. Intel Agilex® 7 M-Series FPGA EMIF IP – DDR5 Support
8. Intel Agilex 7 M-Series FPGA EMIF IP – LPDDR5 Support
9. Intel Agilex® 7 M-Series FPGA EMIF IP – Timing Closure
10. Intel Agilex® 7 M-Series FPGA EMIF IP – Controller Optimization
11. Intel Agilex® 7 M-Series FPGA EMIF IP – Debugging
12. Document Revision History for External Memory Interfaces Intel Agilex® 7 M-Series FPGA IP User Guide

11.5. Generating Traffic with the Test Engine IP

Every Intel Agilex® 7 M-Series FPGA EMIF design example includes an instance of the software-driven programmable AXI traffic generator, known as the Test Engine IP.

You can view the Test Engine IP software within the following Python scripts:

  • A main.py file that parses the .qsys file and selects the traffic program to run during execution.
  • A traffic_patterns.py file that contains many different tutorial programs and functional tests that you can refer to when writing your own traffic patterns.

For the EMIF design example, the hard-coded traffic program selected when you generate a design is the emif_tg_emulation traffic program, which provides these features:

  • Single write and read (with AxLEN=axlen_a 1 )
  • Single write and read (with AxLEN=axlen_b 2 )
  • Sequential address 3 block of 512 writes and 512 reads (with AxLEN=axlen_a 1 )
  • Sequential address 3 block of 512 writes and 512 reads (with AxLEN=axlen_b 2 )
  • Random address 4 block of 512 writes and 512 reads (with AxLEN= axlen_a 1 )
1 The axlen_a value is dependent on the memory technology:
  • For DDR4: 0
  • For DDR5: 1
  • For LPDDR5: 3
2 The axlen_b value is dependent on the memory technology:
  • For DDR4: 0
  • For DDR5: 0 (results in Read-Modify-Write or Data-Masking on the memory side).
  • For LPDDR5: 3
3 Sequential Address pattern starts at address=0, and increments by (AXI_DATA_WIDTH/8)*(AxLEN+1) on each transaction.
4 Random Address pattern starts at address=0, and uses pseudo-random addresses.
Level Two Title