Embedded Systems Design Europe - November 2007 - (Page 29) wireless with light video compression can result in zero impact on the CPU’s performance compared with some CPU loading for IPstack processing for the video-over-IP approach. Video over wireless USB easily saturates the CPU at 100 percent load. These attributes are shown in Table 2. 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 fullscreen 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. A screenshot of the test is Webserver POS/POI PC shown in Figure 5. In every case, the Video over UWB approach out-performed the Video over wireless USB softwarevideo 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 (wayne.daniel@wiquest. com) 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. MICROSPACE® MPC20 _ _ _ _ _ _ _ _ _ 500MHz 256MB DRAM (max. 1GB) 256MB CF, Linux, DOS KB/MS 4x USB (1x internal) 2x LAN VGA MiniPCI slot Option HDD, WLAN Bo Hall 8, oth 228 www.digitallogic.com www.embedded.com/europe | embedded systems design europe | NOVEMBER – DECEMBER 2007 29 026-027-028-029_ESDE.indd 29 6/11/07 17:23:31 http://www.digitallogic.com http://www.passmark.com http://www.embedded.com/europe
For optimal viewing of this digital publication, please enable JavaScript and then refresh the page. If you would like to try to load the digital publication without using Flash Player detection, please click here.