SoftwareX · 2021 · 14 citations · 14 references
ComputingComputer EngineeringComputer ScienceGrid ComputingParallel AlgorithmsParallel ComputingIterative SolversMatrix ComputationNumerical Linear AlgebraParallel ArchitecturesParallel Numerical MethodsParallel Programming ModelsCommunication PrimitivesData SegmentationHybrid Parallel ProgrammingParallel Linear System SolversParallel SolversParallel Sparse Linear AlgebraShared Memory ProgrammingSparse Matrix Computation
This paper presents the XAMG library for solving large sparse systems of linear algebraic equations with multiple right-hand side vectors. The library specializes, but is not limited, to the solution of linear systems obtained from the discretization of elliptic differential equations. A corresponding set of numerical methods includes Krylov subspace, algebraic multigrid, Jacobi, Gauss–Seidel, and Chebyshev iterative methods. The parallelization is implemented with MPI+POSIX shared memory hybrid programming model, which introduces a three-level hierarchical decomposition using the corresponding per-level synchronization and communication primitives. The code contains a number of optimizations, including the multilevel data segmentation, compression of indices, mixed-precision floating-point calculations, vector status flags, and others. The XAMG library uses the program code of the well-known hypre library to construct the multigrid matrix hierarchy. The XAMG’s own implementation for the solve phase of the iterative methods provides up to a twofold speedup compared to hypre for the tests performed. Additionally, XAMG provides extended functionality to solve systems with multiple right-hand side vectors.
14
Samuel Williams, Andrew Waterman, David A. Patterson · Communications of the ACM · 2009 · 2.4K citations · Full text
An overview of the Trilinos project
Michael A. Heroux, Roscoe Bartlett, Vicki E. Howle et al. · ACM Transactions on Mathematical Software · 2005 · 1.1K citations