A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2019; you can also visit the original URL.
The file type is application/pdf
.
Filters
Parallel (‖) ELLPACK: an expert system for parallel processing of partial differential equations
1989
Mathematics and Computers in Simulation
Ahstract We are developing an expen system environment for solving elliptic partial differential equations(pDEs) defined on two and three dimensional domains on MIMD type parallel machines. ...
According to its design objectives, it will provide a uniform programming environment for implementing parallel MIMD PDE solution solvers, an automatic partitioning and allocation of the PDE computation ...
GEOMETRY DECOMPOSITION BASED METHODS FOR SOLVING PARTIAL DIFFERENTIAL EQUATIONS The development of parallel algorithms for a given computation usually assumes the partitioning of the underlying computation ...
doi:10.1016/0378-4754(89)90143-2
fatcat:vgbqwicvangmjknom3wvpcsvwa
Parallel Reservoir Simulation with OpenACC and Domain Decomposition
2018
Algorithms
Meanwhile, domain decomposition is not well used for GPU-based reservoir simulations. ...
In order to address the problems, we propose a parallel method with OpenACC to accelerate serial code and reduce the time and effort during porting an application to GPU. ...
In last experiment, we compare two kinds of parallel reservoir simulation methods which differentiate from the other depending on whether the domain decomposition is used. ...
doi:10.3390/a11120213
fatcat:swrmqhkzujc3fjvozi3jckd7rm
Design and Optimization of OpenFOAM-based CFD Applications for Hybrid and Heterogeneous HPC Platforms
[article]
2015
arXiv
pre-print
Hardware-aware design and optimization is crucial in exploiting emerging architectures for PDE-based computational fluid dynamics applications. ...
We propose a number of optimizations of the dominant kernel of the Krylov solver, aimed at acceleration of the overall execution of the applications on modern GPU-accelerated heterogeneous platforms. ...
Parallel Approach A common approach for parallelizing partial differential equations is domain decomposition. ...
arXiv:1505.07630v1
fatcat:ncqycx2hmvbaxjbfeavwhyw3v4
Implementing Overlapping Domain Decomposition Methods on a Virtual Parallel Machine
[chapter]
2006
Lecture Notes in Computer Science
To solve many partial differential equations of different types domain decomposition techniques were developed. ...
We first develop suitable domain decomposition algorithms for our virtual parallel machine. ...
To solve many partial differential equations of different types domain decomposition techniques were developed. ...
doi:10.1007/11942634_74
fatcat:hm2qv3i3abggrhhh3cmnydiive
PELLPACK: a problem-solving environment for PDE-based applications on multicomputer platforms
1998
ACM Transactions on Mathematical Software
The system employs several parallel reuse methodologies based on the decomposition of discrete geometric data to map sparse PDE computations to parallel machines. ...
This paper presents the software architecture and implementation of the problem solving environment (PSE) PELLPACK for modeling physical objects described by partial differential equations (PDEs). ...
PELLPACK is supported by a library of parallel PDE modules for the numerical solution of stationary and time dependent single equation PDE models on two and three dimensional regions. ...
doi:10.1145/285861.285864
fatcat:ekapzyflknhuffw4tswnptnwya
Performance of preconditioners for the distributed vector finite-element time-domain algorithm
2005
IEEE transactions on magnetics
Index Terms-Edge elements, finite-element (FE) method, iterative solver, parallel numerical algorithms, time-domain algorithm. ...
The properties of the solver are estimated for concurrent three-dimensional formulation of the finite-element time-domain method. ...
The first one is the typical fixed speedup of the algorithm (2) where is the latency time of the PCG solver in a single step of the time-domain algorithm. ...
doi:10.1109/tmag.2005.846055
fatcat:brt2afl43zbojitsj5iic35pke
Parallel FEM Software for CFD Problems
2004
Informatica
Domain decomposition strategy and parallel iterative GM-RES solver have been adapted to the universal space-time FEM code FEMTOOL, which allows implementation of any partial differential equation with ...
The present paper describes the development and the performance of parallel FEM software for solving various CFD problems. ...
Eric De Sturler for helpful suggestions and useful discussions related with some important topics of this work. ...
doi:10.15388/informatica.2004.066
fatcat:cbv6m4whmbdspnt56l2cj7dzju
Hybrid Iterative-Direct Solution Strategy For Improving The Scalability Of Nuclear Waste Management Simulations
2017
Zenodo
The enabling numerical tool is a domain decomposition solution strategy for the sparse system of linear equations resulting from the spatial discretization of the underlying PDEs (Partial Differential ...
A concrete application is considered for assessing the benefits of using a domain decomposition sparse linear solution strategy as compared to the originally used approach, which is based on a more classical ...
Enabling numerical tool: domain decomposition solver Domain decomposition methods are flexible and powerful techniques for the parallel numerical solution of systems of PDEs. ...
doi:10.5281/zenodo.826134
fatcat:hqymvtg4kbchhme2lt5a5m6hii
Domain Decomposition Based High Performance Parallel Computing
[article]
2009
arXiv
pre-print
The study deals with the parallelization of finite element based Navier-Stokes codes using domain decomposition and state-ofart sparse direct solvers. ...
Hence, the parallelization of sparse direct solvers is done using domain decomposition techniques. A highly efficient sparse direct solver PARDISO is used in this study. ...
Acknowledgments Author would like to thank the Ohio Supercomputing Centre for proving the computing facility. ...
arXiv:0911.0910v1
fatcat:6xujlwd52bhq5czdj42vvfjd2u
Finite Element Tearing and Interconnecting Method and its Algorithms for Parallel Solution of Magnetic Field Problems
2013
Electrical, Control and Communication Engineering
Domain decomposition methods (DDMs) for parallel solution of linear systems of equations are based on the partitioning of the analyzed domain into sub-domains which are calculated in parallel while doing ...
In this case, the non-overlapping domain decomposition method is the Lagrange multiplier based Finite Element Tearing and Interconnecting (FETI) method. ...
ACKNOWLEDGEMENT This paper was supported by the TÁMOP-4.2.2.A-11/1/KONV-2012-0012 : Basic research for the development of hybrid and electric vehicles -The Project is supported by the Hungarian Government ...
doi:10.2478/ecce-2013-0011
fatcat:yqdcht2ldrclzek26it3r4qgbi
A Schur Complement Method for DAE/ODE Systems in Multi-Domain Mechanical Design
[chapter]
2008
Lecture Notes in Computational Science and Engineering
A Schur Complement DDM can then be applied. During some time steps, the Jacobian matrix can be frozen allowing to speed-up the Krylov solvers convergence by projecting onto the Krylov subspace. ...
The large increase of unknowns in multi-domain mechanical modeling leads to investigate new parallel implementation of ODE and DAE systems. ...
Conclusion A Schur domain decomposition method has been investigated to solve systems of ordinary/algebraic differential equations. ...
doi:10.1007/978-3-540-75199-1_67
fatcat:mpne7l43zbhgde4sr74jydklle
Fast parallelized algorithms for on-line extended-term dynamic cascading analysis
2009
2009 IEEE/PES Power Systems Conference and Exposition
described as a set of differential algebraic equations (DAEs). ...
This paper reports on the design Index Terms--high-speed extended term time domain simulation, Differential algebraic equation, Recursive Projection method, Waveform relaxation method, linear solver, multifrontal ...
PROBLEM FORMULATION Time domain simulation of power system involves the solution of a large number of differential algebraic equations (DAEs), which are constructed based on the modeling of the power system ...
doi:10.1109/psce.2009.4840238
fatcat:nzgvqpbszbfubfww75gdruhwte
Agent Architecture for Mesh Based Simulation Systems
[chapter]
2006
Lecture Notes in Computer Science
As an example a framework for finite element simulations, employing a modular architecture (described in [1]), is considered. ...
The paper presents an analysis of requirements for building simulation systems with tightly coupled components, such as typical mesh based PDE approximation software. ...
reordering linear equations linear solver which is considered an external software in the proposed architecture
Domain Decomposition for FEM Core For parallel execution the extension shown in Fig. ...
doi:10.1007/11758532_97
fatcat:4rezeumctbbcxju2zigaf46gcy
High Order Finite Element Schemes And Domain Decomposition Solvers For Large-Scale Simulations In Electromagnetics
2017
Zenodo
The enabling numerical tool is a domain decomposition solution strategy for the sparse system of linear equations resulting from the spatial discretization of the underlying PDEs (Partial Differential ...
The PDEs at hand here are the frequency-domain (or time-harmonic) Maxwell equations. ...
Enabling numerical tool: domain decomposition solver Domain decomposition methods are flexible and powerful techniques for the parallel numerical solution of systems of PDEs. ...
doi:10.5281/zenodo.830354
fatcat:zdaf5nmg3bbntevadby5i737ym
Primal Domain Decomposition Method with Direct and Iterative Solver for Circuit-Field-Torque Coupled Parallel Finite Element Method to Electric Machine Modelling
2015
Advances in Electrical and Electronic Engineering
In this paper, the primal Domain Decomposition Method (DDM) with parallel forward-backward and with parallel Preconditioned Conjugate Gradient (PCG) solvers are introduced in two-dimensional parallel time-stepping ...
Simulation results of a rotating machine is also presented. Keywords Field-circuit-torque coupling, parallel finite element method, primal domain decomposition method. ...
However, it can be concluded based on the presented results, the parallel direct solver is more efficient for the smaller problems, whereas the iterative solver is more useful for larger problem. ...
doi:10.15598/aeee.v13i5.1410
fatcat:cqubceqg7vcppmj32zojdvxi5m
« Previous
Showing results 1 — 15 out of 17,317 results