A Safari Through the MPSoC Run-Time Management Jungle

The multiprocessor SoC (MPSoC) revolution is fueled by the need to execute multiple advanced multimedia applications on a single embedded computing platform. At design-time, the applications that will run in parallel and their respective user requirements are unknown. Hence, a run-time manager (RTM) is needed to match all application needs with the available platform resources and services. Creating such a run-time manager requires two decisions. First, one needs to decide what functionality to implement. Second, one has to decide how to implement this functionality in order to meet boundary conditions like e.g. real-time performance. This paper is the first to detail a generic view on MPSoC run-time management functionality and its design space trade-offs. We substantiate the run-time components and the implementation trade-offs with academic state-of-the-art solutions and a brief overview of some industrial multiprocessor run-time management examples. We show a clear trend towards more hardware acceleration, a limited distribution of management functionality over the platform and increasing support for adaptive multimedia applications. In addition, we briefly detail upcoming run-time management research issues.     

Run-Time Management of a MPSoC Containing FPGA Fabric Tiles

Multimedia applications, like, e.g., 3-D games and video decoders, are typically composed of communicating tasks. Their target embedded computing platforms (e.g., TI OMAP3, IBM Cell) contain multiple heterogeneous processing elements. At application design-time, it is often unknown which applications will execute simultaneously. Hence, resource assignment decisions need to be made by a run-time manager. Run-time assignment of these communicating tasks onto the communication and computation resources of such a multiprocessor platform is a challenging task. In the presence of fine-grain reconfigurable hardware processing elements, the run-time manager also needs to consider the creation of a so-called configuration hierarchy. Instead of executing a dedicated hardware task, the fine-grain reconfigurable hardware fabric hosts a programmable softcore block that, in turn, executes the task functionality. Hence, the next challenge for run-time management is to efficiently handle a configuration hierarchy. This paper details a run-time task assignment heuristic that performs fast and efficient task assignment in a multiprocessor system-on-chip containing fine-grain reconfigurable hardware tiles. In addition, this algorithm is capable of managing a configuration hierarchy. We show that being capable of handling a configuration hierarchy significantly improves the task assignment performance (i.e., success rate and assignment quality). In several cases, adding a configuration hierarchy improves the assignment success rate of the assignment heuristic by 20%.     

Distribution of salmonella strains in farrow-to-finish pig herds: a longitudinal study

The aims of this study were to investigate patterns of Salmonella shedding in finishing pigs and to study the role of the sow in the transmission of Salmonella to her offspring. In each of the three herds (A, B, and C), one cohort of sows (n = 34, n = 40, n = 32, respectively) together with three piglets of their offspring (n = 102, n = 120, n = 96, respectively) were selected. Individual fecal and blood samples were taken from the sows at different times during one production cycle and from the piglets from weaning until slaughter. At slaughter, contents from the jejunum, colon, and mesenteric lymph nodes were collected. Fecal samples, as well as the jejunum, colon, and mesenteric lymph node samples collected at slaughter, were submitted to a qualitative Salmonella analysis. Isolates were characterized by random amplified polymorphic DNA, and if necessary, further characterization was done by pulsed-field gel electrophoresis. In herds A and B, Salmonella shedding began in the nursery. A significant increase in the number of Salmonella shedders was seen after transferring pigs to the growing unit in herd B (P = 0.003) and to the finishing unit in herds A (P < 0.001) and B (P = 0.013). None of the fattening pigs in herd C were shedding Salmonella. This study reveals that transferring pigs is an important trigger to induce Salmonella shedding, leading to horizontal spread. Direct transmission of Salmonella from the sows to their piglets could not be demonstrated, but the similarities between the isolates found in the sows and those found during the nursery and finishing periods and at slaughter suggested indirect transmission.     

Methylmercury input to the Mississippi River from a large metropolitan wastewater treatment plant

Methylmercury (MeHg) and total mercury (THg) inputs to the Mississippi River from a large metropolitan wastewater treatment plant were measured to characterize the relative contribution of the treatment plant to in-stream loads of these contaminants. Concentrations of MeHg and THg were determined in filtered and unfiltered whole water samples collected weekly from the treatment plant effluent stream and from the river upstream of the plant discharge. Unfiltered MeHg concentrations in the plant effluent ranged from 0.034 to 0.062 ng L(-1) and were always less than those in the river (range: 0.083-0.227 ng L(-1)). The MeHg loading to the river from the treatment plant ranged from 0.026 to 0.051 g d(-1) and averaged 0.037 g d(-1) over the 13-week sampling period. The in-stream MeHg load in the river upstream varied widely depending on hydrologic conditions, ranging from 0.91 to 18.8 g d(-1) and averaging 4.79 g d(-1). The treatment plant discharge represented 1.6%, on average, of the in-stream MeHg load, ranging from 0.2 to 3.5% depending on flow conditions in the river. MeHg in treatment plant effluent was primarily in the filtered phase (mean: 57%, <0.2 microm), but in the river the filtered/unfiltered ratio (F/UF) was typically less than 30% except during a major precipitation runoff event, when F/UF increased to 78%. The MeHg/THg ratio in unfiltered treatment plant effluent varied little (range: 1.6-1.9%), suggesting that THg concentration can serve as a relatively accurate proxy for MeHg concentration in this effluent stream. Supplemental sampling of the treatment plant influent stream showed that removals of MeHg and THg across the treatment process averaged 97% and 99%, respectively. These results show the treatment plant to be effective in removing MeHg and THg from wastewater and in minimizing its impact on Hg levels in the receiving water.     

Mercury mass balance at a wastewater treatment plant employing sludge incineration with offgas mercury control

Efforts to reduce the deliberate use of mercury (Hg) in modern industrialized societies have been largely successful, but the minimization and control of Hg in waste streams are of continuing importance. Municipal wastewater treatment plants are collection points for domestic, commercial, and industrial wastewaters, and Hg removal during wastewater treatment is essential for protecting receiving waters. Subsequent control of the Hg removed is also necessary to preclude environmental impacts. We present here a mass balance for Hg at a large metropolitan wastewater treatment plant that has recently been upgraded to provide for greater control of the Hg entering the plant. The upgrade included a new fluidized bed sludge incineration facility equipped with activated carbon addition and baghouse carbon capture for the removal of Hg from the incinerator offgas. Our results show that Hg discharges to air and water from the plant represented less than 5% of the mass of Hg entering the plant, while the remaining Hg was captured in the ash/carbon residual stream exiting the new incineration process. Sub-optimum baghouse operation resulted in some of the Hg escaping collection there and accumulating with the ash/carbon particulate matter in the secondary treatment tanks. Overall, the treatment process is effective in removing Hg from wastewater and sequestering it in a controllable stream for secure disposal.     

Type-2 fuzzy sliding mode control without reaching phase for nonlinear system

A new sliding mode control (SMC) algorithm for the nth order nonlinear system suffering from parameters uncertainty and subjected to an external perturbation is proposed. The algorithm employs a time-varying switching plane. At the initial time t=t₀, the plane passes through the point determined by the system initial conditions in the error state space. Afterwards, the plane moves to the origin of the state space. Since the nonlinear system is sensible to the perturbations and uncertainties during the reaching phase, the elimination of such phase yields in a considerable amelioration of system robustness. Switching plane is chosen such that: (1) the reaching phase is eliminated, (2) the nonlinear system is insensitive to the external disturbance and the model uncertainty from the initial time (3) the convergence of the tracking error to zero. Furthermore, a Type-2 fuzzy system is used to approximate system dynamics (assumed to be unknown) and to construct the equivalent controller such that: (1) all signals of closed-loop system are uniformly ultimately bounded, (2) the problems related to adaptive fuzzy controllers like singularity and constraints on the control gain are resolved. To ensure the robustness of the overall closed-loop system, analytical demonstration using Lyapunov theorem is considered. Finally, a robot manipulator is considered as a real time system in order to confirm the efficiency of the proposed approach. The experimentation is done for both regulation and tracking control problems.     

Scalable, Wavelet-Based Video: From Server to Hardware-Accelerated Client

Video source, carrier and client diversification have led the video coding community to develop scalable video codecs supporting efficient decoding at varying resolution, frame rate and quality. Scalable video has several advantages over a nonscalable approach, but a large scale deployment is far from trivial and a lot of open questions remain. To resolve these, we developed a complete video delivery chain for scalable wavelet-based video. This includes a video server, a negotiation framework, a video scaling infrastructure and two scalable video clients, one pure software client and one real-time, hardware accelerated client. This paper describes the complete chain and identifies and quantifies the impact of using scalable video in every link of this chain.     

The effect of probiotic strains on the microbiota of the Simulator of the Human Intestinal Microbial Ecosystem (SHIME)

The aim of the present work was to study five potential probiotic strains (Lactobacillus plantarum, two strains of L. paracasei subsp. paracasei, L. rhamnosus and Bifidobacterium sp.) comparatively in the Simulator of the Human Intestinal Microbial Ecosystem (SHIME) in vitro model, and to evaluate this model as a tool in the screening and selection of probiotic bacteria. The impact of the strains on the composition of microbiota and its metabolic activities (production of lactic acid and short-chain fatty acids) was studied. Changes in composition of the microbiota become apparent as a result of probiotic treatment. A marked, but temporary, increase was noted in the number of lactic acid bacteria and bifidobacteria. The profiles of D(-) and L(+) isomers of lactic acid detected in the SHIME after addition of probiotic strains corresponded well to those that are produced in pure culture conditions. The numbers of enterobacteriaceae decreased markedly and those of clostridia detectably during the intervention, while the enterococci tended to increase after the treatment. This pattern was similar in the reactors representing both the small and large intestine in the model. The changes in short-chain fatty acids were small, and no definite trend was observed.