feature article
Subscribe Now

FPGAs Control Graphics and Video in Embedded Systems

As I sit at my desk, there are six LCD displays within one meter of my chair: cell phone, desk phone, thermometer, calculator, laptop and external monitor.  Not all devices with LCD displays need much intelligence to display information, such as my desk phone, but the number of systems that display complex graphics and video continues to increase.

Declining display prices and rising user expectations for additional product features and functionality fuel this growth.  Companies in the transportation, automotive, information, automation, medical, industrial and consumer markets use displays in a vast array of products.

The personal computer and consumer markets are the largest users of display systems.  However, the embedded market, consisting of all other electronic market segments that use display systems, has several specific requirements not found in the PC and consumer markets.  These include long product manufacturing life, generic system bus interface and flexibility to adapt to new standards and display types.

Typical Graphics System

The block diagram shown in Figure 1 is an example of a typical graphics or video controller system.  On the left side of the diagram are some of the different input signals that can drive a graphics system.  This example shows a 7:1 LVDS or Channel Link signals, a Society of Motion Picture and Television Engineers  (SMPTE) input signal, a type of interface bus and an NTSC/PAL video decoder.

20071113_lattice_fig1.jpg

Figure 1. Typical Graphics System Architecture

Once the signals enter the system, they are processed by a general-purpose processor or, depending on the architecture, sent directly to the graphics processor.  Additionally, there is Flash memory for program storage and SDRAM for storage of page and video information.

The graphics processor may be an Application Specific Standard Processor (ASSP), a custom Application Specific Integrated Circuit (ASIC) or a Field Programmable Gate Array (FPGA) device.  Depending on the system, there may be multiple displays in the system (as shown), which requires additional logic to manage the signals to support each display.

Developers encounter several barriers when attempting to match an ASSP graphics controller into their embedded design.  These barriers include:

  1. Support for new or derivative video and imager standards in legacy systems cannot be supported in hardwired ASSP or ASIC devices.
  2. Hardwired systems also have difficulty adapting to different display types, due to varying resolutions, aspect ratios and display signal interfaces.
  3. PC and consumer products typically have a very short life cycle; in contrast, the embedded markets have very long production and support requirements that cannot tolerate changes forced by an end-of-life situation.
  4. Most ASSP devices have standard PC bus interfaces such as AGP, PCI and PCIexpress.  Unfortunately for embedded designers, many of the systems they develop do not have these bus interfaces.

While ASICs have an attractively low per piece price, they are very expensive to develop.  The mask charges alone can run in the millions of dollars and if the design is changed to support new standards, the mask charges are incurred yet again.

FPGA Graphics System

The versatile nature of FPGA devices, plus commercially available Intellectual Property (IP), allows for the integration of almost all the graphics system functions.  The video controller, RISC processor, display interfaces, bus standards and different video input standards can be included in one device. 

Figure 2 is an example of the high level of integration possible using FPGAs.  The Channel Link and SMPTE interfaces are processed in the I/O structures of the FPGA.   The RISC processor is included in the form of an IP-based, soft-core 32-bit processor core.  IP for the graphics / video core completes the design with built-in support for touch panel inputs, LCD backlight control, memory controller and multiple displays.  This design greatly reduces the number of parts in the design by integrating all the functions into the FPGA.  By using an FPGA with a built-in single-chip boot Flash, another device (boot PROM) can be eliminated from the design.

20071113_lattice_fig2.jpg

Figure 2. Integrated Graphics Solution

An embedded graphics design using an FPGA device mitigates the issues associated with ASSP and ASIC devices.  FPGAs make it easy to develop a modular design that offers the flexibility to integrate different IP blocks, depending on the cost and feature requirements of the system.  FPGAs enable design integration that typically results in a reduction of board space and parts inventory count.  The long life commitments for FPGA devices ensure they will be available for the operational life of the product.  Most FPGAs are field upgradeable (some devices even while they are operating), which allows for easy upgrades to support new standards and options.

Standard video and graphics IP for FPGAs offer tested and verified designs that are easy to integrate into a graphics solution.  Using packaged IP solutions also speeds system development, enabling engineers to concentrate their efforts on the application rather then the low-level interfaces and graphics engines.  Modular graphics IP cores allow the development and inclusion of custom graphics accelerators within the video controller.  In this way, the graphics performance can be specifically scaled and optimized for the target system.

The intelligent home thermostat shown in Figure 3 provides an example of the use of graphics in a “Smart Home” application.  The Flash-based FPGA has standard IP for the graphics controller, as well as wired and wireless interfaces for communicating with other devices in the home.  The LCD display can be used to display temperature trending information and temperature from remote indoor and outdoor thermometers, as well as video feeds from networked security cameras.

20071113_lattice_fig3.jpg

Figure 3.  Intelligent Home Thermostat

FPGAs offer the versatility to include the optimal bus and interface standards.  This allows the system architect to design with the best interfaces for the entire system, rather than having to design around a specific graphics processor interface or bus.  Designs using FPGAs allow the system designer complete control over the system interface: the entire design can be optimized to support real-time control and display systems that process video streams without any performance degradation.

In addition, FPGA manufactures support density migration within the same sized package.  This allows more logic to be added for enhanced features, or less logic capacity for reduced functionality, without affecting the PCB layout.  Density migration results in cost savings in development, production, servicing and logistics.

FPGAs Enable Flexibility For The Future

The use of FPGA devices to build video and graphics controllers is enabling the embedded market to add graphics display technology in more and more applications.  By using non-PC related video products, the embedded market can rely on having an extended product life cycle well beyond the typical 2- to 3-year period.  One concern for designers has been that the prices of FPGAs were too high to be embedded in systems.  Today, however, FPGAs are designed for low-cost with enhanced features that makes the per piece cost of FPGAs very competitive with other graphics solutions.

I am excited by the additional functionality that LCD displays add to many embedded systems.  The ability to receive additional feedback from a system and have custom interfaces tailored for the individual user is the next step in the evolution of embedded technology.

Leave a Reply

featured blogs
Aug 18, 2018
Once upon a time, the Santa Clara Valley was called the Valley of Heart'€™s Delight; the main industry was growing prunes; and there were orchards filled with apricot and cherry trees all over the place. Then in 1955, a future Nobel Prize winner named William Shockley moved...
Aug 17, 2018
Samtec’s growing portfolio of high-performance Silicon-to-Silicon'„¢ Applications Solutions answer the design challenges of routing 56 Gbps signals through a system. However, finding the ideal solution in a single-click probably is an obstacle. Samtec last updated the...
Aug 17, 2018
If you read my post Who Put the Silicon in Silicon Valley? then you know my conclusion: Let's go with Shockley. He invented the transistor, came here, hired a bunch of young PhDs, and sent them out (by accident, not design) to create the companies, that created the compa...
Aug 16, 2018
All of the little details were squared up when the check-plots came out for "final" review. Those same preliminary files were shared with the fab and assembly units and, of course, the vendors have c...
Jul 30, 2018
As discussed in part 1 of this blog post, each instance of an Achronix Speedcore eFPGA in your ASIC or SoC design must be configured after the system powers up because Speedcore eFPGAs employ nonvolatile SRAM technology to store its configuration bits. The time required to pr...