In this paper, the performance of a special algebraic multigrid (AMG) solver for the solution of stress analysis problems in process simulation has been investigated. The discrete stress analysis equations are generat...
详细信息
In this paper, the performance of a special algebraic multigrid (AMG) solver for the solution of stress analysis problems in process simulation has been investigated. The discrete stress analysis equations are generated directly by the process simulator. The practical simulation examples include stress analysis during natively growing and deposited material films. It is shown that approaches using the AMG solver as a preconditioner are better than standard iterative solvers with regard to computing times and convergence behavior. A further comparison demonstrates that these AMG approaches are faster than the SuperLU direct solver.
Numerical simulation in electrical engineering allows one to reduce development costs by predicting device performance. An accurate prediction often requires 3D models, inducing high storage capacity and CPU power nee...
详细信息
Numerical simulation in electrical engineering allows one to reduce development costs by predicting device performance. An accurate prediction often requires 3D models, inducing high storage capacity and CPU power needs. As computation times can be very important, parallel computers are well suited to these models. 3D simulation in electrical engineering is based on recent research work (Whitney's elements, auto-gauged formulations, discretization of the source terms) and it results in complex and irregular codes using sparse matrices, where data accesses are done via indirect addressing. We present the results of the parallelization of a 3D magnetostatic code using High Performance Fortran (HPF). This high level programming language allows a simple and efficient approach to parallel machines. It provides both easier maintenance of the code and higher software productivity for electrical engineers.
The FETI and Neumann-Neumann families of algorithms are among the best known and most severely tested domain decomposition methods for elliptic partial differential equations. They are iterative substructuring methods...
In the numerical simulation of crashworthiness the use of parallel architectures is becoming more and more important. This stems from the desire of engineers in the motorcar industry to get run times whichmake a dialo...
详细信息
The PARMACS message passing interface has been in widespread use by application projects, especially in Europe. With the new MPI standard for message passing, many projects face the problem of replacing PARMACS with M...
The PARMACS message passing interface has been in widespread use by application projects, especially in Europe. With the new MPI standard for message passing, many projects face the problem of replacing PARMACS with MPI. An automatic translation tool has been developed which replaces all PARMACS 6.0 calls in an application program with their corresponding MPI calls. In this paper we describe the mapping of the PARMACS programming model onto MPI. We then present some implementation details of the converter tool.
Motivation: Matching of chemical interacting groups is a common concept for docking and fragment placement algorithms in computer-aided drug design. These algorithms have been proven to be reliable and fast if at leas...
Motivation: Matching of chemical interacting groups is a common concept for docking and fragment placement algorithms in computer-aided drug design. These algorithms have been proven to be reliable and fast if at least a certain number of hydrogen bonds or salt bridges occur: However, the algorithms typically run into problems if hydrophobic fragments or ligands should be placed In order to dock hydrophobic fragments without significant loss of computational efficiency we have extended the interaction model and placement algorithms in our docking tool FlexX. The concept of multi-level interactions is introduced into the algorithms for automatic selection and placement of base fragments. Results: With the multi-level interaction model and the corresponding algorithmic extensions, we were able to improve the overall performance of FlexX significantly. We tested the approach with a set of 200 protein-ligand complexes taken from the Brookhaven Protein Data Bank (PDB). The number of test cases which can be docked within 1.5 Angstrom RMSD from the crystal structure can be increased from 58 to 64%. The performance gain is paid for by an increase in computation time from 73 to 91 s on average per protein-ligand complex.
In order to prepare for the upgrade of the German national scientific network to gigabit capacity in the year 2000, two testbeds have been set up. One of them, the 'Gigabit Testbed West', uses a 2.4 Gbit/s ATM...
详细信息
In order to prepare for the upgrade of the German national scientific network to gigabit capacity in the year 2000, two testbeds have been set up. One of them, the 'Gigabit Testbed West', uses a 2.4 Gbit/s ATM link to connect the Research Centre Julich and the GMD-National Research Center for Information Technology in Sankt Augustin. The testbed is the basis for several application projects, ranging from metacomputing to multimedia. This paper gives an overview of the infrastructure of the testbed and its applications. As an example, the real-time analysis and visualization of functional MRI measurements of the human brain are described in detail.
In this paper, we present our contribution for handling irregular applications with HPF2. We propose a programming style of irregular applications close to the regular case, so that both compile-time and run-time tech...
详细信息
ISBN:
(纸本)3540649522
In this paper, we present our contribution for handling irregular applications with HPF2. We propose a programming style of irregular applications close to the regular case, so that both compile-time and run-time techniques can be more easily performed. We use the well-known tree data structure to represent irregular data structures with hierarchical access, such as sparse matrices. This algorithmic representation avoids the indirections coming from the standard irregular programming style. We use derived data types of Fortran 90 to define trees and some approved extensions of HPF2 for their mapping. We also propose a run-time support for irregular applications with loop-carried dependencies that cannot be determined at compile-time. Then, we present the TriDenT library, which supports distributed trees and provides runtime optimizations based on the inspector/executor paradigm. Finally, we validate our contribution with experimental results on IBM SP2 for a sparse Cholesky factorization algorithm.
暂无评论