Les problèmes d'optimisation combinatoire sont souvent des problèmes très difficiles dont la résolution par des méthodes exactes peut s'avérer très longue ou peu réaliste. L'utilisation de méthodes heuristiques permet d'obtenir des solutions de bonne qualité en un temps de résolution raisonnable. Les heuristiques sont aussi très utiles pour le développement de méthodes exactes fondées sur des techniques d'évaluation et de séparation. Nous nous sommes intéressés dans un premier temps à proposer une méthode heuristique pour le problème du sac à dos multiple MKP. L'approche proposée est comparée à l'heuristique MTHM et au solveur CPLEX. Dans un deuxième temps nous présentons la mise en œuvre parallèle d'une méthode exacte de résolution de problèmes d'optimisation combinatoire de type sac à dos sur architecture GPU. La mise en œuvre CPU-GPU de la méthode de Branch and Bound pour la résolution de problèmes de sac à dos a montré une accélération de 51 sur une carte graphique Nvidia Tesla C2050. Nous présentons aussi une mise en œuvre CPU-GPU de la méthode du Simplexe pour la résolution de problèmes de programmation linéaire. Cette dernière offre une accélération de 12.7 sur une carte graphique Nvidia Tesla C2050. Enfin, nous proposons une mise en œuvre multi-GPU de l'algorithme du Simplexe, mettant à contribution plusieurs cartes graphiques présentes dans une même machine (2 cartes Nvidia Tesla C2050 dans notre cas). Outre l'accélération obtenue par rapport à la mise en œuvre séquentielle de la méthode du Simplexe, une efficacité de 96.5 % est obtenue, en passant d'une carte à deux cartes graphiques.

Les problèmes d'optimisation combinatoire sont souvent des problèmes très difficiles dont la résolution par des méthodes exactes peut s'avérer très longue ou peu réaliste. L'utilisation de méthodes heuristiques permet d'obtenir des solutions de bonne qualité en un temps de résolution raisonnable. Les heuristiques sont aussi très utiles pour le développement de méthodes exactes fondées sur des techniques d'évaluation et de séparation. Nous nous sommes intéressés dans un premier temps à proposer une méthode heuristique pour le problème du sac à dos multiple MKP. L'approche proposée est comparée à l'heuristique MTHM et au solveur CPLEX. Dans un deuxième temps nous présentons la mise en oeuvre parallèle d'une méthode exacte de résolution de problèmes d'optimisation combinatoire de type sac à dos sur architecture GPU. La mise en oeuvre CPU-GPU de la méthode de Branch and Bound pour la résolution de problèmes de sac à dos a montré une accélération de 51 sur une carte graphique Nvidia Tesla C2050. Nous présentons aussi une mise en oeuvre CPU-GPU de la méthode du Simplexe pour la résolution de problèmes de programmation linéaire. Cette dernière offre une accélération de 12.7 sur une carte graphique Nvidia Tesla C2050. Enfin, nous proposons une mise en oeuvre multi-GPU de l'algorithme du Simplexe, mettant à contribution plusieurs cartes graphiques présentes dans une même machine (2 cartes Nvidia Tesla C2050 dans notre cas). Outre l'accélération obtenue par rapport à la mise en oeuvre séquentielle de la méthode du Simplexe, une efficacité de 96.5 % est obtenue, en passant d'une carte à deux cartes graphiques.

Cette thèse traite de la modélisation et de l'approximation numérique des écoulements liquide-gaz compressibles. La difficulté essentielle réside dans la modélisation et l'approximation de l'interface liquide-gaz. Schématiquement, deux types de méthodes permettent l'étude de la dynamique de l'interface : l'approche eulérienne, aussi dite de capture de front ("front capturing method") et l'approche lagrangienne, de suivi de front ("front tracking method"). Nos travaux sont plutôt basés sur la méthode de capture de front. Le modèle bifluide est constitué d'un système de lois de conservation du premier ordre traduisant le bilan de masse, de quantité de mouvement et d'énergie du système physique. Ce système doit être fermé par une loi de pression du mélange gaz-liquide pour que sa résolution soit possible. Cette loi de comportement doit être choisie soigneusement, puisqu'elle conditionne les bonnes propriétés du système comme l'hyperbolicité ou l'existence d'une entropie de Lax. Les méthodes d'approximation doivent permettre de traduire au niveau discret ces propriétés. Les schémas conservatifs classiques de type Godunov peuvent être appliqués au modèle bifluide. Ils conduisent cependant à des imprécisions qui les rendent inutilisables en pratique. Enfin, l'existence de solutions discontinues rend difficile la construction de schémas d'ordre élevé. La structure complexe des solutions nécessite alors des maillages très fins pour une précision acceptable. Il est donc indispensable de proposer des algorithmes performants pour les calculateurs parallèles les plus récents. Au cours de cette thèse, nous allons aborder partiellement chacune de ces problématiques : construction d'une "bonne" loi de pression, construction de schémas numériques adaptés, programmation sur calculateur massivement multicoeur.

We numerically study the dynamics and interactions of vortex rings in the nonlinear Schrödinger equation (NLSE). Single ring dynamics for both bright and dark vortex rings are explored including their traverse velocity, stability, and perturbations resulting in quadrupole oscillations. Multi-ring dynamics of dark vortex rings are investigated, including scattering and merging of two colliding rings, leapfrogging interactions of co-traveling rings, as well as co-moving steady-state multi-ring ensembles. Simulations of choreographed multi-ring setups are also performed, leading to intriguing interaction dynamics. Due to the inherent lack of a close form solution for vortex rings and the dimensionality where they live, efficient numerical methods to integrate the NLSE have to be developed in order to perform the extensive number of required simulations. To facilitate this, compact high-order numerical schemes for the spatial derivatives are developed which include a new semi-compact modulus-squared Dirichlet boundary condition. The schemes are combined with a fourth-order Runge-Kutta time-stepping scheme in order to keep the overall method fully explicit. To ensure efficient use of the schemes, a stability analysis is performed to find bounds on the largest usable time step-size as a function of the spatial step-size. The numerical methods are implemented into codes which are run on NVIDIA graphic processing unit (GPU) parallel architectures. The codes running on the GPU are shown to be many times faster than their serial counterparts. The codes are developed with future usability in mind, and therefore are written to interface with MATLAB utilizing custom GPU-enabled C codes with a MEX-compiler interface. Reproducibility of results is achieved by combining the codes into a code package called NLSEmagic which is freely distributed on a dedicated website.

The work presented in this PhD studies and proposes cellular computation parallel models able to address different types of NP-hard optimization problems defined in the Euclidean space, and their implementation on the Graphics Processing Unit (GPU) platform. The goal is to allow both dealing with large size problems and provide substantial acceleration factors by massive parallelism. The field of applications concerns vehicle embedded systems for stereovision as well as transportation problems in the plane, as vehicle routing problems. The main characteristic of the cellular model is that it decomposes the plane into an appropriate number of cellular units, each responsible of a constant part of the input data, and such that each cell corresponds to a single processing unit. Hence, the number of processing units and required memory are with linear increasing relationship to the optimization problem size, which makes the model able to deal with very large size problems.The effectiveness of the proposed cellular models has been tested on the GPU parallel platform on four applications. The first application is a stereo-matching problem. It concerns color stereovision. The problem input is a stereo image pair, and the output a disparity map that represents depths in the 3D scene. The goal is to implement and compare GPU/CPU winner-takes-all local dense stereo-matching methods dealing with CFA (color filter array) image pairs. The second application focuses on the possible GPU improvements able to reach near real-time stereo-matching computation. The third and fourth applications deal with a cellular GPU implementation of the self-organizing map neural network in the plane. The third application concerns structured mesh generation according to the disparity map to allow 3D surface compressed representation. Then, the fourth application is to address large size Euclidean traveling salesman problems (TSP) with up to 33708 cities.In all applications, GPU implementations allow substantial acceleration factors over CPU versions, as the problem size increases and for similar or higher quality results. The GPU speedup factor over CPU was of 20 times faster for the CFA image pairs, but GPU computation time is about 0.2s for a small image pair from Middlebury database. The near real-time stereovision algorithm takes about 0.017s for a small image pair, which is one of the fastest records in the Middlebury benchmark with moderate quality. The structured mesh generation is evaluated on Middlebury data set to gauge the GPU acceleration factor and quality obtained. The acceleration factor for the GPU parallel self-organizing map over the CPU version, on the largest TSP problem with 33708 cities, is of 30 times faster.

As robotic systems move from well-controlled settings to increasingly unstructured environments, they are required to operate in highly dynamic and cluttered scenarios. Finding an object, estimating its pose, and tracking its pose over time within such scenarios are challenging problems. Although various approaches have been developed to tackle these problems, the scope of objects addressed and the robustness of solutions remain limited. In this thesis, we target a robust object perception using visual sensory information, which spans from the traditional monocular camera to the more recently emerged RGB-D sensor, in unstructured environments. Toward this goal, we address four critical challenges to robust 6-DOF object pose estimation and tracking that current state-of-the-art approaches have, as yet, failed to solve. The first challenge is how to increase the scope of objects by allowing visual perception to handle both textured and textureless objects. A large number of 3D object models are widely available in online object model databases, and these object models provide significant prior information including geometric shapes and photometric appearances. We note that using both geometric and photometric attributes available from these models enables us to handle both textured and textureless objects. This thesis presents our efforts to broaden the spectrum of objects to be handled by combining geometric and photometric features. The second challenge is how to dependably estimate and track the pose of an object despite the clutter in backgrounds. Difficulties in object perception rise with the degree of clutter. Background clutter is likely to lead to false measurements, and false measurements tend to result in inaccurate pose estimates. To tackle significant clutter in backgrounds, we present two multiple pose hypotheses frameworks: a particle filtering framework for tracking and a voting framework for pose estimation. Handling of object discontinuities during tracking, such as severe occlusions, disappearances, and blurring, presents another important challenge. In an ideal scenario, a tracked object is visible throughout the entirety of tracking. However, when an object happens to be occluded by other objects or disappears due to the motions of the object or the camera, difficulties ensue. Because the continuous tracking of an object is critical to robotic manipulation, we propose to devise a method to measure tracking quality and to re-initialize tracking as necessary. The final challenge we address is performing these tasks within real-time constraints. Our particle filtering and voting frameworks, while time-consuming, are composed of repetitive, simple and independent computations. Inspired by that observation, we propose to run massively parallelized frameworks on a GPU for those robotic perception tasks which must operate within strict time constraints.

Monte Carlo (MC) simulations are widely used in the field of medical biophysics, particularly for modelling light propagation in biological tissue. The iterative nature of MC simulations and their high computation time currently limit their use to solving the forward solution for a given set of source characteristics and tissue optical properties. However, applications such as photodynamic therapy treatment planning or image reconstruction in diffuse optical tomography require solving the inverse problem given a desired light dose distribution or absorber distribution, respectively. A faster means for performing MC simulations would enable the use of MC-based models for such tasks. In this thesis, a gold standard MC code called MCML was accelerated using two distinct hardware-based approaches, namely designing custom hardware on field-programmable gate arrays (FPGAs) and programming commodity graphics processing units (GPUs). Currently, the GPU-based approach is promising, offering approximately 1000-fold speedup with 4 GPUs compared to an Intel Xeon CPU.

This thesis presents an efficient self-consistent Hybrid Spectral Ray Tracing (HSRT) technique for analysis and design of multi-scale sub-millimeter wave problems, where sub-wavelength features are modeled using rigorous methods, and complex structures with dimensions in the order of tens or even hundreds of wavelengths are modeled by asymptotic methods. Quasi-optical devices are used in imaging arrays for sub-millimeter and terahertz applications, THz time-domain spectroscopy (THz-TDS), high-speed wireless communications, and space applications to couple terahertz radiation from space to a hot electron bolometer. These devices and structures, as physically small they have become, are very large in terms of the wavelength of the driving quasi-optical sources and may have dimension in the tens or even hundreds of wavelengths. Simulation and design optimization of these devices and structures is an extremely challenging electromagnetic problem. The analysis of complex electrically large unbounded wave structures using rigorous methods such as method of moments (MoM), finite element method (FEM), and finite difference time domain (FDTD) method can become almost impossible due to the need for large computational resources. Asymptotic high-frequency techniques are used for analysis of electrically large quasi-optical systems and hybrid methods for solving multi-scale problems. Spectral Ray Tracing (SRT) has a number of unique advantages as a candidate for hybridization. The SRT method has the advantages of Spectral Theory of Diffraction (STD). STD can model reflection, refraction and diffraction of an arbitrary wave incident on the complex structure, which is not the case for diffraction theories such as Geometrical Theory of Diffraction (GTD), Uniform theory of Diffraction (UTD) and Uniform Asymptotic Theory (UAT). By including complex rays, SRT can effectively analyze both near-fields and far-fields accurately with minimal approximations. In this thesis, a novel matrix representation of SRT is presented that uses only one spectral integration per observation point and applied to modeling a hemispherical and hyper-hemispherical lens. The hybridization of SRT with commercially available FEM and MoM software is proposed in this work to solve the complexity of multi-scale analysis. This yields a computationally efficient self-consistent HSRT algorithm. Various arrangements of the Hybrid SRT method such as FEM-SRT, and MoM-SRT, are investigated and validated through comparison of radiation patterns with Ansoft HFSS for the FEM method, FEKO for MoM, Multi-level Fast Multipole Method (MLFMM) and physical optics. For that a bow-tie terahertz antenna backed by hyper-hemispherical silicon lens, an on-chip planar dipole fabricated in SiGe:C BiCMOS technology and attached to a hyper-hemispherical silicon lens and a double-slot antenna backed by silica lens will be used as sample structures to be analyzed using the HSRT. Computational performance (memory requirement, CPU/GPU time) of developed algorithm is compared to other methods in commercially available software. It is shown that the MoM-SRT, in its present implementation, is more accurate than MoM-PO but comparable in speed. However, as shown in this thesis, MoM-SRT can take advantage of parallel processing and GPU. The HSRT algorithm is applied to simulation of on-chip dipole antenna backed by Silicon lens and integrated with a 180-GHz VCO and radiation pattern compared with measurements. The radiation pattern is measured in a quasi-optical configuration using a power detector. In addition, it is shown that the matrix formulation of SRT and HSRT are promising approaches for solving complex electrically large problems with high accuracy. This thesis also expounds on new measurement setup specifically developed for measuring integrated antennas, radiation pattern and gain of the embedded on-chip antenna in the mmW/ terahertz range. In this method, the radiation pattern is first measured in a quasi-optical configuration using a power detector. Subsequently, the radiated power is estimated form the integration over the radiation pattern. Finally, the antenna gain is obtained from the measurement of a two-antenna system.

Résumé non disponible / The race to computing power increases every day in the simulation community. A few years ago, scientists have started to harness the computing power of Graphics Processing Units (GPUs) to parallelize their simulations. As with any parallel architecture, not only the simulation model implementation has to be ported to the new parallel platform, but all the tools must be reimplemented as well. In the particular case of stochastic simulations, one of the major element of the implementation is the pseudorandom numbers source. Employing pseudorandom numbers in parallel applications is not a straightforward task, and it has to be done with caution in order not to introduce biases in the results of the simulation. This problematic has been studied since parallel architectures are available and is called pseudorandom stream distribution. While the literature is full of solutions to handle pseudorandom stream distribution on CPU-based parallel platforms, the young GPU programming community cannot display the same experience yet.In this thesis, we study how to correctly distribute pseudorandom streams on GPU. From the existing solutions, we identified a need for good software engineering solutions, coupled to sound theoretical choices in the implementation. We propose a set of guidelines to follow when a PRNG has to be ported to GPU, and put these advice into practice in a software library called ShoveRand. This library is used in a stochastic Polymer Folding model that we have implemented in C++/CUDA. Pseudorandom streams distribution on manycore architectures is also one of our concerns. It resulted in a contribution named TaskLocalRandom, which targets parallel Java applications using pseudorandom numbers and task frameworks.Eventually, we share a reflection on the methods to choose the right parallel platform for a given application. In this way, we propose to automatically build prototypes of the parallel application running on a wide set of architectures. This approach relies on existing software engineering tools from the Java and Scala community, most of them generating OpenCL source code from a high-level abstraction layer.

[pt] Modelagem e renderização baseadas em imagem tem sido uma área de pesquisa muito ativa nas últimas décadas, tendo recebido grande atenção como uma alternativa às técnicas tradicionais de síntese de imagens baseadas primariamente em geometria. Nesta área, algoritmos de visão computacional são usados para processar e interpretar fotos ou vídeos do mundo real a fim de construir um modelo representativo de uma cena, ao passo que técnicas de computação gráfica são usadas para tomar proveito desta representação e criar cenas foto-realistas. O propósito deste trabalho é investigar técnicas de renderização capazes de gerar vistas virtuais de alta qualidade de uma cena, em tempo real. Para garantir a performance interativa do algoritmo, além de aplicar otimizações a métodos de renderização existentes, fazemos uso intenso da GPU para o processamento de geometria e das imagens para gerar as imagens finais. Apesar do foco deste trabalho ser a renderização, sem reconstruir o mapa de profundidade a partir das fotos, ele implicitamente contorna possíveis problemas na estimativa da profundidade para que as cenas virtuais geradas apresentem um nível aceitável de realismo. Testes com dados públicos são apresentados para validar o método proposto e para ilustrar deficiências dos métodos de renderização baseados em imagem em geral. / [en] Image-based modeling and rendering has been a very active research topic as a powerful alternative to traditional geometry-based techniques for image synthesis. In this area, computer vision algorithms are used to process and interpret real-world photos or videos in order to build a model of a scene, while computer graphics techniques use this model to create photorealistic images based on the captured photographs or videos. The purpose of this work is to investigate rendering techniques capable of delivering visually accurate virtual views of a scene in real-time. Even though this work is mainly focused on the rendering task, without the reconstruction of the depth map, it implicitly overcomes common errors in depth estimation, yielding virtual views with an acceptable level of realism. Tests with publicly available datasets are also presented to validate our framework and to illustrate some limitations in the IBR general approach.