Hybrid scheduling for the parallel solution of linear systems

By Patrick R. Amestoy, A. Guermouche, Jean-Yves L'Excellent, S. Pralet. Parallel Computing, 2006

1,144 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Hardware and Architecture

View Paper: https://www.semanticscholar.org/paper/fe73a3ac9bc838c375e7e7a7bc5a652cbedb16bf

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Hardware and Architecture

Citations in the corpus

The JOREK non-linear extended MHD code and applications to large-scale instabilities and their control in magnetically confined fusion plasmas (2020, methodology): “Interfaces to the PaStiX [131], MUMPS [132, 133], and WSMP [134] direct sparse matrix solvers are implemented.”
Phase-field modeling of hydraulic fracture (2016, methodology): “For matrix inversion, a parallel, sparse, direct solver from the MUMPS package for the PETSc library is used to solve the problems that are discussed in the next section([80-83]).”
Analysis of melting behavior of PCMs in a cavity subject to a non-uniform magnetic field using a moving grid technique (2020, methodology): “The heat and fluid equations were coupled using the Newton method, and they were solved simultaneously using a MUltifrontal Massively Parallel Sparse (MUMPS) direct solver [48, 49].”
Fast 3D frequency-domain full-waveform inversion with a parallel block low-rank multifrontal direct solver: Application to OBC data from the North Sea (2016, methodology): “In this study, we solve the linear system resulting from the discretization of the time-harmonic wave equation with the MUMPS multifrontal massively parallel solver (Amestoy et al., 2001, 2006) that performs the LU factorization with a multifrontal method (Duff and Reid, 1983).”
Laminar–turbulent transition induced by a discrete roughness element in a supersonic boundary layer (2013, methodology): “…discretizing the two-dimensional PDE of the PSE3D equations (2.12) and the spatial BiGlobal analysis GEVP (2.15), with leading dimension O(104–105), is performed using the parallelizable sparse matrix linear algebra package MUMPS (Amestoy et al. 2001, 2006) and the SPARSKIT2 library (Saad 1994).”
New development in freefem++ (2012, background): “• A large variety of linear direct and iterative solvers (LU, Cholesky, Crout, CG, GMRES, UMFPACK [13], MUMPS [2], SuperLU, ...) and eigenvalue and eigenvector solvers (ARPARK) [24],and Optimatiztion tools like Ipopt [33] • Near optimal execution speed (compared with compiled C++ implementations pro”
Discontinuous Galerkin finite element approximation of quasilinear elliptic boundary value problems II: Strongly monotone quasi-Newtonian flows (2013, positive): “The resulting system of nonlinear equations is solved based on employing a damped Newton method; for each inner (linear) iteration, we employ the Multifrontal Massively Parallel Solver (MUMPS), see [1, 2, 3].”
Continental scale, high order, high spatial resolution, ice sheet modeling using the Ice Sheet System Model (ISSM) (2012, methodology): “As an alternative, ISSM uses the Multifrontal Massively Parallel Sparse direct solver (MUMPS) [Amestoy et al., 2001, 2006].”