Now showing 1 - 4 of 4
PublicationCompositional Real-Time Scheduling Framework(2004-12-06) Shin, Insik; Lee, Insup; Shin, Insik; Lee, InsupOur goal is to develop a compositional real-time scheduling framework so that global (system-level) timing properties can be established by composing independently (specified and) analyzed local (component-level) timing properties. The two essential problems in developing such a framework are (1) to abstract the collective real-time requirements of a component as a single real-time requirement and (2) to compose the component demand abstraction results into the system-level real-time requirement. In our earlier work, we addressed the problems using the Liu and Layland periodic model. In this paper, we address the problems using another well-known model, a bounded-delay resource partition model, as a solution model to the problems. To extend our framework to this model, we develop an exact feasibility condition for a set of bounded-delay tasks over a bounded-delay resource partition. In addition, we present simulation results to evaluate the overheads that the component demand abstraction results incur in terms of utilization increase. We also present new utilization bound results on a bounded-delay resource model. PublicationA Design Approach for Real-Time Embedded Systems with Energy and Code Size Constraints(2004-08-25) Shin, Insik; Lee, Insup; Min, Sang Lyul; Shin, Insik; Lee, Insup; Min, Sang LyulReal-time embedded systems often have multiple resource constraints such as energy and code size constraints. Traditionally, techniques for reducing energy consumption for real-time embedded systems have been developed without considering code size constraints, whereas code size reduction techniques have been developed without considering energy constraints. There, however, is a tradeoff relationship between reducing dynamic energy consumption and reducing code size for real-time embedded systems. Therefore, reducing code size may result in increasing energy consumption. In this paper, we present a triple-tradeoff relationship among code size, execution time, and energy consumption and then address the code size minimization problem while considering simultaneously the energy constraints and the real-time requirements of embedded systems. We formulate such an optimization problem and prove this optimization problem is NP-hard. Given the difficulty of finding the optimal solution to the problem, we then propose four heuristic algorithms to find sub-optimal solutions and evaluate their performance through simulations. PublicationSchedulability Analysis of Hierarchical Real-Time Systems(2007-05-07) Easwaran, Arvind; Shin, Insik; Sokolsky, Oleg; Lee, Insup; Easwaran, Arvind; Shin, Insik; Sokolsky, Oleg; Lee, InsupEmbedded systems are complex as a whole but consist of smaller independent modules interacting with each other. This structure makes embedded systems amenable to compositional design. Real-time embedded systems consist of real-time workloads having temporal deadlines. Compositional design of real-time embedded systems can be done using systems consisting of real-time components arranged in a scheduling hierarchy. Each component consists of some real-time workload and a scheduling policy for the workload. To simplify schedulability analysis for such systems, analysis can be done compositionally using interfaces that abstract the timing requirements of components. To facilitate analysis of dynam- ically changing real-time systems, the framework must support incremental analysis. In this paper, we summarize our work [19, 6] on schedulability analysis for hierarchical real-time systems. We describe a compositional analysis technique that abstracts resource requirements of components using periodic resource models. To support incremental analysis and resource bandwidth minimization, we describe an extension to this interface model. Each extended interface consists of multiple periodic resource models for different periods. This allows the selection of a periodic model that can schedule the system using minimum bandwidth. We also account for context switch overheads in these interfaces. We then describe an associative composition technique for such interfaces that supports incremental analysis. PublicationIncremental Schedulability Analysis of Hierarchical Real-Time Components(2006-10-25) Easwaran, Arvind; Shin, Insik; Sokolsky, Oleg; Lee, Insup; Easwaran, Arvind; Shin, Insik; Sokolsky, Oleg; Lee, InsupEmbedded systems are complex as a whole but consist of smaller independent modules minimally interacting with each other. This structure makes embedded systems amenable to compositional system design. Compositional design of real-time embedded systems can be done using hierarchical systems which consist of real-time components arranged in a scheduling hierarchy. Each component consists of a real-time workload and a scheduling policy for the workload. To simplify schedulability analysis of hierarchical systems, analysis can be done compositionally using interfaces that abstract the timing requirements of components. Associative composition will facilitate analysis of systems in which components are modified on the fly. In this paper, we propose efficient algorithms to abstract the resource requirements of components in the form of periodic resource models. Each component interface consists of a set of periodic resource models for different values of period, which allows the selection of a periodic interface that minimizes the collective real-time requirements of hierarchical components. We also describe an interface composition algorithm which accounts for context switch overheads incurred by components and is associative.