Computational cost of isogeometric multifrontal solvers on parallel distributed memory machines
Abstract
This paper derives theoretical estimates of the computational cost for isogeometric multifrontal direct solver executed on parallel distributed memory machines. We show theoretically that for the Cp1 global continuity of the isogeometric solution, both the computational cost and the communication cost of a direct solver are of order O(log(N)p2) for the one dimensional (1D) case, O(Np2) for the two dimensional (2D) case, and O(N4/3p2) for the three dimensional (3D) case, where N is the number of degrees of freedom and p is the polynomial order of the Bspline basis functions. The theoretical estimates are verified by numerical experiments performed with three parallel multifrontal direct solvers: MUMPS, PaStiX and SuperLU, available through PETIGA toolkit built on top of PETSc. Numerical results confirm these theoretical estimates both in terms of p and N. For a given problem size, the strong efficiency rapidly decreases as the number of processors increases, becoming about 20% for 256 processors for a 3D example with 1283 unknowns and linear Bsplines with C0 global continuity, and 15% for a 3D example with 643 unknowns and quartic Bsplines with C3 global continuity. At the same time, one cannot arbitrarily increase the problem size, since the memory required by higher order continuity spaces is large, quickly consuming all the available memory resources even in the parallel distributed memory version. Numerical results also suggest that the use of distributed parallel machines is highly beneficial when solving higher order continuity spaces, although the number of processors that one can efficiently employ is somehow limited.
Citation
Source Title
ISSN
School
Collection
Related items
Showing items related by title, author, creator and subject.

Wozniak, M.; Kuznik, K.; Paszynski, M.; Calo, Victor; Pardo, D. (2014)In this paper we present computational cost estimates for parallel shared memory isogeometric multifrontal solvers. The estimates show that the ideal isogeometric shared memory parallel direct solver scales as O( p2log(N/p)) ...

Paszynski, M.; Kuznik, K.; Calo, Victor; Pardo, D. (2013)We present a multifrontal direct solver for two dimensional isogeometric finite element method simulations with NVIDIA CUDA and perform numerical experiments for linear, quadratic and cubic Bsplines. We compare the ...

Campbell, Stuart M. (1999)Parallel computing has long been an area of research interest because exploiting parallelism in difficult problems has promised to deliver orders of magnitude speedups. Processors are now both powerful and cheap, so that ...