Simulation of Real-Time Multiprocessor Scheduling Using DES

Chéramy, Maxime; Déplanche, Anne-Marie; Hladik, Pierre-Emmanuel

doi:10.1007/978-3-319-11457-6_3

Cited by 36 publications

(32 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…YARTISS is an open source simulator aimed at the evaluation of real‐time scheduling policies on multiprocessor systems for various models of tasks. SimSo is a simulator designed for the comparison and the understanding of real‐time multiprocessor scheduling algorithms.…”

Section: Related Workmentioning

confidence: 99%

“…In the same line of work, we can mention Probabilistic SimSo, which is a probabilistic extension of SimSo with support for pWCET and pMIT, and DIAGXTRM . The latter implements the Measurement‐Based Probabilistic Timing Analysis, which is an application of the Generalized Extreme Value Theory to estimate the pWCET and evaluate its quality.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

The PROSIT tool: Toward the optimal design of probabilistic soft real‐time systems

et al. 2018

View full text Add to dashboard Cite

Summary In recent years, series of important achievements have paved the way for the introduction of probabilistic analysis in the area of soft real‐time systems design. In this article, we present an extensible design tool, called PROSIT, which facilitates the access to this technology for a potentially large number of researchers and industrial practitioners. The tool enables the probabilistic analysis of the temporal performance of a real‐time task under fixed‐priority and resource reservations scheduling algorithms. For resource reservations, the tool also offers an automatic procedure for the synthesis of scheduling parameters that optimize a quality metric related to the probabilistic behavior of the tasks.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

The PROSIT tool: Toward the optimal design of probabilistic soft real‐time systems

et al. 2018

View full text Add to dashboard Cite

show abstract

“…We simulate the schedule to obtain the total number of context switches using the scheduling simulator SimSo [12] and our task clustering heuristic to evaluate the number of context switches and preemptions before and after task clustering under DM. Our experiments did Deadlines are uniformly distributed between bounds d1 = 0 and d2 = 1 and the utilization factor of the processor is randomly generated between 0.20 and 0.80 for each generated task set.…”

Section: Context Switches and Preemptionsmentioning

confidence: 99%

Minimizing a real-time task set through Task Clustering

Bertout

Forget

Olejnik

2014

Proceedings of the 22nd International Conference on Real-Time Networks and Systems

View full text Add to dashboard Cite

International audienceIn the industry, real-time systems are specified as a set of hundreds of functionalities with timing constraints. Implementing those functionalities as threads in a one-to-one relation is not realistic due to the overhead caused by the large number of threads. In this paper, we present task clustering, which aims at minimizing the number of threads while preserving the schedulability. We prove that our clustering problem is NP-Hard and describe a heuristic to tackle it. Our approach has been applied to fixed-task or fixed-job priority based scheduling policies as Deadline Monotonic (DM) or Earliest Deadline First (EDF)

show abstract

“…Several algorithms of scheduling are optimal in case single processor, like EDF (Earliest Deadline First) or LLF (Least Laxity First) for which the CPU ustlistion 100% is possible while guaranteeing the respect of the deadlines [14]. But, LLF has larger overhead than EDF due to higher number of context switches caused by laxity changes at run time.…”

Section: Related Workmentioning

confidence: 99%

Modeling and Simulation of an Autonomous Power Manager for Sensor Networks

́our¹,

Jmal²,

Abid³

2016

IJMO

View full text Add to dashboard Cite

Abstract-Wireless Sensor Networks (WSN) have widespread applications, ranging from the industrial automation to the home applications, a result of their higher enhanced capabilities and im-proved cost-efficiency. However, there may not be enough resources to process those applications. So raising the energy efficiency of WSN is a paramount objective to extend the lifetime of the sensors network. This paper presents the methodologies followed to develop effective techniques to save the energy consumption of the WSN at the system level and under time constraints. This approach is based on an interplay of online strategies to manage the energy at a local level, as well as a scheduling policy that exploits effectively the resources at the global level. The autonomous power manager combines the Dynamic Power Management (DPM) with a Dynamic Voltage and Frequency Scaling (DVFS) that will be validated using the STORM simulator.

show abstract

Simulation of Real-Time Multiprocessor Scheduling Using DES

Cited by 36 publications

References 22 publications

The PROSIT tool: Toward the optimal design of probabilistic soft real‐time systems

The PROSIT tool: Toward the optimal design of probabilistic soft real‐time systems

Minimizing a real-time task set through Task Clustering

Modeling and Simulation of an Autonomous Power Manager for Sensor Networks

Contact Info

Product

Resources

About