806 resultados para structured parallel computations
Resumo:
In this work, we consider the numerical solution of a large eigenvalue problem resulting from a finite rank discretization of an integral operator. We are interested in computing a few eigenpairs, with an iterative method, so a matrix representation that allows for fast matrix-vector products is required. Hierarchical matrices are appropriate for this setting, and also provide cheap LU decompositions required in the spectral transformation technique. We illustrate the use of freely available software tools to address the problem, in particular SLEPc for the eigensolvers and HLib for the construction of H-matrices. The numerical tests are performed using an astrophysics application. Results show the benefits of the data-sparse representation compared to standard storage schemes, in terms of computational cost as well as memory requirements.
Resumo:
Este Trabalho refere-se ao Projecto de Execução de Fundações e Estruturas de uma Ponte Rodoviária em betão armado pré-esforçado, realizado no âmbito do Trabalho Final de Mestrado em Engenharia Civil – Especialização em Estruturas, do Instituto Superior de Engenharia de Lisboa. O Projecto de Execução é composto de Peças Escritas e Peças Desenhadas. Nas Peças Escritas estão incluídos: Memória Justificativa e Descritiva; Cálculos Justificativos e Anexos. A ponte é composta por dois tabuleiros paralelos com 10,28m de largura cada um e afastados entre si de 0,10m. A obra é constituída de 8 tramos; os tramos correntes com 31m de comprimento e os tramos extremos com 25 e 20m de comprimento, perfazendo um comprimento total de 231m. A obra foi parcialmente isolada dos sismos pela introdução, em todos os pilares, de aparelhos de apoio de elevado amortecimento sísmico do tipo HDRB (High Damping Rubber Bearings). Encontram-se particularmente discriminadas e detalhadas neste projecto as seguintes situações: - Cálculo do Pré-esforço e respectivas perdas; - Acção das sobrecargas rodoviárias; - Diferença de comportamento da obra na entrada em serviço e no longo prazo; - Análise sísmica e do isolamento sísmico; - Estudo dos efeitos diferidos: retracção e fluência. Tendo as abordagens de cálculo e as verificações de segurança seguido a regulamentação nacional em vigor, nomeadamente RSA e REBAP, foi no entanto feita uma aproximação às regras do “Capacity Design” previstas no EC8, em que se privilegia a actuação do projectista sobre o comportamento da estrutura, procurando uma resposta não linear da mesma, visando garantir que: - A rotura não ocorrerá nos elementos de fundação; - Nos pilares a dissipação de energia se faz através de rótulas plásticas, evitando-se roturas associadas a esforços transversos. A aplicação destas regras neste Projecto demonstrou haver um agravamento substancial na definição dos esforços a que devem resistir alguns dos componentes da estrutura, designadamente os pilares e as fundações, originando soluções de secções de betão e armaduras bem mais exigentes do que aqueles que resultariam da simples verificação de segurança, pela comparação entre esforços actuante e esforços resistentes “secção a secção”, imposta pela actual regulamentação nacional.
Resumo:
In the last years there has been a huge growth and consolidation of the Data Mining field. Some efforts are being done that seek the establishment of standards in the area. Included on these efforts there can be enumerated SEMMA and CRISP-DM. Both grow as industrial standards and define a set of sequential steps that pretends to guide the implementation of data mining applications. The question of the existence of substantial differences between them and the traditional KDD process arose. In this paper, is pretended to establish a parallel between these and the KDD process as well as an understanding of the similarities between them.
Resumo:
In the last years there has been a huge growth and consolidation of the Data Mining field. Some efforts are being done that seek the establishment of standards in the area. Included on these efforts there can be enumerated SEMMA and CRISP-DM. Both grow as industrial standards and define a set of sequential steps that pretends to guide the implementation of data mining applications. The question of the existence of substantial differences between them and the traditional KDD process arose. In this paper, is pretended to establish a parallel between these and the KDD process as well as an understanding of the similarities between them.
Resumo:
Francis Xavier’s Letters and Writings are eloquent narratives of a journey that absorbed the Saint’s entire life. His experiences and idiosyncrasies, values and categorizations are presented in a clear literate discourse. The missionary is rarely neutral in his opinions as he sustains his unmistakable and omnipresent objective: the conversion of peoples and the expansion of the Society of Jesus. Parallel with this objective, the reader is introduced to the individuals that Xavier meets or that he summons in his epistolary discourse. Letters and Writings presents us with a structured narrative peopled by all those who are subject to and objects of Xavier’s apostolic mission, by helpful and unhelpful persons of influence, and by leading and secondary actors. What is then the position of women, in the collective sense as well as in the individual sense, in the travels and goals that are the centre of Xavier’s Letters and Writings? What is the role of women, that secondary and suppressed term in the man/woman binomial, a dichotomy similar to the civilized/savage and European/native binomials that punctuate Xavier’s narratives and the historic context of his letters? Women are not absent from his writings, but it would be naïve to argue in favour of the author’s misogyny as much as of his “profound knowledge of the female heart”, to quote from Paulo Durão in "Women in the Letters of Saint Francis Xavier" (1952), the only paper on this subject published so far. We denote four great categories of women in the Letters and Writings: European Women, Converted Women, Women Who Profess another Religion, and Women as the Agents and Objects of Sin, the latter of which traverses the other three categories. They all depend on the context, circumstances and judgements of value that the author chooses to highlight and articulate.
Resumo:
Mestrado em Auditoria
Resumo:
International Conference with Peer Review 2012 IEEE International Conference in Geoscience and Remote Sensing Symposium (IGARSS), 22-27 July 2012, Munich, Germany
Resumo:
A Teia Mundial (Web) foi prevista como uma rede de documentos de hipertexto interligados de forma a criar uma espaço de informação onde humanos e máquinas poderiam comunicar. No entanto, a informação contida na Web tradicional foi/é armazenada de forma não estruturada o que leva a que apenas os humanos a possam consumir convenientemente. Consequentemente, a procura de informações na Web sintáctica é uma tarefa principalmente executada pelos humanos e nesse sentido nem sempre é fácil de concretizar. Neste contexto, tornou-se essencial a evolução para uma Web mais estruturada e mais significativa onde é dado significado bem definido à informação de forma a permitir a cooperação entre humanos e máquinas. Esta Web é usualmente referida como Web Semântica. Além disso, a Web Semântica é totalmente alcançável apenas se os dados de diferentes fontes forem ligados criando assim um repositório de Dados Abertos Ligados (LOD). Com o aparecimento de uma nova Web de Dados (Abertos) Ligados (i.e. a Web Semântica), novas oportunidades e desafios surgiram. Pergunta Resposta (QA) sobre informação semântica é actualmente uma área de investigação activa que tenta tirar vantagens do uso das tecnologias ligadas à Web Semântica para melhorar a tarefa de responder a questões. O principal objectivo do projecto World Search passa por explorar a Web Semântica para criar mecanismos que suportem os utilizadores de domínios de aplicação específicos a responder a questões complexas com base em dados oriundos de diferentes repositórios. No entanto, a avaliação feita ao estado da arte permite concluir que as aplicações existentes não suportam os utilizadores na resposta a questões complexas. Nesse sentido, o trabalho desenvolvido neste documento foca-se em estudar/desenvolver metodologias/processos que permitam ajudar os utilizadores a encontrar respostas exactas/corretas para questões complexas que não podem ser respondidas fazendo uso dos sistemas tradicionais. Tal inclui: (i) Ultrapassar a dificuldade dos utilizadores visionarem o esquema subjacente aos repositórios de conhecimento; (ii) Fazer a ponte entre a linguagem natural expressa pelos utilizadores e a linguagem (formal) entendível pelos repositórios; (iii) Processar e retornar informações relevantes que respondem apropriadamente às questões dos utilizadores. Para esse efeito, são identificadas um conjunto de funcionalidades que são consideradas necessárias para suportar o utilizador na resposta a questões complexas. É também fornecida uma descrição formal dessas funcionalidades. A proposta é materializada num protótipo que implementa as funcionalidades previamente descritas. As experiências realizadas com o protótipo desenvolvido demonstram que os utilizadores efectivamente beneficiam das funcionalidades apresentadas: ▪ Pois estas permitem que os utilizadores naveguem eficientemente sobre os repositórios de informação; ▪ O fosso entre as conceptualizações dos diferentes intervenientes é minimizado; ▪ Os utilizadores conseguem responder a questões complexas que não conseguiam responder com os sistemas tradicionais. Em suma, este documento apresenta uma proposta que comprovadamente permite, de forma orientada pelo utilizador, responder a questões complexas em repositórios semiestruturados.
Resumo:
OBJECTIVE: To understand beliefs and attitudes about fluorosis among young people living in a rural area. METHODOLOGICAL PROCEDURES: Qualitative study consisting of semi-structured interviews with 23 adolescents with dental fluorosis, 14 teachers and three health authorities in the city of São Francisco, Southeastern Brazil, in 2002. Content analysis and social representation theory were applied. ANALYSIS OF RESULTS: The organoleptic characteristics of carbonates that affect groundwater (salty flavor, whitish coloration, and turbidity) associated with negative aspects of household use of this water are considered a cause of mottled enamel. Even after contact with researchers who investigated this phenomenon and helped find a solution for this condition, the local population is still unwilling to accept fluoride as the cause of the problem and does not fully agree to use water from other sources because they are afraid of the quality of water. CONCLUSIONS: Misperceptions of the causes of dental fluorosis and water treatment costs compromise the implementation of uncontaminated surface water supplies. Health education strategies are required in parallel with solutions for securing water supply in drought-ravaged areas.
Resumo:
In the past few years Tabling has emerged as a powerful logic programming model. The integration of concurrent features into the implementation of Tabling systems is demanded by need to use recently developed tabling applications within distributed systems, where a process has to respond concurrently to several requests. The support for sharing of tables among the concurrent threads of a Tabling process is a desirable feature, to allow one of Tabling’s virtues, the re-use of computations by other threads and to allow efficient usage of available memory. However, the incremental completion of tables which are evaluated concurrently is not a trivial problem. In this dissertation we describe the integration of concurrency mechanisms, by the way of multi-threading, in a state of the art Tabling and Prolog system, XSB. We begin by reviewing the main concepts for a formal description of tabled computations, called SLG resolution and for the implementation of Tabling under the SLG-WAM, the abstract machine supported by XSB. We describe the different scheduling strategies provided by XSB and introduce some new properties of local scheduling, a scheduling strategy for SLG resolution. We proceed to describe our implementation work by describing the process of integrating multi-threading in a Prolog system supporting Tabling, without addressing the problem of shared tables. We describe the trade-offs and implementation decisions involved. We then describe an optimistic algorithm for the concurrent sharing of completed tables, Shared Completed Tables, which allows the sharing of tables without incurring in deadlocks, under local scheduling. This method relies on the execution properties of local scheduling and includes full support for negation. We provide a theoretical framework and discuss the implementation’s correctness and complexity. After that, we describe amethod for the sharing of tables among threads that allows parallelism in the computation of inter-dependent subgoals, which we name Concurrent Completion. We informally argue for the correctness of Concurrent Completion. We give detailed performance measurements of the multi-threaded XSB systems over a variety of machines and operating systems, for both the Shared Completed Tables and the Concurrent Completion implementations. We focus our measurements inthe overhead over the sequential engine and the scalability of the system. We finish with a comparison of XSB with other multi-threaded Prolog systems and we compare our approach to concurrent tabling with parallel and distributed methods for the evaluation of tabling. Finally, we identify future research directions.
Resumo:
In the past years, Software Architecture has attracted increased attention by academia and industry as the unifying concept to structure the design of complex systems. One particular research area deals with the possibility of reconfiguring architectures to adapt the systems they describe to new requirements. Reconfiguration amounts to adding and removing components and connections, and may have to occur without stopping the execution of the system being reconfigured. This work contributes to the formal description of such a process. Taking as a premise that a single formalism hardly ever satisfies all requirements in every situation, we present three approaches, each one with its own assumptions about the systems it can be applied to and with different advantages and disadvantages. Each approach is based on work of other researchers and has the aesthetic concern of changing as little as possible the original formalism, keeping its spirit. The first approach shows how a given reconfiguration can be specified in the same manner as the system it is applied to and in a way to be efficiently executed. The second approach explores the Chemical Abstract Machine, a formalism for rewriting multisets of terms, to describe architectures, computations, and reconfigurations in a uniform way. The last approach uses a UNITY-like parallel programming design language to describe computations, represents architectures by diagrams in the sense of Category Theory, and specifies reconfigurations by graph transformation rules.
Resumo:
This paper proposes a global multiprocessor scheduling algorithm for the Linux kernel that combines the global EDF scheduler with a priority-aware work-stealing load balancing scheme, enabling parallel real-time tasks to be executed on more than one processor at a given time instant. We state that some priority inversion may actually be acceptable, provided it helps reduce contention, communication, synchronisation and coordination between parallel threads, while still guaranteeing the expected system’s predictability. Experimental results demonstrate the low scheduling overhead of the proposed approach comparatively to an existing real-time deadline-oriented scheduling class for the Linux kernel.
Resumo:
Dynamic parallel scheduling using work-stealing has gained popularity in academia and industry for its good performance, ease of implementation and theoretical bounds on space and time. Cores treat their own double-ended queues (deques) as a stack, pushing and popping threads from the bottom, but treat the deque of another randomly selected busy core as a queue, stealing threads only from the top, whenever they are idle. However, this standard approach cannot be directly applied to real-time systems, where the importance of parallelising tasks is increasing due to the limitations of multiprocessor scheduling theory regarding parallelism. Using one deque per core is obviously a source of priority inversion since high priority tasks may eventually be enqueued after lower priority tasks, possibly leading to deadline misses as in this case the lower priority tasks are the candidates when a stealing operation occurs. Our proposal is to replace the single non-priority deque of work-stealing with ordered per-processor priority deques of ready threads. The scheduling algorithm starts with a single deque per-core, but unlike traditional work-stealing, the total number of deques in the system may now exceed the number of processors. Instead of stealing randomly, cores steal from the highest priority deque.
Resumo:
Real-time embedded applications require to process large amounts of data within small time windows. Parallelize and distribute workloads adaptively is suitable solution for computational demanding applications. The purpose of the Parallel Real-Time Framework for distributed adaptive embedded systems is to guarantee local and distributed processing of real-time applications. This work identifies some promising research directions for parallel/distributed real-time embedded applications.
Resumo:
High-level parallel languages offer a simple way for application programmers to specify parallelism in a form that easily scales with problem size, leaving the scheduling of the tasks onto processors to be performed at runtime. Therefore, if the underlying system cannot efficiently execute those applications on the available cores, the benefits will be lost. In this paper, we consider how to schedule highly heterogenous parallel applications that require real-time performance guarantees on multicore processors. The paper proposes a novel scheduling approach that combines the global Earliest Deadline First (EDF) scheduler with a priority-aware work-stealing load balancing scheme, which enables parallel realtime tasks to be executed on more than one processor at a given time instant. Experimental results demonstrate the better scalability and lower scheduling overhead of the proposed approach comparatively to an existing real-time deadline-oriented scheduling class for the Linux kernel.