Dissertationen zum Thema „Optimisation de codes parallèles“
Geben Sie eine Quelle nach APA, MLA, Chicago, Harvard und anderen Zitierweisen an
Machen Sie sich mit Top-50 Dissertationen für die Forschung zum Thema "Optimisation de codes parallèles" bekannt.
Neben jedem Werk im Literaturverzeichnis ist die Option "Zur Bibliographie hinzufügen" verfügbar. Nutzen Sie sie, wird Ihre bibliographische Angabe des gewählten Werkes nach der nötigen Zitierweise (APA, MLA, Harvard, Chicago, Vancouver usw.) automatisch gestaltet.
Sie können auch den vollen Text der wissenschaftlichen Publikation im PDF-Format herunterladen und eine Online-Annotation der Arbeit lesen, wenn die relevanten Parameter in den Metadaten verfügbar sind.
Sehen Sie die Dissertationen für verschiedene Spezialgebieten durch und erstellen Sie Ihre Bibliographie auf korrekte Weise.
Benmouhoub, Farah. „Optimisation de la précision numérique des codes parallèles“. Thesis, Perpignan, 2022. http://www.theses.fr/2022PERP0009.
Der volle Inhalt der QuelleIn high performance computing, nearly all the implementations and published experiments use foating-point arithmetic. However, since foating-point numbers are finite approximations of real numbers, it may result in hazards because of the accumulated errors.These round-off errors may cause damages whose gravity varies depending on the critical level of the application. Parallelism introduces new numerical accuracy problems due to the order of operations in this kind of systems. The proposed thesis subject concerns this last point: improving the precision of massively parallel scientific computing codes such as those found in the field of HPC (High Performance Computing)
Laguzet, Florence. „Etude et optimisation d'algorithmes pour le suivi d'objets couleur“. Thesis, Paris 11, 2013. http://www.theses.fr/2013PA112197.
Der volle Inhalt der QuelleThe work of this thesis focuses on the improvement and optimization of the Mean-Shift color object tracking algorithm, both from a theoretical and architectural point of view to improve both the accuracy and the execution speed. The first part of the work consisted in improving the robustness of the tracking. For this, the impact of color space representation on the quality of tracking has been studied, and a method for the selection of the color space that best represents the object to be tracked has been proposed. The method has been coupled with a strategy determining the appropriate time to recalculate the model. Color space selection method was also used in collaboration with another object tracking algorithm to further improve the tracking robustness for particularly difficult sequences : the covariance tracking which is more time consuming. The objective of this work is to obtain an entire real time system running on multi-core SIMD processors. A study and optimization phase has been made in order to obtain algorithms with a complexity that is configurable so that they can run in real time on different platforms, for various sizes of images and object tracking. In this context of compromise between speed and performance, it becomes possible to do real-time tracking on processors like ARM Cortex A9
Fang, Juing. „Décodage pondère des codes en blocs et quelques sujets sur la complexité du décodage“. Paris, ENST, 1987. http://www.theses.fr/1987ENST0005.
Der volle Inhalt der QuelleRaulet, Mickaël. „Optimisations mémoire dans la méthodologie AAA pour code embarqué sur architecture parallèles“. Rennes, INSA, 2006. https://tel.archives-ouvertes.fr/tel-00124276v2.
Der volle Inhalt der QuelleIn the field of embedded electronics, the applications of digital communications and image processing induce very strong time constraints while allowing a limitation in resources and performances of the computation units. The restriction of the memory usable can be in opposite of fields such as video coding. A solution to achieve a real-time implementation can be reached through a distribution on a parallel architecture. These problems are the framework of this work. More precisely, that is why we developed a process of rapid prototyping dedicated to the parallel architectures with several processors of digital signal processing of the last generation (FPGA, DSP). The optimization aspect of the allocated memory is performed here in a more precise way. The prototyping process was elaborate around SynDEx, a tool developed with the INRIA, based on the AAA methodology. This process aims at improving the implementation of an algorithm on a multi-component architecture by determining an optimal distribution and scheduling. SynDEx carries out the adequation phase itself, and generates an executive independent of the target. We initially contributed to the automation of the process on multiprocessors target, by adding a functional layer, and by developing new specific kernels for processors of digital signal. In an embedded context, our concerns are then the minimization of the memory for the generated code. It is still a problem very open for multi-component architectures. The found solution, thanks to the algorithms of colouring of graph, leads to a significant improvement of the results of distributed implementation. The rapid prototyping towards multi-component platforms is automatic today, and memory optimizations are directly integrated in the SynDEx tool. Another part of this work related to the development and integration, through our prototyping process, of consequent applications in the fields both of the image processing (MPEG-4, LAR) and both of the telecommunications (MC-CDMA, UMTS). Results validate the whole process, and show its adaptation to systems oriented data processing. The report is concluded on new perspectives, while being interested in particular in multi-layer systems linking together several layers: a “transport” layer of telecommunication and a “service” layer of image processing
Surós, Rina. „Modélisation et optimisation de systèmes parallèles“. Paris 11, 1988. http://www.theses.fr/1988PA112188.
Der volle Inhalt der QuelleRaulet, Mickaël. „Optimisations Mémoire dans la méthodologie « Adéquation Algorithme Architecture » pour Code Embarqué sur Architectures Parallèles“. Phd thesis, INSA de Rennes, 2006. http://tel.archives-ouvertes.fr/tel-00124276.
Der volle Inhalt der QuelleLa chaîne de prototypage a été élaborée autour de SynDEx, outil développé à l'INRIA basé sur la méthodologie AAA. Cette dernière vise à améliorer l'implantation d'un algorithme sur une architecture multi-processeurs en déterminant une distribution et ordonnancement optimaux. SynDEx réalise la phase d'adéquation proprement dite, et génère un exécutif indépendant de la cible. Nous avons dans un premier temps contribué à l'automatisation du processus sur cible multi-processeurs, en rajoutant d'une couche fonctionnelle, et en développant de nouveaux noyaux spécifiques pour des processeurs de traitement numérique du signal.
Dans un contexte embarqué, nos préoccupations se sont ensuite penchées sur la minimisation de la mémoire pour le code généré. C'est un problème encore très ouvert pour des architectures multi-composants. La solution trouvée, grâce aux algorithmes de coloriage de graphe, aboutit à une amélioration significative des résultats d'implantation distribuée. Le portage vers des plates-formes multi-composants est aujourd'hui automatique, notamment en intégrant directement dans l'outil SynDEx l'optimisation mémoire.
Une autre partie importante de ces travaux a concerné le développement et l'intégration, à travers notre processus de prototypage, d'applications conséquentes dans les domaines du traitement des images (MPEG-4, LAR) et celui des télécommunications (MC-CDMA, UMTS). Les résultats obtenus valident l'ensemble du processus proposé, et démontrent son adaptation à des systèmes globalement orientés traitement de l'information. Le mémoire se conclut en ouvrant sur de nouvelles perspectives, en s'intéressant notamment à des systèmes multi-couches réunissant des couches « transport » de télécommunication numériques et des couches « services » de traitement des images.
Alba-Gomez, Ofélia. „Optimisation de trajectoires de robots parallèles redondants“. Nantes, 2007. http://www.theses.fr/2007NANT2126.
Der volle Inhalt der QuelleThe aims of studies in tbis thesis are the definition of perfonnance indices of3-RRR parallel robots and the formulation of a method for trajectory planning in order to avoid singular configurations and optimize the kinetostatic performances of the manipulator. By using the isotropy conditions we define a characteristic length in order to homogenize the parallel Jacobian matrix. Thus, a consistent performance index is defined by using such a matrix as the distance of a configuration to parallel singularities. The optimum value of this index is determined an ideal isotropic configuration. Then, another index of the manipulator is defined by using a geometric interpretation of conditions of parallel singularities. An additional study allows us to verify the equivalence of the two proposed indices. Then, for our kinematically redundant robot, a method for automatic trajectory planning is proposed which optimizes the manipulator performances during the execution of a specified task. This method is inspired from an algorithm of trajectory planning for auto-guided vehicles. Several cases of study are analyzed in order to validate the effectiveness of our method in environments without and with obstacles. We consider a scenario in which the accessibility to the whole path is not possible using only one working mode; thus, we propose a supplementary formulation in order to achieve a suitable change of working mode to complete the task
Leguay-Durand, Sylvie. „Conception et optimisation de mécanismes parallèles à mobilités restreintes“. Toulouse, ENSAE, 1998. http://www.theses.fr/1998ESAE0014.
Der volle Inhalt der QuelleLegaux, Joeffrey. „Squelettes algorithmiques pour la programmation et l'exécution efficaces de codes parallèles“. Phd thesis, Université d'Orléans, 2013. http://tel.archives-ouvertes.fr/tel-00990852.
Der volle Inhalt der QuelleMattoussi, Ferdaouss. „Conception et optimisation de codes AL-FEC : les codes GLDPC- Staircase“. Phd thesis, Université de Grenoble, 2014. http://tel.archives-ouvertes.fr/tel-00969573.
Der volle Inhalt der QuelleLiu, Zhen. „Modèles d'exécutions parallèles sur des systèmes multiprocesseurs : analyse et optimisation“. Paris 11, 1989. http://www.theses.fr/1989PA112011.
Der volle Inhalt der QuelleThe main concerns of this thesis are the modeling, analysis and optimization problems arising in multiprocessor systems with concurrent tasks. Multiprocessor systems are modeled by a set of processors connected by an interconnection network, parallel programs by directed acyclic graphs. Both exact and approximate methods are proposed for various parallel processing models. The performance measures such as program response time, system throughput, and stability condition, etc. . . , are analyzed. Scheduling algorithm that minimize makespan are also considered. New heuristics are provided together with simple illustrative examples. Besides theoretical studies, the performance evaluation software package SPEC (Software package for Performances Evaluation of Concurrent systems), designed and implemented by the author, is described concisely. This software package contains analytical and simulation tools
Piskorski, Stéphane. „Optimisation de codes multimédias pour systèmes embarqués“. Paris 11, 2009. http://www.theses.fr/2009PA112215.
Der volle Inhalt der QuelleImage processing algorithms tend to become more and more computation-power hungry, while video applications ask for greater amounts of data to process. In order to be able to sustain real-time video streams, microprocessor-based embedded systems have to be carefully tuned. This thesis focuses on studying the required optimizations on several scales. Firstly by modifying the instruction set and computation units of a processor, to improve its computation efficiency at a reasonable hardware cost, leading to interesting electrical consumption results. An applicative example is given through the implementation of a robust embedded localization algorithm based on interval analysis. Secondly by studying the best way to generate hardware modules for soft-core processors on FPGA, in order to not simply accelerate a few instructions but a complete computation bloc. Finally, at a complete treatment scale, a low-level image-processing code generation tool – IPLG – is proposed. This tool automatically generates optimally written stencil-based C code, by exploring all possible computation-loop fusions, and by applying variable rotation, loop-unrolling and data-locality improvement techniques
Luong, Thé Van. „Métaheuristiques parallèles sur GPU“. Thesis, Lille 1, 2011. http://www.theses.fr/2011LIL10058/document.
Der volle Inhalt der QuelleReal-world optimization problems are often complex and NP-hard. Their modeling is continuously evolving in terms of constraints and objectives, and their resolution is CPU time-consuming. Although near-optimal algorithms such as metaheuristics (generic heuristics) make it possible to reduce the temporal complexity of their resolution, they fail to tackle large problems satisfactorily. Over the last decades, parallel computing has been revealed as an unavoidable way to deal with large problem instances of difficult optimization problems. The design and implementation of parallel metaheuristics are strongly influenced by the computing platform. Nowadays, GPU computing has recently been revealed effective to deal with time-intensive problems. This new emerging technology is believed to be extremely useful to speed up many complex algorithms. One of the major issues for metaheuristics is to rethink existing parallel models and programming paradigms to allow their deployment on GPU accelerators. Generally speaking, the major issues we have to deal with are: the distribution of data processing between CPU and GPU, the thread synchronization, the optimization of data transfer between the different memories, the memory capacity constraints, etc. The contribution of this thesis is to deal with such issues for the redesign of parallel models of metaheuristics to allow solving of large scale optimization problems on GPU architectures. Our objective is to rethink the existing parallel models and to enable their deployment on GPUs. Thereby, we propose in this document a new generic guideline for building efficient parallel metaheuristics on GPU. Our challenge is to come out with the GPU-based design of the whole hierarchy of parallel models.In this purpose, very efficient approaches are proposed for CPU-GPU data transfer optimization, thread control, mapping of solutions to GPU threadsor memory management. These approaches have been exhaustively experimented using five optimization problems and four GPU configurations. Compared to a CPU-based execution, experiments report up to 80-fold acceleration for large combinatorial problems and up to 2000-fold speed-up for a continuous problem. The different works related to this thesis have been accepted in a dozen of publications, including the IEEE Transactions on Computers journal
Bachelet, Vincent. „Métaheuristiques parallèles hybrides : application au problème d'affection quadratique“. Lille 1, 1999. https://pepite-depot.univ-lille.fr/LIBRE/Th_Num/1999/50376-1999-397.pdf.
Der volle Inhalt der QuelleMellouli, Racem. „Ordonnancement sur machines parallèles avec contraintes d'indisponibilité“. Troyes, 2007. http://www.theses.fr/2007TROY0022.
Der volle Inhalt der QuelleThis thesis is devoted to parallel machine scheduling with availability constraints for minimizing the flow time. We studied three theoretical models of this problem. The objective is to propose theoretical optimization methods that effectively solve these problems. We develop various approaches. Indeed, we proposed heuristic methods that improved classical methods from literature. Three types of exact approaches were considered : methods based on mixes integer linear programming, branch-and-bound methods using different branching schemes and methods based on dynamic programming. We also proposed constructive and iterative lower bounding schemes. In particular, lower bounds based on Lagrangian relaxation are combined with different tools from operational research, such as the subgradient method, dynamic programming and job splitting. Moreover, a method based on column generation has been developed based on a particular formulation of the problem. Auxiliary problems are solves with a heuristic method and an exact method using the dynamic programming. Furthermore, we proved several mathematical properties and proposed new lower bounds for a model already studied in the literature. Finally, we have studied worst-case performance for simple heuristics and a lower bound
Perez-Seva, Jean-Paul. „Les optimisations d'algorithmes de traitement de signal sur les architectures modernes parallèles et embarquées“. Phd thesis, Université de Nice Sophia-Antipolis, 2009. http://tel.archives-ouvertes.fr/tel-00610865.
Der volle Inhalt der QuelleSaidani, Tarik. „Optimisation multi-niveau d'une application de traitement d'images sur machines parallèles“. Phd thesis, Université Paris Sud - Paris XI, 2012. http://tel.archives-ouvertes.fr/tel-00776111.
Der volle Inhalt der QuelleSaidani, Tarik. „Optimisation multi-niveau d’une application de traitement d’images sur machines parallèles“. Thesis, Paris 11, 2012. http://www.theses.fr/2012PA112268/document.
Der volle Inhalt der QuelleThis thesis aims to define a design methodology for high performance applications on future embedded processors. These architectures require an efficient usage of their different level of parallelism (fine-grain, coarse-grain), and a good handling of the inter-processor communications and memory accesses. In order to study this methodology, we have used a target processor which represents this type of emerging architectures, the Cell BE processor.We have also chosen a low level image processing application, the Harris points of interest detector, which is representative of a typical low level image processing application that is highly parallel. We have studied several parallelisation schemes of this application and we could establish different optimisation techniques by adapting the software to the specific SIMD units of the Cell processor. We have also developped a library named CELL MPI that allows efficient communication and synchronisation over the processing elements, using a simplified and implicit programming interface. This work allowed us to develop a methodology that simplifies the design of a parallel algorithm on the Cell processor.We have designed a parallel programming tool named SKELL BE which is based on algorithmic skeletons. This programming model providesan original solution of a meta-programming based code generator. Using SKELL BE, we can obtain very high performances applications that uses the Cell architecture efficiently when compared to other tools that exist on the market
Diallo, Amadou Tidiane. „Caractérisation analytique et optimisation de codes source-canal conjoints“. Phd thesis, Université Paris Sud - Paris XI, 2012. http://tel.archives-ouvertes.fr/tel-00748545.
Der volle Inhalt der QuelleHaddou, Mounir. „Contribution à l'étude des méthodes de décomposition et de barrières en optimisation convexe“. Clermont-Ferrand 2, 1995. http://www.theses.fr/1995CLF21729.
Der volle Inhalt der QuelleVan, Luong Thé. „Métaheuristiques parallèles sur GPU“. Phd thesis, Université des Sciences et Technologie de Lille - Lille I, 2011. http://tel.archives-ouvertes.fr/tel-00638820.
Der volle Inhalt der QuelleCougo, Bernardo. „Dimensionnement et Optimisation de Transformateurs Inter-Cellules pour les Convertisseurs Multicellulaires Parallèles“. Phd thesis, Institut National Polytechnique de Toulouse - INPT, 2010. http://tel.archives-ouvertes.fr/tel-00578130.
Der volle Inhalt der QuelleBriot, Sébastien. „Analyse et Optimisation d'une Nouvelle Famille de Manipulateurs Parallèles aux Mouvements Découplés“. Phd thesis, INSA de Rennes, 2007. http://tel.archives-ouvertes.fr/tel-00327414.
Der volle Inhalt der Quelleproposées.
Franche, Jean-François. „Optimisation d’algorithmes de codage vidéo sur des plateformes à plusieurs processeurs parallèles“. Mémoire, École de technologie supérieure, 2011. http://espace.etsmtl.ca/1130/1/FRANCHE_Jean%2DFran%C3%A7ois.pdf.
Der volle Inhalt der QuelleMannoni, Valérian. „Optimisation des codes LDPC pour les communications multi-porteuses“. Reims, 2004. http://theses.univ-reims.fr/exl-doc/GED00000536.pdf.
Der volle Inhalt der QuelleThe major drawback of OFDM transmissions is that some symbols might be subject to strong attenuations. Hence, these symbols are potentially affected by an important bit error rate which involves the use of channel coding. The channel codes used are LDPC codes for which we have presented the main notations and a decoding algorithm. Considering the nostationarity of the OFDM frequency selective channel, we introduced a more general description of LDPC codes that we call irregularity profile. The COFDM communication system is then presented (without and with bit allocation) as well as the main characteristics of OFDM frequency selective channels. The channel capacity of this OFDM system with discrete MAQ input has been derived. We have then studied the asymptotic behaviour of LDPC codes with density evolution for OFDM transmissions through a frequency selective channel. In order to make possible this analysis, we have shown that the necessary conditions (messages independence and channel symmetry) are checked for the OFDM channel. A Gaussian approximation of the density evolution has then been presented and used for the optimization of LDPC codes. Two optimization criteria have been introduced, one based on the minimization of the LDPC decoding threshold and another one based on the minimization of the bit error probability at a given SNR. The later criterion has shown better performances for practical applications
Mannoni, Valérian Delaunay Georges. „Optimisation des codes LDPC pour les communications multi-porteuses“. Reims : S.C.D. de l'Université, 2004. http://scdurca.univ-reims.fr/exl-doc/GED00000536.pdf.
Der volle Inhalt der QuelleHadi, Ammar. „Optimisation and analysis of polar codes in communication systems“. Thesis, University of Manchester, 2018. https://www.research.manchester.ac.uk/portal/en/theses/optimisation-and-analysis-of-polar-codes-in-communication-systems(eb4cfc8a-86b5-465c-9231-4e02a3c2723c).html.
Der volle Inhalt der QuelleBhatt, Rishabh. „Algorithmes parallèles en temps pour l'assimilation de données“. Electronic Thesis or Diss., Université Grenoble Alpes, 2023. http://www.theses.fr/2023GRALM066.
Der volle Inhalt der QuelleFour dimensional variational data assimilation (4DVAR) which is based on optimisation algorithms is used by the leading meteorological institutions as a means of initialising the numerical climate models. The optimal initial condition is found by minimisng a cost function which accounts for the misfits of the model trajectory with the observations of the system over a given time window. In its incremental formulation, the integration of the forward and adjoint version of the original model is required in order to compute the gradient. A common issue in the retrieval of the initial condition is the enormous size of the state variable(10^9) which makes the minimisation an expensive and time consuming task. Moreover 4DVAR is an inherently sequential algorithm and to use it in parallel architectures, the models are classically parallelised only in the spatial dimension. This limits the scope of further speed up once spatial saturation is reached and also the maximum number of computing cores that one can use. The objective of this PhD is tointroduce an additional time-paralllelisation in the data assimilation framework by using the well known parareal method. Our approach is used here for running the forward integration. We use a modified version of the inexact conjugate gradient method where the matrix-vector multiplications are supplied through the parareal and thus are not exact. The associated convergence conditions of the inexact conjugate gradient allows us to use parareal adaptively by monitoring the errors in the matrix-vector product and obtaining the same levels of accuracy as with the usual conjugate gradient method at the same time. To ensure the feasibility and a practical implementation, all the norms which are hard to compute are replaced by the easily computable approximations. The results are demonstrated by considering the one and two dimensional shallow water model. They are presented in terms of the accuracy (in comparison with the original exact conjugate gradient) and in terms of the number of required iterations of the parareal algorithm. For the more complex two dimensional model we use a Krylov enhanced subspace parareal version which accelerates the convergence of the parareal and brings down the number of iterations. In the end, the ways to time-parallelisethe adjoint version is discussed as a further avenue for research
Maher, Rebai. „Ordonnancement des tâches de production et de maintenance préventive sur machines parallèles“. Troyes, 2011. http://www.theses.fr/2011TROY0003.
Der volle Inhalt der QuelleIn several areas, such as telecommunications, computer science, transportation and administration, scheduling contributes in the monitoring and the reduction of the production costs and the delays. Indeed, scheduling is considered as the fundamental basis of any planning operation. In this thesis, we studied the problem of scheduling a set of N production tasks on M identical parallel machines where every machine must be stopped during the planning horizon for reasons of preventive maintenance. We assume in our study that the resources ensuring the preventive maintenance are limited in capacity. We also assume that the maintenance should begin at time zero. Our work is related to two main problems: The first one concerns the scheduling of preventive maintenance tasks. In this problem, we aim to find a sequence for the preventative maintenance tasks having a minimal maintenance cost. The second one deals with the integrated scheduling of production and maintenance tasks on a set of parallel machines. Different exact and heuristic methods are developed to solve these two problems
Vander-Swalmen, Pascal. „Aspects parallèles des problèmes de satisfaisabilité“. Phd thesis, Université de Reims - Champagne Ardenne, 2009. http://tel.archives-ouvertes.fr/tel-00545657.
Der volle Inhalt der QuelleKhouri, Antoun. „Optimisation et mise en oeuvre d'algorithmes parallèles pour la reconnaissance de la parole“. Avignon, 1995. http://www.theses.fr/1995AVIG0110.
Der volle Inhalt der QuelleChardon, Marc. „Ordonnancement non préemptif à machines parallèles avec contraintes d'indisponibilité“. Compiègne, 2003. http://www.theses.fr/2003COMP1487.
Der volle Inhalt der QuelleThis thesis deals with the scheduling of tasks on parallel machines with unavailability constraints. Such a problem might be encountered in parallel computing, or in management of a production floor. The unitary execution time tasks scheduling problem is fundamental because it can be solving very efficiency. It is useful for the resolution of arbitrary duration tasks scheduling problem. There is a narrowest gap between the preemptive unitary execution time tasks scheduling problem and the arbitrary execution time tasks scheduling problem. If the durations of the tasks are bounded, we can use it to find lower bound for the general problem
Bird, Robert F. „Performance modelling and optimisation of inertial confinement fusion simulation codes“. Thesis, University of Warwick, 2016. http://wrap.warwick.ac.uk/78677/.
Der volle Inhalt der QuelleDetchart, Jonathan. „Optimisation de codes correcteurs d’effacements par application de transformées polynomiales“. Thesis, Toulouse, ISAE, 2018. http://www.theses.fr/2018ESAE0031/document.
Der volle Inhalt der QuelleErasure codes are widely used to cope with failures for nearly all of today’snetworks communications and storage systems. Most of these codes are based onfinite field arithmetic, defining the addition and the multiplication over a set offinite elements. These operations can be very complex to perform. As a matter offact, codes performance improvements are still an up to date topic considering thecurrent data growth explosion. We propose a method to transform the elements of some finite fields into ring elements and perform the operations in this ring to simplify both coding and decoding of erasure codes, without any threshold on the correction capacities.We also present a scheduling technique allowing to reduce the number of operations thanks to some particular properties of the ring structure. Finally, we analyse the performance ofsuch a method considering several hardware architectures and detail a simple implementation, using only xor operations, fully scalable over a multicore environment
Lalam, Massinissa. „Optimisation de la concaténation de codes spatio-temporels et de codes correcteurs d'erreurs dans une transmission MIMO“. Télécom Bretagne, 2006. http://www.theses.fr/2006TELB0022.
Der volle Inhalt der QuelleLeclerc, Catherine. „Analyse et optimisation des mécanismes parallèles entraînés par câbles : application au simulateur de vol“. Thesis, Université Laval, 2009. http://www.theses.ulaval.ca/2009/25926/25926.pdf.
Der volle Inhalt der QuelleBarreteau, Michel. „Optimisation du placement des scans et des réductions pour machines parallèles à mémoire répartie“. Versailles-St Quentin en Yvelines, 1998. http://www.theses.fr/1998VERS0001.
Der volle Inhalt der QuelleMoukrim, 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.
Der volle Inhalt der QuelleUpadrasta, Ramakrishna. „Sub-Polyhedral Compilation using (Unit-)Two-Variables-Per-Inequality Polyhedra“. Phd thesis, Université Paris Sud - Paris XI, 2013. http://tel.archives-ouvertes.fr/tel-00818764.
Der volle Inhalt der QuelleDelprat, Sébastien. „Evaluation de stratégies de commande pour véhicules hybrides parallèles“. Valenciennes, 2002. https://ged.uphf.fr/nuxeo/site/esupversions/493eb7bd-f6c9-4d5c-a6ba-13e8b9f0c855.
Der volle Inhalt der QuelleHybrid vehicles are usually propelled by one or two electric motor and an internal combustion engine. The first part of this study presents some classical mechanical arrangements and describes the prototype built at the LAMIH during a previous project. Then algorithms, called control strategy, are described. They choose at each sampling time the power split between the engine and the motor. Then this power split is written into the form of an optimization under constraint problem. Several algorithms based on the optimal control theory are proposed. Two new control strategy are proposed, based on the analysis of the global optimization results. Several criterions are proposed in order to characterize speed cycles, to evaluate control strategies
Alabau, Miguel. „Une expression des algorithmes massivement parallèles à structure de données irrégulières“. Bordeaux 1, 1994. http://www.theses.fr/1994BOR10569.
Der volle Inhalt der QuelleCavalec-Amis, Karine. „Optimisation des turbo codes pour les systèmes à grande efficacité spectrale“. Rennes 1, 2001. http://www.theses.fr/2001REN10096.
Der volle Inhalt der QuelleCayrel, Pierre-Louis. „Construction et optimisation de cryptosystèmes basés sur les codes correcteurs d'erreurs“. Limoges, 2008. https://aurore.unilim.fr/theses/nxfile/default/46aac3f7-1539-4684-bef6-9b1ae632c183/blobholder:0/2008LIMO4026.pdf.
Der volle Inhalt der QuelleIn this thesis, we are interested in the study of encryption systems as well as signature schemes whose security relies on difficult problems of error-correcting codes. These research activities have been motivated, a part of a theoretical point of view by creating : new signature schemes with special properties and a way of reducing the size of the key of the McEliece scheme, and on the other hand, a practical point of view to use structural properties to obtain effective implementations of a signature scheme which is based on error-correcting codes. As its title indicates, this thesis deals with the construction and optimization of cryptosystems based on error-correcting codes and more particularly five new protocols. It presents a secure version of the Stern scheme in a low-resources environment, a new construction of the Kabatianski, Krouk and Smeets scheme, a signature scheme based on the identity proved secure in the random oracle model, a threshold ring signature scheme and a reduction of the size of the key of the McEliece scheme using quasi-cyclic alternant codes. In the annex, this work deals with algebraic attacks against linear feedback shift register with memory. It also presents a brief study of cyclic codes on rings of matrices
Donadio, Sébastien. „Optimisation itérative de bibliothèques de calculs par division hiérarchique de codes“. Versailles-St Quentin en Yvelines, 2007. http://www.theses.fr/2007VERS0009.
Der volle Inhalt der QuelleLa complexité grandissante des architectures ne simplifie pas la tâche des compilateurs à générer du code performant. Les générateurs de bibliothèques comme ATLAS, FFTW et SPIRAL ont réussi à intégrer cette difficulté par l'utilisation de recherche itérative. Cette dernière génère différentes versions de programmes et sélectionne la meilleure d'entre elles. Cette thèse explore une solution automatique pour adapter les applications de calculs intensifs à l'architecture complexe des machines. Nous montrerons qu'une approche générative peut être un outil utile à l'implémentation d'une nouvelle approche de compilation hiérarchique pour la génération de code efficace. Cette approche, non spécifique, peut être appliquée sur des structures de boucle générales qu'elle divisera en des fragments de code plus simples à optimiser pour un compilateur. Nous proposerons une nouvelle approche de génération de bibliothèques qui s'appuiera sur la recomposition de ces codes avec un modèle très simplifié
Grishchenko, Dmitry. „Optimisation proximale avec réduction automatique de dimension“. Thesis, Université Grenoble Alpes, 2020. http://www.theses.fr/2020GRALM055.
Der volle Inhalt der QuelleIn this thesis, we develop a framework to reduce the dimensionality of composite optimization problems with sparsity inducing regularizers. Based on the identification property of proximal methods, we first develop a ``sketch-and-project'' method that uses projections based on the structure of the correct point. This method allows to work with random low-dimensional subspaces instead of considering the full space in the cases when the final solution is sparse. Second, we place ourselves in the context of the delay-tolerant asynchronous proximal methods and use our dimension reduction technique to decrease the total size of communications. However, this technique is proven to converge only for well-conditioned problems both in theory in practice.Thus, we investigate wrapping it up into a proximal reconditioning framework. This leads to a theoretically backed algorithm that is guaranteed to cost less in terms of communications compared with a non-sparsified version; we show in practice that it implies faster runtime convergence when the sparsity of the problem is sufficiently big
El, Baz Abdessamad. „Décodage conjoint source-canal : optimisation d'une chaîne de transmission pour images fixes“. Brest, 2002. http://www.theses.fr/2002BRES2008.
Der volle Inhalt der QuelleIn this thesis we considered the optimisation of a still image transmission system over noisy channel. The transmission system adopts a vector quantizer as a source encoder. The codebook used is built using kohonen's self organisation feature map algorithm which confers a topological organisation to the codebook vectors. Those vectors are associated in an optimal way to the constellation points of 16-QAM modulation used to transmit the data. By this association, the system becomes robust to the transmission errors. We then introduced a BCH forward error correction (FEC) code without altering the transmission system robustness to the errors. For this reason we have constrained the channel encoder. An additional constraint is imposed to this encoder to exploit the statistics of the source. When computing the BCH decoding decision rule, we take into account the probability distribution of the vectors generated by the source which we first regarded as independent but with non uniform distribution, and which we modelled in a second step as a first order Markov chain. The gain obtained in terms of BER and PSNR of the decoded image over the Gaussian channel and Rayleigh channel which we considered, are appreciable. We then replaced BCH FEC code by a BCH block turbo code. We took into account the statistics of the source in the calculation of the decision rule and the extrinsic information. The additional gain obtained in terms of PSNR of Lenna image decoded when using the new algorithms approaches the 11dB for low signal noise ratios, as compared to the classical algorithms. Many other images have been considered and the results show that the gain is highly dependent of the characteristics of the images but remains superior to classical algorithms
Chan, Evelyn Yu-San. „Heuristic optimisation for the minimum distance problem“. Thesis, Nottingham Trent University, 2000. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.324569.
Der volle Inhalt der QuelleSchmitt, Maxime. „Génération automatique de codes adaptatifs“. Thesis, Strasbourg, 2019. http://www.theses.fr/2019STRAD029.
Der volle Inhalt der QuelleIn this thesis we introduce a new application programming interface to help developers to optimize an application with approximate computing techniques. This interface is provided as a language extension to advise the compiler about the parts of the program that may be optimized with approximate computing and what can be done about them. The code transformations of the targeted regions are entirely handled by the compiler to produce an adaptive software. The produced adaptive application allocates more computing power to the locations where more precision is required, and may use approximations where the precision is secondary. We automate the discovery of the optimization parameters for the special class of stencil programs which are common in signal/image processing and numerical simulations. Finally, we explore the possibility of compressing the application data using the wavelet transform and we use information found in this basis to locate the areas where more precision may be needed
Weill-Duflos, Christine. „Optimisation de méthodes de résolution itératives de grands systèmes linéaires creux sur machines massivement parallèles“. Paris 6, 1994. http://www.theses.fr/1994PA066284.
Der volle Inhalt der QuellePaugam-Moisy, Hélène. „Optimisation des réseaux de neurones artificiels : analyse et mises en œuvre sur ordinateurs massivement parallèles“. Lyon 1, 1992. http://www.theses.fr/1992LYO10018.
Der volle Inhalt der Quelle