Parallel Implementation of a Low Order Algorithm for Dynamics of Multibody Systems on a Distributed Memory Computing System
| ISSN: |
1435-5663
|
|---|---|
| Keywords: |
Key words. Distributed memory; Low order algorithm; Multibody dynamics; Parallel computing
|
| Source: |
Springer Online Journal Archives 1860-2000
|
| Topics: |
Computer Science
Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
Technology
|
| Notes: |
Abstract. In this paper, a new hybrid parallelisable low order algorithm, developed by the authors for multibody dynamics analysis, is implemented numerically on a distributed memory parallel computing system. The presented implementation can currently accommodate the general spatial motion of chain systems, but key issues for its extension to general tree and closed loop systems are discussed. Explicit algebraic constraints are used to increase coarse grain parallelism, and to study the influence of the dimension of system constraint load equations on the computational efficiency of the algorithm for real parallel implementation using the Message Passing Interface (MPI). The equation formulation parallelism and linear system solution strategies which are used to reduce communication overhead are addressed. Numerical results indicate that the algorithm is scalable, that significant speed-up can be obtained, and that a quasi-logarithmic relation exists between time needed for a function call and numbers of processors used. This result agrees well with theoretical performance predictions. Numerical comparisons with results obtained from independently developed analysis codes have validated the correctness of the new hybrid parallelisable low order algorithm, and demonstrated certain computational advantages.
|
| Type of Medium: |
Electronic Resource
|
| URL: |
| _version_ | 1798296209836736514 |
|---|---|
| autor | Duan, S. Anderson, K.S. |
| autorsonst | Duan, S. Anderson, K.S. |
| book_url | http://dx.doi.org/10.1007/PL00007191 |
| datenlieferant | nat_lic_papers |
| hauptsatz | hsatz_simple |
| identnr | NLM20682419X |
| iqvoc_descriptor_keyword | iqvoc_00000700:Parallel computing |
| issn | 1435-5663 |
| journal_name | Engineering with computers |
| materialart | 1 |
| notes | Abstract. In this paper, a new hybrid parallelisable low order algorithm, developed by the authors for multibody dynamics analysis, is implemented numerically on a distributed memory parallel computing system. The presented implementation can currently accommodate the general spatial motion of chain systems, but key issues for its extension to general tree and closed loop systems are discussed. Explicit algebraic constraints are used to increase coarse grain parallelism, and to study the influence of the dimension of system constraint load equations on the computational efficiency of the algorithm for real parallel implementation using the Message Passing Interface (MPI). The equation formulation parallelism and linear system solution strategies which are used to reduce communication overhead are addressed. Numerical results indicate that the algorithm is scalable, that significant speed-up can be obtained, and that a quasi-logarithmic relation exists between time needed for a function call and numbers of processors used. This result agrees well with theoretical performance predictions. Numerical comparisons with results obtained from independently developed analysis codes have validated the correctness of the new hybrid parallelisable low order algorithm, and demonstrated certain computational advantages. |
| package_name | Springer |
| publikationsjahr_anzeige | 2000 |
| publikationsjahr_facette | 2000 |
| publikationsjahr_intervall | 7999:2000-2004 |
| publikationsjahr_sort | 2000 |
| publisher | Springer |
| reference | 16 (2000), S. 96-108 |
| schlagwort | Key words. Distributed memory; Low order algorithm; Multibody dynamics; Parallel computing |
| search_space | articles |
| shingle_author_1 | Duan, S. Anderson, K.S. |
| shingle_author_2 | Duan, S. Anderson, K.S. |
| shingle_author_3 | Duan, S. Anderson, K.S. |
| shingle_author_4 | Duan, S. Anderson, K.S. |
| shingle_catch_all_1 | Duan, S. Anderson, K.S. Parallel Implementation of a Low Order Algorithm for Dynamics of Multibody Systems on a Distributed Memory Computing System Key words. Distributed memory; Low order algorithm; Multibody dynamics; Parallel computing Key words. Distributed memory; Low order algorithm; Multibody dynamics; Parallel computing Abstract. In this paper, a new hybrid parallelisable low order algorithm, developed by the authors for multibody dynamics analysis, is implemented numerically on a distributed memory parallel computing system. The presented implementation can currently accommodate the general spatial motion of chain systems, but key issues for its extension to general tree and closed loop systems are discussed. Explicit algebraic constraints are used to increase coarse grain parallelism, and to study the influence of the dimension of system constraint load equations on the computational efficiency of the algorithm for real parallel implementation using the Message Passing Interface (MPI). The equation formulation parallelism and linear system solution strategies which are used to reduce communication overhead are addressed. Numerical results indicate that the algorithm is scalable, that significant speed-up can be obtained, and that a quasi-logarithmic relation exists between time needed for a function call and numbers of processors used. This result agrees well with theoretical performance predictions. Numerical comparisons with results obtained from independently developed analysis codes have validated the correctness of the new hybrid parallelisable low order algorithm, and demonstrated certain computational advantages. 1435-5663 14355663 Springer |
| shingle_catch_all_2 | Duan, S. Anderson, K.S. Parallel Implementation of a Low Order Algorithm for Dynamics of Multibody Systems on a Distributed Memory Computing System Key words. Distributed memory; Low order algorithm; Multibody dynamics; Parallel computing Key words. Distributed memory; Low order algorithm; Multibody dynamics; Parallel computing Abstract. In this paper, a new hybrid parallelisable low order algorithm, developed by the authors for multibody dynamics analysis, is implemented numerically on a distributed memory parallel computing system. The presented implementation can currently accommodate the general spatial motion of chain systems, but key issues for its extension to general tree and closed loop systems are discussed. Explicit algebraic constraints are used to increase coarse grain parallelism, and to study the influence of the dimension of system constraint load equations on the computational efficiency of the algorithm for real parallel implementation using the Message Passing Interface (MPI). The equation formulation parallelism and linear system solution strategies which are used to reduce communication overhead are addressed. Numerical results indicate that the algorithm is scalable, that significant speed-up can be obtained, and that a quasi-logarithmic relation exists between time needed for a function call and numbers of processors used. This result agrees well with theoretical performance predictions. Numerical comparisons with results obtained from independently developed analysis codes have validated the correctness of the new hybrid parallelisable low order algorithm, and demonstrated certain computational advantages. 1435-5663 14355663 Springer |
| shingle_catch_all_3 | Duan, S. Anderson, K.S. Parallel Implementation of a Low Order Algorithm for Dynamics of Multibody Systems on a Distributed Memory Computing System Key words. Distributed memory; Low order algorithm; Multibody dynamics; Parallel computing Key words. Distributed memory; Low order algorithm; Multibody dynamics; Parallel computing Abstract. In this paper, a new hybrid parallelisable low order algorithm, developed by the authors for multibody dynamics analysis, is implemented numerically on a distributed memory parallel computing system. The presented implementation can currently accommodate the general spatial motion of chain systems, but key issues for its extension to general tree and closed loop systems are discussed. Explicit algebraic constraints are used to increase coarse grain parallelism, and to study the influence of the dimension of system constraint load equations on the computational efficiency of the algorithm for real parallel implementation using the Message Passing Interface (MPI). The equation formulation parallelism and linear system solution strategies which are used to reduce communication overhead are addressed. Numerical results indicate that the algorithm is scalable, that significant speed-up can be obtained, and that a quasi-logarithmic relation exists between time needed for a function call and numbers of processors used. This result agrees well with theoretical performance predictions. Numerical comparisons with results obtained from independently developed analysis codes have validated the correctness of the new hybrid parallelisable low order algorithm, and demonstrated certain computational advantages. 1435-5663 14355663 Springer |
| shingle_catch_all_4 | Duan, S. Anderson, K.S. Parallel Implementation of a Low Order Algorithm for Dynamics of Multibody Systems on a Distributed Memory Computing System Key words. Distributed memory; Low order algorithm; Multibody dynamics; Parallel computing Key words. Distributed memory; Low order algorithm; Multibody dynamics; Parallel computing Abstract. In this paper, a new hybrid parallelisable low order algorithm, developed by the authors for multibody dynamics analysis, is implemented numerically on a distributed memory parallel computing system. The presented implementation can currently accommodate the general spatial motion of chain systems, but key issues for its extension to general tree and closed loop systems are discussed. Explicit algebraic constraints are used to increase coarse grain parallelism, and to study the influence of the dimension of system constraint load equations on the computational efficiency of the algorithm for real parallel implementation using the Message Passing Interface (MPI). The equation formulation parallelism and linear system solution strategies which are used to reduce communication overhead are addressed. Numerical results indicate that the algorithm is scalable, that significant speed-up can be obtained, and that a quasi-logarithmic relation exists between time needed for a function call and numbers of processors used. This result agrees well with theoretical performance predictions. Numerical comparisons with results obtained from independently developed analysis codes have validated the correctness of the new hybrid parallelisable low order algorithm, and demonstrated certain computational advantages. 1435-5663 14355663 Springer |
| shingle_title_1 | Parallel Implementation of a Low Order Algorithm for Dynamics of Multibody Systems on a Distributed Memory Computing System |
| shingle_title_2 | Parallel Implementation of a Low Order Algorithm for Dynamics of Multibody Systems on a Distributed Memory Computing System |
| shingle_title_3 | Parallel Implementation of a Low Order Algorithm for Dynamics of Multibody Systems on a Distributed Memory Computing System |
| shingle_title_4 | Parallel Implementation of a Low Order Algorithm for Dynamics of Multibody Systems on a Distributed Memory Computing System |
| sigel_instance_filter | dkfz geomar wilbert ipn albert fhp |
| source_archive | Springer Online Journal Archives 1860-2000 |
| timestamp | 2024-05-06T09:48:28.428Z |
| titel | Parallel Implementation of a Low Order Algorithm for Dynamics of Multibody Systems on a Distributed Memory Computing System |
| titel_suche | Parallel Implementation of a Low Order Algorithm for Dynamics of Multibody Systems on a Distributed Memory Computing System |
| topic | SQ-SU ZL ZG |
| uid | nat_lic_papers_NLM20682419X |