Dissertations / Theses on the topic 'Réseaux logiques programmables'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Réseaux logiques programmables.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
Kilic, Alp. "Méthodologie d'optimisation d'architectures pour applications mutuellement exclusives." Paris 6, 2013. http://www.theses.fr/2013PA066603.
Full textToday electronic devices contain more and more features due to emergence of new embedded applications. The interesting point which comes with feature-rich platforms, from hardware designer's point of view, is that lots of features cannot be executed at the same time. The mutually exclusiveness of different features gives the possibility of hardware resource sharing between applications, among other optimization. Designers can implement those using different architectures like CPUs, FPGAs or ASICs. However the higher cost of silicon pushes researchers to find better solutions. Thus, to have a good trade-off between flexibility and performance, Multi-Mode Systems are proposed. This work proposes a new optimization methodology for mutually exclusive applications which contains common logic resources. It takes the advantage of the possibility of resource sharing between applications knowing that resources cannot be used at the same time. A given set of mutually exclusive applications are synthesized and combined in a single multi-mode ASIC called mASIC. This methodology allows to create a multi-mode circuit without changing the hardware description of the input applicationsMASIC generation techniques are also performed to generate a multi standard RF receiver. ZigBee, WiFi and Bluetooth standards are developed separately in the context of the ANR funded project “ASTECAS”. Knowing the fact that they have common resources like adders and multipliers, we used mASIC optimization methodology to share resources between 3 standards
Ben, Dhia Arwa. "Durcissement de circuits logiques reconfigurables." Electronic Thesis or Diss., Paris, ENST, 2014. http://www.theses.fr/2014ENST0068.
Full textAs feature sizes scale down to nano-design level, electronic devices have become smaller, more performant, less power-onsuming, but also less reliable. Indeed, reliability has arisen as a serious challenge in nowadays’ microelectronics industry and as an important design criterion, along with area, performance and power consumption. For instance, physical defects due to imperfections in the manufacturing process have been observed more frequently, impacting the yield. Besides, nanometric circuits have become more vulnerable during their lifetime to ionizing radiation which causes transient faults. Both manufacturing defects and transient faults contribute to decreasing reliability of integrated circuits. When moving to a new technology node, Field Programmable Gate Arrays (FPGAs) are the first coming into the market, thanks to their low development and Non-Recurring Engineering (NRE) costs and their flexibility to be used for any application. FPGAs have especially attractive characteristics for space and avionic applications, where reconfigurability, high performance and low-power consumption can be fruitfully used to develop innovative systems. However, missions take place in a harsh environment, rich in radiation, which can induce soft errors within electronic devices. This shows the importance of FPGA reliability as a design criterion in safety and critical applications. Most of commercial FPGAs have a mesh architecture and their logic blocks are gathered into clusters. Therefore, this thesis deals with the fault tolerance of basic blocks (clusters and switch boxes) in a mesh of clusters FPGA. These blocks are mainly made up of multiplexers. In order to improve their reliability, it is imperative to be able to assess it first, then select the proper hardening approach according to the available budget. So, this is the main outline in which this thesis is conceived. Its goals are twofold: (a) analyze the fault tolerance of the basic blocks in a mesh of clusters FPGA, and point out the most vulnerable components (b) propose hardening schemes at different granularity levels, depending on the hardening budget. As far as the first goal is concerned, a methodology to evaluate the reliability of the cluster is proposed. This methodology uses an existent analytical method for reliability computation of combinational circuits. The same method is employed to identify the worthiest components to be hardened. Regarding the second goal, hardening techniques are proposed at both multiplexer and transistor levels. At multiplexer level, two hardening solutions are presented. The first solution resorts to spacial redundancy and concerns the logic block structure. A novel Configurable Logic Block (CLB) architecture baptized Butterfly is introduced. It is compared with other hardened CLB architectures in terms of reliability and cost penalties. The second hardening solution is a redundanceless scheme. It is based on a “smart” synthesis that consists in seeking the most reliable design in a given founder library, instead of directly using a redundant solution. Then, at transistor level, new single-ended and dual-rail multiplexer architectures are proposed. They are compared to different other transistor structures, according to suitable design metrics
Senouci, Sid-Ahmed Benali. "Optimisation et prédiction temporelles sur les réseaux programmables CPLD." Ecully, Ecole centrale de Lyon, 1998. http://www.theses.fr/1998ECDL0051.
Full textBeyrouthy, Taha. "Logique programmable asynchrone pour systèmes embarqués sécurisés." Grenoble INPG, 2009. http://www.theses.fr/2009INPG0137.
Full textThis thesis focuses on the design and the validation of an embedded FPGA dedicated to critical applications which require a high level of security and confidentiality. Nowadays FPGAs exhibit many weaknesses toward security: 1- They are not intended to efficiently support alternative styles of circuits such as asynchronous circuits. 2- The place and route flow is not completely manageable by the user in order to target our security goal. 3- They are not protected against side channel attacks such as DP A, EMA or DF A. Ln order to overcome these technological problems, the work presented in this thesis proposes an architecture that supports the programming of different styles of asynchronous circuits. Ln addition, it presents a secure programming system and a design that ensurcs a high-Ievel of security against the attacks mentioned above. Finally, the circuit prototype has been evaluated in order to validate the relevance of the proposed solutions
Delahaye, Jean-Philippe. "Plate-forme hétérogène reconfigurable : application à la radio logicielle." Rennes 1, 2007. http://www.theses.fr/2007REN1S181.
Full textThe Software Defined Radio (SDR) techniques aim at offering an access to a broad choice of radio communications standards on a flexible hardware (HW) architecture which is necessary in order to answer the diversity of the processing to carry out. The digital communications techniques involve heterogeneous resources needs. The reconfigurability of a heterogeneous HW platform is thus a key features to a successful appearance of SDR systems. The reconfigurability of a SDR system must meet the needs for adaptation of the processing functions to answer the requirements of the contexts switching. Our work is based on the analysis of the baseband processing in the transmitting chains of the 3 standards UMTS, GSM and 802. 11g. We propose an analysis of factorization of the multistandard baseband processing in order to reduce the number of contexts to be managed and we determine the needs for flexibility of SDR applications. In this context, the configuration management of HW platforms clearly appears as the key feature of a SDR system. We propose a Hierarchical and Distributed Configuration Management (“HDCM”) approach in order to meet the needs of managing various types of flexibility of dataflow oriented applications mapped on heterogeneous HW. The implementation of applications on reconfigurable heterogeneous platforms and in particular on configurable logic devices, requires the uses of new design methodologies in order to extract the potential reconfigurability of these reconfigurables devices. We bring in this work various design methodologies that aim at designing partially and dynamically reconfigurable systems on chip and on FPGA
Ben, Dhia Arwa. "Durcissement de circuits logiques reconfigurables." Thesis, Paris, ENST, 2014. http://www.theses.fr/2014ENST0068/document.
Full textAs feature sizes scale down to nano-design level, electronic devices have become smaller, more performant, less power-onsuming, but also less reliable. Indeed, reliability has arisen as a serious challenge in nowadays’ microelectronics industry and as an important design criterion, along with area, performance and power consumption. For instance, physical defects due to imperfections in the manufacturing process have been observed more frequently, impacting the yield. Besides, nanometric circuits have become more vulnerable during their lifetime to ionizing radiation which causes transient faults. Both manufacturing defects and transient faults contribute to decreasing reliability of integrated circuits. When moving to a new technology node, Field Programmable Gate Arrays (FPGAs) are the first coming into the market, thanks to their low development and Non-Recurring Engineering (NRE) costs and their flexibility to be used for any application. FPGAs have especially attractive characteristics for space and avionic applications, where reconfigurability, high performance and low-power consumption can be fruitfully used to develop innovative systems. However, missions take place in a harsh environment, rich in radiation, which can induce soft errors within electronic devices. This shows the importance of FPGA reliability as a design criterion in safety and critical applications. Most of commercial FPGAs have a mesh architecture and their logic blocks are gathered into clusters. Therefore, this thesis deals with the fault tolerance of basic blocks (clusters and switch boxes) in a mesh of clusters FPGA. These blocks are mainly made up of multiplexers. In order to improve their reliability, it is imperative to be able to assess it first, then select the proper hardening approach according to the available budget. So, this is the main outline in which this thesis is conceived. Its goals are twofold: (a) analyze the fault tolerance of the basic blocks in a mesh of clusters FPGA, and point out the most vulnerable components (b) propose hardening schemes at different granularity levels, depending on the hardening budget. As far as the first goal is concerned, a methodology to evaluate the reliability of the cluster is proposed. This methodology uses an existent analytical method for reliability computation of combinational circuits. The same method is employed to identify the worthiest components to be hardened. Regarding the second goal, hardening techniques are proposed at both multiplexer and transistor levels. At multiplexer level, two hardening solutions are presented. The first solution resorts to spacial redundancy and concerns the logic block structure. A novel Configurable Logic Block (CLB) architecture baptized Butterfly is introduced. It is compared with other hardened CLB architectures in terms of reliability and cost penalties. The second hardening solution is a redundanceless scheme. It is based on a “smart” synthesis that consists in seeking the most reliable design in a given founder library, instead of directly using a redundant solution. Then, at transistor level, new single-ended and dual-rail multiplexer architectures are proposed. They are compared to different other transistor structures, according to suitable design metrics
Brunet, Philippe. "Exploration multicritères d'architectures à Reconfiguration Dynamique." Nancy 1, 2004. http://www.theses.fr/2004NAN10195.
Full textDays after days, new dynamically reconfigurable circuits provides more flexibility and possibilities to implement various algorithms. If progress is significant with regard to the material, an efficient implementation is hard to define according to this new flexibility. It provides to the developers a vast field of solutions meeting their needs. Today, available reconfigurable circuits from the main FPGA companies do not have efficient methods and tools necessary to a good management these components. The goal of this work is to provide tools allowing a complete exploration of the possibilities offered by dynamic reconfiguration for the implementation of an algorithm. We can thus give to the developers an overview of the performances that such or such manner of splitting its application will achieve. The result is then to allow an faster , simpler and less constraining implementation using the dynamic reconfiguration which still appear complex to a beginner in the world of reconfigurable computing
Parvez, Husain. "Conception et exploration des architectures de circuits FPGA hétérogènes à base de structures matricielles et dédiées aux applications spécifiques." Paris 6, 2010. http://www.theses.fr/2010PA066501.
Full textTanguy, Sébastien. "Test et testabilité des FPGA hiérarchiques à base de cellules mémoires SRAM." Montpellier 2, 2006. http://www.theses.fr/2006MON20050.
Full textCanivet, Gaëtan. "Analyse des effets d'attaques par fautes et conception sécurisée sur plate-forme reconfigurable." Grenoble INPG, 2009. http://www.theses.fr/2009INPG0065.
Full textSecurity of digital processing is important in our society. Many applications require high levels of security and/or safety. To meet these requirements, applications often use ASIC components. The main problems of such devices are that they are dedicated to one application and require high production volumes. Another possible approach is to use reconfigurable platforms such as SRAM-based FPGAs. However, the configuration memory of such FPGAs is sensitive to perturbation, thus requiring a specific study. The main goal of this thesis is to characterize the fault injection effects obtained in such devices using lasers and power glitches. In this work, we analyze for a given FPGA the sensitivity of the elements configuring the logic and we identify the main types of modification patterns in interconnections. Fault attack effects have been studied with respect to several parameters: laser spot size or power glitch amplitude, perturbation duration and energy. The determinism of the effects was also analyzed. It was shown for the laser attacks that the shape of sensitive areas depends on the initial bit state and an interpretation was proposed. Based on these characterizations, an AES crypto-processor secured against fault-based attacks was implemented on the FPGA and then attacked. Robustness differences with the ASIC implementation were particularly analyzed and countermeasure improvements were proposed, implemented and validated
Amouri, Emna. "Outils de placement et de routage pour des architectures FPGA sécurisées contre les attaques DPA." Paris 6, 2011. http://www.theses.fr/2011PA066205.
Full textGandriau, Marcel. "CIEL classes et instances en logique /." Grenoble 2 : ANRT, 1988. http://catalogue.bnf.fr/ark:/12148/cb37613782d.
Full textLe, Merrer Erwan. "Protocoles décentralisés pour la gestion de réseaux logiques large-échelle." Rennes 1, 2007. ftp://ftp.irisa.fr/techreports/theses/2007/lemerrer.pdf.
Full textWe focus on large scale distributed and dynamic systems. We are interested in methods that get information from the network, for monitoring and administration purposes. After surveying related work about techniques that assure the service maintenance, we present four protocols which are aimed to mesure key characteristics about the overlay. We introduce an uniform sampling method, based on a random walk. We then present two techniques aimed at estimate the syze of a system. The first method rely on a random walk, and the second one use the birthday paradox reversal. A comparative study is driven, and finally the best one is compared with other techniques of the related work. We also worked on the replica placement issue, for potentially highly used services. Finally we introduce, to the best of our knowledge, the first distributed estimation method on the arrivals and departures dynamics on the network
Khan, Jehangir. "Embedded multiprocessor architectures for automative driver assistance systems." Valenciennes, 2009. http://ged.univ-valenciennes.fr/nuxeo/site/esupversions/d494f35c-ba4b-4230-bb99-881df0742ab6.
Full textLes accidents de véhicules automobiles sont responsables du plus grand nombre de décès dans le monde. Les chercheurs, les constructeurs automobiles et les autorités gouvernementales internationales sont continuellement à la recherche de solutions pour résoudre ce problème. La recherche a montré que la moitié des accidents peut être évitée si le conducteur est alerté d'une collision imminente une fraction de seconde à l'avance. Un mécanisme d'alerte d'un danger proche est appelé Driver Assistance Systems (DAS). Les statistiques montrent qu'une grande majorité des accidents de véhicules se passent à la suite d'une collision frontale. Minimiser les collisions frontales devrait donc diminuer considérablement les accidents de la route. Pour prévoir une collision frontale suffisamment à l'avance, l'obstacle doit être détecté à distance. En outre, pour que le système d’aide à la conduite soit réellement efficace, une collision imminente doit être prévue en tenant compte de toutes les circonstances : par exemple plus il fait mauvais, plus ce système est nécessaire. Un capteur radar remplit les conditions préalables de détection d'obstacles à longue portée en tenant compte des conditions météorologiques. Pour déterminer si un obstacle se trouve sur une trajectoire de collision avec le véhicule équipé, sa trajectoire doit être prévue avant qu'il n’arrive près du véhicule concerné. La détermination de la trajectoire d'un objet en mouvement exige que son comportement dynamique soit suivi sur une période de temps. Dans un scénario de trafic réel, plus d'un obstacle peut être considéré comme un danger, c’est pourquoi les trajectoires d'objets multiples doivent être surveillées simultanément. Un appareil capable d'assurer de telles fonctions est appelé un système de suivi d’obstacles multiples (Multiple Target Tracking : MTT). Dans cette thèse nous proposons un système d’aide à la conduite original utilisant les principes du MTT pour suivre la dynamique d’obstacles situés à plus d’une centaine de mètres et pour éviter une collision avec le véhicule équipé. En théorie, un tel système offre une des meilleures réponses au problème des accidents de la route, mais sa mise en œuvre reste difficile à réaliser. Elle implique des calculs complexes et, par conséquent, les besoins de traitement prennent du temps. Cependant, pour aviser le conducteur d'un danger imminent en temps réel, les calculs doivent être effectués très rapidement. Nous avons alors opté pour une solution optimale utilisant des processeurs afin de partager la charge de calcul et de réduire ainsi le temps de traitement. Les processeurs multiples fonctionnant en parallèle permettent non seulement d'accélérer le calcul, mais aussi d’optimiser la consommation d’énergie du système embarqué. Nous utilisons des FPGA (Field Programmable Gate Array) comme plateforme de mise en œuvre de notre système multiprocesseur. Les FPGA offrent la souplesse nécessaire pour les systèmes embarqués en constante évolution et sont très rentables. Un système multiprocesseur réalisé dans un FPGA rend son architecture flexible et reconfigurable et les processeurs peuvent être reprogrammés si nécessaire. Ainsi les systèmes multiprocesseurs à base de FPGA garantissent une souplesse du matériel ainsi que des logiciels, et par conséquent ces systèmes deviennent facilement évolutifs (scalables). Nous optimisons l'architecture du système afin de minimiser la taille du matériel tout en respectant les délais en temps réel de l’application. La minimisation du matériel ne conduit pas seulement à réduire la consommation d'énergie du système, mais nous permet aussi d'adapter le système dans un FPGA plus réduit, ce qui joue un rôle important dans la réduction du coût du système
Blanc, Frédéric. "Etude d'un nouveau concept de calculateur reconfigurable : architecture et outils." Cergy-Pontoise, 2002. http://www.theses.fr/2002CERG0180.
Full textDue to the improvement of deep sub-microelectronic technologies, more and more transistors are available inside a die. But those improvements are difficult to exploit because of the design complexity and the time-to-market constraints. It is necessary to propose new paradigms of architecture in order to exploit future technologies. The implementation of any application requires two kinds of resources: controls which describe algorithms, operators which perform computation. A new reconfigurable architecture concepts which are suitable for both parts is proposed. The key concepts of the proposed architecture is to map controls using a mechanism called the reconfigurable cache, and to improve the processing performance with an adapted reconfigurable architecture. Furthermore this architecture allows scheduling reconfiguration processes using an event based mechanism which we call auto-reconfiguration. This thesis includes architectural consideration and a tool to manage those innovations
Heron, Olivier. "Test de pannes temporelles dans les circuits programmables de type FPGA-SRAM." Montpellier 2, 2004. http://www.theses.fr/2004MON20101.
Full textMaazouzi, Zahir. "Conception des circuits programmables par la réécriture conditionnelle et étude des aspects vectoriels des fonctions booléennes." Orléans, 2001. http://www.theses.fr/2001ORLE2042.
Full textBoulbair, Zoheir. "Implantation d'algorithmes de commande sur FPGA : une méthodologie pour les systèmes électriques." Nantes, 2005. http://www.theses.fr/2005NANT2121.
Full textFarooq, Umer. "Exploration et optimisation des architectures de circuits FPGA hétérogènes à base de structures arborescentes et dédiées aux applications spécifiques." Paris 6, 2011. http://www.theses.fr/2011PA066284.
Full textFabiani, Erwan. "Implémentation automatique de réseaux réguliers sur circuits reconfigurables." Rennes 1, 2001. http://www.theses.fr/2001REN10139.
Full textTka, Mouna. "Génération automatique de test pour les contrôleurs logiques programmables synchrones." Thesis, Université Grenoble Alpes (ComUE), 2016. http://www.theses.fr/2016GREAM020/document.
Full textThis thesis work done in the context of the FUI project Minalogic Bluesky, concerns the automated functional testing of a particular class of programmable logic controllers (em4) produced by InnoVista Sensors. These are synchronous systems that are programmed by means of an integrated development environment (IDE). People who use and program these controllers are not necessarily expert programmers. The development of software applications should be as result simple and intuitive. This should also be the case for testing. Although applications defined by these users need not be very critical, it is important to test them adequately and effectively. A simulator included in the IDE allows programmers to test their programs in a way that remains informal and interactive by manually entering test data.Based on previous research in the area of synchronous test programs, we propose a new test specification language, called SPTL (Synchronous Testing Programs Language) which makes possible to simply express test scenarios that can be executed on the fly to automatically generate test input sequences. It also allows describing the environment in which the system evolves to put conditions on inputs to arrive to realistic test data and limit unnecessary ones. SPTL facilitates this testing task by introducing concepts such as user profiles, groups and categories. We have designed and developed a prototype named "Testium", which translates a SPTL program to a set of constraints used by a Prolog solver that randomly selects the test inputs. So, generating test data is based on constraint logic programming techniques.To assess this, we experimented this method on realistic and typical examples of em4 applications. Although SPTL was evaluated on EM4, its use can be envisaged for the validation of other types of synchronous controllers or systems
Boudouani, Nassima. "Architectures reconfigurables dynamiquement : synthèse matérielle d'opérateurs de détection et d'estimation de mouvement temps réel." Cergy-Pontoise, 2004. http://www.theses.fr/2004CERG0201.
Full textThe work described in this thesis concerns the real time implementation of motion detection and estimation operators on dynamically reconfigurable FPGA. The motion detector that we studied is based on Markov fields ; it presents variable granularity and its recursive feather prevents its real time implementation. We proposed solutions to break this recursion and we suggested two types of implementations on fine-grained reconfigurable architectures : the dynamic one evaluated on AT40K40 Atmel FPGA, and the static one evaluated on XC4000 and Virtex FPGA. For each solution we detailed the data organization and management. The motion estimators studied are based in block-matching method. The difficulty of the real time implementation of the full search block-matching motion estimator is mainly due to the high quantity of data used in calculation. We evaluated different solutions used to reduce the number of operations or the number of data to process and we demonstrated that their real time implementations are possible on fine-grained reconfigurable circuits like AT40K40. For all applications, we proposed partitioning which takes into account constraints like available computing area, data parallelism, memory bandwidth, and data dependencies between successive configurations. These operators contribute to the Ardoise (Architecture reconfigurable dynamiquement orientée image et signal embarquée) library elaboration and can be used like basics components in other applications like video compression
Abel, Nicolas. "Outils et méthodes pour les architectures reconfigurables dynamiquement à grain fin : Synthèse et gestion automatique des flux de données." Cergy-Pontoise, 2006. http://biblioweb.u-cergy.fr/theses/06CERG0301.pdf.
Full textThis thesis presents tools and methodologies dedicated to fine grain dynamically reconfigurable architectures. In the first part, after studying this reconfiguration mode, we describe a tool set improving dynamical reconfiguration implementation. Firstly, we optimize configuration storage and reconfiguration duration proposing software compressing tools and hardware reconfiguration module. We finish studying the system management of the reconfigurable area. The system, developed with a high level language, makes configurations scheduling flexible. In the second part, we focus on the data flow automatic management. We base this on the separation of treatment modules and data flow managing modules. The second is totally directed by the developing tools and the managing system. In this way, the system has a treatment library and all the tools necessary to interconnect and schedule treatments in real time. The whole studied concepts have been implemented on ARDOISE architecture
Boivin, Benoît. "Commande numérique d'un gyromètre vibrant." Poitiers, 2004. http://www.theses.fr/2004POIT2299.
Full textLegrand, Thomas. "Les réseaux de paquets optiques en mode « burst » : la résolution de leurs contentions." Rennes 1, 2009. http://www.theses.fr/2009REN1S146.
Full textThis thesis presents a new OBS architecture called “Label-Switched OBS” and numerically compares its performances with the ones of conventional OBS and Offset Time Emulated OBS. This thesis discusses burst contention resolution mechanisms in spectrum and time domain for these three network architectures as well as routing issues. The thesis introduces a new scheduling algorithm and compares it with the Latest Available Unused Channel with Void Filling algorithm. The experimental part of this thesis describes our test bed based on a Label-Switched OBS core node. It provides the means to investigate burst contention resolution mechanisms in spectrum and time domain. Our experimental results confirm the node capability to resolve the burst contentions, in spectrum and time domain
Bricas, Gaëtan. "Radiation reliability analysis of FPGA-based systems : testing methodologies and analytical approaches." Electronic Thesis or Diss., Université de Montpellier (2022-....), 2022. http://www.theses.fr/2022UMONS070.
Full textThis work focuses on testing methodologies to analyze the radiation sensitivity of FPGA-based systems. Due to their flexibility, the reliability analysis on these components is a challenging task as the radiation sensitivity is entirely conditioned by the implemented system. Indeed, it depends on the one hand on the intrinsic sensitivity of the component (to both TID and SEEs) and, on the other hand, on the way the different induced perturbations can impact the operation of the implemented system. State-of-the-art methodologies have shown a number of limitations in bridging the intrinsic sensitivity of the FPGA and the one of the implemented systems. The objective of this thesis is to improve radiation testing methodologies to overcome these limitations.Concerning TID effects, a new testing methodology is proposed. Its main contribution is to extend the evaluation of parametric degradations to all logical and routing resources of the component. For this purpose, specific benchmarking structures have been developed to measure the propagation delay deviation of each type of logical and routing resource. A new technique to measure the propagation delay in real time and with limited external instrumentation is also proposed. X-ray radiation tests have been performed on three FPGA families to highlight the benefits of this methodology.As for SEE, the proposed testing methodology lies between the two traditional accelerated particle beam testing approaches (primitive level testing and final application testing) by proposing a sensitivity evaluation at a higher level of granularity. The basic idea is to instantiate a set of dedicated benchmarking structures, simple enough to provide a good testability (low error masking, traversable state spaces) while sufficiently complex to provide a good representativity of the circuits effectively implemented on FPGAs. The benchmarks selected in this study are based on arithmetic operations. By using different implementations of the same arithmetic functions with a large diversity in the circuit parameters, and in the use of resources, the radiation tests fulfill a multifaceted purpose. First, the test results provide extensive information to identify and understand the different failure mechanisms and their predominance; second, it allows to qualitatively evaluate the impact of different types of resources on the global system sensitivity and to quantitatively compare the sensitivity of different implementations of the same logic function and the effectiveness of mitigation solutions. Finally, it provides a set of guidelines for designers to improve the reliability of FPGA-based systems. Several neutron and proton beam tests have been performed to demonstrate the advantages of this approach.The main limitation of radiation testing lies with the difficulty to extrapolate the results of tests performed with a given implemented circuit to estimate the sensitivity of any other circuit. To address these limitations, a new software-based approach has been developed to estimate the susceptibility of circuits implemented on SRAM based FPGA to configuration memory corruptions. This analytical approach uses the physical netlist of the circuit and explores the different nodes and logical resources that compose it to extract all the configuration bits that are critical for the system operation. The main contribution of this approach is to take into account the workload of the circuit, extracted from logic simulation, to analyze the propagation of errors and thus filter among the set of potentially critical configuration bits, those that actually modify the output signals of the system. The efficiency of this approach is validated through fault injection and proton experiment
Zhang, Linlin. "Architecture reconfigurable pour l'analyse d'images spectrales." Saint-Etienne, 2009. http://www.theses.fr/2009STET4022.
Full textThe aim of this thesis is to propose a parameterized architecture for the spectral image applications implemented in Field-programmable gate array (FPGA). The parameterization of the architecture concerns the choice of data processing algorithms and the communication requirements. The global architecture is constructed by using existing IP (Intellectual Property) blocks with the interconnection between them. The architecture can meet most of the image analysis algorithms’ requirements by a minimum adaptation (modification) of the blocks and the interconnections. The communication requirements are important for the image analysis applications. This work is focused on efficient communication architecture design and its adaptability to the algorithms’ requirements. The proposed communication architectures are based on a Network on Chip (NoC) structure, which is considered as the most adaptable and flexible communication architecture at the moment. The context of the research is focused on the spectral image authentication by using spectral image analysis algorithms. A set of parameterized NoC architectures is proposed and evaluated for this application. These architectures have the main required characteristics dedicated to the image authentication process. A Design Space Exploration (DSE) principle is employed for the implementation of the five versions of Time Division Multiplexing (TDM) NoC on FPGA. It allows to identify the ressources and to estimate the achieved performance, in order to determine the best communication structures which reply to the requirements of the targeted applications
Bonté, Eric. "Calcul des extensions dans les théories de défauts en réseau : Application au raisonnement à profondeur variable." Paris 13, 1992. http://www.theses.fr/1992PA132015.
Full textGabourin, Stéphane. "Etude et modélisation du comportement du FPGA A54SX72A d'Actel en milieu radiatif et à températures contrôlées : application à l'environnement du LHC." Chambéry, 2007. http://www.theses.fr/2007CHAMS006.
Full textThe Large Hadrons Collider (LHC) at CERN (Geneva) will provide proton-proton collisions at center of mass energy of 14 TeV. The beam bending and trajectory in the 27 km ring is maintained by superconducting dipole magnets at 1. 9 K. The temperature and pressure readout electronic cards should be placed under the dipole magnets due to sensors fed with currents not exceeding 1μA. The main digital component, embedded in the cards, is an integrated circuit (IC) of type FPGA A54SX72A from Actel (CMOS technology) whose purpose is signal filtering and analysis. Depending of the location along the 27 km accelerator ring, the readout cards will be exposed to different amount of radiation, and at different functioning temperatures. The main goal of my thesis is to model the behavior of the IC, i. E. The electrical current consumption of the IC and the rate of TTL logic errors, taking into account simultaneously both temperature and amount of irradiation. These two parameters are monitored with accurate continuous measurements. The model is empirical and it is built such as to reproduce the measurements and their correlations. The first set of measurements, performed with X-ray radiations, allows the study of dose effects in the silicon dioxide. The second test campaign, performed with a proton beam, allows the study of the IC single events cross sections as a function of the dose and the temperature. The results of theses studies allows to build a model able to predict the behavior of any given readout card in the LHC tunnel. This allows designing a maintenance plan of the readout system in the tunnel. The model is characterized by an equation which describes the functioning time of the IC versus the temperature and the dose rate for X-ray irradiations, i. E. Only for the dose effect. The equivalence with protons has been determined by measurements with a proton beam at energy of 63 MeV. The protons appear to be 8 times harder than X-rays for the equivalent dose rate
He, Michel. "Contribution à l'étude de l'impact des nanotechnologies sur les Architectures : Apprentissage d'inspiration neuronale de fonctions logiques pour circuits programmables." Phd thesis, Université Paris Sud - Paris XI, 2008. http://tel.archives-ouvertes.fr/tel-00422144.
Full textBouchard, Sandra. "Etude d'une méthodologie d'implantation de fonctions logiques adaptées au traitement d'images dans un FPGA." Dijon, 1999. http://www.theses.fr/1999DIJOS061.
Full textPerez, Castañeda Oscar Leopoldo. "Modélisation des effets de la reconfiguration dynamique sur la flexibilité d'une architecture de traitement temps réel." Nancy 1, 2007. http://www.theses.fr/2007NAN10139.
Full textThe principal contribution of the wired logic compared to the microprocessor is the degree of parallelism which is in higher several orders of magnitude. However, the property of configurability of these circuits involves an additionnal cost in term of silicon surface, delay and power consumption compared to circuits ASICs. The dynamic reconfiguration of the FPGA is often presented in the literature like a means of increasing their flexibility, to approach that of the microprocessors, while preserving a level of performance that if not is close to the ASIC is higher than of the microprocessors. If the performance is in general, for a given application, more easy to quantify, the situation is quite different for flexibility. In the litterature this metric has never been defined and quantified. Moreover we did not find any definition of the flexibility of an architecture for processing of data. The principal objective of this work is by one hand, to define and quantify the flexibility and by the other hand, to model the influence of the dynamic reconfiguration on flexibility. We put at the disposition the designer a metric as well as the bases of methodology allowing it to choose or not this solution according to its constraints and objectives
Colancon, Stéphane. "Conception de systèmes analogiques : méthodologie et environnement de prototypage." Montpellier 2, 2001. http://www.theses.fr/2001MON20181.
Full textFaure, Philippe. "Test orienté utilisateur des circuits configurables de type FGPA à base de SRAM." Montpellier 2, 2002. http://www.theses.fr/2002MON20136.
Full textHarb, Naim. "Dynamically and Partially Reconfigurable Embedded System Architecture for Automotive and Multimedia Applications." Valenciennes, 2011. http://ged.univ-valenciennes.fr/nuxeo/site/esupversions/1810c575-b28e-4817-a3be-f0527631eabd.
Full textShort time-to-market windows, high design and fabricationcosts, and fast changing standards of application-specificprocessors, make them a costly and risky investment for embedded system designers. To overcome these problems, embedded system designersare increasingly relying on Field Programmable Gate Arrays(FPGAs) as target design platforms. FPGAs are generally slower and consumemore power than application-specific integrated circuits(ASICs), and this can restrict their use to limited applicationdomains. However, recent advances in FPGA architectures,such as dynamic partial reconfiguration (DPR), are helpingbridge this gap. DPR reduces area and enables mutually exclusive subsystemsto share the same physical space on a chip. It also reducescomplexity, which usually results in faster circuits and lowerpower consumption. The work in this PhD targets first a Driver Assistant System (DAS) system based on a Multiple Target Tracking (MTT) algorithm as our automotive base system. We present a dynamically reconfigurable filtering hardwareblock for MTT applications in DAS. Our system shows thatthere will be no reconfiguration overhead because the systemwill still be functioning with the original configuration until thesystem reconfigures itself. The free reconfigurable regions canbe implemented as improvement blocks for other DAS systemfunctionalities. Two approaches were used to design the filtering block according to driving conditions. We then target another application on the basis of DPR, the H. 264 encoder as a multimedia system. Regarding the H. 264 multimedia system, we propose a reconfigurable H. 264 Motion Estimation (ME) unit whose architecture can be modified to meet specific energy and image quality constraints. By using DPR, we were able to support multiple configurations each with different levels of accuracy and energy consumption. Image accuracy levels were controlled via application demands, user demands or support demands
Talbi, El-Ghazali. "Allocation de processus sur les architectures parallèles à mémoire distribuée." Grenoble INPG, 1993. http://www.theses.fr/1993INPG0070.
Full textKebe, Ahmed. "Implémentation sur FPGA de l'algorithme MUSIC sur antenne-réseau expérimentale à 10 GHz." Master's thesis, Université Laval, 2016. http://hdl.handle.net/20.500.11794/27285.
Full textThe techniques of Directions of Arrival (DOA) are a promising way to increase the capacity of systems and telecommunications services to better estimate the mobile-radio channel. They allow precise monitoring of cellular users to orient the antenna beams at them. Therefore, in this context, this paper describes step by step implementation of the high-level algorithm MUSIC (Multiple SIgnal Classification) on an FPGA platform to determine in real time the angle of arrival of one or incident sources to an antenna array. The Rapid Control Prototyping (RCP) with the tools of XilinxTM System generator (XSG) and MBDK (Model Based Design Kit) of NutaqTM is the development concept used. This concept is based on a high level programming code through models, to automatically generate a low-level code. A special attention is devoted to the method chosen to solve the eigenvalues decomposition problem for the complex autocorrelation matrix by Jacobi algorithm. The architecture designed implementing it in FPGA (Field Programmable Gate Array) is detailed. Furthermore, it is proved that MUSIC can perform an interesting estimate of the position of the sources without prior calibration of the antenna array. Thus, the calibration technique G matrix used in this project is presented, in addition to the implementation model. Finally, the experimental results of the system tested in a real environment in the presence of one source then two highly correlated sources are illustrated and analyzed.
Kouadri, Mostéfaoui Abdellah Medjadji. "Architectures Flexibles pour la Validation et L'exploration de Réseaux-sur-Puce." Grenoble INPG, 2009. https://tel.archives-ouvertes.fr/tel-00431799.
Full textFor A multiprocessor system-on-chip (MPSOC), the communication backbone is a central component of prime importance. This is due to the importance of the communications on such distributed systems. Now that networks-on-chip (NoCs) are admitted to be the solution which theoretically best solves the problem of on-chip communications, an important problem which rises consists in providing the designer with fast validation techniques able to tackle such complexes systems. Indeed, despite their regular architectures networks-in-chip internal interactions are difficult to formalize. On the other side, classical validation approaches are far from being suited for NoC-based systems due to their lack of flexibility and scalability. This thesis introduces a new concept in the field of hardware validation of networkson- chip; we have called this new concept “Inaccurate Hardware Emulation” in contrast with most hardware emulation approaches which assume a “cycle accurate bit accurate” precision. Our approach inherits from all advantages of hardware prototyping on reconfigurable devices and adds new scalability features. Study conducted during this thesis showed that under the non-congested regime a NoC may admit a number of alterations on its characteristics (introduced by the emulation platform) without adopting a completely different behavior. The multi-FPGA emulation technique proposed in this thesis is highly flexible since it relies on serial inter-FPGA interconnections. Serial interconnections are less sensitive to noises than parallel style of interconnections, and allow then for higher transfer rates. On the other hand, our emulation approaches does not poses any constraint on the emulation speed. If we consider the fact that serial interconnection schemes may introduce additional delays and the high speeds of the emulation process, performance of the NoC being emulated on the multi-FPGA emulator may deviate from the original NoC. We have studied this phenomenon and we have proposed various solutions for it
Bhasin, Shivam. "Contre-mesures au niveau logique pour sécuriser les architectures de crypto-processeurs dans les FPGA." Paris, Télécom ParisTech, 2011. https://pastel.hal.science/pastel-00683079.
Full textModern field programmable gate arrays (FPGA) are capable of implementing complex system on chip (SoC) and providing high performance. Therefore, FPGAs are finding wide application. A complex SoC generally contains embedded cryptographic cores to encrypt/decrypt data to ensure security. These cryptographic cores are computationally secure but their physical implementations can be compromised using side channel attacks (SCA) or fault attacks (FA). This thesis focuses on countermeasures for securing cryptographic cores on FPGAs. First, a register-transfer level countermeasure called ``Unrolling'' is proposed. This hiding countermeasure executes multiple rounds of a cryptographic algorithm per clock which allows deeper diffusion of data. Results show excellent resistance against SCA. This is followed by dual-rail precharge logic (DPL) based countermeasures, which form a major part of this work. Wave dynamic differential logic (WDDL), a commonly used DPL countermeasure well suited for FPGAs is studied. Analysis of WDDL (DPL in general) against FA revealed that it is resistant against a majority of faults. Therefore, if flaws in DPL namely early propagation effect (EPE) and technological imbalance are fixed, DPL can evolve as a common countermeasure against SCA and FA. Continuing on this line of research we propose two new countermeasures: DPL without EPE and Balanced-Cell based DPL (BCDL). Finally advanced evaluation tools like stochastic model, mutual information and combined attacks are discussed which are useful when analyzing countermeasures
Sahade, Mohamad. "Un démonstrateur automatique basé sur la méthode de tableaux pour les logiques modales : implémentation et études de stratégies." Toulouse 3, 2006. http://www.theses.fr/2006TOU30055.
Full textDuhem, François. "Méthodologie de conception d'architectures reconfigurables dynamiquement pour des applications temps-réel." Nice, 2012. http://www.theses.fr/2012NICE4062.
Full textDespite promising capabilities, FPGAs partial reconfiguration feature is not anchored in the industry yet, mostly for two reasons. First of all, Xiling controller shows low performance and might introduce a large time overhead compared to the task period, incompatible with the use of partial reconfiguration. Also, developing such a dynamic application requires an extra design effort compared to a static solution for developing scheduling strategies. Indeed, it is impossible to evaluate architecture and/or a scheduling algorithm to verify that real-time constraints are met before the implementation step. This thesis offers solutions to the issues previously mentioned. We will first introduce FaRM, a Fast Reconfiguration Manager reaching partial reconfiguration theoretical limits thanks to an efficient compression algorithm and an optimized architecture. Then, we present RecoSim, a high-level SystemC simulator for reconfigurable architectures. It makes use of FaRM reconfiguration overhead cost model to allow for developing and verifying SystemS compliant with Xilinx partial reconfiguration design flow. This work was carried out in the framework of project ARDMAHN, sponsored by the French National Research Agency
Dagues, Bruno. "Conception et réalisation d'un générateur automatique de programmes de simulation SOSIE : application aux ensembles convertisseurs-machines-commandes." Toulouse, INPT, 1990. http://www.theses.fr/1990INPT014H.
Full textBrevier, Robert. "Admittance-mètre large bande programmable utilisant une méthode de comparaison : application à la caractérisation de composants semiconducteurs." Toulouse, INPT, 1987. http://www.theses.fr/1987INPT083H.
Full textBilavarn, Sébastien. "Exploration architecturale au niveau comportemental : application aux FPGAs." Lorient, 2002. http://www.theses.fr/2002LORIS012.
Full textA significant factor in the evolution of modern electronic systems is the appearance of new architectures based on the programming of hardware components such as Field programmable Gate Arrays (FPGAs). The introduction of those components as an alternative computation unit and the flexibility they offer increase the interest of suche an integration solution. Moreover, the recent evolutions of the different families allow today the implementation of complex systems with higher constraints on performances. Few works focus on the estimation of an application on a technology of this type. Until now, researchers mainly carried their efforts on the imrpovement of reconfigurable architectures in order to make them powerful and thus to constitute an alternative to ASICs (Application Specific Integrated Circuits). The objective of the work presented in this thesis is to propose techniques and tools associated on programmable architectures. The developed method is generic (it can be applied to several FPGA families) and is located at the behavioral level. It allows the browsing of several architectural solutions and is integrated in a hardware : software codesign methodology
Ildevert, Michel. "Auto-test intégré de PLAs CMOS dynamiques." Montpellier 2, 1992. http://www.theses.fr/1992MON20133.
Full textSoni, Hardik. "Une approche modulaire avec délégation de contrôle pour les réseaux programmables." Thesis, Université Côte d'Azur (ComUE), 2018. http://www.theses.fr/2018AZUR4026/document.
Full textNetwork operators are facing great challenges in terms of cost and complexity in order to incorporate new communication technologies (e.g., 4G, 5G, fiber) and to keep up with increasing demands of new network services to address emerging use cases. Softwarizing the network operations using SoftwareDefined Networking (SDN) and Network Function Virtualization (NFV) paradigms can simplify control and management of networks and provide network services in a cost effective way. SDN decouples control and data traffic processing in the network and centralizes the control traffic processing to simplify the network management, but may face scalability issues due to the same reasons. NFV decouples hardware and software of network appliances for cost effective operations of network services, but faces performance degradation issues due to data traffic processing in software. In order to address scalability and performance issues in SDN/NFV, we propose in the first part of the thesis, a modular network control and management architecture, in which the SDN controller delegates part of its responsibilities to specific network functions instantiated in network devices at strategic locations in the infrastructure. We have chosen to focus on a modern application using an IP multicast service for live video streaming applications (e.g., Facebook Live or Periscope) that illustrates well the SDN scalability problems. Our solution exploits benefits of the NFV paradigm to address the scalability issue of centralized SDN control plane by offloading processing of multicast service specific control traffic to Multicast Network Functions (MNFs) implemented in software and executed in NFV environment at the edge of the network. Our approach provides smart, flexible and scalable group management and leverages centralized control of SDN for Lazy Load Balance Multicast (L2BM) traffic engineering policy in software defined ISP networks. Evaluation of this approach is tricky, as real world SDN testbeds are costly and not easily available for the research community. So, we designed a tool that leverages the huge amount of resources available in the grid, to easily emulate such scenarios. Our tool, called DiG, takes into account the physical resources (memory, CPU, link capacity) constraints to provide a realistic evaluation environment with controlled conditions. Our NFV-based approach requires multiple application specific functions (e.g., MNFs) to control and manage the network devices and process the related data traffic in an independent way. Ideally, these specific functions should be implemented directly on hardware programmable routers. In this case, new routers must be able to execute multiple independently developed programs. Packet-level programming language P4, one of the promising SDN-enabling technologies, allows applications to program their data traffic processing on P4 compatible network devices. In the second part of the thesis, we propose a novel approach to deploy and execute multiple independently developed and compiled applications programs on the same network device. This solution, called P4Bricks, allows multiple applications to control and manage their data traffic, independently. P4Bricks merges programmable blocks (parsers/deparsers and packet processing pipelines) of P4 programs according to processing semantics (parallel or sequential) provided at the time of deployment
Boyer, Michel. "Étude et réalisation d'un ASIC dédié à la commande des convertisseurs à résonance série non réversibles : commande par trajectoire optimale." Toulouse, INPT, 1996. http://www.theses.fr/1996INPT074H.
Full textAmiot, Franck. "Vers une architecture parallèle reconfigurable dédiée au traitement d'image et à la vision." Rouen, 2000. http://www.theses.fr/2000ROUES077.
Full textBoussaid, Lotfi. "Etude et implémentation de descripteurs de contenu AV pour les applications multimedia temps réel." Dijon, 2006. http://www.theses.fr/2006DIJOS049.
Full textThe works presented in this thesis contribute to the design of embedded electronic systems which are dedicated for real time multimedia applications. They fall within the framework of design methodology of the new hardware and/or software architecture used for analysis and description of audiovisual content. In this thesis we are first interested in the validation and optimization of shot boundary detection algorithms and in the extraction of high level semantic information using low level audiovisual descriptors. After that, we present the solutions of hardware and/or software implementation related to cut and dissolve detectors at different abstraction levels (logic, RTL and high level based platform). In the last part of this thesis, we propose a generic architecture template for audiovisual content analysis and description. The transposition of this template on embedded systems became possible with the evolution of recently marketed FPGA and the new tools and methodology used on system on programmable chip (SOPC)
Killian, Cédric. "Réseaux embarqués sur puce reconfigurable dynamiquement et sûrs de fonctionnement." Electronic Thesis or Diss., Université de Lorraine, 2012. http://www.theses.fr/2012LORR0396.
Full textThe need of performance of embedded Syxtena-on-Chlps (Socs) are increasing constantly to meet the requirements of applications becoming more and more complexes, and new processing architectures and new computing paradigms have emerged. The integration within a single chip of dozens, or hundreds of computing and processing elements has given birth to Mukt1 Pmcesmr Systena-on-Chp (MPSoC) allowing to feature a high level of parallel processing. Nowaday s, the performance of these systems rely on the communication medium between the interconnected processing elements. The problematic of the communication medium to feature a high bandwidth and flexibility is primordial in order to efficiently use the parallel processing capacity of the MPSoC In this context, Network-on-Chlps (NoCs) are developed where the aim is to allow the interconnection of a large number of elements in the same device while maintaining a tradeoff between performance and logical resources. Moreover, the emergence of the partial reconfigurable FPGA technology allows to the MPSoC to adapt their elements during its operation in order to meet the system requirements. Given this increasing complexity of the electronic systems and the shrinking size of the devices, the sensibility of the chip against phenomena generating fault has increased. Thereby, to design efficient and reliable Socs, new error detection and localization techniques must be proposed for the dynamic NoCs where the main difficulty is the identification and the distinction between real errors and adaptive behavior of the NoCs. In this context, we present new mechanisms and architectural solutions allowing to check during the system operation the correctness of dynamic NoCs in order to locate and isolate efficiently the faulty components avoiding a failure of the system