AN 1003: Multi Memory IP System Resource Planning: for Intel Agilex® 7 M-Series FPGAs

Download PDF
ID 788295
Date 11/22/2023
Public
Document Table of Contents
Document Table of Contents x
1. Answers to Top FAQs 2. About This Application Note 3. Component Bandwidth Projections and Limitations 4. Resource Planning for Intel Agilex® 7 M-Series FPGAs 5. Factors Affecting NoC Performance 6. Debugging the NoC 7. Document Revision History of AN 1003: Multi Memory IP System Resource Planning for Intel Agilex® 7 M-Series FPGAs
2. About This Application Note x
2.1. Preliminary Guidelines 2.2. Document Prerequisites 2.3. Terminology for Intel Agilex® 7 M-Series FPGAs
3. Component Bandwidth Projections and Limitations x
3.1. Memory Controller Efficiency 3.2. Hard Memory NoC Bandwidth 3.3. Overall Bandwidth for NoC Systems
3.1. Memory Controller Efficiency x
3.1.1. HBM2E UIB Controller Efficiency 3.1.2. External Memory Interface Controller Efficiency
3.2. Hard Memory NoC Bandwidth x
3.2.1. Horizontal NoC Bandwidth 3.2.2. Initiator NoC Bandwidth 3.2.3. Target NoC Bandwidth 3.2.4. Initiator Target Link Bandwidth
4. Resource Planning for Intel Agilex® 7 M-Series FPGAs x
4.1. Hard Memory NoC Resource Planning Overview 4.2. I/O Bank Blockage 4.3. Planning Avalon® Streaming Utilization 4.4. Planning for Initiator Blockage Impact from GPIO, LVDS SERDES, and PHY Lite Bypass Mode 4.5. Planning NoC PLL and I/O PLL 4.6. Pin Planning for HPS EMIF 4.7. Planning for an External Memory Interface 4.8. Planning for HBM2E 4.9. Planning for the Fabric NoC 4.10. Planning for AXI4-Lite 4.11. Planning NoC and Memory Solution Clocks
4.2. I/O Bank Blockage x
4.2.1. Top Hard Memory NoC 4.2.2. Bottom Hard Memory NoC
4.10. Planning for AXI4-Lite x
4.10.1. Single AXI4 Lite Initiator for Each Horizontal NoC 4.10.2. AXI4-Lite Initiator for HBM2E 4.10.3. AXI4-Lite Initiator for EMIF
4.11. Planning NoC and Memory Solution Clocks x
4.11.1. Clocking without the Fabric NoC 4.11.2. Clocking with the Fabric NoC
5. Factors Affecting NoC Performance x
5.1. Recommended Performance Tuning Procedure 5.2. NoC Initiator and Target Clock Rate 5.3. Recommended NoC Design Topologies 5.4. Traffic Access Pattern and Memory Controller Efficiency 5.5. Traffic Access Pattern Due To Multiple Traffic Flows 5.6. Transaction Size 5.7. Congestion Interaction 5.8. Bandwidth Sharing At Each Switch 5.9. Exceeding NoC Bandwidth Limits 5.10. Maximum Number of Outstanding Transactions 5.11. QoS Priority 5.12. AxID 5.13. Example: 2x2 HBM Crossbars 5.14. Example: 16x16 Crossbar
5.3. Recommended NoC Design Topologies x
5.3.1. 1:1 Connectivity with EMIF and HBM 5.3.2. HBM Crossbars 5.3.3. Connectivity with HPS
6. Debugging the NoC x
6.1. Debugging NoC AXI Transaction Issues 6.2. Debugging NoC Bit Errors 6.3. Debugging NoC Performance Issues
6.3. Debugging NoC Performance Issues x
6.3.1. Measuring Performance with the Signal Tap Logic Analyzer 6.3.2. Measuring Performance with the Performance Monitor 6.3.3. Performance Debug Steps
1. Answers to Top FAQs
2. About This Application Note
3. Component Bandwidth Projections and Limitations
4. Resource Planning for Intel Agilex® 7 M-Series FPGAs
5. Factors Affecting NoC Performance
6. Debugging the NoC
7. Document Revision History of AN 1003: Multi Memory IP System Resource Planning for Intel Agilex® 7 M-Series FPGAs

4.8. Planning for HBM2E

Each HBM2E stack has four or eight layers, with each layer providing 2 GB. Therefore, a single HBM2E can contain 8 or 16 GB of high-bandwidth memory. Each stack has an associated universal interface bus (UIB) function, which includes 16 hard controller cores and hard PHYs. Each hard controller core services one HBM2E pseudo channel.

At maximum performance, HBM2E can provide up to 410GBps per stack. Combining the two HBM2E stacks can provide up to 820 GBps of peak memory bandwidth.

To achieve the optimum possible bandwidth on HBM2E:

  • You must use all 16 initiators.
  • Place all 16 initiators in the center.
  • Place 9 initiators directly across from the UIB.
  • Place the remaining initiators in adjacent sectors on the left and right of the UIB section to create a balanced distribution of initiators. The actual physical placement of these seven remaining initiators also depends on your system requirements of GPIO, EMIF, and HPS EMIF.

Initial performance analysis does not show bandwidth impact when placing the HBM2E initiator where the traffic goes through multiple switches in the horizontal NoC to communicate with targets. You could see latency impact in your specific application.

Figure 7. Achievable Bandwidth for HBM2E Across Device Speed Grade

HBM2E also has a limitation on achievable bandwidth across speed grade, even if HBM2E is running faster. This impact occurs regardless of the hard memory controller capabilities. Achievable Bandwidth for HBM2E Across Device Speed Grade uses color coding to represent the effect of initiator frequency on bandwidth loss. Green color shading signifies no degradation, while red color shading indicates the severity of bandwidth loss. More than 16 initiators are needed to fully saturate a -1 device bandwidth due to limited initiator frequency support.

If your application requires less bandwidth, you can choose to use fewer initiators with centralized placement, talking to multiple targets.

Level Two Title