Les systèmes de calcul actuels sont généralement des grappes de machines composés de nombreux processeurs à l'architecture fortement hiérarchique. Leur exploitation constitue le défi majeur des implémentations de modèles de programmation tels MPI ou OpenMP. Une pratique courante consiste à mélanger ces deux modèles pour bénéficier des avantages de chacun. Cependant ces modèles n'ont pas été pensés pour fonctionner conjointement ce qui pose des problèmes de performances. Les travaux de cette thèse visent à assister le développeur dans la programmation d'application de type hybride. Il s'appuient sur une analyse de la hiérarchie architecturale du système de calcul pour dimensionner les ressources d'exécution (processus et threads). Plutôt qu'une approche hybride classique, créant un processus MPI multithreadé par noeud, nous évaluons de façon automatique des solutions alternatives, avec plusieurs processus multithreadés par noeud, mieux adaptées aux machines de calcul modernes.

This thesis describes techniques for defining independent tasks in Java programs forparallelization. Existing Java parallelization APIs like JOMP, Parallel Java,Deterministic Parallel Java, JConqurr and JaMP are discussed. We have seen that JaMPis an implementation of OpenMP for Java, and it has a set of OpenMP directives andruntime library functions. We have discussed that JaMP has source to byte codecompiler, and it does not help in debugging the parallel source codes. There is no designtime syntax checking support of JaMP directives, and we know about mistakes onlywhen we compile the source code with JaMP compiler. So we have decided tocontribute JaMP with adding an option in the compiler to get parallel source code. Wehave created an eclipse plug-in to support design time syntax checking of JaMPdirectives too. It also helps the programmers to get quickly parallel source code withjust one click instead of using shell commands with JaMP compiler.

L'assimilation variationnelle de données 4D-Var est une technique très utilisée en géophysique, notamment en météorologie et océanographie. Elle consiste à estimer des paramètres d'un modèle numérique direct, en minimisant une fonction de coût mesurant l'écart entre les sorties du modèle et les mesures observées. La minimisation, qui est basée sur une méthode de gradient, nécessite le calcul du modèle adjoint (produit de la transposée de la matrice jacobienne avec le vecteur dérivé de la fonction de coût aux points d'observation). Lors de la mise en œuvre de l'AD 4D-Var, il faut faire face à des problèmes d'implémentation informatique complexes, notamment concernant le modèle adjoint, la parallélisation du code et la gestion efficace de la mémoire. Afin d'aider au développement d'applications d'AD 4D-Var, le logiciel YAO qui a été développé au LOCEAN, propose de modéliser le modèle direct sous la forme d'un graphe de flot de calcul appelé graphe modulaire. Les modules représentent des unités de calcul et les arcs décrivent les transferts des données entre ces modules. YAO est doté de directives de description qui permettent à un utilisateur de décrire son modèle direct, ce qui lui permet de générer ensuite le graphe modulaire associé à ce modèle. Deux algorithmes, le premier de type propagation sur le graphe et le second de type rétropropagation sur le graphe permettent, respectivement, de calculer les sorties du modèle direct ainsi que celles de son modèle adjoint. YAO génère alors le code du modèle direct et de son adjoint. En plus, il permet d'implémenter divers scénarios pour la mise en œuvre de sessions d'assimilation.Au cours de cette thèse, un travail de recherche en informatique a été entrepris dans le cadre du logiciel YAO. Nous avons d'abord formalisé d'une manière plus générale les spécifications deYAO. Par la suite, des algorithmes permettant l'automatisation de certaines tâches importantes ont été proposés tels que la génération automatique d'un parcours "optimal" de l'ordre des calculs et la parallélisation automatique en mémoire partagée du code généré en utilisant des directives OpenMP. L'objectif à moyen terme, des résultats de cette thèse, est d'établir les bases permettant de faire évoluer YAO vers une plateforme générale et opérationnelle pour l'assimilation de données 4D-Var, capable de traiter des applications réelles et de grandes tailles.

This study deals with the use of high-order spectral/hp approximation functions in the finite element models of various nonlinear boundary-value and initial-value problems arising in the fields of structural mechanics and flows of viscous incompressible fluids. For many of these classes of problems, the high-order (typically, polynomial order p greater than or equal to 4) spectral/hp finite element technology offers many computational advantages over traditional low-order (i.e., p < 3) finite elements. For instance, higher-order spectral/hp finite element procedures allow us to develop robust structural elements for beams, plates, and shells in a purely displacement-based setting, which avoid all forms of numerical locking. The higher-order spectral/hp basis functions avoid the interpolation error in the numerical schemes, thereby making them accurate and stable. Furthermore, for fluid flows, when combined with least-squares variational principles, such technology allows us to develop efficient finite element models, that always yield a symmetric positive-definite (SPD) coefficient matrix, and thereby robust direct or iterative solvers can be used. The least-squares formulation avoids ad-hoc stabilization methods employed with traditional low-order weak-form Galerkin formulations. Also, the use of spectral/hp finite element technology results in a better conservation of physical quantities (e.g., dilatation, volume, and mass) and stable evolution of variables with time in the case of unsteady flows. The present study uses spectral/hp approximations in the (1) weak-form Galerkin finite element models of viscoelastic beams, (2) weak-form Galerkin displacement finite element models of shear-deformable elastic shell structures under thermal and mechanical loads, and (3) least-squares formulations for the Navier-Stokes equations governing flows of viscous incompressible fluids. Numerical simulations using the developed technology of several non-trivial benchmark problems are presented to illustrate the robustness of the higher-order spectral/hp based finite element technology.

Les processeurs graphiques (GPU), originellement dédiés à l'accélération de traitements graphiques, ont une structure hautement parallèle. Les innovations matérielles et de langage de programmation ont permis d'ouvrir le domaine du GPGPU, où les cartes graphiques sont utilisées comme des accélérateurs de calcul pour des applications HPC généralistes. L'objectif de nos travaux est de faciliter l'utilisation de ces nouvelles architectures pour les besoins du calcul haute performance ; ils suivent deux objectifs complémentaires. Le premier axe de nos recherches concerne la transformation automatique de code, permettant de partir d'un code de haut niveau pour le transformer en un code de bas niveau, équivalent, pouvant être exécuté sur des accélérateurs. Dans ce but nous avons implémenté un transformateur de code capable de prendre en charge les boucles " pour " parallèles d'un code OpenMP (simples ou imbriquées) et de le transformer en un code CUDA équivalent, qui soit suffisamment lisible pour permettre de le retravailler par des optimisations ultérieures. Par ailleurs, le futur des architectures HPC réside dans les architectures distribuées basées sur des noeuds dotés d'accélérateurs. Pour permettre aux utilisateurs d'exploiter les noeuds multiGPU, il est nécessaire de mettre en place des schémas d'exécution appropriés. Nous avons mené une étude comparative et mis en évidence que les threads OpenMP permettent de gérer de manière efficace plusieurs cartes graphiques et les communications au sein d'un noeud de calcul multiGPU.

Submitted by HETHINI DO NASCIMENTO RIBEIRO (hethini.ribeiro@outlook.com) on 2018-10-08T23:20:34Z No. of bitstreams: 1 Dissertação_hethini.pdf: 1986842 bytes, checksum: f1d6e8b9be8decd1fb1e992204d2b2d0 (MD5) / Rejected by Elza Mitiko Sato null (elzasato@ibilce.unesp.br), reason: Solicitamos que realize correções na submissão seguindo as orientações abaixo: Problema 01) A FICHA CATALOGRÁFICA (Obrigatório pela ABNT NBR14724) está desconfigurada e falta número do CDU. Problema 02) Falta citação nos agradecimentos, segundo a Portaria nº 206, de 4 de setembro de 2018, todos os trabalhos que tiveram financiamento CAPES deve constar nos agradecimentos a expressão: "O presente trabalho foi realizado com apoio da Coordenação de Aperfeiçoamento de Pessoal de Nível Superior - Brasil (CAPES) - Código de Financiamento 001 Problema 03) Falta o ABSTRACT (resumo em língua estrangeira), você colocou apenas o resumo em português. Problema 04) Na lista de tabelas, a página referente a Tabela 9 está desconfigurada. Problema 05) A cidade na folha de aprovação deve ser Bauru, cidade onde foi feita a defesa. Bauru 31 de agosto de 2018 Problema 06) A paginação deve ser sequencial, iniciando a contagem na folha de rosto e mostrando o número a partir da introdução, a ficha catalográfica ficará após a folha de rosto e não deverá ser contada. OBS:-Estou encaminhando via e-mail o template/modelo das páginas pré-textuais para que você possa fazer as correções da paginação, sugerimos que siga este modelo pois ele contempla as normas da ABNT Lembramos que o arquivo depositado no repositório deve ser igual ao impresso, o rigor com o padrão da Universidade se deve ao fato de que o seu trabalho passará a ser visível mundialmente. Agradecemos a compreensão on 2018-10-09T14:18:32Z (GMT) / Submitted by HETHINI DO NASCIMENTO RIBEIRO (hethini.ribeiro@outlook.com) on 2018-10-10T00:30:40Z No. of bitstreams: 1 Dissertação_hethini_corrigido.pdf: 1570340 bytes, checksum: a42848ab9f1c4352dcef8839391827a7 (MD5) / Approved for entry into archive by Elza Mitiko Sato null (elzasato@ibilce.unesp.br) on 2018-10-10T14:37:37Z (GMT) No. of bitstreams: 1 ribeiro_hn_me_sjrp.pdf: 1566499 bytes, checksum: 640247f599771152e290426a2174d30f (MD5) / Made available in DSpace on 2018-10-10T14:37:37Z (GMT). No. of bitstreams: 1 ribeiro_hn_me_sjrp.pdf: 1566499 bytes, checksum: 640247f599771152e290426a2174d30f (MD5) Previous issue date: 2018-08-31 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / No início desta década havia cerca de 5 bilhões de telefones em uso gerando dados. Essa produção global aumentou aproximadamente 40% ao ano no início da década passada. Esses grandes conjuntos de dados que podem ser capturados, comunicados, agregados, armazenados e analisados, também chamados de Big Data, estão colocando desafios inevitáveis em muitas áreas e, em particular, no campo Machine Learning. Algoritmos de Machine Learning são capazes de extrair informações úteis desses grandes repositórios de dados e por este motivo está se tornando cada vez mais importante o seu estudo. Os programas aptos a realizarem essa tarefa podem ser chamados de algoritmos de classificação e clusterização. Essas aplicações são dispendiosas computacionalmente. Para citar alguns exemplos desse custo, o algoritmo Quality Threshold Clustering tem, no pior caso, complexidade O(�������������5). Os algoritmos hierárquicos AGNES e DIANA, por sua vez, possuem O(n²) e O(2n) respectivamente. Sendo assim, existe um grande desafio, que consiste em processar grandes quantidades de dados em um período de tempo realista, encorajando o desenvolvimento de algoritmos paralelos que se adequam ao volume de dados. O objetivo deste trabalho é apresentar a paralelização do algoritmo de hierárquico divisivo DIANA. O desenvolvimento do algoritmo foi realizado em MPI e OpenMP, chegando a ser três vezes mais rápido que a versão monoprocessada, evidenciando que embora em ambientes de memória distribuídas necessite de sincronização e troca de mensagens, para um certo grau de paralelismo é vantajosa a aplicação desse tipo de otimização para esse algoritmo. / Earlier in this decade there were about 5 billion phones in use generating data. This global production increased approximately 40% per year at the beginning of the last decade. These large datasets that can be captured, communicated, aggregated, stored and analyzed, also called Big Data, are posing inevitable challenges in many areas, and in particular in the Machine Learning field. Machine Learning algorithms are able to extract useful information from these large data repositories and for this reason their study is becoming increasingly important. The programs that can perform this task can be called classification and clustering algorithms. These applications are computationally expensive. To cite some examples of this cost, the Quality Threshold Clustering algorithm has, in the worst case, complexity O (n5). The hierarchical algorithms AGNES and DIANA, in turn, have O (n²) and O (2n) respectively. Thus, there is a great challenge, which is to process large amounts of data in a realistic period of time, encouraging the development of parallel algorithms that fit the volume of data. The objective of this work is to present the parallelization of the DIANA divisive hierarchical algorithm. The development of the algorithm was performed in MPI and OpenMP, reaching three times faster than the monoprocessed version, evidencing that although in distributed memory environments need synchronization and exchange of messages, for a certain degree of parallelism it is advantageous to apply this type of optimization for this algorithm. / 1757857

Hlavním cílem této práce je navrhnout novu metodu rekonstrukce obrazu z dat fotoakustického snímkování. Fotoakustické snímkování je velmi populární neinvazivní metoda snímkování založená na detekování ultrazvukových vln vyvolaných laserovým paprskem. Proces snímkování generuje velké množství dat, a kvůli tomu je proces rekonstrukce obrazu velmi časově náročný. Táto práce demonstruje proces rekonstrukce obrazu pomocí zpětné projekce, algoritmu který je dostatečně jednoduchý na přizpůsobení moderním architekturám procesorů umožňující různé způsoby optimalizovaného výpočtu. Dvě různé variantu algoritmu byly navrženy: z pohledu pixelu a z pohledu senzoru, který detekuje ultrazvukové vlny. Obě varianty byly implementovány třemi různými způsoby: pomocí vektorového paralelismu, vláknového paralelismu a paralelismu na grafické karetě (GPU). Všechny 3 implementace obou variant algoritmu byly testovány a výsledky byly srovnány s výsledkem rekonstrukce algoritmu reverzního času, přesnějšího ale mnohokrát pomalejšího algoritmu. Výsledky ukázaly, že GPU paralelismus nabízí nejrychlejší výpočet, cca. 200 krát rychlejší než u algoritmu reverzního času, a proto se dá použit i v aplikacích pracující v reálném čase.

Nowadays, the simulation of ultrasound acoustic waves has a wide range of practical usage. As one of them we can name the simulation in realistic tissue media, which is successfully used in medicine. There are several software applications dedicated to perform such simulations. k-Wave is one of them. The computational difficulty of the simulation itself is very high, and this leaves a space to explore new speed-up methods. In this master's thesis, we proposed a way to speed-up the simulation based on parallelization using Intel Xeon Phi accelerator. The accelerator contains large amount of cores and an extra-wide vector unit, and therefore, is ideal for purpose of parallelization and vectorization. The implementation is using OpenMP version 4.0, which brings some new options such as explicit vectorization. Results were measured during extensive experiments.

SkePU 3 is a framework for parallel program execution that uses higher order functions called skeletons, which provide a layer of abstraction between user code and the parallel implementation it provides through its backends. The backend that enables SkePU to run on an HPC cluster has a slowdown of a factor two. This reduces the viability of SkePU as an alternative for HPC, and as such, warrants an investigation. Programs written in SkePU are sequential-looking, single-source C++ programs where skeleton calls can transparently execute on multiple different types of processing units, such as CPU cores, GPUs and clusters, using different backends. In this thesis, a strategy for improving the performance of SkePU on clusters is presented, and with it, the design and implementation of a new cluster backend that is simpler and more closely integrated with the non-cluster SkePU code base. Runtime measurements are made, which show that the new cluster backend sees a relative speedup of about a factor of two, which effectively eliminates the slowdown.

Den här studien beskriver hur grafikkort kan användas på en bredare front änmultimedia. Arbetet förklarar och diskuterar huvudsakliga alternativ som finnstill att använda grafikkort till generella operationer i dagsläget. Inom denna studieanvänds Nvidias CUDA arkitektur. Studien beskriver hur grafikkort användstill egna operationer rent praktiskt ur perspektivet att vi redan kan programmerai högnivåspråk och har grundläggande kunskap om hur en dator fungerar. Vianvänder s.k. accelererade bibliotek på grafikkortet (THRUST och CUBLAS) föratt uppnå målet som är utveckling av programvara och prestandatest. Resultatetär program som använder GPU:n till generella och prestandatest av dessa,för lösning av olika problem (matrismultiplikation, sortering, binärsökning ochvektor-inventering) där grafikkortet jämförs med processorn seriellt och parallellt.Resultat visar att grafikkortet exekverar upp till ungefär 50 gånger snabbare(tidsmässigt) kod jämfört med seriella program på processorn. / This study describes how we can use graphics cards for general purpose computingwhich differs from the most usual field where graphics cards are used, multimedia.The study describes and discusses present day alternatives for usinggraphic cards for general operations. In this study we use and describe NvidiaCUDA architecture. The study describes how we can use graphic cards for generaloperations from the point of view that we have programming knowledgein some high-level programming language and knowledge of how a computerworks. We use accelerated libraries (THRUST and CUBLAS) to achieve our goalson the graphics card, which are software development and benchmarking. Theresults are programs countering certain problems (matrix multiplication, sorting,binary search, vector inverting) and the execution time and speedup forthese programs. The graphics card is compared to the processor in serial andthe processor in parallel. Results show a speedup of up to approximatly 50 timescompared to serial implementations on the processor.