AN 802: Intel® Stratix® 10 SoC Device Design Guidelines

Download PDF
ID 683117
Date 8/05/2021
Public
Document Table of Contents
Document Table of Contents x
1. Introduction to the Intel® Stratix® 10 SoC Device Design Guidelines 2. Board Design Guidelines for Stratix 10 SoC FPGAs 3. Interfacing to the FPGA for Stratix 10 SoC FPGAs 4. System Considerations for Stratix 10 SoC FPGAs 5. Embedded Software Design Guidelines for Intel® Stratix® 10 SoC FPGAs 6. Recommended Resources for Stratix 10 SoC FPGAs
1. Introduction to the Intel® Stratix® 10 SoC Device Design Guidelines x
1.1. Introduction to the Stratix 10 SoC Device Design Guidelines Revision History
2. Board Design Guidelines for Stratix 10 SoC FPGAs x
2.1. Pin Connection Considerations for Board Design 2.2. HPS Clocking and Reset Design Considerations 2.3. Design Considerations for Connecting Device I/O to HPS Peripherals and Memory 2.4. Design Guidelines for HPS Interfaces 2.5. HPS EMIF Design Considerations 2.6. HPS Memory Debug 2.7. Boundary Scan for HPS 2.8. Embedded Software Debugging and Trace 2.9. Board Design Guidelines for Intel® Stratix® 10 SoC FPGAs Revision History
2.1. Pin Connection Considerations for Board Design x
2.1.1. Board-Related Intel® Quartus® Prime Settings
2.1.1. Board-Related Intel® Quartus® Prime Settings x
2.1.1.1. Unused Pins
2.2. HPS Clocking and Reset Design Considerations x
2.2.1. HPS Clock Planning 2.2.2. Early Pin Planning and I/O Assignment Analysis 2.2.3. Pin Features and Connections for HPS Clocks, Reset and PoR 2.2.4. Direct to Factory Pin Support for Remote System Update (RSU) Feature 2.2.5. Internal Clocks 2.2.6. HPS Peripheral Reset Management
2.3. Design Considerations for Connecting Device I/O to HPS Peripherals and Memory x
2.3.1. HPS Pin Multiplexing Design Considerations 2.3.2. HPS I/O Settings: Constraints and Drive Strengths
2.4. Design Guidelines for HPS Interfaces x
2.4.1. HPS EMAC PHY Interfaces 2.4.2. USB Interface Design Guidelines 2.4.3. SD/MMC and eMMC Card Interface Design Guidelines 2.4.4. Design Guidelines for Flash Interfaces 2.4.5. UART Interface Design Guidelines 2.4.6. I2C Interface Design Guidelines
2.4.1. HPS EMAC PHY Interfaces x
2.4.1.1. PHY Interfaces 2.4.1.2. PHY Interfaces Connected Through FPGA I/O 2.4.1.3. MDIO 2.4.1.4. Common PHY Interface Design Considerations
2.4.1.1. PHY Interfaces x
2.4.1.1.1. RMII 2.4.1.1.2. RGMII
2.4.1.2. PHY Interfaces Connected Through FPGA I/O x
2.4.1.2.1. GMII/MII 2.4.1.2.2. Adapting to RGMII 2.4.1.2.3. Adapting to RMII 2.4.1.2.4. Adapting to SGMII
2.4.1.4. Common PHY Interface Design Considerations x
2.4.1.4.1. Signal Integrity
2.4.4. Design Guidelines for Flash Interfaces x
2.4.4.1. NAND Flash Interface Design Guidelines
2.5. HPS EMIF Design Considerations x
2.5.1. Considerations for Connecting HPS to SDRAM 2.5.2. HPS SDRAM I/O Locations
3. Interfacing to the FPGA for Stratix 10 SoC FPGAs x
3.1. Overview of HPS Memory-Mapped Interfaces 3.2. Recommended System Topologies 3.3. Recommended Starting Point for HPS-to-FPGA Interface Designs 3.4. Timing Closure for FPGA Accelerators 3.5. Information on How to Configure and Use the Bridges 3.6. Interfacing to the FPGA for Intel® Stratix® 10 SoC FPGAs Revision History
3.1. Overview of HPS Memory-Mapped Interfaces x
3.1.1. HPS-to-FPGA Bridge 3.1.2. Lightweight HPS-to-FPGA Bridge 3.1.3. FPGA-to-HPS Bridge 3.1.4. FPGA-to-SDRAM Ports 3.1.5. Interface Bandwidths Relative Latencies and Throughputs for Each HPS Interface GUIDELINE: Avoid using the HPS-to-FPGA bridge to access peripheral registers in the FPGA from the MPU. GUIDELINE: Avoid using the lightweight HPS-to-FPGA bridge to access memory in the FPGA from the MPU. GUIDELINE: Avoid using the FPGA-to-HPS bridge to access non-cache coherent SDRAM from masters in the FPGA. GUIDELINE: Use soft logic in the FPGA (for example, a DMA controller) to move shared data between the HPS and FPGA. Avoid using the MPU and the HPS DMA controller for this use case.
3.2. Recommended System Topologies x
3.2.1. HPS Accesses to FPGA Fabric 3.2.2. MPU Sharing Data with FPGA 3.2.3. Examples of Cacheable and Non-Cacheable Data Accesses From the FPGA
3.2.3. Examples of Cacheable and Non-Cacheable Data Accesses From the FPGA x
3.2.3.1. Example 1: FPGA Reading Data from HPS SDRAM Directly 3.2.3.2. Example 2: FPGA Writing Data into HPS SDRAM Directly 3.2.3.3. Example 3: FPGA Reading Cache Coherent Data from HPS 3.2.3.4. Example 4: FPGA Writing Cache Coherent Data to HPS
4. System Considerations for Stratix 10 SoC FPGAs x
4.1. Timing Considerations 4.2. Maximizing Performance 4.3. System Level Cache Coherency 4.4. System Considerations for Stratix 10 SoC FPGAs Revision History
4.1. Timing Considerations x
4.1.1. Timing Closure for FPGA Accelerators 4.1.2. USB Interface Design Guidelines
4.1.1. Timing Closure for FPGA Accelerators x
4.1.1.1. HPS First and FPGA First Boot Considerations
5. Embedded Software Design Guidelines for Intel® Stratix® 10 SoC FPGAs x
5.1. Overview 5.2. Assembling the Components of Your Software Development Platform 5.3. Golden Hardware Reference Design (GHRD) 5.4. Selecting an Operating System for Your Application 5.5. Assembling Your Software Development Platform for Linux* 5.6. Assembling your Software Development Platform for a Bare-Metal Application 5.7. Assembling your Software Development Platform for Partner OS or RTOS 5.8. Choosing the Bootloader Software 5.9. Selecting Software Tools for Development, Debug and Trace 5.10. Boot And Configuration Considerations 5.11. System Reset Considerations 5.12. Flash Considerations 5.13. Embedded Software Debugging and Trace 5.14. Embedded Software Design Guidelines for Intel® Stratix® 10 SoC FPGAs Revision History
5.4. Selecting an Operating System for Your Application x
5.4.1. Using Linux* or RTOS 5.4.2. Developing a Bare-Metal Application 5.4.3. Using the Bootloader as a Bare-Metal Framework 5.4.4. Using Symmetrical vs. Asymmetrical Multiprocessing (SMP vs. AMP) Modes
5.5. Assembling Your Software Development Platform for Linux* x
5.5.1. Golden System Reference Design (GSRD) for Linux* 5.5.2. Source Code Management Considerations
5.9. Selecting Software Tools for Development, Debug and Trace x
5.9.1. Selecting Software Build Tools 5.9.2. Selecting Software Debug Tools 5.9.3. Selecting Software Trace Tools
5.10. Boot And Configuration Considerations x
5.10.1. Configuration Sources 5.10.2. Configuration Flash 5.10.3. Configuration Clock 5.10.4. Selecting HPS Boot Options 5.10.5. HPS Boot Sources 5.10.6. Remote System Update (RSU)
5.12. Flash Considerations x
5.12.1. Flash Programming Method 5.12.2. Using a Single flash for Both FPGA Configuration and HPS Mass Storage
6. Recommended Resources for Stratix 10 SoC FPGAs x
6.1. Device Documentation 6.2. Tools and Software Web Pages 6.3. Recommended Resources for Intel® Stratix® 10 SoC FPGAs Revision History
1. Introduction to the Intel® Stratix® 10 SoC Device Design Guidelines
2. Board Design Guidelines for Stratix 10 SoC FPGAs
3. Interfacing to the FPGA for Stratix 10 SoC FPGAs
4. System Considerations for Stratix 10 SoC FPGAs
5. Embedded Software Design Guidelines for Intel® Stratix® 10 SoC FPGAs
6. Recommended Resources for Stratix 10 SoC FPGAs

3.1.5. Interface Bandwidths

To identify which interface should be used to move data between the HPS and FPGA fabric, an understanding of the bandwidth of each interface is necessary. The figure below illustrates the peak throughput available between the HPS and FPGA fabric as well as the internal bandwidths within the HPS. The example shown assumes that the FPGA fabric operates at 400 MHz, the MPU operates at 1200 MHz, and the 64-bit external SDRAM operates at 1067 MHz.

Figure 12. Stratix 10 HPS Memory Mapped BandwidthFor abbreviations, refer to the figure in Overview of HPS Memory-Mapped Interfaces.

Relative Latencies and Throughputs for Each HPS Interface

Interface

Transaction Use Case

Latency

Throughput

HPS-to-FPGA

MPU accessing memory in FPGA

Medium

Medium

HPS-to-FPGA

MPU accessing peripheral in FPGA

Medium

Very Low

Lightweight HPS-to-FPGA

MPU accessing register in FPGA

Low

Low

Lightweight HPS-to-FPGA

MPU accessing memory in FPGA

Low

Very Low

FPGA-to-HPS

FPGA master accessing non-cache coherent SDRAM

High

Medium

FPGA-to-HPS

FPGA master accessing HPS on-chip RAM

Low

High

FPGA-to-HPS

FPGA master accessing HPS peripheral

Low

Low

FPGA-to-HPS

FPGA master accessing coherent memory resulting in cache miss

High

Medium

FPGA-to-HPS

FPGA master accessing coherent memory resulting in cache hit

Low

Medium-High

FPGA-to-SDRAM

FPGA master accessing SDRAM through single FPGA-to-SDRAM port

Medium

High

FPGA-to-SDRAM

FPGA masters accessing SDRAM through multiple FPGA-to-SDRAM ports

Medium

Very High
Note: For the interfaces with no configuration recommended, refer to the corresponding interface sections: "HPS-to-FPGA Bridge", "Lightweight HPS-to-FPGA Bridge", and "FPGA-to-HPS Bridge".

GUIDELINE: Avoid using the HPS-to-FPGA bridge to access peripheral registers in the FPGA from the MPU.

The HPS-to-FPGA bridge is optimized for bursting traffic and peripheral accesses are typically short word-sized accesses of only one beat. As a result if peripherals are accessed through the HPS-to-FPGA bridge, the transaction can be stalled by other bursting traffic that is already in flight.

GUIDELINE: Avoid using the lightweight HPS-to-FPGA bridge to access memory in the FPGA from the MPU.

The lightweight HPS-to-FPGA bridge is optimized for non-bursting traffic and typically memory accesses are performed as bursts (often 32 bytes due to cache operations). As a result, if memory is accessed through the lightweight HPS-to-FPGA bridge, the throughput is limited.

GUIDELINE: Avoid using the FPGA-to-HPS bridge to access non-cache coherent SDRAM from masters in the FPGA.

The FPGA-to-HPS bridge is optimized for accessing non-SDRAM accesses (peripherals, on-chip RAM). As a result, accessing SDRAM directly by performing non-coherent accesses increases the latency and limits the throughput compared to accesses to FPGA-to-SDRAM ports.

GUIDELINE: Use soft logic in the FPGA (for example, a DMA controller) to move shared data between the HPS and FPGA. Avoid using the MPU and the HPS DMA controller for this use case.

When moving shared data between the HPS and FPGA Intel® recommends to do so from the FPGA instead of moving the data using the MPU or HPS DMA controller. If the FPGA must access cache coherent data then it must access the FPGA-to-HPS bridge with the appropriate ACE-Lite cache extensions signaling to issue a cacheable transaction. If non-cache coherent data must be moved to the FPGA or HPS, a DMA engine implemented in FPGA logic can move the data through one of the FPGA-to-SDRAM bridge ports, achieving the highest throughput possible. Even though the HPS includes a DMA engine internally that can move data between the HPS and FPGA, its purpose is to assist peripherals that do not master memory or provide memory to memory data movements on behalf of the MPU.

Related Information
Level Two Title