Dominique Geniet

WCET free time analysis of hard real-time systems on multiprocessors: A regular language-based model

This paper presents the initial step of an aid design method earmarked for operational validation of hard real-time systems. We consider systems that are composed of sequential hard real-time tasks, which are embedded on centralized multiprocessor architectures. We introduce a model based upon untimed finite automata and meant to collect the operational behaviors of the system compatible with its time specifications, and we go on to provide a feasibility decision result for systems composed of tasks presenting CPU loads which are exact values: execution times are not WCET values. This is why we call this approach WCET-free analysis. The results we have achieved likewise involve hardware specifications such as multiprocessors and speeds of processors.

Discrete geometry applied in hard real-time systems validation

Off-line validation of hard real-time systems usually stands on state based models. Such approaches always deal with both space and time combinatorial explosions. This paper proposes a discrete geometrical approach to model applications and to compute operational feasability from topological properties. Thanks to this model, we can decide the feasability of real-time synchronous systems composed of periodic tasks, sharing resources, running on multiprocessor architectures. This method avoids state enumeration and therefore limits both space and time explosion: computing an automaton model takes at least 2 hours for a real application instead of at most 1 second using discrete geometry.

Queen-bee: query interaction-aware for buffer allocation and scheduling problem

In the relational data warehouses, each OLAP query shall involve the fact table. This situation increases the interaction between queries that can have a significant impact on the warehouse performance. This interaction has been largely exploited in solving isolated problems like (i) the multiple-query optimization, (ii) the materialized view selection, (iii) the buffer management, (iv) the query scheduling, etc. Recently, some research efforts studied the impact of the query interaction on optimization problems combining interdependent sub-problems such as buffer management problem (BMP) and the query scheduling problem (QSP). Note that combining two complex problems usually increases the complexity of the integrated problem. In this paper, we study the effect of considering the query interaction on an integrated problem including BMP and QSP (namely, BMQSP). We first present a formalization of the BMQSP and show its hardness study. Due to high complexity of the BMQSP, we propose an algorithm called queen-bee inspired from the natural life of bees. Finally, theoretical and effective (on Oracle 11G) experiments are done using the star schema benchmark data set.

Quantification du taux d'invalidité d'applications temps réel à contraintes strictes

A postoperative dynamic splint for controlled mobilization of a digit following tendon repair consists of a supportive brace assembly, having an attachment member for attachment of said brace assembly to the distal portion of the arm and the proximal portion of the hand and a tensioning unit which comprises a housing mounted on the supportive brace assembly, a spiral torsion spring mounted at one end to said housing and terminating at its other end to a work arm, which extends out of said housing. The work arm attaches to a rubber band, which is trained under a rotatable roller, mounted on a bracket attached to said brace assembly and at the other end to a connecting member, such as a nail cover, for the affected digit. This allows for extension and flexion of the recuperating digit, so as to prevent adhesion of the tendon to the tendon sheath during the healing process and thus insure full use of the digit after healing.

A Query Beehive Algorithm for Data Warehouse Buffer Management and Query Scheduling

Analytical queries, like those used in data warehouses and OLAP, are generally interdependent. This is due to the fact that the database is usually modeled with a denormalized star schema or its variants, where most queries pass through a large central fact table. Such interaction has been largely exploited in query optimization techniques such as materialized views. Nevertheless, such approaches usually ignore buffer management and assume queries have a fixed order and are known in advance. We believe such assumptions are too strong and thus they need to be revisited and simplified. In this paper, we study the combination of two problems: buffer management and query scheduling, in both static and dynamic scenarios. We present an NP-hardness study of the joint problem, highlighting its complexity. We then introduce a new and highly efficient algorithm inspired by a beehive. We conduct an extensive experimental evaluation on a real DBMS showing the superiority of our algorithm compared to previous ones as well as its excellent scalability.

Simultaneous Resolution of Buffer Allocation and Query Scheduling Problems

Database management systems (DBMS) use external magnetic devices (disks) for the storage of mass data. In the context of very large databases, the query response time may be strongly influenced by two main factors: (i) the amount data needed to be accessed from the disk to the main memory cache and (ii) the order of queries, especially if queries share some common intermediate results. These two factors are related to two well known problems in databases: Buffer Management Problem (BMP) and Query Scheduling Problem (QSP). Usually, BMP and QSP are treated in the isolated way and their strong interaction is ignored by the existing solutions. This situation motivates us to consider the integrated problem including BMP and QSP. In this paper, we first propose a formalization of the integrated problem and show complexity. Secondly, three heuristics are proposed: naive, hill climbing and genetic algorithms dealing with our integrated problem. Finally, two intensive experiments are conducted: (1) theoretically using a cost model and (2) a real validation on Oracle11G.

Scheduling hard sporadic tasks with regular languages and generating functions

In this paper, we consider offline validation of hard real-time systems composed of both periodic and sporadic tasks, embedded on centralized multi-processor architectures. To model hard real-time systems, we use untimed finite automata: each accepted word is a valid operational behavior of the periodic component of the system. Then, by associating generating functions with edges of the automaton, we give a modular decisional technique to decide the feasibility of sporadic tasks.

Term validation of distributed hard real-time applications

To validate real-time systems, one must especially validate on the one hand its functional behaviours (by proving that it does what it must do), and on the other hand its operational behaviours (by proving that it respects its time specifications). Here, we deal with the operational aspects. In previous works, we presented a technique, based on finite automata, to validate real-time systems designed to run on a centralised architecture. Here, we extend this approach to distributed systems. The main contribution of this work is to show that, when the modeled physical process is closed, finite automata and product operators are sufficient to valid distributed systems on an operational way.

Scheduling Hard Sporadic Tasks by Means of Finite Automata and Generating Functions

In a previous work, we propose a technique to decide feasability of periodic hard real-time systems based on finite automata. Here, associating generating functions (whose role is to predict the future) to a finite automaton, we extend this technique to hard sporadic tasks, independent or interdependent with the periodic tasks.

On the morphometric identity of populations of Helicotylenchus pseudorobustus (Steiner, 1914) Golden, 1956 (Tylenchida: Hoplolaimidae)

Helicotylenchus microlobus is considered to be a junior synonym of H. pseudorobustus by several authors while others consider it as valid. To clarify the status of both species, 39 samples collected from various countries were subjected to statistical analyses that showed they could be grouped into six groups. Topotypes of H. pseudorobustus and H. microlobus belong to two different groups. However, samples in the other groups were morphologically intermediate between these two groups. Characters used in the past to uphold the validity of H. microlobus were variable and overlapping from group to group. The 28 samples studied are identified as H. pseudorobustus . Helicotylenchus microlobus , H. bradys and H. phalerus are confirmed as junior synonyms of H. pseudorobustus . There was no complete congruence between the morphological groups and molecular groups proposed by other authors. For these, two MOTU (Molecular Operational Taxonomic Unit) are accepted within H. pseudorobustus .