Abstract
Many mesh optimization applications are based on vertex repositioning algorithms (VrPA). Since the time required for VrPA programs may be large and there is concurrency in processing mesh elements, parallelism has been used to improve performance. In this paper, we propose a performance model for parallel VrPA algorithms that are implemented on memory-distributed computers. This model is validated on two parallel computers and used in a quantitative analysis of performance scalability, load balancing and synchronization and communication overheads. We show that load imbalance and synchronization between boundary partitions are the major causes of the parallel bottlenecks. In order to diminish load imbalance, a new approach to mesh partitioning is proposed. This strategy reduces the imbalance in mesh element evaluations caused by multilevel k-way partitioning algorithms and consequently, improves the performance of parallel VrPA algorithms.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
K. Barker, N. Chrisochoides, Practical performance model for optimizing dynamic load balancing of adaptive applications, in Proceedings of the 19th IPDPS, 28.a-28.b (2005)
D. Benitez, J.M. Escobar, R. Montenegro, E. Rodriguez, Performance comparison and workload analysis of mesh untangling and smoothing algorithms, in Proceedings of the 27th International Meshing Roundtable (2018)
D. Bozdag, A. Gebremedhin, F. Manne, E. Boman, U. Catalyurek, A framework for scalable greedy coloring on distributed memory parallel computers. J. Parallel Distrib. Comput. 68(4), 515–535 (2008)
M. Brewer, L. Diachin, P. Knupp, T. Leurent, D. Melander, The mesquite mesh quality improvement toolkit, in Proceedings of the 12th International Meshing Roundtable (2003), pp. 239–250
N. Chrisochoides, A survey of parallel mesh generation methods. Technical Report. SC-2005-09. Brown University (2005)
L. Diachin, P. Knupp, T. Munson, S. Shontz, A comparison of inexact Newton and coordinate descent mesh optimization techniques, in Proceedings of the 13th International Meshing Roundtable (2004), pp. 243–254
J.M. Escobar, E. Rodríguez, R. Montenegro, G. Montero, J.M. González-Yuste, Simultaneous untangling and smoothing of tetrahedral meshes. Comput. Methods Appl. Mech. Eng. 192, 2775–2787 (2003)
L. Freitag, M.T. Jones, P.E. Plassmann, A parallel algorithm for mesh smoothing. SIAM J. Sci. Comput. 20(6), 2023–2040 (1999)
C. Geuzaine, J.F. Remacle, Gmsh: a three-dimensional finite element mesh generator with built-in pre- and post-processing facilities. Int. J. Numer. Methods Eng. 79(11), 1309–1331 (2009)
W. Gropp, L.N. Olson, P. Samfass, Modeling MPI communication performance on SMP nodes, in Proceedings of the 23rd European MPI Users Group Meeting (2016)
G. Karypis, METIS (version 5.1.0) – A Software Package for Partitioning Unstructured Graphs, Partitioning Meshes, and Computing Fill-reducing Orderings of Sparse Matrices. University of Minnesota (2013)
P. Knupp, Updating meshes on deforming domains: an application of the target-matrix paradigm. Commun. Numer. Method Eng. 24, 467–476 (2007)
M. Mathis, D. Kerbyson, A general performance model of structured and unstructured mesh particle transport computations. J. Supercomput. 34, 181–199 (2005)
R. Montenegro, J.M. Cascón, J.M. Escobar, E. Rodríguez, G. Montero, An automatic strategy for adaptive tetrahedral mesh generation. Appl. Numer. Math. 59(9), 2203–2217 (2009)
T. Panitanarak, S.M. Shontz, A parallel log barrier-based mesh warping algorithm for distributed memory machines. Eng. Comput. 34, 59–76 (2018)
A. Sarje, S. Song, D. Jacobsen, K. Huck, J. Hollingsworth, A. Malony, S. Williams, L. Oliker, Parallel performance optimizations on unstructured mesh-based simulations. Procedia Comput. Sci. 51, 2016–2025 (2015)
S.P. Sastry, S.M. Shontz, A parallel log-barrier method for mesh quality improvement and untangling. Eng. Comput. 30(4), 503–515 (2014)
S.P. Sastry, S.M. Shontz, S.A. Vavasis, A log-barrier method for mesh quality improvement and untangling. Eng. Comput. 30(3), 315–329 (2014)
R.B. Schnabel, Concurrent function evaluations in local and global optimization. CU-CS-345-86. Computer Science Technical Report. 332. University of Colorado, Boulder (1986)
Acknowledgements
This work has been supported by Spanish Government, “Secretaría de Estado de Universidades e Investigación”, “Ministerio de Economía y Competitividad” and FEDER, grant contract: CTM2014-55014-C3-1-R. Cluster2 (TeideHPC) was provided by the “Instituto Tecnológico y de Energías Renovables, S.A.”. We thank to anonymous reviewers for their valuable comments and suggestions on this manuscript.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this chapter
Cite this chapter
Benitez, D., Escobar, J.M., Montenegro, R., Rodriguez, E. (2019). Parallel Performance Model for Vertex Repositioning Algorithms and Application to Mesh Partitioning. In: Roca, X., Loseille, A. (eds) 27th International Meshing Roundtable. IMR 2018. Lecture Notes in Computational Science and Engineering, vol 127. Springer, Cham. https://doi.org/10.1007/978-3-030-13992-6_23
Download citation
DOI: https://doi.org/10.1007/978-3-030-13992-6_23
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-13991-9
Online ISBN: 978-3-030-13992-6
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)