Abstract
ESPRESO is a FEM package that includes a Hybrid Total FETI (HTFETI) linear solver targeted at solving large scale engineering problems. The scalability of the solver was tested on several of the world’s largest supercomputers. To provide our scalable implementation of HTFETI algorithms to all potential users, a simple C API was developed and is presented. The paper describes API methods, compilation and linking process.
As a proof of concept we interfaced ESPRESO with the CSC ELMER solver and compared its performance with the ELMER FETI solver. HTFETI performs two level decomposition, which significantly improves both memory utilization and solver performance. To select optimal second level decomposition we have developed a performance model that controls decomposition automatically. This is a major simplification for all users that ensures optimal solver settings.
We show that the ESPRESO HTFETI solver is up to 3.7 times faster than the ELMER FETI solver when running on 13 500 MPI processes (the 614 compute nodes of the Salomon supercomputer) and solving 1.5 billion unknown problems of 3D linear elasticity.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Farhat, C., Roux, F.X., Oden, J.T.: Implicit Parallel Processing in Structural Mechanics. Elsevier Science, Amsterdam (1994)
Farhat, C., Mandel, J., Roux, F.X.: Optimal convergence properties of the FETI domain decomposition method. Comput. Method Appl. Mech. Eng. 115, 365–385 (1994)
Farhat, C., Lesoinne, M., LeTallec, P., Pierson, K., Rixen, D.: FETI-DP: a dual-primal unified FETI method, part I: a faster alternative to the two-level FETI method. Int. J. Numer. Meth. Eng. 50(7), 1523–1544 (2001)
Klawonn, A., Widlund, O.B., Dryja, M.: Dual-primal FETI methods for three-dimensional elliptic problems with heterogeneous coefficients. SIAM J. Numer. Anal. 40, 159–179 (2002)
Dostál, Z., Horák, D., Kučera, R.: Total FETI - an easier implementable variant of the FETI method for numerical solution of elliptic PDE. Commun. Numer. Methods Eng. 196, 1155–1162 (2006)
Klawonn, A., Rheinbach, R.: Highly scalable parallel domain decomposition methods with an application to biomechanics. ZAMM 1, 5–32 (2010)
Klawonn, A., Lanser, M., Rheinbach, O.: Toward extremely scalable nonlinear domain decomposition methods for elliptic partial differential equations. SIAM J. Sci. Comput. 37(6), C667–C696 (2015)
Brzobohatý, T., Jarošová, M., Kozubek, T., Menšík, M., Markopoulos, A.: The hybrid total FETI method. In: Proceedings of the Third International Conference on Parallel, Distributed, Grid and Cloud Computing for Engineering. Civil-Comp, Ltd. (2011)
Intel: Math kernel library. https://software.intel.com/en-us/mkl
Petra, C.G., Schenk, O., Lubin, M., Gärtner, K.: An augmented incomplete factorization approach for computing the Schur complement in stochastic optimization. SIAM J. Sci. Comput. 36(2), C139–C162 (2014)
Petra, C.G., Schenk, O., Anitescu, M.: Real-time stochastic optimization of complex energy systems on high-performance computers. IEEE Comput. Sci. Eng. 16(5), 32–42 (2014)
Suzuki, A., Roux, F.X.: A dissection solver with kernel detection for symmetric finite element matrices on shared memory computers. Int. J. Numer. Methods Eng. 100(2), 136–164 (2014)
Karypis, G., Kumar, V.: A fast and high quality multilevel scheme for partitioning irregular graphs. SIAM J. Sci. Comput. 20(1), 359–392 (1998)
Říha, L., Brzobohatý, T., Markopoulos, A., Meca, O., Kozubek, T.: Massively parallel hybrid total FETI (HTFETI) solver. In: Proceedings of the Platform for Advanced Scientific Computing Conference, PASC 2016, pp. 7:1–7:11. ACM, New York (2016)
ESPRESO: Public repository. https://github.com/It4innovations/espreso
ESPRESO: Documentation. http://espreso.it4i.cz/
Elmer: CSC - IT Center for Science. https://www.csc.fi/web/elmer
Elmer: Public repository. https://github.com/elmercsc/elmerfem
Acknowledgement
This work was supported by The Ministry of Education, Youth and Sports from the Large Infrastructures for Research, Experimental Development and Innovations project “IT4Innovations National Supercomputing Center – LM2015070”.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2018 Springer International Publishing AG, part of Springer Nature
About this paper
Cite this paper
Meca, O., Říha, L., Markopoulos, A., Brzobohatý, T., Kozubek, T. (2018). Using ESPRESO as Linear Solver Library for Third Party FEM Tools for Solving Large Scale Problems. In: Kozubek, T., et al. High Performance Computing in Science and Engineering. HPCSE 2017. Lecture Notes in Computer Science(), vol 11087. Springer, Cham. https://doi.org/10.1007/978-3-319-97136-0_10
Download citation
DOI: https://doi.org/10.1007/978-3-319-97136-0_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-97135-3
Online ISBN: 978-3-319-97136-0
eBook Packages: Computer ScienceComputer Science (R0)