Search

Background The clinical presentation of SARS-CoV-2 disease ranges from asymptomatic respiratory infection to acute respiratory distress syndrome. Risk factors upon hospital admission associated with the need for invasive mechanical ventilation are not well documented. Methods 185 hospitalized patients with confirmed COVID-19 were enrolled in this study, and they were classified as patients who required invasive mechanical ventilation and patients who did not require it. Comorbidities such as diabetes, high blood pressure, obesity, chronic lung disease and immunodeficiency were recorded. Laboratory studies were requested upon admission such as C-reactive protein, leukocyte and lymphocyte levels, D-dimer, troponin, serum ferritin and procalcitonin. Results Of the patients who entered the study, 65 patients (35%) required invasive mechanical ventilation (IMV), while 120 (65%) did not require advanced airway management. Of the patients with invasive mechanical ventilation, age > 65 years, male sex, obesity (BMI > 30) and high blood pressure were the most frequent characteristics, presenting the latter two in 26% and 27% respectively. Regarding laboratory studies, the parameters most associated with the requirement for mechanical ventilation were a D-dimer (> 1000) and troponin (> 1), with 26% and 18%, respectively. Conclusion This study showed the high proportion of obesity, hypertension and advanced age among patients who required invasive mechanical ventilation associated with SARS-CoV2 infection. The presence of elevated D-dimer and troponin on admission are associated with more severe presentations and a requirement for invasive mechanical ventilation. Disclosures All Authors: No reported disclosures

In this paper, we propose the Distributed using Optimal Priority Assignment (DOPA) heuristic that finds a feasible partitioning and priority assignment for distributed applications based on the linear transactional model. DOPA partitions the tasks and messages in the distributed system, and makes use of the Optimal Priority Assignment (OPA) algorithm known as Audsley’s algorithm, to find the priorities for that partition. The experimental results show how the use of the OPA algorithm increases in average the number of schedulable tasks and messages in a distributed system when compared to the use of Deadline Monotonic (DM) usually favoured in other works. Afterwards, we extend these results to the assignment of Parallel/Distributed applications and present a second heuristic named Parallel-DOPA (P-DOPA). In that case, we show how the partitioning process can be simplified by using the Distributed Stretch Transformation (DST), a parallel transaction transformation algorithm introduced in [1].

This paper presents a holistic timing analysis for fixed-priority fork-join Parallel/Distributed tasks (P/D tasks) over a Flexible Time Triggered — Switched Ethernet (FTT-SE) network. The holistic approach considers both time-triggered and event-triggered tasks/messages.

Distributed real-time systems such as automotive applications are becoming larger and more complex, thus, requiring the use of more powerful hardware and software architectures. Furthermore, those distributed applications commonly have stringent real-time constraints. This implies that such applications would gain in flexibility if they were parallelized and distributed over the system. In this paper, we consider the problem of allocating fixed-priority fork-join Parallel/Distributed real-time tasks onto distributed multi-core nodes connected through a Flexible Time Triggered Switched Ethernet network. We analyze the system requirements and present a set of formulations based on a constraint programming approach. Constraint programming allows us to express the relations between variables in the form of constraints. Our approach is guaranteed to find a feasible solution, if one exists, in contrast to other approaches based on heuristics. Furthermore, approaches based on constraint programming have shown to obtain solutions for these type of formulations in reasonable time.

Modern real-time embedded applications present high computation requirements which need to be realized within strict time constraints. The current trend towards parallel processing in the embedded domain allows providing higher processing power. However, in some embedded applications, the use of powerful enough multi-core processors, may not be possible due to energy, space or cost constraints. A solution for this problem is to extend the parallel execution of the applications, allowing them to distribute their workload among networked nodes, on peak situations, to remote neighbour nodes in the system. In this context, we present the Partitioned-Distributed-Deadline Monotonic Scheduling algorithm for fork-join parallel/distributed fixed-priority tasks. We study the problem of scheduling fork-join tasks that execute in a distributed system, where the inherent transmission delay of tasks must be considered and cannot be deemed negligible, as in the case of multicore systems. Our scheduling algorithm is shown to have a resource augmentation bound of 4, which implies that any task set that is feasible on m unit-speed processors and a single shared real-time network, can be scheduled by our algorithm on m processors and a single real-time network that are 4 times faster. We confirm through simulations our analytical results.

An increasing number of real-time embedded applications present high computation requirements which need to be realized within strict time constraints. Simultaneously, architectures are becoming more and more heterogeneous, programming models are having difficulty in scaling or stepping outside of a particular domain, and programming such solutions requires detailed knowledge of the system and the skills of an experienced programmer. In this context, this paper advocates the transparent integration of a parallel and distributed execution framework, capable of meeting real-time constraints, based on OpenMP programming model, and using MPI as the distribution mechanism. The paper also introduces our modified implementation of GCC compiler, enabled to support such parallel and distributed computations, which is evaluated through a real implementation. This evaluation gives important hints, towards the development of the parallel/distributed fork-join framework for supporting real-time embedded applications.

Embedded real-time applications increasingly present high computation requirements, which need to be completed within specific deadlines. But, those applications present highly variable patterns, depending on the data set in a determined instant. The current trend to provide parallel processing in the embedded domain allows providing higher processing power, however, it does not address the variability in the processing pattern. Dimensioning each device for its worst-case scenario implies lower average utilization, and increased available, but unusable, processing in the overall system. A solution for this problem is to extend the parallel execution of the applications, allowing networked nodes to distribute the workload, on peak situations, to neighbour nodes. In this context, this paper proposes a framework to develop parallel and distributed real-time embedded applications, transparently using OpenMP and Message Passing Interface (MPI), within a programming model based on OpenMP. The paper also devises an integrated timing model, which enables the structured reasoning on the timing behaviour of these hybrid architectures.

Los sistemas técnicos de operación autónoma y los sistemas adaptativos tales como los sistemas mecatrónicos son aplicaciones dinámicas capaces de ajustarse a condiciones de operación cambiantes. Típicamente, estos se encuentran en sistemas distribuidos de tiempo real y requieren de un alto grado de flexibilidad en control. Además tratan con la variación de parámetros extrínsecos que causan condiciones de cambio para los periodos y los tiempos de ejecución de los cómputos de fin-a-fin. Como consecuencia la reasignación de tareas a procesadores puede ser necesaria. En la presente tesis, se propone la optimización del costo de reasignación de tareas para diferentes configuraciones del sistema. Se consideran procesadores idénticos y uniformes, la arquitectura de bus común y la arquitectura de arreglo lineal de procesadores. Se introducen funciones que miden el esfuerzo de realizar la reasignación de tareas a procesadores para cada modelo. Se proponen y analizan algoritmos óptimos y heurísticas. Además, se concluye que las heurísticas propuestas encuentran soluciones factibles para sistemas críticos de tiempo real y presentan un equilibrio entre el tiempo de ejecución y la calidad de la solución. Autonomously operating technical and adaptive systems as in mechatronics are dynamic applications that are able to adjust to changed operation conditions. Typically they are realized as distributed real-time systems requiring high flexibility in control. They have to deal with varying extrinsic parameters that cause changing conditions for the frequency and the run-times of the end-to-end computations. As a consequence, re-allocations of tasks to hosts will become necessary. In this thesis, we focus on the optimization of the task re-allocation cost for different system configurations. Identical and uniform hosts, the common bus architecture and linear array of hosts are considered. Re-allocation cost functions that measures the effort of realizing a re-allocation of computational tasks to hosts are introduced for each model. Optimal algorithms and heuristics are proposed and analyzed. And we conclude that the proposed heuristics presents feasible solutions for critical real time systems and tradeoff between the execution time and suitable cost can be found.