Abstract. With the rise of multi-core platforms even more complex software systems can be implemented. Designers are facing various new challenges during the development of efficient, predictable, and correct applications for such platforms. To efficiently map software applications to these architectures, the impact of platform decisions with respect to the hardware and the software infrastructure (OS, scheduling policies, priorities, mapping) has to be explored in early design phases.Especially shared resource accesses are critical in that regard. The efficient mapping of tasks to processor cores and their local scheduling are increasingly difficult on multi-core architectures. In this work we present an integration of shared resources into a SystemC-based simulation framework, which enables early functional simulation and provides a refinement flow towards an implementation, covering an increasing level of platform details. We propose shared resource extensions towards multicore platform models and discuss which aspects of the system behaviour can be captured.
In this paper a middleware architecture for distributed automotive systems that supports self-configuration by dynamic load balancing of tasks is presented. The inclusion of self-configurability is able to offer reliability within the multimedia network of the vehicle (Infotainment). Load balancing of tasks could be applied if an error occurred within the network. The error detection in the network and the load balancing should run automatically. Therefore, the middleware architecture has to deal on one hand with the error detection and on the other hand with the migration of tasks. Additionally, to enable the migration it is important to identify the requirements of all electronic control units (ECU) and tasks within the network.
Abstract. For embedded systems multicores are becoming more important. The flexibility of multicores is the main reason for this increasing extension. Considering embedded systems are often applied for real-time task, the usage of multicores implicates several problems. This is caused by the architecture of multicore chips. Usually such chips consist of 2 or more cores, a communication bus, I/O's and memory. Exactly the accesses to these resources from a core make it hard to ensure real-time. Therefore, well known mechanisms for resource access must be used, but for sure this is not sufficient enough. Because, a lot of design decisions depend on the applications. As a result, it is mandatory to analyze the requirements of the applications in detail and from the targeted multicore system. The aim of this analysis process is to derive a method for an optimal system design with respect to real-time support. This paper gives an overview of the requirement analysis for multicores and RT scheduling algorithms. Additionally, existing scheduling strategies are reviewed and proposals for new schedulers will be made.
To solve health problems with medical applications that use complex algorithms is a trend nowadays. It could also be a chance to help patients with critical problems caused from nerve irritations to overcome them and provide a better living situation. In this paper a system for monitoring and controlling the nerves from the intestine is described on a theoretical basis. The presented system could be applied to the irritable bowel syndrome. For control a neural network is used. The advantages for using a neural network for the control of irritable bowel syndrome are the adaptation and learning. These two aspects are important because the syndrome behavior varies from patient to patient and have also concerning the time a lot of variations with respect to each patient. The developed neural network is implemented and can be simulated. Therefore, it can be shown how the network monitor and control the nerves for individual input parameters.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.