Gabriela Moreira Azevedo · LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) · 2019
In the finite element structural analysis, complex mechanisms representation in structures are increasing and requiring models with a great number of degrees of freedom. This situation represents a significant problem both in performance and memory usage on computers, particularly on phases such as assembling and solving of the equations system. Thus, there is a great need for high technology and performance computers. However, the use of these machines is very inefficient when considering its cost and, as the technology advances, the need for occasional replacement. In order to solve this situation, attentions turned to the use of parallel computers. In this system modality, a big and complex problem is divided in smaller portions, that are individually solved in different computers. Therefore, parallel computing bring great advantages, such as smaller demand on components like memory and processor, besides the easiness to add new units on the system. Nonetheless, the concurrency demand the use of algorithms other than those from sequential computing, especially when high performance is needed. For the resulting time of a parallel computing be advantageous, the division of tasks must be performed in such way that all processes end at the same time along with minimum communication. Considering the finite element method, procedures that perform a homogeneous division of elements among all processors and domains frontier minimization are essential. As a consequence of this, the requirement for well balanced workload and minimal communication is met. This work addresses a finite element method parallel implementation. For this, the INSANE (Interactive Structural Analysis Environment) system, the Java programming language, the Object Oriented paradigm and the MPI (Message Passing Interface) pattern of data exchenge and communication are used.
Cited by 0Open access
Moto Mpong, S., de Montleau, P., Godinas, A. et al. · Open Repository and Bibliography (University of Liège) · 2002
peer reviewed
Cited by 0Open access
Chinchalkar And, S. Chinchalkar, D. L. Taylor · 2007
This paper describes methods for parallel stochastic finite element analysis using distributed memory multiprocessors. The conventional finite element method is deterministic and fails to account for uncertainties in loads, material properties, geometry and boundary conditions. Stochastic fem can be used to compute the variability in the structural response. It requires considerable more computational effort than the deterministic method, making it necessary to exploit parallelism in order to solve large, realistic structural problems. This paper describes parallel versions of the First Order Second Moment method as well as Monte Carlo simulation for analyzing structures with random material properties. Stochastic fem is composed of several sub-problems such as solution of a banded system of equations, the real symmetric eigenvalue problem, sensitivity analysis and structural reanalysis. Parallelism can be exploited at all stages of the solution process. These methods were implemented ...
Cited by 0
Michelle R. Hribar, Valerie E. Taylor · 1994
The use of parallel processors has made it possible to execute large scale applications such as finite element analysis. Generally, the speedup is limited by the interprocessor communication used by message-passing multicomputers. The major question addressed by users of message-passing machines is the identification of the most efficient type of communication scheme for the particular application. Practical considerations such as the following are frequently neglected: the range of message sizes for which a communication scheme is appropriate, the impact on the subdomain size, the memory requirements versus the actual memory of the machine, and how the optimal communication method changes as a fixed size problem is scaled to a larger number of processors. In this paper we address these practical issues for 2-D finite element problems executed on the Intel Delta machine. 1 INTRODUCTION The use of parallel processors has made it possible to execute large scale applications such as fini...
Cited by 0
Jiang, Rong · eScholarship@McGill (McGill) · 2004
One of the primary methods in the numerical solution of large-scale scientific and engineering applications is to use the finite element method. Consequently, maintaining a good mesh quality becomes very important in the unstructured mesh. In order to achieve high quality meshes, a number of mesh smoothing techniques have been used. Most of these techniques are able to improve the mesh quality effectively. In this research, the Laplacian smoothing algorithm, combined with two complementary methods, is investigated.
Cited by 0Open access
Chaojiang Fu, Mian-Yue Yang · DEStech Transactions on Environment Energy and Earth Science · 2016
The parallel algorithm for nonlinear dynamic analysis of large structures is presented using domain decomposition and preconditioned conjugate gradient(PCG) technique. In the formulation called the global interface formulation(GIF), the PCG algorithm is applied on the assembled interface stiffness coefficient matrices of all subdomains. Newmark-β average acceleration technique is employed for time integration. Numerical results indicate that the proposed GIF formulation is superior to the conventional domain decomposition algorithm.
Cited by 0Open access
T. Horie, Hiroyuki KURAMAE · Computer-Aided Civil and Infrastructure Engineering · 1997
Cited by 8
Chaojiang Fu · 2009
A parallel algorithm for nonlinear transient dynamic analysis of large structures is presented in this paper. An unconditionally stable Newmark-ß method (average acceleration technique) is employed for time integration. The proposed parallel algorithm is devised using overlapped domains, unlike most of the existing parallel algorithms which are basically derived using nonoverlapped domains. A predictor-corrector scheme is formulated for iteratively improving the solution in each step. The algorithm is implemented on a cluster of workstation. Numerical results indicate that the proposed algorithm is superior in performance to the conventional domain decomposition algorithms.
Cited by 3
M. Papadrakakis, D.C. Harbis · Civil-comp proceedings · 2009
Cited by 1
Chris Salisbury, Woosoon Yim · Volume 7: Dynamic Systems and Control; Mechatronics and Intelligent Machines, Parts A and B · 2011
A novel three-dimensional robotic surface is devised and implemented using triangular modules. Each module is connected by a passive sixbar mechanism that mimics the constraints of a spherical joint at each triangle intersection. The finite element method (FEM) is applied to the static loading of this device using linear three dimensional (6 degrees of freedom) beam elements to calculate the cartesian displacement and force and the angular displacement and torque at each joint. In this way, the traditional methods of finding joint forces and torques are completely bypassed. An effiecient algorithm is developed to linearly combine local stiffness matrices into a full structural stiffness matrix for the easy application of loads. This is then decomposed back into the local matrices to easily obtain joint variables used in the design and open-loop control of the surface.
Cited by 0
Wu Zhou, Yaoru Liu, Yin Huang · 2026
For FEM solution of complex hydraulic structures, parallel method is usually needed to deal with large amount of numerical computations. In this paper, the authors present an EBE-PCG solver which adopt Jacobi-conditioned conjugate gradient algorithm. For data exchange, a working scheme in which only necessary data is needed to gather and scatter is submitted to make EBE method available for distributedmemory parallel computers. This method could dramatically reduce data exchange and consequently improve efficiency of parallel computing. At the same time, it is very easy to reach load balance for solving three-dimensional FEM. For any complicated three-dimensional structures, the algorithm can be convenient for automatically allocate the task in parallel computing. Based on this algorithm, the authors developed PFEM code using MPICH and C/C++ language. Numerical example of an Arch dam-foundation system demonstrates that PFEM is applicable for complicated three-dimensional underground structures.
Cited by 0
S. Ratnajeevan H. Hoole · Elsevier eBooks · 1995
Cited by 1
G. Bedrosian, R. W. Benway · Journal of Applied Physics · 1993
This paper examines our recent experiences and progress in porting an in-house magnetostatic finite-element analysis code, H3D, to multiple-instruction, multiple-data (MIMD) parallel computers using the distributed-memory, message-passing (DMMP) paradigm. Experiments with two different message-passing software libraries were done, one specifically for the Intel iPSC/860 Hypercube, and another called parallel virtual machine (PVM) that runs on many different systems from networks of heterogeneous workstations connected by a local area network to supercomputers with multiple closely coupled CPUs. Techniques are discussed for performing key parts of the finite-element analysis in a parallel environment, including calculation of the source field, matrix assembly, and matrix solution. In conclusion, PVM is the preferable environment for most applications, despite its lack of maturity, because it facilitates porting software to many hardware systems without extensive rewriting.
Cited by 1
S I Homenyk, V Yu Kozub · IOP Conference Series Materials Science and Engineering · 2021
Abstract To optimize finite elements computational processes of the “MIRELA +” computing complex, parallel programming algorithms have been developed for creating stiffness matrices of finite elements and calculating the stress-strain. The parallel data processing is implemented using OpenMP library. On the basis of computational methods of experiments, the use of parallel computing algorithms at the beginning of solving problems with traditional finite element algorithms for large-dimensional grids has been established.
Cited by 3Open access
Chris Salisbury · 2011
A novel three-dimensional robotic surface is devised using triangular modules connected by revolute joints that mimic the constraints of a spherical joint at each triangle intersection. The finite element method (FEM) is applied to the dynamic loading of this device using three dimensional (6 degrees of freedom) beam elements to not only calculate the cartesian displacement and force, but also the angular displacement and torque at each joint. In this way, the traditional methods of finding joint forces and torques are completely bypassed. An effiecient algorithm is developed to linearly combine local mass and stiffness matrices into a full structural stiffness matrix for the easy application of loads. An analysis of optimal dynamic joint forces is carried out in Simulink® with the use of an algebraic Ricatti equation.
Cited by 0
Hoppe, Ronald H. W., Iliash, Yuri, Kuznetsov, Yuri A. et al. · OPUS (Augsburg University) · 1998
Cited by 5
Takayuki Sasaki, Hiroshi Okuda · Keisan Rikigaku Koenkai koen ronbunshu/Keisan Rikigaku Kouenkai kouen rombunshuu · 2004
Key r Finite El ent Nethod( nta t AnaIysis the Augnented Lagrangian Method
Cited by 0Open access
Vr. Annamalai, C.S. Krishnamoorthy, V. Kamakoti · Parallel Computing · 1999
Cited by 11
Balaji Raghavan, Piotr Breitkopf, Catherine Knopf‐Lenoir · HAL (Le Centre pour la Communication Scientifique Directe) · 2010
International audience
Cited by 1
Naveen Sharma · 1992
In this thesis, I develop a coupled symbolic-numeric approach to solve PDE-based mathematical models. Existing software packages to solve these models are written in F scORTRAN and provide facilities for frequently used local formulations and numerical solution procedures. These canned packages can not be used where new formulations, new solution procedures, or parallel execution is required. The present research work is concerned with design and development of a program synthesizer for computationally intensive and problem formulation, dependent phases of the solution method. The emphasis is on the finite element analysis (FEA) method of solution although the techniques developed are applicable for other methods of solution.
The idea is to employ methods from computer algebra to derive element formulations like shape functions, element stiffness matrices, etc. for more than one formulation. The problem specific information and element approximations are then used to generate sequential and parallel numerical procedures for FEA solution steps. An experimental software system, PIER, is being developed in Common Lisp for the purpose.
PIER features a programming knowledge base of program schemas which can be instantiated to construct code fragments or subroutines required in FEA solution solution steps. A very high level user input specification mechanism enables the modeler to transcribe a textbook-like FEA procedure description into PIER input form and to add the same to the programming knowledge base. Experiments with two different FEA schemes i.e. element-by-element and traditional assembly approaches are carried out. The generated parallel routines execute in conjunction with an existing FEA package. Currently the target parallel architectures include the Warp (systolic array) and the Sequent Balance shared memory architectures.
Cited by 1