A simulação de propagação de onda é uma ferramenta crucial na pesquisa de geofísica (para análise eficiente dos terremotos, mitigação de riscos e a exploração de petróleo e gáz). Devido à sua simplicidade e sua eficiência numérica, o método de diferenças finitas é uma das técnicas implementadas para resolver as equações da propagação das ondas. Estas aplicações são conhecidas como estênceis porque consistem num padrão que replica a mesma computação num domínio multidimensional de dados. A Computação de Alto Desempenho é requerida para solucionar este tipo de problemas, como consequência do grande número de pontos envolvidos nas simulações tridimensionais do subsolo. A optimização do desempenho dos estênceis é um desafio e depende do arquitetura usada. Neste contexto, focamos nosso trabalho em duas partes. Primeiro, desenvolvemos nossa pesquisa nas arquiteturas multicore; analisamos a implementação padrão em OpenMP dos modelos numéricos da transferência de calor (um estêncil Jacobi de 7 pontos), e o aplicativo Ondes3D (um simulador sísmico desenvolvido pela Bureau de Recherches Géologiques et Minières); usamos dois algoritmos conhecidos (nativo, e bloqueio espacial) para encontrar correlações entre os parâmetros da configuração de entrada, na execução, e o desempenho computacional; depois, propusemos um modelo baseado no Aprendizado de Máquina para avaliar, predizer e melhorar o desempenho dos modelos estênceis na arquitetura usada; também usamos um modelo de propagação da onda acústica fornecido pela empresa Petrobras; e predizemos o desempenho com uma alta precisão (até 99%) nas arquiteturas multicore. Segundo, orientamos nossa pesquisa nas arquiteturas heterogêneas, analisamos uma implementação padrão do modelo de propagação de ondas em CUDA, para encontrar os fatores que afetam o desempenho quando o número de aceleradores é aumentado; então, propusemos uma implementação baseada em tarefas para amelhorar o desempenho, de acordo com um conjunto de configuração no tempo de execução (algoritmo de escalonamento, tamanho e número de tarefas), e comparamos o desempenho obtido com as versões de só CPU ou só GPU e o impacto no desempenho das arquiteturas heterogêneas; nossos resultados demostram um speedup significativo (até 25) em comparação com a melhor implementação disponível para arquiteturas multicore. / Wave modeling is a crucial tool in geophysics, for efficient strong motion analysis, risk mitigation and oil & gas exploration. Due to its simplicity and numerical efficiency, the finite-difference method is one of the standard techniques implemented to solve the wave propagation equations. This kind of applications is known as stencils because they consist in a pattern that replicates the same computation on a multi-dimensional domain. High Performance Computing is required to solve this class of problems, as a consequence of a large number of grid points involved in three-dimensional simulations of the underground. The performance optimization of stencil computations is a challenge and strongly depends on the underlying architecture. In this context, this work was directed toward a twofold aim. Firstly, we have led our research on multicore architectures and we have analyzed the standard OpenMP implementation of numerical kernels from the 3D heat transfer model (a 7-point Jacobi stencil) and the Ondes3D code (a full-fledged application developed by the French Geological Survey). We have considered two well-known implementations (naïve, and space blocking) to find correlations between parameters from the input configuration at runtime and the computing performance; thus, we have proposed a Machine Learning-based approach to evaluate, to predict, and to improve the performance of these stencil models on the underlying architecture. We have also used an acoustic wave propagation model provided by the Petrobras company and we have predicted the performance with high accuracy on multicore architectures. Secondly, we have oriented our research on heterogeneous architectures, we have analyzed the standard implementation for seismic wave propagation model in CUDA, to find which factors affect the performance; then, we have proposed a task-based implementation to improve the performance, according to the runtime configuration set (scheduling algorithm, size, and number of tasks), and we have compared the performance obtained with the classical CPU or GPU only versions with the results obtained on heterogeneous architectures.

Embora a utilização do concreto de alto desempenho (CAD) para a fabricação de elementos pré-moldados seja frequentemente usado na construção civil, o presente trabalho apresenta um estudo do emprego de microconcreto em aduelas tubulares de pequenas espessuras protendidas dentro de critérios fabris, com materiais regionais, a fim de repassar para a iniciativa privada os resultados colhidos das análises já elaboradas. As aduelas servirão para compor o tabuleiro de passarelas estaiadas, com a intenção de projetar uma estrutura que, além de harmônica aos olhos e arrojada, também seja econômica, pois se aplicando a protensão nas aduelas que formam o tabuleiro, pode-se explorar uma das características que os concretos de alto desempenho e resistência têm de melhor, que é a resistência à compressão (> 80MPa). Os materiais utilizados na dosagem do microconcreto para a confecção dos elementos em escala real, foram os seguintes: CP V ARI RS, sílica de ferro-silício em substituição volumétrica ao cimento em 10%, três tipos de areias de cava da região para o melhor empacotamento das partículas reduzindo os vazios, pedrisco basáltico com dimensão máxima de 9,5 mm em consonância com as características geométricas do elemento estrutural e da armadura e um superplastificante para atingir a consistência desejada. Levaram-se em conta na produção desse trabalho os recentes desenvolvidos havidos na reologia dos concretos frescos, ação da carbonatação e ação de cloretos. A consistência do concreto foi um fator importante para a determinação do traço, pois o concreto foi lançado nos moldes a uma altura de 2,40 m, permanecendo coeso. A concretagem foi realizada através de betonadas consecutivas para o total preenchimento do molde, onde em todas as betonadas foram realizadas a mesma seqüência de mistura pré-estabelecida. Foram moldadas duas aduelas em escala real, as quais foram estudadas seguindo a simulação do processo de montagem e uso da passarela, a fim de se analisar as solicitações atuantes e as formas de ruína das aduelas acopladas. As resistências mecânicas dos corpos-de-prova foram analisadas nas idades de 1, 3, 7, 28, 63 e 91 dias, cujos resultados de resistência à compressão simples, compressão diametral e o módulo de elasticidade atingiram ao previsto no projeto. O acabamento superficial, o tempo de lançamento, adensamento, desforma, cura e o transporte foram adequados para o reaproveitamento dos moldes. Com os resultados obtidos das análises realizadas com os dois módulos do tabuleiro, verificou-se a possibilidade de construir passarelas com elementos tubulares de pequena espessura protendidos com barras de Dywidag pelo sistema de protensão proposto. Verificou-se também uma pequena amplitude das deformações e deslocamentos das aduelas no processo de montagem e uso da passarela, assim como no transporte das aduelas. Não foram observadas a formação de quaisquer tipos de fissuras durante todo o processo envolvido, quais sejam, desmoldagem, estocagem, transporte, lançamento e utilização simulada. / Although the use of high performance concrete (HPC) for precast elements manufacture is frequently used in civil construction, this work presents a study of the utilization of microconcrete in prestressed small thicknesses tubular barrel stave, in manufacturing criteria, with regional materials, in order to repass to private initiative the already elaborated analyses results. Barrel stave will serve to compose cable-stayed footbridge deck, with the intent to project a structure that, beyond pleasant and bold, must be also economic, therefore applying prestress in barrel stave to form the deck, it\'s possible to explored the most important high performance and strength concrete characteristics, the compressive strength (> 80MPa). The used materials to design a microconcrete for the elements confection in real scale, are the following: CP V ARI RS, ferrosilicon silica fume in 10% volumetric substitution to the cement, three types of regional sands for optimum particles packing to reduce the emptinesses, 9,5 mm basaltic grave in accord with the geometric characteristics of the structural element and reinforcement, and superplasticizer additives to reach the desired consistency. Recent researches about fresh concrete rheology, carbonation and chloride action had been taken in account in the production of this work. The consistency was an important factor for concrete design, therefore the concrete would be was launched in 2,40 m height molds, remaining united. The molding was carried through consecutive load concrete mixer operation for the total fulfilling of the mold, where in all load of a concrete mixer had been carried through the same sequence of pre-established mixture. Two were molded barrel stave full scale, which were studied in the simulation of process of assembly and use of footbridge in order to examine the requests engaged in the forms of ruin from barrel stave coupled. The mechanical strength of the samples had been analyzed in ages of 1, 3, 7, 28, 63 and 91 days, whose results of simple compressive strength, diametrical compression and the modulus of elasticity had reached to the foreseen in project. The superficial finishing, the time of launching, compacting, desmoulding, cure and the transport had been adjusted for molds reuse. With the results of analyses conducted with two modules of deck, there was the possibility of building footbridges with tubular elements of small thickness prestressed with bars of Dywidag the system protention proposed. There was also a small extent of deformation and displacement of barrel stave in process of assembly and use of footbridge as well as the transport of barrel stave. Not been observed the formation of any types of cracks during all the involved process, which are, desmoulding, storage, transport, launching and simulated use.

A ligação entre concretos com cimento Portland de diferentes idades, composições e resistências é um dos problemas da tecnologia dos concretos estruturais. A continuidade desta ligação é prejudicada por uma diversidade de fatores que implicam desde a retomada de uma concretagem (junta fria) até a recuperação de estruturas de concreto deterioradas. Sob esse ponto de vista apresenta−se neste trabalho uma análise do comportamento de um sistema de reparos aplicados à recuperação de estruturas, ligações concretos velhos x concretos novos (caso das ampliações) e continuidades de concretagens. Um dos pontos mais frágeis de uma estrutura é a zona de interface, tanto dos materiais que a compõe quanto da transição entre os diferentes concretos. Utilizou−se como substrato corpos−de−prova prismáticos executados com concretos (fck=15MPa, 18MPa, 21MPa, 25MPa, 30MPa, 40MPa e 50MPa), que após ruptura completa através de ensaios de tração na flexão foi posteriormente executada ligação com concretos de reparo, e corpos−de−prova cilíndricos de concretos convencionais apresentando ninhos de concretagem. Com a finalidade de melhorar a zona de transição citada, utilizou−se como sistema de reparo, concretos de elevado desempenho executados com cimento Portland CP V ARI RS − NBR 5733⁄NBR 5737 − ABNT, agregados: miúdo de origem quartzosa, e graúdo de Dmáx ≤ 6,3 mm de origem basáltica, adições de sílica ativa (Fe−Si) de 5%, 10% e 15% e aditivo superplastificante de pega normal em teores de 1,5%, 1,8% e 2,0%, após prévio tratamento, através de desbaste superficial e imprimação com pastas de cimento de elevado desempenho. A eficácia da ligação é percebida principalmente pelo fato de que em resultados de ensaios de tração na flexão do corpo−de−prova prismático recuperado a ruptura ocorreu, em quase 100% dos casos na região do concreto velho. Em ensaios de compressão axial com corpos−de−prova cilíndricos com ninhos de concretagem recuperados, percebeu−se através do modo de ruptura, que as transferências de tensões ocorreram normalmente através do sistema de reparo, sem que houvesse desvio de tensões, além de um acréscimo de resistência em alguns casos. / The bonding among Portland cement concrete of different ages, compositions and resistances is one of the technological problems of structural concretes. The continuity of this connection is harmed by a several factors from the re−starting of a casting (cold joint) to the recovery of deteriorated concrete structures. From this point of view this paper presents an analysis of the behavior of a repair system applied to the recovery of structures, new−to−old concrete bonding (amplification cases) and casting continuities. One of the most fragile points of a concrete structure is the interface zone, of both materials that compose it and the transition among the different concretes. Prismatic specimens executed with concretes (fck=15MPa, 18MPa, 21MPa, 25 MPa, 30 MPa, 40 MPa and 50 MPa), were used as substratum after a previous complete rupture through a flexural strength test for a further connection, with repair concrete as a bond link, and cylindrical specimens of conventional concretes presenting intentionally \"holes\". High−performance concretes with Portland cement CP V ARI RS (NBR 5733⁄NBR 5737 − ABNT), small quartz aggregates, basaltic coarse aggregates with Dmáx ≤ 6,3mm, silica fume (Fe−Si) additions of 5%, 10% and 15%, and normal setting superplasticizer with contents of 1,5%, 1,8% and 2,0% were used as repair system to improve the transition zone mentioned. Such materials were used after the specimens had been treated superficially and primed with High−performance Portland cement paste. The effectiveness of the connection is noticed mainly by the fact that in results of the flexural strength test of recovered prismatic specimens, the rupture occurred in almost 100% of the cases in the area of the old concrete. In axial compression tests with cylindrical specimens presenting recovered \"holes\", the rupture way demonstrated that the transfers of tensions usually occurred through the repair system, with no tension deviation, and there was a resistance increase in some cases.

Per job isolation of temporary file storage in High Performance Computing (HPC) environments provide benefits in security, efficiency, and administration. HPC system administrators can use the mount_isolation Slurm task plugin to improve security by isolating temporary files where no isolation previously existed. The mount_isolation plugin also increases efficiency by removing obsolete temporary files immediately after each job terminates. This frees valuable disk space in the HPC environment to be used by other jobs. These two improvements reduce the amount of work system administrators must expend to ensure temporary files are removed in a timely manner.Previous temporary file removal solutions were removal on reboot, manual removal, or removal through a Slurm epilog script. The epilog script was the most effective of these, allowing files to be removed in a timely manner. However, HPC users can have multiple supercomputing jobs running concurrently. Temporary files generated by these concurrent or overlapping jobs are only deleted by the epilog script when all jobs run by that user on the compute node have completed. Even though the user may have only one running job, the temporary directory may still contain temporary files from many previously executed jobs, taking up valuable temporary storage on the compute node. The mount_isolation plugin isolates these temporary files on a per job basis allowing prompt removal of obsolete files regardless of job overlap.

La simulation numérique fait partie intégrante du processus d'analyse. Que l'on veuille concevoir le profil d'un véhicule, ou chercher à prévoir le résultat d'un forage pétrolier, la simulation numérique est devenue un outil complémentaire à la théorie et aux expérimentations. Cet outildoit produire des résultats précis en un minimum de temps. Pour cela, nous avons à disposition des méthodes numériques précises, et des machines de calcul aux performances importantes. Cet outil doit être générique sur les maillages, l'ordre de la solution, les méthodes numériques, et doitmaintenir ses performances sur les machines de calculs modernes avec une hiérarchie complexes d'unité de calculs. Nous présentons dans cette thèse le background mathématiques de deux classes de schémas numériques, les méthodes aux éléments finis continus et discontinus. Puis nous présentons les enjeux de la conception d'une plateforme en prenant en compte l'ensemble de ces contraintes. Ensuite nous nous intéressons au sous-problème de l'assemblage au dessus d'un support d'exécution. L'opération d'assemblage se retrouve en algèbre linéaire dans les méthodes multi-frontales ou dans les applications de simulations assemblant un système linéaire. Puis, nous concluons en dressant un bilan sur la plateforme AeroSol et donnons des pistes d'évolution possibles. / Numerical simulation is nowadays an essential part of engineering analysis, be it to design anew plane, or to detect underground oil reservoirs. Numerical simulations have indeed become an important complement to theoretical and experimental investigation, allowing one to reduce the cost of engineering design processes. In order to achieve a high level of precision, one need to increase the resolution of his computational domain. So to keep getting results in reasonable time, one shall nd a way to speed-up computations. To do this, we use high performance computing, HPC, to exploit the complex architecture of modern supercomputers. Under these two constraints, and some other like the genericity of finite elements, or the mesh dimension, we developed a new platform AeroSol. In this thesis, we present the mathematical background, and the two types of schemes that are implemented in the platform, the continuous finite elements method, and the discontinuous one. Then, we present the design choices made in the platform,then, we study a sub-problem, the assembly operation, which can be found in linear algebra multi-frontal methods.

<p>Client-side computers connected to the Internet today are exposed to a lot malicious activity. Browsing the web can easily result in malware infection even if the user only visits well known and trusted sites. Attackers use website vulnerabilities and ad-networks to expose their malicious code to a large user base. The continuing trend of the attackers seems to be botnet construction that collects large amounts of data which could be a serious threat to company secrets and personal integrity. Meanwhile security researches are using a technology known as honeypots/honeyclients to find and analyze new malware. This thesis takes the concept of honeyclients and combines it with a proxy and database software to construct a new kind of real time defense mechanism usable in live environments. The concept is given the name Honeyscout and it analyzes any content before it reaches the user by using visited sites as a starting point for further crawling, blacklisting any malicious content found. A proof-of-concept honeyscout has been developed using the honeyclient Monkey-Spider by Ali Ikinci as a base. Results from the evaluation shows that the concept has potential as an effective and user-friendly defense technology. There are however large needs to further optimize and speed up the crawling process.</p>

Mathematical and statistical modeling of biological systems is a desired goal for many years. Many biochemical models are often evaluated using a deterministic approach, which uses differential equations to describe the chemical interactions. However, such an approach is inaccurate for small species populations as it neglects the discrete representation of population values, presents the possibility of negative populations, and does not represent the stochastic nature of biochemical systems. The Stochastic Simulation Algorithm (SSA) developed by Gillespie is able to properly account for these inherent noise fluctuations. Due to the stochastic nature of the Monte Carlo simulations, large numbers of simulations must be run in order to get accurate statistics for the species populations and reactions. However, the algorithm tends to be computationally heavy and leads to long simulation runtimes for large systems. Therefore, this thesis explores implementing the SSA on a Field Programmable Gate Array (FPGA) to improve performance. Employing the Field programmable Gate Arrays exploits the parallelism present in the SSA, providing speedup over the software implementations that execute sequentially. In contrast to prior work that requires re-construction and re-synthesis of the design to simulate a new biochemical system, this work explores the use of reconfigurable hardware in implementing a generic biochemical simulator.

Ces dernières années, la virtualisation a connu un important regain d'intérêt dans les centres de traitement de données. Elle séduit par la grande flexibilité qu'elle apporte, par ses propriétés d'isolation et de tolérance aux pannes ainsi que par sa capacité à tirer partie des processeurs multicoeurs. Toutes ces caractéristiques en font une solution intéressante pour répondre aux problèmes liés aux évolutions matérielles des grappes de calcul. Cependant, la virtualisation est encore peu mise en oeuvre dans ce cadre, notamment car son impact sur les performances des applications parallèles est considéré comme prohibitif. Pour pallier ce problème, nous avons conçu un périphérique virtuel de communication permettant l'exécution efficace d'applications parallèles dans une grappe de machines virtuelles. Nous proposons en outre un ensemble de techniques permettant de faciliter le déploiement d'applications virtualisées. Ces fonctionnalités ont été regroupées au sein d'un support exécutif permettant de bénéficier des avantages de la virtualisation de la manière la plus transparente possible pour l'utilisateur, et ce en minimisant l'impact sur les performances.

Optimized implementations of blocking and nonblocking collective operations are most important for scalable high-performance applications. Offloading such collective operations into the communication layer can improve performance and asynchronous progression of the operations. However, it is most important that such offloading schemes remain flexible in order to support user-defined (sparse neighbor) collective communications. In this work we propose a design for a collective offload unit. Our hardware design is able to execute dependency graph based representations of collective functions. To cope with the scarcity of memory resources we designed a new point to point messaging protocol which does not need to store information about unexpected messages. The offload unit proposed in this thesis could be integrated into high performance networks such as EXTOLL. Our design achieves a clock frequency of 212 MHz on a Xilinx Virtex6 FPGA, while using less than 10% of the available logic slices and less than 30% of the available memory blocks. Due to the specialization of our design we can accelerate important tasks of the message passing framework, such as message matching by a factor of two, compared to a software implementation running on a CPU with a ten times higher clock speed.

<p>We study techniques to enforce and provision differentiated service levels in <i>Computational Grid</i> systems. The Grid offers simplified provisioning of peak-capacity for applications with computational requirements beyond local machines and clusters, by sharing resources across organizational boundaries. Current systems have focussed on access control, i.e., managing who is allowed to run applications on remote sites. Very little work has been done on providing differentiated service levels for those applications that are admitted. This leads to a number of problems when scheduling jobs in a fair and efficient way. For example, users with a large number of long-running jobs could starve out others, both intentionally and non-intentionally. We investigate the requirements of High Performance Computing (HPC) applications that run in academic Grid systems, and propose two models of service-level management. Our first model is based on global real-time quota enforcement, where projects are granted resource quota, such as CPU hours, across the Grid by a centralized allocation authority. We implement the SweGrid Accounting System to enforce quota allocated by the Swedish National Allocations Committee in the SweGrid production Grid, which connects six Swedish HPC centers. A flexible authorization policy framework allows provisioning and enforcement of two different service levels across the SweGrid clusters; high-priority and low-priority jobs. As a solution to more fine-grained control over service levels we propose and implement a <i>Grid</i> <i>Market </i>system, using a market-based resource allocator called Tycoon. The conclusion of our research is that although the Grid accounting solution offers better service level enforcement support than state-of-the-art production Grid systems, it turned out to be complex to set the resource price and other policies manually, while ensuring fairness and efficiency of the system. Our Grid Market on the other hand sets the price according to the dynamic demand, and it is further incentive compatible, in that the overall system state remains healthy even in the presence of strategic users.</p>