Static Scheduling Generation for Multicore Partitioned Systems
Multicore systems are present in many sectors and arriving others, as real-time systems, traditionally reluctant to them due to the difficulty to estimate worst case execution time in multicore platforms. However, partitioned systems integrated by a parti
- PDF / 696,277 Bytes
- 12 Pages / 439.37 x 666.14 pts Page_size
- 32 Downloads / 230 Views
Abstract&Multicore systems are present in many sectors and arriving others, as real-time systems, traditionally reluctant to them due to the difficulty to estimate worst case execution time in multicore platforms. However, partitioned systems integrated by a partitioning kernel and a set of partitions with different levels of criticality is one of the emerging software technologies in real-time systems to deal with multi-core platforms. This paper presents a method to generate a static schedule for a multicore partitioned system. Several issues are considered: partitions with different levels of criticality, hierarchical schedule, allocation of partitions to cores and generation of the global schedule. The aim is to generate a cyclic static schedule for a multicore system which fulfils the temporal constraints of the partitions.
1
Introduction
The increasing use of multicore systems in many sectors is also arrived to real-time systems besides the difficulty to estimate worst case execution time in multicore platforms. Software architecture and real-time scheduling issues will be fundamental to use and consolidate the multicore approach in real-time systems. In real-time systems, or in a wide sense critical systems, there is an increasingly important trend for using applications with different levels of criticality where multiple components with different dependability and real-time constraints are integrated into a shared computing platform [4]. The reasons behind the trend for mixed-criticality are mainly non-functional: reduce costs, volume, weight and power consumption, and can be found in a multitude of different domains such as industrial control, airborne and automotive systems and space avionics, only to cite the most notable ones. A. Crespo() · P. Balbastre · J. Simo · P. Albertos Instituto de Automática e Informática Industrial (AI2), Universitat Politcnica de Valncia, Valencia, Spain e-mail: [email protected] © Springer Science+Business Media Singapore 2016 K.J. Kim and N. Joukov (eds.), Information Science and Applications (ICISA) 2016, Lecture Notes in Electrical Engineering 376, DOI: 10.1007/978-981-10-0557-2_51
511
512
A. Crespo et al.
At the same time mixed-criticality systems are proliferating, computing platforms are migrating from single cores to multicore architectures [18] [14]. It is estimated that multicores will be used in about 50% industrial applications by 2017. Multicores open new opportunities to develop robust mixed-criticality systems at competitive price, but they also create new challenges as software architecture and scheduling among others. From a software architecture point of view, there is a trend in using virtualization techniques to provide a partitioning architecture under the temporal and spatial isolation. This approach was initiated in the avionics sector [16] and extended to space [19] and automotive [9]. Virtualization support for partitioning is provided by hypervisors. Hypervisors are layers of software that exploit the features of the hardware platform to es
Data Loading...
