hypre
hypre copied to clipboard
hypre-space
Parallel solvers for sparse linear systems featuring multigrid methods.
This is part of a series of PRs for enabling BoomerAMG to be applied to multivectors. Changes in this PR: 1. Extends hypre's SpMV on GPUs to work with multivectors....
The main computational loop nest under "hypre_CSRBlockMatrixMatvecT( )" within csr_block_matvec.c has been manually parallelized. I am struggling to understand how the outermost i-loop is parallelizable. Array "A_j[ ]" has repeating...
This PR fixes the compiler warnings (GPU build): ``` ./csr_spgemm_device_symbl.h: In instantiation of ‘HYPRE_Int hypre_spgemm_symbolic_rownnz(HYPRE_Int, HYPRE_Int*, HYPRE_Int, HYPRE_Int, bool, HYPRE_Int*, HYPRE_Int*, HYPRE_Int*, HYPRE_Int*, HYPRE_Int*, bool, char*) [with int BIN =...
Why is hypre_ForceSyncComputeStream necessary when using GPU-aware MPI? Alternatively, why isn't hypre_SyncComputeStream sufficient? -Paul
This is part of a series of PRs for enabling BoomerAMG to be applied to multivectors. Changes in this PR: 1. Extend `hypre_ParCSRCommPkg` with a new member (`num_components`) that allows...
Implementation of GMRES, COGMRES GramSchmidt using MassDotpTwo, MassInnerProduct and MassAxpy. This includes the an option to choose classical (CGS) or modified Gram-Schmidt (MGS) in GMRES. There is also a Thrust...
The ParCSR solvers can solve the linear system with OpenMP off, but failed with OpenMP on. Error code is as follows `hypre error in file "pcg.c", line 709, error code...
Jacobi iterative solver for ILU smoother/preconditioner implemented on CPU/GPU currently for Nvidia only since we don't have AMD ILU factorization yet. This will occur in the next PR. This works...
Metadata
Owner
Metadata
Parallel solvers for sparse linear systems featuring multigrid methods.