Multi-GPU support on the marrow algorithmic skeleton framework

Dissertação para obtenção do Grau de Mestre em Engenharia Informática

Maintaining the correctness of transactional memory programs

Dissertação para obtenção do Grau de Doutor em Engenharia Informática

O biofeedback cinemático na realização de exercícios escápulo-torácicos

RESUMO: O Biofeedback cinemático na realização de exercícios escápulo-torácicos Patrícia Ribeiro; Ricardo Matias Desenho do estudo: Estudo quantitativo, experimental, prospetivo de fator único. Objetivos: Determinar a efetividade do biofeedback cinemático tridimensional (3D) em tempo real, como informação de retorno extrínseca, no reconhecimento da zona neutra da omoplata, em indivíduos saudáveis; medir o desempenho temporal, através do tempo que os sujeitos demoram a atingir a posição pretendida, e o desempenho no percurso, através da diferença entre o percurso efetuado e aquele que seria o percurso mais curto, sem Informação de Retorno Extrínseca (IRE), com Informação de Retorno Extrínseca clinica verbal e palpatória (IRE-VP) e com informação de retorno extrínseca visual cinemática (IRE-VC). Enquadramento: Reconhecer aquela que deve ser a posição adequada da omoplata e tomar consciência da importância dessa posição para a estabilidade e correto funcionamento da articulação gleno-umeral é uma tarefa difícil, pois a grande maioria do indivíduos não têm os conhecimentos necessários. É reconhecido o contributo que a IRE tem na reaprendizagem motora, em especial na primeira fase da aprendizagem motora – a consciencialização. Vários estudos se têm debruçado em avaliar a influencia da IRE na reabilitação de indivíduos com disfunção do ombro, tendo-se limitado ao formato electromiográfico. No sentido de encontrar novas estratégias para facilitar o processo de reaprendizagem motora nestes indivíduos, foi escolhido biofeedback cinemático tridimensional. Métodos: Participaram no estudo 60 sujeitos, sem queixas de dor no ombro, com idades compreendidas entre os 18 e os 54 anos, com um valor médio de 21,66 anos (±5.89), divididos aleatoriamente em três grupos com uma tarefa comum: o reconhecimento da zona neutra da omoplata. Um grupo não recebeu qualquer tipo de IRE - Grupo Controlo (GC), outro grupo recebeu IRE-VP e outro recebeu IRE-VC. Para efeitos de análise da performance foram consideradas duas variáveis: tempo e qualidade da execução. A abordagem estatística destas variáveis consistiu numa análise de variância simples e num teste de comparações múltiplas. Resultados: Observámos que o grupo controlo e o grupo IRE-VC efetuaram a tarefa pedida em menos tempo que o grupo IRE-VP (p<0.01) e que o grupo IRE-VC obteve melhores resultados no que respeita à qualidade da execução da tarefa do que o GC e o grupo IRE-VP (p<0.01). Conclusão: Pelos resultados obtidos, na tarefa de reconhecimento da zona neutra da omoplata, podemos concluir que o biofeedback cinemático é mais efetivo na facilitação da obtenção de melhor qualidade de execução da tarefa do que o feedback clinico ou a inexistência de feedback e igualmente efetivo à inexistência de IRE no que respeita ao tempo demorado a reconhecer essa posição. -------------- ABSTRACT:Study Design: Single factor experimental design. Objectives: To determine the effectiveness of real time cinematic biofeedback as extrinsic information in the recognition of the neutral zone of the scapula in healthy subjects; to measure the temporal performance and quality of the execution without extrinsic feedback, with clinical feedback and with cinematic feedback. Background: To recognize the proper scapula position and to be aware of the importance of this position to the stability and correct function of the gleno-umeral joint is a difficult task, because most people don’t have the necessary knowledge. It is known that extrinsic feedback is effective in motor learning, specially in the early stages. There are several studies that evaluated the influence of extrinsic feedback in rehabilitation of shoulder dysfunctions, but only in the electromyography format. Material and Methods: Sixty healthy subjects were randomly divided into 3 groups that received no feedback (group 1 – control group), verbal and palpatory feedback (group 2) and real time cinematic feedback (group 3). The performance variables considered – time and quality of execution - were statistically analyzed with ANOVA one-way and multiple comparisons test. Results: Control group and group 3 executed the task in less time that group 2 (p<0.01) and group 3 executed the task with better quality than control group and group 2 (p<0.01). Conclusions: From the results of this study we conclude that in the studied task, the cinematic feedback is more effective to facilitate a better quality of execution than no feedback or clinical feedback and, regarding to time taken to attain the requested position, equally effective to no feedback.

Lightweight monitoring of transactional memory programs

Dissertação para obtenção do Grau de Mestre em Engenharia Informática

Preventing atomicity violations with contracts

Concurrent programming is a difficult and error-prone task because the programmer must reason about multiple threads of execution and their possible interleavings. A concurrent program must synchronize the concurrent accesses to shared memory regions, but this is not enough to prevent all anomalies that can arise in a concurrent setting. The programmer can misidentify the scope of the regions of code that need to be atomic, resulting in atomicity violations and failing to ensure the correct behavior of the program. Executing a sequence of atomic operations may lead to incorrect results when these operations are co-related. In this case, the programmer may be required to enforce the sequential execution of those operations as a whole to avoid atomicity violations. This situation is specially common when the developer makes use of services from third-party packages or modules. This thesis proposes a methodology, based on the design by contract methodology, to specify which sequences of operations must be executed atomically. We developed an analysis that statically verifies that a client of a module is respecting its contract, allowing the programmer to identify the source of possible atomicity violations.

Business development in Siemens global shared services delivery center Portugal

A Work Project, presented as part of the requirements for the Award of a Masters Degree in Management from the NOVA – School of Business and Economics

A system’s approach to cache hierarchy-aware decomposition of data-parallel computations

Dissertação para obtenção do Grau de Mestre em Engenharia Informática

Exposição a ozono em cabinas de avião

RESUMO - O ozono é o principal componente da poluição fotoquímica do ar. Como agente irritante do aparelho respiratório, os seus efeitos sobre a saúde caracterizam-se, essencialmente, por tosse, dispneia, desconforto torácico e alterações da função pulmonar, encontrando-se também associadas à exposição ambiental a O3 tanto uma maior frequência e gravidade de crises de asma como a ocorrência de quadros clínicos de irritação conjuntival. É sobretudo a partir dos anos 50, com a descoberta de concentrações elevadas de ozono em ambientes de trabalho respeitantes à actividade de soldadura «a arco», que aquele gás passa a ser encarado como factor profissional de risco. No início dos anos 60 surgem os primeiros estudos de exposição a O3 em cabinas de avião, suscitados pela ocorrência, em tripulantes e passageiros, de queixas clínicas de irritação do tracto respiratório. Esta sintomatologia era, até então, atribuída à acção de outros factores, designadamente o sistema de ventilação e o baixo teor de humidade do ar. Posteriormente, alguns estudos revelaram que, em voos comerciais subsónicos, os teores elevados de O3 observados no interior das cabinas poderiam ser provocados pela sua insuficiente destruição nos sistemas de entrada de ar.O presente estudo, efectuado em voos de longo curso realizados em aeronaves Airbus A340-300 numa única rota comercial, teve por objectivo avaliar a exposição a ozono no ar interior em cabina de avião. Os teores médios de concentração de ozono observados foram inferiores aos valores susceptíveis de provocarem efeitos adversos sobre o aparelho respiratório. Como valor máximo instantâneo, foi atingida a concentração de 152 ppb. Adicionalmente, foi constatada a influência das estações do ano nos teores de O3. O conjunto dos resultados obtidos permite concluir que as concentrações de ozono no ar interior nas cabinas de avião estudadas são inferiores às correspondentes concentrações máximas admissíveis, tendo, em todos os voos, sido observado o cumprimento da norma da FAA respeitante à protecção da exposição ao ozono em cabinas de aeronaves de aviação comercial.

Characterization and surface reconstruction of objects in tomographic images of composite materials

Dissertação para obtenção do Grau de Mestre em Engenharia Informática

Diving into the depth of primary motor cortex: a high-resolution investigation of the motor system using 7Tesla fMRI

Dissertação para a obtenção do Grau de Mestre em Engenharia Biomédica

Design of a tool to study the fate of Chlamydia trachomatis infected cells

Chlamydia trachomatis has a unique obligate intracellular developmental cycle that ends by the lysis of the cell and/or the extrusion of the bacteria in order to allow for re-infections. While Chlamydia trachomatis infections are often asymptomatic the diagnosis of Chlamydia trachomatis is usually late, occurring after manifestation of persistency. Investigations on the consequences of long-term infections and the molecular mechanisms behind it will reveal light to what extent bacteria can modulate host cell function and what the ultimate fate of host cells after clearance of an infection is. Such studies on the host cell fate could be greatly facilitated if the infected cells become permanently marked during and after the infection. Therefore, this project intends to develop a new genetic tool that would allow permanently labeling of Chlamydia trachomatis host cells. The plan was to generate a Chlamydia trachomatis strain that encodes a recombinant CRE recombinase, fused to a secretory effector function of the Chlamydia type 3 secretion system (T3SS). Upon translocation into the host cell, this recombinant CRE enzyme could then, owing to its site-specific recombination function, switch a reporter gene contained in the host cell genome. To this end, the reporter line carried a membrane-tagged tdTomato (mT) gene flanked by two LoxP sequences followed by a GFP gene. The translocation of the recombinant CRE recombinase into this cell line was designed to trigger the recombination of the LoxP sites whereby the cells would turn from red fluorescence to green as an irreversible label of the infected cells. Successful execution of this mechanism would allow to draw a direct link between Chlamydia trachomatis infection and the subsequent fate of the infected cell.

Heterogeneous computing with an algorithmic skeleton framework

The Graphics Processing Unit (GPU) is present in almost every modern day personal computer. Despite its specific purpose design, they have been increasingly used for general computations with very good results. Hence, there is a growing effort from the community to seamlessly integrate this kind of devices in everyday computing. However, to fully exploit the potential of a system comprising GPUs and CPUs, these devices should be presented to the programmer as a single platform. The efficient combination of the power of CPU and GPU devices is highly dependent on each device’s characteristics, resulting in platform specific applications that cannot be ported to different systems. Also, the most efficient work balance among devices is highly dependable on the computations to be performed and respective data sizes. In this work, we propose a solution for heterogeneous environments based on the abstraction level provided by algorithmic skeletons. Our goal is to take full advantage of the power of all CPU and GPU devices present in a system, without the need for different kernel implementations nor explicit work-distribution.To that end, we extended Marrow, an algorithmic skeleton framework for multi-GPUs, to support CPU computations and efficiently balance the work-load between devices. Our approach is based on an offline training execution that identifies the ideal work balance and platform configurations for a given application and input data size. The evaluation of this work shows that the combination of CPU and GPU devices can significantly boost the performance of our benchmarks in the tested environments, when compared to GPU-only executions.

Heritages, Identities, and Policy in the Metropolitan Area of Lisbon

In a world that has moved away from narratives based on the idea of progress, the past has established itself as a place of reference: confirming to ourselves that what we were is indispensible for sustaining what we think we are. The recovery of the past is thus one of the most common symbolic instruments used in negotiating identities. The cultural practices that have recourse to representation mechanisms that call on the past in order to consider the present always end up translating themselves, insofar as they fragment, reorganize and interpret it in their transformation, or, to use a formula that has become unavoidable, in their “invention”. Patrimonialization is one such practice. It associates the notion of heritage – which is not a given fact, but rather a socially constructed classification, and therefore one that is constantly being negotiated – with specific objects that come to serve as cultural representations of the groups who consider themselves to be their rightful owners. In the Lisbon Metropolitan Area, as in other ethnographic contexts, patrimonialization encompasses things as diverse as landscapes, monuments, popular architecture, handicrafts, local feast days/processions/pilgrimages and people; all things that can, once transformed into material representations of the past, serve as arguments for the identity fictions of the people who inhabit them.

Molecular simulation of gas adsorption equilibria in nanoporous materials

This work is divided into two distinct parts. The first part consists of the study of the metal organic framework UiO-66Zr, where the aim was to determine the force field that best describes the adsorption equilibrium properties of two different gases, methane and carbon dioxide. The other part of the work focuses on the study of the single wall carbon nanotube topology for ethane adsorption; the aim was to simplify as much as possible the solid-fluid force field model to increase the computational efficiency of the Monte Carlo simulations. The choice of both adsorbents relies on their potential use in adsorption processes, such as the capture and storage of carbon dioxide, natural gas storage, separation of components of biogas, and olefin/paraffin separations. The adsorption studies on the two porous materials were performed by molecular simulation using the grand canonical Monte Carlo (μ,V,T) method, over the temperature range of 298-343 K and pressure range 0.06-70 bar. The calibration curves of pressure and density as a function of chemical potential and temperature for the three adsorbates under study, were obtained Monte Carlo simulation in the canonical ensemble (N,V,T); polynomial fit and interpolation of the obtained data allowed to determine the pressure and gas density at any chemical potential. The adsorption equilibria of methane and carbon dioxide in UiO-66Zr were simulated and compared with the experimental data obtained by Jasmina H. Cavka et al. The results show that the best force field for both gases is a chargeless united-atom force field based on the TraPPE model. Using this validated force field it was possible to estimate the isosteric heats of adsorption and the Henry constants. In the Grand-Canonical Monte Carlo simulations of carbon nanotubes, we conclude that the fastest type of run is obtained with a force field that approximates the nanotube as a smooth cylinder; this approximation gives execution times that are 1.6 times faster than the typical atomistic runs.

Towards an algorithmic skeleton framework for programming the Intel R Xeon PhiTM processor

The Intel R Xeon PhiTM is the first processor based on Intel’s MIC (Many Integrated Cores) architecture. It is a co-processor specially tailored for data-parallel computations, whose basic architectural design is similar to the ones of GPUs (Graphics Processing Units), leveraging the use of many integrated low computational cores to perform parallel computations. The main novelty of the MIC architecture, relatively to GPUs, is its compatibility with the Intel x86 architecture. This enables the use of many of the tools commonly available for the parallel programming of x86-based architectures, which may lead to a smaller learning curve. However, programming the Xeon Phi still entails aspects intrinsic to accelerator-based computing, in general, and to the MIC architecture, in particular. In this thesis we advocate the use of algorithmic skeletons for programming the Xeon Phi. Algorithmic skeletons abstract the complexity inherent to parallel programming, hiding details such as resource management, parallel decomposition, inter-execution flow communication, thus removing these concerns from the programmer’s mind. In this context, the goal of the thesis is to lay the foundations for the development of a simple but powerful and efficient skeleton framework for the programming of the Xeon Phi processor. For this purpose we build upon Marrow, an existing framework for the orchestration of OpenCLTM computations in multi-GPU and CPU environments. We extend Marrow to execute both OpenCL and C++ parallel computations on the Xeon Phi. We evaluate the newly developed framework, several well-known benchmarks, like Saxpy and N-Body, will be used to compare, not only its performance to the existing framework when executing on the co-processor, but also to assess the performance on the Xeon Phi versus a multi-GPU environment.