Most existing research in probabilistic real-time scheduling analysis has primarily focused on systems with only stochastic execution times, neglecting the stochastic nature of task release patterns in many real-world applications. Current approaches for handling stochastic release times rely on computationally expensive convolution-based methods, which has poor scalability, especially when both execution and release times are stochastic. This paper presents novel techniques to apply the Chernoff Bound approach to the analysis of systems with both stochastic execution and release times. The key challenge lies in adapting the Chernoff Bound, which traditionally operates on a fixed number of random variables, to handle the stochastic job counts resulting from stochastic release patterns. Our main contribution is a new technique for bounding convolutions involving random numbers of random variables using Chernoff principles. Through comprehensive evaluation, we demonstrate that our approach achieves several orders of magnitude speedup compared to state-of-the-art convolution-based methods while simultaneously improving analysis precision.

In recent years, extensive research has been carried out on real-time typed scheduling and analysis of parallel tasks represented as directed acyclic graphs (DAGs) executed on heterogeneous multicores. Although previous studies have examined the schedulability of typed DAG tasks, they still encounter pessimism caused by interference from other tasks. In this article, we explore the worst case response time (WCRT) analysis of typed scheduling for DAG tasks under global scheduling. Here, each vertex in a typed DAG task experiences interference from within itself as well as from higher priority tasks. First, we propose an efficient method to bound the WCRT of typed DAG tasks based on the state-of-the-art parallel task analysis approach. Then, we discover a technique to mitigate the pessimism caused by other tasks, albeit in a nonoptimal manner. Finally, we conduct experiments using randomly generated typed DAG tasks to evaluate the performance of our proposed methods. The results indicate that our proposed approach can yield less pessimistic WCRT under global scheduling.

We introduce core tangibles: physical interaction elements which serve common roles across a variety of tangible and embedded interfaces. We describe two such tangibles: tangible menus and interaction trays. These may be composed together to dynamically bind discrete and continuous interactors to various digital behaviors. We discuss our approach, implementation, and early usage experiences.