n/a

n/a

n/a

n/a

n/a

n/a

n/a

A crescente utilização de Unidades de Processamento Gráfico (GPUs) na computação de caráter geral levanta questões de desempenho e de escalabilidade. Para responder a estes requisitos de forma efetiva, cada vez mais se recorre à utilização colaborativa de vários GPUs num só sistema. Esta abordagem introduz, no entanto, novos desafios, tal como a decomposição do domínio do problema e a gestão da possível heterogeneidade dos dispositivos. Neste contexto assume particular relevância a proposta de abstrações que escondam a complexidade da programação destes sistemas. Existe já algum trabalho na área, mas este restringe-se ao paralelismo de dados. Por conseguinte, neste artigo abordamos a utilização de uma biblioteca de esqueletos algorítmicos, Marrow, para a exploração de paralelismo de tarefas em sistemas computacionais com estas características. Os resultados são promissores, apresentado a escalabilidade esperada nos sistemas testados.

The Graphics Processing Unit (GPU) is gaining popular- ity as a co-processor to the Central Processing Unit (CPU). However, harnessing its capabilities is a non-trivial exercise that requires good knowledge of parallel programming, more so when the complexity of these applications is increasingly rising. Languages such as StreamIt [1] and Lime [2] have addressed the offloading of composed computations to GPUs. However, to the best of our knowledge, no support exists at library level. To this extent, we propose Marrow, an algorithmic skeleton frame- work for the orchestration of OpenCL computations. Marrow expands the set of skeletons currently available for GPU computing, and enables their combination, through nesting, into complex structures. Moreover, it introduces optimizations that overlap communication and computa- tion, thus conjoining programming simplicity with performance gains in many application scenarios. We evaluated the framework from a perfor- mance perspective, comparing it against hand-tuned OpenCL programs. The results are favourable, indicating that Marrow’s skeletons are both flexible and efficient in the context of GPU computing.

n/a

Complex software systems inherently require a variety of models used in all of the development stages. A general concern is to guarantee consistency and traceability among these models. Model-driven development (MDD) can help tackle this concern. Although MDD has been mainly used in later development stages, it is relatively unexplored in requirements engineering. In this article, the authors discuss how to
leverage MDD to support consistency and traceability in requirements modeling. To illustrate this, they apply MDD to goaloriented requirements engineering (GORE) by making bidirectional mappings between two well-known GORE approaches (i* and KAOS). The result is an interoperable framework that can be used to migrate from one goal model to another through automatic model transformations, keeping consistency and traceability, so requirements engineers can make the best use of each approach.

The objective of this work is to quantify As, Hg, Cd, Ni and Pb in Portuguese red wines. First, the methods for the quantification of trace elements in red wines were validated. Several pre-treatments were compared, namely a pre-digestion process with HNO3, a pre-oxidation step with H2O2, and a spiking step of wine samples with a known concentration of the trace elements analyzed. Except for As, it was determined that the quantification of the trace elements does not require a pre-digestion process with HNO3. For all of the trace elements analyzed, a pre-oxidation step with H2O2 may enable an accurate quantification. The techniques chosen for the quantification of trace elements were hydride generation atomic absorption spectrometry (HGAAS) for As and Hg, electrothermal atomic absorption spectrometry (ETAAS) for Cd, and flame atomic absorption spectrometry (FAAS) for Ni and Pb. In the second stage of this work, 25 Portuguese red wines spanning all of the red wine-producing regions were analyzed for all of the five trace elements referred to above. Only Cd and Pb have shown concentrations above the limit values defined by the “Organization Internationale de la Vigne et du Vin.” The Target Hazard Quotient (THQ) equation was used to determine in which wine-producing regions that wine consumption can be a problem for public health in terms of the concentrations of the five trace elements analyzed. THQ values have indicated that for the universe of the 25 red wines analyzed no region produces wines that can pose problems for public health, when the Portuguese red wine standard consumption is considered.

n/a

A semigroup is amiable if there is exactly one idempotent in each ℛ*-class and in each ℒ*-class. A semigroup is adequate if it is amiable and if its idempotents commute. We characterize adequate semigroups by showing that they are precisely those amiable semigroups that do not contain isomorphic copies of two particular non-adequate semigroups as subsemigroups.

This paper proposes a set of metrics for the assessment of the complexity of models defining the business logic of spreadsheets. This set can be considered the first step in the direction of building a quality standard for spreadsheet models, that is still to be defined. The computation of concrete metric values has further been integrated under a well-established model-driven spreadsheet development environment, providing a framework for the analysis of spreadsheet models under spreadsheets themselves.