A mixed-criticality system comprises safety-critical and non-safety-critical tasks sharing a computational platform. Thus, different levels of assurance are required by different tasks in terms of real-time performance. In addition, as the computational demands of real-time tasks are increasing, tasks may require internal parallelism in order to complete within stringent deadlines. In this paper, we consider the problem of mixed-criticality scheduling of parallel real-time tasks and propose a novel mixed-criticality federated scheduling (MCFS) algorithm for parallel real-time tasks based on the directed acyclic graph model. MCFS is based on federated intuition for scheduling parallel real-time tasks. It strategically assigns cores and virtual deadlines to tasks in order to achieve good schedulability. For task sets with only high-utilization tasks (utilization >= 1), we prove that MCFS provides a capacity augmentation bound of 3.41 and 3.73 for dual-criticality and multi- criticality, respectively. We also show that MCFS have capacity augmentation bounds of 3.67m/(m-1) for a dual-criticality system with both high- and low-utilization tasks, which to our knowledge is the first such performance bound for parallel mixed-criticality tasks. We also present an implementation of an MCFS runtime system in Linux that supports parallel programs written in OpenMP. We conduct both numerical and empirical experiments to demonstrate the practicality of our MCFS approach.

Real-time hybrid simulation (RTHS) is an important tool in the design and testing of civil and mechanical structures when engineers and scientists wish to understand the performance of an isolated component within the context of a larger structure. Performing full-scale physical experimentation with a large structure can be prohibitively expensive. Instead, a hybrid testing framework connects part of a physical structure within a closed loop (through sensors and actuators) to a numerical simulation of the rest of the structure. If we wish to understand the dynamic response of the combined structure, this testing must be done in real-time, which significantly restricts both the size of the simulation and the rate at which it can be conducted.

Recently, multi-core processors have become mainstream in processor design. To take full advantage of multi-core processing, computation-intensive real-time systems must exploit intra-task parallelism. In this paper, we address the problem of real-time scheduling for a general model of deterministic parallel tasks, where each task is represented as a directed acyclic graph (DAG) with nodes having arbitrary execution requirements. We prove processor-speed augmentation bounds for both preemptive and non-preemptive real-time scheduling for general DAG tasks on multi-core processors. We first decompose each DAG into sequential tasks with their own release times and deadlines. Then we prove that these decomposed tasks can be scheduled using preemptive global EDF with a resource augmentation bound of$4$. This bound is as good as the best known bound for more restrictive models, and is the first for a general DAG model. We also prove that the decomposition has a resource augmentation bound of$4$plus a constant non-preemption overhead for non-preemptive global EDF scheduling. To our knowledge, this is the first resource augmentation bound for non-preemptive scheduling of parallel tasks. Finally, we evaluate our analytical results through simulations that demonstrate that the derived resource augmentation bounds are safe in practice.

The multi-core revolution presents both opportunities and challenges for real-time systems. Parallel computing can yield significant speedup for individual tasks (enabling shorter deadlines, or more computation within the same deadline), but unless managed carefully may add complexity and overhead that could potentially wreck real-time performance. There is little experience to date with the design and implementation of realtime systems that allow parallel tasks, yet the state of the art cannot progress without the construction of such systems. In this work we describe the design and implementation of a scheduler and runtime dispatcher for a new concurrency platform, RT-OpenMP, whose goal is the execution of real-time workloads with intra-task parallelism.