Tobias Meyer Andersen 4b0dd54f15 Add CUDA implementation of the DILU ...

preconditioner. Uses graph coloring to exploit
parallelism in upper and triangular solves when
computing a diagonal approximate inverse of a
sparse matrix. Supports blocksizes up to 3.

2024-01-25 14:26:38 +01:00

..

detail

Add CUDA implementation of the DILU

2024-01-25 14:26:38 +01:00

CuBlockPreconditioner.hpp

Expose CuISTL solver in FlexibleSolver.

2023-05-31 15:03:31 +02:00

CuDILU.cpp

Add CUDA implementation of the DILU

2024-01-25 14:26:38 +01:00

CuDILU.hpp

Add CUDA implementation of the DILU

2024-01-25 14:26:38 +01:00

CuJac.cpp

Add CUDA implementation of the DILU

2024-01-25 14:26:38 +01:00

CuJac.hpp

Combine new diagonalMV kernels into one using

2023-10-16 09:53:02 +02:00

CuOwnerOverlapCopy.hpp

Expose CuISTL solver in FlexibleSolver.

2023-05-31 15:03:31 +02:00

CuSeqILU0.cpp

Fixed typo in error message.

2023-05-31 14:03:59 +02:00

CuSeqILU0.hpp

Typo in variable name.

2023-05-31 13:14:37 +02:00

CuSparseMatrix.cpp

Renamed types.

2023-05-30 10:30:55 +02:00

CuSparseMatrix.hpp

Renamed types.

2023-05-30 10:30:55 +02:00

CuVector.cpp

Added test of size for copyToHost.

2023-05-30 10:03:54 +02:00

CuVector.hpp

Update test properties of new tests using CUDA. Avoid comparison causing new warning

2023-10-16 11:31:00 +02:00

PreconditionerAdapter.hpp

Simplify and optimize the Jacobi preconditioner

2023-10-13 10:31:17 +02:00

PreconditionerConvertFieldTypeAdapter.hpp

Documentation fixes.

2023-05-31 13:13:48 +02:00

PreconditionerHolder.hpp

Expose CuISTL solver in FlexibleSolver.

2023-05-31 15:03:31 +02:00

set_device.cpp

Removed call to deprecated cudaThreadExit

2023-10-09 10:49:31 +02:00

set_device.hpp

Setting CUDA device for MPI runs.

2023-05-31 21:47:46 +02:00

SolverAdapter.hpp

SolverAdapter now takes a reference to scalar product.

2023-05-31 16:39:45 +02:00