Papers by Keyword: Parallel Computing

Abstract: This paper is devoted to the numerical computation of a steady-state thermo-fluid modeling related to the Friction Stir Welding Process in a two-dimensional cylindrical geometry. It analyzes the efficiency of the implementation on parallel architectures of two finite-difference schemes on a structured grid. The first one applies the Newton-Raphson method to compute a numerical solution of this non-linear elliptic type equation, and uses an iterative sparse solver. The second one is based on a time-marching approach converging to the steady state solution thanks to a time-explicit computation. Their respective performance is presented and discussed. Some numerical simulation results are presented to validate the proposed approach.

Abstract: This study presents parallelization of Hamming Distance algorithm, which is used for iris comparison on iris recognition systems, for heterogeneous systems that can be included Central Processing Units (CPUs), Graphics Processing Units (GPUs), Digital Signal Processing (DSP) boards, Field Programmable Gate Array (FPGA) and some other mobile platforms with OpenCL. OpenCL allows to run same code on CPUs, GPUs, FPGAs and DSP boards. Heterogeneous computing refers to systems include different kind of devices (CPUs, GPUs, FPGAs and other accelerators). Heterogeneous computing gains performance or reduces power for suitable algorithms on these OpenCL supported devices. In this study, Hamming Distance algorithm has been coded with C++ as a sequential code and has been parallelized a designated method by us with OpenCL. Our OpenCL code has been executed on Nvidia GT430 GPU and Intel Xeon 5650 processor. The OpenCL code implementation demonstrates that speed up to 87 times with parallelization. Also our study differs from other studies, which accelerate iris matching, with regard to ensure heterogeneous computing by using OpenCL.

Abstract: With the development of Internet industry, equipment data is increasing. The traditional method is not suitable for processing large data. Aiming at inefficient problem of Apriori algorithm when mining very large database, an efficient parallel association rules mining algorithm (Advanced Pruning Parallel Apriori Algorithm) based on a cluster is presented. APPAA algorithm can enhance the mining efficiency, as well as the system’s extension. Experimental results show that APPAA algorithm cuts down 85% mining time of Apriori, and it has good characteristics of parallel and expandable.so it is suitable for mining very large size database of fault diagnosis.

Abstract: The paper is devoted to the simulation of queueing networks on high performance computer clusters. The objective is to develop a mathematical model of queueing network and simulation approach to the modelling of the general network functionality, as well as to provide a software implementation on a high-performance computer cluster. The simulation is based on a discrete-event approach, object oriented programming, and MPI technology. The model of the queueing networks simulation system was developed as an application that allows a user to simulate networks of rather free configuration. The experiments on a high performance computer cluster emphasize the high efficiency of parallel computing.

Abstract: This paper introduces a procedure for parallel computing with the Dynamic Relaxation method (DR) on a Graphic Processing Unit (GPU).This method facilitates the consideration of a variety of nonlinearities in an easy and explicit manner.Because of the presence of inertial forces, a static problem leads to a transient dynamic problem where the Central Difference Method is usedas a method for direct integration of equations of motion which arise from the Finite Element model.The natural characteristic of this explicit method is that the scheme can be easily parallelized. The assembly of a global stiffness matrix is not required.Due to slow convergence with this method, the high performance which GPUs provide is strongly suitable for this kind of computation.NVIDIA's CUDA is used for general-purpose computing on graphics processing units (GPGPU) for NVIDIA's GPUs with CUDA capability.

Abstract: Instrumentation technology has been widely used in debugging interactive applications, such as interactive games and virtual reality. Debug codes are instrumented into a target program in order to collect run-time information. Although instrumentation provides detail information of the target program behavior, it can significantly prolong execution time, change program behavior and lead to incorrect debugging results, especially for time dependent and real-time applications. This paper aims to design a scalable parallel debugging mechanism to reduce instrumentation overhead while collecting detail run-time information. We design a new synchronization mechanism of instrumentation, named MDM, which uses multiple buffers to process debug messages. Also, a binding mechanism is used to specify the relationship between the target program, helper threads and cores. We conduct a case study of augmented reality interactive games on an Intel Core i7-2600 processor with Linux 2.6.38. Compared to existing methods, MDM can reduce instrumentation overhead by up to 19%.

Abstract: Submarine slides can trigger tsunamis with high affecting offshore structures, subsea facilities and human lives along the shoreline. Unfortunately, slide-generated tsunami is a difficult problem due to the source of sliding of mass failure by itself or by the other earthquakes. There are no effective numerical model that could simulate simultaneously all stages of generation, propagation, run-up and impact of tsunami phenomena. Physical understanding of slide tsunami hazards is very poor. We must understand substance of tsunami clearly and how to find methods to reduce damage from tsunami wave. This paper will present a parallel computing based on ParallelSPHysics, it can simulate a comprehensive model of tsunami wave by using Smooth Particle Hydrodynamics method.

Abstract: This paper develops a three dimensional elastic fracture analysis method, PDS-FEM (Particle Discretization Scheme Finite Element Method), to its elasto-plastic version. The Newton-Raphson iteration method is adopted for solving material nonlinearity, and the conjugate gradient method is applied to solve the linear equations of FEM. In order to apply the fracture analysis method to the engineering scale analysis, CPU based parallel computing technology is applied, and the computation speed is highly advanced. In this trial test, a simple stress based failure criterion is employed for the failure analysis of a cantilever steel beam. The numerical results without fracture match well with the commercial FEM software, ANSYS’s, which verifies the accuracy of the developed platform.

Abstract: This paper proposes a parallel computing method of topological analysis based on the partition of grid model data, and based on the smart grid dispatch control system it design and develop the parallel topology analysis service using the OpenMP shared memory programming model and C/C++ programming language. According to the layering and zoning features of the smart grid dispatch control system, this method divides the grid mode by area and power station. Package the topology search function and do parallel processing for mode data according to different area and power station, which can realize the parallel network topology analysis. The test result on the actual grid shows that this method has good stability and real-time, and it can meet the system online simulation, analysis and control applications requires for the topology analysis.

Abstract: This study attempts to introduce parallel computing into processing of remote sensing images and discuss its influence on the processing results. We select an processing of remote sensing images called feature point extraction to run in parallel computing environment and calculate the time consumption and root-mean-square error, then give an analysis based on the result.