Video and Vision Processing Suite Intel® FPGA IP User Guide

Download PDF
ID 683329
Date 9/30/2022
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A newer version of this document is available.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 Video and Vision Processing Suite 2. Getting Started with the Video and Vision Processing IPs 3. Video and Vision Processing IPs Functional Description 4. Video and Vision Processing IP Interfaces 5. Video and Vision Processing IP Registers 6. Video and Vision Processing IPs Software Programming Model 7. Protocol Converter Intel® FPGA IP 8. 3D LUT Intel® FPGA IP 9. AXI-Stream Broadcaster Intel® FPGA IP 10. Chroma Key Intel® FPGA IP 11. Chroma Resampler Intel® FPGA IP 12. Clipper Intel® FPGA IP 13. Clocked Video Input Intel® FPGA IP 14. Clocked Video to Full-Raster Converter Intel® FPGA IP 15. Clocked Video Output Intel® FPGA IP 16. Color Space Converter Intel® FPGA IP 17. Deinterlacer Intel® FPGA IP 18. FIR Filter Intel® FPGA IP 19. Frame Cleaner Intel® FPGA IP 20. Full-Raster to Clocked Video Converter Intel® FPGA IP 21. Full-Raster to Streaming Converter Intel® FPGA IP 22. Generic Crosspoint Intel® FPGA IP 23. Genlock Signal Router Intel® FPGA IP 24. Guard Bands Intel® FPGA IP 25. Interlacer Intel® FPGA IP 26. Mixer Intel® FPGA IP 27. Pixels in Parallel Converter Intel® FPGA IP 28. Scaler Intel® FPGA IP 29. Stream Cleaner Intel® FPGA IP 30. Switch Intel® FPGA IP 31. Tone Mapping Operator Intel® FPGA IP 32. Test Pattern Generator Intel® FPGA IP 33. Video Frame Buffer Intel® FPGA IP 34. Video Streaming FIFO Intel® FPGA IP 35. Video Timing Generator Intel® FPGA IP 36. Warp Intel® FPGA IP 37. Design Security 38. Document Revision History for Video and Vision Processing Suite User Guide
1. About the Video and Vision Processing Suite x
1.1. Video and Vision Processing IPs Features 1.2. Device Family Support 1.3. Video and Vision Processing IPs Release Information 1.4. Lite versus Full IP Variants 1.5. Glossary of Video and Vision Terminology
2. Getting Started with the Video and Vision Processing IPs x
2.1. Video and Vision Processing IP Evaluation Time-out Behavior 2.2. Generating a Video and Vision Processing IP 2.3. Simulating the Video and Vision Processing IPs
3. Video and Vision Processing IPs Functional Description x
3.1. Auxiliary Control Packets 3.2. Latency 3.3. IP Debugging Features 3.4. Stall Behavior and Error Recovery 3.5. Avalon Streaming Video Protocol Versus Intel FPGA Streaming Video Protocol
5. Video and Vision Processing IP Registers x
5.1. Video and Vision Processing IP Control Examples
7. Protocol Converter Intel® FPGA IP x
7.1. About the Protocol Converter IP 7.2. Protocol Converter IP Parameters 7.3. Protocol Converter IP Functional Description 7.4. Protocol Converter IP Interfaces 7.5. Protocol Converter IP Registers 7.6. Protocol Converter IP Software API
7.1. About the Protocol Converter IP x
7.1.1. Protocol Converter IP Performance and Resources
8. 3D LUT Intel® FPGA IP x
8.1. About the 3D LUT Intel® FPGA IP 8.2. 3D LUT IP Parameters 8.3. 3D LUT IP Block Description 8.4. 3D LUT IP Registers 8.5. 3D LUT IP Software API
8.1. About the 3D LUT Intel® FPGA IP x
8.1.1. 3D LUT IP Features 8.1.2. 3D LUT IP Performance IP and Resource Information
8.3. 3D LUT IP Block Description x
8.3.1. 3D LUT IP Interfaces 8.3.2. 3D LUT IP Latency
9. AXI-Stream Broadcaster Intel® FPGA IP x
9.1. About the AXI-Stream Broadcaster IP 9.2. AXI-Stream Broadcaster IP Parameters 9.3. AXI-Stream Broadcaster IP Interfaces
9.1. About the AXI-Stream Broadcaster IP x
9.1.1. AXI-Stream Broadcaster IP Features 9.1.2. AXI-Stream Broadcaster IP Performance and Resources
10. Chroma Key Intel® FPGA IP x
10.1. About the Chroma Key IP 10.2. Chroma Key IP Parameters 10.3. Chroma Key IP Interfaces 10.4. Chroma Key Replacement 10.5. Chroma Key IP Registers 10.6. Chroma Key IP Software API
10.1. About the Chroma Key IP x
10.1.1. Chroma Key IP Performance and Resources
11. Chroma Resampler Intel® FPGA IP x
11.1. About the Chroma Resampler IP 11.2. Chroma Resampler IP Parameters 11.3. Chroma Resampler IP Functional Description 11.4. Chroma Resampler IP Registers 11.5. Chroma Resampler IP Software API
11.1. About the Chroma Resampler IP x
11.1.1. Chroma Resampler Performance and Resources
11.3. Chroma Resampler IP Functional Description x
11.3.1. Chroma Resampler IP Interfaces
12. Clipper Intel® FPGA IP x
12.1. About the Clipper IP 12.2. Clipper IP Parameters 12.3. Clipper IP Interfaces 12.4. Clipper IP Registers 12.5. Clipper IP Software API
12.1. About the Clipper IP x
12.1.1. Clipper IP Performance and Resources
13. Clocked Video Input Intel® FPGA IP x
13.1. About the Clocked Video Input IP 13.2. Initializing the Clocked Video Input IP 13.3. Clocked Video Input IP Parameters 13.4. Clocked Video Input IP Interfaces 13.5. Clocked Video Input IP Registers 13.6. Clocked Video Input IP Software API
13.1. About the Clocked Video Input IP x
13.1.1. Clocked Video Input IP Features 13.1.2. Clocked Video Input IP Performance and Resources
14. Clocked Video to Full-Raster Converter Intel® FPGA IP x
14.1. About the Clocked Video to Full-Raster Converter IP 14.2. Clocked Video to Full-Raster Converter Parameters 14.3. Clocked Video to Full-Raster Converter Block Description 14.4. Clocked Video Converter to Full-Raster IP Registers
14.1. About the Clocked Video to Full-Raster Converter IP x
14.1.1. Clocked Video to Full-Raster Converter Features 14.1.2. Clocked Video to Full-Raster Converter Performance and Resources
14.3. Clocked Video to Full-Raster Converter Block Description x
14.3.1. Clocked Video to Full-Raster Converter Interfaces
15. Clocked Video Output Intel® FPGA IP x
15.1. About the Clocked Video Output IP 15.2. Clocked Video Output IP Parameters 15.3. Clocked Video Output IP Functional Description 15.4. Clocked Video Output IP Interfaces 15.5. Clocked Video Output IP Registers 15.6. Clocked Video Output IP Software API
15.1. About the Clocked Video Output IP x
15.1.1. Clocked Video Output IP Performance and Resources 15.1.2. Clocked Video Output IP Features
16. Color Space Converter Intel® FPGA IP x
16.1. About the Color Space Converter IP 16.2. Color Space Converter IP Parameters 16.3. Color Space Converter IP Functional Description 16.4. Color Space Converter IP Registers 16.5. Color Space Converter IP Software API
16.1. About the Color Space Converter IP x
16.1.1. Color Space Converter IP Features 16.1.2. Color Space Converter IP Performance and Resources
16.3. Color Space Converter IP Functional Description x
16.3.1. Color Space Converter IP Interfaces
17. Deinterlacer Intel® FPGA IP x
17.1. About the Deinterlacer IP 17.2. Deinterlacer Parameters 17.3. Deinterlacer Interfaces 17.4. Deinterlacer Registers 17.5. Deinterlacer IP Software API
17.1. About the Deinterlacer IP x
17.1.1. Deinterlacer Performance and Resources
18. FIR Filter Intel® FPGA IP x
18.1. About the FIR Filter 18.2. FIR Filter Parameters 18.3. FIR Filter IP Operation 18.4. FIR Filter Interfaces 18.5. FIR Filter Registers 18.6. FIR Filter IP Software API
18.3. FIR Filter IP Operation x
18.3.1. FIR Filter Processing 18.3.2. FIR Filter Precision 18.3.3. FIR Coefficient Specification 18.3.4. FIR Filter Symmetry 18.3.5. Result to Output Data Type Conversion
18.3.4. FIR Filter Symmetry x
18.3.4.1. No Symmetry 18.3.4.2. Horizontal Symmetry 18.3.4.3. Vertical Symmetry 18.3.4.4. Horizontal and Vertical Symmetry 18.3.4.5. Diagonal Symmetry
19. Frame Cleaner Intel® FPGA IP x
19.1. About the Frame Cleaner IP 19.2. Frame Cleaner IP Parameters 19.3. Frame Cleaner IP Functional Description 19.4. Frame Cleaner IP Interfaces 19.5. Frame Cleaner IP Registers 19.6. Frame Cleaner IP Software API
19.1. About the Frame Cleaner IP x
19.1.1. Frame Cleaner IP Performance and Resources
20. Full-Raster to Clocked Video Converter Intel® FPGA IP x
20.1. About the Full-Raster to Clocked Video Converter 20.2. Full Raster to Clocked Video Converter Parameters 20.3. Full-Raster to Clocked Video Converter Block Description 20.4. Full-Raster to Clocked Video Converter Registers
20.1. About the Full-Raster to Clocked Video Converter x
20.1.1. Full-Raster to Clocked Video Converter Features 20.1.2. Full-Raster to Clocked Video Converter Performance and Resource Utilization
20.3. Full-Raster to Clocked Video Converter Block Description x
20.3.1. Full Raster to Clocked Video Converter Interfaces
21. Full-Raster to Streaming Converter Intel® FPGA IP x
21.1. About the Full-Raster to Streaming Converter IP 21.2. Full-Raster to Streaming Converter Parameters 21.3. Full-Raster to Streaming Converter Block Description
21.1. About the Full-Raster to Streaming Converter IP x
21.1.1. Full-Raster to Streaming Converter Features 21.1.2. Full-Raster to Streaming Converter Performance and Resources
21.3. Full-Raster to Streaming Converter Block Description x
21.3.1. Full-Raster to Streaming Converter Interfaces
22. Generic Crosspoint Intel® FPGA IP x
22.1. About the Generic Crosspoint IP 22.2. Generic Crosspoint IP Parameters 22.3. Generic Crosspoint IP Interfaces 22.4. Generic Crosspoint IP Registers 22.5. Generic Crosspoint IP Software API
22.1. About the Generic Crosspoint IP x
22.1.1. Generic Crosspoint IP Features 22.1.2. Generic Crosspoint Performance and Resources
23. Genlock Signal Router Intel® FPGA IP x
23.1. About the Genlock Signal Router IP 23.2. Genlock Signal Router IP Parameters 23.3. Genlock Signal Router IP Interfaces 23.4. Genlock Signal Router IP Registers 23.5. Genlock Signal Router IP Software API
23.1. About the Genlock Signal Router IP x
23.1.1. Genlock Signal Router IP Features 23.1.2. Genlock Signal Router IP Performance and Resources
24. Guard Bands Intel® FPGA IP x
24.1. About the Guard Bands IP 24.2. Guard Bands IP Parameters 24.3. Guard Bands IP Interfaces 24.4. Guard Bands IP Registers 24.5. Guard Bands IP Software API
24.1. About the Guard Bands IP x
24.1.1. Guard Bands IP Performance and Resources
25. Interlacer Intel® FPGA IP x
25.1. About the Interlacer IP 25.2. Interlacer IP Parameters 25.3. Interlacer IP Functional Description 25.4. Interlacer IP Registers 25.5. Interlacer IP Software API
25.1. About the Interlacer IP x
25.1.1. Interlacer IP Performance and Resources
25.3. Interlacer IP Functional Description x
25.3.1. Interlacer IP Interfaces
26. Mixer Intel® FPGA IP x
26.1. About the Mixer IP 26.2. Mixer IP Parameters 26.3. Mixer IP Functional Description 26.4. Mixer IP Registers 26.5. Mixer IP Software API
26.1. About the Mixer IP x
26.1.1. Mixer IP Performance and Resources
26.3. Mixer IP Functional Description x
26.3.1. Mixer IP Interfaces
27. Pixels in Parallel Converter Intel® FPGA IP x
27.1. About the Pixels in Parallel Converter IP 27.2. Pixels in Parallel IP Converter Parameters 27.3. Pixels in Parallel Converter Interfaces 27.4. Pixels in Parallel Converter Registers 27.5. Pixels in Parallel Converter IP Software API
27.1. About the Pixels in Parallel Converter IP x
27.1.1. Pixels in Parallel IP Converter Performance and Resources
28. Scaler Intel® FPGA IP x
28.1. About the Scaler 28.2. Scaler IP Parameters 28.3. Scaler IP Functional Description 28.4. Scaler IP Registers 28.5. Scaler IP Software API
28.1. About the Scaler x
28.1.1. Scaler IP Performance and Resources
28.2. Scaler IP Parameters x
28.2.1. Scaler Maximum Resolution
28.3. Scaler IP Functional Description x
28.3.1. Coefficient Selection 28.3.2. Coefficient Quantization 28.3.3. Partial Frame Scaling 28.3.4. 422 and 420 Chroma Sampled Data Scaling 28.3.5. Scaler IP Interfaces
28.3.1. Coefficient Selection x
28.3.1.1. Updating Scaler IP Runtime Coefficients
29. Stream Cleaner Intel® FPGA IP x
29.1. About the Stream Cleaner IP 29.2. Stream Cleaner IP Parameters 29.3. Stream Cleaner IP Functional Description
29.1. About the Stream Cleaner IP x
29.1.1. Stream Cleaner IP Performance and Resources
29.3. Stream Cleaner IP Functional Description x
29.3.1. Stream Cleaner IP Interfaces
30. Switch Intel® FPGA IP x
30.1. About the Switch IP 30.2. Switch IP Parameters 30.3. Switch IP Functional Description 30.4. Switch IP Registers 30.5. Switch IP Software API
30.1. About the Switch IP x
30.1.1. Switch IP Performance and Resources
30.3. Switch IP Functional Description x
30.3.1. Switch IP Latency 30.3.2. Switch IP Interfaces
31. Tone Mapping Operator Intel® FPGA IP x
31.1. About the Tone Mapping Operator IP 31.2. TMO IP Parameters 31.3. TMO IP Block Description 31.4. TMO IP Registers 31.5. TMO IP Software API
31.1. About the Tone Mapping Operator IP x
31.1.1. TMO IP Features 31.1.2. TMO IP Performance and Resource Utilization
31.3. TMO IP Block Description x
31.3.1. TMO IP Interfaces 31.3.2. TMO IP Latency
32. Test Pattern Generator Intel® FPGA IP x
32.1. About the Test Pattern Generator IP 32.2. Test Pattern Generator IP Parameters 32.3. Test Pattern Generator IP Functional Description 32.4. Test Pattern Generator IP Registers 32.5. Test Pattern Generator IP Software API
32.1. About the Test Pattern Generator IP x
32.1.1. Test Pattern Generator IP Performance and Resources
32.3. Test Pattern Generator IP Functional Description x
32.3.1. Test Pattern Generator IP Interfaces
33. Video Frame Buffer Intel® FPGA IP x
33.1. About the Video Frame Buffer IP 33.2. Video Frame Buffer IP Parameters 33.3. Video Frame Buffer IP Functional Description 33.4. Video Frame Buffer IP Registers 33.5. Video Frame Buffer IP Software API
33.1. About the Video Frame Buffer IP x
33.1.1. Video Frame Buffer Performance and Resources
33.3. Video Frame Buffer IP Functional Description x
33.3.1. Video Frame Buffer IP Interfaces
34. Video Streaming FIFO Intel® FPGA IP x
34.1. About the Video Streaming FIFO IP 34.2. Video Streaming FIFO IP Parameters 34.3. Video Streaming FIFO IP Interfaces
34.1. About the Video Streaming FIFO IP x
34.1.1. Video Streaming FIFO IP Performance and Resources
35. Video Timing Generator Intel® FPGA IP x
35.1. About the Video Timing Generator IP 35.2. Video Timing Generator IP Parameters 35.3. Video Timing Generator IP Functional Description 35.4. Video Timing Generator IP Interfaces 35.5. Video Timing Generator IP Registers 35.6. Video Timing Generator IP Software API
35.1. About the Video Timing Generator IP x
35.1.1. Video Timing Generator IP Features 35.1.2. Video Timing Generator IP Performance and Resources
36. Warp Intel® FPGA IP x
36.1. About the Warp IP 36.2. Warp IP Parameters 36.3. Warp IP Block Description 36.4. Warp IP Registers 36.5. Warp IP Software API
36.1. About the Warp IP x
36.1.1. Warp IP Features 36.1.2. Warp IP Performance and Resource Utilization
36.3. Warp IP Block Description x
36.3.1. Block Cache Tool 36.3.2. Warp IP Interfaces 36.3.3. Warp IP Latency 36.3.4. External Memory for Warp IP Memory Space Allocation in External Memory Bandwidth to External Memory Total Warp IP Memory Traffic Peak Memory Bandwidth Approximation for Video Streams Peak Memory Bandwidth Approximation for Coefficient Streams Peak Memory Bandwidth Approximation for Cache Loads Memory Interface Bandwidth Requirements Example system sharing access to memory Multiple Warp IPs sharing access to memory
36.5. Warp IP Software API x
36.5.1. Using Warp IP Software 36.5.2. Warp IP Software Code Examples
37. Design Security x
37.1. Memory Subsystems 37.2. Considering Design Security
1. About the Video and Vision Processing Suite
2. Getting Started with the Video and Vision Processing IPs
3. Video and Vision Processing IPs Functional Description
4. Video and Vision Processing IP Interfaces
5. Video and Vision Processing IP Registers
6. Video and Vision Processing IPs Software Programming Model
7. Protocol Converter Intel® FPGA IP
8. 3D LUT Intel® FPGA IP
9. AXI-Stream Broadcaster Intel® FPGA IP
10. Chroma Key Intel® FPGA IP
11. Chroma Resampler Intel® FPGA IP
12. Clipper Intel® FPGA IP
13. Clocked Video Input Intel® FPGA IP
14. Clocked Video to Full-Raster Converter Intel® FPGA IP
15. Clocked Video Output Intel® FPGA IP
16. Color Space Converter Intel® FPGA IP
17. Deinterlacer Intel® FPGA IP
18. FIR Filter Intel® FPGA IP
19. Frame Cleaner Intel® FPGA IP
20. Full-Raster to Clocked Video Converter Intel® FPGA IP
21. Full-Raster to Streaming Converter Intel® FPGA IP
22. Generic Crosspoint Intel® FPGA IP
23. Genlock Signal Router Intel® FPGA IP
24. Guard Bands Intel® FPGA IP
25. Interlacer Intel® FPGA IP
26. Mixer Intel® FPGA IP
27. Pixels in Parallel Converter Intel® FPGA IP
28. Scaler Intel® FPGA IP
29. Stream Cleaner Intel® FPGA IP
30. Switch Intel® FPGA IP
31. Tone Mapping Operator Intel® FPGA IP
32. Test Pattern Generator Intel® FPGA IP
33. Video Frame Buffer Intel® FPGA IP
34. Video Streaming FIFO Intel® FPGA IP
35. Video Timing Generator Intel® FPGA IP
36. Warp Intel® FPGA IP
37. Design Security
38. Document Revision History for Video and Vision Processing Suite User Guide

36.3.4. External Memory for Warp IP

The IP requires access to two separate areas of external memory: one for its input and output video buffers and one for its coefficient tables. The processor system running the Warp Software API must be able to access the coefficient tables but does not need access to the buffer area.

Memory Space Allocation in External Memory

Table 664.   Warp IP Video Buffer Memory Region - maximum usageThe table defines how much space is required in external memory by the Warp IP for the video buffer region when you turn off Use easy warp and turn off Use single memory bounce. This space depends on the size of the images to be processed in a system. It is defined by the Memory frame buffer size parameter. Six buffers require space in total: four input and two output.
Buffer Space Configuration Region Size (MB) Memory Region Required Alignment (multiples of)
SD buffer size (1024x1024) 24 0x0180_0000 0x0200_0000
HD buffer size (2048x2048) 96 0x0600_0000 0x0800_0000
UHD buffer size (4096x4096) 384 0x1800_0000 0x2000_0000
Table 665.   Warp IP Video Buffer Memory Region - reduced usage

The table defines how much space is required in external memory by the Warp IP for the video buffer region when you turn on Use easy warp or turn on Use single memory bounce. This space depends on the size of the images to be processed in a system. It is defined by the Memory frame buffer size parameter. Four buffers require space in total.

Buffer Space Configuration Region Size (MB) Memory Region Required Alignment (multiples of)
SD buffer size (1024x1024) 16 0x0100_0000 0x0100_0000
HD buffer size (2048x2048) 64 0x0400_0000 0x0400_0000
UHD buffer size (4096x4096) 256 0x1000_0000 0x1000_0000

The IP passes the base address of the memory region allocated to the frame buffers to the software API using the ram_addr element in the structure.

The memory region that the coefficient tables require is related to the number of warp engines, the resolution of the images, and the type of warp. The IP only requires this memory region when you turn off Use easy warp.

Table 666.  Warp IP Coefficient Tables Memory RegionThe table shows the maximum size of the coefficient table memory region, per engine.
Warp Engines Region Size (MB) Memory Region Required Alignment (multiples of)
1 16 0x0100_0000 0x0100_0000
2 32 0x0200_0000 0x0200_0000

Bandwidth to External Memory

The performance of the interface from the Warp IP to the external memory is important for the correct operation of a system using the Warp IP.

The Warp IP generates a substantial amount of memory traffic. It has up to four video streams passing to and from external memory. In addition, each engine has three read streams to access the coefficient tables. All these streams combine to make Warp IP memory accesses complex. The streams affect how much efficiency you can obtain when accessing memory such as DDR4.

The Warp IP memory controller mitigates potential inefficiencies caused by these complex access patterns. It uses burst lengths of 8 beats for all its read and write accesses to improve the burst performance of DDR4 memory. It also attempts to cluster individual read and write bursts together to eliminate some of the issues with read and write turnaround dead time at the DDR4 interface.

These memory access patterns depend on the image transform that you apply. Some complex image transforms may reduce memory traffic because of the skip region functionality. When Use single memory bounce is off, one of the worst transforms for generated memory traffic is a unity warp that gives a 1:1 mapping between input and output pixels. When Use single memory bounce is on, memory traffic is proportional to the amount of compression in the vertical direction of the transform. The higher the amount of compression in the transform vertically, the higher the memory bandwidth.

The operation of the Warp IP is easier to predict when it is the only user of the DDR4 memory in a system. Ensure the Warp IP is the only high bandwidth user of the DDR4 memory in a system. When other high bandwidth accesses are made to the memory at the same time as the Warp IP, ensure that any interactions don’t adversely affect performance.

Total Warp IP Memory Traffic

Three different configurations of the warp IP affect the way it connects to the external memory and hence affect the total memory traffic:

  • When Use easy warp is on
  • Use easy warp is off and Use single memory bounce is either on or off.
Figure 98. External Memory Data Streams

The figure shows a schematic view of all the possible data streams the IP uses. Depending on the settings of Use easy warp and Use single memory bounce, the IP does not require all of these streams.

Table 667.  Active Data Streams for Different Configurations

The table shows which external memory data streams are active for the different configuration settings.

Data Stream Use easy warp on Use single memory bounce on Use single memory bounce off
Input video Active Active Active
Cache loads Active Active
Warped image Active
Coefficient reads Active Active
Output video Active Active

The bandwidth for each data stream is:

  • A video stream (input video, warped image and output video)
  • A coefficient stream (coefficient reads)
  • Cache loads (a scaled version of a video stream).

Peak Memory Bandwidth Approximation for Video Streams

The equation calculates the peak bandwidth (in bits per second) for the video streams passing through the warp (where number_of_lines includes blanking). Each pixel of data is transferred to or from external memory as a 32bit word.

Peak bandwidth = 32 * pixels_per_line * number_of_lines * frame_rate

Table 668.  Video Stream Memory Bandwidth Examples

The table shows the peak memory bandwidth per video stream for various resolutions and frame rates.

Resolution Frame Rate (fps) Peak Data Rate (Gbps)
3840x2160 (2250 lines) 60 16.6
3840x2160 (2250 lines) 30 8.3
1920x1080 (1125 lines) 60 4.2

Peak Memory Bandwidth Approximation for Coefficient Streams

You can approximate the memory bandwidth required by the coefficient streams as 9% of a video stream.

Table 669.  Coefficient Stream Memory Bandwidth Examples

The table shows the peak memory bandwidth per stream for various resolutions and frame rates.

Resolution Frame Rate (fps) Peak Data Rate (Gbps)
3840x2160 60 1.5
3840x2160 30 0.75
1920x1080 60 0.4

Peak Memory Bandwidth Approximation for Cache Loads

The memory bandwidth required by the IP for the cache loads is closely linked to the warp transform that the IP applies. The memory bandwidth is proportional to the bandwidth required by a standard video stream. It is also affected by Use single memory bounce.

When Use single memory bounce is off, the worst-case bandwidth required for cache loads is experienced for a 1:1 or unity warp and is approximately 25% higher than a normal video stream. The unity warp gives an upper bound for the bandwidth. Other transforms give lower.

When Use single memory bounce is on, the amount of vertical compression in the transform that the IP performs affects the bandwidth required for cache loads. A 1:1 or unity warp has a 1:1 vertical compression. The resultant cache load bandwidth is equivalent to the bandwidth for a standard video stream. In contrast, a 53 degree vertical keystone warp has a vertical compression approaching 2:1 in some regions. The maximum cache load bandwidth for this warp is two times the standard video stream bandwidth. The 2:1 ratio provides an upper bound for the cache load bandwidth for recommended operation.

The recommended 2:1 compression limit comes from the limitations of the low pass filtering that takes place in the bicubic pixel interpolation process when generating output pixels. However, you can generate transforms that have a compression ratio of greater than 2:1, which can potentially affect the single memory bounce memory bandwidth and reduce the final picture quality.

Memory Interface Bandwidth Requirements

Table 670.  Memory Interface Bandwidth Requirements – Easy WarpThe table shows the burst data rate scaling across resolutions and frame rates when Use easy warp is set to on. When Use easy warp is on, you can approximate the memory bandwidth using two video streams.
Resolution Frame Rate (fps) Maximum Burst Data Rate (Gbps)
3840x2160 60 34
3840x2160 30 17
1920x1080 60 8.5
Table 671.  Memory Interface Bandwidth Requirements – Single Memory BounceThe table shows the burst data rate scaling across resolutions and frame rates when Use single memory bounce is on. Tthe cache load data rate assumes a 2:1 vertical compression factor, which gives worst-case figures. When Use single memory bounce is on, you can approximate the memory bandwidth using one video stream, a coefficient stream, and the cache load stream (with an upper bound of twice the bandwidth of a standard video stream).
Resolution Frame Rate (fps) Maximum Burst Data Rate (Gbps)
3840x2160 60 51.3
3840x2160 30 25.7
1920x1080 60 8.5
Table 672.  Memory Interface Bandwidth Requirements - Double Memory Bounce The table shows the burst data rate scaling across resolutions and frame rates when Use single memory bounce is off. The cache load data rate assumes a 1:1 warp transform, which gives the worst-case figures. You can approximate the memory bandwidth using three video streams, a coefficient stream, and the cache load stream (with a 25% overhead above the bandwidth of a standard video stream).
Resolution Frame Rate (fps) Maximum Burst Data Rate (Gbps)
3840x2160 60 72
3840x2160 30 36
1920x1080 60 18

Intel references these burst data rates to the memory interface of the IP. The total data rates available are affected by other factors outside of the IP such as the performance of the interconnect fabric and the efficiency of the memory controller.

Example system sharing access to memory

In this example system the Warp IP shares the DDR4 interface with a frame buffer in a system that processes UHD frames at 60 fps. The system runs on an Intel Arria 10 GX Development Kit with the DDR4 EMIF running a 2,133 MHz interface to a DDR4 memory.

Figure 99. Warp and Video Frame Buffer Platform DesignerThe figure shows the Platform Designer connectivity where the Frame Buffer II component is sharing access to the DDR4 EMIF with the Warp IP. The Frame Buffer is part of the same video processing pipeline as the Warp IP.

For this system to work:

  • Configure Frame Buffer to use bursts of 32 beats for read and write.
  • Configure Frame Buffer to use read and write FIFO depths of 128
  • Set the arbitration weighting at the front end of the DDR4 EMIF to 16:1 in favor of the Warp IP (versus the Frame Buffer’s read and write interfaces connected through the mm_bridge_vfb component).
  • Set the Maximum pending read transactions parameter in the pipelined transfers section of the Avalon memory-mapped agent port to be at 8.
  • Set Limit interconnect pipeline stages to for the domain at the front end of the DDR4 EMIF to 4.
Figure 100. Video Frame Buffer Parameterization
Figure 101. Maximum Pending Read Transactions
Figure 102. Parameterizing interconnect pipeline stages

Multiple Warp IPs sharing access to memory

Figure 103.  Multiple Warp IPs sharing access to memory The figure shows an example with two Warp IPs that share a DDR4 interface. To match the burst access patterns of the Warp IP, set the arbitration values at the combining interface to 8.
Level Two Title