Vladimir Z Tomov
e2a382dca4
Moved DGMassInverse::DGMassCGIteration to hpp. Removed specializations (done in remhos).
2026-01-06 17:26:29 -08:00
Vladimir Z Tomov
d26be8cbca
Kernels needed for the Remhos gpu tests.
...
Function to setup mesh partitioning.
2025-12-23 15:27:09 -08:00
Will Pazner
aac94d0f67
Add error message
2025-04-21 16:19:35 -07:00
Will Pazner
2204bc003f
Supress Doxygen warnings
2025-04-19 13:58:27 -07:00
Will Pazner
eec41dd6c0
Use kernel dispatch in DGMassInverse
2025-04-19 12:16:36 -07:00
Will Pazner
56ae55580c
Const correctness in DGMassInverse
2025-04-19 10:52:19 -07:00
Will Pazner
7e3b442102
Use unique_ptr in DGMassInverse
2025-04-17 16:30:55 -07:00
Will Pazner
081635ffd3
Support 1D in DGMassInverse
2025-04-17 16:26:57 -07:00
Tzanio Kolev
e4c2152419
Update Copyright to 2010-2025
2025-02-03 12:17:26 -08:00
Will Pazner
1241960dc4
Merge remote-tracking branch 'origin/master' into pa-empty-partitions
...
# Conflicts:
# fem/gridfunc.cpp
2024-06-24 10:16:56 -07:00
Ido Akkerman
91a0179a18
Update dgmassinv.cpp
...
Modify L140 as well
2024-05-14 14:01:46 +02:00
IdoAkkerman
56978781f5
Use int instead or real_t for iter_max
2024-04-24 12:47:19 +02:00
Will Pazner
ef9043a122
Replace many instances of GetFE(0) with GetTypicalFE()
...
Also replace many instances of GetElementTransformation(0) with
GetTypicalElementTransformation() and instances of GetElementGeometry(0) with
GetTypicalElementGeometry().
Remove some "early returns" in PA code with empty partitions. The reasoning is
that the early returns create divergent code paths among different MPI ranks,
which can cause deadlocks if e.g. collectives are used in code paths on not all
ranks.
2024-04-23 14:45:30 -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
87290fbf56
Update Copyright to 2010-2024
2024-01-27 13:06:49 -08:00
Tzanio Kolev
d983b34924
Renamed ftype -> real_t
2023-12-13 12:51:43 -08:00
Dylan Copeland
a8c34e351e
Reverted to fmin and fmax for GPU kernels. Fixed some examples for pcuda build.
2023-11-10 21:30:07 -08:00
Dylan Copeland
ee3a46af24
Added support for LAPACK in single-precision. Changed fmax -> std::max, etc.
2023-10-31 14:30:44 -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
Will Pazner
9529062888
Remove unused template parameters
2023-09-26 09:28:08 -07:00
Will Pazner
9f4bf49945
Merge remote-tracking branch 'origin/master' into max-q1d-d1d-cpu
...
# Conflicts:
# fem/bilininteg_hcurl.cpp
# fem/bilininteg_mass_pa.cpp
# fem/bilininteg_vectorfe.cpp
# fem/integ/bilininteg_hdiv_kernels.cpp
# fem/integ/bilininteg_vecdiffusion_pa.cpp
# fem/integ/bilininteg_vecmass_pa.cpp
2023-06-28 12:08:47 -07:00
Will Pazner
7c4986546b
Introduce DofQuadLimits struct
...
In kernel code, DeviceDofQuadLimits will give the relevant limits depending on
whether execution is on CUDA/HIP GPU or CPU.
In host code, DeviceDofQuadLimits::Get() will return the limits according to the
backend configuration of the Device object
2023-06-28 11:48:11 -07:00
Sebastian Grimberg
2392f3e8e1
Merge branch 'master' into sjg/integs-reorg-dev
2023-04-20 09:36:26 -07:00
Sebastian Grimberg
cb962cf1db
Minor refactor for common kernel
2023-04-10 16:35:03 -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
camierjs
5f6fd83301
Adjust extended lambdas comment and style
2023-02-17 10:40:48 -08:00
camierjs
018d5cfb8b
Debugging lambdas in mfem::forall
2023-02-08 15:03:34 -08:00
Will Pazner
5352a2d910
Move host device kernel functions into internal namespace
2022-08-23 12:44:50 -07:00
Will Pazner
caff2c1ce3
Add DGMassInverse::Update
2022-08-18 15:03:28 -07:00
Will Pazner
b4a8e6218d
Comments and clean up
2022-08-01 12:03:48 -07:00
Will Pazner
1233966f72
Fix some warnings in DGMassInverse
2022-08-01 10:47:16 -07:00
Will Pazner
94eac27cbf
Add local CG iteration for DG mass on device
2022-08-01 10:16:35 -07:00
Vladimir Z Tomov