Parallel Algorithm for DC Resistivity Method Based on CUDA-Enabled GPU

2013 ◽  
Vol 765-767 ◽  
pp. 1752-1756 ◽  
Author(s):  
Tuo Wang ◽  
Rui Chen
Keyword(s):  
Computer Architecture ◽  
Large Scale ◽  
Graphic Processing Unit ◽  
Three Dimensional ◽  
Parallel Computer ◽  
Processing Unit ◽  
The Finite Element Method ◽  
Electrical Method ◽  
Resistivity Method ◽  
Electrical Prospecting

During the electrical prospecting, the three-dimensional forward problem has been the hot topic in the research of DC electrical method. When the forward computation results are solved through the finite element method and the finite difference method, a large-scale sparse linear equation set should be obtained, moreover the computation in the solution of large-scale linear algebraic equation sets are very heavy. If we adopt serial computation, the computing efficiency is very low, which greatly affects the application efficiency. With the increasing maturation of the parallel computer architecture, the Graphic Processing Unit (GPU) parallel computing modeling can apply in this field to enable the efficiency of the three-dimensional forward modeling to be significantly improved.

scholarly journals Prediction of Residual Stresses in a Multipass Pipe Weld by a Novel 3D Finite Element Approach

2018 ◽  
Author(s):  
Hui Huang ◽  
Jian Chen ◽  
Blair Carlson ◽  
Hui-Ping Wang ◽  
Paul Crooker ◽  
...  
Keyword(s):  
Finite Element ◽  
Residual Stresses ◽  
High Performance ◽  
Large Scale ◽  
Graphics Processing Unit ◽  
Computational Cost ◽  
Three Dimensional ◽  
Processing Unit ◽  
Girth Welds ◽  
Welding Processes

Due to enormous computation cost, current residual stress simulation of multipass girth welds are mostly performed using two-dimensional (2D) axisymmetric models. The 2D model can only provide limited estimation on the residual stresses by assuming its axisymmetric distribution. In this study, a highly efficient thermal-mechanical finite element code for three dimensional (3D) model has been developed based on high performance Graphics Processing Unit (GPU) computers. Our code is further accelerated by considering the unique physics associated with welding processes that are characterized by steep temperature gradient and a moving arc heat source. It is capable of modeling large-scale welding problems that cannot be easily handled by the existing commercial simulation tools. To demonstrate the accuracy and efficiency, our code was compared with a commercial software by simulating a 3D multi-pass girth weld model with over 1 million elements. Our code achieved comparable solution accuracy with respect to the commercial one but with over 100 times saving on computational cost. Moreover, the three-dimensional analysis demonstrated more realistic stress distribution that is not axisymmetric in hoop direction.

Large-scale 3D inversion of marine magnetotelluric data: Case study from the Gemini prospect, Gulf of Mexico

Geophysics ◽  
2011 ◽  
Vol 76 (1) ◽  
pp. F77-F87 ◽  
Author(s):  
Michael S. Zhdanov ◽  
Le Wan ◽  
Alexander Gribenko ◽  
Martin Čuma ◽  
Kerry Key ◽  
...  
Keyword(s):  
Gulf Of Mexico ◽  
Large Scale ◽  
Three Dimensional ◽  
Integral Equation Method ◽  
Computer Code ◽  
Hydrocarbon Exploration ◽  
Parallel Computer ◽  
3D Inversion ◽  
Magnetotelluric Data ◽  
Geoelectrical Structures

Three-dimensional magnetotelluric (MT) inversion is an emerging technique for offshore hydrocarbon exploration. We have developed a new approach to the 3D inversion of MT data, based on the integral equation method. The Tikhonov regularization and physical constraint have been used to obtain a stable and reasonable solution of the inverse problem. The method is implemented in a fully parallel computer code. We have applied the developed method and software for the inversion of marine MT data collected by the Scripps Institution of Oceanography (SIO) in the Gemini prospect, Gulf of Mexico. The inversion domain was discretized into 1.6 million cells. It took nine hours to complete 51 iterations on the 832-processor cluster with a final misfit between the observed and predicted data of 6.2%. The inversion results reveal a resistive salt structure, which is confirmed by a comparison with the seismic data. These inversion results demonstrate that resistive geoelectrical structures like salt domes can be mapped with reasonable accuracy using the 3D inversion of marine MT data.

scholarly journals Efficient Parallel Algorithms for 3D Laplacian Smoothing on the GPU

2019 ◽  
Vol 9 (24) ◽  
pp. 5437
Author(s):  
Lei Xiao ◽  
Guoxiang Yang ◽  
Kunyang Zhao ◽  
Gang Mei
Keyword(s):  
Large Scale ◽  
Graphics Processing Unit ◽  
Parallel Implementation ◽  
Three Dimensional ◽  
Smoothing Method ◽  
Three Dimensions ◽  
Processing Unit ◽  
Mesh Quality ◽  
Mesh Smoothing ◽  
Laplacian Smoothing

In numerical modeling, mesh quality is one of the decisive factors that strongly affects the accuracy of calculations and the convergence of iterations. To improve mesh quality, the Laplacian mesh smoothing method, which repositions nodes to the barycenter of adjacent nodes without changing the mesh topology, has been widely used. However, smoothing a large-scale three dimensional mesh is quite computationally expensive, and few studies have focused on accelerating the Laplacian mesh smoothing method by utilizing the graphics processing unit (GPU). This paper presents a GPU-accelerated parallel algorithm for Laplacian smoothing in three dimensions by considering the influence of different data layouts and iteration forms. To evaluate the efficiency of the GPU implementation, the parallel solution is compared with the original serial solution. Experimental results show that our parallel implementation is up to 46 times faster than the serial version.

scholarly journals Electric Propulsion Plume Simulations Using Parallel Computer

2007 ◽  
Vol 15 (2) ◽  
pp. 83-94 ◽  
Author(s):  
Joseph Wang ◽  
Yong Cao ◽  
Raed Kafafy ◽  
Viktor Decyk
Keyword(s):  
Electric Propulsion ◽  
Large Scale ◽  
Three Dimensional ◽  
Particle Simulation ◽  
Parallel Computer ◽  
Solar Array ◽  
Electron Mass ◽  
Ion Thruster ◽  
Particle In Cell ◽  
Pic Code

A parallel, three-dimensional electrostatic PIC code is developed for large-scale electric propulsion simulations using parallel supercomputers. This code uses a newly developed immersed-finite-element particle-in-cell (IFE-PIC) algorithm designed to handle complex boundary conditions accurately while maintaining the computational speed of the standard PIC code. Domain decomposition is used in both field solve and particle push to divide the computation among processors. Two simulations studies are presented to demonstrate the capability of the code. The first is a full particle simulation of near-thruster plume using real ion to electron mass ratio. The second is a high-resolution simulation of multiple ion thruster plume interactions for a realistic spacecraft using a domain enclosing the entire solar array panel. Performance benchmarks show that the IFE-PIC achieves a high parallel efficiency of ≥ 90%

Numerical Simulation of Three-Dimensional Violent Free Surface Flows by GPU-Based MPS Method

2019 ◽  
Vol 16 (04) ◽  
pp. 1843012 ◽  
Author(s):  
Xiang Chen ◽  
Decheng Wan
Keyword(s):  
Free Surface ◽  
Large Scale ◽  
Three Dimensional ◽  
Free Surface Flows ◽  
Dam Break ◽  
Impact Pressure ◽  
Processing Unit ◽  
Mps Method ◽  
Acceleration Technique ◽  
Calculation Step

The Moving Particle Semi-implicit (MPS) method has been widely used in the field of computational fluid dynamics in recent years. However, the inefficient drawback of MPS method limits its three-dimensional (3D) large-scale applications. In order to overcome this disadvantage, a novel acceleration technique, graphics processing unit (GPU) parallel computing, is applied in MPS. Based on modified MPS method and GPU technique, an in-house solver MPSGPU-SJTU has been developed by using Compute Unified Device Architecture (CUDA) language. In this paper, 3D dam break and sloshing, two typical violent flows with large deformation and nonlinear fragmentation of free surface are simulated by MPSGPU-SJTU solver. In dam break case, the results of fluid flied, water front, wave height and impact pressure by GPU simulation are compared to those by CPU calculation, experimental research, Smooth Particle Hydrodynamics (SPH) and Boundary Element Method (BEM) simulations. And the comparison of fluid field and impact pressure among GPU, CPU and experiment is made in sloshing flow. The accuracy of GPU solver is verified by these comparisons. Moreover, the computation time of every part in each calculation step is compared between GPU and CPU solvers. The results show that computational efficiency is improved dramatically by employing GPU acceleration technique.

The influence of VLSI technology on computer architecture

1988 ◽  
Vol 326 (1591) ◽  
pp. 377-393 ◽  
Keyword(s):  
Computer Architecture ◽  
Programming Languages ◽  
Large Scale ◽  
Parallel Computers ◽  
General Purpose ◽  
Parallel Computer ◽  
Vlsi Technology ◽  
Large Scale Integration ◽  
Scale Integration ◽  
The Cost

Very-large-scale integration (VLSI) offers new opportunities in computer architecture. The cost of a processor has been reduced to that of a few thousand bytes of memory, with the result that parallel computers can be constructed as easily and economically as their sequential predecessors. In particular, a parallel computer constructed by replication of a standard computing element is well suited to the mass-production economics of the technology. The emergence of the new parallel computers has stimulated the development of new programming languages and algorithms. One example is the Occam language which has been designed to enable applications to be expressed in a form suitable for execution on a variety of parallel architectures. Further developments in language and architecture will enable processing resources to be allocated and deallocated as freely as memory, giving rise to some hope that users of general-purpose parallel computers will be freed from the current need to design algorithms to suit specific architectures.

Sign in / Sign up

Export Citation Format

Share Document