This paper considers the offline assignment of fixed priorities in partitioned preemptive real-time systems where tasks have precedence constraints. This problem is crucial in this type of systems, as having a good fixed priority assignment allows for an efficient use of the processing resources while meeting all the deadlines. In the literature, we can find several proposals to solve this problem, which offer varying trade-offs between the quality of their results and their computational complexities. In this paper, we propose a new approach, leveraging existing algorithms that are widely exploited in the field of Machine Learning: Gradient Descent, the Adam Optimizer, and Gradient Noise. We show how to adapt these algorithms to the problem of fixed priority assignment in conjunction with existing worst-case response time analyses. We demonstrate the performance of our proposal on synthetic task-sets with different sizes. This evaluation shows that our proposal is able to find more schedulable solutions than previous heuristics, approximating optimal but intractable algorithms such as MILP or brute-force, while requiring reasonable execution times.

Abstract In multicore scheduling of hard real-time systems, there is a significant source of unpredictability due to the interference caused by the sharing of hardware resources. This paper deals with the schedulability analysis of multicore systems where the interference caused by the sharing of hardware resources is taken into account. We rely on a task model where this interference is integrated in a general way, without depending on a specific type of hardware resource. There are similar approaches but they consider fixed priorities. The schedulability analysis is provided for dynamic priorities assuming constrained deadlines and based on the demand bound function. We propose two techniques, one more pessimistic than the other but with a lower computational cost. We evaluate the two proposals for different task allocators in terms of the increased estimated utilization. The results show that both bounds are valid for ensuring schedulability although, as expected, one is tighter than the other. The evaluation also serves to compare allocators to see which one produces less interference.

In hard real-time embedded systems, switching to multicores is a step that most application domains delay as much as possible. This is mainly due to the number of sources of indeterminism, which mainly involve shared hardware resources, such as buses, caches, and memories. In this paper, a new task model that considers the interference that task execution causes in other tasks running on other cores due to memory contention is proposed. We propose a scheduling algorithm that calculates the exact interference. We also analyse and compare existing partitioning algorithms and propose three strategies to allocate tasks to cores to schedule as many tasks as possible and minimise total interference.

Demand for Advanced Driver Assistance Systems (ADAS) is growing larger with the key focus of increased road safety, driver comfort and the futuristic autonomous vehicles. ADAS is typically a mixed-criticality system (MCS) with interdependent tasks which change their criticality level with the dynamic changes in the environment. In an MCS, the timing of safety-critical tasks must be strictly guaranteed to prevent accidents. From the conventional scheduling techniques in ADAS, more challenge is involved in meeting the timing performance of task scheduling and resource sharing while ADAS as MCS. This is a work-in-progress paper. Its objective is the design of ADAS with multicore partitioned architecture on the Xtratum hypervisor with the improved load and resource sharing among the subsystems. This is to address the dynamic changes in criticality and later to reduce the make-span for high critical tasks so as to prevent accidents. Two safety-critical ADAS subsystems Forward Collision Avoidance System (FCAS) and Blind Spot Avoidance System (BSAS) help to illustrate the architecture in this paper.

This paper addresses the problem of energy characterization in partitioned systems. The goal is to use this model to minimize energy consumption. Controlling the frequency at which CPUs can operate is a common technique to reduce the system energy consumption. Techniques as DVFS assume that decreasing the system frequency decreases the system energy, in spite of increasing the time the processor is busy. This relationship between temporal load, frequency and energy is studied in this paper. All works assume that this relationship is linear but we provide a new energy model that relates the previous variables through a non-linear relation. We also present a comparison in terms of energy between the linear and the non-linear model.