A Fast and High Quality Multilevel Scheme for Partitioning Irregular Graphs
SIAM Journal on Scientific Computing
Mesh Partitioning: A Multilevel Balancing and Refinement Algorithm
SIAM Journal on Scientific Computing
On the Quality of Partitions Based on Space-Filling Curves
ICCS '02 Proceedings of the International Conference on Computational Science-Part III
Towards Convergence in Job Schedulers for Parallel Supercomputers
IPPS '96 Proceedings of the Workshop on Job Scheduling Strategies for Parallel Processing
Validity of the single processor approach to achieving large scale computing capabilities
AFIPS '67 (Spring) Proceedings of the April 18-20, 1967, spring joint computer conference
| Hi-index | 0.00 |
In this paper we show the efficient parallelisation of an application for transient structural dynamics analysis which is used in an industrial environment. The parallelisation is designed for shared memory systems and includes a highly dynamic load balancing and the ability to change the number of computing threads during runtime. Furthermore, we suggest a runtime support system (Application Parallelism Manager) for parallel systems in multi-user mode which calculates a processor assignment on-line. It ensures a fair and dynamic management of the jobs whereby the machine is neither idle nor overloaded. It communicates with the applications which report measurement values and adjust the number of their threads. Results of artificial examples and real-world experiments with the runtime support system are presented.