While most of the approaches are new to the market, their performance differs greatly.
A number of wireless digital-video technologies are beginning to appear on the market. It's interesting that, at this time last year, no satisfactory architectures were available. Because of the high bandwidth required, video has been difficult to support over wireless communications. With the emergence of ultrawideband (UWB), users of digital video and other bandwidth-intensive applications can now enjoy the benefits of mobility without a fistful of cables. Several architectures based on UWB technology have emerged that use different approaches to wireless digital video. Each takes unique approaches that result in different performance, size, and cost. Some integrate directly with existing functions available on the wired system, while others may require additional components, such as CPUs, encoders, and decoders, to complete the system.
In evaluating the various wireless architectures for digital video, you should carefully analyze the architecture you choose to make sure it truly meets your system's requirements at the lowest cost and best performance. The final goal is to enable the same user experience as a wired connection.
Before you start analyzing the options, you'll need to define your digital-video application and know what devices will be sending (hosting) and accepting (receiving) wireless video. For instance, you want to add wireless capability to a system that consists of a handheld portable video source and a monitor or between a home entertainment system and a TV. For the purposes of this article, I'll focus on a personal computer's wireless docking application that uses UWB. Within the PC space, I'll compare three wireless architectures that transmit digital video: Video over wireless USB; Video over UWB with light compression; and Video over Internet Protocol. All three options are viable but the first two are more applicable to PCs and PC peripherals. Wireless Video over IP is a more complex and costly solution for PC graphics. We'll take a look at why that is.
The wired architecture
Let's first take a look at the wired PC-to-display system we want to convert, as shown in Figure 1. In a PC, the major I/O peripherals attach to the CPU via the north-bridge and south-bridge ICs. The north bridge provides an interface between the CPU and high-bandwidth functions such as RAM and a graphics processor unit (GPU). (In some cases, the GPU may be integrated into the north bridge.) The north bridge interfaces to a south bridge, which typically implements I/O interfaces such as Ethernet local area network (LAN), parallel or serial hard-drive interfaces, USB, serial or parallel ports, digital audio, and PCI Express expansion-bus card slots for Wireless LAN. Video is rendered by the GPU and drives a monitor over VGA, digital visual interface, or a DisplayPort video interface.
View the full-size image
The PC architecture is optimized so that compute-intensive tasks performed by the CPU have low latency and high-speed access to memory and graphics that are attached through the north bridge. While the CPU is a powerful general-purpose processor, it's not as effective for graphics computations. For video graphics, a special-purpose processor, the GPU, is more suited for graphics rendering. GPUs include special functions to autonomously create graphics such as 2D and 3D primitives, shaders, and block moving and copying. Modern applications, whether business applications, computer-aided design tools, multimedia programs, or games, all require powerful GPUs to render graphics. For wireless video, it's imperative to use the capabilities of the GPU just as wired displays do.
Comparing wireless options
When choosing a wireless digital-video architecture, it's important that its design closely matches the architecture of today's wired systems. Adding more components has an impact on cost, performance, and size. The most efficient designs will only require the added silicon associated with the UWB technology, including integrated support for wireless digital video on the host and device sides. Recent integrated product introductions have been designed specifically for PC wireless docking. These solutions support not only wireless video but also wireless audio and USB peripherals.
In the Video over UWB configuration shown in Figure 2, instead of transmitting video, audio, and data over separate VGA, speaker, and USB physical cables, the system transmits the information wirelessly on the host side to the device side, bypassing the interface cabled chips. Note that the GPU and south-bridge chips function normally as if they were wired to a remote display or dock. This configuration reduces the system cost and doesn't burden other portions of the system with additional hardware or software. The WiDV boxes are Wireless Digital Video interface transceivers containing video compression/decompression and UWB functions to serve as wireless equivalents of the wired interfaces (marked I/F).
View the full-size image
In the Video over wireless USB approach, the video, audio, and USB information is similarly passed through the UWB chip on the host to the UWB chip on the device, as shown on Figure 3. However, because video must be sent using USB protocol, special software is required to capture and send video data over the USB bus. This configuration software has several negative effects. First, the system can't use the video rendered by the integrated GPU. Second, the CPU is burdened with special software to send graphics data to the remote decoder/GPU. The result is both slower video and system performance because fewer CPU MIPS are available for running normal applications and I/O. Third, system cost is not optimal because the integrated GPU isn't used. Finally, the USB protocol overhead and latency introduced by sending video over USB means that significantly less bandwidth is available for remote graphics, which further limits performance.
View the full-size image
Note that, since the PC's high-performance GPU is not used in this topology, 3D graphics will not render, effectively making the system unusable for gaming and other applications. A unique additional decoder/GPU is required on the device side to display graphics. This IC can be thought of as a remote GPU that performs the functions of the idle and unused integrated host-side GPU. Because additional ICs are needed, extra cost, complexity, and memory are also added to support this approach.
In the Video over IP approach shown in Figure 4, an additional encoder chip on the host side interfaces to the GPU to compress and encode video before it's input into the UWB transmitter. A matching decoder chip is needed on the device side, among other requirements. Additional CPU and memory chips are also required on the device side to implement an IP stack and perform housekeeping for the display decoder, thereby increasing the complexity and the number of ICs on the device side. For the display, Video over IP is unnatural compared with a traditional video display architecture. The Video over IP approach is significantly more complex, power hungry, and costly compared with either a wired or Video over UWB approach.
View the full-size image
Counting components
Considering the number of additional ICs required for some of these architectures, developing a system that optimizes the number of components is a complex problem to solve. Video over UWB with light-compression algorithms is one technology that's reduced the number of components, as shown in Table 1.
View the full-size image
When so many additional components are required, primary concerns include component size and cost. It's easy to see with the previous examples that the impact on those areas can be significant. Analyses of the bills of material have shown a greater than 20% increase in total system cost with the Video over wireless USB and Video over IP approaches versus the Video over UWB option.
Benchmarks
In addition to the architectural differences, a thorough benchmarking study using digital-video benchmarking software reveals differences such as CPU load, latency, performance, and bandwidth efficiency among the various approaches. CPU load is an important consideration, especially if multiple applications are running simultaneously or if the user is running CPU-intensive applications such as a media player.
The performance differences in this area are quite telling. Comparing the three approaches, the Video over UWB with light video compression can result in zero impact on the CPU's performance compared with some CPU loading for IP-stack processing for the video-over-IP approach. Video over wireless USB easily saturates the CPU at 100% load. You can see these attributes in Table 2.
View the full-size image
Generally with software-based approaches, when the CPU load increases, the frame rate decreases during video playback. In the Video over wireless USB approach, it's almost impossible to run full-screen video unless it's at a reduced frame rate. Software-video approaches also result in higher latency and nondeterministic graphics because the CPU must share cycles with other applications. Graphics that may work in some cases may have different latency or frame rates in other cases due to other applications simultaneously running on the CPU.
You must thoroughly understand video bandwidth efficiency or the efficiency of the protocol (for example, USB or IP). The video application throughput that's achievable over the USB protocol, for example, is significantly reduced because you not only have the overhead associated with the USB protocol, but you also have the overhead associated with UWB wireless communications as well. On the other hand, the light compression algorithms available in UWB-based products have been built from the ground up to optimize the available bandwidth.
For quantitative results, benchmarking programs can test and stress the system's performance. We used the Passmark Version 6 2D Video Benchmark product (www.passmark.com) to run the 2D graphics performance analysis shown in Table 2. Also, a screenshot of the test is shown in Figure 5.
View the full-size image
In every case, the Video over UWB approach out-performed the Video over wireless USB software-video approach. For "2D rectangles" and "fonts and text" tests, in particular, this approach outperformed Video over wireless USB by 117% and 103%, respectively. In every case, the Video over UWB approach outperformed the other solutions by 40% to 117%.
In addition to 2D performance tests, 3D tests were also run. Each 3D test for the Video over USB software-video failed, making it unusable for 3D graphics applications. For the Video over UWB approach, however, performance was the same as wired because the internal GPU performs the graphics rendering. Video over IP would have similar 2D and 3D rendering results as Video over UWB but latency would be greater.
Wayne Daniel is the director of technical marketing at WiQuest Communications Inc. where he's responsible for UWB IC, software, and reference-design roadmaps and product requirements. He can be reached at wayne.daniel@wiquest.com.
