Andrew Ho
003afb8a4c
Merge branch 'master' into hybridization-gpu-amr
2025-10-28 14:00:27 -07:00
Will Pazner
e4dc9a3941
Small change to indentation style
2025-10-07 16:20:06 -07:00
Will Pazner
8425377bd1
Rename MFEM_REAL_T to MFEM_CUDA_or_HIP_REAL_T
2025-09-09 16:47:35 -07:00
Will Pazner
a402b4e9b2
HostRead in SparseMatrix::BooleanMultTranspose
2025-08-08 10:37:24 -07:00
Will Pazner
7f263221dd
Workaround and unit test for bug CUSPARSE-1897
2025-08-07 15:21:24 -07:00
Will Pazner
09aa9374a9
Use MFEM_REAL_T macro for CUDA/HIP datatype
2025-06-04 20:34:10 -07:00
Will Pazner
78e8cdd7e8
Update SparseMatrix::SortColumnIndices (CUDA or HIP)
...
Use non-deprecated APIs, and unify the CUDA and HIP implementations.
2025-06-04 14:09:20 -07:00
Andrew Ho
04a3fd9bb2
Merge branch 'master' into cusparseXcsrsort
2025-06-02 11:38:00 -07:00
Veselin Dobrev
0a0117d4bc
In SLISolver::Mult, support optimized handling of the case b = 0 by
...
providing empty b (i.e. b.Size() == 0) as the input; this is allowed
only in iterative mode where it makes sense for smoothing operations.
In class OperatorChebyshevSmoother, in the constructor using the
power method to estimate the maximal eigenvalue, add an optional
random seed parameter used to initialize the starting random vector.
Fix a warning in mfem::internal::sqrt for dual numbers.
Fix a doxygen warning in the definition of SparseMatrix::handle.
2025-03-20 19:55:47 -07:00
adam-sim-dev
90f33b1a86
Merge branch 'master' into cusparseXcsrsort
2025-02-19 08:36:21 +08:00
camierjs
bc56be2092
Replace GetIJData with HostReads
2025-02-06 20:21:21 -08:00
adam-sim-dev
449a57d9ad
Merge branch 'master' into cusparseXcsrsort
2025-02-05 09:41:21 +08:00
camierjs
999d6e9e94
Merge branch 'master' into bltp
2025-02-04 12:53:53 -08:00
camierjs
ea041467ae
Address reviewers comments
2025-02-04 10:32:44 -08:00
Tzanio Kolev
e4c2152419
Update Copyright to 2010-2025
2025-02-03 12:17:26 -08:00
camierjs
27c526578d
Use device vectors in solvers
2025-01-29 11:45:24 -08:00
adam-sim-dev and Andrew Ho
a9e5c58897
Correct descrA to matA_descr
...
Co-authored-by: Andrew Ho <ho37@llnl.gov >
2024-10-16 08:21:37 +08:00
adam-sim-dev
d4d149a5ff
Use cusparseXcsrsort instead of the deprecated cusparseXcsru2csr
2024-09-29 14:27:26 +08:00
Stowell, Mark L
ed256ff9a3
Removing special character from suggested Mathematica code
2024-09-05 18:03:27 -07:00
Tzanio Kolev
988439f60a
Merge pull request #4360 from mfem/print-mathematica-dev
...
Adding SparseMatrix::PrintMathematica member function [print-mathematica-dev]
2024-07-09 22:32:46 +01:00
Stowell, Mark L
ef6d80189f
Adding SparseMatrix::PrintMathematica member function
2024-06-14 11:28:35 -07:00
Will Pazner
94ca7d26e8
Check for A.Empty() instead of A == NULL in SparseMatrix
2024-06-13 08:53:05 -07:00
Veselin Dobrev
8876a84dd4
A set of fixes for small bugs uncovered during the more extensive
...
testing of https://github.com/spack/spack/pull/44010 .
2024-06-12 12:06:56 -07:00
Veselin Dobrev
7be646b8ce
Fix the HIP build with single precision.
...
Fix warnings about RAND_MAX when using single precision.
Introduce an inline function `real_t rand_real()` that returns a
random number in the interval [0,1) using rand(). This function
handles better the case of single precision where the expression
`real_t(rand())/(real_t(RAND_MAX)+1)` can return 1.0f due to round-off
when rand() returns a number close to RAND_MAX.
Use `rand_real()` in a few places that before used code similar to
`real_t(rand())/(real_t(RAND_MAX)+1)`.
2024-03-24 10:43:15 -07:00
Veselin Dobrev
1314428770
Fix two 'make test' failures in a CUDA build using HYPRE+CUDA.
2024-03-18 17:53:18 -07:00
Dylan Copeland
046a874cfb
Merge branch 'master' of github.com:mfem/mfem into float
2024-02-06 10:56:41 -08:00
Tzanio Kolev
3dda9a5042
Merge pull request #4078 from mfem/najlkin/misc-bugfix
...
Various minor bug/deficiency fixes
2024-02-03 14:22:35 -08:00
Tzanio Kolev
8ec618739c
Merge branch 'master' into najlkin/sparsemat-print-fix
2024-01-31 13:19:01 -08:00
Tzanio Kolev
87290fbf56
Update Copyright to 2010-2024
2024-01-27 13:06:49 -08:00
Jan Nikl
1a9cf065d9
Adding printing of non-finalized sparse matrices.
2024-01-22 13:38:50 -08:00
Jan Nikl
19d1c7226e
Fixed printing methods of sparse matrices on devices.
2024-01-22 13:38:35 -08:00
Jan Nikl
4c547f52c2
Minor optimization of SparseMatrix::EliminateCol().
2024-01-22 10:16:37 -08:00
Dylan Copeland
7c81683d1b
Introducing MFEM_USE_DOUBLE.
2024-01-02 14:40:33 -08:00
dylan-copeland
9beaa836b0
MFEM_USE_FLOAT -> MFEM_USE_SINGLE
2023-12-19 17:51:19 -08:00
Tzanio Kolev
d983b34924
Renamed ftype -> real_t
2023-12-13 12:51:43 -08:00
Dylan Copeland
c80fdc6f74
Generalized CUDA for float case, so example device runs succeed with a pcuda build.
2023-11-04 19:55:18 -07:00
Dylan Copeland
f106c03dd1
Generalized floating point type. So far, ex1 works for a serial build without lapack.
2023-10-09 14:19:25 -07:00
Veselin Dobrev
397abc4190
Changes to suppress gcc warnings when building with -Og
2023-08-18 02:03:18 -07:00
camierjs
dce372389b
Merge master in forall
2023-03-24 07:52:56 -07:00
Tzanio Kolev
96e00dc815
Updated COPYRIGHT to 2010-2023
2023-03-11 16:58:18 -08:00
Veselin Dobrev
4f0a7d4773
Small updates:
...
* Bugfix in SparseMatrix::SortColumnIndices()
* More general definition of AsConst()
* Fix nvcc warning in miniapps/meshing/reflector.cpp
2023-03-10 23:48:14 -08:00
camierjs
018d5cfb8b
Debugging lambdas in mfem::forall
2023-02-08 15:03:34 -08:00
Tom Stitt
0c42f3751d
fixes "no known conversion from 'int **' to 'void **'" compilation error during hip compilation
2022-11-28 16:49:22 -08:00
Will Pazner
a6830a367a
Merge remote-tracking branch 'origin/master' into yohann/sort+test
2022-11-04 09:55:29 -07:00
Veselin Dobrev
b1dceed4c0
Fix the places for the EnsureMultTranspose calls in class
...
SparseMatrix.
Fix a warning in class KershawTransformation.
2022-10-21 05:34:37 -07:00
Veselin Dobrev
1482864193
Remove the need to explicitly call EnsureMultTranspose in the
...
classes SparseMatrix and HypreParMatrix.
Added new methood HypreParMatrix::ResetTranspose.
Added some crarifying doxygen documentation.
2022-10-20 16:03:23 -07:00
Will Pazner
62eda9466d
Merge pull request #3127 from mfem/yohann/check-diag-poplicy
...
Check for consistent diagonal policy in `FABilinearFormExtension::EliminateBC`
2022-09-09 09:55:01 -07:00
Yohann Dudouit
c4f5897b20
Use Cu/Hip allocations to avoid int overflow with Memory interface.
2022-09-01 10:29:36 -07:00
Yohann Dudouit
5a18775378
Merge branch 'yohann/sort+test' of https://github.com/mfem/mfem into yohann/sort+test
2022-08-31 17:21:07 -07:00
Yohann Dudouit
f1a2fc2295
Factor out isSorted.
2022-08-31 17:21:03 -07:00
Andrew Ho