Image Re-Ranking Acceleration on GPUs

Huge image collections are becoming available lately. In this scenario, the use of Content-Based Image Retrieval (CBIR) systems has emerged as a promising approach to support image searches. The objective of CBIR systems is to retrieve the most similar images in a collection, given a query image, by taking into account image visual properties such as texture, color, and shape. In these systems, the effectiveness of the retrieval process depends heavily on the accuracy of ranking approaches. Recently, re-ranking approaches have been proposed to improve the effectiveness of CBIR systems by taking into account the relationships among images. The re-ranking approaches consider the relationships among all images in a given dataset. These approaches typically demands a huge amount of computational power, which hampers its use in practical situations. On the other hand, these methods can be massively parallelized. In this paper, we propose to speedup the computation of the RL-Sim algorithm, a recently proposed image re-ranking approach, by using the computational power of Graphics Processing Units (GPU). GPUs are emerging as relatively inexpensive parallel processors that are becoming available on a wide range of computer systems. We address the image re-ranking performance challenges by proposing a parallel solution designed to fit the computational model of GPUs. We conducted an experimental evaluation considering different implementations and devices. Experimental results demonstrate that significant performance gains can be obtained. Our approach achieves speedups of 7x from serial implementation considering the overall algorithm and up to 36x on its core steps.

Design and Analysis of Optical Interconnection Networks for a Dataflow Parallel Computer

This work shows the design, simulation, and analysis of two optical interconnection networks for a Dataflow parallel computer architecture. To verify the optical interconnection network performance on the Dataflow architecture, we have analyzed the load balancing among the processors during the parallel programs executions. The load balancing is a very important parameter because it is directly associated to the dataflow parallelism degree. This article proves that optical interconnection networks designed with simple optical devices can provide efficiently the dataflow requirements of a high performance communication system.

A VHDL-based protocol controller for NCAP processors

This work presents the development of an IEEE 1451.2 protocol controller based on a low-cost FPGA that is directly connected to the parallel port of a conventional personal computer. In this manner it is possible to implement a Network Capable Application Processor (NCAP) based on a personal computer, without parallel port modifications. This approach allows supporting the ten signal lines of the 10-wire IEEE 1451.2 Transducer Independent Interface (TII), that connects the network processor to the Smart Transducer Interface Module (STIM) also defined in the IEEE 1451.2 standard. The protocol controller is connected to the STIM through the TII's physical interface, enabling the portability of the application at the transducer and network processor level. The protocol controller architecture was fully developed in VHDL language and we have projected a special prototype configured in a general-purpose programmable logic device. We have implemented two versions of the protocol controller, which is based on IEEE 1451 standard, and we have obtained results using simulation and experimental tests. (c) 2008 Elsevier B.V. All rights reserved.

Bifurcation Analysis of a Van der Pol-Duffing Circuit with Parallel Resistor

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

An investigation on parallel, divergent and convergent acetylene dual jet diffusion flames

Results are presented and discussed of an experimental investigation on acetylene turbulent dual jet diffusion flames. The study includes parameters of flames in parallel, divergent and convergent configurations. Tests with two parallel jets with addition of helium in the fuel stream were also performed and analysed. The variation of overall flame length and of other name physical characteristics, such as width, volume and conditions for lifting, are presented as functions of burner tip Reynolds number, jet distance from each other and inclination angle. The effects of diluent concentration in the fuel gas stream are presented for single and two parallel jets. (C) 1999 Elsevier B.V. Ltd.

Differential-Evolution-Based Optimization of the Dynamic Response for Parallel Operation of Inverters With No Controller Interconnection

In this paper, the use of differential evolution ( DE), a global search technique inspired by evolutionary theory, to find the parameters that are required to achieve optimum dynamic response of parallel operation of inverters with no interconnection among the controllers is proposed. Basically, in order to reach such a goal, the system is modeled in a certain way that the slopes of P-omega and Q-V curves are the parameters to be tuned. Such parameters, when properly tuned, result in system's eigenvalues located in positions that assure the system's stability and oscillation-free dynamic response with minimum settling time. This paper describes the modeling approach and provides an overview of the motivation for the optimization and a description of the DE technique. Simulation and experimental results are also presented, and they show the viability of the proposed method.

On the dynamic behaviour of a mass supported by a parallel combination of a spring and an elastically connected damper

This paper presents a consistent and concise analysis of the free and forced vibration of a mass supported by a parallel combination of a spring and an elastically supported damper (a Zener model). The results are presented in a compact form and the physical behaviour of the system is emphasised. This system is very similar to the conventional single-degree-of freedom system (sdof)-(Voigt model), but the dynamics can be quite different depending on the system parameters. The usefulness of the additional spring in series with the damper is investigated, and optimum damping values for the system subject to different types of excitation are determined and compared.There are three roots to the characteristic equation for the Zener model; two are complex conjugates and the third is purely real. It is shown that it is not possible to achieve critical damping of the complex roots unless the additional stiffness is at least eight times that of the main spring. For a harmonically excited system, there are some possible advantages in using the additional spring when the transmitted force to the base is of interest, but when the displacement response of the system is of interest then the benefits are marginal. It is shown that the additional spring affords no advantages when the system is excited by white noise. (c) 2007 Elsevier Ltd. All rights reserved.

Ethyl Carbamate Analysis in German Fruit Spirits and Brazilian Sugarcane Spirits (Cachaca): Improved Sample Cleanup with Automated Parallel Evaporation

The analysis of alcoholic beverages for the important carcinogenic contaminant ethyl carbamate is very time-consuming and expensive. Due to possible matrix interferences, sample cleanup using diatomaceous earth (Extrelut) column is required prior to gas chromatographic and mass spectrometric measurement. A limiting step in this process is the rotary evaporation of the eluate containing the analyte in organic solvents, which is currently conducted manually and requires approximately 20-30 min per sample. This paper introduces the use of a parallel evaporation device for ethyl carbamate analysis, which allows for the simultaneous evaporation of 12 samples to a specified residual volume without manual intervention. A more efficient and, less expensive analysis is therefore possible. The method validation showed no differences between the fully-automated parallel evaporation and the manual operation. The applicability was proven by analyzing authentic spirit samples from Germany, Canada and Brazil. It is interesting to note that Brazilian cachacas had a relatively high incidence for ethyl carbamate contamination (55% of all samples were above 0.15 mg/l), which may be of public health relevance and requires further evaluation.

Postoperative periodontal pain prevention using two dexamethasone medication protocols: A double-blind, parallel-group, placebo-controlled randomized clinical trial

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Thermal performance of multipass parallel and counter-cross-flow heat exchangers

A thorough study of the thermal performance of multipass parallel cross-flow and counter-cross-flow heat exchangers has been carried out by applying a new numerical procedure. According to this procedure, the heat exchanger is discretized into small elements following the tube-side fluid circuits. Each element is itself a one-pass mixed-unmixed cross-flow heat exchanger. Simulated results have been validated through comparisons to results from analytical solutions for one- to four-pass, parallel cross-flow and counter-cross-flow arrangements. Very accurate results have been obtained over wide ranges of NTU (number of transfer units) and C* (heat capacity rate ratio) values. New effectiveness data for the aforementioned configurations and a higher number of tube passes is presented along with data for a complex flow configuration proposed elsewhere. The proposed procedure constitutes a useful research tool both for theoretical and experimental studies of cross-flow heat exchangers thermal performance.

Speedup and scalability analysis of Master-Slave applications on large heterogeneous clusters

Although cluster environments have an enormous potential processing power, real applications that take advantage of this power remain an elusive goal. This is due, in part, to the lack of understanding about the characteristics of the applications best suited for these environments. This paper focuses on Master/Slave applications for large heterogeneous clusters. It defines application, cluster and execution models to derive an analytic expression for the execution time. It defines speedup and derives speedup bounds based on the inherent parallelism of the application and the aggregated computing power of the cluster. The paper derives an analytical expression for efficiency and uses it to define scalability of the algorithm-cluster combination based on the isoefficiency metric. Furthermore, the paper establishes necessary and sufficient conditions for an algorithm-cluster combination to be scalable which are easy to verify and use in practice. Finally, it covers the impact of network contention as the number of processors grow. (C) 2007 Elsevier B.V. All rights reserved.

THEORY OF ELASTICITY OF THE ABRIKOSOV FLUX-LINE LATTICE FOR UNIAXIAL SUPERCONDUCTORS - PARALLEL FLUX LINES

In this paper, we consider the extension of the Brandt theory of elasticity of the Abrikosov flux-line lattice for a uniaxial superconductor for the case of parallel flux lines. The results show that the effect of the anisotropy is to rescale the components of the wave vector k and the magnetic field and order-parameter wave vector cut off by a geometrical parameter previously introduced by Kogan.

A W-matrix methodology for solving sparse network equations on multiprocessor computers

This paper describes a methodology for solving efficiently the sparse network equations on multiprocessor computers. The methodology is based on the matrix inverse factors (W-matrix) approach to the direct solution phase of A(x) = b systems. A partitioning scheme of W-matrix , based on the leaf-nodes of the factorization path tree, is proposed. The methodology allows the performance of all the updating operations on vector b in parallel, within each partition, using a row-oriented processing. The approach takes advantage of the processing power of the individual processors. Performance results are presented and discussed.