Papers by Emmanuel Grolleau
Springer eBooks, 2000
We present an off-line methodology of analysis of real-time systems, composed of periodic, preced... more We present an off-line methodology of analysis of real-time systems, composed of periodic, precedence and resource constrained real-time tasks. As there is no polynomial optimal scheduling technique for such tasks sets, we present an enumerative method based on the construction of the state graph of a Petri net. The time is modeled by the Petri net through the earliest firing rule.
The software architecture of a critical embedded control system generally consists of a set of mu... more The software architecture of a critical embedded control system generally consists of a set of multi-periodic communicating tasks. In order to be able to describe such a system, we define the notion of semaphore precedence constraint, which supports multi-rate communications that follow regular repetitive patterns. We propose a feasibility test for EDF and we study three implementations, for periodic task sets related by such extended precedences on monoprocessor architectures.
HAL (Le Centre pour la Communication Scientifique Directe), Mar 28, 2000
Nous montrons que toute séquence d'ordonnancement valide construite par un algorithme conservatif... more Nous montrons que toute séquence d'ordonnancement valide construite par un algorithme conservatif (i.e. au plus tôt), pour un système de tâches périodiques (pouvant partager des ressources et communiquer) différées, est cyclique de période le PPCM des périodes des tâches à partir du dernier temps creux acyclique. Nous améliorons et généralisons ainsi la borne proposée par Leung et Merrill. Ce résultat permet de borner la durée de simulation d'ordonnancements en-ligne, et de connaître la longueur nécessaire de construction de séquences d'ordonnancement hors-ligne.
HAL (Le Centre pour la Communication Scientifique Directe), May 16, 2013
This paper is proposing a general periodicity result concerning any deterministic and memoryless ... more This paper is proposing a general periodicity result concerning any deterministic and memoryless scheduling algorithm (including non-work-conserving algorithms), for any context, on identical multiprocessor platforms. By context we mean the hardware architecture (uniprocessor, multicore), as well as task constraints like critical sections, precedence constraints, selfsuspension, etc. Since the result is based only on the releases and deadlines, it is independent from any other parameter. Note that we do not claim that the given interval is minimal, but it is an upper bound for any cycle of any feasible schedule provided by any deterministic and memoryless scheduler.
HAL (Le Centre pour la Communication Scientifique Directe), Mar 6, 2001
HAL (Le Centre pour la Communication Scientifique Directe), Mar 26, 2002
HAL (Le Centre pour la Communication Scientifique Directe), Jun 9, 1998
IFAC Proceedings Volumes, May 1, 2000
Theoretical Computer Science, 2004
We consider real-time systems in highly safety context where tasks have to meet strict deadlines.... more We consider real-time systems in highly safety context where tasks have to meet strict deadlines. Tasks are periodic, may have o sets, share critical resources and be precedence constrained. O -line scheduling should be of great help for such systems, but methods proposed in the literature cannot deal with them. Our aim is to extend and improve the well-known cyclicity result of Leung and Merill to every scheduling algorithm and to systems of interacting tasks with o sets. One of the main beneÿt of our result is to enable the use of o -line scheduling methods for those real-time critical systems.

HAL (Le Centre pour la Communication Scientifique Directe), 2000
ABSTRACT. We present a methodology of off line analysis for hard real time applications, constitu... more ABSTRACT. We present a methodology of off line analysis for hard real time applications, constituted of interacting tasks, submitted to hard temporal constraints. By means of a Petri net with terminal markings, under the maximal firing rule, we compute all the feasible schedules and we present extraction techniques of optimal schedules, for some performance criteria (e.g. optimal response time of a subset of tasks..). Our approach takes into account asynchronous task systems, read and write resources. Furthermore, communicating tasks do not have to share the same period provided the emission and reception rates are the same. The considered class is the wider which has been considered for off line approaches. MOTS-CLÉS. ordonnancement -analyse hors ligne -séquences optimales -réseaux de Petrirègle de tir maximal -marquages terminaux KEYWORDS. Scheduling -off line analysis -optimal schedules -Petri nets -maximal firing rule -terminal markings
HAL (Le Centre pour la Communication Scientifique Directe), Jul 5, 2022
On UAVs, telemetry messages are often sent following a FIFO schedule, and some messages, dependin... more On UAVs, telemetry messages are often sent following a FIFO schedule, and some messages, depending on the FIFO queue state may suffer long delays, and can even be lost if the FIFO queue is full. Considering the high complexity of the problem of assigning offsets to periodic tasks, we propose a new heuristic, called GCD+, that we compare to the methods of the state of the art, showing that GCD+ significantly outperforms them on synthetic tasks sets. Then we use a real UAV use case, based on Paparazzi autopilot, to show that GCD+ behaves well. The proposed algorithm is meant to be the new Paparazzi's automatic offset assignment method for messages.
HAL (Le Centre pour la Communication Scientifique Directe), Jul 5, 2000

HAL (Le Centre pour la Communication Scientifique Directe), Mar 24, 1999
Nous présentons l'extension d'une méthodologie de détermination de toutes les séquences d'ordonna... more Nous présentons l'extension d'une méthodologie de détermination de toutes les séquences d'ordonnancement des systèmes de tâches temps réel. La méthode, jusqu'alors appliquée aux systèmes de tâches étant activées à la même date, est étendue aux systèmes de tâches dont certaines peuvent être initialement retardées. Elle se base sur une représentation du système de tâches par des réseaux de Petri colorés avec ensemble terminal fonctionnant avec la règle de tir maximal. ABSTRACT. We present an extension of a methodology used to determinate the whole schedule set of real-time systems. This methodology which was ever applied to task systems with the same first release date is generalized to systems where some tasks have a non zero first release date. Colored Petri net running under the maximal firing strategy is used to generate the schedules. MOTS-CLÉS : temps réel, ordonnancement, réseaux de Petri.
Cet article présente les avancées récentes en terme de modèles de tâches, et leur utilisatio... more Cet article présente les avancées récentes en terme de modèles de tâches, et leur utilisation dans le cadre monopro-cesseur. Nous nous concentrons sur les modèles de tâches prenant en compte les décalages de dates d’activation, et notamment sur les transactions, et les modèles multiframes et ses généralisations, jusqu’au modèle digraph. Sur ces modèles complexes, il y a principalement deux types d’analyse. D’une part, l’analyse de pire temps de réponse (RTA- Response Time Analysis), est utilisée pour étudier des systèmes ordonnancés par des algorithmes à priorités fixes. D’autre part, l’analyse de la demande processeur (DBF- Demand Bound Function), est utilisée pour étudier l’ordonnançabilite ́ globale d’un système. Nous nous intéressons ici a ̀ l’analyse de temps de réponse.

Non-preemptive scheduling reduces both runtime and design time overhead since it avoids context s... more Non-preemptive scheduling reduces both runtime and design time overhead since it avoids context switches, preserves cache affinity, and simplifies the use of shared resources. As a result, it increases the accuracy of worst-case execution time (WCET) estimation and improves system predictability. Many safety critical systems use table driven scheduling in which tasks are dispatched according to a schedule stored in a table. This table contains a cyclic schedule that needs to be repeated during the lifetime of the system. Since the table must be kept in memory, a smaller table is preferable particularly for embedded systems with limited memory. For example, the Atmel UC3A0512 microcontroller, which is used in mission critical space applications [1], has 64 KiB of internal SRAM, 512 KiB of internal flash memory, and is clocked at 12 MHz. Similarly, an Arm Cortex-M3 has 4 KiB RAM, 16 KiB flash, and clock speed 24 MHz. With such limited resources, non-preemptive execution becomes the na...

2018 Design, Automation & Test in Europe Conference & Exhibition (DATE), 2018
Architecture Analysis and Design Language (AADL) is a standard in avionics system design. However... more Architecture Analysis and Design Language (AADL) is a standard in avionics system design. However, the communication patterns provided by AADL are not sufficient to the current context of Real-Time Embedded System (RTES) in which some multi-periodic communication patterns may occur. We propose an extension of a precedence model between tasks of different periods (multiperiodic communication). This relies on the Semaphore Precedence Constraint (SPC) model that is inspired from the concept of Semaphore, and more specifically on the m-n producer/consumer paradigm. We reinforce the SPC semantics by allowing cycles in the SPC precedence graph. We also present another viewpoint on the periodicity of tasks system using SPC based on a graph apart from the encoding technique presented in the SPC seminal work. An implementation of SPC in AADL and its associated analysis tool are also provided to study the temporal behaviour of systems using SPC.
IFAC Proceedings Volumes, 2000
Proceedings of the 6th International Conference on Simulation and Modeling Methodologies, Technologies and Applications, 2016
Amongst real-time scheduling community, several methods aim at enhencing the performance of the c... more Amongst real-time scheduling community, several methods aim at enhencing the performance of the control. Subtask scheduling is one of the embedded convenient methods that reduce the input-output latency in the control loops. The predictive-Delay control is a new method based on input-output latency prediction in order to reduce the impact of this artefact on the quality of the control. Combining both subtask scheduling and predictive delay methods can be of a great help in combatting the impairments induced by this scheduling artifact.

Real-Time Systems, 2016
This paper gives and proves correct a simulation interval for any schedule generated by a determi... more This paper gives and proves correct a simulation interval for any schedule generated by a deterministic and memoryless scheduler (i.e., one where the scheduling decision is the same and unique for any two identical system states) for identical multiprocessor platforms. We first consider independent periodic tasks, then generalize the simulation interval to tasks sharing critical resources, and subject to precedence constraints or self-suspension. The simulation interval is based only on the periods, release times and deadlines, and is independent from any other parameters. It is proved large enough to cover any feasible schedule produced by any deterministic and memoryless scheduler on multiprocessor platforms, including non conservative schedulers. To the best of our knowledge, this simulation interval covers the largest class of tasks systems and scheduling algorithms on identical multiprocessor platforms ever studied. This simulation interval is used to derive a simulation algorithm using a linear space complexity. Finally, a generic exact schedulability test based on simulation is presented. This test can be applied only when sustainability is consistent with online variability of the tasks' parameters.

Tsi Technique Et Science Informatiques, 2000
ABSTRACT. We present a methodology of off line analysis for hard real time applications, constitu... more ABSTRACT. We present a methodology of off line analysis for hard real time applications, constituted of interacting tasks, submitted to hard temporal constraints. By means of a Petri net with terminal markings, under the maximal firing rule, we compute all the feasible schedules and we present extraction techniques of optimal schedules, for some performance criteria (e.g. optimal response time of a subset of tasks..). Our approach takes into account asynchronous task systems, read and write resources. Furthermore, communicating tasks do not have to share the same period provided the emission and reception rates are the same. The considered class is the wider which has been considered for off line approaches. MOTS-CLÉS. ordonnancement -analyse hors ligne -séquences optimales -réseaux de Petrirègle de tir maximal -marquages terminaux KEYWORDS. Scheduling -off line analysis -optimal schedules -Petri nets -maximal firing rule -terminal markings
Uploads
Papers by Emmanuel Grolleau