Next-Generation VME

Deploying VITA 46 in Real-World Applications

The embedded market will soon witness the debut of the first boards and systems based on the emerging VITA 46 architecture, an industry milestone that promises to deliver the next generation of embedded computing board performance.


  • Page 1 of 1
    Bookmark and Share

Designed to address the performance and environmental limits now confronting VME64x, VITA 46 provides an open standard for hardware form-factor and electrical connectivity uniquely suited for high-bandwidth distributed processor systems. It provides several significant advances over traditional VME including its high-speed connector interface and, through the complementary VITA 48 standard, support for 2-Level Maintenance for in-the-field repair and replacement. Three particular application case examples highlight the most likely target applications for early use of VITA 46: these include radar systems, mission computer systems and small form-factor graphics display systems. Each of these applications highlights specific technological advantages of VITA 46 over the existing VME64x or CompactPCI systems that it will replace or enhance in heterogeneous systems. Table 1 shows a comparison between VME64x and VITA 46.

Radar Processor Systems

Radar systems comprise a classic “hard” problem for embedded multi-computing: they typically involve multiple channels of high-speed streaming input data. Significant data errors can occur if the streaming data is interrupted to allow processing to catch up. In radar systems, performance must be as close to real time as possible. As latency in the system increases, so does the risk of data loss. Because human operators use the processed data from these systems for targeting or navigation, the resulting data can be life-critical, making it all the more important to minimize latency as much as possible.

Today’s VME64x-based radar processing systems typically receive their preprocessed sensor input data through high-speed A/D boards or front panel I/O connectors such as FPDP. The initial stage of signal processing was formerly handled by ASICs, but it is now more commonly handled by an FPGA-based board on which a customer adds their own proprietary algorithms to the FPGA bit stream. The data is then pushed to a microprocessor-based multi-computer board such as one populated by multiple PowerPCs.

Another factor that makes radar processing in parallel systems especially complex is the need for “all-to-all communication” at certain stages of processing. During processing, radar data must undergo a “corner turn,” or a distributed matrix transpose. In a distributed corner turn every processor in the system has a piece of data that every other processor needs for the next stage of processing. In today’s VMEbus-based radar systems every processor in the matrix must wait its turn to get a chance to move its data across the bus. Not only does this stall the processing of the current block of data, but it also stalls the incoming data.

Switched fabrics directly address this problem by parallelizing the all-to-all data movement, thus minimizing both the processing stalls and the interruption to the input data streams. Switched fabrics were first introduced into the VME world in the mid-1990s and have grown significantly larger and faster in the intervening 10 years. StarFabric is one serial switched fabric currently used to connect embedded multicomputing products using existing VME64x backplanes. However, physical limits in the legacy VME64x connectors prevent further growth.

Prior to the development of VITA 46, radar systems had begun to confront fundamental performance limits. The two most serious limits being the amount of data that the VME signaling pins could sustain, and the amount of power that could be dissipated per board slot. These are both problems VITA 46 was designed to address. While the number of operations performed on incoming radar data has grown to a certain extent, the amount of incoming raw data has grown tremendously.

Radar data pipes have grown much bigger because the higher the frequency at which data is collected the better the resulting imagery. In addition, the increased availability of large quantities of data is driving even more demanding radar system applications such as moving target identification (MTI), Multi-Hypothesis Tracking (MHT) and Identify Friend-or-Foe (IFF). What’s more, there is greater use and deployment of radar sensors. The increased use of UAVs, for example, has increased the amount of data to be processed, while simultaneously, because of stringent constraints on payload size and weight, driving demand for smaller and smaller packages.

As the amount of data has increased, so has the number of processors needed to process the data. This increases the amount of power consumed and the amount of heat generated by a radar system. Unfortunately, the demand for processing power threatens to exceed the ability to cool the components in these systems. This has led some leading vendors to attempt to address the urgent need for higher processor densities with proprietary standards.

However, the industry clearly desires an open standard approach. Smaller radar systems that don’t feature such significant amounts of I/O may continue to follow the VME64x path—and for these systems VME or serial switched fabrics on VITA 41 may remain attractive. However, systems that require very large or multiple input data pipes and that use lots of interprocessor communications are expected to migrate to VITA 46.

In the final stage of processing, a radar system sends its data out for operator exploitation. The operator then uses the data, for example, to command a sensor to point in a certain direction or to zoom in on a target of interest. In many cases the operator terminal will be an existing data exploitation terminal with proprietary protocols or interfaces built with legacy SBCs or with custom I/O. With VITA 64, system designers get the best of both worlds, because the new standard provides support for legacy VME64x electrical signals and can utilize a hybrid backplane to house both VITA 64 and VME64x cards. This enables system designers to take advantage of the performance of their distributed fabric of choice while protecting their existing hardware investment.

Another advantage of VITA 46 for radar applications is the large number of I/O pins it provides the user in comparison to VME64x. The availability of numerous I/O pins enables system designers to add Gigabit Ethernet off the backplane on VITA 46 and to support multiple ports of rich fabric and the legacy VME electrical signals, as well as provide many additional pins for user-defined general-purpose signals. The abundance of I/O helps to ensure that data flows will keep up to speed, so that no radar image or data will be lost, and no target goes unseen. One more advantage is that control data can be easily split from processing data and delivered throughout the system network via Gigabit Ethernet. This helps eliminate any chance of the high-priority processing data being delayed by lower-priority control data (Figure 1).

Because airborne radar systems commonly have size and weight constraints, it’s expected that some of the early adopters of VITA 46 technology will range from tactical fighters and UAVs to large radar platforms such as JSTARS, AWACS and E2C.

Mission Computers

VITA 46 will also play an important role in the improvement of mission computers. Mission computers provide the intelligent processing needed to handle high densities of standard I/O such as 1553, ARINC, SCSI and RS-422, as well as network fabrics such as Ethernet or Gigabit Ethernet. The mission computer is used to control the I/O or convert the incoming data into commands for fire command computers. It also integrates, consolidates and interprets the data for the user. In addition to handling legacy I/O types, including discrete I/O and A/D and D/A, mission computers are also frequently tasked to control high-speed serial interconnects for data storage and fabric interconnects for a redundant mission computer.

The more data delivered to a mission computer, the better the quality of data available to the system, which results in better and more information that can be analyzed and displayed graphically. As with radar processing systems, the mission computer is continually being tasked to handle larger amount of incoming data. This is driven in large part by the proliferation of sensors deployed on a given platform. Unlike the radar processor system though, the mission computer usually has either a single or a small number of CPUs.

However, mission computers are also taking on larger workloads these days thanks to higher resolution cameras, more data sources and high-speed communications. In today’s networked battlefield, the mission computer might need to link its database up to the main computer at the central command and control site. In addition to the burden of command and control and security, networked communication also adds the processing burden of data encryption. All of these trends increase the need for faster data rates. As a result, there is a burgeoning demand for higher levels of intelligence, faster I/O and external networking on mission computers.

Another trend driving the need for faster I/O on mission computers is the move away from dedicated platforms, where each displays data from a single sensor or sensor type. The trend today is toward the use of integrated sensors that incorporate data from multiple sensors on a single console resulting in sensor fusion for the war fighter. Increased use of processor-hungry formats such as FLIR and InfraRed are also putting pressure on today’s mission computers. At the same time, software is becoming more modular and complex.

As a result, vehicles such as battle tanks and UAVs, which might formerly have had 1553 sensor data coming in, and 1553 and more RS-422 data out, are being enhanced with 1394B, Gigabit Ethernet and FPDP to handle the higher speed data of today’s applications. In the past, higher compute requirements had been typically addressed through the use of proprietary secondary buses like RaceWay, SkyChannel, Myrinet and StarFabric, which provide no standard way of connecting multi-vendor components together. VITA 46, in comparison, delivers a standard architecture that eliminates the need for secondary data buses while preserving the user’s investment in VME64x hardware and software (Figure 2).

Small Form-Factor Smart Displays

The 3U variant of VITA 46 will also find a waiting niche. Today, space and weight-restricted video capture and graphical display systems designed with high-bandwidth interconnects for digital video distribution and image manipulation are frequently built with smaller boards such as 3U CompactPCI cards. These small form-factor intelligent display systems are finding their way onto vehicles like tanks and helicopters where space and weight are a big concern. With helicopters, for example, the combined weight of the onboard systems translates into the distance that can be covered with a given amount of fuel, directly impacting which missions can be accomplished.

There is a growing requirement on these platforms to migrate toward the use of higher resolution flat panel displays for mapping, position location and other real-time data display. The move is from today’s standard displays (typically up to 1280 x 1024 dpi) to a larger format (typically from 1600 x 1200 and above, including HDTV resolutions) while also enabling system designers to more effectively process and display sensor data by using layers and real-time data updates. This is being hampered by the limits of the connector chain found on traditional CompactPCI systems. The problem is that the greater quantity of data transmitted to the higher resolution displays, and consequently, the higher frequencies and higher signal integrity requirements, cannot always be met by the electrical performance limits of the CompactPCI and PMC connectors.

Customized solutions that do not use COTS can prove to be costly to manufacture and maintain over the lifecycle of the product. The MultiGig connector defined by VITA 46 addresses these electrical limitations. The resulting ability to maintain better signal integrity can also translate to the benefit of driving greater line lengths between the system and the flat panel display. This permits hardware to be placed flexibly in the limited space available in an already dense tank or helicopter interior.

The use of switched serial fabrics also opens the door for more distributed video processing solutions by enabling the separation of the video capture and processing functions from the synthetic graphics generation and display functions. As these two functions no longer need to be so closely coupled, benefits can be realized on both ends of the chain. VITA 46 supports more complex data streams on the input side and more specialized display types on the output side. The increase in backplane data bandwidth provided by the switched fabric also simplifies the addition of video processing stages in the data path (Figure 3). As highlighted by these three application scenarios, VITA 46 already has some hungry customers looking to take advantage of the higher performance and total cost of ownership savings.

VITA 46 products are now starting to appear on the market (Figure 4) and can soon be expected to move in to meet the demands for increased throughput, connectivity and processing power being placed on today’s high-end systems.

Curtiss-Wright Controls
Embedded Computing
Leesburg, VA.
(703) 779-7800.