Efficiently Handling Process Overruns and Underruns on Multiprocessors in Real-Time Embedded Systems

2017 ◽  
Author(s):  
Jia Xu
Keyword(s):  
Embedded Systems ◽  
Real Time ◽  
Time Complexity ◽  
Multiprocessor System ◽  
Multiprocessor Systems ◽  
Worst Case ◽  
Real World Applications ◽  
Run Time ◽  
Hard Real Time ◽  
Time Overhead

In hard real-time and embedded multiprocessor system real-world applications, it is very important to strive to minimize the run-time overhead of the scheduler as much as possible, especially in hard real-time and embedded multiprocessor systems with limited processor and system resources. In this paper, we present a method that reduces the worst-case time complexity of the run-time scheduler for re-computing latest start times and for selecting processes for execution on a multiprocessor at run-time to O(n), where n is the number of processes.

An Overview of Worst-Case Execution Time Estimation for Embedded Programs

2014 ◽  
Vol 651-653 ◽  
pp. 624-629
Author(s):  
Liang Liang Kong ◽  
Lin Xiang Shi ◽  
Lin Chen
Keyword(s):  
Embedded Systems ◽  
Real Time ◽  
Execution Time ◽  
Time Estimation ◽  
Worst Case ◽  
Performance Metric ◽  
Worst Case Execution Time ◽  
Hard Real Time ◽  
Time Systems

Most embedded systems are real-time systems, so real-time is an important performance metric for embedded systems. The worst-case execution time (WCET) estimation for embedded programs could satisfy the requirement of hard real-time evaluation, so it is widely used in embedded systems evaluation. Based on sufficient survey on the progress of WCET estimation around the world, it proposes a new classification of WCET estimation. After introducing the principle of WCET estimation, it mainly demonstrates various types of technologies to estimate WCET and classifies them into two main streams, namely, static and dynamic WCET estimations. Finally, it shows the development of WCET analysis tools.

Efficiently Handling Process Overruns and Underruns in Real-Time Embedded Systems

2015 ◽  
Author(s):  
Jia Xu
Keyword(s):  
Embedded Systems ◽  
Real Time ◽  
Time Process ◽  
Time System ◽  
Worst Case ◽  
Real Time System ◽  
System Utilization ◽  
System Overhead ◽  
Run Time

Methods for handling process underruns and overruns when scheduling a set of real-time processes increase both system utilization and robustness in the presence of inaccurate estimates of the worst-case computations of real-time processes. In this paper, we present a method that efficiently re-computes latest start times for real time processes during run-time in the event that a real-time process is preempted or has completed (or overrun). The method effectively identifies which process latest start times will be affected by the preemption or completion of a process. Hence the method is able to effectively reduce real-time system overhead by selectively re-computing latest start times for the specific processes whose latest start times are changed by a process preemption or completion, as opposed to indiscriminately re-computing latest start times for all the processes.

scholarly journals A Group-Based Energy-Efficient Dual Priority Scheduling for Real-Time Embedded Systems

Information ◽  
2020 ◽  
Vol 11 (4) ◽  
pp. 191
Author(s):  
Yongqi Ge ◽  
Rui Liu
Keyword(s):  
Energy Consumption ◽  
Embedded Systems ◽  
Real Time ◽  
System Reliability ◽  
Energy Efficient ◽  
Worst Case ◽  
Priority Scheduling ◽  
Different Types ◽  
Time Overhead ◽  
Case Response

As the limitation of energy consumption of real-time embedded systems becomes more and more strict, it has been difficult to ignore the time overhead and energy consumption of context switches for fixed-priority tasks with preemption scheduling (FPP) in multitasking environments. In addition, the scheduling for different types of tasks may disrupt each other and affect system reliability. A group-based energy-efficient dual priority scheduling (GEDP) is proposed in this paper. The GEDP isolates different types of tasks to avoid the disruption. Furthermore, it also reduces context switches effectively, thus decreasing system energy consumption. As many studies ignored the context switches’ overhead in the worst-case response time (WCRT) model, and it will affect the accuracy of WCRT, thereby affecting the system schedulability. Consequently, the WCRT model is improved based on considering context switches’ overhead. The GEDP is designed and implemented in Linux, and the time overhead and energy consumption of context switches is compared in different situations with GEDP and FPP. The experimental results show that GEDP can reduce context switches by about 1% and decrease energy consumption by about 0.6% for given tasks.

Efficient Scheduling Algorithm for Hard Real-Time Tasks in Primary-Backup Based Multiprocessor Systems

2009 ◽  
Vol 20 (10) ◽  
pp. 2628-2636 ◽  
Author(s):  
Jian WANG ◽  
Jian-Ling SUN ◽  
Xin-Yu WANG ◽  
Shen-Kang WANG ◽  
Jun-Bo CHEN
Keyword(s):  
Real Time ◽  
Scheduling Algorithm ◽  
Multiprocessor Systems ◽  
Hard Real Time

scholarly journals Logic-based schedulability analysis for compositional hard real-time embedded systems

2015 ◽  
Vol 12 (1) ◽  
pp. 56-64 ◽  
Author(s):  
André de Matos Pedro ◽  
David Pereira ◽  
Luís Miguel Pinho ◽  
Jorge Sousa Pinto
Keyword(s):  
Embedded Systems ◽  
Real Time ◽  
Schedulability Analysis ◽  
Hard Real Time

A Fast 3-D Visualization Methodology Using Characteristic Views of Objects

1998 ◽  
Vol 08 (01) ◽  
pp. 97-114 ◽  
Author(s):  
Soochan Hwang ◽  
Sang-Young Cho ◽  
Taehyung Wang ◽  
Phillip C.-Y. Sheu
Keyword(s):  
Finite Number ◽  
Real Time ◽  
Time Complexity ◽  
Object Oriented ◽  
Equivalence Classes ◽  
Visualization Method ◽  
Tree Algorithm ◽  
Projected Image ◽  
Characteristic Views ◽  
Run Time

This paper describes a 3-D visualization method based on the concept of characteristic views (CVs). The idea of characteristic views was derived based on the observation that the infinite possible views of a 3-D object can be grouped into a finite number of equivalence classes so that within each class all the views are isomorphic in the sense that they have the same line-junction graphs. To visualize the changes of scenes in real time, the BSP tree algorithm is known to be efficient in a static environment in which the viewpoint can be changed easily. However, if a scene consists of many objects and each object consists of many polygons, the time complexity involved in traversing a BSP tree increases rapidly so that the original BSP tree algorithm may not be efficient. The method proposed in this paper is object-oriented in the sense that, for all viewpoints, at the preprocessing stage the ordering for displaying the objects is determined. At run time, the objects are displayed based on a pre-calculated ordering according to the viewpoint. In addition, a CV is used as a basic 2-D projected image of a 3-D object.

Reliability-Aware Proactive Energy Management in Hard Real-Time Systems

2010 ◽  
Vol 1 (4) ◽  
pp. 1-11
Author(s):  
Satyakiran Munaga ◽  
Francky Catthoor
Keyword(s):  
Energy Management ◽  
Ad Hoc ◽  
Failure Criteria ◽  
Worst Case ◽  
Time Control ◽  
Run Time ◽  
Cost Penalty ◽  
Hard Real Time ◽  
The Cost ◽  
Time Systems

Advanced technologies such as sub-45nm CMOS and 3D integration are known to have more accelerated and increased number of reliability failure mechanisms. Classical reliability assessment methodology, which assumes ad-hoc failure criteria and worst-case for all influencing dynamic aspects, is no longer viable in these technologies. In this paper, the authors advocate that managing temperature and reliability at run-time is necessary to overcome this reliability-wall without incurring significant cost penalty. Nonlinear nature of modern systems, however, makes the run-time control very challenging. The authors suggest that full cost-consciousness requires a truly proactive controller that can efficiently manage system slack with future in perspective. This paper introduces the concept of “gas-pedal,” which enhances the effectiveness of the proactive controller in minimizing the cost without sacrificing the hard guarantees required by the constraints. Reliability-aware dynamic energy management of a processor running AVC motion compensation task is used as a motivational case study to illustrate the proposed concepts.

scholarly journals Hard Real-Time Performances in Multiprocessor-Embedded Systems Using ASMP-Linux

2008 ◽  
Vol 2008 ◽  
pp. 1-16 ◽  
Author(s):  
Emiliano Betti ◽  
Daniel Pierre Bovet ◽  
Marco Cesati ◽  
Roberto Gioiosa
Keyword(s):  
Embedded Systems ◽  
Real Time ◽  
Hard Real Time ◽  
Multiprocessor Embedded Systems
Sign in / Sign up

Export Citation Format

Share Document