“…Since the goal of the methodology was to gain performance estimates early, but without starting actual implementational work, we estimated the execution time of DSP code from figures found in the literature. The authors of [5] break down the MPEG decoding algorithm into 5 major functional parts and provide an analysis of how much time is spent in each functional part. We used this analysis to determine the fraction of time spent in those functional parts in order to delegate their computation to the DSP.…”
In this experience report, we present experiences we have gained in applying performance engineering techniques during the design of a DVB-H enabled handheld device. The modelling methodology we applied uses UML 2.0 to model the system following a strict separation of architectural and behavioural aspects of the systems. From sequence diagrams and composite structure diagrams, a queueing network is generated for the analysis of the system performance. The configuration of the hardware resources and the resource demands is done using the standard SPT-profile. We describe our implementation and its seamless integration into a UML 2.0 CASE tool. Finally, the paper outlines lessons learnt during the design process which may be used to enhance the methodology.
“…Since the goal of the methodology was to gain performance estimates early, but without starting actual implementational work, we estimated the execution time of DSP code from figures found in the literature. The authors of [5] break down the MPEG decoding algorithm into 5 major functional parts and provide an analysis of how much time is spent in each functional part. We used this analysis to determine the fraction of time spent in those functional parts in order to delegate their computation to the DSP.…”
In this experience report, we present experiences we have gained in applying performance engineering techniques during the design of a DVB-H enabled handheld device. The modelling methodology we applied uses UML 2.0 to model the system following a strict separation of architectural and behavioural aspects of the systems. From sequence diagrams and composite structure diagrams, a queueing network is generated for the analysis of the system performance. The configuration of the hardware resources and the resource demands is done using the standard SPT-profile. We describe our implementation and its seamless integration into a UML 2.0 CASE tool. Finally, the paper outlines lessons learnt during the design process which may be used to enhance the methodology.
“…These comprise both custom ASIC solutions [8], and multimedia platforms with video-specific hardware accelerators, e.g., TI's OMAP [9] [10]. Again, these solutions do not consider bandwidth constraints.…”
Enabling real-time video streaming from a wireless appliance requires compute intensive video compression to be performed in real-time on the appliance before transmitting the data upstream. However, the task of real-time video encoding and streaming from the wireless appliances is challenging due to a) limited computational and battery resources, and b) limited and time-varying network bandwidth availability.In this paper, we present a technique for enabling realtime video compression and transmission from wireless appliances based on run-time video adaptation. We present an adaptation engine for dynamic selection of video compression parameters such that both the computational and the network bandwidth constraints are satisfied, while maximizing the end user's viewing quality. The algorithm is based on the analysis of the effect of different video compression parameters on computational and network resource usage, and the video quality. Since our approach is based on judicious selection of video compression parameters and does not require changes to the compression algorithm itself, it is applicable to a wide range of video compression standards. We have also developed an iPAQ-based end-to-end video streaming system to evaluate our approach. Experiments conducted on this test-bed indicate that our proposed technique achieves significant improvements in overall video quality under computation (up to 4x) and network bandwidth (∼3dB) constraints. We also show significant improvements in the energy efficiency as a result of adaptation.
I. INTRODUCTIONAdvancements in wireless data communications and mobile computing have led to a growing demand for realtime video-based applications, such as Multimedia Messaging Services (MMS), two-way video conferencing and remote monitoring using wireless appliances such as camera phones, wireless handhelds and video sensors. These applications require the input video to be compressed on the mobile device in real-time before streaming it over the wireless channel. However, such applications, originally developed for high-end desktop processors with high bandwidth wired connectivity, are characterized by their resource intensive nature both in terms of their computational resource (CPU usage) and network bandwidth requirements. This makes it extremely challenging to deploy such applications on mobile appliances with limited computational and battery resources over wireless networks with limited bandwidth.Video encoding is more compute intensive than video decoding. Therefore, it is more challenging to encode and stream a real-time video from a mobile device than to download and decode it on the device. Our experiments indicate that a fully dedicated high-end mobile processor (Intel XScale [1] at 400 MHz) is barely able to encode and upload a 15 frames per second (fps) Quarter Common Intermediate Format (QCIF) video clip having moderately high motion. Even this would be difficult to support in real scenario when various other tasks such as real-time video capturing and audio processi...
“…For example, Gumstix Overo products integrate WiFi/Bluetooth connectivity, microSD storage, and 600 MHz Texas Instruments OMAP (Open Multimedia Application Platform) 35xx processors with up to 256 MB of flash memory/SDRAM, offering laptop-like resources and performance in a form factor of a stick of gum (Chaoui, et al, 2001). This speaks to the potential for wearable, wireless medical devices based on such products to process signals on-board; functionality that previously required expensive, bulky, benchtop/bedside equipment.…”
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.