Relatórios

In this report, we present a comparison of model performance indicators for severaloperational coastal forecast systems and structural engineering predictions and evaluationsexecuted in local workstations, in HPC cluster nodes and in a pilot cloud, aiming atcontributing to the best choice for the National Infrastructure for Scientific Computing.Results show that the scalability and flexibility of cloud computing resources makes theman attractive alternative for the implementation of multiple forecast systems using serial,non-MPI models, as well as for sensor data acquisition and processing applications.For MPI-based models, tests using cloud virtual machines with resources equal to or lowerthan the smaller physical bases performed well relative to the other resources. However, asthe cloud resources under testing did not reach the optimal number of processors for thepresent use cases, the HPC cluster remained the best option, as it fits better therequirements for the typical dimensions of computational grids for multi-scale (port toocean) analysis.Federated cloud resources allowed a better performance for small pool sizes, allowing thecombination of the processing power of several hosts. However, the performance doesscale very badly if the choice relies in any combination that uses many processes (by usingmany hosts or many processes within each host), even if we use resources with somehardware assistance.Further testing is still necessary to explore this possibility in detail, taking into account theneed to assure an adequate quality of service (QoS), especially to meet forecastingdeadlines and real-time streaming bandwidth.We conclude that an evolution from the current cluster setup to a cloud-based architecturewill satisfy most of our simulation requirements while offering a more flexible andaffordable computing environment.

We present herein the implementation, test and performance comparison of GPUs inphysical and cloud/virtual environment of: i) an image processing algorithm for coastalapplications using Synthetic Aperture Radar (SAR) imagery; ii) a hybrid programmingalgorithm (CPU/GPU) to automatically compute the correspondences between similarimages. The first test is based on an algorithm developed by LNEC in OpenCL and therespective Python wrapper. The second test uses the photogrammetry software

Neste Relatório de Atividades 6 e 7 apresentam-se os trabalhos desenvolvidos no âmbito da Atividade 6

O presente relatório descreve a atividade realizada pelo Núcleo de Tecnologias da Informação em Engenharia Civil, no âmbito do processo

This document constitutes a Deliverable of Action B3

This document constitutes a Deliverable of Action B4

A ERSARA promoveu a elaboração do presente guia de orientação, tendo em vista apoiar as entidades gestoras a construir, gerir, manter e atualizar o cadastro das suas infraestruturas, de forma a ser possível tirar o maior benefício da informação para uma melhor gestão dos seus sistemas.

A ERSARA promoveu a elaboração do presente guia de orientação, que constitui uma versão parcial do Guia Técnico da ERSAR

A ERSARA promoveu a elaboração do presente guia de orientação, tendo em vista apoiar as entidades gestoras na gestão operacional, registo e análise de intervenções nas redes de abastecimento de água e de drenagem de águas residuais e pluviais.

A ERSARA promoveu a elaboração do presente guia de orientação, tendo em vista apoiar as entidades gestoras na construção de um sistema de avaliação de desempenho orientado para o processo de tomada de decisão, no âmbito da gestão patrimonial de infraestruturas.