Дисертації з теми "Passage à message"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-44 дисертацій для дослідження на тему "Passage à message".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте дисертації для різних дисциплін та оформлюйте правильно вашу бібліографію.
Genaud, Stéphane. "Exécutions de programmes parallèles à passage de messages sur grille de calcul." Habilitation à diriger des recherches, Université Henri Poincaré - Nancy I, 2009. http://tel.archives-ouvertes.fr/tel-00440503.
Повний текст джерелаSabah, Quentin. "Siaam : Simple Isolation for an Actor-based Abstract Machine." Thesis, Grenoble, 2013. http://www.theses.fr/2013GRENM082/document.
Повний текст джерелаIn this thesis we study state isolation and efficient message-passing in the context of concurrent object-oriented programming. The ’ownership’ and ’reference uniqueness’ techniques have been extensively employed to address concurrency safety in the past. Strikingly the vast majority of the previous works rely on a set of statically checkable typing rules, either requiring an annotation overhead or introducing strong restrictions on the shape and the aliasing of the exchanged messages.Our contribution with SIAAM is the demonstration of a purely runtime, actor-based, annotation-free, aliasing-proof approach to concurrent state isolation allowing efficient communication of arbitrary objects graphs. We present the formal semantic of SIAAM, along with a machine-checked proof of isolation. An implementation of the model has been realized in a state-of-the-art Java virtual-machine and a set of custom static analyses automatically reduce the runtime overhead
Kumar, Ratnesh. "Segmentation vidéo et suivi d'objets multiples." Thesis, Nice, 2014. http://www.theses.fr/2014NICE4135/document.
Повний текст джерелаIn this thesis we propose novel algorithms for video analysis. The first contribution of this thesis is in the domain of video segmentation wherein the objective is to obtain a dense and coherent spatio-temporal segmentation. We propose joining both spatial and temporal aspects of a video into a single notion Fiber. A fiber is a set of trajectories which are spatially connected by a mesh. Fibers are built by jointly assessing spatial and temporal aspects of the video. Compared to the state-of-the-art, a fiber based video segmentation presents advantages such as a natural spatio-temporal neighborhood accessor by a mesh, and temporal correspondences for most pixels in the video. Furthermore, this fiber-based segmentation is of quasi-linear complexity w.r.t. the number of pixels. The second contribution is in the realm of multiple object tracking. We proposed a tracking approach which utilizes cues from point tracks, kinematics of moving objects and global appearance of detections. Unification of all these cues is performed on a Conditional Random Field. Subsequently this model is optimized by a combination of message passing and an Iterated Conditional Modes (ICM) variant to infer object-trajectories. A third, minor, contribution relates to the development of suitable feature descriptor for appearance matching of persons. All of our proposed approaches achieve competitive and better results (both qualitatively and quantitatively) than state-of-the-art on open source datasets
Glück, Olivier. "Optimisations de la bibliothèque de communication MPI pour machines parallèles de type " grappe de PCs " sur une primitive d'écriture distante." Paris 6, 2002. http://www.theses.fr/2002PA066158.
Повний текст джерелаGabrié, Marylou. "Towards an understanding of neural networks : mean-field incursions." Thesis, Paris Sciences et Lettres (ComUE), 2019. http://www.theses.fr/2019PSLEE035.
Повний текст джерелаMachine learning algorithms relying on deep new networks recently allowed a great leap forward in artificial intelligence. Despite the popularity of their applications, the efficiency of these algorithms remains largely unexplained from a theoretical point of view. The mathematical descriptions of learning problems involves very large collections of interacting random variables, difficult to handle analytically as well as numerically. This complexity is precisely the object of study of statistical physics. Its mission, originally pointed towards natural systems, is to understand how macroscopic behaviors arise from microscopic laws. In this thesis we propose to take advantage of the recent progress in mean-field methods from statistical physics to derive relevant approximations in this context. We exploit the equivalences and complementarities of message passing algorithms, high-temperature expansions and the replica method. Following this strategy we make practical contributions for the unsupervised learning of Boltzmann machines. We also make theoretical contributions considering the teacher-student paradigm to model supervised learning problems. We develop a framework to characterize the evolution of information during training in these model. Additionally, we propose a research direction to generalize the analysis of Bayesian learning in shallow neural networks to their deep counterparts
Barbier, Jean. "Statistical physics and approximate message-passing algorithms for sparse linear estimation problems in signal processing and coding theory." Sorbonne Paris Cité, 2015. http://www.theses.fr/2015USPCC130.
Повний текст джерелаThis thesis is interested in the application of statistical physics methods and inference to signal processing and coding theory, more precisely, to sparse linear estimation problems. The main tools are essentially the graphical models and the approximate message-passing algorithm together with the cavity method (referred as the state evolution analysis in the signal processing context) for its theoretical analysis. We will also use the replica method of statistical physics of disordered systems which allows to associate to the studied problems a cost function referred as the potential of free entropy in physics. It allows to predict the different phases of typical complexity of the problem as a function of external parameters such as the noise level or the number of measurements one has about the signal: the inference can be typically easy, hard or impossible. We will see that the hard phase corresponds to a regime of coexistence of the actual solution together with another unwanted solution of the message passing equations. In this phase, it represents a metastable state which is not the true equilibrium solution. This phenomenon can be linked to supercooled water blocked in the liquid state below its freezing critical temperature. Thanks to this understanding of blocking phenomenon of the algorithm, we will use a method that allows to overcome the metastability mimicing the strategy adopted by nature itself for supercooled water: the nucleation and spatial coupling. In supercooled water, a weak localized perturbation is enough to create a crystal nucleus that will propagate in all the medium thanks to the physical couplings between closeby atoms. The same process will help the algorithm to find the signal, thanks to the introduction of a nucleus containing local information about the signal. It will then spread as a "reconstruction wave" similar to the crystal in the water. After an introduction to statistical inference and sparse linear estimation, we will introduce the necessary tools. Then we will move to applications of these notions. They will be divided into two parts. The signal processing part will focus essentially on the compressed sensing problem where we seek to infer a sparse signal from a small number of linear projections of it that can be noisy. We will study in details the influence of structured operators instead of purely random ones used originally in compressed sensing. These allow a substantial gain in computational complexity and necessary memory allocation, which are necessary conditions in order to work with very large signals. We will see that the combined use of such operators with spatial coupling allows the implementation of an highly optimized algorithm able to reach near to optimal performances. We will also study the algorithm behavior for reconstruction of approximately sparse signals, a fundamental question for the application of compressed sensing to real life problems. A direct application will be studied via the reconstruction of images measured by fluorescence microscopy. The reconstruction of "natural" images will be considered as well. In coding theory, we will look at the message-passing decoding performances for two distincts real noisy channel models. A first scheme where the signal to infer will be the noise itself will be presented. The second one, the sparse superposition codes for the additive white Gaussian noise channel is the first example of error correction scheme directly interpreted as a structured compressed sensing problem. Here we will apply all the tools developed in this thesis for finally obtaining a very promising decoder that allows to decode at very high transmission rates, very close of the fundamental channel limit
Taftaf, Ala. "Développements du modèle adjoint de la différentiation algorithmique destinés aux applications intensives en calcul." Thesis, Université Côte d'Azur (ComUE), 2017. http://www.theses.fr/2017AZUR4001/document.
Повний текст джерелаThe adjoint mode of Algorithmic Differentiation (AD) is particularly attractive for computing gradients. However, this mode needs to use the intermediate values of the original simulation in reverse order at a cost that increases with the length of the simulation. AD research looks for strategies to reduce this cost, for instance by taking advantage of the structure of the given program. In this work, we consider on one hand the frequent case of Fixed-Point loops for which several authors have proposed adapted adjoint strategies. Among these strategies, we select the one introduced by B. Christianson. We specify further the selected method and we describe the way we implemented it inside the AD tool Tapenade. Experiments on a medium-size application shows a major reduction of the memory needed to store trajectories. On the other hand, we study checkpointing in the case of MPI parallel programs with point-to-point communications. We propose techniques to apply checkpointing to these programs. We provide proof of correctness of our techniques and we experiment them on representative CFD codes
Diakhaté, François. "Contribution à l'élaboration de supports exécutifs exploitant la virtualisation pour le calcul hautes performances." Phd thesis, Université Sciences et Technologies - Bordeaux I, 2010. http://tel.archives-ouvertes.fr/tel-00798832.
Повний текст джерелаRocha, barbosa Cassandra. "Coordination et ordonnancement de tâches à grains fins entre environnements d'exécution HPC." Electronic Thesis or Diss., Reims, 2023. http://www.theses.fr/2023REIMS016.
Повний текст джерелаSupercomputers are becoming more and more complex to use. This is why the use of so-called hybrid programming models, MPI + X, are being implemented in applications. These new types of models allow a more efficient use of a supercomputer, but also create new problems during the execution of applications. These problems are of different types.More specifically, we will study three problems related to MPI + X programming. The progression of non-blocking MPI communications within the X environment. Then two types of possible imbalance in MPI+X applications. The first being between MPI processes and the second within an MPI process, i.e., imbalance within X.A solution in the case of an X environment in recursive tasks will first be presented for the MPI communication progress problem using progress task insertion in the X environment. For the imbalance between MPI processes, a solution for resource rebalancing within a node will be presented. Finally, for the imbalance in the X environment, a solution to use the imbalance to run a second application will also be presented
De, Bacco Caterina. "Decentralized network control, optimization and random walks on networks." Thesis, Paris 11, 2015. http://www.theses.fr/2015PA112164/document.
Повний текст джерелаIn the last years several problems been studied at the interface between statistical physics and computer science. The reason being that often these problems can be reinterpreted in the language of physics of disordered systems, where a big number of variables interacts through local fields dependent on the state of the surrounding neighborhood. Among the numerous applications of combinatorial optimisation the optimal routing on communication networks is the subject of the first part of the thesis. We will exploit the cavity method to formulate efficient algorithms of type message-passing and thus solve several variants of the problem through its numerical implementation. At a second stage, we will describe a model to approximate the dynamic version of the cavity method, which allows to decrease the complexity of the problem from exponential to polynomial in time. This will be obtained by using the Matrix Product State formalism of quantum mechanics. Another topic that has attracted much interest in statistical physics of dynamic processes is the random walk on networks. The theory has been developed since many years in the case the underneath topology is a d-dimensional lattice. On the contrary the case of random networks has been tackled only in the past decade, leaving many questions still open for answers. Unravelling several aspects of this topic will be the subject of the second part of the thesis. In particular we will study the average number of distinct sites visited during a random walk and characterize its behaviour as a function of the graph topology. Finally, we will address the rare events statistics associated to random walks on networks by using the large-deviations formalism. Two types of dynamic phase transitions will arise from numerical simulations, unveiling important aspects of these problems. We will conclude outlining the main results of an independent work developed in the context of out-of-equilibrium physics. A solvable system made of two Brownian particles surrounded by a thermal bath will be studied providing details about a bath-mediated interaction arising for the presence of the bath
Benkahla-Aktouf, Oum-el-Kheir. "Diagnostic des architectures parallèles à passage de messages." Grenoble INPG, 1997. http://www.theses.fr/1997INPG0063.
Повний текст джерелаDamez, Lionel. "Approche multi-processeurs homogènes sur System-on-Chip pour le traitement d'image." Phd thesis, Université Blaise Pascal - Clermont-Ferrand II, 2009. http://tel.archives-ouvertes.fr/tel-00724443.
Повний текст джерелаAktouf, Chouki, and Guy Mazaré. "Test fonctionnel et reconfiguration d'architectures massivement parallèles à passage de messages." Grenoble INPG, 1995. http://www.theses.fr/1995INPG0001.
Повний текст джерелаBoisvert, Sébastien. "Assemblage adaptatif de génomes et de méta-génomes par passage de messages." Thesis, Université Laval, 2014. http://www.theses.ulaval.ca/2014/30598/30598.pdf.
Повний текст джерелаGenerally speaking, current processes – industrial, for direct-to-consumers, or researchrelated – yield far more data than humans can manage. Big Data is a trend of its own and concerns itself with the betterment of humankind through better understanding of processes and systems. To achieve that end, the mean is to leverage massive amounts of big data in order to better comprehend what they contain, mean, and imply. DNA sequencing is such a process and contributes to the discovery of knowledge in genetics and other fields. DNA sequencing instruments are parallel objects and output unprecedented volumes of data. Computer infrastructures, cloud and other means of computation open the door to the analysis of data stated above. However, they need to be programmed for they are not acquainted with natural languages. Massively parallel software must match the parallelism of supercomputers and other distributed computing systems before attempting to decipher big data. Message passing – and the message passing interface – allows one to create such tools, and a granular design of blueprints consolidate production of results. Herein, a line of products that includes RayPlatform, Ray (which includes workflows called Ray Meta and Ray Communities for metagenomics) and Ray Cloud Browser are presented. Its main application is scalable (adaptive) assembly and profiling of genomes using message passing.
Aubin, Benjamin. "Mean-field methods and algorithmic perspectives for high-dimensional machine learning." Thesis, université Paris-Saclay, 2020. http://www.theses.fr/2020UPASP083.
Повний текст джерелаAt a time when the use of data has reached an unprecedented level, machine learning, and more specifically deep learning based on artificial neural networks, has been responsible for very important practical advances. Their use is now ubiquitous in many fields of application, from image classification, text mining to speech recognition, including time series prediction and text analysis. However, the understanding of many algorithms used in practice is mainly empirical and their behavior remains difficult to analyze. These theoretical gaps raise many questions about their effectiveness and potential risks. Establishing theoretical foundations on which to base numerical observations has become one of the fundamental challenges of the scientific community. The main difficulty that arises in the analysis of most machine learning algorithms is to handle, analytically and numerically, a large number of interacting random variables. In this manuscript, we revisit an approach based on the tools of statistical physics of disordered systems. Developed through a rich literature, they have been precisely designed to infer the macroscopic behavior of a large number of particles from their microscopic interactions. At the heart of this work, we strongly capitalize on the deep connection between the replica method and message passing algorithms in order to shed light on the phase diagrams of various theoretical models, with an emphasis on the potential differences between statistical and algorithmic thresholds. We essentially focus on synthetic tasks and data generated in the teacher-student paradigm. In particular, we apply these mean-field methods to the Bayes-optimal analysis of committee machines, to the worst-case analysis of Rademacher generalization bounds for perceptrons, and to empirical risk minimization in the context of generalized linear models. Finally, we develop a framework to analyze estimation models with structured prior informations, produced for instance by deep neural networks based generative models with random weights
Bosilca, George. "Contribution à l'étude des environnements d'exécution parallèle fortement dynamiques à passage de messages." Paris 11, 2004. http://www.theses.fr/2004PA112316.
Повний текст джерелаGlobal Computing platforms, large scale clusters and future TeraGRID systems gather thousands of nodes for computing parallel scientific applications. These parallel architectures currently uses different approaches depending on the hardware memory model of the architecture, the abstraction level of the programming environment and the nature of the application. On the first part, I introduce an original client-server execution model based on RPCs called out-of-order parallel virtual machine (OVM). OVM aims to provide three main features: portability through a unique memory model, load-balancing using a plug-in support and high performance provided by several optimizations. The main optimizations are: non-blocking RPCs, data-flow management, persistent and non-persistent data, dynamic scheduling and asynchronous global operations. I present OVM general architecture and demonstrate high performance for several types of parallel applications: regular, with load balancing needs and with real-time constraints. At this scale, node failures or disconnections are frequent events. This Volatility reduces the MTBF of the whole system in the range of hour or minutes. On the second part, I present MPICH-V, an automatic fault tolerant MPI environment based on uncoordinated checkpoint/rollback and distributed message logging. MPICH-V architecture relies on Channel Memories, Checkpoint servers and theoretically proven protocols to execute SPMD and Master-Worker MPI applications on volatile nodes. Focusing on the channel memory, I present and analyse the performances for non-trivial parallel applications. Experimental results demonstrate good scalability and high tolerance to faults
Gauchard, David. "Simulation hybride des réseaux IP-DiffServ-MPLS multi-services sur environnement d'exécution distribuée." Toulouse 3, 2003. http://www.theses.fr/2003TOU30192.
Повний текст джерелаDujardin, Éric. "Reseau d'interconnexion pour une machine a passage de messages specialisee dans le traitement d'images." Paris 6, 1994. http://www.theses.fr/1994PA066558.
Повний текст джерелаSahin, Serdar. "Advanced receivers for distributed cooperation in mobile ad hoc networks." Thesis, Toulouse, INPT, 2019. http://www.theses.fr/2019INPT0089.
Повний текст джерелаMobile ad hoc networks (MANETs) are rapidly deployable wireless communications systems, operating with minimal coordination in order to avoid spectral efficiency losses caused by overhead. Cooperative transmission schemes are attractive for MANETs, but the distributed nature of such protocols comes with an increased level of interference, whose impact is further amplified by the need to push the limits of energy and spectral efficiency. Hence, the impact of interference has to be mitigated through with the use PHY layer signal processing algorithms with reasonable computational complexity. Recent advances in iterative digital receiver design techniques exploit approximate Bayesian inference and derivative message passing techniques to improve the capabilities of well-established turbo detectors. In particular, expectation propagation (EP) is a flexible technique which offers attractive complexity-performance trade-offs in situations where conventional belief propagation is limited by computational complexity. Moreover, thanks to emerging techniques in deep learning, such iterative structures are cast into deep detection networks, where learning the algorithmic hyper-parameters further improves receiver performance. In this thesis, EP-based finite-impulse response decision feedback equalizers are designed, and they achieve significant improvements, especially in high spectral efficiency applications, over more conventional turbo-equalization techniques, while having the advantage of being asymptotically predictable. A framework for designing frequency-domain EP-based receivers is proposed, in order to obtain detection architectures with low computational complexity. This framework is theoretically and numerically analysed with a focus on channel equalization, and then it is also extended to handle detection for time-varying channels and multiple-antenna systems. The design of multiple-user detectors and the impact of channel estimation are also explored to understand the capabilities and limits of this framework. Finally, a finite-length performance prediction method is presented for carrying out link abstraction for the EP-based frequency domain equalizer. The impact of accurate physical layer modelling is evaluated in the context of cooperative broadcasting in tactical MANETs, thanks to a flexible MAC-level simulator
Khoumsi, Khalid. "Optimisation des performances dans les réseaux de communication des machines parallèles à passage de messages." Grenoble INPG, 1996. http://www.theses.fr/1996INPG0202.
Повний текст джерелаLokhov, Andrey Y. "Dynamic cavity method and problems on graphs." Thesis, Paris 11, 2014. http://www.theses.fr/2014PA112331/document.
Повний текст джерелаA large number of optimization, inverse, combinatorial and out-of-equilibrium problems, arising in the statistical physics of complex systems, allow for a convenient representation in terms of disordered interacting variables defined on a certain network. Although a universal recipe for dealing with these problems does not exist, the recent years have seen a serious progress in understanding and quantifying an important number of hard problems on graphs. A particular role has been played by the concepts borrowed from the physics of spin glasses and field theory, that appeared to be extremely successful in the description of the statistical properties of complex systems and in the development of efficient algorithms for concrete problems.In the first part of the thesis, we study the out-of-equilibrium spreading problems on networks. Using dynamic cavity method on time trajectories, we show how to derive dynamic message-passing equations for a large class of models with unidirectional dynamics -- the key property that makes the problem solvable. These equations are asymptotically exact for locally tree-like graphs and generally provide a good approximation for real-world networks. We illustrate the approach by applying the dynamic message-passing equations for susceptible-infected-recovered model to the inverse problem of inference of epidemic origin. In the second part of the manuscript, we address the optimization problem of finding optimal planar matching configurations on a line. Making use of field-theory techniques and combinatorial arguments, we characterize a topological phase transition that occurs in the simple Bernoulli model of disordered matching. As an application to the physics of the RNA secondary structures, we discuss the relation of the perfect-imperfect matching transition to the known molten-glass transition at low temperatures, and suggest generalized models that incorporate a one-to-one correspondence between the contact matrix and the nucleotide sequence, thus giving sense to the notion of effective non-integer alphabets
Smith, Ronda. "The influence of nonsmokers' argumentativeness and verbal aggressiveness on compliance-gaining message selection in a smoking situation." Virtual Press, 1992. http://liblink.bsu.edu/uhtbin/catkey/834139.
Повний текст джерелаDepartment of Speech Communication
Moukrim, Aziz. "Génération automatique de codes parallèles et nouvelles heuristiques d'ordonnancement pour les machines à passage de messages." Clermont-Ferrand 2, 1995. http://www.theses.fr/1995CLF21755.
Повний текст джерелаBouteiller, Aurélien. "Tolérance automatique aux défaillances par points de reprise et retour en arrière dans les systèmes hautes performances à passage de messages." Paris 11, 2006. http://www.theses.fr/2006PA112219.
Повний текст джерелаIncreasing the number of components of high performance architectures arises reliability issues: mean time between failures is now less than 10 hours. A solution to ensure progression of a numerical application hit by failures is to periodically save checkpoints. However, the state of each process depends on network's non deterministic events. Thus, a fault tolerance protocol has to ensure the ability to recover to a correct global state from a set of ckeckpoints. Our work aims to study checkpoint based automatic fault tolerance for message passing applications using the MPI standard. First we present a software environnement designed to express various families of fault tolerance algorithms and compare them in an fair and uniform testbed. We implement many fault tolerant protocols in this environment (including two originals) : one using coordinated checkpoints, two pessimistic message logging and three causal message logging. We shows through experimental comparison between all those protocol a fault frequency afterward message logging protocols are performing better than coordinated ones. Last we describe a novel modeling of pessimistic message logging focusing on very high performance networks. In those networks, using intermediate memory buffers and copies leads to high overhead. We present performances of an implementation of this protocol
Saade, Alaa. "Spectral inference methods on sparse graphs : theory and applications." Thesis, Paris Sciences et Lettres (ComUE), 2016. http://www.theses.fr/2016PSLEE024/document.
Повний текст джерелаIn an era of unprecedented deluge of (mostly unstructured) data, graphs are proving more and more useful, across the sciences, as a flexible abstraction to capture complex relationships between complex objects. One of the main challenges arising in the study of such networks is the inference of macroscopic, large-scale properties affecting a large number of objects, based solely on he microscopic interactions between their elementary constituents. Statistical physics, precisely created to recover the macroscopic laws of thermodynamics from an idealized model of interacting particles, provides significant insight to tackle such complex networks.In this dissertation, we use methods derived from the statistical physics of disordered systems to design and study new algorithms for inference on graphs. Our focus is on spectral methods, based on certain eigenvectors of carefully chosen matrices, and sparse graphs, containing only a small amount of information. We develop an original theory of spectral inference based on a relaxation of various meanfield free energy optimizations. Our approach is therefore fully probabilistic, and contrasts with more traditional motivations based on the optimization of a cost function. We illustrate the efficiency of our approach on various problems, including community detection, randomized similarity-based clustering, and matrix completion
Krawezik, Géraud. "Contribution à l'étude de la programmation des machines parallèles complexes." Paris 11, 2004. http://www.theses.fr/2004PA112160.
Повний текст джерелаThe goal of this thesis?is to study the programming of complex parallel machines, which are used to solve large scale numerical problems. It mainly concentrates in three points which are first the study of standard parallel languages and their respective efficiency. Then we will study a fault tolerant parallel programming labrary and its runtime. At last we will consider the future languages, with the presentation of already existing ones and their common caracteristics before presenting the definition of a new language. In the first part, we will show that the OpenMP tool in the case of shared memory machines enables the user to get more performance than with MPI which is now the standard of parallel programming. But this is done with a high programming effort which goes against the easyness intended in OpenMP. In the next part, we will present MPICH-V, an automatic fault-tolerant implementation, and especially its runtime, by presenting three caracteristics that are important for this part, which are the remote launching, the connection between nodes and the handling of fault detection. In each case we will discuss the possible technical choices before extending them to a grid environment. At last, we will present upcoming parallel languages with different examples of their usage, before presenting our own, based on a shared memory mechanism and programmed communications
Coti, Camille. "Environnements d'exécution pour applications parallèles communiquant par passage de messages pour les systèmes à grande échelle et les grilles de calcul." Phd thesis, Université Paris Sud - Paris XI, 2009. http://tel.archives-ouvertes.fr/tel-00676937.
Повний текст джерелаCoti, Camille. "Environnements d’exécution pour applications parallèles communiquant par passage de messages pour les systèmes à grande échelle et les grilles de calcul." Paris 11, 2009. http://www.theses.fr/2009PA112233.
Повний текст джерелаThe run-time environment is a key component of a parallel programming and execution environment. It features some services to the processes of parallel applications. The most fundamental of these services is to allow processes to communicate with one another and forwarding IOs and signals. In this thesis, I present results concerning run-time environments for large-scale systems and the services provided to large-scale applications. The first part studies the run-time environment's performance for large-scale systems and proposes an approach centered on topologies to support applications efficiently. The second part studies an additional feature provided by the run-time environment on systems made of a large number of components: fault tolerance. The third and the fourth part concern a specific kind of large-scale systems: computational grids. These systems present particularities that are specific to the usage of remote, heterogeneous resources. Problematic related to connectivity throughout computational grids are presented in the third part of this thesis, as well as an extension of the run-time environment designed to face them. The fourth part presents a method to design and program applications for computational grids and examples of typical applications that achieve a good performance
Corrêa, Abel. "Alocação de tarefas de desastre na plataforma RMASBench : uma abordagem baseada em passagem de mensagens e formação de grupos." reponame:Biblioteca Digital de Teses e Dissertações da UFRGS, 2015. http://hdl.handle.net/10183/130528.
Повний текст джерелаIn urban disaster environments, groups of rescue agents must solve tasks in order to minimize the damage that can occur in a city. Such environments are dynamic and partially observable, with features that correspond to spatial distance, amount of resources, difficulty of the disaster task, and the capability of the agent to handle it. The communication between the agents can be noisy or non-existent. Multiagent systems are developed to solve complex and comprehensive problems, that are beyond the capability of one single agent. In this context, the agents are autonomous computational elements that are responsible for a piece of the solution of the problem. The agents are situated in an environment, and may have social ability, interacting with other agents to solve the tasks. Commonly, the urban disaster domain is formalized as a task allocation problem, and modelled as a constraint optimization problem distributed among heterogeneous agents, where they have to choose the tasks that maximize their individual utilities or minimize their individual costs. This master thesis proposes a model for formation of groups of agents based in the minimization of a distance. The model is formalized as a distributed constraint optimization problem, using algorithms to exchange messages between agents. The model called Formation of Groups by Minimization of Distance (FGMD) has self-organizing autonomous agents without a centralized control. We applied the FGMD in the RMASBench platform, that is a simulator for urban disaster situations. We compare the FGMD with the most recent message passing algorithms, verifying that FGMD uses less non-parallel computation. With respect to the minimization of the damage in the city, we show that it is possible to obtain better results than the state-of-art approaches, with slightly increase of computational effort.
Nguyen, Ly Thien Truong. "Mise en oeuvre matérielle de décodeurs LDPC haut débit, en exploitant la robustesse du décodage par passage de messages aux imprécisions de calcul." Thesis, Cergy-Pontoise, 2017. http://www.theses.fr/2017CERG0904/document.
Повний текст джерелаThe increasing demand of massive data rates in wireless communication systems will require significantly higher processing speed of the baseband signal, as compared to conventional solutions. This is especially challenging for Forward Error Correction (FEC) mechanisms, since FEC decoding is one of the most computationally intensive baseband processing tasks, consuming a large amount of hardware resources and energy. The conventional approach to increase throughput is to use massively parallel architectures. In this context, Low-Density Parity-Check (LDPC) codes are recognized as the foremost solution, due to the intrinsic capacity of their decoders to accommodate various degrees of parallelism. They have found extensive applications in modern communication systems, due to their excellent decoding performance, high throughput capabilities, and power efficiency, and have been adopted in several recent communication standards.This thesis focuses on cost-effective, high-throughput hardware implementations of LDPC decoders, through exploiting the robustness of message-passing decoding algorithms to computing inaccuracies. It aims at providing new approaches to cost/throughput optimizations, through the use of imprecise computing and storage mechanisms, without jeopardizing the error correction performance of the LDPC code. To do so, imprecise processing within the iterative message-passing decoder is considered in conjunction with the quantization process that provides the finite-precision information to the decoder. Thus, we first investigate a low complexity code and decoder aware quantizer, which is shown to closely approach the performance of the quantizer with decision levels optimized through exhaustive search, and then propose several imprecise designs of Min-Sum (MS)-based decoders. Proposed imprecise designs are aimed at reducing the size of the memory and interconnect blocks, which are known to dominate the overall area/delay performance of the hardware design. Several approaches are proposed, which allow storing the exchanged messages using a lower precision than that used by the processing units, thus facilitating significant reductions of the memory and interconnect blocks, with even better or only slight degradation of the error correction performance.We propose two new decoding algorithms and hardware implementations, obtained by introducing two levels of impreciseness in the Offset MS (OMS) decoding: the Partially OMS (POMS), which performs only partially the offset correction, and the Imprecise Partially OMS (I-POMS), which introduces a further level of impreciseness in the check-node processing unit. FPGA implementation results show that they can achieve significant throughput increase with respect to the OMS, while providing very close decoding performance, despite the impreciseness introduced in the processing units.We further introduce a new approach for hardware efficient LDPC decoder design, referred to as Non-Surjective Finite-Alphabet Iterative Decoders (FAIDs). NS-FAIDs are optimized by Density Evolution for regular and irregular LDPC codes. Optimization results reveal different possible trade-offs between decoding performance and hardware implementation efficiency. To validate the promises of optimized NS-FAIDs in terms of hardware implementation benefits, we propose three high-throughput hardware architectures, integrating NS-FAIDs decoding kernels. Implementation results on both FPGA and ASIC technology show that NS-FAIDs allow significant improvements in terms of both throughput and hardware resources consumption, as compared to the Min-Sum decoder, with even better or only slightly degraded decoding performance
Barbolosi, Laurence. "De la nécessité du messager à celle du confident : pour une approche dramaturgique de l'espace tragique." Rennes 2, 2004. http://www.theses.fr/2004REN20035.
Повний текст джерелаIn Greek tragedies or French classical tragedies, the aesthetic production of the meaning of the tragic effect is based on a method of connection : the determine role of the visible space and the invisible space. The latter creates a tragical space that coincides with the imaginary of the spectator and throws " the sign of transcendency " back to him. Thus, the spectator can go beyond his pathetic first emotion to reach the tragical conscience. This space needs to be configured, the interpreter of a dramaturgic system : " the poetical mediator ". The examination of Greek tragedies and French classical tragedies shows that this mediatory role can be taken charge by deeply unlike characters, on the one hand , the messenger , on the other hand , the confident, no without revealing the presence of a constant structure in spite of the distant sociohistorical backgrounds
Zdeborová, Lenka. "Statistical physics of hard optimization problems." Paris 11, 2008. http://www.theses.fr/2008PA112080.
Повний текст джерелаOptimization is fundamental in many areas of science, from computer science and information theory to engineering and statistical physics, as well as to biology or social sciences. It typically involves a large number of variables and a cost function depending on these variables. Optimization problems in the NP-complete class are particularly difficult, it is believed that the number of operations required to minimize the cost function is in the most difficult cases exponential in the system size. However, even in an NP-complete problem the practically arising instances might, in fact, be easy to solve. The principal question we address in this thesis is: How to recognize if an NP-complete constraint satisfaction problem is typically hard and what are the main reasons for this? We adopt approaches from the statistical physics of disordered systems, in particular the cavity method developed originally to describe glassy systems. We describe new properties of the space of solutions in two of the most studied constraint satisfaction problems - random satisfiability and random graph coloring. We suggest a relation between the existence of the so-called frozen variables and the algorithmic hardness of a problem. Based on these insights, we introduce a new class of problems which we named "locked" constraint satisfaction, where the statistical description is easily solvable, but from the algorithmic point of view they are even more challenging than the canonical satisfiability
Sonoda, Eloiza Helena. "Paralelização de um programa para cálculo de propriedades físicas de impurezas magnéticas em metais." Universidade de São Paulo, 2001. http://www.teses.usp.br/teses/disponiveis/76/76132/tde-19102001-135247/.
Повний текст джерелаThis dissertation discuss the parallelization of a program that calculates physical properties of dilute magnetic alloys. The renormalization group method applied to Anderson's two impurities model showed to be specially suitable to parallel processing because a large amount of calculations as well as variations of data entries required by the method can be performed simultaneously. To achieve this we rewrote the sequential program previously used by the Theoretical Physics Group of the IFSC and wrote three parallel versions. These versions differ from each other by the parallelization approach. The use of computer clusters revealed to be an appropriate option because the calculation time is the limiting factor on performance instead of communication time. The results show a good reduction of execution time, but speedup and scalability lack due to load balancing problems. We analyze these problems and suggest possible solutions.
Walters, Mark M. "Elevating the hope of members of First Baptist Church, Nicoma Park through expository messages from selected passages on the New Testament doctrine of hope." Theological Research Exchange Network (TREN), 2002. http://www.tren.com.
Повний текст джерелаGermain, Cécile. "Étude des mécanismes de communication pour une machine massivement parallèle : mega." Paris 11, 1989. http://www.theses.fr/1989PA112385.
Повний текст джерелаThe Machine to Explore Giant Architectures (MEGA) project of the "Architecture et Conception des Circuits Intégrés" team of the LRI includes both the study of a logical model, the Dynamic Processes Networks, and of a hardware architecture, the MEGA machine. MEGA is a MIMD message-passing machine, intended to support an Ether communication model. Its target is very massive parallelism, up to 1 Million Elementary Processors. Each of these processors integrates in a single VLSI chip a processing unit, a local memory and a communication management unit. The communication design is one of the key features of such an architecture. It bears a very high technological constraint from a feasibility point of view, but it's performances determines the whole system ones. Therefore hardware parallelism may be actually useful only if the communication to computation ratio may be balanced. The communication design study includes three points of view : the communication model as an interface between software and hardware communication tools, the network topology and the routing strategy. In the three cases, the extreme parallelism target induced us to propose solutions which are original beside these in use in medium-grain multicomputers such as the commercial hypercubes. The communication model offers a direct interprocess relation when possible and allows however the processes graph dynamicity. The constant wiring density comparison for topologies shows that low dimensional meshes have better performances than hypercubes; the 3D mesh is then a good compromise between performances and feasibility constraints. We developed also a new routing strategy which we called Forced Routing. This strategy provides an efficient channels use. It limits contention by a randomized dispersion of messages and only needs very little buffering area. We achieved a logical specification for a routing and network/processor interface circuit. This circuit manages the messages without interfering with the processing unit activity and implements Forced Routing
Wahle, Stephan. "Gottes-Gedenken Untersuchungen zum anamnetischen Gehalt christlicher und jüdischer Liturgie." Innsbruck Wien Tyrolia-Verl, 2005. http://deposit.ddb.de/cgi-bin/dokserv?id=2715732&prov=M&dok_var=1&dok_ext=htm.
Повний текст джерелаZdeborova, Lenka. "Physique statistique des problèmes d'optimisation." Phd thesis, Université Paris Sud - Paris XI, 2008. http://tel.archives-ouvertes.fr/tel-00294232.
Повний текст джерелаGAUCHARD, David. "Simulation hybride des réseaux IP-DiffServ-MPLS multi-services sur environnement d'exécution distribuée." Phd thesis, Université Paul Sabatier - Toulouse III, 2003. http://tel.archives-ouvertes.fr/tel-00011034.
Повний текст джерелаSabah, Quentin. "SIAAM: Isolation dynamique pour une machine abstraite à base d'acteurs." Phd thesis, Université de Grenoble, 2013. http://tel.archives-ouvertes.fr/tel-00933072.
Повний текст джерелаLasalle-Ratelle, Jérémie. "Implantation des futures sur un système distribué par passage de messages." Thèse, 2010. http://hdl.handle.net/1866/4900.
Повний текст джерелаThis master’s thesis presents an implementation of lazy task creation for distributed memory multiprocessors. It offers a subset of Message-Passing Interface’s functionality and allows parallelization of some problems that are hard to statically partition thanks to its dynamic partitionning and load balancing system. It is based on Multilisp, a Scheme dialect for parallel computing, and implements an MPI like interface on top of it. It offers a richer and more expressive language than C and simplify the work needed to developp programs similar to those in MPI. Finally, dynamic partitioning allows some programs that would be very hard to develop in MPI. Tests were made on a 16 cpus computer and on a 16 cpus cluster. The system gets good accelerations when compared to equivalent sequential programs and acceptable performances when compared to MPI. It shows that it is possible to use futures as a dynamic partitioning method on distributed memory multiprocessors.
Diallo, Alpha Boubacar. "Développement et parallélisation d'algorithmes bioinformatiques pour la reconstruction d'arbres phylogénétiques et de réseaux réticulés." Mémoire, 2007. http://www.archipel.uqam.ca/4752/1/M10004.pdf.
Повний текст джерелаChao, Chen-ni, and 趙真妮. "The positive and passive messages construction between health and eco-protection influence vegetarianism and environmental consensus – taking junior high students as examples." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/3z3ft2.
Повний текст джерела健行科技大學
企業管理系碩士班
104
This study takes the method of two times two - the experiment between testers. Edit four films about environmental education, focusing on the vegetarian education to deal with the information construction and informational variables, to discuss that in the environmental education, the positive and passive messages construction and health, eco-protection and the sexual elements influence the dutiful senses toward environment. This study takes the 9th grade students of junior high in Taoyuan City as examples. There are 260 valid questionnaires. The conclusion is as following:First, basing on the message construction, the testers who watch the film of positive message have higher sense on environmental duty than those who watch the negative ones. Next, those who watch the film about health and eco-protection messages have more on vegetarian tendency; however, there are no obvious difference on the sense of environmental duty. Finally, the female testers have higher vegetarian tendency and the sense of environmental duty between than male ones.
Mácha, Slavomír. "Role médií při utváření veřejného mínění a politického myšlení v České republice." Master's thesis, 2012. http://www.nusl.cz/ntk/nusl-313791.
Повний текст джерелаGORLA, Sandra. "Metamorfosi e magia nel Roman de Renart. Traduzione e commento delle branches XXII e XXIII." Doctoral thesis, 2018. http://hdl.handle.net/11393/251268.
Повний текст джерела