|
| This Article | ||
| ||
| Share | ||
| Bibliographic References | ||
| Add to: | ||
| | ||
| Search | ||
| ||
2009 International Conference on Parallel Processing Workshops
Flat MPI vs. Hybrid: Evaluation of Parallel Programming Models for Preconditioned Iterative Solvers on
Vienna, Austria
September 22-September 25
ISBN: 978-0-7695-3803-7
| ASCII Text | x | ||
| Kengo Nakajima, "Flat MPI vs. Hybrid: Evaluation of Parallel Programming Models for Preconditioned Iterative Solvers on ," 2012 41st International Conference on Parallel Processing Workshops, pp. 73-80, 2009 International Conference on Parallel Processing Workshops, 2009. | |||
| BibTex | x | ||
| @article{ 10.1109/ICPPW.2009.68, author = {Kengo Nakajima}, title = {Flat MPI vs. Hybrid: Evaluation of Parallel Programming Models for Preconditioned Iterative Solvers on }, journal ={2012 41st International Conference on Parallel Processing Workshops}, volume = {0}, year = {2009}, issn = {1530-2016}, pages = {73-80}, doi = {http://doi.ieeecomputersociety.org/10.1109/ICPPW.2009.68}, publisher = {IEEE Computer Society}, address = {Los Alamitos, CA, USA}, } | |||
| RefWorks Procite/RefMan/Endnote | x | ||
| TY - CONF JO - 2012 41st International Conference on Parallel Processing Workshops TI - Flat MPI vs. Hybrid: Evaluation of Parallel Programming Models for Preconditioned Iterative Solvers on SN - 1530-2016 SP73 EP80 A1 - Kengo Nakajima, PY - 2009 KW - Parallel Iterative Solvers KW - Preconditning KW - Hybrid Parallel Programming Model VL - 0 JA - 2012 41st International Conference on Parallel Processing Workshops ER - | |||
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/ICPPW.2009.68
In this work, parallel preconditioning methods based on “Hierarchical Interface Decomposition (HID)” and hybrid parallel programming models were applied to finite-element based simulations of linear elasticity problems in media with heterogeneous material properties. Reverse Cuthill-McKee reordering with cyclic multicoloring (CM-RCM) was applied for parallelism through OpenMP. The developed code has been tested on the “T2K Open Supercomputer (Todai Combined Cluster)” using up to 512 cores. Performance of Hybrid 4´4 parallel programming model is competitive with that of flat MPI using appropriate command lines for NUMA control. Furthermore, reordering of the mesh data for contiguous access to memory with first touch data placement provides excellent improvement on performance of Hybrid 8´2 and 16´1, especially if the problem size for each core is relatively small. Thus, hybrid parallel programming model could be a reasonable choice for large-scale computing of sparse linear solvers on multi-core/multi-socket architectures, such as “T2K Open Supercomputer”.
Index Terms:
Parallel Iterative Solvers, Preconditning, Hybrid Parallel Programming Model
Citation:
Kengo Nakajima, "Flat MPI vs. Hybrid: Evaluation of Parallel Programming Models for Preconditioned Iterative Solvers on ," icppw, pp.73-80, 2009 International Conference on Parallel Processing Workshops, 2009
Usage of this product signifies your acceptance of the Terms of Use.
