Aymen Gammoudi - Academia.edu (original) (raw)
Papers by Aymen Gammoudi
HAL (Le Centre pour la Communication Scientifique Directe), Jun 26, 2018
La conception de systèmes temps-réel embarqués se développe de plus en plus avec l’intégration cr... more La conception de systèmes temps-réel embarqués se développe de plus en plus avec l’intégration croissante de fonctionnalités critiques pour les applications de surveillance, notamment dans le domaine biomédical, environnemental, domotique, etc. Le développement de ces systèmes doit relever divers défis en termes de minimisation de la consommation énergétique. Gérer de tels dispositifs embarqués, entièrement autonomes, nécessite cependant de résoudre différents problèmes liés à la quantité d’énergie disponible dans la batterie, à l’ordonnancement temps-réel des tâches qui doivent être exécutées avant leurs échéances, aux scénarios de reconfiguration, particulièrement dans le cas d’ajout de tâches, et à la contrainte de communication pour pouvoir assurer l’échange des messages entre les processeurs, de façon à assurer une autonomie durable jusqu’à la prochaine recharge et ce, tout en maintenant un niveau de qualité de service acceptable du système de traitement. Pour traiter cette pro...
IEEE Transactions on Parallel and Distributed Systems, 2008
Multicore processors deliver a higher throughput at lower power consumption than unicore processo... more Multicore processors deliver a higher throughput at lower power consumption than unicore processors. In the near future, they will thus be widely used in mobile real-time systems. There have been many research on energy-efficient scheduling of real-time tasks using DVS. These approaches must be modified for multicore processors, however, since normally all the cores in a chip must run at the same performance level. Thus, blindly adopting existing DVS algorithms that do not consider the restriction will result in a waste of energy. This article suggests Dynamic Repartitioning algorithm based on existing partitioning approaches of multiprocessor systems. The algorithm dynamically balances the task loads of multiple cores to optimize power consumption during execution. We also suggest Dynamic Core Scaling algorithm, which adjusts the number of active cores to reduce leakage power consumption under low load conditions. Simulation results show that Dynamic Repartitioning can produce energy savings of about 8 percent even with the best energy-efficient partitioning algorithm. The results also show that Dynamic Core Scaling can reduce energy consumption by about 26 percent under low load conditions.
Abstract—Energy management is a central problem in battery powered real-time systems design, in p... more Abstract—Energy management is a central problem in battery powered real-time systems design, in particular for periodically reconfigurable embedded wireless devices. This kind of systems can be more or less intensive in computing, but must remain alive until the next recharge. They are not always critical, or at least some treatments are not critical. In this case, modification on tasks parameters of non-critical parts of the system can be done to increase the autonomy of the battery. The objective of this work is to develop a software plugin, called Reconf-Middleware, which corresponds to a software layer to be placed above the Operating System (OS). The main role of this software layer is to manage tasks execution for reconfigurable architecture when the battery recharges are done periodically. We integrate also a new schedul- ing strategy to ensure that the system will run correctly, after any reconfiguration scenario, under memory, real-time and energy constraints until the next...
This paper addresses the management of independent periodic OS tasks running on battery-powered r... more This paper addresses the management of independent periodic OS tasks running on battery-powered real-time systems which can change their parameters at run-time for each reconfiguration scenario. A reconfiguration is assumed to be any run-time automatic addition, re- moval, or also update of software tasks according to external events or also user requirements. After any sce- nario, the system can become not feasible and can also lead to a shortage of energy before the next recharge. To resolve these problems, we propose a dynamic strat- egy to be applied at run-time based on grouping tasks in packs. This strategy o↵ers five di↵erent solutions to ensure the system remains up until the next battery recharge while remaining feasible. In this context, we present, in this paper, a new simulator Reconf-Pack for analyzing a reconfiguration and applying the proposed strategy for real-time systems. It is based upon another tool Task-Generator which generates random tasks. Ac- cording to the ...
Proceedings of the 13th International Conference on Evaluation of Novel Approaches to Software Engineering, 2018
Multi-core Real-time Systems (MRS) powered by a battery have been adopted for a wide range of hig... more Multi-core Real-time Systems (MRS) powered by a battery have been adopted for a wide range of high performance applications, such as mobile communication and automotive systems. A system is composed of N dependent and periodic Operating System (OS) tasks to be assigned to p heterogeneous cores linked by a network-on-chip (NoC). This paper deals with the problem of task allocation in MRS in such a way that the cost of communication between cores is minimized by trying to place the dependent tasks as close as possible to each other. The main objective is to develop a new strategy for allocating N tasks to p cores of a given distributed system using task clustering by considering both the cost of inter task communication and that of communication between cores. The proposed strategy guarantees that, when a task is mapped into the system and accepted, then it is correctly executed prior to the task deadline. A novel periodic task model based on elastic coefficients is proposed to compute useful temporal parameters allowing to assign all tasks to p cores, by minimizing the traffic between cores. Experimental results reveal the effectiveness of the proposed strategy by comparing the derived solutions with the optimal ones, obtained by solving an Integer Linear Program (ILP).
La conception de systemes temps-reel embarques se developpe de plus en plus avec l’integration cr... more La conception de systemes temps-reel embarques se developpe de plus en plus avec l’integration croissante de fonctionnalites critiques pour les applications de surveillance, notamment dans le domaine biomedical, environnemental, domotique, etc. Le developpement de ces systemes doit relever divers defis en termes de minimisation de la consommation energetique. Gerer de tels dispositifs embarques, entierement autonomes, necessite cependant de resoudre differents problemes lies a la quantite d’energie disponible dans la batterie, a l’ordonnancement temps-reel des tâches qui doivent etre executees avant leurs echeances, aux scenarios de reconfiguration, particulierement dans le cas d’ajout de tâches, et a la contrainte de communication pour pouvoir assurer l’echange des messages entre les processeurs, de facon a assurer une autonomie durable jusqu’a la prochaine recharge et ce, tout en maintenant un niveau de qualite de service acceptable du systeme de traitement. Pour traiter cette pro...
2016 IEEE 28th International Conference on Tools with Artificial Intelligence (ICTAI), 2016
This paper deals with the real-time scheduling in a reconfigurable multi-core platform powered by... more This paper deals with the real-time scheduling in a reconfigurable multi-core platform powered by a rechargeable battery. A reconfiguration scenario is defined as an operation that allows the addition-removal-modification of tasks which may result in timing unfeasibility. Such a system may face several scenarios: i) increased power consumption that, in the worst case, may surpass the available energy budget, ii) increased computing demand, which may lead to the violation of real-time constraints, and iii) increased memory demand, potentially exceeding the provided memory capacity. To prevent these problems during the execution, a new scheduling strategy is necessary. The proposal is based on the assignment of tasks to different processor cores to satisfy these constraints simultaneously after any reconfiguration scenario. The effectiveness and performance of the designed approach are evaluated through simulation studies. An intelligent tool named Reconf-Pack is developed in our research laboratory to support this new proposed approach and to simulate it over randomly generated tasks.
HAL (Le Centre pour la Communication Scientifique Directe), Jun 26, 2018
La conception de systèmes temps-réel embarqués se développe de plus en plus avec l’intégration cr... more La conception de systèmes temps-réel embarqués se développe de plus en plus avec l’intégration croissante de fonctionnalités critiques pour les applications de surveillance, notamment dans le domaine biomédical, environnemental, domotique, etc. Le développement de ces systèmes doit relever divers défis en termes de minimisation de la consommation énergétique. Gérer de tels dispositifs embarqués, entièrement autonomes, nécessite cependant de résoudre différents problèmes liés à la quantité d’énergie disponible dans la batterie, à l’ordonnancement temps-réel des tâches qui doivent être exécutées avant leurs échéances, aux scénarios de reconfiguration, particulièrement dans le cas d’ajout de tâches, et à la contrainte de communication pour pouvoir assurer l’échange des messages entre les processeurs, de façon à assurer une autonomie durable jusqu’à la prochaine recharge et ce, tout en maintenant un niveau de qualité de service acceptable du système de traitement. Pour traiter cette pro...
IEEE Transactions on Parallel and Distributed Systems, 2008
Multicore processors deliver a higher throughput at lower power consumption than unicore processo... more Multicore processors deliver a higher throughput at lower power consumption than unicore processors. In the near future, they will thus be widely used in mobile real-time systems. There have been many research on energy-efficient scheduling of real-time tasks using DVS. These approaches must be modified for multicore processors, however, since normally all the cores in a chip must run at the same performance level. Thus, blindly adopting existing DVS algorithms that do not consider the restriction will result in a waste of energy. This article suggests Dynamic Repartitioning algorithm based on existing partitioning approaches of multiprocessor systems. The algorithm dynamically balances the task loads of multiple cores to optimize power consumption during execution. We also suggest Dynamic Core Scaling algorithm, which adjusts the number of active cores to reduce leakage power consumption under low load conditions. Simulation results show that Dynamic Repartitioning can produce energy savings of about 8 percent even with the best energy-efficient partitioning algorithm. The results also show that Dynamic Core Scaling can reduce energy consumption by about 26 percent under low load conditions.
Abstract—Energy management is a central problem in battery powered real-time systems design, in p... more Abstract—Energy management is a central problem in battery powered real-time systems design, in particular for periodically reconfigurable embedded wireless devices. This kind of systems can be more or less intensive in computing, but must remain alive until the next recharge. They are not always critical, or at least some treatments are not critical. In this case, modification on tasks parameters of non-critical parts of the system can be done to increase the autonomy of the battery. The objective of this work is to develop a software plugin, called Reconf-Middleware, which corresponds to a software layer to be placed above the Operating System (OS). The main role of this software layer is to manage tasks execution for reconfigurable architecture when the battery recharges are done periodically. We integrate also a new schedul- ing strategy to ensure that the system will run correctly, after any reconfiguration scenario, under memory, real-time and energy constraints until the next...
This paper addresses the management of independent periodic OS tasks running on battery-powered r... more This paper addresses the management of independent periodic OS tasks running on battery-powered real-time systems which can change their parameters at run-time for each reconfiguration scenario. A reconfiguration is assumed to be any run-time automatic addition, re- moval, or also update of software tasks according to external events or also user requirements. After any sce- nario, the system can become not feasible and can also lead to a shortage of energy before the next recharge. To resolve these problems, we propose a dynamic strat- egy to be applied at run-time based on grouping tasks in packs. This strategy o↵ers five di↵erent solutions to ensure the system remains up until the next battery recharge while remaining feasible. In this context, we present, in this paper, a new simulator Reconf-Pack for analyzing a reconfiguration and applying the proposed strategy for real-time systems. It is based upon another tool Task-Generator which generates random tasks. Ac- cording to the ...
Proceedings of the 13th International Conference on Evaluation of Novel Approaches to Software Engineering, 2018
Multi-core Real-time Systems (MRS) powered by a battery have been adopted for a wide range of hig... more Multi-core Real-time Systems (MRS) powered by a battery have been adopted for a wide range of high performance applications, such as mobile communication and automotive systems. A system is composed of N dependent and periodic Operating System (OS) tasks to be assigned to p heterogeneous cores linked by a network-on-chip (NoC). This paper deals with the problem of task allocation in MRS in such a way that the cost of communication between cores is minimized by trying to place the dependent tasks as close as possible to each other. The main objective is to develop a new strategy for allocating N tasks to p cores of a given distributed system using task clustering by considering both the cost of inter task communication and that of communication between cores. The proposed strategy guarantees that, when a task is mapped into the system and accepted, then it is correctly executed prior to the task deadline. A novel periodic task model based on elastic coefficients is proposed to compute useful temporal parameters allowing to assign all tasks to p cores, by minimizing the traffic between cores. Experimental results reveal the effectiveness of the proposed strategy by comparing the derived solutions with the optimal ones, obtained by solving an Integer Linear Program (ILP).
La conception de systemes temps-reel embarques se developpe de plus en plus avec l’integration cr... more La conception de systemes temps-reel embarques se developpe de plus en plus avec l’integration croissante de fonctionnalites critiques pour les applications de surveillance, notamment dans le domaine biomedical, environnemental, domotique, etc. Le developpement de ces systemes doit relever divers defis en termes de minimisation de la consommation energetique. Gerer de tels dispositifs embarques, entierement autonomes, necessite cependant de resoudre differents problemes lies a la quantite d’energie disponible dans la batterie, a l’ordonnancement temps-reel des tâches qui doivent etre executees avant leurs echeances, aux scenarios de reconfiguration, particulierement dans le cas d’ajout de tâches, et a la contrainte de communication pour pouvoir assurer l’echange des messages entre les processeurs, de facon a assurer une autonomie durable jusqu’a la prochaine recharge et ce, tout en maintenant un niveau de qualite de service acceptable du systeme de traitement. Pour traiter cette pro...
2016 IEEE 28th International Conference on Tools with Artificial Intelligence (ICTAI), 2016
This paper deals with the real-time scheduling in a reconfigurable multi-core platform powered by... more This paper deals with the real-time scheduling in a reconfigurable multi-core platform powered by a rechargeable battery. A reconfiguration scenario is defined as an operation that allows the addition-removal-modification of tasks which may result in timing unfeasibility. Such a system may face several scenarios: i) increased power consumption that, in the worst case, may surpass the available energy budget, ii) increased computing demand, which may lead to the violation of real-time constraints, and iii) increased memory demand, potentially exceeding the provided memory capacity. To prevent these problems during the execution, a new scheduling strategy is necessary. The proposal is based on the assignment of tasks to different processor cores to satisfy these constraints simultaneously after any reconfiguration scenario. The effectiveness and performance of the designed approach are evaluated through simulation studies. An intelligent tool named Reconf-Pack is developed in our research laboratory to support this new proposed approach and to simulate it over randomly generated tasks.