Simulation of free surface flows in a distributed memory environment

A parallel technique, for a distributed memory machine, based on domain decomposition for solving the Navier-Stokes equations in cartesian and cylindrical coordinates in two dimensions with free surfaces is described. It is based on the code by Tome and McKee (J. Comp. Phys. 110 (1994) 171-186) and Tome (Ph.D. Thesis, University of Strathclyde, Glasgow, 1993) which in turn is based on the SMAC method by Amsden and Harlow (Report LA-4370, Los Alamos Scientific Laboratory, 1971), which solves the Navier-Stokes equations in three steps: the momentum and Poisson equations and particle movement, These equations are discretized by explicit and 5-point finite differences. The parallelization is performed by splitting the computation domain into vertical panels and assigning each of these panels to a processor. All the computation can then be performed using nearest neighbour communication. Test runs comparing the performance of the parallel with the serial code, and a discussion of the load balancing question are presented. PVM is used for communication between processes. (C) 1999 Elsevier B.V. B.V. All rights reserved.

Uma metodologia para o controle de seguranca dinamica de sistemas de energia eletrica

This work presents an algorithm for the security control of electric power systems using control actions like generation reallocation, determined by sensitivity analysis (linearized model) and optimization by neural networks. The model is developed taking into account the dynamic network aspects. The preventive control methodology is developed by means of sensitivity analysis of the security margin related with the mechanical power of the system synchronous machines. The reallocation power in each machine is determined using neural networks. The neural network used in this work is of Hopfield type. These networks are dedicated electric circuits which simulate the constraint set and the objective function of an optimization problem. The advantage of using these networks is the higher speed in getting the solutions when compared to conventional optimization algorithms due to the great convergence rate of the process and the facility of the method parallelization. Then, the objectives are: formulate and investigate these networks implementations in determining. The generation reallocation in digital computers. Aiming to illustrate the proposed methodology an application considering a multi-machine system is presented.

Técnicas de paralelização em GPGPU aplicadas em algoritmo para remoção de ruído multiplicativo

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Paralelização da ferramenta de alinhamento de sequências MUSCLE para um ambiente distribuído

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

An Efficient Parallel Algorithm for Multiple Sequence Similarities Calculation Using a Low Complexity Method

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Redução do tempo de setup de máquinas de usinagem em uma industria automobilística

Continuous improvement of industrial processes is one way to become companies more competitive in the market. For this, a fairly widespread use is the methodology of lean production systems, by eliminating waste. One of the tools of these systems is the method of rapid exchange of die or also called SMED, which will be applied in this study. The study aims to develop proposals for reducing the time of set up of two machines in two machining lines, watching also the ergonomics and safety conditions in this operations. The set up time reduction is justified among others, due to increase the machine productivity. In applying the connecting rod machining line, there were two types of exchange. Reductions in time to set up proposals reached values of 47% to one of them, and 55% to the other. It is important to underline that to reach this result, there was no need for large investments. In the application in block machining line, was developed an improvement in the ergonomic area. It was placed a pulley block that came to increase the time of tool change. Aiming to improve the security of the exchange, without productivity loss, the method was applied to reduce this time. It was developed two proposals.: the first would reduce that time by 19%, and does not require many resources of the company. The second involves the parallelization of the exchange, so that the reduction is 48%. However, this proposal requires one more manpower at the time of exchange and it is not always possible

Using Threads to Overcome Synchronization Delays in Parallel Multiple Progressive Alignment Algorithms

Sao Paulo State Research Foundation-FAPESP

Modelos dinâmicos simplificados, para verificação do comportamento de rede de satélites amarrados por cabos flexíveis, usando-se o método explícito das diferenças finitas

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Paralelização automática de laços

Identify opportunities for software parallelism is a task that takes a lot of human time, but once some code patterns for parallelism are identified, a software could quickly accomplish this task. Thus, automating this process brings many benefits such as saving time and reducing errors caused by the programmer [1]. This work aims at developing a software environment that identifies opportunities for parallelism in a source code written in C language, and generates a program with the same behavior, but with higher degree of parallelism, compatible with a graphics processor compatible with CUDA architecture.